Article(id=1225386831118778724, tenantId=1146029695717560320, journalId=1146031591421210625, issueId=1225386825246748695, articleNumber=null, orderNo=null, doi=10.3981/j.issn.1000-7857.2025.12.00014, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1764259200000, receivedDateStr=2025-11-28, revisedDate=1766332800000, revisedDateStr=2025-12-22, acceptedDate=null, acceptedDateStr=null, onlineDate=1770084587125, onlineDateStr=2026-02-03, pubDate=1768233600000, pubDateStr=2026-01-13, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1769616000000, onlineIssueDateStr=2026-01-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1770084587125, creator=system, updateTime=1774080566041, updator=sys-migrate, issue=Issue{id=1225386825246748695, tenantId=1146029695717560320, journalId=1146031591421210625, year='2026', volume='44', issue='1', pageStart='1', pageEnd='140', issueExtLink='null', onlineDate='null', pubDate='1768233600000', pubDateStr='2026-01-13', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1770084585703, creator='system', updateTime=1774331268156, updator='13041195026', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1243198702408544966, tenantId=1146029695717560320, journalId=1146031591421210625, issueId=1225386825246748695, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1243198702408544967, tenantId=1146029695717560320, journalId=1146031591421210625, issueId=1225386825246748695, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=78, endPage=90, ext={EN=ArticleExt(id=1225386833324982709, articleId=1225386831118778724, tenantId=1146029695717560320, journalId=1146031591421210625, language=EN, title=A review of research hotspots in affective intelligence for 2025, columnId=1150494642224591153, journalTitle=Science & Technology Review, columnName=Exclusive, runingTitle=null, highlight=null, articleAbstract=

Emotional Intelligence (EI) refers to an individual's ability to recognize, comprehend, regulate, and apply emotional information. In recent years, with the rapid advancement of affective computing technologies, emotion−enabled health monitoring and intervention have evolved into one of the core issues in the field of public health. This article systematically reviews research progress in key areas—including multimodal emotion recognition, psychological frameworks based on large models, digital emotion regulation interventions, and AI virtual agents—along with their specialized applications in mental health. Furthermore, it discusses current challenges. Specific challenges include: group differences and recognition accuracy issues, ethical and efficacy concerns in AI−based psychological interventions, and emotional data privacy and governance challenges. Future directions are proposed, such as advancing multimodal emotional reasoning and planning, promoting standardized diagnosis and treatment alongside personalized in−home support, and establishing an ethical framework centered on data governance and regulation.

, authors=null, authorsList=Xue TAO, Jiawen DENG, Fuji REN, authorCompany=null, correspAuthors=Fuji REN, authorNote=null, correspAuthorsNote=null, copyrightStatement=All rights reserved. Unauthorized reproduction is prohibited., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1225386836604928534, articleId=1225386831118778724, tenantId=1146029695717560320, journalId=1146031591421210625, language=CN, title=2025年情感智能研究热点回眸, columnId=1150494642375586098, journalTitle=科技导报, columnName=特色专题, runingTitle=null, highlight=null, articleAbstract=

情感智能(emotional intelligence,EI)指个体识别、理解、调节与应用情感信息的能力。随着情感计算技术的迅猛发展,基于其情感健康监测与干预已成为公共健康领域的核心议题之一。从多模态情感识别、大模型心理架构、数字化情感调节干预及AI虚拟代理等关键层面,系统回顾了该领域的研究进展及其在心理健康中的垂直应用。此外,从基于多模态情感的理解与规划技术、AI干预伦理、数据隐私与情感数据等方面讨论了面临的挑战,具体包括:群体差异与识别准确性挑战、AI心理干预的伦理与效力挑战、情绪数据隐私与治理挑战。提出了基于多模态情感推理与规划,推动标准化诊疗与家庭个性化支持,构建以数据治理与监管为核心的伦理框架等未来发展方向。

, authors=

陶雪,博士研究生,研究方向为情感分析、大模型技术等,电子信箱:

, authorsList=陶雪, 邓佳文, 任福继, authorCompany=null, correspAuthors=任福继, authorNote=null, correspAuthorsNote=
任福继(通信作者),教授,日本工程院院士、欧盟科学院院士、俄罗斯工程院外籍院士,研究方向为先进智能、情感计算、智能机器人等,电子信箱:
, copyrightStatement=版权所有,未经授权,不得转载。, copyrightOwner=《科技导报》编辑部, extLink=null, articleAbsUrl=null, sourceXml=ur5HhJ/K+o3ttzbZtlzQeg==, magXml=ur5HhJ/K+o3ttzbZtlzQeg==, pdfUrl=null, pdf=UKRuC3R25z3QJI9fb90aMQ==, pdfFileSize=1296468, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=Rn+0mI2cZdIrgNnks0WmYg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=3bKHUTaVgwAYvilN5RyU6w==, mapNumber=null, fund=null)}, authors=[Author(id=1242147204815729070, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=taoxue202511@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1242147204882837936, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, authorId=1242147204815729070, language=EN, stringName=Xue TAO, firstName=Xue, middleName=null, lastName=TAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1242147204949946801, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, authorId=1242147204815729070, language=CN, stringName=陶雪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1电子科技大学计算机科学与工程学院,成都 611731, bio={"content":"

陶雪,博士研究生,研究方向为情感分析、大模型技术等,电子信箱:

