Method and device for determining user quality

A user quality and user technology, applied in the Internet field, can solve the problems of difficult user quality data, low user quality efficiency, and difficulty in determining the actual needs of user quality, so as to improve accuracy and efficiency and reduce inefficiency.

Inactive Publication Date: 2018-11-23
BEIJING QIYI CENTURY SCI & TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the different requirements for user quality in different application scenarios, the labeling standards for labeling sample users are often difficult to meet the actual needs of determining user quality, which makes it difficult to accurately determine user quality data using trained models. At the same time, a large number of Annotation operations also lead to inefficiencies in determining user quality

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 determining user quality
  • Method and device for determining user quality
  • Method and device for determining user quality

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] refer to figure 1 , shows a flowchart of steps of a method for determining user quality in an embodiment of the present invention. Specific steps include:

[0051] Step 101, acquiring quality evaluation features of multiple users, where the quality evaluation features include at least one of user features and data features of program data belonging to each user.

[0052] Since different users may have different education levels, environments, and social experiences and other factors, the quality of different users will also vary, and user quality may directly affect the quality of the data uploaded by the user to the server. quality, which in turn affects the network environment where the data is located and other users who obtain the data. Therefore, in order to facilitate the subsequent determination of the user quality of the user, to facilitate the management and control of the user or the data uploaded by the user, and to optimize the network environment, it is po...

Embodiment 2

[0077] refer to figure 2 , shows a flow chart of steps of a method for determining user quality in an embodiment of the present invention. Specific steps include:

[0078] Step 201, acquire quality evaluation features of multiple users, where the quality evaluation features include at least one of user features and data features of program data belonging to each user.

[0079] Wherein, for the manner of acquiring the quality evaluation features of multiple users, reference may be made to the relevant description in the foregoing, and details will not be repeated here.

[0080] In this embodiment of the present invention, optionally, in order to obtain more dimensional quality evaluation features, improve the accuracy of subsequent user clustering processing, and further improve the accuracy of determining user quality data, if the program data If multimedia data is included, the data features may include at least one of playback completeness, average number of fans, average...

Embodiment 5

[0130] refer to Figure 4 , shows a structural block diagram of an apparatus for determining user quality in an embodiment of the present invention. The device may include:

[0131]An acquisition module 401, configured to acquire quality evaluation features of multiple users, where the quality evaluation features include at least one of user features and data features of program data belonging to each user;

[0132] A clustering module 402, configured to perform clustering processing on the multiple users according to the quality evaluation features;

[0133] The first determining module 403 is configured to determine the user quality data of the multiple users according to the clustering result.

[0134] Optionally, the program data includes multimedia data, and the data features include at least one of the completeness of playing, the average number of fans, the average number of likes, the average number of comments, the average number of plays, the average clarity, and t...

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 method and a device for determining user quality, and relates to the technical field of the internet. The method comprises the steps of acquiring quality evaluation characteristics of multiple users, wherein the quality evaluation characteristics include at least one of user characteristics and data characteristics belonging to program data of each user; performing clustering processing on the users according to the quality evaluation characteristics; and determining user quality data of the users according to a clustering result. The method and the device have the advantages that the accuracy and efficiency of determining the user quality data can be improved.

Description

technical field [0001] The invention relates to the technical field of the Internet, in particular to a method and device for determining user quality. Background technique [0002] With the development of Internet technology, the network has been able to provide users with more and more convenience. Generally, a user can upload data to the server to share data with other users. If the user quality of the user is low, the quality of the data uploaded by the user may also be low, thereby causing adverse effects on other users and the network environment. [0003] In the existing technology, a large number of users can be obtained in advance as sample users, and the labeling staff will label the sample users according to the labeling standards, and then train the machine learning model according to the labeled sample users, and use the trained model to determine the users of other users quality. However, due to the different requirements for user quality in different applica...

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): G06Q10/06G06Q50/00G06K9/62
CPCG06Q10/06395G06Q50/01G06F18/23213
Inventor 胡军
Owner BEIJING QIYI CENTURY SCI & TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products