Recommendation list generation method, device, media server, client and method

A media server and recommendation list technology, applied in the computer field, can solve the problems of single recommendation list user preferences, waste of system and network resources, poor user experience, etc., to reduce poor experience, reduce waste of system resources and network resources, The effect of increasing the hit rate

Active Publication Date: 2011-11-09
TENCENT TECH (SHENZHEN) CO LTD
View PDF4 Cites 58 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problems in the prior art that various resource providing websites and resource downloading software use a single recommendation list and cannot generate a recommendation list according to user

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
  • Recommendation list generation method, device, media server, client and method
  • Recommendation list generation method, device, media server, client and method
  • Recommendation list generation method, device, media server, client and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] The first embodiment of the present invention proposes a method for generating a recommendation list, the flow of which is as follows figure 1 shown, including:

[0066] Step 101: Classify the stored files to obtain the tags of the files;

[0067] Step 102: Recording the attributes of the files read by the user, the attributes at least including the tags of the read files;

[0068] Step 103: Generate a recommendation list according to the classification of the stored files and the attributes of the files read by the user.

[0069] The embodiment of the present invention proposes a method for generating a recommendation list. Aiming at records of files read by users, a recommendation list is generated from files in categories with high reading times. In this way, the preferences of the user can be learned according to the record of the user reading the file, so that a recommendation list can be generated for the files in the user's favorite category. Compared with the...

Embodiment 2

[0071] The second embodiment of the present invention proposes a method for generating a recommendation list, the process of which is as follows figure 2 shown, including:

[0072] Step 201: Classify the stored files, set different classification methods, and set a unique category key code for each classification method; classify the stored files according to each classification method, and classify each classification method A unique category value code is set for the classification under the document; a label of the file is generated according to the category key code and category value code corresponding to the file.

[0073] Wherein, step 201 adopts the form of identifying each category and generating a label for each file, so as to classify the stored files. Taking video content as an example, the videos stored in the server can be classified in multiple dimensions, for example:

[0074] It can be classified by content (CT): it can include movies (FM), TV dramas (PL), ...

Embodiment 3

[0169] The third embodiment of the present invention proposes a device for generating a recommendation list, the structure of which is as follows image 3 shown, including:

[0170] The classification module 1 classifies the stored files to obtain the tags of the files;

[0171] The historical information recording module 2 is used to record the attribute of the file read by the user, and the attribute at least includes the label of the file read;

[0172] The recommendation list generation module 3 is configured to generate a recommendation list according to the classification of the stored files and the attributes of the files read by the user.

[0173] An embodiment of the present invention proposes a device for generating a recommendation list, which generates a recommendation list from files in categories with a high number of times the user has read files for records of files read by the user. In this way, the usage habit and usage behavior of the user can be learned a...

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 discloses a recommendation list generation method, a recommendation list generation device, a media server, a client and a method, and belongs to the technical field of computers. The embodiment of the invention generates a recommendation list according to files in classes with higher user reading frequency for the file reading records of a user. In the embodiment, the likes and dislikes of the user can be learned according to the file reading records of the user, thereby generating the recommendation list for the files in the favorite classes of the user. Compared with the conventional single recommendation list way, the embodiment of the invention can be closer to the likes and dislikes of the user, improve user experiences, increase the hit rate, enable the user to more rapidly find own interested files and solve the problems of poor experiences and wasting of system resources and network resources caused by the random clicking of the user.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for generating a recommendation list, a media server, a client and the method. Background technique [0002] With the development of communication technology, the bandwidth of users continues to increase, and more and more users watch videos online through online playback software (such as PPStream, PPLive, QQLive, etc.). Existing streaming software has a recommendation list. In the prior art, the same recommendation list is used for all access users. [0003] In the process of realizing the present invention, the inventor finds that there are at least the following problems in the prior art: [0004] Because the existing video playback platform provides a lot of content, each user has different preferences. Therefore, this unified recommendation list method makes it difficult for users to quickly find the content they are interested in through the recomm...

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
IPC IPC(8): G06F17/30
Inventor 吴运声
Owner TENCENT TECH (SHENZHEN) 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap