Knowledge graph construction method and system based on manufacturing field

Abstract

The invention relates to a knowledge graph construction method and system based on a manufacturing field. The method comprises the steps of acquiring description statements of the machining process ofthe manufacturing field; performing statement splitting and semantic analysis on the description statement of the manufacturing field processing process based on a pre-established knowledge dictionary to extract corresponding words; performing automatic matching according to the knowledge dictionary to classify the words; querying the knowledge dictionary, and replacing the classified words to obtain standard words corresponding to the classified words in the knowledge dictionary; generating a triple relation structure according to the standard words; obtaining structured data of a knowledgegraph of a to-be-constructed manufacturing field according to the triple relation structure, wherein the structured data comprises a plurality of entity names; and updating the structured data according to the reference entity names corresponding to the plurality of entity names to obtain a knowledge graph of the manufacturing field. The knowledge graph in the manufacturing field constructed by the method is high in accuracy.

Description

technical field [0001] The present invention relates to the field of data processing, in particular to a method and system for building a knowledge map based on the manufacturing field. Background technique [0002] The manufacturing process refers to the process in which the processed object undergoes chemical or physical changes through production equipment and a series of processing devices to finally obtain the product. The manufacturing process is a professional category in the manufacturing field, which contains a lot of proprietary Industrial machining terms such as rough turning, turning, grinding and finish turning. [0003] The knowledge data in the manufacturing field involves multi-organization, multi-process, and multi-product, and has the characteristics of multi-source and interconnection. Each subdivision of the manufacturing process has its own terms and customary expressions, and the processing operations described in natural language Due to the diversity ...

AI Technical Summary

Problems solved by technology

[0003] The knowledge data in the manufacturing field involves multi-organization, multi-process, and multi-product, and has the characteristics of multi-source and interconnection. Each subdivision of the manufacturing process has its own terms and customary expressions, and the processing operations described in natural language Due to the diversity of personnel and the richness of natural language, the processing method of expression is complex and diverse. For example, the same processing method may have many different expressions. In addition, the multi-source of data leads to the diversity of data Large differences in description and large semantic span make it difficult to understand and communicate in a unified manner. For example, the multi-source of data leads to large differences in data description and large semantic span, that is, the unified expression of manufacturing knowledge and the construction of knowledge graphs

[0004] 1. The traditional keyword-based input method will lead to repeated storage of the content of many synonymous sentences, so that users or references cannot quickly and accurately obtain the relevant knowledge they want to obtain;

[0005] 2. The constructed knowledge map in the manufacturing field is not uniform and has low accuracy

Images