Click rate prediction method and device based on commodity representation
A prediction method and click-through rate technology, applied in the field of data processing, can solve problems such as inability to effectively reflect product characteristics and inaccurate click-through rate predictions, and achieve the effects of improving expression efficiency and accuracy, increasing revenue, and increasing click-through rate
Pending Publication Date: 2021-11-12
ALIBABA GRP HLDG LTD
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
It can be seen that the existing multi-modal product representation cannot effectively reflect the product characteristics, resulting in inaccurate click-through rate prediction based on this product representation.
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
[0028] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.
[0029] In the click-through rate prediction method based on commodity representation proposed by the embodiment of the present invention, a new commodity representation method is proposed, especially for commodities provided in e-commerce, which are usually represented by multiple heterogeneous modalities, However, the existing product representation only extracts features from different modes of the product according to fixed weights, and for d...
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 click rate prediction method and device based on commodity representation, relates to the technical field of data processing, and mainly aims to perform more accurate commodity representation on multi-modal commodities so as to improve the accuracy of click rate prediction. According to the main technical scheme of the invention, the method comprises the steps: obtaining a user behavior of a target user and a group of multi-modal information corresponding to a target commodity; using the first model to determine unique features corresponding to each group of multi-modal information, the unique features including features existing in one mode and having dynamic weights for different modes; determining common features corresponding to each group of multi-modal information by using a second model, wherein the common features comprise features co-existing in multiple modals; respectively determining a user representation of the target user and a commodity representation of the target commodity according to the unique features and the common features; and processing the user representation and the commodity representation by using a deep neural network to obtain the probability that the target user clicks the target commodity.
Description
technical field [0001] The present invention relates to the technical field of data processing, in particular to a method and device for predicting click rate based on product representation. Background technique [0002] Existing large-scale e-commerce portals provide hundreds of millions of users with billions of products through mobile applications and PC websites. In order to obtain better user experience and business effects, more accurate and effective representations of products are helpful for recommending products to users. The products they follow and like, so as to increase the click-through rate of recommended products. The more accurate the click-through rate prediction of commodities, the more effectively the revenue of e-commerce and platforms can be improved. [0003] At present, commodities in e-commerce usually have multiple heterogeneous modal representations, such as commodity names, images, titles, and statistical features. For item representation, fea...
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): G06F16/9535G06F16/958G06Q30/06
CPCG06F16/9535G06F16/958G06Q30/0601
Inventor 李响
Owner ALIBABA GRP HLDG LTD