A method and system for automatic open identification of archives based on semantic analysis

Abstract

The invention discloses a semantic analysis-based file automatic open identification method and system, wherein the method includes: obtaining batch set of file information to be identified; converting the batch set of file information to be identified into batch set plain text file information; Batches of plain text file information are input into the format semantic library to obtain the first training result and the second training result; the second batch of plain text file information is input into the keyword library to obtain the third training result and the fourth training result; the fourth training result is obtained Enter the batches of plain text file information into the semantic knowledge base to obtain the fifth training result and the sixth training result; send the sixth batch of plain text file information to the manual review terminal for content semantic review, and generate the first review result; obtain open Profile information. It solves the technical problem in the prior art that the file is openly identified based on a single optical character recognition technology, so that the identification result has the defects of high misjudgment rate and low accuracy rate.

Description

technical field [0001] The invention relates to the technical field of file open identification, in particular to a semantic analysis-based automatic file open identification method and system. Background technique [0002] The fundamental purpose of archives work is to integrate various archives information resources to facilitate the use of the public. Opening archives is the most basic and important way for the public to obtain and utilize archives information. With the rapid development of science and technology, electronic information technology has also brought great changes to archives work. The introduction and application of new technologies will not change the fundamental purpose of archives work, but to serve the public more efficiently and conveniently. [0003] However, in the process of realizing the technical solution of the invention in the embodiment of the present application, the inventor of the present application found that the above-mentioned technology...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a method and system for automatic opening and identification of files based on semantic analysis, which solves the problem of opening and identifying files based on a single optical character recognition technology in the prior art, so that the identification results have a high misjudgment rate and are accurate. For the technical problem of defects with a low rate, the files to be identified are converted into plain text files based on the character recognition system, and then the first round of format retrieval is performed based on the format semantic database, and the second round of keyword retrieval is performed based on the keyword database. The third round of preset semantic retrieval is performed based on the semantic knowledge base, and finally the openable files are sent to the manual review terminal for the last line of manual review to ensure the accuracy of file open identification without increasing the cost of identification. , the technical effect of further improving the accuracy and coverage of open file identification

Images