1,068
个编辑
更改
跳到导航
跳到搜索
第4行：
第4行： − {{short description|Area of research in computer science aiming to understand the emotional state of users}} − + 第30行：
第29行： − + − '''情感计算''' '''Affective computing （'''也被称为人工情感智能或情感AI）是基于系统和设备的研究和开发来识别、理解、处理和模拟人的情感。这是一个融合'''计算机科学'''、'''心理学'''和'''认知科学'''的跨学科领域<ref name="TaoTan" />。虽然该领域的一些核心思想可以追溯到早期对情感<ref name=":0" />的哲学研究，但计算机科学的现代分支研究起源于罗莎琳德·皮卡德1995年关于情感计算的论文<ref name=":1" />和她的由麻省理工出版社<ref name=":2" /><ref name=":3" /> 出版的《情感计算》<ref name="Affective Computing" /> 。这项研究的动机之一是赋予机器情感智能，包括具备'''同理心'''。机器应能够解读人类的情绪状态，适应人类的情绪，并对这些情绪作出适当的反应。+ − + − === 检测和识别情感信息 ===+ − Detecting emotional information usually begins with passive [[sensors]] that capture data about the user's physical state or behavior without interpreting the input. The data gathered is analogous to the cues humans use to perceive emotions in others. For example, a video camera might capture facial expressions, body posture, and gestures, while a microphone might capture speech. Other sensors detect emotional cues by directly measuring [[physiological]] data, such as skin temperature and [[galvanic skin response|galvanic resistance]].<ref name=":4">{{cite journal 第50行：
第48行： − + − − 检测情感信息通常从被动式'''传感器'''开始，这些传感器捕捉关于用户身体状态或行为的数据，而不解释输入信息。收集的数据类似于人类用来感知他人情感的线索。例如，摄像机可以捕捉面部表情、身体姿势和手势，而麦克风可以捕捉语音。一些传感器可以通过直接测量生理数据(如皮肤温度和电流电阻)来探测情感信号<ref name=":4" />。 − Recognizing emotional information requires the extraction of meaningful patterns from the gathered data. This is done using machine learning techniques that process different [[Modality (human–computer interaction)|modalities]], such as [[speech recognition]], [[natural language processing]], or [[face recognition|facial expression detection]]. The goal of most of these techniques is to produce labels that would match the labels a human perceiver would give in the same situation: For example, if a person makes a facial expression furrowing their brow, then the computer vision system might be taught to label their face as appearing "confused" or as "concentrating" or "slightly negative" (as opposed to positive, which it might say if they were smiling in a happy-appearing way). These labels may or may not correspond to what the person is actually feeling. − Another area within affective computing is the design of computational devices proposed to exhibit either innate emotional capabilities or that are capable of convincingly simulating emotions. A more practical approach, based on current technological capabilities, is the simulation of emotions in conversational agents in order to enrich and facilitate interactivity between human and machine.<ref name=":5">{{Cite book|last=Heise|first=David|contribution=Enculturating agents with expressive role behavior|year=2004|title=Agent Culture: Human-Agent Interaction in a Mutlicultural World|editor1=Sabine Payr|pages=127–142|publisher=Lawrence Erlbaum Associates|editor2-first=Robert |editor2-last=Trappl}}</ref> − − 情感计算的另一个研究领域是设计出能够展示天然的感情（或令人信服地模拟情感）的计算设备。基于当前的技术，一个更加可行的方法是模拟对话机器人的情感，以丰富和促进人与机器之间的互动<ref name=":5" />。 − [[Marvin Minsky]], one of the pioneering computer scientists in [[artificial intelligence]], relates emotions to the broader issues of machine intelligence stating in ''[[The Emotion Machine]]'' that emotion is "not especially different from the processes that we call 'thinking.'"<ref name=":6">{{cite news|url=https://www.washingtonpost.com/wp-dyn/content/article/2006/12/14/AR2006121401554.html|title=Mind Over Matter|last=Restak|first=Richard|date=2006-12-17|work=The Washington Post|access-date=2008-05-13}}</ref>+ − + − In psychology, cognitive science, and in neuroscience, there have been two main approaches for describing how humans perceive and classify emotion: continuous or categorical. The continuous approach tends to use dimensions such as negative vs. positive, calm vs. aroused.
