Text detection method and device, electronic equipment and storage medium

By performing entity extraction and target character conversion on the original character string, the problem of difficulty in detecting drainage information in the prior art is solved, and higher detection accuracy and network security are achieved.

CN119647477AActive Publication Date: 2025-03-18BEIJING BAIDU NETCOM SCI & TECH CO LTD +1
8 Cites 0 Cited by

Patent Information

Application Number
CN202411819687.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-11
Publication Date
2025-03-18
Estimated Expiration
2044-12-11

AI Technical Summary

Technical Problem

The prior art is difficult to accurately detect whether additional information is present for drainage of a character string, especially because the characters are transformed in many ways and the transformation speed is fast.

Method used

By extracting the original character string to be detected, the target character string and its body category are obtained. Based on the similarity between the entity category and the candidate character set, the target character is converted into characters before the variant, and the converted character string is obtained, and the detection result of the original string is finally determined.

Benefits of technology

It improves detection accuracy, can more accurately identify and intercept content containing drainage information, and enhances the security of the network platform.

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

Abstract

The invention provides a text detection method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence, in particular to the fields of deep learning, knowledge maps and the like. According to the specific implementation scheme, entity extraction is conducted on an original character string according to features of all characters in the original character string to be detected, a target character string with variants in the original character string is obtained, and the entity category of the target character string is obtained; according to the entity category and the similarity between each candidate character in the candidate character set and the target character, the target character is converted into a character before a variant, and a converted character string is obtained; wherein the target character is a character in the target character string; and determining a detection result of the original character string according to the converted character string.
Need to check novelty before this filing date? Find Prior Art