Keyword-to-enterprise retrieval method based on semi-supervised learning

Abstract

The invention relates to a retrieval method, in particular to a keyword-to-enterprise retrieval method based on semi-supervised learning, and belongs to the field of information retrieval. The self-training method comprises the following steps: firstly, training a model by using initial annotation data, then identifying part of unannotated data by using the model, and adding the identified part ofunannotated data into an annotation data set to serve as new training data; and obtaining a final model through multiple rounds of automatic data annotation and iterative training learning. The semi-supervised learning method can greatly reduce the manual annotation cost and improve the retrieval matching efficiency.

Description

technical field [0001] The invention relates to a retrieval method, in particular to a retrieval method for keywords to enterprises based on semi-supervised learning, which belongs to the field of information retrieval. Background technique [0002] Retrieval of enterprises by keywords refers to the use of keywords of enterprise brands, products or factories to retrieve the specific enterprises behind this part of the information, which is beneficial for market personnel to carry out precise marketing. For example, marketers hope to find the companies behind the medical device industry brand "Medster". Because different enterprises have the same keyword information in the text content such as enterprise name, enterprise trademark, business scope, etc., the keyword information retrieval in different data sources will return a large number of enterprises with ambiguous content. For example, for the brand keyword "Medster", the search result of the trademark registration infor...

AI Technical Summary

Problems solved by technology

[0004] Traditional supervised methods need to provide a large amount of manually labeled training data, and the labor cost is too high

Images