Method and system for estimating user similarity

A similarity and user-friendly technology, applied in the field of similarity estimation methods and estimation systems, can solve problems such as complex estimation methods, affecting estimation speed and accuracy, and large errors, and achieve fast estimation speed, high accuracy, and low system resources. The effect of taking up less

Active Publication Date: 2020-05-12
TENCENT TECH (SHENZHEN) CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of this, the purpose of the present invention is to provide a user similarity estimation method and estimation system, which can solve the technical problems of complex estimation methods and large errors in the prior art, which further affect the estimation speed and accuracy

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 system for estimating user similarity
  • Method and system for estimating user similarity
  • Method and system for estimating user similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] see figure 1 , which is a schematic flowchart of a method for estimating user similarity. The method for estimating the user similarity is usually executed on the server side to provide data support for information recommendation methods or systems.

[0035] The method for estimating the similarity of users is used to estimate the similarity between users by analyzing the items associated or concerned by known users, wherein the items include but are not limited to: shopping list, TV list , and / or exercise expenditure, etc.

[0036] The method for estimating the user similarity includes:

[0037] In step S101, user attributes are obtained, and different users are divided into multiple user groups according to the user attributes.

[0038] Wherein, the user attribute refers to the status of the user, such as age, gender, constellation, education, marriage status, and / or hobbies. Using age as an example, you can have 10-year-old users as one group, 11-year-old users a...

Embodiment 2

[0068] see figure 2 , which is a schematic flowchart of a method for estimating user similarity. The method for estimating the user similarity is usually executed on the server side to provide data support for information recommendation methods or systems.

[0069] The method for estimating the user similarity includes:

[0070] In step S201, user attributes are obtained, and different users are divided into multiple user groups according to the user attributes.

[0071] When the number of users in the user group exceeds the user threshold, a preset number of sample users may be randomly selected.

[0072] In step S202, two user groups are selected.

[0073] In step S203, the item lists corresponding to the two user groups are merged and duplicated to generate a new list.

[0074] Wherein, for the sample users, this step specifically includes: generating a list of sampling items according to the items corresponding to the sample users in the user group.

[0075] In step ...

Embodiment 3

[0089] see image 3 , is a schematic diagram of an information recommendation method, which is based on the method or system for estimating user similarity provided by the present invention.

[0090] The information recommendation methods include:

[0091] In step S301, user attributes are obtained, and different users are divided into multiple user groups according to the user attributes.

[0092] In step S302, the items corresponding to each user in the user group are read to generate an item list.

[0093] In step S303, users in the user group and items in the item list are processed into a bipartite graph.

[0094] In step S304, the intra-group similarity of users is estimated through the bipartite graph; and / or the inter-group similarity of users is estimated through the bipartite graph.

[0095] In step S305, target users or target user groups are determined.

[0096] In step S306, according to the intra-group similarity or inter-group similarity, the target user or ...

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 present invention provides a user similarity estimation method and estimation system, comprising: obtaining user attributes, and dividing different users into multiple user groups according to the user attributes; reading the item corresponding to each user in the user group , to generate a list of items; processing the users in the user group and the items in the item list into a bipartite graph; estimating the intra-group similarity of users through the bipartite graph; and / or estimating users through the bipartite graph similarity between groups. The invention analyzes users and items through a bipartite graph, has the advantages of simple algorithm and high accuracy, can adapt to the environment of massive data, occupies less system resources, and has fast estimation speed.

Description

technical field [0001] The invention belongs to the field of data processing, and in particular relates to a user similarity estimation method and estimation system. Background technique [0002] With the popularization of the Internet, information resources expand exponentially, which brings about the problem of information overload, which makes users often get lost in a large amount of information space and cannot find the information they need smoothly. Therefore, various information recommendation technologies have emerged. Based on the user's operating habits, a certain relationship between users and items is established, such as watching or liking, and then generating information recommendation lists, such as program recommendation lists, shopping recommendation lists, or friends. Recommended list etc. [0003] The principles of these recommendation technologies are mainly based on the similarity of users, and select the list of items of known users with high similari...

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 Patents(China)
IPC IPC(8): G06K9/62
CPCG06F18/22
Inventor 杨春风
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