Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

New concept discovery method and device of rule association model

A technology related to models and new concepts, applied in computational models, special data processing applications, instruments, etc., can solve problems such as incomplete models and information loss, and achieve the effect of solving information loss and avoiding repeated re-modeling processes.

Inactive Publication Date: 2017-11-24
ULTRAPOWER SOFTWARE
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides a new concept discovery method and device for a rule association model to solve the problem that the traditional modeling method is easy to cause information loss and make the constructed model imperfect

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
  • New concept discovery method and device of rule association model
  • New concept discovery method and device of rule association model
  • New concept discovery method and device of rule association model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] see figure 2 , is a flow diagram of a new concept discovery method for rule association models. The new concept discovery method of the rule association model provided by the present application includes the following steps:

[0069] S101, acquiring training corpus of the current business scenario;

[0070] Regarding step S101, the training corpus of the current business scenario is obtained. Wherein, the training corpus is various corpus texts collected from actual business processing scenarios. Corpus texts can be related text materials obtained through big data systems, or service texts collected in related business processing platforms, such as consulting texts in consulting platforms, advertising texts in promotion platforms, etc. The training corpus of the current business scenario is used to generate a recommendation model through the information provided by the corpus, and use it as the basis for discovering new concepts.

[0071] S102, generating a recomme...

Embodiment 2

[0079] Such as image 3 As shown, the difference between this embodiment and Embodiment 1 is that step S101, obtaining the training corpus of the current business scenario, also includes the following steps:

[0080] S201, determine the current business scenario;

[0081] S202. Obtain business data of the current business scenario;

[0082] S203. Extract sample data from the business data, and use the sample data as the training corpus.

[0083] For step S201, before data processing, it is necessary to determine the current business scenario, that is, determine the technical field to which the processed data belongs. The current business scenario can be determined before data processing, or the current business scenario can be determined according to the keyword information in the processed data.

[0084] After the current business scenario is determined, the technical solution provided by this application acquires the business data of the current business scenario. Among ...

Embodiment 3

[0087] Such as Figure 4 As shown, the difference between this embodiment and the foregoing embodiments lies in the step of generating a recommendation model based on the training corpus, which also includes:

[0088] S301, performing word-by-item segmentation on the training corpus to generate a word segmentation list, and obtaining a list of inactive vocabulary;

[0089] S302. According to the disabled vocabulary list, filter the disabled vocabulary in the word segmentation list, and remove the disabled vocabulary from the word segmentation list;

[0090] S303. Determine the filtered word segmentation list as a training vocabulary, and generate a word space vector model according to the positions of the words in the training vocabulary in the training corpus text;

[0091] S304. Determine a real value vector of each word in the training vocabulary according to the word space vector model.

[0092] It can be seen from the above technical solution that the training corpus is...

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 new concept discovery method and device of a rule association model. The method includes the steps that a training corpus of a current service scene is obtained, and a recommendation model comprising a training vocabulary and a real value vector is generated according to the training corpus; a rule association model corresponding to the current service scene is obtained, and a new concept corresponding to each tuple of the rule association model is determined according to the recommendation model; finally, the new concepts are added into the rule association model. According to the method, by learning the training corpus of the current service scene, service concepts in the built rule association model are expanded, and accordingly the rule association model is improved. By means of the new concept discovery method, the new concepts with high association degree with the rule association model are discovered when the new concepts are generated in the service field, so that the problem that information is likely to be lost in a traditional modeling method and accordingly a built model is not perfect is solved.

Description

technical field [0001] The present application relates to the technical field of data mining, in particular to a method and device for discovering new concepts of rule association models. Background technique [0002] Correlation analysis refers to the discovery of data rules and the relationship between data from the database. Data rules and the relationship between data have important reference value in the control decision-making process of specific business scenarios. For a specific business scenario, correlation analysis is to sort out the business concepts concerned and the correlation between concepts in the sample data of the business scenario, and save the business concepts and the correlation between concepts as a model, so as to serve Follow-up business control and decision-making. [0003] Existing association analysis methods mainly rely on machine learning algorithms, such as the Apriori algorithm that mines frequent itemsets through two stages of candidate se...

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): G06F17/30G06N99/00
CPCG06F16/2465G06N20/00
Inventor 席丽娜李德彦王文军
Owner ULTRAPOWER SOFTWARE
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com