Text information matching measurement method and device, server and storage medium

Abstract

The invention relates to the field of artificial intelligence, and discloses a text information matching measurement method, which comprises the following steps of: when a target text and a similar text are received, reading word granularity in the target text and the similar text; obtaining vector representation information of the target text and vector representation information of the similar text according to the read word granularity of the target text and the word granularity of the similar text; when the vector representation information of the target text and the vector representationinformation of the similar text serve as input values of a preset twin network model, obtaining the similarity, calculated by the preset twin network model, of the target text and the similar text; and when the similarity between the target text and the similar text is obtained, matching the similar text with the highest similarity with the target text. The invention further discloses a device, aserver and a storage medium. A text similarity matching algorithm based on word and individual character integration is realized, and the sentence semantic analysis effect is further improved.

Description

technical field [0001] The invention relates to the field of intelligent recommendation, in particular to a method, device, server and computer-readable storage medium for text information matching measurement. Background technique [0002] In recent years, with the emergence and improvement of word distribution representation tools such as word2vec and GloVe, the representation information of words has become more and more abundant. Each word vector not only contains relatively rich semantic information, but also has certain differences between each word vector. relationship, the vector information that does not contain words that are not expected can be obtained through simple operations. Since 2012, the convolutional neural network (CNN) model has shined in image recognition, and more researchers have begun to transplant the CNN model to the task of natural language processing to obtain the relationship between different texts. similarity. [0003] At present, the probl...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to provide a method of text information matching measurement, aiming to solve the problem that the semantics of the text obtained in the similarity algorithm often have large deviations, resulting in Technical issues with inaccurate similarity metrics

Images