Text processing method and device, server and storage medium

Abstract

The embodiment of the invention discloses a text processing method and device, a server and a storage medium, and the method comprises the steps: obtaining a to-be-processed text, carrying out the word segmentation of the text according to a preset strategy when the type of the text is a subjective type, and obtaining words forming the text; calculating the surface similarity between the text andeach corpus in a corpus library according to the words; calculating the information entropy similarity between the corpus of which the surface similarity is greater than a preset threshold and the text; and screening out the corpus with the highest information entropy similarity. According to the scheme, the surface layer similarity between the text and the corpus can be calculated, preliminary screening of the corpus can be achieved through the surface layer similarity, the information entropy similarity between the corpus with the surface layer similarity larger than the preset threshold value and the text is calculated, the corpus with the highest information entropy similarity is screened out, and the text processing efficiency and accuracy are improved.

Description

technical field [0001] The present application relates to the technical field of data processing, in particular to a text processing method, device, server and storage medium. Background technique [0002] With the development of science and technology, many industries have pre-sales and after-sales services, such as reservation, order checking, payment, complaints and other multi-faceted services in the express delivery industry. However, due to the fact that manual customer service cannot be online 24 hours a day, and labor efficiency is low and costs are high, etc. , the always-on intelligent customer service terminal came into being. [0003] At present, intelligent customer service terminals generally answer questions by analyzing the semantic information of the question first, and then find relevant answers from the corpus content of the local corpus according to the semantic information. However, simple semantic matching makes it impossible to obtain some questions fr...

AI Technical Summary

Problems solved by technology

[0002] With the development of science and technology, many industries have pre-sales and after-sales services, such as reservation, order checking, payment, complaints and other multi-faceted services in the express delivery industry. However, due to the fact that manual customer service cannot be online 24 hours a day, and labor efficiency is low and costs are high, etc. , the always-on intelligent customer service terminal came into being

[0003] At present, intelligent customer service terminals generally answer questions by analyzing the semantic information of the question first, and then find relevant answers from the corpus content of the local corpus according to the semantic information. However, simple semantic matching makes it impossible to obtain some questions from the corpus, or the searched answers are different from the questions. The correlation between them is low, that is, the accuracy is low, so the answers provided by the intelligent customer service terminal cannot fully meet the needs of users

Moreover, it takes a lot of time for semantic matching, resulting in a significant lag in the reply of the intelligent customer service terminal

Images