Data processing method and device for human-computer interaction and electronic equipment

CN121680707BActive Publication Date: 2026-04-28UNIV OF SCI & TECH OF CHINA
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
UNIV OF SCI & TECH OF CHINA
Filing Date
2026-02-10
Publication Date
2026-04-28

AI Technical Summary

Technical Problem

In existing technologies, when relying on fixed speed or acceleration thresholds to preprocess the trajectory of input devices, it is difficult to accurately capture the true boundaries of changes in user behavior, resulting in inaccurate segmentation results and an inability to effectively distinguish complex and subtle interactive behaviors.

Method used

An initial weighted undirected chain graph related to the mouse trajectory sequence is constructed, its structural entropy is calculated, and trajectory segmentation is performed based on the structural entropy. Combined with differential information enhancement and fusion processing, fine-grained and adaptive trajectory subsequences are obtained.

Benefits of technology

It enables precise segmentation of complex and subtle interactive behaviors, improves the consistency and reliability of segmentation results, and provides high-quality data support for user identity authentication.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121680707B_ABST
    Figure CN121680707B_ABST
Patent Text Reader

Abstract

The application provides a data processing method and device for human-computer interaction and electronic equipment, and applies to the technical field of computers. The method comprises the following steps: constructing an initial weighted undirected chain graph related to a mouse track sequence; calculating a first structure entropy of the initial weighted undirected chain graph; for each edge in the initial weighted undirected chain graph, calculating a second structure entropy of a new weighted undirected chain graph obtained by assuming that each edge is deleted; based on the first structure entropy and a plurality of second structure entropies, performing track segmentation on the mouse track sequence to obtain a plurality of mouse track subsequences; and performing differential information enhancement processing on the plurality of mouse track subsequences respectively, and performing fusion processing on the processed plurality of mouse track subsequences to obtain a target mouse track sequence.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Continuous identity authentication method, medium and system based on mouse interaction behavior

    CN114662069A

  • Random number generation method, system and equipment based on mouse sliding track and medium

    CN118963701A