Entity matching method and device

Abstract

The invention discloses an entity matching method and device, and relates to the technical field of the Internet. The method comprises the steps: performing entity identification on keywords in a received query request to obtain keyword entities; performing similarity calculation of a multi-dimensional identification result on the keyword entity and service information in a preset database to obtain multi-dimensional similarity between the keyword entity and the service information in the preset database; obtaining target service information matched with the keyword entity according to the multi-stage similarity between the keyword entity and the service information in a preset database and the multi-dimensional similarity; and generating an operation instruction corresponding to the queryrequest according to the target service information. By means of the technical scheme, the query experience of the user can be effectively improved, and meanwhile, the technical problem that the keyword query accuracy is low under the condition that no knowledge graph exists temporarily or the knowledge graph is incomplete is effectively solved.

Description

technical field [0001] The present application relates to the technical field of the Internet, in particular to an entity matching method and a device thereof. Background technique [0002] With the continuous development of the mobile Internet, users increasingly prefer to search for service content they are interested in through platforms such as application programs that provide business services, and the demand for personalized search functions of platforms such as application programs is getting higher and higher. [0003] The personalized search functions of existing platforms such as applications that provide business services are based on the existing knowledge graph for similarity calculations, and calculate the multiple options that the user wants to search according to the keywords entered by the user, so that the user can select from multiple Select the option that is most appropriate to the keyword among the options to complete the search operation. [0004] Ho...

AI Technical Summary

Problems solved by technology

[0005] In view of this, this application provides an entity matching method and its device, the main purpose of which is to solve the knowledge graph based on manual construction in the prior art, and complete the corresponding push by performing similarity calculation on the keywords input by the user, resulting in the construction of the knowledge graph High cost, and when there is no knowledge map or the knowledge map is not perfect, it is difficult to meet the super high standard of keyword search, resulting in inaccurate push and poor user experience technical problems

Images