Method, device and system for recommending search terms

A technology for recommending devices and search words, which is applied in the Internet field, can solve the problems of insufficient flexibility, poor recommendation effect, and inability of search words to accurately reflect user needs, etc., and achieve the effect of improving accuracy and recommendation effect

Active Publication Date: 2015-04-29
SHENZHEN TENCENT COMP SYST CO LTD
View PDF3 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] During the research and practice of the existing technology, the inventors of the present invention found that the existing search word recommendation scheme is not only not flexible enough, but also cannot be updated in time, so that the recommended search words cannot accurately reflect the needs of users. not effectively

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, device and system for recommending search terms
  • Method, device and system for recommending search terms
  • Method, device and system for recommending search terms

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] This embodiment will be described from the perspective of a search word recommendation device, and the search word recommendation device may specifically be integrated in a network device such as a server.

[0038] A method for recommending search terms, comprising: acquiring user behavior logs, user portrait information, and preset user group characteristics of multiple user groups of multiple users; calculating search terms according to the user behavior logs, user portrait information, and user group characteristics The group popularity of the word; calculate the group differentiation degree of the search term according to the user behavior log, user portrait information and user group characteristics; calculate the search word quality according to the user behavior log; according to the group popularity, group differentiation degree and Search term quality recommends search terms to users.

[0039] Such as Figure 1b As shown, the search word recommendation method,...

Embodiment 2

[0097] According to the method described in Embodiment 1, an example will be given below for further detailed description.

[0098] In this embodiment, it will be described by taking that the search word recommendation device is specifically integrated in a server as an example.

[0099] Such as Figure 2a and Figure 2b As shown, a search word recommendation method, the specific process can be as follows:

[0100] 201. The server acquires user behavior logs, user portrait information, and preset user group characteristics of multiple user groups within a certain time window of each user in the network.

[0101] Wherein, the user behavior log may include a plurality of user search behaviors, and the user search behaviors are represented by four tuples: {user identifier, search term, search time, click / download rate}. User portrait information is expressed as {user ID, age, gender, location} in a quadruple, while user group characteristics can include information such as age...

Embodiment 3

[0223]Based on the method described in Embodiment 2, it should be noted that, in actual implementation, the device for recommending search words can be integrated in a server, or can be divided into multiple modules, which are respectively integrated in multiple devices, such as multiple In the server, for example, if the search term recommendation system includes a client and a search term recommendation device, and the search term recommendation device includes a preprocessing module, a search module, a processing module and a security module as an example, the specific functions of each module can be as follows :

[0224] (1) Preprocessing module;

[0225] The preprocessing module is used to receive the login request sent by the user through the client, wherein the user identification carried by the login request obtains corresponding user portrait information according to the user identification, and provides the user portrait information to the search module; and receives...

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 embodiment of the invention discloses a method, a device and a system for recommending search terms. The method provided by the embodiment of the invention comprises the following steps of acquiring user behavior logs of a plurality of users, user portrayal information and preset user group characteristics of a plurality of user groups; calculating group heat of search terms according to the user behavior logs, the user portrayal information and the user group characteristics; calculating group distinction degrees of the search terms according to the user behavior logs, the user portrayal information and the user group characteristics; calculating the quality of the search terms according to the user behavior logs; recommending the search terms to the users according to the group heat of the search terms, the group distinction degrees and the quality of the search terms. According to the scheme, the individual recommendation for different user groups can be realized, the timely dynamic updating capacity is achieved, the accuracy of recommendation is increased and the recommendation effect is improved.

Description

technical field [0001] The present invention relates to the technical field of the Internet, in particular to a search word recommendation method, device and system. Background technique [0002] The application market is an important application distribution channel for the mobile Internet, providing services such as application search and download for smart terminal users. In order to facilitate users to use the search function, increase the number of search users and the number of search downloads of applications, the application market usually displays a certain number of search terms on the search start page, and guides users to click on the search and download the application. [0003] In the prior art, the operator generally constructs a keyword list manually as a general recommended search term, or the system sorts all search terms according to certain rules, such as the number of searches or the number of downloads, etc., and then Select the head search term as 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 Applications(China)
IPC IPC(8): G06F17/30
CPCG06F16/9535G06F16/958
Inventor 黄泽谦卓居超李明致
Owner SHENZHEN TENCENT COMP SYST 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