Knowledge graph construction method, device, electronic equipment and medium

Abstract

The embodiment of the invention provides a knowledge graph construction method, a knowledge graph construction device, electronic equipment and a medium, belongs to the technical field of informationprocessing and aims to enable a constructed knowledge graph to have relatively high accuracy. According to the method provided by the embodiments of the invention, the method comprises the following steps of obtaining knowledge information to be classified; inputting the knowledge information to be classified into a classification model to obtain a classification result corresponding to the knowledge information to be classified output by the classification model; and adding the knowledge information to be classified into a knowledge graph according to the classification result corresponding to the knowledge information to be classified. As for each piece of knowledge information to be trained in a training set, the classification results of to-be-trained knowledge information included ina training set used for non-first training are classification results re-determined according to a first confidence coefficient and a second confidence coefficient, wherein the first confidence coefficient is the confidence coefficient of the classification result of the to-be-trained knowledge information by a deep learning model, and the second confidence coefficient is the confidence coefficient of the initial classification result of the to-be-trained knowledge information based on a preset classification rule.

Description

technical field [0001] The present invention relates to the technical field of information processing, in particular to a method, device, electronic equipment and medium for constructing a knowledge map. Background technique [0002] The knowledge map is used to describe various entities in the real world and the relationship between entities. Specifically, visualization technology can be used to describe knowledge resources and their carriers, mining, analyzing, constructing, drawing and displaying knowledge and their interrelationships . Taking the video website as an example, the current method of constructing the knowledge map in the video website is to obtain the film and television materials in the video website, and obtain the information from each vertical website through crawler technology, and then use the preset classification rules to classify the acquired The data are classified, so that each data is stored in the corresponding category in the knowledge map acc...

AI Technical Summary

Problems solved by technology

[0003] However, in the process of classifying data in the prior art, manually set classification rules are used. Due to the limited ability to obtain information manually, it is difficult to ensure comprehensive and accurate classification rules. It is difficult to guarantee the accuracy, and it is difficult to accurately build a knowledge map

Images