Intelligent patent retrieval method and system based on knowledge graph

Abstract

The invention provides an intelligent patent retrieval method and system based on a knowledge graph. The method includes: obtaining original information of each patent from a database, taking basic information, patent authors and patent application units in the original information as entities, constructing entity nodes of the patents and the authors of the patents through attribute information ofthe entities, and obtaining a knowledge graph library containing all the entity nodes and relationships among the entity nodes according to relationships among the entity nodes; obtaining retrieval information, judging whether the retrieval information is basic information or not; if so, retrieving all patents of which the similarity corresponding to the retrieval information is greater than a preset value in a knowledge graph library, and otherwise, judging whether the retrieval information is attribute information or not, if so, describing the attribute information through a graphic relationship, generating a retrieval sub-graph, carrying out sub-graph matching in a knowledge graph library according to the retrieval sub-graph to obtain a matching result set, and taking patents of whichsimilarity values are greater than a preset value as retrieval results, otherwise, ending retrieval.

Description

technical field [0001] The present invention relates to the fields of information technology, artificial intelligence and intellectual property rights, and in particular to a patent intelligent retrieval method and system based on a knowledge map. Background technique [0002] As of 2018, my country has ranked first in the world in terms of the number of patent applications for eight consecutive years. Under such circumstances, how to obtain effective patent information from a large amount of patent data is an important basis for further knowledge innovation. At present, the patent retrieval method is still based on keyword matching and full-text retrieval as the core retrieval methods. This retrieval method is prone to problems such as a large amount of matching of retrieval content, low matching accuracy, and the need for users to perform a large number of secondary searches, making it impossible for users to obtain accurate patent data in a short period of time. In rece...

AI Technical Summary

Problems solved by technology

This retrieval method is prone to problems such as a large amount of search content matching, low matching accuracy, and users need to perform a large number of secondary searches, making it impossible for users to obtain accurate patent data in a short time

Images