File comparison method and device and medium

The file title and text are obtained through layout parsing and text recognition models, and the semantic vector model is used for similarity processing, which solves the problems of poor differences and low efficiency of conventional file comparison methods, and achieves more efficient and accurate file comparison.

CN119830890AActive Publication Date: 2025-04-15INSPUR SUZHOU INTELLIGENT TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202510076142.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-01-17
Publication Date
2025-04-15
Estimated Expiration
2045-01-17

Smart Images

  • Figure CN119830890A_ABST
    Figure CN119830890A_ABST
Patent Text Reader

Abstract

The invention discloses a file comparison method and device and a medium, and relates to the technical field of data processing. The target files are analyzed through the layout analysis model to obtain the corresponding text information, the text information is recognized through the text recognition model to obtain the corresponding file title, and the efficiency of searching the file title in the files is improved. And performing hierarchical processing on the file titles to construct a structured outline directory, and obtaining the target file titles subjected to subsequent title vector processing, so as to realize an outline comparison analysis function between the target files through the file element, namely the file titles. The semantic vector model is used for processing the target file title to obtain the corresponding title vector, and the situation that the comparison quality is reduced due to the fact that characters with similar meanings are compared manually and subjectively is avoided. The title vector parameters of the target file title of the outline catalog are adopted for similarity processing, the semantics of the whole title is concerned, and the overall difference is improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • File association method and system

    CN107844493A

  • Research report generation method and system and computer storage medium

    CN115270738A

  • Intelligent writing method, device, equipment and medium

    CN115630640A

  • Article outline generation method and device and storage medium

    CN117633214A

  • Document generation method and device, equipment and medium

    CN117725895A