Food safety event risk research and judgment method and device based on knowledge graph reasoning

Abstract

The embodiment of the invention provides a food safety event risk research and judgment method and device based on knowledge graph reasoning. The method comprises the following steps: inputting a foodsafety knowledge graph containing entities, relationships among the entities and entity characteristics into a food safety event risk research and judgment model, obtaining a risk level of a target entity, and carrying out food safety event reason reasoning and event consequence prediction, wherein the food safety event risk research and judgment model comprises a triad internal attention mechanism layer, a triad external attention mechanism layer, an entity classification layer and a relationship prediction layer. The embodiment of the invention provides a food safety event risk research andjudgment method and device based on knowledge graph reasoning, a food safety knowledge graph is input into a food safety event risk research and judgment model, the risk level of the target entity isobtained, food safety event reason reasoning and event consequence dynamic prediction are carried out, risk dynamic research and judgment and dynamic prediction of important activity food safety events are achieved, and the accuracy of risk research and judgment and dynamic prediction is improved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a method and device for researching and judging risks of food safety incidents based on knowledge map reasoning. Background technique [0002] With the rapid development of the economy and the improvement of the comprehensive national strength of various countries, political, economic, cultural, sports and other major activities in various places are carried out more and more frequently. Due to the tight schedule of major events, all kinds of food safety hazards are concentrated, involve a wide range of areas, and have a great impact. Once a food safety accident occurs, the consequences will be quite serious. The whole chain of food safety for major events mainly includes: procurement, general warehouse, distribution, processing, catering, etc. All links are potential sources of food safety risks, and problems in any link may lead to food safety risk incidents. T...

AI Technical Summary

Problems solved by technology

However, the data mining technology is too complicated for the operation of the database, and it is impossible to update the data in a timely manner, which leads to a decrease in the accuracy of research and judgment, and greatly reduces the analysis efficiency.

[0006] The rise of knowledge graphs has greatly changed the way data is stored. Real-world data are often displayed in the form of knowledge graphs. Knowledge graphs can more abundantly display the food safety data information of major events. For non-structural data such as knowledge graphs, data, traditional data mining methods are no longer applicable

Images