Text link embedding method

Abstract

The present invention involves the field of Internet text analysis technology, and it involves a text link embedding method.The vector, then calculate the characteristic vector similarity of the entity and the target entry to find the similar entity corresponding to the target entry, and finally embed the corresponding objects corresponding to the corresponding entity to the corresponding target entry to complete the text link.The text link embedding method of the present invention By converting the characteristic vector that can retain semantic characteristics, it is similar to whether the word entry between the target entry and the entity are similar according to the characteristic vector similarity of the entity and the physical vector of the entity.In this way, even in the case of synonymous words, the target entry can be accurately matched with the entity, thereby effectively avoiding physical omissions.

Description

technical field [0001] The invention relates to the technical field of Internet text analysis, in particular to a text link embedding method. Background technique [0002] With the development of knowledge graph-related technologies, various knowledge bases and encyclopedia applications emerge in an endless stream, providing users with a lot of high-quality content. However, at present, such content is mostly actively searched by users, and the frequency of use is low. Since hyperlinks are a common display form of Internet pages, hyperlinks are usually embedded in texts at this stage to solve the above problems. The hyperlink embedding method is to obtain the association relationship between the text in the article and the entity in the entity knowledge base, and then add the corresponding entity link entry in the text content. When the user clicks on the linked text, the link target will be displayed on the browser. In this way, the convenience and user experience of kno...

AI Technical Summary

Problems solved by technology

However, since this method strongly depends on the vocabulary coverage of the dictionary constructed by the entity knowledge base, when the keywords are not included in the entity knowledge base, the matching of keywords cannot be realized; and for different text contents, different Authors often have different understandings of the same concept, so the same object may have different names. At this time, the keywords in the text cannot accurately correspond to the entities in the entity knowledge base, which often causes a large number of entities in the document to be missed.

Images