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

User intention and data collaboration non-personalized recommendation algorithm model

A recommendation algorithm and user intent technology, applied in the field of information processing, can solve the problems of attenuation of user intent, weakening of the variability of user recommended content, and inability to push content that users are interested in, so as to achieve the effect of ensuring accuracy

Pending Publication Date: 2020-09-04
镇江纵陌阡横信息科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The personalized recommendation algorithm model has a cold-start stage of data accumulation, that is, the user's personalized recommendation cannot effectively analyze the user's intention at the beginning, and cannot perceive the user's intention in the early stage and push the content that the user is interested in to the user.
[0003] At the same time, the long-term personalized recommendation of users by conventional recommendation algorithms will lead to attenuation of user intentions, weaken the variability of user recommendation content, and fail to perceive the momentary changes of user intentions. A large number of data models are needed to obtain the correct balance.

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
  • User intention and data collaboration non-personalized recommendation algorithm model
  • User intention and data collaboration non-personalized recommendation algorithm model
  • User intention and data collaboration non-personalized recommendation algorithm model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] A non-personalized recommendation algorithm model in which user intent and data are coordinated, comprising the following steps:

[0038] S1: The user enters the intention;

[0039] S2: extracting the keyword intent of the user input intent;

[0040] S3: If the number of times or frequency of use of the user is low, the collaborative filtering recommendation algorithm is used for calculation; if the number of use of the user is large and the calculation collects the usage habits of many users, the calculation is performed using the content-based personalized recommendation algorithm;

[0041] S4: Carry out data recommendation, get the recommended content that matches the user's intention after calculation, and recommend it to the user.

[0042] In S1, the input of the user's intention includes voice input and text input, that is, the user can express the intention through voice or text, and when the user performs voice input, the following steps are included:

[0043]...

Embodiment 2

[0063] A non-personalized recommendation algorithm model in which user intent and data are coordinated, comprising the following steps:

[0064] S1: The user enters the intention;

[0065] S2: extracting the keyword intent of the user input intent;

[0066] S3: If the number of times or frequency of use of the user is low, the collaborative filtering recommendation algorithm is used for calculation; if the number of use of the user is large and the calculation collects the usage habits of many users, the calculation is performed using the content-based personalized recommendation algorithm;

[0067] S4: Carry out data recommendation, get the recommended content that matches the user's intention after calculation, and recommend it to the user.

[0068] In S1, the input of the user's intention includes voice input and text input, that is, the user can express the intention through voice or text, and when the user performs voice input, the following steps are included:

[0069]...

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 user intention and data collaboration non-personalized recommendation algorithm model, and relates to the technical field of information processing. The method comprises thefollowing steps: enabling a user to input an intention to extract a keyword intention of the user input intention; performing calculating by utilizing a collaborative filtering recommendation algorithm if the use frequency or frequency of the user is low, and performing calculating by utilizing a content-based personalized recommendation algorithm if the use frequency of the user is high and the use habits of a plurality of users are collected in a calculation set; and performing data recommendation, performing calculation to obtain recommended content matched with the user intention, and recommending the recommended content to the user. According to the invention, different algorithms can be selected for calculation according to different use frequencies of users; and the similar data obtained after calculation is recommended to the user, so that items with cold start, popularity prejudice and rare characteristics can be recommended, accidents can be generated, diversified non-personalized recommendation can be realized, and when the user has new behaviors, real-time change of a recommendation result can be certainly caused.

Description

technical field [0001] The invention relates to the technical field of information processing, in particular to a non-personalized recommendation algorithm model in which user intentions and data are coordinated. Background technique [0002] At present, the common personalized recommendation models in the market are based on user search terms or preset data scores to match user portraits accumulated over a long period of time for personalized recommendations. The personalized recommendation algorithm model has a cold-start stage of data accumulation, that is, the user's personalized recommendation cannot effectively analyze the user's intention at the beginning, and cannot perceive the user's intention in the early stage and push the content that the user is interested in to the user. [0003] At the same time, long-term personalized recommendation by conventional recommendation algorithms will lead to the attenuation of user intentions, weaken the variability of user recom...

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): G06F16/9532G06F16/9535G06F16/9536G10L15/22
CPCG06F16/9532G06F16/9535G06F16/9536G10L15/22G10L2015/223
Inventor 秦谦李宇鹏
Owner 镇江纵陌阡横信息科技有限公司
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