Visual analysis method and system for high-risk food and hazards based on graph embedding

Abstract

The invention discloses a method and system for visual analysis of high-risk food and hazards based on graph embedding. Food is used as a node, and edges are established on the condition of whether common hazards are detected in food to construct a food association network; The nodes of the associated network are vectorized; the vectorized nodes are clustered, so that the nodes with similar structural characteristics are divided into the same subgraph. The visualization design of Force‑Radar is to display the radar graph of the characteristic index of the subgraph as a node, and use the relationship between the subgraphs as the edge, and use the force-oriented layout to form an overview diagram of the entire network, effectively displaying the overview of the entire food association network and the structure of the subgraph Relationships between features and subgraphs. By adopting the invention, it is possible to interactively analyze and explore food related networks, discover high-risk foods and hazards, and provide support for food safety supervision.

Description

technical field [0001] The invention relates to the technical fields of information visualization, graph model information mining, and food safety, and mainly relates to a graph embedding-based visual exploration method and system for high-risk foods and hazards. Background technique [0002] Food safety is an issue that everyone has to pay attention to in daily life. With the continuous improvement of people's living standards and awareness of rights protection, people's requirements for food safety and quality are getting higher and higher, so that ordinary people can eat safe and secure food It has become an important issue of people's livelihood that has been widely concerned by governments, academia and industry. To this end, the national food safety supervision department conducts random inspections of various foods in various places and obtains a large amount of inspection data. These data include food names, types, and names of inspection items and other entities and...

AI Technical Summary

Problems solved by technology

The existing statistical analysis methods can quickly discover the distribution characteristics of the detection data, but it is difficult to display all the nodes and relationships of the large-scale data association network; the existing exploration methods for high-risk foods and high-risk detection items are based on the detection results Compared with the limit standard, it is impossible to consider the relationship between foods to find potentially risky foods and problems with testing items; it is difficult for users to discover and mine the entities and relationships that need to be focused on, as well as the hidden correlation patterns. It is difficult to analyze and warn potential food safety hazards

Images