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

Hidden feedback recommending method of multiple-GRU-layer neural network based on user space and system thereof

A neural network, user space technology, applied in the field of implicit feedback recommendation

Inactive Publication Date: 2018-04-13
NO 709 RES INST OF CHINA SHIPBUILDING IND CORP
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of this, it is necessary to provide a method and system for providing accurate recommendations for users by using user historical access records. This kind of recommendation scenario is based on implicit feedback recommendation. In order to solve the problem of implicit feedback recommendation, the present invention provides a user-based Method and system for implicit feedback recommendation of spatial multi-GRU layer neural network

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
  • Hidden feedback recommending method of multiple-GRU-layer neural network based on user space and system thereof
  • Hidden feedback recommending method of multiple-GRU-layer neural network based on user space and system thereof
  • Hidden feedback recommending method of multiple-GRU-layer neural network based on user space and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The present invention will be described in further detail below in conjunction with accompanying drawing

[0053] like figure 1 The implicit feedback recommendation method based on the user-space multi-GRU layer neural network includes the following steps:

[0054] 1) Collect the historical behavior information of the items accessed by the user, and generate training samples for each user according to the records of each user's access to the item and in the order of the behavior occurrence time;

[0055] Among them, the network service provider records the item information that the user has visited, and the record is a set of triplets (u, i, t), where u is the user number, i is the item number accessed by the user, and t is the time when the behavior occurred time.

[0056] 2) Map items to user space;

[0057] Among them, each item is represented by a vector v, which is randomly generated at the beginning, and each user has a matrix u representing its preference, whi...

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 relates to a hidden feedback recommending method of a multiple-GRU-layer neural network based on a user space and a system thereof. The method comprises the steps of through mapping an object to the user space, selecting an attention object characteristic for a user, performing multidirectional time sequence analysis according to a BP or PBTT algorithm and a recursion structure whichis unique in a multiple-GRU-layer neural network, predicating an interested object of the user according to the object sequence which is accessed by the user, and supplying a recommended service forthe user. The system comprises a historical behavior collecting module for an object which is accessed by the user, an object mapping user space module, a multiple-GRU-layer neural network training module and a recommending list generating module. Based on the system of the invention, the user behavior with relatively high randomness can be more accurately represented, and more accurate recommending result is obtained.

Description

technical field [0001] The invention relates to the technical field of system recommendation, in particular to an implicit feedback recommendation method and system based on a multi-GRU layer neural network in user space. Background technique [0002] Currently, network service providers provide users with online recommendation services such as news, commodities, pictures, videos, audio, documents, etc. (hereinafter collectively referred to as items). This kind of historical access records can only show that the user has a certain interest in the items that have been visited, and it does not mean that the user is not interested in the items that have not been accessed. This is because relative to the number of items that the user knows, the service provider provides The number of items is very large, the user does not visit an item may be because the user does not know the item, rather than dislike the item, this kind of ambiguous user feedback brings difficulties to the rec...

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
IPC IPC(8): G06Q30/06G06Q30/02G06N3/04
CPCG06Q30/0201G06Q30/0631G06N3/045
Inventor 刘俊涛张毅王元斌
Owner NO 709 RES INST OF CHINA SHIPBUILDING IND CORP
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