Writing content processing method and device and computer equipment

CN120805919APending Publication Date: 2025-10-17北京大学长沙计算与数字经济研究院 +1
0 Cites 0 Cited by

Patent Information

Application Number
CN202510856882.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-25
Publication Date
2025-10-17

AI Technical Summary

Technical Problem

Traditional psychological assessment methods rely on psychological assessment scales, which are easily affected by respondents' incorrect or incomplete answers or misunderstandings of questions/options, resulting in low accuracy in mental health risk assessment.

Method used

By extracting at least one dimension of target features from users' writing content, including emotion, cognitive patterns, narrative structure, and meaning construction, psychological language feature models and graph neural networks are used to predict mental health risks.

Benefits of technology

It improves the accuracy of mental health risk assessment, reduces users' incorrect and missing answers on the scale, reduces the stigma associated with mental illness, and enables a more natural and authentic expression of mental health status.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120805919A_ABST
    Figure CN120805919A_ABST
Patent Text Reader

Abstract

The invention relates to a writing content processing method and device and computer equipment. The method comprises the steps of obtaining writing content of a user; performing semantic feature extraction on the writing content to obtain target features of at least one dimension; wherein the target features of at least one dimension comprise at least one of a first dimension feature, a second dimension feature, a third dimension feature or a fourth dimension feature, the first dimension feature is used for representing an emotion expressed in the writing content, the second dimension feature is used for representing a cognitive mode expressed in the writing content, and the fourth dimension feature is used for representing a cognitive mode expressed in the writing content. The third dimension feature is used for representing a narrative structure in the writing content, and the fourth dimension feature is used for representing significance construction of the user for an event in the writing content; and performing mental health risk prediction according to the target features of the at least one dimension to obtain a prediction result. The method can improve the accuracy of mental health risk prediction.
Need to check novelty before this filing date? Find Prior Art