Supercharge Your Innovation With Domain-Expert AI Agents!

A Recommendation Method Based on Deep Learning

A recommendation method and deep learning technology, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as unpredictability of latent factor vectors and inaccurate recommendations, so as to improve recommendation performance, training efficiency, and accuracy degree of effect

Active Publication Date: 2022-06-21
SHENZHEN THINKIVE INFORMATION TECH CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the problem that the existing recommendation method cannot effectively predict the latent factor vector of the item from the text content information containing the description and metadata of the item, resulting in inaccurate recommendation; the present invention provides A Recommendation Method Based on Deep Learning

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 Recommendation Method Based on Deep Learning
  • A Recommendation Method Based on Deep Learning
  • A Recommendation Method Based on Deep Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention.

[0057] (1) Collect the user's historical behavior data, and use the implicit feedback-based Weighted Latent Factor Model (WLFM) to model the user's historical behavior information, and learn to obtain the latent factor vectors of users and items. ,Specific steps are as follows:

[0058] (11) For user historical behavior data r ui Perform normalization by introducing a binary variable p ui , assuming there are m users and n items, binarize user u's preference for item i into a preference matrix The formula is as follows:

[0059]

[0060] (12) The preference matrix P contains both p...

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 recommendation method based on deep learning, which belongs to the field of data mining technology, and solves the problem that the existing recommendation method cannot predict the latent factor vector of the item from the text content information including the description and metadata of the item. Causes the problem of inaccurate recommendation; the present invention models the implicit feedback characteristics of the user's historical behavior data, and learns the hidden factor vector of the user and the item after modeling; uses the hidden factor vector of the item as a label to train the text content of the item The network model for modeling and deep mining of time series information; for new items that do not appear in the user's historical behavior data, the hidden factor of the item is obtained by predicting the network model obtained through step (2) in the text content information of the item vector, and then directly match it with the user latent factor vector obtained in step (1), and sort the matching degrees to obtain a new item recommendation list for each user. The present invention is used for the recommendation of new items.

Description

technical field [0001] A recommendation method based on deep learning is used for recommending new items, and belongs to the technical fields of data mining, natural language processing, and personalized recommendation. Background technique [0002] Content-based recommendation usually predicts user preferences from content information such as item descriptions and metadata. The most basic recommendation algorithm is to recommend based on the available metadata of the item. For example, in the movie recommendation, the metadata of the movie may include the category attribute of the movie, the actors involved, the director of the production, and the popular rating of the movie, etc. However, this will result in predictable recommendations. For example recommending movies of actors that the user is already familiar with, usually this would not be a valid recommendation. Another recommendation algorithm is to recommend based on the description information of the item. For exa...

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): G06F16/9535G06N3/08
CPCG06N3/08
Inventor 石鑫屈鸿符明晟史冬霞
Owner SHENZHEN THINKIVE INFORMATION TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com