Word segmentation method, device, system and equipment

Abstract

The invention provides a word segmentation technical scheme, which comprises the following steps of: performing word segmentation on an obtained text to be subjected to word segmentation to obtain a first word segmentation result; based on a first preset condition, traversing the first word segmentation result, judging each word segmentation in the first word segmentation result, and if the current word segmentation meets the first preset condition, determining the current word segmentation as a trigger word; judging whether other words in a preset range before and after the trigger word meet a second preset condition or not, and if so, re-segmenting the word segmentation result in the preset range before and after the trigger word based on a preset rule; continuing to traverse until the last word segmentation of the first word segmentation result, and obtaining a second word segmentation result. Through the method, on the basis of the word segmentation result obtained by adopting the existing word segmentation tool, the word segmentation result can be further optimized in combination with the preset strategy which can be flexibly adjusted, so that the word segmentation result which is more accurate in semantics is obtained.

Description

technical field [0001] The present application relates to the technical field of computer data processing, in particular to a word segmentation technology. Background technique [0002] With the popularization of digital infrastructure such as the Internet, human beings have entered the era of information explosion, and more and more data need to be processed. However, a large number of natural language texts, pictures, and videos in the network are often unstructured data. Among them, The number of natural language texts is the largest. In order to be able to analyze and utilize these natural language text information, NLP (Natural Language Processing, natural language processing) technology is needed. NLP is equivalent to a translation or a communication bridge between computer language and human language, so as to achieve the purpose of human-computer interaction. [0003] As a basic content in NLP, word segmentation is the process of recombining continuous word sequenc...

AI Technical Summary

Problems solved by technology

[0006] The purpose of this application is to provide a word segmentation technical solution to solve the technical problem that satisfactory word segmentation results cannot be obtained when using existing word segmentation tools to segment special word texts containing specific fields

Images