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

Method and device for text mining

A text mining and text technology, which is applied in the fields of instruments, computing, electrical digital data processing, etc., can solve the problem of insufficient accuracy of text mining

Active Publication Date: 2019-04-30
CANON INFORMATION TECHNOLOGY (BEIJING) CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the method is highly dependent on the terms extracted, so the accuracy of text mining is not high enough

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
  • Method and device for text mining
  • Method and device for text mining
  • Method and device for text mining

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0034] The core value of customer feedback, complaints or suggestions is that companies can take measures to improve products, services, processes, etc. based on this. Measures or actions taken in response to customer feedback or input text content are called actions. The first embodiment of the present invention provides a method of mining response actions from input text. The method can automatically and batch process customer feedback or input text.

[0035] In the prior art, when processing input text, it is based on terms or words in the text, and this processing is flat, without performing structural or semantic-level analysis on the entire input text.

[0036] However, the present invention provides a method for structured analysis and processing of input text strings. see image 3 , image 3 A general flowchart for generating action text according to the first embodiment is shown. People's feedback is often the text content formed by expressing their opinions with...

no. 2 example

[0095] The second embodiment of the present invention provides a method for classifying input text. The method can automatically and batch classify input texts based on generated action texts. The mechanism of this classification is that the value of customer feedback information lies in the response actions taken. If the action texts corresponding to two pieces of input text are the same, the input texts should be classified into one category even though the expressions of the input texts may be very different. vice versa. This method of classifying the input text based on the action of the response can eliminate the differences on the surface of the input text and achieve the purpose of analyzing or processing the input text. The classification mechanism is more meaningful.

[0096] Figure 8 A general flowchart for classifying text strings according to the second embodiment is shown. Wherein, the implementation of steps 100, 200 and 300 is as described in the first embo...

no. 3 example

[0104] A third embodiment of the present invention provides a method of classifying input text strings. The method includes a text string pre-classification step.

[0105] Figure 10 A general flowchart for classifying text strings including a text string pre-classifying step according to the third embodiment is shown. and Figure 8 In comparison, a text string pre-classification step 500 is added after step 100 .

[0106] More specifically, Figure 11 An exemplary flow chart of classifying text strings including the step of pre-classifying text strings according to the third embodiment is shown. and Figure 10 compared to, Figure 11 An exemplary implementation of step 500 is given, namely steps 510 to 550 .

[0107] Step 510, retrieve similar historical text strings. Step 520, judging whether the similarity between the current text string and one of the historical text strings is greater than the threshold T2. In other words, among all historical text strings, wheth...

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 provides a text mining method and device. The method comprises a text string receiving step used for receiving an input text string; a state pair extraction step used for extracting a state pair according to the input text string, wherein the state pair comprises a first state and a second state, the first state contains a first satisfaction value and a first description unit, the first satisfaction value is satisfaction or dissatisfaction, the first description unit contains a first noun and a first description phrase, an object described by the first description phrase is the first noun, the first description phrase contains a first adjective or a first verb, and the second state and the first state are opposite; and an action text generation step used for generating an action text, wherein the action text describes an action, the action corresponds to state transition from the first state to the second state, and the action text contains a third verb and an object of the third verb. Through the text mining method and device, the action text can be accurately generated, and input text strings can be accurately classified.

Description

technical field [0001] The present invention relates to information extraction, text mining, and in particular to methods and apparatus for processing and classifying input text. Background technique [0002] In today's society, customer relationship management (Customer Relationship Management) is an important link in the development of modern enterprises. Through customer relationship management, enterprises record, evaluate, and respond to customer opinions, thereby improving product or service levels and maintaining customer loyalty. In customer relationship management, it is very important to deal with various feedbacks from customers promptly and accurately. A large number of customers put forward their feedback through various channels such as hotlines, the Internet, and emails, and companies can obtain customers' expectations, likes and dislikes, etc. from these feedbacks. The traditional method is to sort out and mine these information manually, but obviously, the...

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 Patents(China)
IPC IPC(8): G06F17/27
Inventor 张碧川黄耀海清水涉
Owner CANON INFORMATION TECHNOLOGY (BEIJING) CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com