Unlock instant, AI-driven research and patent intelligence for your innovation.

Commodity recommendation method and device

A product recommendation and product technology, applied in the field of implicit feedback recommendation, can solve the problem of dislike and achieve the effect of good recommendation effect

Active Publication Date: 2021-10-26
杭州贝购科技有限公司 +1
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Considering that there are differences in the popularity of products, popular products are more likely to be known by users, and if users are not observed to buy a popular product, then compared with unpopular products, the user is more likely to be real don't like this trending item

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
  • Commodity recommendation method and device
  • Commodity recommendation method and device
  • Commodity recommendation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The specific implementation manners of the embodiments of the present invention will be further described in detail below in conjunction with the drawings and embodiments. The following examples are used to illustrate the embodiments of the present invention, but are not intended to limit the scope of the embodiments of the present invention.

[0030] In existing implicit feedback prediction models, only behaviors that can directly reflect user preferences (such as purchase behavior in product recommendation) are considered. But in fact, there are a lot of additional behaviors that users pay attention to during the process of purchasing products, such as clicking, browsing, searching and other behaviors. Compared with purchasing behaviors, these behaviors reflect users' preferences with lower credibility.

[0031] The inventive idea of ​​the embodiment of the present invention is to reflect the user's attention behavior in the prediction model based on the eALS algorith...

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

An embodiment of the present invention provides a commodity recommendation method and device, including: acquiring shopping data of a user group, using the shopping data to train a prediction model constructed based on the eALS algorithm, and obtaining each The user feature vector of the user and the product feature vector of each product; the inner product of the user feature vector and the product feature vector is used to characterize the user's predicted preference for the product; for any user in the user group, according to the user The inner product of the user's feature vector and each product's feature vector is used to obtain the user's predicted preferences for all products, and the user's product recommendation list is obtained according to the user's predicted preferences for all products. In the embodiment of the present invention, the eALS algorithm adds the influence of the product information concerned by the user, so that the constructed prediction model can more truly reflect the user's preference for the product, thereby achieving a better recommendation effect.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of implicit feedback recommendation, and more specifically, to a product recommendation method and device. Background technique [0002] The difficulty of the implicit feedback recommendation system lies in the processing of unobserved data. There are usually two methods to deal with unobserved data: (1) Based on the overall strategy, all unobserved samples are regarded as negative feedback, which has better convergence , but will generate a large number of inefficient negative samples; (2) Sampling-based strategy, sampling negative feedback samples from unobserved samples, this strategy can effectively reduce the number of negative samples during training, but the performance of the algorithm may be affected. [0003] Element-wise Alternating Least Squares (eALS) is an implicit feedback recommendation algorithm based on Matrix Factorization (MF). The optimization goals of eALS are as ...

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): G06Q10/04G06Q30/06
CPCG06Q10/04G06Q30/0631
Inventor 李勇郁佳杰丁璟韬张良伦金德鹏
Owner 杭州贝购科技有限公司