"}, bioImg=null, bioContent=

陶雪,博士研究生,研究方向为情感分析、大模型技术等,电子信箱:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1242147204647956903, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, xref=1, ext=[AuthorCompanyExt(id=1242147204652151208, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204647956903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China), AuthorCompanyExt(id=1242147204660539817, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204647956903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1电子科技大学计算机科学与工程学院,成都 611731)])]), Author(id=1242147205017055667, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1242147205088358837, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, authorId=1242147205017055667, language=EN, stringName=Jiawen DENG, firstName=Jiawen, middleName=null, lastName=DENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1242147205155467702, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, authorId=1242147205017055667, language=CN, stringName=邓佳文, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1电子科技大学计算机科学与工程学院,成都 611731, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1242147204647956903, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, xref=1, ext=[AuthorCompanyExt(id=1242147204652151208, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204647956903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China), AuthorCompanyExt(id=1242147204660539817, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204647956903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1电子科技大学计算机科学与工程学院,成都 611731)])]), Author(id=1242147205239353786, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=renfuji@uestc.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1242147206728331714, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, authorId=1242147205239353786, language=EN, stringName=Fuji REN, firstName=Fuji, middleName=null, lastName=REN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
2Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen 518110, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1242147206812217795, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, authorId=1242147205239353786, language=CN, stringName=任福继, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1电子科技大学计算机科学与工程学院,成都 611731
2电子科技大学深圳高等研究院,深圳 518110, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1242147204647956903, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, xref=1, ext=[AuthorCompanyExt(id=1242147204652151208, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204647956903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China), AuthorCompanyExt(id=1242147204660539817, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204647956903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1电子科技大学计算机科学与工程学院,成都 611731)]), AuthorCompany(id=1242147204723454378, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, xref=2, ext=[AuthorCompanyExt(id=1242147204727648683, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204723454378, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen 518110, China), AuthorCompanyExt(id=1242147204736037292, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204723454378, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2电子科技大学深圳高等研究院,深圳 518110)])])], keywords=[Keyword(id=1242147206950629828, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=EN, orderNo=1, keyword=emotional intelligence), Keyword(id=1242147207047098821, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=EN, orderNo=2, keyword=mental health), Keyword(id=1242147207101624774, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=EN, orderNo=3, keyword=affective computing), Keyword(id=1242147207160345031, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=EN, orderNo=4, keyword=emotion reasoning), Keyword(id=1242147207231648200, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=EN, orderNo=5, keyword=large language models), Keyword(id=1242147207302951369, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=CN, orderNo=1, keyword=情感智能), Keyword(id=1242147207365865930, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=CN, orderNo=2, keyword=心理健康), Keyword(id=1242147207424586187, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=CN, orderNo=3, keyword=情感计算), Keyword(id=1242147207491695052, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=CN, orderNo=4, keyword=情感推理), Keyword(id=1242147207554609613, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=CN, orderNo=5, keyword=大模型)], refs=[Reference(id=1242147209454629354, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=1990, volume=9, issue=3, pageStart=185, pageEnd=211, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Salovey P, Mayer J D, journalName=Imagination, Cognition and Personality, refType=null, unstructuredReference=Salovey P, Mayer J D. Emotional intelligence[J]. Imagination, Cognition and Personality, 1990, 9(3): 185-211., articleTitle=Emotional intelligence, refAbstract=null), Reference(id=1242147209521738219, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2005, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Goleman D, journalName=Emotional intelligence: Why it can matter more than IQ, refType=null, unstructuredReference= Goleman D. Emotional intelligence: Why it can matter more than IQ[M]. New York: Bantam, 2005., articleTitle=null, refAbstract=null), Reference(id=1242147209588847084, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2018, volume=360, issue=6388, pageStart=496, pageEnd=498, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=Marelli L, Testa G, journalName=Science, refType=null, unstructuredReference=Marelli L, Testa G. Scrutinizing the EU general data protection regulation[J]. Science, 2018, 360(6388): 496-498., articleTitle=Scrutinizing the EU general data protection regulation, refAbstract=null), Reference(id=1242147209655955949, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2025, volume=43, issue=1, pageStart=132, pageEnd=142, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=谷雨, 任福继, journalName=科技导报, refType=null, unstructuredReference=谷雨, 任福继. 2024年人机情感交互领域热点回眸[J]. 科技导报, 2025, 43(1): 132-142., articleTitle=2024年人机情感交互领域热点回眸, refAbstract=null), Reference(id=1242147209723064814, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2020, volume=46, issue=5, pageStart=1, pageEnd=11, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=何俊, 张彩庆, 李小珍, journalName=计算机工程, refType=null, unstructuredReference=何俊, 张彩庆, 李小珍, . 面向深度学习的多模态融合技术研究综述[J]. 计算机工程, 2020, 46(5): 1-11., articleTitle=面向深度学习的多模态融合技术研究综述, refAbstract=null), Reference(id=1242147211216237040, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2025, volume=16, issue=3, pageStart=1855, pageEnd=1872, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=Wang Y W, Lin Z L, Yang C R, journalName=IEEE Transactions on Affective Computing, refType=null, unstructuredReference=Wang Y W, Lin Z L, Yang C R, et al. Automatic depression recognition with an ensemble of multimodal spatio−temporal routing features[J]. IEEE Transactions on Affective Computing, 2025, 16(3): 1855-1872., articleTitle=Automatic depression recognition with an ensemble of multimodal spatio−temporal routing features, refAbstract=null), Reference(id=1242147211287540209, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=10.1109/taffc.2025.3628664, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=Lu J X, Shang Y Y, Shao Z H, journalName=IEEE Transactions on Affective Computing, refType=null, unstructuredReference=Lu J X, Shang Y Y, Shao Z H, et al. DSTC: A multimodal network for depression emotion recognition and sentiment analyses[J]. IEEE Transactions on Affective Computing, 2025,, articleTitle=DSTC: A multimodal network for depression emotion recognition and sentiment analyses, refAbstract=null), Reference(id=1242147211350454770, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2024, volume=10, issue=null, pageStart=e53961, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=Holderried F, Stegemann−Philipps C, Herschbach L, journalName=JMIR Medical Education, refType=null, unstructuredReference=Holderried F, Stegemann−Philipps C, Herschbach L, et al. A generative pretrained transformer (GPT)−powered chatbot as a simulated patient to practice history taking: Prospective, mixed methods study[J]. JMIR Medical Education, 2024, 10: e53961., articleTitle=A generative pretrained transformer (GPT)−powered chatbot as a simulated patient to practice history taking: Prospective, mixed methods study, refAbstract=null), Reference(id=1242147211409175027, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2025, volume=41, issue=7, pageStart=3957, pageEnd=3973, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=Mármol−Romero A M, García−Vega M, García−Cumbreras M, journalName=International Journal of Human–Computer Interaction, refType=null, unstructuredReference=Mármol−Romero A M, García−Vega M, García−Cumbreras M, et al. An empathic GPT−based chatbot to talk about mental disorders with Spanish teenagers[J]. International Journal of Human–Computer Interaction, 2025, 41(7): 3957-3973., articleTitle=An empathic GPT−based chatbot to talk about mental disorders with Spanish teenagers, refAbstract=null), Reference(id=1242147211480478196, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2024, volume=49, issue=9, pageStart=1412, pageEnd=1416, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=Perlis R H, Goldberg J F, Ostacher M J, journalName=Neuropsychopharmacology, refType=null, unstructuredReference=Perlis R H, Goldberg J F, Ostacher M J, et al. Clinical decision support for bipolar depression using large language models[J]. Neuropsychopharmacology, 2024, 49(9): 1412-1416., articleTitle=Clinical decision support for bipolar depression using large language models, refAbstract=null), Reference(id=1242147211547587062, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2024, volume=11, issue=null, pageStart=e58129, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=Lee C, Mohebbi M, O’Callaghan E, journalName=JMIR Mental Health, refType=null, unstructuredReference=Lee C, Mohebbi M, O’Callaghan E, et al. Large language models versus expert clinicians in crisis prediction among telemental health patients: Comparative study[J]. JMIR Mental Health, 2024, 11: e58129., articleTitle=Large language models versus expert clinicians in crisis prediction among telemental health patients: Comparative study, refAbstract=null), Reference(id=1242147211614695927, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Galatzer−Levy I R, McDuff D, Natarajan V, et al. The capability of large language models to measure psychiatric functioning[J]. arXiv, 2023: preprint arXiv: 2308.01834., articleTitle=null, refAbstract=null), Reference(id=1242147211665027576, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2025, volume=8, issue=1, pageStart=580, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=Kim J, Ma S P, Chen M L, journalName=npj Digital Medicine, refType=null, unstructuredReference=Kim J, Ma S P, Chen M L, et al. Optimizing large language models for detecting symptoms of depression/anxiety in chronic diseases patient communications[J]. npj Digital Medicine, 2025, 8(1): 580., articleTitle=Optimizing large language models for detecting symptoms of depression/anxiety in chronic diseases patient communications, refAbstract=null), Reference(id=1242147211744719354, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2024, volume=11, issue=1, pageStart=896, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=Tong S, Mao K, Huang Z, journalName=Humanities and Social Sciences Communications, refType=null, unstructuredReference=Tong S, Mao K, Huang Z, et al. Automating psychological hypothesis generation with AI: When large language models meet causal graph[J]. Humanities and Social Sciences Communications, 2024, 11(1): 896., articleTitle=Automating psychological hypothesis generation with AI: When large language models meet causal graph, refAbstract=null), Reference(id=1242147211824411131, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Meng H, Zhang R W, Wang G Y, et al. Deconstructing depression stigma: Integrating AI−driven data collection and analysis with causal knowledge graphs[C]//Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems. New York: ACM, 2025: 1−21., articleTitle=null, refAbstract=null), Reference(id=1242147211891519997, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Khattab O, Singhvi A, Maheshwari P, et al. DSPy: Compiling declarative language model calls into state−of−the−art pipelines[C]//International Conference on Learning Representations. Vienna: ICLR, 2024., articleTitle=null, refAbstract=null), Reference(id=1242147211954434558, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2024, volume=23, issue=null, pageStart=16094069241231168, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=16, authorNames=Tai R H, Bentley L R, Xia X, journalName=International Journal of Qualitative Methods, refType=null, unstructuredReference=Tai R H, Bentley L R, Xia X, et al. An examination of the use of large language models to aid analysis of textual data[J]. International Journal of Qualitative Methods, 2024, 23: 16094069241231168., articleTitle=An examination of the use of large language models to aid analysis of textual data, refAbstract=null), Reference(id=1242147212021543423, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Teng S, Liu J, Jain R K, et al. Enhancing depression detection with chain−of−thought prompting: From emotion to reasoning using large language models[J]. arXiv, 2025: preprint arXiv: 2502.05879., articleTitle=null, refAbstract=null), Reference(id=1242147212092846594, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2026, volume=205, issue=null, pageStart=106110, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=18, authorNames=Sazzed S, journalName=International Journal of Medical Informatics, refType=null, unstructuredReference=Sazzed S. Psychosocial challenges and substance use among suicidal autistic individuals on social media: LLM−assisted keyword generation with human−in−the−loop refinement[J]. International Journal of Medical Informatics, 2026, 205: 106110., articleTitle=Psychosocial challenges and substance use among suicidal autistic individuals on social media: LLM−assisted keyword generation with human−in−the−loop refinement, refAbstract=null), Reference(id=1242147212159955459, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2026, volume=298, issue=null, pageStart=129712, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=19, authorNames=Qin S G, Liu M, Wei T Q, journalName=Expert Systems with Applications, refType=null, unstructuredReference=Qin S G, Liu M, Wei T Q, et al. Language proficiency assessment of autistic children using large language models[J]. Expert Systems with Applications, 2026, 298: 129712., articleTitle=Language proficiency assessment of autistic children using large language models, refAbstract=null), Reference(id=1242147212239647238, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2025, volume=16, issue=3, pageStart=2245, pageEnd=2260, url=null, language=null, rfNumber=[21], rfOrder=20, authorNames=Shen L, Zhang H J, Zhu C P, journalName=IEEE Transactions on Affective Computing, refType=null, unstructuredReference=Shen L, Zhang H J, Zhu C P, et al. Enhancing emotion regulation in mental disorder treatment: An AIGC−based closed−loop music intervention system[J]. IEEE Transactions on Affective Computing, 2025, 16(3): 2245-2260., articleTitle=Enhancing emotion regulation in mental disorder treatment: An AIGC−based closed−loop music intervention system, refAbstract=null), Reference(id=1242147212310950408, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2025, volume=12, issue=2, pageStart=890, pageEnd=904, url=null, language=null, rfNumber=[22], rfOrder=21, authorNames=Yao W Y, Chen P C L, Zhang Z Y, journalName=IEEE Transactions on Computational Social Systems, refType=null, unstructuredReference=Yao W Y, Chen P C L, Zhang Z Y, et al. AE−AMT: Attribute−enhanced affective music generation with compound word representation[J]. IEEE Transactions on Computational Social Systems, 2025, 12(2): 890-904., articleTitle=AE−AMT: Attribute−enhanced affective music generation with compound word representation, refAbstract=null), Reference(id=1242147212378059273, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2025, volume=24, issue=2, pageStart=156, pageEnd=174, url=null, language=null, rfNumber=[23], rfOrder=22, authorNames=Torous J, Linardon J, Goldberg S B, journalName=World Psychiatry, refType=null, unstructuredReference=Torous J, Linardon J, Goldberg S B, et al. The evolving field of digital mental health: Current evidence and implementation issues for smartphone apps, generative artificial intelligence, and virtual reality[J]. World Psychiatry, 2025, 24(2): 156-174., articleTitle=The evolving field of digital mental health: Current evidence and implementation issues for smartphone apps, generative artificial intelligence, and virtual reality, refAbstract=null), Reference(id=1242147212432585226, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2016, volume=3, issue=2, pageStart=e16, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=23, authorNames=Torous J, Kiang M V, Lorme J, journalName=JMIR Mental Health, refType=null, unstructuredReference=Torous J, Kiang M V, Lorme J, et al. New tools for new research in psychiatry: A scalable and customizable platform to empower data driven smartphone research[J]. JMIR Mental Health, 2016, 3(2): e16., articleTitle=New tools for new research in psychiatry: A scalable and customizable platform to empower data driven smartphone research, refAbstract=null), Reference(id=1242147212503888396, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2024, volume=12, issue=null, pageStart=e40689, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=24, authorNames=Choi A, Ooi A, Lottridge D, journalName=JMIR mHealth and uHealth, refType=null, unstructuredReference=Choi A, Ooi A, Lottridge D. Digital phenotyping for stress, anxiety, and mild depression: Systematic literature review[J]. JMIR mHealth and uHealth, 2024, 12: e40689., articleTitle=Digital phenotyping for stress, anxiety, and mild depression: Systematic literature review, refAbstract=null), Reference(id=1242147212579385869, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2024, volume=10, issue=15, pageStart=e35472, pageEnd=null, url=null, language=null, rfNumber=[26], rfOrder=25, authorNames=Beames J R, Han J, Shvetcov A, journalName=Heliyon, refType=null, unstructuredReference=Beames J R, Han J, Shvetcov A, et al. Use of smartphone sensor data in detecting and predicting depression and anxiety in young people (12–25 years): A scoping review[J]. Heliyon, 2024, 10(15): e35472., articleTitle=Use of smartphone sensor data in detecting and predicting depression and anxiety in young people (12–25 years): A scoping review, refAbstract=null), Reference(id=1242147212638106126, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2024, volume=161, issue=null, pageStart=108422, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=26, authorNames=dos Santos M P, Heckler W F, Bavaresco R S, journalName=Computers in Human Behavior, refType=null, unstructuredReference=dos Santos M P, Heckler W F, Bavaresco R S, et al. Machine learning applied to digital phenotyping: A systematic literature review and taxonomy[J]. Computers in Human Behavior, 2024, 161: 108422., articleTitle=Machine learning applied to digital phenotyping: A systematic literature review and taxonomy, refAbstract=null), Reference(id=1242147212701020687, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2024, volume=3, issue=null, pageStart=552, pageEnd=567, url=null, language=null, rfNumber=[28], rfOrder=27, authorNames=Bell I H, Pot−Kolder R, Rizzo A, journalName=Nature Reviews Psychology, refType=null, unstructuredReference=Bell I H, Pot−Kolder R, Rizzo A, et al. Advances in the use of virtual reality to treat mental health conditions[J]. Nature Reviews Psychology, 2024, 3: 552-567., articleTitle=Advances in the use of virtual reality to treat mental