User portrait generation method and device, electronic equipment and storage medium

CN120873473APending Publication Date: 2025-10-31CHINA UNITED NETWORK COMM GRP CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202510990349.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-17
Publication Date
2025-10-31

AI Technical Summary

Technical Problem

In existing technologies, called number user profiling relies on single-dimensional data such as call duration and call frequency, which cannot fully reflect the user's real needs and characteristics, resulting in insufficient accuracy of user profiles.

Method used

By acquiring decrypted target call audio and text, features are extracted using a multimodal fusion model and input into a user profile generation model to generate a set of user profile tags. Data protection is then achieved by combining blockchain and encryption technologies.

Benefits of technology

This improves the accuracy of user profiles, enabling them to more comprehensively reflect users' real needs and characteristics, while ensuring data privacy and security.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120873473A_ABST
    Figure CN120873473A_ABST
Patent Text Reader

Abstract

The invention provides a user portrait generation method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring a decrypted target call audio and a target call text corresponding to the target call audio; the target call text is desensitized text data; the target call audio is the call audio of a target user of which the user portrait is to be generated or updated; performing feature extraction processing and feature fusion processing on the target call audio and the target call text by adopting a preset multi-modal fusion model to generate corresponding multi-modal fusion features; inputting the multi-modal fusion features into a preset user portrait generation model to generate a user portrait tag set corresponding to the target call audio; and generating or updating a user portrait corresponding to the target user based on the user portrait label set. According to the user portrait generation method, the accuracy of the user portrait is improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Cited By

  • User portrait and demand prediction generation method, electronic equipment, medium and product

    CN122114997A