Method and apparatus for processing hyperlinks and storage medium

Abstract

The invention discloses a hyperlink processing method, a device and a storage medium. The method includes: converting first context information of a first hyperlink in a first object into a first context vector; acquiring a first input vector when the first object is a link source, wherein the first object contains information pointing to the first hyperlink of the second object; acquiring a firstaverage vector according to the first context vector and the first input vector; adjusting the first input vector, at least one of the first context vector and a first output vector corresponding tothe second object; calculating a similarity between the first output vector and the first average vector according to an adjustment result, and outputting the first output vector as an output vector of the second object when the similarity between the first output vector and the first average vector is greater than or equal to a first target threshold value.

Description

technical field [0001] The present invention relates to the field of computers, in particular to a hyperlink processing method, device and storage medium. Background technique [0002] Text with a hyperlink structure is called a hypertext document or hypertext. For hypertext documents, it is first necessary to vectorize hypertext documents and express them in the form of a fixed-length feature vector. [0003] At present, the vectorization processing method for hypertext documents is usually to convert hypertext documents into ordinary documents, and then perform vectorization processing. However, the above-mentioned hypertext document processing method ignores the relationship between the hyperlink content in the hypertext document and the source document and related context, resulting in information loss. For example, the context is regarded as an absolute description of the target document, and the source The document provides background information such that the intent...

AI Technical Summary

Problems solved by technology

However, the above-mentioned hypertext document processing method ignores the relationship between the hyperlink content in the hypertext document and the source document and related context, resulting in information loss. For example, the context is regarded as an absolute description of the target document, and the source The document provides background information such that the intent of the source document to refer to the target document cannot be obtained by comparing the two documents

Images