Entity matching method and device and electronic equipment

Abstract

The invention discloses an entity matching method and apparatus, and an electronic device. The method comprises the steps of obtaining an entity name to be matched; Searching a plurality of candidateentity names with higher matching degree with the entity names from a standard name library containing a plurality of standard entity names; Determining similarities between the entity names and the candidate entity names in at least one preset dimension; Synthesizing the similarity of the entity names and the candidate entity names in at least one preset dimension, and determining the candidate entity name with the highest comprehensive similarity of the entity name in at least one preset dimension from the plurality of candidate entity names; And determining the candidate entity name with the highest comprehensive similarity as a standard entity name corresponding to the entity name. According to the scheme, the applicable situation of entity name matching can be increased, the accuracyof entity name matching is improved, and manpower resource consumption is reduced.

Description

technical field [0001] The present invention relates to the technical field of communication, and more specifically, to an entity matching method, device and electronic equipment. Background technique [0002] Entity matching has been applied in many different fields, which refers to finding two objects belonging to the same entity. For example, a relatively common application scenario of entity matching is to find out the entity standard name corresponding to the entity name to be matched according to the entity name to be matched. For example, in the field of sales and circulation, it may be necessary to count and track the circulation of goods between different companies, but due to the different sources of data recorded in the sales flow, the company name of the same company recorded in the sales flow is not standard. Therefore, In order to realize the tracking and statistics of the sales flow, it is necessary to match these non-standard company names in the sales flow ...

AI Technical Summary

Problems solved by technology

However, the sample data of human observation is relatively limited, therefore, the rule logic based on human observation cannot cover all situations, resulting in some non-standard entity names that cannot be matched to the corresponding entity standard names

Moreover, the method of summarizing rule logic by manually observing sample data also requires high manual experience and consumes more human resources.

Images