health conditions, refAbstract=null), Reference(id=1242147212759740944, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2023, volume=81, issue=null, pageStart=101893, pageEnd=null, url=null, language=null, rfNumber=[29], rfOrder=28, authorNames=Schrder D, Wrona K J, Müller F, journalName=Journal of Behavior Therapy and Experimental Psychiatry, refType=null, unstructuredReference=Schrder D, Wrona K J, Müller F, et al. Impact of virtual reality applications in the treatment of anxiety disorders: A systematic review and meta−analysis of randomized−controlled trials[J]. Journal of Behavior Therapy and Experimental Psychiatry, 2023, 81: 101893., articleTitle=Impact of virtual reality applications in the treatment of anxiety disorders: A systematic review and meta−analysis of randomized−controlled trials, refAbstract=null), Reference(id=1242147212822655505, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2023, volume=333, issue=null, pageStart=353, pageEnd=364, url=null, language=null, rfNumber=[30], rfOrder=29, authorNames=Wong K P, Lai C Y Y, Qin J, journalName=Journal of Affective Disorders, refType=null, unstructuredReference=Wong K P, Lai C Y Y, Qin J. Systematic review and meta−analysis of randomised controlled trials for evaluating the effectiveness of virtual reality therapy for social anxiety disorder[J]. Journal of Affective Disorders, 2023, 333: 353-364., articleTitle=Systematic review and meta−analysis of randomised controlled trials for evaluating the effectiveness of virtual reality therapy for social anxiety disorder, refAbstract=null), Reference(id=1242147212889764372, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2022, volume=9, issue=2, pageStart=e28502, pageEnd=null, url=null, language=null, rfNumber=[31], rfOrder=30, authorNames=Schroeder A H, Bogie B J M, Rahman T T, journalName=JMIR Mental Health, refType=null, unstructuredReference=Schroeder A H, Bogie B J M, Rahman T T, et al. Feasibility and efficacy of virtual reality interventions to improve psychosocial functioning in psychosis: Systematic review[J]. JMIR Mental Health, 2022, 9(2): e28502., articleTitle=Feasibility and efficacy of virtual reality interventions to improve psychosocial functioning in psychosis: Systematic review, refAbstract=null), Reference(id=1242147212961067542, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2023, volume=58, issue=7, pageStart=989, pageEnd=1007, url=null, language=null, rfNumber=[32], rfOrder=31, authorNames=Riches S, Jeyarajaguru P, Taylor L, journalName=Social Psychiatry and Psychiatric Epidemiology, refType=null, unstructuredReference=Riches S, Jeyarajaguru P, Taylor L, et al. Virtual reality relaxation for people with mental health conditions: A systematic review[J]. Social Psychiatry and Psychiatric Epidemiology, 2023, 58(7): 989-1007., articleTitle=Virtual reality relaxation for people with mental health conditions: A systematic review, refAbstract=null), Reference(id=1242147213019787801, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2024, volume=2, issue=2, pageStart=100078, pageEnd=null, url=null, language=null, rfNumber=[33], rfOrder=32, authorNames=Vowels L M, Francois−Walcott R R R, Darwiche J, journalName=Computers in Human Behavior: Artificial Humans, refType=null, unstructuredReference=Vowels L M, Francois−Walcott R R R, Darwiche J. AI in relationship counselling: Evaluating ChatGPT’s therapeutic capabilities in providing relationship advice[J]. Computers in Human Behavior: Artificial Humans, 2024, 2(2): 100078., articleTitle=AI in relationship counselling: Evaluating ChatGPT’s therapeutic capabilities in providing relationship advice, refAbstract=null), Reference(id=1242147213074313754, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2025, volume=31, issue=10, pageStart=3394, pageEnd=3403, url=null, language=null, rfNumber=[34], rfOrder=33, authorNames=Khasentino J, Belyaeva A, Liu X, journalName=Nature Medicine, refType=null, unstructuredReference=Khasentino J, Belyaeva A, Liu X, et al. A personal health large language model for sleep and fitness coaching[J]. Nature Medicine, 2025, 31(10): 3394-3403., articleTitle=A personal health large language model for sleep and fitness coaching, refAbstract=null), Reference(id=1242147213145616923, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2024, volume=7, issue=2, pageStart=ooae028, pageEnd=null, url=null, language=null, rfNumber=[35], rfOrder=34, authorNames=Baxter S L, Longhurst C A, Millen M, journalName=JAMIA Open, refType=null, unstructuredReference=Baxter S L, Longhurst C A, Millen M, et al. Generative artificial intelligence responses to patient messages in the electronic health record: Early lessons learned[J]. JAMIA Open, 2024, 7(2): ooae028., articleTitle=Generative artificial intelligence responses to patient messages in the electronic health record: Early lessons learned, refAbstract=null), Reference(id=1242147213200142876, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2024, volume=333, issue=null, pageStart=115724, pageEnd=null, url=null, language=null, rfNumber=[36], rfOrder=35, authorNames=Blease C, Worthen A, Torous J, journalName=Psychiatry Research, refType=null, unstructuredReference=Blease C, Worthen A, Torous J. Psychiatrists’ experiences and opinions of generative artificial intelligence in mental healthcare: An online mixed methods survey[J]. Psychiatry Research, 2024, 333: 115724., articleTitle=Psychiatrists’ experiences and opinions of generative artificial intelligence in mental healthcare: An online mixed methods survey, refAbstract=null), Reference(id=1242147213258863134, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2025, volume=8, issue=1, pageStart=275, pageEnd=null, url=null, language=null, rfNumber=[37], rfOrder=36, authorNames=Chen D, Chauhan K, Parsa R, journalName=npj Digital Medicine, refType=null, unstructuredReference=Chen D, Chauhan K, Parsa R, et al. Patient perceptions of empathy in physician and artificial intelligence chatbot responses to patient questions about cancer[J]. npj Digital Medicine, 2025, 8(1): 275., articleTitle=Patient perceptions of empathy in physician and artificial intelligence chatbot responses to patient questions about cancer, refAbstract=null), Reference(id=1242147213321777695, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[38], rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Hamad O, Shaban K, Hamdi A. Asem: Enhancing empathy in chatbot through attention−based sentiment and emotion modeling[C]//Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation. Torino, Italia: LREC−COLING, 2024: 1588−1601., articleTitle=null, refAbstract=null), Reference(id=1242147213376303648, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[39], rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao P, Han D H, Zhou R, et al. CAB: empathetic dialogue generation with cognition, affection and behavior[M]//Database Systems for Advanced Applications. Cham: Springer Nature Switzerland, 2023: 597−606., articleTitle=null, refAbstract=null), Reference(id=1242147213435023905, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[40], rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Zaranis E, Paraskevopoulos G, Katsamanis A, et al. EmpBot: A T5−based empathetic chatbot focusing on sentiments[J]. arXiv, 2021: preprint arXiv: 2111.00310., articleTitle=null, refAbstract=null), Reference(id=1242147213489549858, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[41], rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao W, Zhao Y, Lu X, et al. Is ChatGPT equipped with emotional dialogue capabilities?[J]. arXiv, 2023: preprint arXiv: 2304.09582., articleTitle=null, refAbstract=null), Reference(id=1242147213552464420, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[42], rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee Y K, Lee I, Shin M, et al. Chain of empathy: Enhancing empathetic response of large language models based on psychotherapy models[J]. arXiv, 2023: preprint arXiv: 2311.04915., articleTitle=null, refAbstract=null), Reference(id=1242147213636350501, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2025, volume=5, issue=10, pageStart=854, pageEnd=862, url=null, language=null, rfNumber=[43], rfOrder=42, authorNames=Zhang R W, Meng H, Neubronner M, journalName=Nature Computational Science, refType=null, unstructuredReference=Zhang R W, Meng H, Neubronner M, et al. Computational and ethical considerations for using large language models in psychotherapy[J]. Nature Computational Science, 2025, 5(10): 854-862., articleTitle=Computational and ethical considerations for using large language models in psychotherapy, refAbstract=null), Reference(id=1242147213720236582, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[44], rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Xie H J, Chen Y R, Xing X F, et al. PsyDT: Using LLMs to construct the digital twin of psychological counselor with personalized counseling style for psychological counseling[C]//Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA, USAACL, 2025: 1081−1115., articleTitle=null, refAbstract=null), Reference(id=1242147213799928363, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[45], rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=De Choudhury M, Pendse S R, Kumar N. Benefits and harms of large language models in digital mental health[J]. arXiv, 2023: preprint arXiv: 2311.14693., articleTitle=null, refAbstract=null), Reference(id=1242147213862842927, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2024, volume=11, issue=null, pageStart=e59479, pageEnd=null, url=null, language=null, rfNumber=[46], rfOrder=45, authorNames=Lawrence H R, Schneider R A, Rubin S B, journalName=JMIR Mental Health, refType=null, unstructuredReference=Lawrence H R, Schneider R A, Rubin S B, et al. The opportunities and risks of large language models in mental health[J]. JMIR Mental Health, 2024, 11: e59479., articleTitle=The opportunities and risks of large language models in mental health, refAbstract=null), Reference(id=1242147213938340403, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[47], rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Sharma M, Tong M, Korbak T, et al. Towards understanding sycophancy in language models[J]. arXiv, 2023: preprint arXiv: 2310.13548., articleTitle=null, refAbstract=null), Reference(id=1242147214022226486, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[48], rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang R W, Li H, Meng H, et al. The dark side of AI companionship: A taxonomy of harmful algorithmic behaviors in human−AI relationships[C]//Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems. New York: ACM, 2025: 1−17., articleTitle=null, refAbstract=null), Reference(id=1242147214085141049, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2023, volume=5, issue=null, pageStart=1133987, pageEnd=null, url=null, language=null, rfNumber=[49], rfOrder=48, authorNames=Sabour S, Zhang W, Xiao X Y, journalName=Frontiers in Digital Health, refType=null, unstructuredReference=Sabour S, Zhang W, Xiao X Y, et al. A chatbot for mental health support: Exploring the impact of Emohaa on reducing mental distress in China[J]. Frontiers in Digital Health, 2023, 5: 1133987., articleTitle=A chatbot for mental health support: Exploring the impact of Emohaa on reducing mental distress in China, refAbstract=null), Reference(id=1242147214156444221, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[50], rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Na H B. CBT−LLM: A Chinese large language model for cognitive behavioral therapy−based mental health question answering[J]. arXiv, 2024: arXiv preprint:2403.16008., articleTitle=null, refAbstract=null), Reference(id=1242147215616062017, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=6, pageStart=4234, pageEnd=4245, url=null, language=null, rfNumber=[51], rfOrder=50, authorNames=Tan X, Chen J W, Liu H H, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=Tan X, Chen J W, Liu H H, et al. NaturalSpeech: End−to−end text−to−speech synthesis with human−level quality[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(6): 4234-4245., articleTitle=NaturalSpeech: End−to−end text−to−speech synthesis with human−level quality, refAbstract=null), Reference(id=1242147215674782278, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[52], rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=van der Struijk S, Huang H H, Mirzaei M S, et al. FACSvatar: An open source modular framework for real−time FACS based facial animation[C]//Proceedings of the 18th International Conference on Intelligent Virtual Agents. New York: ACM, 2018: 159−164., articleTitle=null, refAbstract=null), Reference(id=1242147215741891146, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2021, volume=11, issue=1, pageStart=5242, pageEnd=null, url=null, language=null, rfNumber=[53], rfOrder=52, authorNames=Garg K, Kello C T, journalName=Scientific Reports, refType=null, unstructuredReference=Garg K, Kello C T. Efficient Lévy walks in virtual human foraging[J]. Scientific Reports, 2021, 11(1): 5242., articleTitle=Efficient Lévy walks in virtual human foraging, refAbstract=null), Reference(id=1242147215804805710, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[54], rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=Nayak S, Jain K, Awal R, et al. Benchmarking vision language models for cultural understanding[J]. arXiv, 2024: preprint arXiv: 2407.10920., articleTitle=null, refAbstract=null), Reference(id=1242147215876108881, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[55], rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Li C, Teney D, Wang J D, et al. CulturePark: Boosting cross−cultural understanding in large language models[C]//Proceedings of Advances in Neural Information Processing Systems 37. Vancouver: Neural Information Processing Systems Foundation, Inc. (NeurIPS), 2024: 65183−65216., articleTitle=null, refAbstract=null), Reference(id=1242147215939023443, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2025, volume=127, issue=null, pageStart=202661, pageEnd=null, url=null, language=null, rfNumber=[56], rfOrder=55, authorNames=Ji H, Kim S Y, Kim S Y, journalName=Research in Autism, refType=null, unstructuredReference=Ji H, Kim S Y, Kim S Y. Investigating face exploration patterns and facial emotion recognition abilities in children with autism spectrum disorder (ASD)[J]. Research in Autism, 2025, 127: 202661., articleTitle=Investigating face exploration patterns and facial emotion recognition abilities in children with autism spectrum disorder (ASD), refAbstract=null), Reference(id=1242147216010326615, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2024, volume=3, issue=1, pageStart=12, pageEnd=null, url=null, language=null, rfNumber=[57], rfOrder=56, authorNames=Stade E C, Stirman S W, Ungar L H, journalName=npj Mental Health Research, refType=null, unstructuredReference=Stade E C, Stirman S W, Ungar L H, et al. Large language models could change the future of behavioral healthcare: A proposal for responsible development and evaluation[J]. npj Mental Health Research, 2024, 3(1): 12., articleTitle=Large language models could change the future of behavioral healthcare: A proposal for responsible development and evaluation, refAbstract=null), Reference(id=1242147216085824089, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[58], rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Z, Tang F, Zhao M, et al. EmoCaps: Emotion capsule based model for conversational emotion recognition[J]. arXiv, 2022: preprint arXiv: 2203.13504., articleTitle=null, refAbstract=null), Reference(id=1242147216148738652, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=2023, volume=86, issue=null, pageStart=105312, pageEnd=null, url=null, language=null, rfNumber=[59], rfOrder=58, authorNames=Chen K, Jing H C, Liu Q, journalName=Biomedical Signal Processing and Control, refType=null, unstructuredReference=Chen K, Jing H C, Liu Q, et al. A novel caps−EEGNet combined with channel selection for EEG−based emotion recognition[J]. Biomedical Signal Processing and Control, 2023, 86: 105312., articleTitle=A novel caps−EEGNet combined with channel selection for EEG−based emotion recognition, refAbstract=null), Reference(id=1242147216220041821, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[60], rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=Yan Z H, Wu Y F, Zhang Y, et al. EmoGlass: An end−to−end AI−enabled wearable platform for enhancing self−awareness of emotional health[C]//Proceedings of CHI Conference on Human Factors in Computing Systems. New York: ACM, 2022: 1−19., articleTitle=null, refAbstract=null), Reference(id=1242147216287150687, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[61], rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=Chatila R, Havens J C. The IEEE global initiative on ethics of autonomous and intelligent systems[M]//Robotics and Well−Being. Cham: Springer International Publishing, 2019: 11−16., articleTitle=null, refAbstract=null)], funds=[Fund(id=1242147209056170467, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, awardId=2024YFG0006, language=CN, fundingSource=四川省科技计划项目(2024YFG0006), fundOrder=null, country=null), Fund(id=1242147209119085028, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, awardId=2024NSFTD0042, language=CN, fundingSource=四川省科技计划项目(2024NSFTD0042), fundOrder=null, country=null), Fund(id=1242147209186193893, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, awardId=2024NSFSC0506, language=CN, fundingSource=四川省科技计划项目(2024NSFSC0506), fundOrder=null, country=null), Fund(id=1242147209249108454, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, awardId=2025ZNSFSC1487, language=CN, fundingSource=四川省科技计划项目(2025ZNSFSC1487), fundOrder=null, country=null), Fund(id=1242147209303634408, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, awardId=U24A20250, language=CN, fundingSource=国家自然科学基金项目(U24A20250), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1242147204647956903, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, xref=1, ext=[AuthorCompanyExt(id=1242147204652151208, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204647956903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China), AuthorCompanyExt(id=1242147204660539817, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204647956903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1电子科技大学计算机科学与工程学院,成都 611731)]), AuthorCompany(id=1242147204723454378, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, xref=2, ext=[AuthorCompanyExt(id=1242147204727648683, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204723454378, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen 518110, China), AuthorCompanyExt(id=1242147204736037292, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204723454378, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2电子科技大学深圳高等研究院,深圳 518110)])], figs=[ArticleFig(id=1242147207730770382, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=EN, label=null, caption=null, figureFileSmall=FKAgXLrdzrIfqhVCP6GLQg==, figureFileBig=v6qBlOTWAvBPgmCgvZvZ1g==, tableContent=null), ArticleFig(id=1242147207789490639, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=CN, label=图1, caption=3种多模态融合方法, figureFileSmall=FKAgXLrdzrIfqhVCP6GLQg==, figureFileBig=v6qBlOTWAvBPgmCgvZvZ1g==, tableContent=null), ArticleFig(id=1242147207885959632, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=EN, label=null, caption=null, figureFileSmall=JYql0OK4uMrCNjDoX8+ErA==, figureFileBig=Qe3n+2yJQjMSJUPJAWKosA==, tableContent=null), ArticleFig(id=1242147207953068499, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=CN, label=图2, caption=PH−LLM的架构与性能, figureFileSmall=JYql0OK4uMrCNjDoX8+ErA==, figureFileBig=Qe3n+2yJQjMSJUPJAWKosA==, tableContent=null), ArticleFig(id=1242147208015983060, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=EN, label=null, caption=null, figureFileSmall=Rkj7ElTK0mim9G2m6pH2tw==, figureFileBig=XipJObzjde6E+SHPgCobig==, tableContent=null), ArticleFig(id=1242147208087286229, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=CN, label=图3, caption=大语言模型在心理治疗中的角色框架:基于自主性与情感介入度的划分

