Commodity recommendation method based on Tucker decomposition and knowledge graph
A knowledge graph and product recommendation technology, applied in business, instrumentation, data processing applications, etc., can solve the problems of missing information, inability to recommend system learning, simple knowledge graph completion model, etc., to achieve the effect of improving the accuracy of recommendation
Active Publication Date: 2022-03-25
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Some existing models that combine knowledge graph completion tasks and recommendation system tasks have some problems. The main reason is that the knowledge graph completion model used is too simple, and the representation of entities and relationships in the knowledge graph learned by this method will be missing. Some information, and the inner product between vectors is often used in the recommendation module to calculate the recommendation score of the product for the user. This simple method cannot fully enable the recommendation system to learn the representation of users and products.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0034] This embodiment proposes a product recommendation method based on Tucker decomposition and knowledge graph, based on such as figure 1 The shown model is realized by a recommendation system module and a knowledge map module, and the recommendation system module includes a product feature vector generation module and a preference feature vector generation module.
[0035] The product recommendation method includes the following steps:
[0036] Step 1: Construct a recommendation learning database based on the interaction records between users and products in the past. The way of interaction can be that a certain user has clicked on a certain product; construct multiple triplets in the form of A knowledge graph database that composes and contains the information of all commodities in the recommended learning database, in which the head entity and the tail entity belong to entities; since the actual meaning of the entity corresponding to the commodity in the knowledge graph...
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
Login to view more Abstract
The invention discloses a commodity recommendation method based on Tucker decomposition and a knowledge graph, which belongs to the technical field of information recommendation, and comprises the following steps: firstly, constructing a recommendation learning database, a knowledge graph database and a contact data table; initializing to obtain feature vectors of each user, each commodity, each entity and each relation; respectively calculating to obtain a commodity feature vector and a preference feature vector, learning recommendation system information by adopting inverse operation of Tucker decomposition in combination with the user feature vector, extracting triple and learning knowledge graph information by adopting the inverse operation of Tucker decomposition, and respectively obtaining corresponding score functions; and training by taking the recommendation learning database and the knowledge graph database as a training set, and carrying out top-N commodity recommendation on the user by using the trained model. According to the method, the knowledge graph completion task and the recommendation system task are jointly learned, and the score of the recommendation system is calculated by using the inverse operation of Tucker decomposition, so that the recommendation result is improved.
Description
technical field [0001] The invention belongs to the technical field of information recommendation, and in particular relates to a product recommendation method based on Tucker decomposition and knowledge graph. Background technique [0002] At present, it is gradually becoming a trend to introduce knowledge graphs into recommendation systems. The rich entity information and relationship information in the knowledge graph can help the recommender system to understand the relationship between users and products at a deeper level, thus providing more accurate recommendation results. [0003] The knowledge graph is essentially a collection of triples, where the triples are in the form of <head entity, relation, tail entity>. Each triple represents a fact in real life, such as the triple <Joss Whedon, director of, The Avengers> represents the fact that "Joss Whedon is the director of the Avengers". The knowledge map completion task is an important task in the field ...
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
Login to view more Patent Type & Authority Applications(China)
IPC IPC(8): G06Q30/06G06F16/2458
CPCG06Q30/0631G06F16/2458
Inventor 曹扬杨波李少松
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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
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