A method and device for reducing sample space in BPR
A sample space and space technology, applied in the field of recommendation systems, can solve the problems of negative sample sampling and inefficient product recommendation, and achieve the effect of reducing the negative sample space and improving efficiency
Active Publication Date: 2022-07-08
TSINGHUA UNIV
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0008] In order to overcome the above-mentioned existing BPR model based on the entire negative sample space, which leads to the inefficiency of negative sample sampling and product recommendation, or at least partially solve the above-mentioned problems, the present invention provides a method and device for reducing the sample space in BPR
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 Construction
[0025] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and embodiments. The following examples are intended to illustrate the present invention, but not to limit the scope of the present invention.
[0026] In an embodiment of the present invention, a method for reducing sample space in BPR is provided, figure 1 A schematic diagram of the overall flow of the method for reducing sample space in BPR provided by the embodiment of the present invention, the method includes: S101, for any user in the target shopping system, obtain the negative sampling proportional coefficient corresponding to the user according to the commodities purchased by the user, Take the commodities in the complete set of commodities of the target shopping system except the commodities purchased by the user as the negative sample candidate set;
[0027] The target shopping system is a shopping system that needs to recom...
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 present invention provides a method and device for reducing sample space in BPR. The method includes: for any user in a target shopping system, obtaining a negative sampling proportional coefficient corresponding to the user according to the commodities purchased by the user, and converting the target The commodities in the complete set of commodities of the shopping system except the commodities purchased by the user are taken as the negative sample candidate set; according to the negative sampling proportional coefficient corresponding to the user and the negative sample candidate set, the negative sample space corresponding to the user is obtained. The invention reduces the negative sample space, and on the basis of ensuring the recommendation performance, the product recommendation is performed based on the reduced negative sample space, and the efficiency of the product recommendation is improved.
Description
technical field [0001] The present invention belongs to the technical field of recommendation systems, and more particularly, relates to a method and device for reducing sample space in BPR. Background technique [0002] Personalized sorting refers to providing users with a list of products for users to choose from, also known as product recommendation. A typical example is that an e-commerce company wants to recommend a personalized ranking list of products that the user may have purchased to the user. In most application scenarios, such a sorted list can only be inferred from the implicit feedback behavior between users and products. For example, purchases are implicit feedback, while product ratings are explicit feedback. The feature of implicit feedback recommendation system is that only the positive feedback behavior of the user can be observed, such as purchasing a product, while the unobserved behavior, that is, a user has not purchased a certain product, is composed...
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 Patents(China)
IPC IPC(8): G06Q30/06
CPCG06Q30/0631
Inventor 金德鹏丁璟韬李勇
Owner TSINGHUA UNIV