A text similarity calculation method and device, electronic equipment and storage medium

By directly extracting text feature vectors from images and calculating similarity, the problem of low OCR recognition efficiency in existing technologies is solved, achieving high efficiency and accuracy in judging the leakage of sensitive information.

CN116543397BActive Publication Date: 2026-07-03BEIJING WANLIHONG TECH CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING WANLIHONG TECH CO LTD
Filing Date
2023-05-19
Publication Date
2026-07-03

Smart Images

  • Figure CN116543397B_ABST
    Figure CN116543397B_ABST
Patent Text Reader

Abstract

This application relates to a text similarity calculation method, apparatus, electronic device, and storage medium, relating to the field of text matching. The method includes acquiring an image to be identified; determining whether at least one text segment exists in the image to be identified; if at least one text segment exists, determining a text image from the image to be identified, wherein the text image includes at least one text segment; extracting feature vectors from the text image to obtain text feature vectors; and calculating a preset sensitive information feature vector and the similarity between the text feature vectors. This application can improve the efficiency of determining and calculating the similarity between texts.
Need to check novelty before this filing date? Find Prior Art