Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Content intelligent recommendation and distribution method and system based on multi-element collaboration

A technology for distributing systems and content, applied in the field of Internet applications, can solve problems such as large manpower consumption and material resource costs, and achieve the effect of expanding the domain of interest and saving labor and material costs.

Pending Publication Date: 2020-04-14
GUANGDONG UCAP INTERNET INFORMATION TECH +1
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The current content recommendation system is generally based on the similarity recommendation based on object attributes or user attributes. The problem with this recommendation method is that the quality of the recommendation depends entirely on whether the attribute characteristics of the object or user are complete. However, building a full and complete attribute feature library often consumes a lot of manpower and material costs.

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
  • Content intelligent recommendation and distribution method and system based on multi-element collaboration
  • Content intelligent recommendation and distribution method and system based on multi-element collaboration
  • Content intelligent recommendation and distribution method and system based on multi-element collaboration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] see figure 1 , which is a method for intelligent recommendation and distribution of content based on multiple collaborations provided in this embodiment, the examples given are only used to explain the present invention, and are not used to limit the scope of the present invention. The specific implementation steps are as follows:

[0038] S1. The system obtains the full amount of content through an external source system interface, wherein the full amount of content may include crawling by crawlers, UGC (user-generated content) and PGC (professional production content), etc.;

[0039] S2. Manually set or system automatically set filter conditions;

[0040] S3. Filter the content with defects or problems in the full amount of content, wherein the defects or problems may include low quality, containing sensitive words, garbled characters, and missing content;

[0041] S4. The aggregated and filtered content is merged into the library;

[0042] S5. Build an algorithm c...

Embodiment 2

[0059] see figure 2 , which is an intelligent content recommendation and distribution system based on multiple collaborations provided in this embodiment, the examples given are only used to explain the present invention, and are not used to limit the scope of the present invention. The specific structure is as follows:

[0060] Content Standards Center: Obtain full content from external source systems, set filter conditions manually or automatically by the system, and filter content with defects or problems in the full content;

[0061] Content resource library: aggregate and filter content into the library;

[0062] Interface management module: manage the external source system and each release terminal interface, wherein each release terminal includes WeChat open platform, Tencent open platform and Weibo open platform, etc.;

[0063] Manual collaboration unit: perform manual sorting and manual release of the stored content, which further includes:

[0064] Content manua...

Embodiment 3

[0074] see image 3 , a method for intelligent recommendation and distribution of news content based on user-similarity and content-similarity recommendation algorithms provided in this embodiment, the examples given are only used to explain the present invention, not to limit the scope of the present invention. The specific implementation steps are as follows:

[0075] 1. Recommendation algorithm based on user similarity

[0076] a. Record the news content dataset and the current user, and find out other users with similar preferences to the current user. Calculation method:

[0077]

[0078] Among them, sim(i, j) is the similarity between user i and user j, I ij is the news content co-browsed by user i and user j, R i，x is the rating of user i on news content x, The average score of all ratings for user i.

[0079] b. Record the news content that is not recommended to the current user, and use users with similar preferences to the current user to predict the score ...

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 provides a content intelligent recommendation and distribution method and system based on multi-element collaboration. The system comprises a manual collaboration unit, an algorithm collaboration unit and a social collaboration unit. Compared with the prior art, the system provided by the invention has the advantages that a ternary collaboration system of artificial collaboration, social collaboration and algorithm collaboration is constructed, a full-amount and complete attribute feature library is created; accurate matching of content and a user is achieved; the content platform is helped to establish content adjustability through manual cooperation; the content exposure amount is improved through social cooperation; and the content platform is helped to accurately distribute interested content to the user through algorithm cooperation. The method comprises the steps of creating a scoring matrix of 'user + content'; performing similarity calculation on the user vector and the content vector by utilizing statistical data; predicting user preferences ; and realizing intelligent recommendation and distribution of content . An optimal recommendation result is provided for the user by setting a content quality influence factor definition content scoring formula. The interest domain of the user is expanded, and manpower and material resource costs are saved.

Description

technical field [0001] The present invention relates to the field of Internet application technology, in particular to a multi-collaboration-based intelligent content recommendation and distribution method and system thereof. Background technique [0002] In the past ten years, with the popularization of mobile devices, the content industry has undergone earth-shaking changes. In particular, content production industries such as social media and news information have shown explosive growth, gradually expanding from a single business model to a multi-business model. The public's enthusiasm for media content production is unprecedentedly high. The content industry has entered the era of mass media, and a large number of UGC and PGC content are produced every day. So how to select high-quality and high-value content from massive content reports, and accurately distribute it to users who are interested in it, while preventing users from entering the island of interest, has becom...

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): G06F16/9536
CPCG06F16/9536
Inventor 汪敏严妍贾亦赫董瑞代丽娟
Owner GUANGDONG UCAP INTERNET INFORMATION TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com