A knowledge map construction method and related equipment

Abstract

The invention discloses a method for constructing a knowledge map and a related device. The method includes: acquiring corpus data; performing entity pair matching on multiple sentences in the corpus data using a preset entity pair relationship to obtain a matching result; using a training learning model to pair The sentences containing positive examples of entities and the sentences containing negative examples of entities are trained to obtain training results. The training results include at least the weight value of each word in the sentence in the sentence; the relationship template is generated based on the words whose weight value satisfies the first preset condition; Calculate the probability value of the relationship template based on the positive statement and its probability value and the negative statement and its probability value; determine the target relationship template whose probability value in the relationship template meets the third preset condition, and use the target for the entity pair in the statement The relationship template calculates the ratio value of the corresponding entity-to-relationship; selects the entity pair whose ratio value of the entity-to-relationship satisfies the fourth preset condition to construct the knowledge map.

Description

technical field [0001] The present application relates to the technical field of data processing, in particular to a knowledge map construction method and related equipment. Background technique [0002] The knowledge map is a combination of theories and methods of applied mathematics, graphics, information visualization technology, information science and other disciplines with metrology citation analysis, co-occurrence analysis and other methods, and uses the visual map to vividly display the core structure and development of the subject. History, frontier fields, and the overall knowledge structure achieve the modern theory of multidisciplinary integration. It displays complex knowledge fields through data mining, information processing, knowledge measurement and graphic drawing, reveals the dynamic development law of knowledge fields, and provides practical and valuable references for subject research. Knowledge graph technology is an integral part of artificial intelli...

AI Technical Summary

Problems solved by technology

The current knowledge map construction methods mainly include the following types: one is manual construction, which is obtained by manually sorting out structured data, which usually has the problem of time-consuming and labor-intensive construction; the other is automatic construction, mainly through NLP technology extracts entities from the data, and then obtains the relationship between entities through template matching or classification models to build a knowledge map. Although this solution can improve the construction efficiency, the classification model still requires a large amount of manually labeled training corpus, resulting in still There is a problem of low efficiency, and a lot of noise will be generated when the relationship between the entities extracted from the data is obtained through template matching or classification models, resulting in low construction accuracy

Images