A ranking system and method based on natural language analysis

Abstract

The invention discloses a sorting system and method based on the natural language analysis. The system comprises a data acquisition module, a data storage preprocessing module, a data retrieval preprocessing module, a database, a business rule module, a natural language analysis system, a data index module and a retrieval display module. The data acquisition module is used for acquiring text data;the business rule module is used to set the rules of the business domain violation words and the business derived vocabulary, and the natural language analysis system is used to extract keywords andsemantic fragments. The data index module is used for creating the index and storing the index pieces in the data index library. The retrieval display module is used for visually outputting the retrieval results after sorting. Through the natural language analysis system, the invention analyzes the content to be analyzed, and obtains relevant keywords and semantic segments. Through the establishment of the relevant business rules and the business derivatives vocabulary, the natural sentence analysis system is perfected to analyze the same type of depth and breadth.

Description

technical field [0001] The invention belongs to the technical field of data retrieval, and in particular relates to a sorting system and method based on natural language analysis. Background technique [0002] Nowadays, keyword matching technology and fuzzy matching technology are the main methods used by retrieval systems. This method has the following disadvantages: 1. The search efficiency is low. Keyword matching technology and fuzzy matching technology are used for retrieval. Due to the large number of keywords, there are many synonyms or derivative words of keywords. It is difficult to effectively separate the required data from a large amount of data, which cannot meet the current requirements for the accuracy of data discovery; on the other hand, it is difficult to find other words with the same meaning or derivatives of keywords. 2. The ranking and display of search results are not very relevant. The ranking display of search results is only judged by keywords, an...

AI Technical Summary

Problems solved by technology

[0002] Nowadays, keyword matching technology and fuzzy matching technology are the main methods used by retrieval systems. This method has the following disadvantages: 1. Low search efficiency

The ranking display of search results is only judged by keywords, and the ranking correlation is not high, so that users cannot quickly find the required data information through the display sequence. It has limited effect in some scenarios that need to quickly and accurately retrieve a large amount of data and display related content.

Images