Document atlas extraction method and device based on machine learning and storage medium

Abstract

The invention discloses a document atlas extraction method and device based on machine learning and a storage medium. The method comprises the steps of obtaining a document text, wherein the documenttext comprises a document title, a document body and document content; carrying out fragmentization processing on the document text to obtain fragmentized data; and according to the fragmented data, extracting a document map by using a trained knowledge unit classification model. According to the method, the trained knowledge unit classification model is used for extracting the document text to obtain structured document atlas data, the document atlas of the brain graph structure can be automatically formed, the document content is clear at a glance, the reading time can be greatly shortened,and the reading quality is improved. The method can be widely applied to the technical field of knowledge maps.

Description

technical field

[0001] The present invention relates to the technical field of knowledge graphs, in particular to a method, device and storage medium for extracting document graphs based on machine learning. Background technique

[0002] A knowledge graph is a language network that reveals the relationship between entities. It is usually used to describe the relationship between objects, people, institutions, cities, etc. in the real world, and is used for intelligence analysis, semantic search, intelligent question answering, and recommendation systems. The core point of the knowledge map is to collect a series of large-scale structured or unstructured data, analyze and model the data based on domain expertise, and find out the rules through machine calculations to generate calculation rules for relevant data. Many concepts in documents are not entities, and are usually intangible concepts. Existing knowledge map technology cannot decompose a document into a structured, min...

Images