The Method of Realizing the Automatic Appraisal of the Value of Documents and Archives

Abstract

The invention relates to a method for automatically authenticating the value of documentary archives. The method includes the steps that the keywords of the tile and the full text of a documentary archive are extracted respectively; keyword distribution is conducted according to a controlled word list to obtain a keyword set; the keyword distribution result is calculated and discriminated, the archiving class is determined through keyword weight word frequency calculation, the retention period is determined through automatic annotation classification calculation, and then a first conclusion and a second conclusion which include the archiving class and the retention period respectively are obtained; the archiving class and the retention period are comprehensively recommended. A keyword base with the documentary archive retention value as the theme is built, the keywords in the tile and the document are extracted according to a related file, the archiving class of the documentary archive is determined, a means is provided for automatically authenticating the value of a large batch of documentary archives, the concurrent operation of authenticating the retention value of multiple documentary archives can be achieved, and the efficiency of authenticating the value of the documentary archives is improved.

Description

technical field [0001] The invention relates to the field of analysis and processing of Chinese electronic documents, in particular to a method for realizing the automatic appraisal of document archives value. Background technique [0002] Documentary archives are the customary titles of government agencies, groups, enterprises and institutions for files transformed from general documents generated in administrative management activities, and are generally managed by archives departments. The work of appraising the value of archives is a work commonly known as "two distinctions", that is, to distinguish which ones need to be preserved and which ones do not need to be preserved, that is, to distinguish "preservation" and "destruction". It is clear how long the documents and files that should be kept should be kept, and the storage period for the corresponding documents and files should be defined. At present, all agencies and units use manual definition to divide the storage...

AI Technical Summary

Problems solved by technology

However, the flow of clerical personnel is large, and there are often errors in the scope of filing and storage period settings, resulting in the inability to accumulate long-term work experience in value appraisal

At present, there is a lack of representative empirical data in the industry to support the development of document and archive value appraisal automation.

[0006] 2. Use the method of measuring the similarity of keywords (words) of documents and archives to realize the automatic recommendation of the value appraisal of documents and archives. At present, this technology is still blank in the industry

[0008] The traditional method only relies on the statistical information of vocabulary to extract keywords (words), and does not take into account the impact of the keyword (word) extraction of the topic degree of the industry to which the document belongs

From the business perspective of the archives industry, the industry has not yet established a complete keyword (word) recommendation and tagging system with the theme of document and archive preservation value, let alone a set of "automatic recommendation" solutions for the preservation value of documents and archives

Images