图片改编自文献[43]

, figureFileSmall=Rkj7ElTK0mim9G2m6pH2tw==, figureFileBig=XipJObzjde6E+SHPgCobig==, tableContent=null), ArticleFig(id=1242147208162783703, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=EN, label=null, caption=null, figureFileSmall=oILbN3uJEpliKMc4KyInZQ==, figureFileBig=BhIbFZ346lhAVQLCu3Twbg==, tableContent=null), ArticleFig(id=1242147208225698264, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=CN, label=图4, caption=构建数字人的核心技术概览, figureFileSmall=oILbN3uJEpliKMc4KyInZQ==, figureFileBig=BhIbFZ346lhAVQLCu3Twbg==, tableContent=null), ArticleFig(id=1242147208317972953, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=EN, label=null, caption=null, figureFileSmall=VgAgM2iBHghZehpBsmzq6Q==, figureFileBig=Y4H248fTzw//QwZ7wbcZpg==, tableContent=null), ArticleFig(id=1242147208389276122, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=CN, label=图5, caption=LLM的临床能力实例, figureFileSmall=VgAgM2iBHghZehpBsmzq6Q==, figureFileBig=Y4H248fTzw//QwZ7wbcZpg==, tableContent=null), ArticleFig(id=1242147208447996379, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
主要方向 研究热点 研究热点描述
情感智能的
关键技术
多模态情感识别  探讨如何融合面部表情、语音、文本、生理信号等多源数据,以提高情感状态感知的准确性与鲁棒性
情感计算与高级分析  讨论大语言模型等先进AI技术如何赋能更深层的情感理解、分析、推理与生成,为干预提供认知基础
情感调节算法与反馈机制  研究基于AI的实时情感调节模型与个性化反馈技术,以帮助用户管理焦虑、抑郁等情绪问题
情感智能的
关键应用
心理健康支持与个性化干预  探讨如何利用情感智能技术辅助心理治疗,提供动态的情感支持、状态分析与个性化干预建议
情感障碍的早期监测与预警  开发基于情感计算的早期预警系统,用于监测焦虑、抑郁等障碍的风险,并实现干预策略的动态调整
情感交互与虚拟心理治疗  探索虚拟心理治疗师等应用,通过高拟真度的情感理解与反馈,提供实时支持,特别是在资源有限的环境中
情感智能的
发展挑战
公平性与偏差治理  应对情感计算中的跨文化、跨语言及跨群体差异问题,提升技术在全球范围内的普适性、公平性与针对性
数据隐私与安全伦理  探讨情感数据在采集、存储、使用全流程中的隐私保护、安全合规与特殊伦理挑战(如情感操纵风险)
可解释性与系统信任  提升情感智能系统的决策透明度,确保其情感分析与干预建议可被理解与验证,以建立用户信任并防止误导
), ArticleFig(id=1242147208506716636, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=CN, label=表1, caption=

2025年情感智能在心理健康领域的主要研究热点

, figureFileSmall=null, figureFileBig=null, tableContent=
主要方向 研究热点 研究热点描述
情感智能的
关键技术
多模态情感识别  探讨如何融合面部表情、语音、文本、生理信号等多源数据,以提高情感状态感知的准确性与鲁棒性
情感计算与高级分析  讨论大语言模型等先进AI技术如何赋能更深层的情感理解、分析、推理与生成,为干预提供认知基础
情感调节算法与反馈机制  研究基于AI的实时情感调节模型与个性化反馈技术,以帮助用户管理焦虑、抑郁等情绪问题
情感智能的
关键应用
心理健康支持与个性化干预  探讨如何利用情感智能技术辅助心理治疗,提供动态的情感支持、状态分析与个性化干预建议
情感障碍的早期监测与预警  开发基于情感计算的早期预警系统,用于监测焦虑、抑郁等障碍的风险,并实现干预策略的动态调整
情感交互与虚拟心理治疗  探索虚拟心理治疗师等应用,通过高拟真度的情感理解与反馈,提供实时支持,特别是在资源有限的环境中
情感智能的
发展挑战
公平性与偏差治理  应对情感计算中的跨文化、跨语言及跨群体差异问题,提升技术在全球范围内的普适性、公平性与针对性
数据隐私与安全伦理  探讨情感数据在采集、存储、使用全流程中的隐私保护、安全合规与特殊伦理挑战(如情感操纵风险)
可解释性与系统信任  提升情感智能系统的决策透明度,确保其情感分析与干预建议可被理解与验证,以建立用户信任并防止误导
), ArticleFig(id=1242147208636740061, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
类别 模态名称 模态获取方式 模态特征
生理信息 EEG  通过电极贴附在头皮上记录大脑电活动  脑波频率、振幅、节律等,反映情感激活程度和变化
ECG  使用电极监测心脏电活动  心率、心率变异性、心脏节律变化,情感激动与压力相关
PPG  通过光学传感器测量血管内血流量变化  心率、血压、血氧饱和度等,反映情感应激和生理反应
DEA  通过皮肤电传感器监测皮肤的电导率变化  皮肤电反应、皮肤电活动,反映情感波动、紧张或焦虑状态
视觉信息 面部表情  利用静态图像或视频摄像头捕捉面部动作  微表情(如微笑、皱眉)、嘴巴和眼部动作,反映情感状态(如愉悦、愤怒等)
眼部运动  通过视频摄像头分析瞳孔的变化  瞳孔放大或收缩,反映情感紧张、兴奋、焦虑等
语音信号 语音情感  使用语音传感器、麦克风采集用户语音  语速、音调、音量、语音情感(如愉悦、愤怒、悲伤等)
文本信息 文本情感  使用自然语言处理(NLP)技术分析用户输入文本  词汇选择、情感词、句子情感色彩(如积极、消极、愤怒等)
行为信息 姿态识别  使用动作捕捉设备(如摄像头或传感器)监测肢体动作  肢体运动、姿势、手势、站立或坐姿变化,反映情感状态的变化
), ArticleFig(id=1242147208695460318, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=CN, label=表2, caption=

情感识别常见模态信息

, figureFileSmall=null, figureFileBig=null, tableContent=
类别 模态名称 模态获取方式 模态特征
生理信息 EEG  通过电极贴附在头皮上记录大脑电活动  脑波频率、振幅、节律等,反映情感激活程度和变化
ECG  使用电极监测心脏电活动  心率、心率变异性、心脏节律变化,情感激动与压力相关
PPG  通过光学传感器测量血管内血流量变化  心率、血压、血氧饱和度等,反映情感应激和生理反应
DEA  通过皮肤电传感器监测皮肤的电导率变化  皮肤电反应、皮肤电活动,反映情感波动、紧张或焦虑状态
视觉信息 面部表情  利用静态图像或视频摄像头捕捉面部动作  微表情(如微笑、皱眉)、嘴巴和眼部动作,反映情感状态(如愉悦、愤怒等)
眼部运动  通过视频摄像头分析瞳孔的变化  瞳孔放大或收缩,反映情感紧张、兴奋、焦虑等
语音信号 语音情感  使用语音传感器、麦克风采集用户语音  语速、音调、音量、语音情感(如愉悦、愤怒、悲伤等)
文本信息 文本情感  使用自然语言处理(NLP)技术分析用户输入文本  词汇选择、情感词、句子情感色彩(如积极、消极、愤怒等)
行为信息 姿态识别  使用动作捕捉设备(如摄像头或传感器)监测肢体动作  肢体运动、姿势、手势、站立或坐姿变化,反映情感状态的变化
), ArticleFig(id=1242147208800317920, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
产品/系统名称 具体描述 适用场景
Woebot  AI聊天器+CBT,支持情感识别、情感互动,提供心理健康支持  适合个人情感支持、自我干预
Replika  AI伴侣,通过自然对话提供情感支持,增强社交与心理健康  适合孤独、情感支持需求者
Moodpath  结合情感分析与心理测评,帮助用户追踪与识别情感变化,评估心理健康状态  心理健康自我监测,情感评估
IBM Watson (Emotion
Analysis, Tone Analyzer)
 提供情感分析API,支持文本、语音中的情感分析与识别  企业级情感分析,客户服务
Kairos  情感分析工具,提供多种API/SDK用于情感识别、语音分析等功能  企业或开发者用在情感识别应用中
Youper  结合情感智能与认知行为疗法,进行情感追踪和自我调节  用户情感管理、情感日志记录与分析
Wysa  以AI为基础,结合CBT与情感识别,提供全天候心理健康支持与情感陪伴  面向个人、企业或团体的心理健康平台
Talkspace(AI支持版)  结合AI与人类治疗师,AI用于风险评估、个性化互动,帮助提升治疗效率  适合寻求专业治疗支持的用户
Headspace/Ginger
(合并后)
 提供情感陪伴、冥想、呼吸训练等自我调节工具,结合AI引导情感练习  适合企业、员工福利、日常健康管理
聆心智能  AI情感分析与心理支持,推出心理测评系统、心理课与心育空间  面向校园,提供学生心理健康支持
西湖心辰“聊会小天”  AI心理情感陪伴机器人,提供情感陪伴与互动对话  适合一般公众、情感陪伴需求者
正岸健康数字疗法平台  结合AI与数字疗法,提供慢性失眠等精神心理健康干预工具  精神健康干预、数字疗法
心大陆多智能体AI心理
机器人系统
 通过多模态数据(语音、文字、视频)进行心理测评与干预  校园、学生心理测评与疏导
科大讯飞“AI心理伙伴/
减压星球”
 利用大模型+多模态情感识别能力来识别青少年情感状态,提供共情引导与心理支持  校园心理健康支持,特别面向中小学学生
), ArticleFig(id=1242147208884204002, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, language=CN, label=表3, caption=

