Article information recommending method and device

A technology for item information and recommendation methods, which is applied in the field of item information recommendation methods and devices, can solve the problems of insufficient personalization of recommendation results, inaccurate recommendation results, limited nonlinear expression ability, etc., so as to improve the recommendation effect and accuracy , enhance the effect of personalization

Inactive Publication Date: 2016-09-21
TENCENT TECH (SHENZHEN) CO LTD
View PDF5 Cites 63 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] During the research and practice of the prior art, the inventors of the present invention found that since LR is a linear model with limited nonlinear expressive ability, and the LR model is a statistical probability model based on crowds, it is difficult to Non-linear problems in the recommendation of various types of items, there will be problems with insufficient personalization of recommendation results and inaccurate recommendation results

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
  • Article information recommending method and device
  • Article information recommending method and device
  • Article information recommending method and device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0037] In this embodiment, description will be made from the perspective of the device for recommending item information, and the device for recommending item information may specifically be integrated in a network device such as a server or a gateway.

[0038] A method for recommending item information, comprising: when an item access request is received, acquiring attribute information and user behavior data of an accessing user; acquiring a corresponding set of candidate items; based on a preset similarity matrix, the attribute information of the accessing user Information and user behavior data, determining items that meet preset conditions in the candidate item set, and the preset similarity matrix is ​​used to indicate the similarity between candidate items and the similarity between candidate items and attribute information; The item information corresponding to the item satisfying the preset condition is recommended to the visiting user.

[0039] see Figure 1b , Fi...

no. 2 example

[0093] According to the method described in the first embodiment, an example will be given below for further detailed description.

[0094] First, the method for recommending item information provided by the embodiment of the present invention can be built on Hadoop and Spark distributed computing and storage clusters. Secondly, the device for recommending item information in this embodiment predicts the user's intention through the heat conduction algorithm, and screens and sorts the items through the LR algorithm, and finally obtains and recommends the most suitable item for the user. The details will be described below.

[0095] see Figure 2a , Figure 2a It is a schematic flowchart of a method for recommending item information provided in the second embodiment of the present invention. The method includes step S21, obtaining a data source; step S22, performing offline calculation according to the data source; step S23, scoring and sorting online, and outputting a recom...

no. 3 example

[0117] In order to better implement the method for recommending item information provided by the embodiment of the present invention, the embodiment of the present invention further provides an apparatus based on the method for recommending item information above. The meanings of the nouns are the same as those in the above method for recommending item information, and for specific implementation details, please refer to the description in the method embodiments.

[0118] see Figure 3a , Figure 3a It is a schematic structural diagram of an apparatus for recommending item information provided in an embodiment of the present invention, wherein the apparatus for recommending item information may include a first acquisition unit 301 , a second acquisition unit 302 , a determination unit 303 and a recommendation unit 304 .

[0119] The first acquiring unit 301 is configured to acquire attribute information and user behavior data of the accessing user when an item access request ...

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 an article information recommending method and device. The method comprises the steps of obtaining attribute information and user behavior data of an access user when an article access request is received; obtaining a corresponding candidate article set; determining articles satisfying preset conditions in the candidate article set based on a similarity matrix, the attribute information and the user behavior data, wherein the similarity matrix is used for indicating the similarities among the candidate articles, and the similarities between the candidate articles and the attribute information; and recommending the information of the articles satisfying the preset conditions to the access user. Through adoption of the similarity matrix, the attribute information of the access user and recent different click and consumption behaviors to the articles, intention prediction is carried out on user access; and therefore, the articles suitable for the user are determined and recommended to the user. Compared with the mode of carrying out recommendation through prediction of the click-through-rate scores of the user to the articles based on a linear model, the method and the device have the advantages of improving individuation of the recommendation results and improving the accuracy of the recommendation results.

Description

technical field [0001] The invention belongs to the field of communication technology, and in particular relates to a method and device for recommending item information. Background technique [0002] With the continuous advancement of the network, users have higher and higher requirements for various functions of the network when accessing the network. For example, taking item recommendation as an example, users generally hope that websites or app stores recommend similar items or related items to the items they need. , so that the required items can be accessed more conveniently by means of comparison and query. [0003] At present, the traditional item recommendation generally uses the Logistic Regression (LR, Logistic Regression) model to predict the user's exposure conversion rate (CTR, Click-Through-Rate) score for the item, such as the number of downloads and The ratio of the number of exposures, and then sort the items according to the CTR to get the recommendation ...

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
CPCG06F16/9535
Inventor 庄广安梁宇贺鹏岳亚丁
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