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

A Rating Prediction Method for Joint Topic Model and Heterogeneous Information Network

A technology of heterogeneous information network and topic model, applied in the field of score prediction in recommendation system, can solve the problems of poor interpretability and low accuracy

Active Publication Date: 2020-05-22
温州开晨科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the prior art, the present invention provides a score prediction method that combines topic models and heterogeneous information networks to solve the problems of cold start, poor interpretability, and low accuracy in score prediction

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 Rating Prediction Method for Joint Topic Model and Heterogeneous Information Network
  • A Rating Prediction Method for Joint Topic Model and Heterogeneous Information Network
  • A Rating Prediction Method for Joint Topic Model and Heterogeneous Information Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The accompanying drawing discloses a schematic flow diagram of a preferred embodiment involved in the present invention; the technical scheme of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0055] Step 1. Construct vector representations of users and products:

[0056] 1-1 First obtain the contextual vector representation of a word in the comment through bidirectional lstm. Assume that users can be expressed as a K-dimensional latent factor vector, where each dimension represents the user's preference for related topics.

[0057] 1-2 The traditional LDA model assumes that the document is a multinomial distribution of topics, and the topic is a multinomial distribution of words; since the importance of each comment is different for each topic, the importance of different words to the topic is also different, so We set a context topic vector v for each topic k ∈R dim , for the i-th comment of the user, express...

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 rating prediction method for a joint topic model and a heterogeneous information network. The steps of the present invention are as follows: step (1) for a designated user commodity pair, use a topic model to extract comment information, thereby constructing a vector representation of the user and commodity; step (2) construct a heterogeneous information network by using commodity attribute information and user common purchase information; Step (3) Extract the final relationship representation vector of the user-product pair from the heterogeneous network; Step (4) For the user-product pair, connect the user vector, relationship representation vector, and product vector representation, and input it to AFM to achieve score prediction; step 5. According to the predicted scoring data calculated by the model and the real scoring data, calculate the RMSE value, and use this value as the evaluation index of the model effect. The invention solves the problems of cold start, poor explainability and low accuracy in score prediction.

Description

technical field [0001] The invention relates to the field of score prediction in recommendation systems, in particular to a score prediction method for joint topic models and heterogeneous information networks. Background technique [0002] There are currently three types of methods for predicting users' ratings for unpurchased products: [0003] The first is to use collaborative filtering to achieve rating prediction based on user historical rating records. This method will cause cold start problem for sparse user rating data. [0004] The second is to use comment and rating information to achieve rating prediction. LDA is a relatively traditional method of analyzing comment data, but currently more methods are used to process comment information through deep learning such as CNN. This method ignores the inherent attribute information of the product and the prediction effect of the user's common purchase information is not good. [0005] The third is to construct a heter...

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): G06Q30/02G06F16/35G06K9/62
CPCG06Q30/0202G06Q30/0201G06F16/35G06F18/24147
Inventor 汤景凡张秀杰张旻姜明黄涛吴鑫强
Owner 温州开晨科技有限公司
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

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