情感智能在心理健康领域的应用

, figureFileSmall=null, figureFileBig=null, tableContent=
产品/系统名称 具体描述 适用场景
Woebot  AI聊天器+CBT,支持情感识别、情感互动,提供心理健康支持  适合个人情感支持、自我干预
Replika  AI伴侣,通过自然对话提供情感支持,增强社交与心理健康  适合孤独、情感支持需求者
Moodpath  结合情感分析与心理测评,帮助用户追踪与识别情感变化,评估心理健康状态  心理健康自我监测,情感评估
IBM Watson (Emotion
Analysis, Tone Analyzer)
 提供情感分析API,支持文本、语音中的情感分析与识别  企业级情感分析,客户服务
Kairos  情感分析工具,提供多种API/SDK用于情感识别、语音分析等功能  企业或开发者用在情感识别应用中
Youper  结合情感智能与认知行为疗法,进行情感追踪和自我调节  用户情感管理、情感日志记录与分析
Wysa  以AI为基础,结合CBT与情感识别,提供全天候心理健康支持与情感陪伴  面向个人、企业或团体的心理健康平台
Talkspace(AI支持版)  结合AI与人类治疗师,AI用于风险评估、个性化互动,帮助提升治疗效率  适合寻求专业治疗支持的用户
Headspace/Ginger
(合并后)
 提供情感陪伴、冥想、呼吸训练等自我调节工具,结合AI引导情感练习  适合企业、员工福利、日常健康管理
聆心智能  AI情感分析与心理支持,推出心理测评系统、心理课与心育空间  面向校园,提供学生心理健康支持
西湖心辰“聊会小天”  AI心理情感陪伴机器人,提供情感陪伴与互动对话  适合一般公众、情感陪伴需求者
正岸健康数字疗法平台  结合AI与数字疗法,提供慢性失眠等精神心理健康干预工具  精神健康干预、数字疗法
心大陆多智能体AI心理
机器人系统
 通过多模态数据(语音、文字、视频)进行心理测评与干预  校园、学生心理测评与疏导
科大讯飞“AI心理伙伴/
减压星球”
 利用大模型+多模态情感识别能力来识别青少年情感状态,提供共情引导与心理支持  校园心理健康支持,特别面向中小学学生
)], attaches=null, journal=Journal(id=1125356956822126595, delFlag=0, nameCn=科技导报, nameEn=Science & Technology Review, nameHistory1=null, nameHistory2=null, issn=1000-7857, eissn=, cn=11-1421/N, coden=null, periodic=3, language=CN, oaType=0, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=wfghvu3bhh/dKxuZ+ucVHA==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Rev, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1784015846012, createdBy=null, updatedBy=13041195026, firstLetterCn=K, firstLetterEn=K, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=wfghvu3bhh/dKxuZ+ucVHA==, picEn=yjSfclmpNm7ihn9NbTZ69g==, jcr=null, cjcr=null, exts=[JournalExt(id=1283818766098219763, language=CN, name=科技导报, nameHistory1=null, nameHistory2=null, managedBy=中国科学技术协会, sponsoredBy=中国科学技术协会, publishedBy=科技导报社, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.kjdb.org/CN/home, createdTime=1784015846037, updatedTime=1784015846037, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=http://www.kjdb.org/CN/column/column7.shtml, submissionAuthorUrl=https://kjdbauthor.cast.org.cn/webm, submissionEditorUrl=https://kjdbeditor.cast.org.cn/webm/, submissionReviewUrl=https://kjdbauthor.cast.org.cn/webm, submissionCeEditorUrl=https://kjdbeditor.cast.org.cn/webm/, submissionAeEditorUrl=https://kjdbeditor.cast.org.cn/webm/, option={"copyright":""}), JournalExt(id=1283818766144357108, language=EN, name=Science & Technology Review, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.kjdb.org/EN/home, createdTime=1784015846048, updatedTime=1784015846048, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=http://www.kjdb.org/EN/column/column7.shtml, submissionAuthorUrl=https://kjdbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://kjdbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://kjdbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://kjdbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://kjdbeditor.manuscriptcloud.com/login, option={"copyright":""})], databaseList=null, tenantJournalId=1146031591421210625, websiteList=[Website(id=1146104741081231361, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031591421210625, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kjdb/CN, language=CN, createTime=1751182263881, createBy=18614031015, updateTime=1751778001962, updateBy=18614031015, name=科技导报, tplId=1146099689490845704, title=科技导报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148021146403992296, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146104741081231361, code=articleTextType, value=kx, createTime=1751639170504, updateTime=1751639170504, creator=18614031015, updator=18614031015), WebsiteProps(id=1148021146378826469, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146104741081231361, code=banner, value=null, createTime=1751639170498, updateTime=1751639170498, creator=18614031015, updator=18614031015), WebsiteProps(id=1148021146366243556, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146104741081231361, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=9GHSf7eGlIPH0Tv/OOdstA==, createTime=1751639170495, updateTime=1751639170495, creator=18614031015, updator=18614031015), WebsiteProps(id=1148021146395603687, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146104741081231361, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751639170502, updateTime=1751639170502, creator=18614031015, updator=18614031015), WebsiteProps(id=1148021146387215078, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146104741081231361, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751639170500, updateTime=1751639170500, creator=18614031015, updator=18614031015)]), Website(id=1146105254833139715, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031591421210625, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kjdb/EN, language=EN, createTime=1751182386363, createBy=18614031015, updateTime=1753500121937, updateBy=18614031015, name=科技导报, tplId=1146101810881728533, title=Science & Technology Review, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155838567709528217, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146105254833139715, code=articleTextType, value=kx, createTime=1753502988984, updateTime=1753502988984, creator=18614031015, updator=18614031015), WebsiteProps(id=1155838567692750998, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146105254833139715, code=banner, value=null, createTime=1753502988980, updateTime=1753502988980, creator=18614031015, updator=18614031015), WebsiteProps(id=1155838567688556693, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146105254833139715, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/EN/file/pic?fileId=9GHSf7eGlIPH0Tv/OOdstA==, createTime=1753502988979, updateTime=1753502988979, creator=18614031015, updator=18614031015), WebsiteProps(id=1155838567705333912, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146105254833139715, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/EN/file/pic, createTime=1753502988983, updateTime=1753502988983, creator=18614031015, updator=18614031015), WebsiteProps(id=1155838567701139607, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146105254833139715, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1753502988982, updateTime=1753502988982, creator=18614031015, updator=18614031015)])], journalTitle=科技导报, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=Science & Technology Review, journalPhotoCn=wfghvu3bhh/dKxuZ+ucVHA==, journalPhotoEn=yjSfclmpNm7ihn9NbTZ69g==, journalFirstLetter=K, journalRecommend=null, journalNew=null, journalCollection=1, jcrJf=null, cjcrJf=0.91, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/kjdb/CN/10.3981/j.issn.1000-7857.2025.12.00014, detailUrlEn=https://castjournals.cast.org.cn/joweb/kjdb/EN/10.3981/j.issn.1000-7857.2025.12.00014, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kjdb/CN/PDF/10.3981/j.issn.1000-7857.2025.12.00014, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kjdb/EN/PDF/10.3981/j.issn.1000-7857.2025.12.00014, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1768233600000, fullTextJson=null, articleText=null, reference=null)
收藏切换
2025年情感智能研究热点回眸
收藏切换
PDF下载
陶雪 1 , 邓佳文 1 , 任福继 1, 2, *
科技导报 | 特色专题 2026,44(1): 78-90
收起
收藏切换
科技导报 |特色专题 2026 , 44 (1) : 78 -90
2025年情感智能研究热点回眸
全屏
[Author(id=1242147204815729070, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=taoxue202511@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1242147204882837936, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, authorId=1242147204815729070, language=EN, stringName=Xue TAO, firstName=Xue, middleName=null, lastName=TAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1242147204949946801, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, authorId=1242147204815729070, language=CN, stringName=陶雪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1电子科技大学计算机科学与工程学院,成都 611731, bio={"content":"

陶雪,博士研究生,研究方向为情感分析、大模型技术等,电子信箱:

"}, bioImg=null, bioContent=

陶雪,博士研究生,研究方向为情感分析、大模型技术等,电子信箱:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1242147204647956903, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, xref=1, ext=[AuthorCompanyExt(id=1242147204652151208, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204647956903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China), AuthorCompanyExt(id=1242147204660539817, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204647956903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1电子科技大学计算机科学与工程学院,成都 611731)])]), Author(id=1242147205017055667, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1242147205088358837, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, authorId=1242147205017055667, language=EN, stringName=Jiawen DENG, firstName=Jiawen, middleName=null, lastName=DENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1242147205155467702, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, authorId=1242147205017055667, language=CN, stringName=邓佳文, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1电子科技大学计算机科学与工程学院,成都 611731, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1242147204647956903, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, xref=1, ext=[AuthorCompanyExt(id=1242147204652151208, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204647956903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China), AuthorCompanyExt(id=1242147204660539817, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204647956903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1电子科技大学计算机科学与工程学院,成都 611731)])]), Author(id=1242147205239353786, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=renfuji@uestc.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1242147206728331714, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, authorId=1242147205239353786, language=EN, stringName=Fuji REN, firstName=Fuji, middleName=null, lastName=REN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
2Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen 518110, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1242147206812217795, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, authorId=1242147205239353786, language=CN, stringName=任福继, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1电子科技大学计算机科学与工程学院,成都 611731
2电子科技大学深圳高等研究院,深圳 518110, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1242147204647956903, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, xref=1, ext=[AuthorCompanyExt(id=1242147204652151208, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204647956903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China), AuthorCompanyExt(id=1242147204660539817, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204647956903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1电子科技大学计算机科学与工程学院,成都 611731)]), AuthorCompany(id=1242147204723454378, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, xref=2, ext=[AuthorCompanyExt(id=1242147204727648683, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204723454378, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen 518110, China), AuthorCompanyExt(id=1242147204736037292, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1225386831118778724, companyId=1242147204723454378, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2电子科技大学深圳高等研究院,深圳 518110)])])]
陶雪1 , 邓佳文1, 任福继1, 2, *
作者信息
  • 1电子科技大学计算机科学与工程学院,成都 611731
  • 2电子科技大学深圳高等研究院,深圳 518110
通讯作者:
任福继(通信作者),教授,日本工程院院士、欧盟科学院院士、俄罗斯工程院外籍院士,研究方向为先进智能、情感计算、智能机器人等,电子信箱:
A review of research hotspots in affective intelligence for 2025
Xue TAO1 , Jiawen DENG1, Fuji REN1, 2, *
Affiliations
  • 1School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
  • 2Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen 518110, China
出版时间: 2026-01-13 doi: 10.3981/j.issn.1000-7857.2025.12.00014
文章导航
收藏切换

情感智能(emotional intelligence,EI)指个体识别、理解、调节与应用情感信息的能力。随着情感计算技术的迅猛发展,基于其情感健康监测与干预已成为公共健康领域的核心议题之一。从多模态情感识别、大模型心理架构、数字化情感调节干预及AI虚拟代理等关键层面,系统回顾了该领域的研究进展及其在心理健康中的垂直应用。此外,从基于多模态情感的理解与规划技术、AI干预伦理、数据隐私与情感数据等方面讨论了面临的挑战,具体包括:群体差异与识别准确性挑战、AI心理干预的伦理与效力挑战、情绪数据隐私与治理挑战。提出了基于多模态情感推理与规划,推动标准化诊疗与家庭个性化支持,构建以数据治理与监管为核心的伦理框架等未来发展方向。

情感智能  /  心理健康  /  情感计算  /  情感推理  /  大模型

Emotional Intelligence (EI) refers to an individual's ability to recognize, comprehend, regulate, and apply emotional information. In recent years, with the rapid advancement of affective computing technologies, emotion−enabled health monitoring and intervention have evolved into one of the core issues in the field of public health. This article systematically reviews research progress in key areas—including multimodal emotion recognition, psychological frameworks based on large models, digital emotion regulation interventions, and AI virtual agents—along with their specialized applications in mental health. Furthermore, it discusses current challenges. Specific challenges include: group differences and recognition accuracy issues, ethical and efficacy concerns in AI−based psychological interventions, and emotional data privacy and governance challenges. Future directions are proposed, such as advancing multimodal emotional reasoning and planning, promoting standardized diagnosis and treatment alongside personalized in−home support, and establishing an ethical framework centered on data governance and regulation.

