A cross-domain recommendation method combining personality characteristics under a neural network

A neural network and recommendation method technology, applied in the field of personalized recommendation, can solve the problems of low personalization accuracy and cold start, and achieve the effects of not being easy to change predictions, easy to predict, and improving recommendation accuracy

Active Publication Date: 2019-05-17
HARBIN ENG UNIV
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the existing technical difficulties such as low personalization accuracy and cold start, the present invention proposes a cross-domain recommendation method based on personality information

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
  • A cross-domain recommendation method combining personality characteristics under a neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] In order to facilitate the understanding of the present invention, the core part is how to use personality characteristics to build a neural network for personalized recommendation. After understanding the convolutional neural network CNN, the following is a detailed description:

[0019] The neural network we built is also composed of many convolutions, and the construction process is actually the data training process.

[0020] Specifically divided into three layers:

[0021] (1) The input layer is the input of keywords extracted from user data;

[0022] (2) The hidden layer is the key point. Bring the extracted data into the convolution formula to get the weight value of users with such personality characteristics and music / food with these keywords. The weight value is the degree of association Size, repeated convolution means that the next user is convolved on the basis of the previous one, that is, after many times, an interrelated neural network (to obtain mutual...

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 belongs to the field of personalized recommendation based on big data, and particularly provides a cross-domain recommendation method combining personality characteristics under a neuralnetwork. The cross-domain recommendation method specifically comprises the following steps of (1) acquiring data; (2) screening users; (3) extracting keywords, and (4) building a neural network, and(5) recommending personalized articles to people with similar personality characteristics according to the personality characteristics. According to the method, by combining personality characteristics, on the basis of a neural network, a convolutional neural network CNN is used for building a tranquillization network system, and related articles are recommended to users with similar personality characteristics. The personality characteristics are not easy to change and easy to predict, and the recommendation accuracy can be improved due to personalized recommendation based on the personalitycharacteristics.

Description

technical field [0001] The invention belongs to the field of personalized recommendation based on big data, and specifically proposes a cross-domain recommendation method combined with personality characteristics under a neural network. Background technique [0002] Personalized recommendation is playing an increasingly important role in today's big data era. How to use massive data to predict user behavior and accurately recommend items of interest to users is a concern of personalization researchers. [0003] Personality is a predictable and fairly stable factor that shapes human behavior. Of these, the 5-factor model is considered one of the most comprehensive models that can introduce five broad dimensions, so-called factors and characteristics, often referred to as the "Big Five" to describe an individual's personality: Openness to Existence (OPE) , Conscientiousness (COS), Extraversion (EXT), Agreeableness (AGR) and Neuroticism (NEU). Measurement of the Big Five is u...

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): G06F16/9535G06N3/04
Inventor 曲立平刘云鹏
Owner HARBIN ENG UNIV
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