Mental health state evaluation method

Abstract

The invention provides a mental health state evaluation method. The method comprises steps of using a machine learning method to build and train a network behavior characteristic-based mental health state evaluation model on the basis of individual network behavior characteristics and demographic characteristics of a known sample, and acquiring the network behavior characteristics and demographic characteristics of a new individual and acquiring the mental health state of the new individual according to the network behavior characteristic-based mental health state evaluation model. According to the mental health state evaluation method, influences of individual subjective factors on data acquisition can be eliminated, and mental health state evaluation can be more accurately carried out. In addition, needed individual data for mental health state evaluation acquisition can be more conveniently acquired, large-scale individual data acquisition can be carried out in a wider range, and large-scale mental health state evaluation can be realized.

Description

technical field [0001] The present invention relates to the technical field of mental health status evaluation and Internet, in particular, the invention relates to a mental health status evaluation method. Background technique [0002] At present, in the world, mental health problems have become the primary cause of individual "disability", and its negative consequences account for 37% of all disease hazards. Combined with its "global", " According to the development trend of "chronic" and "prevalent", the existence of mental health problems will not only cause huge consumption and waste of social resources, increase the burden on the whole society, but also directly threaten the health of individuals. Quality of daily life and subjective well-being. Specific to the actual situation in our country, according to the survey and research results, the overall level of people's mental health is also not optimistic, and the overall incidence of mental health problems has reached...

AI Technical Summary

Problems solved by technology

Although some of the subjective bias factors can be checked through some control methods (for example, validity scales, experimental design), it is very cumbersome and inefficient to implement similar controls repeatedly in similar studies, and some invalid data cannot be ruled out (for example, wrong answer, missing answer, blind answer)

[0007] (2) The details and scale of the collected data are limited

First of all, due to the constraints of time and space and some social conditions, it is difficult to recruit a sufficient number of individuals to fill in the scale for each experiment, and it is also difficult to track and measure the same group of individuals

Secondly, in order to facilitate individuals to complete the survey, it is impossible to design a large number of items on the scale, so that more details of individual behavior samples cannot be collected

In addition, the distribution, collection and entry of scales have also brought adverse effects on large-scale data collection.

Images