Method, user modeling equipment and system for carrying out personalized recommendation for users

A user model and user technology, applied in the field of communication, can solve problems such as difficulty in identifying users, inability to solve cold start, inability to accurately match user interests, etc., achieving high accuracy and solving cold start problems.

Active Publication Date: 2014-06-18
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF5 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, on the one hand, user behavior is implicit user feedback, and determining which information to finally recommend based on user behavior cannot accurately match user interests (for example, it is difficult to determine whether a user is because the news is popular or because interest and click); on the other hand, for users who have no historical behavior, it is impossible to use existing technologies to make accurate information recommendations, that is, it is impossible to solve the so-called cold start problem in the industry

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, user modeling equipment and system for carrying out personalized recommendation for users
  • Method, user modeling equipment and system for carrying out personalized recommendation for users
  • Method, user modeling equipment and system for carrying out personalized recommendation for users

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0073] In Embodiment 1, the method for personalized recommendation for users includes the above-mentioned figure 1 All processing in the method shown, where, as figure 2 As shown, the method also includes:

[0074] S11: Establish an information model for the celebrity according to the first modeling strategy, and store the information model of the celebrity in the information model database.

[0075] optional, such as image 3 As shown, establishing an information model for the celebrity according to the first modeling strategy can be implemented in the following first manner:

[0076] S111: Obtain information about the celebrity from a third-party information platform;

[0077] S112: Establish an information model of the celebrity according to the information of the celebrity. Thereafter, the information model of the celebrity may be stored in an information model database.

[0078] Please refer to Embodiment 2 for the detailed description of the above-mentioned first m...

Embodiment 2

[0086] In Embodiment 2, the method for establishing an information model for the celebrity according to the first modeling strategy is described by taking the third-party information platform as an example of an online encyclopedia, as follows Figure 4 Shown:

[0087] S111 includes:

[0088] S1111: Search for the celebrity through the online encyclopedia;

[0089] S1112: Grab encyclopedia entries about the celebrity from the search results.

[0090] S112 includes:

[0091] S1121: Parse the text of the encyclopedia entry, and perform word segmentation on the encyclopedia entry.

[0092] S1122: Perform tf-idf (term frequency–inverse document frequency) calculation to obtain keywords and keyword weights in the encyclopedia entry, wherein the keywords and keyword weights represent the celebrity individual attributes.

[0093] S1123: Determine the classification of the celebrity by using a classification model established by svm (Support Vector Machine), wherein the classific...

Embodiment 3

[0111] In embodiment 3, the method for personalized recommendation for users may include the above-mentioned figure 1 , figure 2 , image 3 or Figure 4 In all processing manners of the shown methods, the information model established for the celebrity based on the first modeling strategy includes components representing individual attributes and / or group attributes of the celebrity.

[0112] Optionally, in this embodiment, such as Figure 5 As shown, the S13 includes:

[0113] S131: According to the information model of the celebrities followed by the user, cluster the individual attributes and / or group attributes of the celebrities, and determine the individual attributes and / or group attributes followed by the user;

[0114] S132: Establish the user model according to the individual attributes and / or group attributes concerned by the user.

[0115] In an example of Embodiment 3, the individual attributes and group attributes of celebrities followed by the user may be ...

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 method, user modeling equipment and a corresponding system for carrying out personalized recommendation for users. The method comprises the following steps: extracting information models of famous persons concerned by a user from an information model database, wherein the famous persons are persons meeting predetermined conditions in a social network, and information models established for the famous persons on the basis of a first modeling strategy are stored in the information model database; establishing a user model for the user according to the information models of the famous persons concerned by the user and a second modeling strategy; acquiring information which is extracted according to the user model and is suitable for the user and recommending the information to the user. According to the method, the user modeling equipment and the corresponding system disclosed by the invention, the user model established according to the information models of the famous persons concerned by the user can accurately represent interests of the user, and the information recommended for the user according to the user model can be accurately matched with the interests of the user, thus the information recommendation accuracy is high, and the cold start problem caused by shortage or absence of historical behaviors of users is solved.

Description

technical field [0001] The present invention relates to the communication field, and more specifically, relates to a method for making personalized recommendations for users, a user modeling device and a system, and the system includes a server system for making personalized recommendations for users and a system including the server system Network Systems. Background technique [0002] With the strong development of Internet technology and the large-scale coverage of network information, users usually need to choose the content they are interested in from a large amount of information when browsing information, which not only wastes users' time, but also causes serious information waste. For example, in an e-commerce system, the number and types of products increase rapidly, and users need to spend a lot of time to find the product information they want, which will undoubtedly affect the user experience. Therefore, a personalized information recommendation method that reco...

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): G06F17/30G06F17/27H04L29/06
CPCG06F16/951H04L67/55
Inventor 李本阳秦锋剑宋奇
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) 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