Data processing system based on graph network

Abstract

The embodiment of the invention discloses a data processing system based on a graph network, and the system comprises: a data collection device which employs a crawler technology to crawl the basic information of each individual from a public webpage, wherein the basic information comprises unstructured information and is stored in a database; and the graph network construction device which is used for extracting information from the database, constructing a graph network by taking an individual as a node, connecting nodes with an association relationship, taking the unstructured information as a plurality of attributes of the nodes, and encoding each attribute into an attribute vector to obtain a plurality of attribute vectors. According to the graph network constructed by the system, more attribute information can be introduced during application based on the graph network, so that the accuracy of a calculation result can be improved.

Description

technical field [0001] The invention belongs to the technical field of big data, and in particular, the invention relates to a data processing system based on a graph network. Background technique [0002] It is impossible for an enterprise to exist independently in the process of operation, and it will inevitably have a relationship with other enterprises or individuals or organizations, and establish a mutual relationship between enterprises. In the subsequent application analysis, it can be based not only on the data of the enterprise itself, but also on the basis of its own data. The data of related enterprises can improve the accuracy of analysis results. At present, the method of establishing the mutual relationship between enterprises is to establish the relationship network graph of the enterprise (or called the knowledge map of the enterprise, or the graph network), that is, each node in the graph is an enterprise, and the nodes with related relationships are connec...

AI Technical Summary

Problems solved by technology

However, the graph network constructed in this way has certain technical defects. For example, the data of each node is displayed on the node in the form of information. When the graph network is used for corresponding calculations, it is difficult for these data to participate in the calculation. Especially unstructured data (such as company introduction, product pictures, financial statements, etc.), which in turn makes the accuracy of calculation results limited

Images