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

Professional field system cold start recommendation method based on knowledge graph

A professional field and knowledge graph technology, applied in the fields of natural language processing and data mining, can solve problems such as inability to achieve system cold start, poor accuracy, etc.

Active Publication Date: 2019-11-08
杭州智策略科技有限公司
View PDF3 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005]Aiming at the shortcomings of existing recommendation methods that cannot achieve system cold start and poor accuracy, the present invention proposes a system cold start recommendation based on knowledge graphs method, considering user registration information and item content information at the same time, to achieve a cold start of the system; build a knowledge graph based on professional domain knowledge, to achieve accurate and quantitative matching of user registration information and item content 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
  • Professional field system cold start recommendation method based on knowledge graph
  • Professional field system cold start recommendation method based on knowledge graph
  • Professional field system cold start recommendation method based on knowledge graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further described below in conjunction with the accompanying drawings.

[0034] refer to Figure 1 ~ Figure 3 , a cold-start recommendation method for professional domains based on knowledge graphs, including the following steps:

[0035] (1) Construction of professional domain knowledge graph: construct professional domain knowledge graph in a semi-automatic way, first manually initialize professional domain knowledge graph based on professional domain classification directory, and then use Internet knowledge to automatically expand professional domain knowledge graph;

[0036] (2) User / item portrait and word vector training: extract tags from user registration information and item description text, and train professional field word vectors based on Internet texts;

[0037] (3) User / item matching score: firstly, link user tags and item tags in the knowledge graph respectively, and then calculate the user / item matching value based on the s...

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

A professional field system cold start recommendation method based on a knowledge graph comprises the following steps of (1) constructing the professional field knowledge graph in a semi-automatic mode, firstly, the professional field knowledge graph is manually initialized based on a professional field classification directory, and then the professional field knowledge graph is automatically expanded through internet knowledge; (2) respectively extracting tags from registration information of a user and a description text of an article, and training a professional field word vector based on an internet text; (3) firstly, respectively carrying out entity linking on the user label and the article label in the knowledge graph, and then calculating a user / article matching degree value based on the shortest path between link nodes; and (4) recommending a plurality of articles with the highest matching degree values to the user. User registration information and article content informationare considered at the same time, and cold start of the system is achieved; a knowledge graph is constructed based on professional domain knowledge, and accurate and quantitative matching of user registration information and article content information is realized.

Description

technical field [0001] The present invention relates to natural language processing and data mining technology, in particular to a recommendation method. Background technique [0002] The cold-start recommendation problem is divided into three categories: user cold-start recommendation, item cold-start recommendation and system cold-start recommendation. Among them, user cold start refers to making recommendations for new users, item cold start refers to recommending new items to interested users, and system cold start refers to personalized recommendations in a newly developed system (that is, no user behavior data at all). Obviously, the system cold start has the least available data and is the most difficult to implement. [0003] The existing methods to solve the cold-start recommendation problem mainly include the following: (1) Provide non-personalized recommendations (such as recommended hot list), but the items recommended by this method cannot meet the personalized...

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): G06F16/9535G06F16/9538G06F16/36G06F16/332G06F17/27
CPCG06F16/9535G06F16/9538G06F16/367G06F16/332
Inventor 吕明琪王琦晖邢顺华
Owner 杭州智策略科技有限公司
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