无编辑摘要
}}
}}
'''Affective computing''' is the study and development of systems and devices that can recognize, interpret, process, and simulate human [[Affect (psychology)|affects]]. It is an interdisciplinary field spanning [[computer science]], [[psychology]], and [[cognitive science]].<ref name=TaoTan>{{cite conference |first=Jianhua |last=Tao |author2=Tieniu Tan |title=Affective Computing: A Review |book-title=Affective Computing and Intelligent Interaction |volume=[[LNCS]] 3784 |pages=981–995 |publisher=Springer |year=2005 |doi=10.1007/11573548 }}</ref> While some core ideas in the field may be traced as far back as to early philosophical inquiries into [[Emotion#The James-Lange Theory|emotion]],<ref name=":0">{{cite journal |last=James |first=William |year=1884 |title=What Is Emotion |journal=Mind |volume=9 |issue=34 |pages=188–205 |doi=10.1093/mind/os-IX.34.188|url=https://zenodo.org/record/1431811 }} Cited by Tao and Tan.</ref> the more modern branch of computer science originated with [[Rosalind Picard]]'s 1995 paper<ref name=":1">[http://affect.media.mit.edu/pdfs/95.picard.pdf "Affective Computing"] MIT Technical Report #321 ([http://vismod.media.mit.edu/pub/tech-reports/TR-321-ABSTRACT.html Abstract]), 1995</ref> on affective computing and her book ''Affective Computing''<ref name="Affective Computing">{{cite book|last1=Picard|first1=Rosalind|title=Affective Computing|date=1997|publisher=MIT Press|location=Cambridge, MA|page=1}}</ref> published by [[MIT Press]].<ref name=":2">
'''情感计算''' '''Affective computing （'''也被称为人工情感智能或情感AI）是基于系统和设备的研究和开发来识别、理解、处理和模拟人的情感。这是一个融合'''计算机科学'''、'''心理学'''和'''认知科学'''的跨学科领域<ref name=TaoTan>{{cite conference |first=Jianhua |last=Tao |author2=Tieniu Tan |title=Affective Computing: A Review |book-title=Affective Computing and Intelligent Interaction |volume=[[LNCS]] 3784 |pages=981–995 |publisher=Springer |year=2005 |doi=10.1007/11573548 }}</ref>。虽然该领域的一些核心思想可以追溯到早期对情感<ref name=":0">{{cite journal |last=James |first=William |year=1884 |title=What Is Emotion |journal=Mind |volume=9 |issue=34 |pages=188–205 |doi=10.1093/mind/os-IX.34.188|url=https://zenodo.org/record/1431811 }} Cited by Tao and Tan.</ref> 的哲学研究，但计算机科学的现代分支研究起源于罗莎琳德·皮卡德1995年关于情感计算的论文<ref name=":1">[http://affect.media.mit.edu/pdfs/95.picard.pdf "Affective Computing"] MIT Technical Report #321 ([http://vismod.media.mit.edu/pub/tech-reports/TR-321-ABSTRACT.html Abstract]), 1995</ref>和她的由麻省理工出版社<ref name=":2">
{{cite web
{{cite web
|url=http://ls12-www.cs.tu-dortmund.de//~fink/lectures/SS06/human-robot-interaction/Emotion-RecognitionAndSimulation.pdf
|url=http://ls12-www.cs.tu-dortmund.de//~fink/lectures/SS06/human-robot-interaction/Emotion-RecognitionAndSimulation.pdf
|quote= Rosalind Picard, a genial MIT professor, is the field's godmother; her 1997 book, ''Affective Computing'', triggered an explosion of interest in the emotional side of computers and their users.
|quote= Rosalind Picard, a genial MIT professor, is the field's godmother; her 1997 book, ''Affective Computing'', triggered an explosion of interest in the emotional side of computers and their users.
| archive-url= https://web.archive.org/web/20080518185630/http://www.wired.com/wired/archive/11.12/love.html| archive-date= 18 May 2008 | url-status= live}}
| archive-url= https://web.archive.org/web/20080518185630/http://www.wired.com/wired/archive/11.12/love.html| archive-date= 18 May 2008 | url-status= live}}
</ref> One of the motivations for the research is the ability to give machines emotional intelligence, including to simulate [[empathy]]. The machine should interpret the emotional state of humans and adapt its behavior to them, giving an appropriate response to those emotions.
