Heterogeneous graph-based user mental health monitoring method and system

A mental health and user technology, applied in health index calculation, data processing application, electrical digital data processing, etc., can solve problems such as unresolved personality portraits, and achieve the effect of strengthening positive effects, improving accuracy, and making accurate judgments

Active Publication Date: 2021-09-03
ANHUI UNIVERSITY
View PDF12 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004]However, none of the above-mentioned existing literatures has solved how to use heterogeneous graphs to establish a user's personality portrait, and combine th

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Heterogeneous graph-based user mental health monitoring method and system
  • Heterogeneous graph-based user mental health monitoring method and system
  • Heterogeneous graph-based user mental health monitoring method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0084] Such as figure 1 and figure 2 As shown, a user mental health monitoring method based on a heterogeneous graph includes the following steps:

[0085] 1. Collect text data from various platforms, rely on crowdsourcing technology and crowdsourcing platforms, establish emotion training sets, learn and optimize emotion classifier BERT model and behavior word recognition BERT+CRF model, as follows:

[0086] 1-1. Crawl massive amounts of text data from platforms with high probability of expressing emotions, such as Weibo, Douban movie reviews, and Netease cloud music reviews;

[0087] 1-2. Divide the crawled text into phrase levels, mark the phrases with emotional categories through crowdsourcing, and then perform truth-value inference, and divide the obtained data into training data and test data in a ratio of 7:3 for use in Train the sentiment classifier BERT model;

[0088] 1-3. Input the data into the emotion classifier BERT model, learn and optimize the emotion classi...

Embodiment 2

[0123] A user mental health monitoring system based on a heterogeneous graph, including:

[0124] The model optimization module is used to collect text data from various platforms, rely on crowdsourcing technology and crowdsourcing platforms, establish emotion training sets, learn and optimize emotion classifier BERT model and action word recognition BERT+CRF model;

[0125] Time-series personality meta-structure building module, which is used to describe the personality network model of the relationship between the big-five personality, emotion and behavior according to the psychological Big Five personality theory system, and establish a time-series personality meta-structure;

[0126] The user personality portrait building module is used to construct a user's heterogeneous graph through the user's historical social network text data, using the emotion classifier BERT model and the behavior word recognition BERT+CRF model to discover user emotions and behaviors, combined with...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a user mental health monitoring method based on a heterogeneous graph and a system, belongs to the technical field of data processing and analysis, and solves the problem of how to establish a personality portrait of a user by adopting the heterogeneous graph through social network text information of the user and physiological information of wearable equipment and carry out detection and early warning on a mental health state of the user. A heterogeneous graph is constructed through text information, personality analysis is carried out on a user by analyzing emotion expressed by a text and user behaviors extracted from the text, so that a user personality portrait is established, text content published by the user in real time is analyzed in combination with the personality portrait, and if the text content is different from a normal state, the physiological information provided by the wearable device of the user is combined for verification, and the mental health state of the user is pre-warned, so that the accuracy of mental health intervention of the user is improved, and the positive effect of mental health monitoring of the user is enhanced.

Description

technical field [0001] The invention belongs to the technical field of data processing and analysis, and relates to a user mental health monitoring method and system based on a heterogeneous graph. Background technique [0002] Mental health refers to all aspects of the mind and the process of activities in a good or normal state. With the development of the economy and the intensification of competition, the pace of people's life and work is getting faster and faster. For Chinese people who are in the period of economic transition, there is no doubt that they need to bear greater psychological pressure. The number of people suffering from psychological problems in China will continue to increase, especially problems such as population loss brought about by social changes, urbanization, tense working environment, and one-child families will increase people's psychological pressure. However, the current society generally has insufficient acceptance of psychologists and insu...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G16H50/30G16H50/20G06F40/289G06K9/62G06Q50/00
CPCG16H50/30G16H50/20G06F40/289G06Q50/01G06F18/24G06F18/214
Inventor 王庆人严康李炜张以文颜登程许正
Owner ANHUI UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap