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

Application classification model constructing method and system and application classification method and system

A technology of application classification and construction method, which is applied in the field of application classification model construction, application classification and system, and can solve problems such as high labor cost, difficult maintenance, and low average accuracy

Inactive Publication Date: 2015-11-11
SHANGHAI ZHUO YOU NETWORK TECH
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the software is being promoted, searched, and downloaded in the application market. The classification of new applications is manually reviewed one by one to classify the applications. This method has high labor costs, and the average accuracy is not high, so it is difficult to maintain.

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
  • Application classification model constructing method and system and application classification method and system
  • Application classification model constructing method and system and application classification method and system
  • Application classification model constructing method and system and application classification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0084] Such as figure 1 As shown, the present invention provides a method for building an application classification model, including:

[0085] Step S1, obtain application basic classification data from multiple data sources of different application providers as training data; here, the multiple data sources may come from websites of different application providers, since the application basic classification data are all manually processed, resulting in The classification effect of each data source is different. In order to eliminate the influence caused by a single data source, the training data will collect classification data from multiple data sources to balance the error;

[0086] Step S2, obtain the permission list of each application in the training data; optionally, the permission list of each application is obtained from the permission setting information of the configuration file in the application installation package of each application, here, the configuration fil...

Embodiment 2

[0113] Such as Image 6 As shown, according to another aspect of the present invention, the present invention also provides an application classification method adopted from the above-mentioned primary and secondary matching models, and the application classification method includes:

[0114] Step S7, obtaining a permission list of applications to be classified;

[0115] Step S8, using a matching model, and judging whether the application to be classified belongs to a certain first category according to the permission list of the application to be classified,

[0116] Step S9, if it only belongs to a certain first category, then output the result that the application to be classified belongs to a certain first category;

[0117] Step S10, if it does not only belong to a certain first category, obtain the topic information of the application to be classified, use the secondary matching model, and judge whether the application to be classified belongs to a second category accor...

Embodiment 3

[0128] Such as Figure 10 As shown, the present invention also provides another application classification model building system, including:

[0129] The first device 1 is used to obtain application basic classification data from multiple data sources of different application providers as training data;

[0130] The second device 2 is used to obtain the permission list of each application in the training data;

[0131] The third means 3 is configured to construct a primary matching model according to the permission lists of all applications in the training data, the primary matching model including multiple first classifications of applications;

[0132] The fourth device 4 is used to obtain the topic information of each application in the training data, and perform feature selection according to the topic information of all applications in the training data;

[0133] The fifth means 5 is configured to construct a secondary matching model according to the selected features, ...

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 an application classification model constructing method and system and an application classification method and system. According to an authority list and theme information of an application, the application classification method reflects the classification of the application in view of a behavior generated by the application, may effectively reduce manual intervention and labor cost and improve average classification precision by means of a primary matching model and a secondary matching model.

Description

technical field [0001] The invention relates to a method and system for constructing an application classification model. Background technique [0002] With the improvement of the performance of mobile terminals such as mobile phones and the rapid growth of the scale of downloadable application software, users will face greater noise when selecting applications. How to effectively classify large-scale applications to improve user experience? Become a mobile phone An important technical means of the market. At present, when the software is being promoted, searched, and downloaded in the application market, new applications are classified by manual review one by one. This method has high labor costs, and the average accuracy is not high, so it is difficult to maintain. Contents of the invention [0003] The purpose of the present invention is to provide a method and system for constructing an application classification model, which can effectively reduce labor costs and imp...

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): G06K9/62
CPCG06F18/2411G06F18/24
Inventor 马松玉
Owner SHANGHAI ZHUO YOU NETWORK TECH
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