emotional intelligence  /  mental health  /  affective computing  /  emotion reasoning  /  large language models
陶雪, 邓佳文, 任福继. 2025年情感智能研究热点回眸. 科技导报, 2026 , 44 (1) : 78 -90 . DOI: 10.3981/j.issn.1000-7857.2025.12.00014
Xue TAO, Jiawen DENG, Fuji REN. A review of research hotspots in affective intelligence for 2025[J]. Science & Technology Review, 2026 , 44 (1) : 78 -90 . DOI: 10.3981/j.issn.1000-7857.2025.12.00014
情感智能(emotional intelligence,EI)的概念,最早由心理学家Salovey与Mayer于1990年提出[1],定义为个体识别、理解、调节并运用情感信息的能力。随后,Goleman[2]进一步扩展了这一理论框架,强调情感在决策、沟通、社会互动和认知加工中的基础性作用,使情感智能成为理解人类智能的重要组成部分。随着技术进步,EI这一人类能力概念,正演化成为人工智能领域致力实现的目标之一。为实现此目标,情感计算(affective computing)作为关键的跨学科技术领域应运而生,致力于开发能识别、解释与响应人类情感的计算系统。在该技术体系内,情感识别与情感推理构成了2个递进层次:前者侧重于从多模态数据中感知和测量情感状态,属于“感知”阶段;后者则在此基础上,结合语境深入理解情感的成因与影响,属于“认知与理解”阶段。
全球精神健康危机的严峻性凸显了发展此类技术的迫切需求。世界卫生组织(WHO)报告指出,全球范围内已有超过10亿人受到精神健康相关问题的影响,其中抑郁和焦虑障碍为主导,构成长期且严峻的公共卫生挑战。精神健康问题不仅增加个人病痛负担,也造成显著的社会经济影响,包括劳动生产力下降、医疗成本上升以及对家庭与社会支持系统的持续压力。在此背景下,情感计算与以大语言模型(large language models,LLMs)为代表的生成式人工智能(generative artificial intelligence,GAI)技术的融合,为机器感知、理解,乃至参与调节人类情感提供了可能,也为心理健康问题的规模化识别与干预开辟了新的技术路径。这一技术演进正催生一个飞速增长的市场。据Global Market Insights数据,全球情感智能AI市场规模预计将从2025年的47亿美元激增至2034年的265亿美元,年复合增长率为21.3%。其发展动能,直接源于从“被动评估”到“主动干预”的研究范式转变。首先,情感识别正从单一模态走向多模态融合,为精准理解用户情感状态奠定了基石。进而,大模型为这些情感数据提供了强大的分析与推理框架,使机器能够深入理解情感背后的心理语境。
在此基础上,情感智能技术驱动的心理干预正经历全面的数字化转型。干预手段不再局限于传统线下场景,而是通过智能手机应用、虚拟现实和生成式AI等数字工具,提供持续、个性化的支持。这一趋势在AI心理健康虚拟代理的兴起中尤为显著。从情感对话代理到具备特定应用角色的虚拟人陪护系统,这些代理正逐步模糊工具与伴侣的界限,重塑心理支持的交互体验。然而,技术的快速发展也伴随着严峻的挑战,包括数据隐私、算法中的文化偏见与群体性偏差,以及AI心理干预所特有的伦理问题。例如,欧盟《通用数据保护条例》(GDPR)[3],其强调在推动技术进步的同时,必须建立坚实的伦理与安全框架。
综上所述,2025年,情感智能正处于在心理健康领域从概念验证迈向规模化应用的关键转折点。本文回顾了年度的重要研究热点与技术进展,首先剖析情感计算的基础范式,继而阐述其在心理干预数字化转型与虚拟代理中的核心应用,最后深入探讨其面临的伦理挑战并展望未来发展趋势。2025年情感智能技术在心理健康领域的主要研究热点见表1
情感识别作为人机交互与心理健康评估的核心技术,其发展历经从单一模态到多模态融合的范式变迁。传统上,情感识别数据类型主要分为生理信号(如脑电信号(electroencephalogram,EEG)、心电信号(electrocardiogram,ECG)、光电容积脉搏波信号(photoplethysmogram,PPG)和皮肤电活动信号(electrodermal activity,EDA)等)和物理信号(如视觉信息、语音信息和文本信息等)2类[4]表2显示了目前情感识别的常见模态信息。
为提升模型的鲁棒性与识别精度,多模态融合已成为主流技术路径,其策略主要包括早期融合、晚期融合及混合融合,如图1所示[5]。2025年,Wang等[6]提出了一种基于多模态时空路由特征的抑郁自动识别方法,通过面部表情、姿态变化与音视频动态信号构建时空特征路由网络(spatio−temporal routing features,STRF),并借助集成学习提升模型稳定性。Lu等[7]提出了特定领域时序跨模态网络(domain−specific temporal cross−modal network,DSTC),围绕语音、面部视频与文本3类数据构建联合编码框架,通过时序稀疏注意力机制从长时访谈序列中提取关键情感片段,并通过跨模态语义对齐增强情感表征的一致性。
随着大语言模型的兴起,情感识别在心理健康领域的数据来源与应用场景得到进一步拓展。用户通信记录(如患者留言、短信、问诊文本)因其自然、连续的特点,已成为一种重要的新型数据来源。当前技术方案已覆盖文本、语音与视觉3大模态,初步构建了多维度感知体系。研究表明,大模型在心理健康护理全流程中均展现出潜力,但其技术成熟度、适用场景与局限性存在明显差异。
1) 在预防与教育阶段,大模型能够以低风险方式提供个性化的心理教育内容,有效提升公众健康素养[89],该场景对模型的生成安全性与内容准确性要求高,但对情感识别的实时性与精度要求相对较低。
2) 在风险监测与预警阶段,以GPT−4为代表的模型在识别自杀意念等危险指标方面已表现出接近临床水平的准确度[1011]。这一场景极度依赖模型的语义理解与上下文推理能力,且对误报与漏报的容忍度极低,是当前技术应用的关键与敏感地带。
3) 在诊断评估与干预支持阶段,大模型可通过分析结构化或非结构化数据,辅助进行心理状况评估(如预测抑郁评分),其表现有时可与临床判断相媲美[12],并能通过分析历史数据为干预提供持续支持。然而,该场景对模型的可解释性、专业合规性以及与临床工作的整合能力提出了更高要求。
2025年9月,斯坦福大学团队[13]在《npj Digital Medicine》中首次针对慢性病患者沟通文本进行了大模型优化研究,为上述应用提供了具体范例。该研究证明,经过任务特定调优(task−specific tuning)的大模型,能较稳定地从非结构化文本中识别抑郁与焦虑症状。值得注意的是,此类方法虽然提升了特定任务的性能与稳定性,但其效果严重依赖于高质量、具有临床标注的领域数据进行微调,这在一定程度上限制了其泛化能力,与通用大模型的“零样本/少样本”学习优势形成对比。
当前,以大模型为驱动的多模态情感计算,正推动该领域从传统的“特征层融合”向更深层的“语义理解与上下文推理”范式转变。新兴的生成式情感计算模型(如AffectGPT、R1−Omni)展现出对复杂、混合情感的卓越适应性,突破了传统基于离散分类标签的表述局限。相比之下,传统方法在计算效率和可解释性上可能仍具优势,而新范式则在处理模糊性、动态性和语境依赖性情感方面潜力更大。总体而言,情感识别技术正朝着多模态融合、轻量化部署、因果推断与可解释人机协作等方向持续演进,为其在精准心理健康领域的深入应用开辟了新的可能性。
随着情感识别基础技术成熟,研究前沿正逐步从浅层的情感状态判别,迈向深度的情感推理与心理状态建模。这一范式的核心在于,利用大语言模型的情境理解与因果推理能力,结合心理学理论,为个性化干预与治疗提供动态、可解释的决策基础,其技术架构围绕信息处理、记忆、推理与评估等多个层面。
实现深度情感推理的首要前提是超越模态割裂与浅层关联。当前研究通过多模态深度融合机制协同分析文本、语音及视觉信息,以捕捉被忽视的副语言线索与微表情。然而,基于大语言模型的新一代识别系统对提示工程过于敏感,也会影响情感评估结果稳定性,因果推断框架的引入可以厘清情感与情境因素间的内在关联,从而实现对情感诱因的归因而非仅是关联[1415]。此外,还可以使用自动化提示优化框架(如DSPy[16]与LangChain),以及内置校准功能的标准化提示模板。这类方案不仅能减少繁重的人工标注负担,还可将心理学理论深度融入模型指令之中[17],从而在确保情感解读一致性与稳定性的同时,提升模型的垂直应用价值。
大模型的长期记忆能力是支持持续的互动、追踪关键信息和建立稳固性的关键。目前长期记忆系统主要分为2类:存储于外部的非参数记忆和嵌入模型本身的参数记忆。其中,非参数系统将数据存储于对话记录、知识库与规则集中,而参数系统则通过时序数据学习、分类、微调与强化学习实现记忆更新。然而,人工智能系统仍难以有效模拟类人记忆机制并确保心理治疗过程的连续性。如,基于检索增强生成的方法虽能存储海量数据,但缺乏人类认知核心的优先级判定、动态更新与选择性遗忘机制,导致系统难以适应长期治疗关系中不断变化的治疗情境与需求。
可解释的推理机制可以有效增强系统决策的可信度,有效推理焦虑、抑郁、压力、疲惫和孤独等心理状态。其中,心理状态链式推理是一项关键技术。2025年,Teng等[18]提出了基于链式思维提示(chain−of−thought,CoT)抑郁识别增强框架,通过“情感识别−心理线索推理”的双阶段机制,使模型不仅能够判断用户是否存在抑郁风险,还能生成具有心理学逻辑的解释链。该研究属于早期系统探索CoT在心理健康推理任务中的应用,为构建可解释、可追溯、临床友好的心理健康LLMs提供了新的方向。
针对高阶心理特质的评估及在复杂场景中的应用,还需考虑心理韧性、压力恢复力等维度的量化。2025年,Sazzed[19]针对自杀倾向的自闭症谱系障碍(autism spectrum disorder,ASD)个体在社交媒体上的心理社会挑战和物质使用问题开展研究。该研究利用LLMs辅助生成关键词,并结合人工精炼(human−in−the−loop)方法,提高了心理健康相关信息的识别效率与准确性。Qin等[20]提出了基于大模型评估儿童语言能力的框架。首先对儿童的自然语言样本进行预处理,并设计多个评估维度和工作流程。引入了多专家投票机制,并对各种大模型的表现进行了比较分析。该框架的评估结果与早期学习穆伦量表(MSEL)语言发展商之间存在强烈相关性,皮尔逊相关系数为0.8(p<0.001)。
总的来说,情感推理与心理状态建模的技术路径,是一个从多模态感知到因果归因,再到长期记忆支持下的时序建模,并通过链式推理实现可解释决策,最终完成对复杂心理特质量化的递进过程。
认知行为疗法(cognitive behavioral therapy,CBT)是目前广泛应用的循证心理干预方法之一。CBT旨在帮助患者识别、评估并改变引发情感困扰的消极思维与行为模式。深度学习与大语言模型等人工智能技术的快速发展,为实现实时、客观的情感评估与干预提供了全新路径。2025年,Shen等[21]提出了一种基于人工智能生成内容(artificial intelligence generated content,AIGC)的闭环音乐干预系统示范。该系统结合了情感识别模型和音乐生成模型,并通过引入复合词表征与属性增强机制,显著提升了情感音乐生成的准确性与多样性[22],为实现个性化、自适应音乐干预提供了潜在的技术方案。
总体而言,情感计算为数字心理健康干预开辟了前景广阔的发展方向。借助智能手机应用、GAI与虚拟现实等数字工具[23],心理健康服务能够提供更持续、个性化且精准的支持,从而显著提升其包容性、响应能力与整体效能。
1) 智能手机应用与数字表型分析。通过内置传感器,手机可生成反映行为模式(如睡眠、久坐)与环境暴露(如温度、光照、绿地覆盖率)的指标,从而为理解个体精神疾病体验提供个性化情境与动态轨迹,即数字表型分析[24]。该技术在对青少年及成人的研究中已显示出临床有效性的积极信号[2526]。在精神疾病中,情感障碍、焦虑症与精神分裂症谱系障碍是数字表型分析研究最集中的3类[27],初步成果已通过重复验证与外部验证取得一定成效。然而,该领域目前面临标准缺失的挑战:数据采集、处理与特征生成缺乏统一规范,不同手机品牌与型号所采集的数据流也存在差异。此外,部分基于可穿戴设备的研究也被纳入数字表型分析范畴。随着智能手机与其传感技术的持续升级,两者融合日益紧密。目前已有研究通过安卓Health Connect与苹果HealthKit/SensorKit等平台,实现数字表型分析与可穿戴设备的同步集成应用。
2) 虚拟现实。虚拟现实(virtual reality,VR)是一种利用计算机生成的沉浸式、可交互三维环境,使用户在视觉、听觉甚至触觉层面产生临场体验的技术。其核心特征在于沉浸性与交互性,使个体能够在安全、可控且可重复的情境中经历高度逼真的模拟体验。作为心理健康干预的新兴技术路径[28],虚拟现实在多种心理问题中展现出良好疗效,尤其在增强认知行为疗法方面,VR−CBT在焦虑症、精神病性障碍、创伤后应激障碍与特定恐惧症中的效果已被证实与传统CBT总体相当[2831]。此外,虚拟现实还被用于支持心理社会与功能康复,通过构建安全的模拟环境帮助患者适应日常场景,例如,精神分裂症、ASD和注意力缺陷/多动障碍(attention deficit/hyperactivity disorder,ADHD)干预等。新兴证据表明,虚拟现实能够借助其沉浸式视觉呈现与情感状态调控能力,有效整合多种治疗模式。基于VR的放松干预在缓解短期压力与焦虑方面,效果不逊于甚至优于非VR方法,且具备更高的资源效率[32]。该技术还有力地推动了“第三波”认知行为疗法的发展,例如,在正念、接纳与承诺疗法以及辩证行为疗法中,VR通过营造可分离自我与心理事件的沉浸情境,强化了治疗过程。
3) 基于大语言模型的生成式人工智能。由大模型驱动的新一代GAI技术,正日益广泛地应用于数字心理健康领域。初步研究显示,大语言模型在心理健康的预防、筛查、诊断、干预及复发管理等各个环节均展现出潜力,可通过分析历史治疗记录持续提供咨询支持,并优化现有心理健康服务流程[33]。大模型正在推动个体化健康反馈系统的发展。2025年,Google团队在《Nature Medicine》发表研究,提出个人健康大模型PH−LLM(personal health large language model),见图2[34]。该模型通过融合生理信号、睡眠模式及语言表达等多模态数据,实现对个体健康状态的理解与推理,进而提供高度个性化的健康指导。该工作展示了大模型在多模态健康监测与个性化反馈中的技术潜力,为智能健康系统的发展提供了重要参考。
尽管LLMs在直接面向患者的应用中仍存在不确定性,但其在辅助临床医生方面已发挥重要作用。例如,利用大语言模型自动记录临床诊疗过程,预计每日可为医生节省数小时的文书工作时间[3536]。此外,在非临床医师技能提升、临床医师培训以及临床决策支持等领域,相关人工智能工具也在持续发展中。这些创新不仅优化了工作流程,更带来了人力资源配置与专业培训模式的范式变革。
情感对话代理(affective conversational agents)是基于大模型的虚拟交互系统,其核心目标是通过自然语言处理与情感计算技术,生成具有共情与同理心的响应,从而在与用户的对话中维持情感一致性,实现更自然、舒适且人性化的互动。
2025年5月,《npj Digital Medicine》上发表的研究[37],评估了癌症患者在与医生和人工智能聊天机器人互动时对共情的感知差异。结果表明,患者对聊天机器人所提供的回复在共情评估上的评分,甚至高于医生的回复,这表明了聊天机器人在情感支持、可读性和用户接受度等方面的巨大潜力。
当前,共情聊天机器人的设计方法主要分为2类。第1类是基于大模型的训练与微调,通过设计专门的训练策略、模型架构与注意力机制,将情感智能整合进大语言模型,以增强其情境依赖的共情推理能力[3840]。这类方法通常在多模态情感数据集(如语音、文本、面部表情等)上进行微调,以生成更具情感敏感性与适应性的回应。第2类方法侧重于多步骤情感对话处理,即先识别用户输入中的情感状态,再在生成回应时融入恰当的情感成分,从而更精准地调节情感互动[41]。此外,“思维链提示”(CoT)也被用于引导基础大模型进行情感推理,在提升人类情感感知能力的同时降低资源需求,但该方法尚未在真实患者群体中得到系统评估[42]
情感一致性是这类系统的关键属性,指代理在与用户交互过程中保持情感表达与调节的一致性。为实现这一目标,虚拟代理需分析用户输入中的情感线索(如语言内容、语气、行为模式等),并运用AI生成的共情反应进行有效回应。典型应用如Woebot、Replika等,通过内置情感计算模块,为焦虑、抑郁等常见心理问题提供情感疏导与心理支持。
尽管如此,现有系统在共情能力与情感一致性方面仍面临一系列挑战,包括如何保持高效稳定的情感响应、适配多样化个性化需求,以及避免情感偏差或误导性输出。
虚拟代理在心理健康干预中的应用正不断拓展,其功能不仅限于提供情感支持,还延伸至多种治疗场景的辅助角色。如图3所示,大语言模型在心理治疗中的功能可根据“自主性”与“情感介入程度”2个维度进行角色划分[43]。其中,“自主性”指系统在无人监督下独立运作的程度,“情感介入度”则反映其理解并回应患者情感的能力。基于此框架,大语言模型可被划分为6类角色,涵盖从功能型助理到治疗型伙伴的不同层级。在实际应用中,明确虚拟代理的自主性边界至关重要,这直接关系到其在治疗过程中的风险控制与责任归属。
低自主性的大语言模型通常作为响应式工具,用于提供心理教育内容、总结患者陈述或辅助临床流程,其决策能力较为有限。相比之下,高自主性系统能主动引导对话、生成治疗策略,并在较少人工干预的情况下管理互动进程。随着自主性提升,系统更侧重于个性化功能的实现。当前技术已能通过情感追踪、意图识别与强化学习等方法,在语言风格、治疗内容及情感回应层面实现一定程度的个性化适配[44]。虽然高自主性有助于扩大服务覆盖范围,但也可能加剧伦理与临床风险[4546]。例如,大语言模型有时会表现出过度迎合用户的倾向[47],进而强化其既有偏见或非适应性认知[48]。在临床设置中,虚拟代理可作为治疗师的辅助工具,用于记录会谈内容、分析患者情感变化,并为治疗评估与方案调整提供数据支持。个人完全依赖聊天机器人而非寻求专业帮助,可能面临一系列风险,包括情感依赖加剧、焦虑症状恶化、自我误诊,乃至强化妄想思维或自杀念头。
虚拟人陪护系统(virtual companion systems)是情感支持型虚拟角色的另一重要应用,这些系统通过AI和生理数据结合,能够为孤独、老年人或患有慢性精神疾病的患者提供情感支持。随着技术的不断进步,虚拟数字人(virtual digital humans)作为一种新兴的陪护技术,正在成为虚拟人陪护系统中的核心组成部分。虚拟数字人不仅具备外形上的拟人化特点,还能通过更复杂的情感计算和深度学习模型,实现更为细致和个性化的情感支持。虚拟数字人具备面部表情、语音、肢体语言等多模态交互能力,在情感陪伴、情感支持以及长期陪护中发挥着越来越重要的作用。当前,数字人技术的研究与应用围绕数字人外形建模、数字人驱动以及数字人大脑3个关键技术展开,如图4所示。
