Unlock instant, AI-driven research and patent intelligence for your innovation.

Text mining method and system

A text mining and unification technology, applied in the field of information mining, can solve problems such as insufficient keyword extraction, failure to consider text semantic features, etc., and achieve the effect of improving the resolution rate

Pending Publication Date: 2021-08-10
深圳市云网万店科技有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] (2) Insufficient keyword extraction
It may cause diametrically opposite semantics, but it is divided into the same category if it contains the same keyword at the same time. This method does not take into account the semantic characteristics of the text

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Text mining method and system
  • Text mining method and system
  • Text mining method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] In order to make the purpose, technical solutions and advantages of the present application, the present application will be described in further detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are intended to explain the present application and is not intended to limit the present application.

[0050] The text mining method provided by this application first builds a template library containing a variety of copy-like layout styles. Select a template according to the designed screening conditions, then refer to the template prototype to arrange text typography, depending on the different template, the final implementation Style varied. The method is applied to the integration of the Synthetic E-Commerce Banner, according to the copy content and the designated layout area input by the user, the method can design a variety of copy typography patterns in the current layout area witho...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a text mining method and system. The method comprises the steps of receiving a user question vector, performing similarity judgment on the user question vector and an existing corpus, and determining to-be-clustered data according to a judgment result; according to a preset cluster center list, generating a cluster corresponding to the preset cluster center list from the to-be-clustered data; traversing all the clusters, segmenting the clusters containing a plurality of user question categories, and enabling each cluster to correspond to one user question category; simplifying all the clusters, and combining all the clusters containing the same intention; and comparing results generated by each cluster, and determining optimal clustering data. According to the method, text vectorization can be carried out, vectorized texts are clustered, all similar user questions are summarized into new categories, corpus categories of original robots are expanded, and the solution rate of customer service robots is improved.

Description

Technical field [0001] The present application relates to the technical field of information mining, involving a text mining method and system, in particular by using the K-MeANS mean cluster of Faiss to minuse text. Background technique [0002] Existing text mining is generally divided into two steps, the first step is to cluster the quantized text. Text feature is accurately cut by joining sentences, and cleaning text is cleaned by deactivating the word meter and a series of regular rules, and the pretreatment of the text is completed. The text is quantified by the Word2Vec training word vector or TF-IDF word frequency statistics, the word in natural language is converted into a density vector that the computer can understand. For quantified text, text clustering in clustering methods such as K-Means, DBSCAN, divided into the same cluster. The second step is to extract keywords. Text feature passes the text and attaches the text through the clause fraction, gives different wor...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/35G06F40/30G06K9/62
CPCG06F16/35G06F40/30G06F18/23213G06F18/22
Inventor 王露瑶沈艺陈述钟涛张兵兵
Owner 深圳市云网万店科技有限公司