Recommendation system based on knowledge graph representation learning

A knowledge map and recommendation system technology, applied in relational databases, special data processing applications, instruments, etc., to achieve the effects of avoiding single type of results, improving interpretability, and improving divergence

Pending Publication Date: 2021-10-08
NANJING UNIV +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although they can improve recommendation performance, there are still many challenges

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
  • Recommendation system based on knowledge graph representation learning
  • Recommendation system based on knowledge graph representation learning
  • Recommendation system based on knowledge graph representation learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings. A recommendation system based on knowledge map representation learning, comprising the following steps:

[0049]Step 1. For heterogeneous sources, including relational databases, non-relational databases, and HDFS distributed file storage systems, and heterogeneous sources, including unstructured data, semi-structured data, and structured data, format data in accordance with the standard format ;

[0050] Step 2. Perform data preprocessing on the formatted data, and extract training and test data sets required to generate the knowledge graph representation learning algorithm model and the inference algorithm model based on knowledge graph representation learning;

[0051] Step 3. Construct a knowledge graph representation learning algorithm model and a recommendation algorithm model based on knowledge graph representation learning;

[0052] ...

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 provides a recommendation system based on knowledge graph representation learning. The recommendation system mainly comprises 1, a data format conversion module for formatting and converting heterogeneous data according to specifications, 2, a data preprocessing module for extracting a data set for model training test from the formatted data, 3, a data import and export module for completing data import and export operation of data among a relational database, a non-relational database and an HDFS, 4, a data storage module which penetrates through the operation cycle of the system and completes storage of source data, formatted data, preprocessed data, model result data, log data and the like, 5, a model construction module which is used for constructing a knowledge graph representation learning algorithm model and a recommendation algorithm model based on knowledge graph representation learning, and 6, a data visualization and interaction module which is used for displaying a model operation result to a user, wherein the model operation result comprises a loss curve graph, result numerical display and interaction based on a user recommendation result.

Description

technical field [0001] The invention belongs to the field of combining knowledge graphs and recommendation systems, and in particular relates to an optimized knowledge graph representation learning algorithm. The application of the knowledge map in the recommendation system is still immature. The present invention applies the knowledge map to the recommendation system, and provides intuitive operation methods such as integration and webpage. Background technique [0002] With the rapid development of the mobile Internet, we have entered the era of information explosion. At present, there are more and more platforms providing services through the Internet, and corresponding types of services (shopping, video, news, movies, music, social networking, etc.) emerge in endlessly. Facing the exponential growth of network resources and causing people to face information overload, how to present interesting information to users has become a hot research challenge. Recommendation is...

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): G06F16/9535G06F16/28
CPCG06F16/9535G06F16/288
Inventor 陈境高阳
Owner NANJING 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