A clustering-based text supervision checking method, device and computer equipment

By adopting a cluster-based text supervision and inspection method, the problems of low efficiency and insufficient accuracy in text analysis of supervision and inspection archives are solved. It achieves accurate classification of text analysis under low resource requirements, provides an intelligent text analysis assistant, and supports supervision and inspection management.

CN115269839BActive Publication Date: 2026-06-02NAT UNIV OF DEFENSE TECH
2 Cites 0 Cited by

Patent Information

Application Number
CN202210860421.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-07-21
Publication Date
2026-06-02
Estimated Expiration
2042-07-21

AI Technical Summary

Technical Problem

Existing methods for analyzing supervisory and inspection archives are inefficient and highly subjective. Furthermore, existing machine learning methods are not suitable for fields with insufficient historical labeled data, have high computational hardware requirements, and lack lightweight intelligent classification methods for textual issues.

Method used

The clustering-based text supervision and inspection method achieves accurate classification of text clusters through feature word extraction, weight calculation, clustering, and chi-square statistics optimization. This includes the calculation of feature word weight sets and clustering calculations, and the optimization of classification results in conjunction with business logic.

Benefits of technology

It improves the accuracy and efficiency of text analysis with low computing resource requirements, supports direct processing from paper or spreadsheets, is suitable for various data accumulation scenarios, provides an intelligent text analysis assistant, and supports supervision and management.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application relates to a clustering-based text supervision checking method and device and a computer device. Feature word sets corresponding to a plurality of question description texts in a question list are obtained by respectively extracting feature words from the question description texts. The word frequency of each feature word in the question description text, the first inverse document frequency in all question description texts and the second inverse document frequency in all checked units are respectively calculated to obtain a feature word weight set of the question description text of each checked unit. A plurality of question description text clusters and a plurality of initial high-correlation-degree feature word sets corresponding to the question description text clusters are obtained through clustering. Finally, the initial high-correlation-degree feature word set is optimized according to a chi-square statistic to obtain an accurate high-correlation-degree feature word set. The method saves the calculation resources while ensuring the accuracy of the results by optimizing the feature word weight calculation, adopting a clustering algorithm for preliminary clustering and optimizing the clustering results through chi-square statistics.
Need to check novelty before this filing date? Find Prior Art