Target user detection method, apparatus, terminal and electronic device

By constructing a tree structure of user communication behavior statistics and using a tree edit distance algorithm, the problems of low efficiency and accuracy in user similarity evaluation are solved, achieving efficient and accurate user similarity identification and cross-regional analysis.

CN118828627BActive Publication Date: 2026-06-16CHINA MOBILE GROUP ZHEJIANG +3
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHINA MOBILE GROUP ZHEJIANG
Filing Date
2023-09-05
Publication Date
2026-06-16

AI Technical Summary

⚠Technical Problem

Existing technologies for user similarity evaluation have low efficiency and accuracy, relying on text analysis or base station location information, resulting in low computational efficiency and limited applicability.

⚗Method used

By constructing user communication behavior statistics into a tree structure, the tree edit distance algorithm is used to determine the similarity between users, avoiding complex text analysis and base station location dependence. The weight of each communication behavior statistics is considered to improve the efficiency and accuracy of similarity evaluation.

🎯Benefits of technology

It achieves efficient and accurate evaluation of user communication behavior similarity, identifies target users with similar communication behaviors, is suitable for cross-regional analysis, does not require user authorization, and has a wide range of applications.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118828627B_ABST
    Figure CN118828627B_ABST
Patent Text Reader

Abstract

The application relates to the technical field of communication, and provides a target user detection method and device, a terminal and electronic equipment. The method comprises the following steps: constructing a first communication object tree according to communication behavior statistical data of a user to be detected; determining the similarity between the first communication object tree and a second communication object tree of a reference user based on a tree edit distance algorithm; and determining that the user to be detected is a target user with similar communication behavior to the reference user when the similarity is greater than a preset similarity threshold. The target user detection method provided by the application can evaluate the similarity of user communication behavior, mine target users with similar communication behavior to the reference user, so as to accurately serve and analyze the target users, and improve the efficiency and accuracy of user similarity evaluation.
Need to check novelty before this filing date? Find Prior Art