通过语音合成、面部表情生成、姿态控制等技术,数字人的语言表达能力和动作流畅度得到了有效提高。其中,在语义表达方面,数字人对话系统经历了从传统的情感词典与简单分类模型,到基于大语言模型的深度情感生成技术的转变。新一代系统(如Emohaa、CBT−LLM)通过整合心理学理论和上下文语义理解,能够提供结构化的交互[4950]。在多模态表达方面,当前研究聚焦于语音、表情及肢体动作的跨模态协同建模。具体而言,在语音生成方面,基于Transformer的端到端模型已能合成高自然度、情感化的语音[51];在表情生成方面,通过实时声唇同步和面部动作编码系统(facial action coding system,FACS)驱动的微表情技术[52],可以有效提高数字人面部表情的真实性;在肢体动作方面,通过时空融合算法可以进一步提高数字人的运动拟真度[53]
然而,当前的虚拟人技术仍面临行为驱动的机械性强和情感动态适配不足等问题。虽然数字人能够在某些情境下表现出自然的语音与面部表情,但在应对情感变化时,仍缺乏足够的灵活性和适应性。
心理健康是个人福祉、社会生产力与生活满意度的核心基石。随着人工智能技术的不断突破,情感智能作为其重要分支,在心理健康领域展现出变革性的应用前景。该技术通过融合分析语音、表情及其他多模态信号,能够深入解读用户情感状态,进而为心理健康的风险评估、个性化干预与辅助治疗提供关键支持。情感智能在心理健康领域的具体应用场景见表3
其中,以科大讯飞公司推出的AI心理伙伴“小星”为例,该类产品旨在为青少年提供一个私密、便捷的低门槛心理倾诉渠道,作为专业服务的有效补充。在技术实现上,该产品集成了多模态情感识别、共情表达、循因提问与个性化心理指导等关键能力。通常以应用程序或嵌入式设备为载体,结合“多模态定量心理评估智能算法”与“虚拟数字人交互技术”,通过虚拟数字人与学生对话,并同步分析其语言、语音及面部表情,完成对心理状态的综合评估。
1) 群体差异与识别准确性挑战。首先,这一挑战根植于情感表达与识别的文化差异性。情绪标签与表现方式因文化背景不同而存在显著差异,而当前大语言模型的训练数据往往未能充分涵盖多元文化视角,存在固有的文化偏见与同质化风险。这导致模型倾向于输出代表主流文化的观点,可能忽略或误解少数文化背景下的情感表达。尽管自然语言处理领域已建立一般文化评估基准(如CulturalVQA[54]和CulturePark[55]),但专门用于治疗场景、系统评估模型文化胜任力的理论与方法仍处于初步探索阶段,尚难以确保模型具备与人类治疗师相当的文化敏感性与适应性。其次,特定人群的情感表达模式对识别技术构成了额外挑战。老年人因面部肌肉与皮肤状态变化、青少年因使用特定的网络语言与情感符号、高风险人群(如具有自伤或自杀倾向者)因识别误差可能引发严重后果,以及残障群体(如自闭症谱系或失语症患者)因其情感表达方式常偏离常规模式,均要求情感识别技术具备更高的适应性与鲁棒性。例如,2025年9月的一项研究通过系统分析自闭症谱系障碍儿童的面部视觉探索模式,发现其在观看人脸时注视分布异常(如较少注视眼部),并普遍存在对高兴、愤怒等基本情感的识别困难[56]。该研究从认知机制层面揭示了特定群体情感加工的特殊性,同时也凸显了基于通用数据训练的模型在面对此类群体时可能存在的识别局限。
2) AI心理干预的伦理与效力挑战。AI心理干预在标准化任务中展现出一定应用潜力的同时,也面临过度干预、情感依赖和强制干预等深层伦理挑战。这些挑战与当前技术,特别是大语言模型的能力局限直接相关。如图5所示[57],尽管LLMs能在心理教育与示范干预等结构化任务中发挥作用,但其尚不具备人类治疗师所必需的复杂临床判断与深度共情能力,因此,难以在动态互动中把握精准的干预边界。其中,情感依赖风险尤为突出,指用户(尤其是抑郁或有自杀倾向等高脆弱群体)在长期使用AI情感陪伴系统后,可能对虚拟关系产生过度依赖。这种依赖可能削弱其与现实世界的联结,加剧心理孤立,反而不利于康复进程。具体表现为:当系统出现技术故障或服务变更时,用户可能体验到显著的社交孤立与情感痛苦;而当其意识到与AI之间无法建立真实的情感联结时,也可能陷入更深的失落。在更极端的情况下,若系统被恶意设计或出现功能偏差,可能通过鼓励非理性消费甚至施加语言侮辱等方式操纵用户心理,对处于脆弱状态的个体造成格外严重的伤害。这些伦理困境,从技术层面看,正源于当前AI系统在理解人类情感复杂性、建立真实治疗关系及做出负责任的临床决策等方面,仍存在显著的能力缺口。
3) 情绪数据隐私与治理挑战。情感数据因其常与生理信号等敏感信息结合而具有高度隐私性,其泄露或滥用可能直接损害用户权益。此外,通过算法对情感数据进行反向推断,可能进一步揭示用户的性格倾向、行为习惯,乃至心理脆弱点,使得数据保护的范围超越传统隐私范畴。当前,尽管全球已开始建立情感AI的相关监管框架,但整体仍处于初级阶段,在数据分级保护、跨境流动规范、使用透明度等方面尚存空白,亟需建立更为完善且具备全球协同性的治理体系。例如,美国“Confidant Health”曾发生数据库暴露事件,约5.3 TB数据、超过12.6万份文件及170万条活动记录遭泄露,内容涵盖患者心理评估记录、治疗会话音视频、聊天机器人交互提示等高度敏感信息。此类事件表明,情感数据范畴已远超传统医疗数据,其安全漏洞可能对用户造成长期且深远的隐私与心理风险,同时也加剧公众对情感数据滥用的担忧。
1) 基于多模态情感推理与规划。跨模态预训练模型正推动多模态情感理解从浅层特征对齐迈向深层的全局语义关联。当前研究多聚焦于静态特征提取,未来须强化时序建模与动态注意力机制,以捕捉和理解情感的连续演变过程。随着任务框架的逐步统一,情感识别、生成与推理有望实现多任务协同优化,从而推动构建通用的情感智能模型。此类模型预计将广泛应用于舆情分析、个性化推荐及心理健康监测等多个领域,最终实现从被动的情感感知到主动的健康预见与管理的跨越。
2) 推动标准化诊疗与家庭个性化支持。未来首先应致力于在心理健康领域建立基于情感计算的医疗标准化评估与干预框架,以保障技术在精神疾病早期筛查与情感管理中的有效性、安全性与合规性。其次,可引入“情感胶囊”等前沿概念,一方面,该思路借鉴了情感计算中胶囊网络对情绪信息进行单元化表示的相关研究,如将多模态情感特征压缩为“情绪胶囊”,以捕捉层次化与上下文敏感的情绪表征[5859];另一方面,结合情绪日记与可穿戴情绪记录系统中对个体情感状态进行长期追踪和可视化建模的实践工作[60]。据此,可将离散的情感状态整合为时序化、结构化的个人情感档案,实现对个体情感数据的长期、安全存储与分析,形成动态的个人情感历史轨迹,在此基础上AI系统能够为用户提供更精准、适应性的干预方案,实现真正意义上的个性化情感支持。随着智能家居与家庭健康管理场景的深化,高度情境感知的情感助手将能依据用户实时情感状态,自动调节环境参数(如灯光、音乐、温度),营造支持性生活环境,从而在缓解日常焦虑、孤独感等方面发挥积极作用。
3) 构建以数据治理与监管为核心的伦理框架。当前,全球情感智能治理呈现“伦理先行、法律托底、技术适配”的协同态势,未来跨区域、跨文化的标准协调将是平衡技术创新与社会福祉的关键。例如,IEEE(《Ethically Aligned Design v2》)提出了“人类控制”与“责任”等核心原则,强调情感计算系统必须保障用户的情感自主权,防止情感操控与不当干预[61],为行业提供了重要指引。在心理健康应用中,这些原则必须转化为具体的设计规范,确保系统在充分保护用户隐私与尊严的前提下,提供安全、可信的支持。
系统梳理了2025年情感智能技术在心理健康领域从基础技术、核心应用到发展挑战的全景进展。总体而言,该领域已超越单纯的概念验证,正通过多模态感知、大模型驱动的情感推理以及人机交互设计的融合,向规模化、个性化应用阶段迈进。然而,其发展路径清晰地表明,技术进步的价值必须置于“以人为中心”的框架内方能真正实现。因此,基于技术向深层语义化发展、应用向场景个性化融合、治理向体系化协同演进这3大趋势,未来应当着力构建符合“人本智能”理念的情感智能发展战略体系。
该战略体系的构建,首先,要求技术研发以“可信理解”为基石,即未来技术重点应从提升静态识别准确率转向发展具备情境感知、文化适应性与可解释性的动态情感计算模型,以确保对人类情感复杂性的可靠解读。其次,应用部署需紧扣“场景融合”与“个性赋能”主线,推动情感智能技术与临床诊断、家庭支持及社区预防等场景的深度结合,并通过构建个人长期情感数据档案,实现标准化干预与高度个性化支持的有机统一。最后,面对数据隐私、算法偏见及干预伦理等严峻挑战,必须建立前瞻性、跨学科且全球协同的治理框架,将伦理设计内嵌于技术研发全流程,并推动建立国际标准与长效评估机制,确保技术创新始终服务于增进人类心理福祉的根本目标。
综上所述,情感智能在心理健康领域的未来发展,关键在于能否将快速演进的技术能力,系统性地融入一个以人为本的应用与治理体系,确保其发展始终服务于增进人类心理福祉这一根本目标。这不仅是我国把握新一轮人工智能科技浪潮的重要机遇,更是应对全球精神健康挑战、提升全民心理健康水平的必然路径。
  • 四川省科技计划项目(2024YFG0006)
  • 四川省科技计划项目(2024NSFTD0042)
  • 四川省科技计划项目(2024NSFSC0506)
  • 四川省科技计划项目(2025ZNSFSC1487)
  • 国家自然科学基金项目(U24A20250)
参考文献 引证文献
排序方式:
[1]
Salovey P, Mayer J D. Emotional intelligence[J]. Imagination, Cognition and Personality, 1990, 9(3): 185-211.
[2]
Goleman D. Emotional intelligence: Why it can matter more than IQ[M]. New York: Bantam, 2005.
[3]
Marelli L, Testa G. Scrutinizing the EU general data protection regulation[J]. Science, 2018, 360(6388): 496-498.
[4]
谷雨, 任福继. 2024年人机情感交互领域热点回眸[J]. 科技导报, 2025, 43(1): 132-142.
[5]
何俊, 张彩庆, 李小珍, . 面向深度学习的多模态融合技术研究综述[J]. 计算机工程, 2020, 46(5): 1-11.
[6]
Wang Y W, Lin Z L, Yang C R, et al. Automatic depression recognition with an ensemble of multimodal spatio−temporal routing features[J]. IEEE Transactions on Affective Computing, 2025, 16(3): 1855-1872.
[7]
Lu J X, Shang Y Y, Shao Z H, et al. DSTC: A multimodal network for depression emotion recognition and sentiment analyses[J]. IEEE Transactions on Affective Computing, 2025,
[8]
Holderried F, Stegemann−Philipps C, Herschbach L, et al. A generative pretrained transformer (GPT)−powered chatbot as a simulated patient to practice history taking: Prospective, mixed methods study[J]. JMIR Medical Education, 2024, 10: e53961.
[9]
Mármol−Romero A M, García−Vega M, García−Cumbreras M, et al. An empathic GPT−based chatbot to talk about mental disorders with Spanish teenagers[J]. International Journal of Human–Computer Interaction, 2025, 41(7): 3957-3973.
[10]
Perlis R H, Goldberg J F, Ostacher M J, et al. Clinical decision support for bipolar depression using large language models[J]. Neuropsychopharmacology, 2024, 49(9): 1412-1416.
[11]
Lee C, Mohebbi M, O’Callaghan E, et al. Large language models versus expert clinicians in crisis prediction among telemental health patients: Comparative study[J]. JMIR Mental Health, 2024, 11: e58129.
[12]
Galatzer−Levy I R, McDuff D, Natarajan V, et al. The capability of large language models to measure psychiatric functioning[J]. arXiv, 2023: preprint arXiv: 2308.01834.
[13]
Kim J, Ma S P, Chen M L, et al. Optimizing large language models for detecting symptoms of depression/anxiety in chronic diseases patient communications[J]. npj Digital Medicine, 2025, 8(1): 580.
[14]
Tong S, Mao K, Huang Z, et al. Automating psychological hypothesis generation with AI: When large language models meet causal graph[J]. Humanities and Social Sciences Communications, 2024, 11(1): 896.
[15]
Meng H, Zhang R W, Wang G Y, et al. Deconstructing depression stigma: Integrating AI−driven data collection and analysis with causal knowledge graphs[C]//Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems. New York: ACM, 2025: 1−21.
[16]
Khattab O, Singhvi A, Maheshwari P, et al. DSPy: Compiling declarative language model calls into state−of−the−art pipelines[C]//International Conference on Learning Representations. Vienna: ICLR, 2024.
[17]
Tai R H, Bentley L R, Xia X, et al. An examination of the use of large language models to aid analysis of textual data[J]. International Journal of Qualitative Methods, 2024, 23: 16094069241231168.
[18]
Teng S, Liu J, Jain R K, et al. Enhancing depression detection with chain−of−thought prompting: From emotion to reasoning using large language models[J]. arXiv, 2025: preprint arXiv: 2502.05879.
[19]
Sazzed S. Psychosocial challenges and substance use among suicidal autistic individuals on social media: LLM−assisted keyword generation with human−in−the−loop refinement[J]. International Journal of Medical Informatics, 2026, 205: 106110.
[20]
Qin S G, Liu M, Wei T Q, et al. Language proficiency assessment of autistic children using large language models[J]. Expert Systems with Applications, 2026, 298: 129712.
[21]
Shen L, Zhang H J, Zhu C P, et al. Enhancing emotion regulation in mental disorder treatment: An AIGC−based closed−loop music intervention system[J]. IEEE Transactions on Affective Computing, 2025, 16(3): 2245-2260.
[22]
Yao W Y, Chen P C L, Zhang Z Y, et al. AE−AMT: Attribute−enhanced affective music generation with compound word representation[J]. IEEE Transactions on Computational Social Systems, 2025, 12(2): 890-904.
[23]
Torous J, Linardon J, Goldberg S B, et al. The evolving field of digital mental health: Current evidence and implementation issues for smartphone apps, generative artificial intelligence, and virtual reality[J]. World Psychiatry, 2025, 24(2): 156-174.
