Food and health knowledge graph construction method based on deep learning

Abstract

The invention provides a food and health knowledge graph construction method based on deep learning. A knowledge graph oriented to the field of food safety is constructed and applied from six aspects of information extraction, knowledge representation, knowledge fusion, knowledge storage, knowledge reasoning and knowledge graph application. The functions of efficiently querying food safety data and scientifically analyzing food safety problems are realized. In the information extraction stage, a deep learning method based on manual annotation data set application comprises the steps that entity recognition is achieved based on a BiLSTM-CRF model, and relation extraction is achieved based on a Transformer model. On the basis, a triple type of (entities, relationships and entities) is adopted as input of knowledge graph representation learning, and high-dimensional knowledge is subjected to Embedding through representation learning, so that the data sparsity is effectively solved, the calculation efficiency is improved, and the method can be applied to entity similarity calculation and relationship prediction.

Description

technical field [0001] The invention belongs to the technical field of knowledge graphs, and in particular relates to a method for constructing food and health knowledge graphs based on deep learning. Background technique [0002] Food safety is a very important and at the same time very complex field. There are a large number of food safety-oriented standard documents, but they are huge in number, wide in coverage and complex in content, making it difficult to deal with them manually. Therefore, the introduction of knowledge graphs can help people analyze food safety issues more precisely, such as the limits of additives in various foods, the symptoms that will be caused by exceeding the limits, disease and treatment information, and other data closely related to food safety. [0003] Knowledge Graph (KG) first appeared as one of the research contents of Semantic Web. Domestic and foreign knowledge bases and knowledge map products emerge in endlessly. There are proprietar...

AI Technical Summary

Problems solved by technology

[0004] Because the knowledge in the food field is very complex, and there is not even a unified numbering system for corresponding foods, there are major difficulties in the process of knowledge fusion. Even if representation learning is used for entity clustering, it may be because entities with different names of the same substance are not collected. full and ineffective

[0005] The knowledge storage method based on the graph database is close to the actual business needs, but its structure is artificially designed, so the efficiency of query and retrieval will be affected by database modeling

Images