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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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