Method, device and system for processing specification documents based on configuration files

Abstract

The embodiment of the present application discloses a configuration file-based specification document processing method, device and system, using at least one extraction tree and an editable configuration file; the extraction tree includes a plurality of nodes, and the nodes include The expression matched by the node; the configuration file contains multiple configurations, including identity extraction configuration, document segmentation configuration and element extraction configuration. According to the configuration of the identity extraction class in the configuration file, the identity of the document is extracted from the normative document; according to the configuration of the document slicing class, the normative document with known document identity is divided into multiple content blocks; according to the configuration of the element extraction class, from each Extract document elements from the content block. Since this application uses an editable configuration file, as long as the content of the configuration file is edited, the document elements extracted from the standard document can be changed, so that it can adapt to different requirements for extracting document elements and has strong adaptability.

Description

technical field [0001] The present application relates to the technical field of natural language processing, in particular to a configuration file-based specification document processing method, device and system. Background technique [0002] A normative document (also called a special document) refers to a professional document of a specific format given to an individual or company in a specific legal environment or business environment. The normative document usually has an agreed-upon format and structural framework. Specification documents are usually used to express a specified type of information and have a specific purpose. For example, in the legal field, the judgment documents used by the court record the detailed information of the case in a specified format; in the commercial field, the insurance contract also records the various agreed terms contained in the insurance in a standardized format. [0003] Since normative documents contain information with specifi...

AI Technical Summary

Problems solved by technology

However, the normative document extraction program in the prior art is written for specific normative documents, and different extraction programs need to be written for normative documents in different fields and purposes, and the extraction content of document elements is usually solidified in the extraction program , it is not easy to modify, and the program must be recompiled and released every time it is modified, or even refactored

However, for practitioners in related fields, according to different actual needs, the demand for document elements will also change, which requires that the normative document processing method can be adaptively modified according to the needs of users. It can be seen that the above-mentioned prior art The standard document processing method cannot meet the needs of users because it is not easy to modify, so the applicability is poor

Images