Conversational AI Therapist for Daily Function Screening in Home Environments

Conversational AI Therapist for Daily Function Screening in Home Environments
复制标题

用于家庭环境中日常功能筛查的对话式人工智能治疗师

DOI:
10.1145/3539490.3539603
复制
发表时间:
2022
期刊:
IASA '22: Proceedings of the 1st ACM International Workshop on Intelligent Acoustic Systems and Applications
影响因子:
--
通讯作者:
Jiang, Xiaofan
Jiang, Xiaofan
中科院分区:
--
文献类型:
--
作者:
Nie, Jingping;Shao, Hanya;Zhao, Minghui;Xia, Stephen;Preindl, Matthias;Jiang, Xiaofan

文献摘要

参考文献

被引文献

相似文献

智能设备的增长正在使典型的家庭变得更加智能。在这项工作中,我们与治疗师合作,介绍了一位基于家庭的AI治疗师,该治疗师利用智能家居环境来筛选日常功能并推断居住者的心理健康。与现有的通过对话识别用户精神状态的聊天机器人工作不同,我们的人工智能治疗师还利用家庭中的智能设备和传感器来推断心理健康,并评估用户的日常功能。我们提出了一系列37个维度的日常功能,我们的系统通过与用户交谈并使用传感器和智能传感器检测家庭中的日常活动事件来观察这些维度。我们的系统结合新的自然语言处理架构利用这37个维度来检测精神状态(例如,愤怒或抑郁)、幸福感和日常功能方面的异常,并在检测到异常时生成对控制台用户的响应。通过一系列的用户研究,我们证明我们的系统能够自然地与用户对话,准确地检测幸福感中的异常,并提供适当的响应来安慰用户。
The growth of smart devices is making typical homes more intelligent. In this work, in collaboration with therapists, we introduce a home-based AI therapist that takes advantage of the smart home environment to screen the day-to-day functioning and infer mental wellness of an occupant. Unlike existing “chatbot” works that identify the mental status of users through conversation, our AI therapist additionally leverages smart devices and sensors throughout the home to infer mental well-being and assesses a user's daily functioning. We propose a series of 37 dimensions of daily functioning, that our system observes through conversing with the user and detecting daily activity events using sensors and smart sensors throughout the home. Our system utilizes these 37 dimensions in conjunction with novel natural language processing architectures to detect abnormalities in mental status (e.g., angry or depressed), well-being, and daily functioning and generate responses to console users when abnormalities are detected. Through a series of user studies, we demonstrate that our system can converse with a user naturally, accurately detect abnormalities in well-being, and provide appropriate responses consoling users.
DOI: 10.1016/j.japh.2017.02.023
发表时间: 2017-05-01
影响因子: 2.1
作者:
Bible, Lisa J.;Casper, Kristin A.;Porter, Kyle A.
通讯作者: Porter, Kyle A.
DOI: 10.1177/0886260507312942
发表时间: 2008-04-01
影响因子: 2.5
作者:
Helfrich, Christine A.;Fujiura, Glenn T.;Rutkowski-Kmitta, Violet
通讯作者: Rutkowski-Kmitta, Violet
别再节食了!
DOI: 10.1002/9781119487142.ch8
发表时间: 2006
期刊: U.S. news & world report
影响因子: --
作者:
A. Spake
通讯作者: A. Spake
SPINDLES:用于腿部抖动检测的自适应个性化系统
DOI: --
发表时间: 2018
期刊: Smart Health
影响因子: --
作者:
S. Xia;Peter Wei;Jordan Vega;Xiaofan Jiang
通讯作者: Xiaofan Jiang
语音转文字
DOI: --
发表时间: 2021
期刊: Text as Data
影响因子: --
作者:
Anish Ashirgade;Head Celebal;Tech. Singapore
通讯作者: Tech. Singapore