Recommended methods for cross-source accounts on two micro-ends and one end

A recommendation method and account technology, which is applied in the field of Internet applications, can solve the problems of single consideration of recommendation results, small number of fans, and small number of blog posts, etc., and achieve accurate and reasonable account recommendation results

Active Publication Date: 2022-06-17
NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These account recommendation methods have the problem of a single factor in the recommendation results. Some account information that users care about is often ranked behind the big V account due to the number of fans and blog posts.

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
  • Recommended methods for cross-source accounts on two micro-ends and one end
  • Recommended methods for cross-source accounts on two micro-ends and one end

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The present invention will be further described in detail below with reference to the accompanying drawings, so that those skilled in the art can refer to the description and implement accordingly.

[0022] It should be understood that terms such as "having", "comprising" and "including" as used herein do not assign the presence or addition of one or more other elements or combinations thereof.

[0023] In order to achieve these objects and other advantages according to the present invention, a method for recommending cross-source accounts at one end of two micro-channels is provided. Each first-level indicator is divided into multiple second-level indicators, and each dimension data field corresponding to each second-level indicator is a third-level indicator;

[0024] Determine the seed account and multiple target accounts; collect the data of each dimension under the three-level indicators, and quantify the similarity of the data of each dimension;

[0025] Determin...

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 for recommending cross-source accounts on two micro-ends and one terminal, which includes: dividing the measurement indicators of cross-source account correlation between two micro-ends and one terminal into three levels, including multiple first-level correlation measurement indicators, and each first-level indicator There are multiple second-level indicators, and the corresponding dimension data fields of each second-level indicator are third-level indicators; determine the seed account and multiple target accounts; collect the data of each dimension under the third-level indicators, and quantify the similarity of each dimension data ;Determine the weight of the first-level indicators and the weights of each second-level indicator under the first-level indicators based on the user's attention requirements; calculate the weighted sum of the data similarity of each dimension under the various third-level correlation measurement indicators and their respective weights, and obtain each target account Relevance index, and recommend these target account relevancy indexes in reverse order. The recommendation method of the present invention can perform account recommendation across sources, and the recommendation result is accurate and reasonable.

Description

technical field [0001] The invention relates to the technical field of Internet applications. More specifically, the present invention relates to a cross-source account recommendation method for two micro-channels and one terminal. Background technique [0002] At present, the method of recommending related accounts through known accounts is mainly aimed at a single source of Weibo, and the recommendation methods mostly use following relationship information for recommendation, or recommend through user registration information, such as address book information, school and work information filled in when registering an account. Wait. These account recommendation methods have the problem of a single factor in the recommendation results. The account information that some users care about is often ranked after the big V accounts because of the small number of fans and the small amount of blogging. SUMMARY OF THE INVENTION [0003] An object of the present invention is to so...

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): G06F16/958G06Q10/06G06Q50/00
CPCG06Q10/06393G06Q50/01
Inventor 张旭刘春阳李雄王慧王臻
Owner NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT
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