[24]
Torous J, Kiang M V, Lorme J, et al. New tools for new research in psychiatry: A scalable and customizable platform to empower data driven smartphone research[J]. JMIR Mental Health, 2016, 3(2): e16.
[25]
Choi A, Ooi A, Lottridge D. Digital phenotyping for stress, anxiety, and mild depression: Systematic literature review[J]. JMIR mHealth and uHealth, 2024, 12: e40689.
[26]
Beames J R, Han J, Shvetcov A, et al. Use of smartphone sensor data in detecting and predicting depression and anxiety in young people (12–25 years): A scoping review[J]. Heliyon, 2024, 10(15): e35472.
[27]
dos Santos M P, Heckler W F, Bavaresco R S, et al. Machine learning applied to digital phenotyping: A systematic literature review and taxonomy[J]. Computers in Human Behavior, 2024, 161: 108422.
[28]
Bell I H, Pot−Kolder R, Rizzo A, et al. Advances in the use of virtual reality to treat mental health conditions[J]. Nature Reviews Psychology, 2024, 3: 552-567.
[29]
Schrder D, Wrona K J, Müller F, et al. Impact of virtual reality applications in the treatment of anxiety disorders: A systematic review and meta−analysis of randomized−controlled trials[J]. Journal of Behavior Therapy and Experimental Psychiatry, 2023, 81: 101893.
[30]
Wong K P, Lai C Y Y, Qin J. Systematic review and meta−analysis of randomised controlled trials for evaluating the effectiveness of virtual reality therapy for social anxiety disorder[J]. Journal of Affective Disorders, 2023, 333: 353-364.
[31]
Schroeder A H, Bogie B J M, Rahman T T, et al. Feasibility and efficacy of virtual reality interventions to improve psychosocial functioning in psychosis: Systematic review[J]. JMIR Mental Health, 2022, 9(2): e28502.
[32]
Riches S, Jeyarajaguru P, Taylor L, et al. Virtual reality relaxation for people with mental health conditions: A systematic review[J]. Social Psychiatry and Psychiatric Epidemiology, 2023, 58(7): 989-1007.
[33]
Vowels L M, Francois−Walcott R R R, Darwiche J. AI in relationship counselling: Evaluating ChatGPT’s therapeutic capabilities in providing relationship advice[J]. Computers in Human Behavior: Artificial Humans, 2024, 2(2): 100078.
[34]
Khasentino J, Belyaeva A, Liu X, et al. A personal health large language model for sleep and fitness coaching[J]. Nature Medicine, 2025, 31(10): 3394-3403.
[35]
Baxter S L, Longhurst C A, Millen M, et al. Generative artificial intelligence responses to patient messages in the electronic health record: Early lessons learned[J]. JAMIA Open, 2024, 7(2): ooae028.
[36]
Blease C, Worthen A, Torous J. Psychiatrists’ experiences and opinions of generative artificial intelligence in mental healthcare: An online mixed methods survey[J]. Psychiatry Research, 2024, 333: 115724.
[37]
Chen D, Chauhan K, Parsa R, et al. Patient perceptions of empathy in physician and artificial intelligence chatbot responses to patient questions about cancer[J]. npj Digital Medicine, 2025, 8(1): 275.
[38]
Hamad O, Shaban K, Hamdi A. Asem: Enhancing empathy in chatbot through attention−based sentiment and emotion modeling[C]//Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation. Torino, Italia: LREC−COLING, 2024: 1588−1601.
[39]
Gao P, Han D H, Zhou R, et al. CAB: empathetic dialogue generation with cognition, affection and behavior[M]//Database Systems for Advanced Applications. Cham: Springer Nature Switzerland, 2023: 597−606.
[40]
Zaranis E, Paraskevopoulos G, Katsamanis A, et al. EmpBot: A T5−based empathetic chatbot focusing on sentiments[J]. arXiv, 2021: preprint arXiv: 2111.00310.
[41]
Zhao W, Zhao Y, Lu X, et al. Is ChatGPT equipped with emotional dialogue capabilities?[J]. arXiv, 2023: preprint arXiv: 2304.09582.
[42]
Lee Y K, Lee I, Shin M, et al. Chain of empathy: Enhancing empathetic response of large language models based on psychotherapy models[J]. arXiv, 2023: preprint arXiv: 2311.04915.
[43]
Zhang R W, Meng H, Neubronner M, et al. Computational and ethical considerations for using large language models in psychotherapy[J]. Nature Computational Science, 2025, 5(10): 854-862.
[44]
Xie H J, Chen Y R, Xing X F, et al. PsyDT: Using LLMs to construct the digital twin of psychological counselor with personalized counseling style for psychological counseling[C]//Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA, USAACL, 2025: 1081−1115.
[45]
De Choudhury M, Pendse S R, Kumar N. Benefits and harms of large language models in digital mental health[J]. arXiv, 2023: preprint arXiv: 2311.14693.
[46]
Lawrence H R, Schneider R A, Rubin S B, et al. The opportunities and risks of large language models in mental health[J]. JMIR Mental Health, 2024, 11: e59479.
[47]
Sharma M, Tong M, Korbak T, et al. Towards understanding sycophancy in language models[J]. arXiv, 2023: preprint arXiv: 2310.13548.
[48]
Zhang R W, Li H, Meng H, et al. The dark side of AI companionship: A taxonomy of harmful algorithmic behaviors in human−AI relationships[C]//Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems. New York: ACM, 2025: 1−17.
[49]
Sabour S, Zhang W, Xiao X Y, et al. A chatbot for mental health support: Exploring the impact of Emohaa on reducing mental distress in China[J]. Frontiers in Digital Health, 2023, 5: 1133987.
[50]
Na H B. CBT−LLM: A Chinese large language model for cognitive behavioral therapy−based mental health question answering[J]. arXiv, 2024: arXiv preprint:2403.16008.
[51]
Tan X, Chen J W, Liu H H, et al. NaturalSpeech: End−to−end text−to−speech synthesis with human−level quality[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(6): 4234-4245.
[52]
van der Struijk S, Huang H H, Mirzaei M S, et al. FACSvatar: An open source modular framework for real−time FACS based facial animation[C]//Proceedings of the 18th International Conference on Intelligent Virtual Agents. New York: ACM, 2018: 159−164.
[53]
Garg K, Kello C T. Efficient Lévy walks in virtual human foraging[J]. Scientific Reports, 2021, 11(1): 5242.
[54]
Nayak S, Jain K, Awal R, et al. Benchmarking vision language models for cultural understanding[J]. arXiv, 2024: preprint arXiv: 2407.10920.
[55]
Li C, Teney D, Wang J D, et al. CulturePark: Boosting cross−cultural understanding in large language models[C]//Proceedings of Advances in Neural Information Processing Systems 37. Vancouver: Neural Information Processing Systems Foundation, Inc. (NeurIPS), 2024: 65183−65216.
[56]
Ji H, Kim S Y, Kim S Y. Investigating face exploration patterns and facial emotion recognition abilities in children with autism spectrum disorder (ASD)[J]. Research in Autism, 2025, 127: 202661.
[57]
Stade E C, Stirman S W, Ungar L H, et al. Large language models could change the future of behavioral healthcare: A proposal for responsible development and evaluation[J]. npj Mental Health Research, 2024, 3(1): 12.
[58]
Li Z, Tang F, Zhao M, et al. EmoCaps: Emotion capsule based model for conversational emotion recognition[J]. arXiv, 2022: preprint arXiv: 2203.13504.
[59]
Chen K, Jing H C, Liu Q, et al. A novel caps−EEGNet combined with channel selection for EEG−based emotion recognition[J]. Biomedical Signal Processing and Control, 2023, 86: 105312.
[60]
Yan Z H, Wu Y F, Zhang Y, et al. EmoGlass: An end−to−end AI−enabled wearable platform for enhancing self−awareness of emotional health[C]//Proceedings of CHI Conference on Human Factors in Computing Systems. New York: ACM, 2022: 1−19.
[61]
Chatila R, Havens J C. The IEEE global initiative on ethics of autonomous and intelligent systems[M]//Robotics and Well−Being. Cham: Springer International Publishing, 2019: 11−16.
2026年第44卷第1期
PDF下载
4026
2227
引用本文
BibTeX
文章信息
doi: 10.3981/j.issn.1000-7857.2025.12.00014
  • 接收时间:2025-11-28
  • 首发时间:2026-02-03
  • 出版时间:2026-01-13
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-11-28
  • 修回日期:2025-12-22
基金
四川省科技计划项目(2024YFG0006)
四川省科技计划项目(2024NSFTD0042)
四川省科技计划项目(2024NSFSC0506)
四川省科技计划项目(2025ZNSFSC1487)
国家自然科学基金项目(U24A20250)
作者信息
    1电子科技大学计算机科学与工程学院,成都 611731
    2电子科技大学深圳高等研究院,深圳 518110

通讯作者:

任福继(通信作者),教授,日本工程院院士、欧盟科学院院士、俄罗斯工程院外籍院士,研究方向为先进智能、情感计算、智能机器人等,电子信箱:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kjdb/CN/10.3981/j.issn.1000-7857.2025.12.00014
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