Scoring prediction method and device thereof

A technology of score prediction and score value, applied in data processing applications, biological neural network models, instruments, etc., can solve problems such as low efficiency, labor cost, and unreasonable application scenarios of recommendation systems, so as to improve accuracy and widely The effect of practicality

Inactive Publication Date: 2018-10-16
EAST CHINA NORMAL UNIV
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Such a method consumes labor costs and is not efficient
In order to overcome the problems of cost and efficiency, there are still some existing technologies that use machine learning methods to try, but there is a problem in these existing technologies. When predicting the rating of the target product, the target user's rating of the product is often used. Scoring, but this is unreasonable in the actual recommendation system application scenario

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
  • Scoring prediction method and device thereof
  • Scoring prediction method and device thereof
  • Scoring prediction method and device thereof

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0024] figure 1 is a flowchart of the score prediction method 100 according to an embodiment of the present invention. Such as figure 1 As shown, the specific processing flow of this method is as follows:

[0025] S110. Generate a portrait of both the user and the item by constructing a neural network model of user comments on the item.

[0026] According to the embodiment of the present invention, in order to better capture the contextual information of text such as user comments, and the global characteristics of users and products to obtain the portrait information of users and items, a long-short-term memory neural network can be used. The network can fully capture fine-grained text semantic information from the character, word and sentence levels, taking into account emotion and context factors through a hierarchical structure. Such as figure 2 As shown, assume that X represents an input comment, which contains n sentences {S 1 , S 2 ,...,S n}, l i Indicates the ...

no. 2 example

[0048] Figure 4 is a schematic block diagram of a score prediction device 400 according to an embodiment of the present invention. This device is used for carrying out above-mentioned method flow process, comprises:

[0049] The generating module 410 is used to generate portraits of both the user and the item by constructing a neural network model for user comments on the item;

[0050] The prediction module 420 is configured to optimize the matrix factorization model by using the portraits of users and items, and train the matrix factorization model to predict the target score.

[0051] Optionally, the neural network model is a long-short-term memory network model, and features of users and items are extracted by using an attention mechanism in the long-short-term memory network model, and portraits are generated according to the features.

[0052] Optionally, user and item profiles are added to the matrix factorization model via nonlinear transformations.

[0053] The fi...

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 scoring prediction method and device thereof. The method comprises the following steps of: a generating step: generating a representation of both a user and an item by constructing a neural network model for a user review of an item; a prediction step: optimizing a matrix decomposition model by utilizing the representation of a user and an item, and training the matrix decomposition model to predict target score, wherein the neural network model is a long and short time memory network model; extracting features of the user and the item by using an attention mechanismin the long and short time memory network model, and generating representation according to features; and adding the representation of the user and the item to the matrix decomposition model by nonlinear transformation. The scoring prediction method and device thereof provided by the invention is low in cost, and migration can be well performed among different data fields; the unknown score can bepredicted more comprehensively and correctly by combining the user scoring numerical information and the user comment text information; the prediction results can be obtained in a faster time with anoptimized matrix decomposition algorithm.

Description

technical field [0001] The present invention relates to the field of rating prediction of recommendation systems, in particular to a method and device for rating prediction of user and item portraits. Background technique [0002] With the development of modern society, including e-commerce platforms (e.g., Alibaba and JD.com), web portals (e.g., Google and Yahoo), social media (e.g., WeChat and Twitter), and location-based social networks (e.g., Foursquare) and Yelp) have greatly changed the way people live and think. Frequent commercial activities and user behaviors generate a large amount of data, which contains rich and valuable information, but at the same time, these data also bring about the problem of information overload. For example, on shopping websites, users are getting more and more The more difficult it is to find the one you really like among the dazzling array of products. The recommendation system provides a perfect solution to solve this problem, that 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
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q30/02G06N3/04
CPCG06Q30/0202G06N3/049G06Q30/0282
Inventor 贺樑陈璐
Owner EAST CHINA NORMAL 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