</ref>出版的《情感计算》<ref name="Affective Computing">{{cite book|last1=Picard|first1=Rosalind|title=Affective Computing|date=1997|publisher=MIT Press|location=Cambridge, MA|page=1}}</ref>。这项研究的动机之一是赋予机器情感智能，包括具备'''同理心'''。机器应能够解读人类的情绪状态，适应人类的情绪，并对这些情绪作出适当的反应。
== 研究范围 ==
= 研究范围 =
=== 检测和识别情感信息 ===
检测情感信息通常从被动式'''传感器'''开始，这些传感器捕捉关于用户身体状态或行为的数据，而不解释输入信息。收集的数据类似于人类用来感知他人情感的线索。例如，摄像机可以捕捉面部表情、身体姿势和手势，而麦克风可以捕捉语音。一些传感器可以通过直接测量生理数据(如皮肤温度和电流电阻)来探测情感信号<ref name=":4">{{cite journal
| last = Garay
| last = Garay
| first = Nestor
| first = Nestor
| access-date = 2008-05-12
| access-date = 2008-05-12
| archive-url= https://web.archive.org/web/20080528135729/http://www.humantechnology.jyu.fi/articles/volume2/number1/2006/humantechnology-april-2006.pdf| archive-date= 28 May 2008 | url-status= live | doi=10.17011/ht/urn.2006159| doi-access = free
| archive-url= https://web.archive.org/web/20080528135729/http://www.humantechnology.jyu.fi/articles/volume2/number1/2006/humantechnology-april-2006.pdf| archive-date= 28 May 2008 | url-status= live | doi=10.17011/ht/urn.2006159| doi-access = free
}}</ref>
}}</ref>。
识别情感信息需要从收集到的数据中提取出有意义的模式。这通常要使用'''[[wikipedia:Multimodality|多模态]]'''机器学习技术，如'''语音识别'''、'''自然语言处理'''或'''面部表情检测'''等。大多数这些技术的目标是给出与人类感情相一致的标签: 例如，如果一个人做出皱眉的面部表情，那么计算机视觉系统可能会被教导将他们的脸标记为“困惑”、“专注”或“轻微消极”(与象征着积极的快乐微笑相反)。这些标签可能与人们的真实感受相符，也可能不相符。
识别情感信息需要从收集到的数据中提取出有意义的模式。这通常要使用'''[[wikipedia:Multimodality|多模态]]'''机器学习技术，如'''语音识别'''、'''自然语言处理'''或'''面部表情检测'''等。大多数这些技术的目标是给出与人类感情相一致的标签: 例如，如果一个人做出皱眉的面部表情，那么计算机视觉系统可能会被教导将他们的脸标记为“困惑”、“专注”或“轻微消极”(与象征着积极的快乐微笑相反)。这些标签可能与人们的真实感受相符，也可能不相符。
=== 机器中的情感 ===
=== 机器中的情感 ===
情感计算的另一个研究领域是设计出能够展示天然的感情（或令人信服地模拟情感）的计算设备。基于当前的技术，一个更加可行的方法是模拟对话机器人的情感，以丰富和促进人与机器之间的互动<ref name=":5">{{Cite book|last=Heise|first=David|contribution=Enculturating agents with expressive role behavior|year=2004|title=Agent Culture: Human-Agent Interaction in a Mutlicultural World|editor1=Sabine Payr|pages=127–142|publisher=Lawrence Erlbaum Associates|editor2-first=Robert |editor2-last=Trappl}}</ref>。
人工智能领域的计算机科学先驱之一[https://zh.wikipedia.org/wiki/%E9%A9%AC%E6%96%87%C2%B7%E9%97%B5%E6%96%AF%E5%9F%BA 马文•明斯基](Marvin Minsky)在[[wikipedia:The_Emotion_Machine|《情绪机器》]](The Emotion Machine)一书中将情绪与更广泛的机器智能问题联系起来。他在书中表示，情绪“与我们所谓的‘思考’过程并没有特别的不同。'"<ref name=":6" />
人工智能领域的计算机科学先驱之一[https://zh.wikipedia.org/wiki/%E9%A9%AC%E6%96%87%C2%B7%E9%97%B5%E6%96%AF%E5%9F%BA 马文•明斯基](Marvin Minsky)在[[wikipedia:The_Emotion_Machine|《情绪机器》]](The Emotion Machine)一书中将情绪与更广泛的机器智能问题联系起来。他在书中表示，情绪“与我们所谓的‘思考’过程并没有特别的不同。'"<ref name=":6">{{cite news|url=https://www.washingtonpost.com/wp-dyn/content/article/2006/12/14/AR2006121401554.html|title=Mind Over Matter|last=Restak|first=Richard|date=2006-12-17|work=The Washington Post|access-date=2008-05-13}}</ref>
== 技术 ==
== 技术 ==
在心理学、认知科学和神经科学中，描述人类如何感知和分类情绪的方法主要有两种: 连续的和分类的。连续的方法倾向于使用诸如消极与积极、平静与激动之类的维度。
在心理学、认知科学和神经科学中，描述人类如何感知和分类情绪的方法主要有两种: 连续的和分类的。连续的方法倾向于使用诸如消极与积极、平静与激动之类的维度。