Commodity recommending method and system based on offline behavior
A product recommendation and behavior technology, applied in neural learning methods, marketing, special data processing applications, etc., can solve the problems of poor recommendation effect, low purchase conversion rate, and inability to accurately predict the products that offline customers like, so as to improve purchases. Conversion rate, the effect of improving accuracy
Inactive Publication Date: 2018-09-21
帷幄匠心科技(杭州)有限公司
View PDF7 Cites 20 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This method is only an extensive product recommendation form, and the recommendation effect is poor; and it does not take into account the behavior characteristics of offline customers, resulting in the inability to accurately predict the products that offline customers may like, the recommended products cannot meet the needs of customers, and the purchase conversion rate is low. Low
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
[0041] The above and other technical features and advantages of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Apparently, the described embodiments are only some of the embodiments of the present invention, not all of them.
[0042] see figure 1 The method for recommending products based on offline behavior provided in Embodiment 1 of the present invention includes the following steps;
[0043] S100. Obtain customer characteristic information and behavior interaction information of the customer and commodity characteristic information of the product, and screen the behavior interaction information to obtain browsing interaction information;
[0044] S200. Using machine learning to establish a product recommendation model based on customer feature information, behavior interaction information, and product feature information; when building a product recommendation model, use browsing interaction information a...
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 commodity recommending method and system based on offline behavior. The method comprises the following steps: screening acquired behavior interaction information of customersto obtain browse interaction information; establishing a commodity recommendation model by utilizing machine learning according to the obtained customer feature information, the behavior interactioninformation and commodity feature information; when the commodity recommendation model is established, taking the browse interaction information as a negative sample; acquiring current customer feature information and current behavior interaction information of customers, and determining corresponding recommend commodity information through the commodity recommendation model according to the current customer feature information and the current behavior interaction information; moreover, recommending the commodity recommendation information to corresponding customers in real time. According tothe commodity recommending method and the commodity recommending system, disclosed by the invention, the behavior interaction information is considered and the browse interaction information in the behavior interaction information is divided into the negative samples, so that the prediction accuracy of the commodity recommendation model is effectively improved; the recommendation commodity information satisfies the demands of the customers and the effect of purchase conversion rate of the customers on the recommended commodity is improved.
Description
technical field [0001] The present invention relates to the technical field of information recommendation, in particular to a commodity recommendation method and system based on offline behavior. Background technique [0002] With the development of information technology, computers and the Internet are widely used in all walks of life, and have brought great changes to people's communication, travel methods and industrial production methods. As a product of the information age, e-commerce has risen rapidly in recent years, and has had a great impact on the traditional physical retail industry with its characteristics of low cost, high efficiency, globalization and interactivity. [0003] In physical stores, the existing recommendation method is to recommend products to customers in the form of advertisements directly through billboards or setting playback devices according to the needs of store sales. This method is only an extensive product recommendation form, and the re...
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 IPC IPC(8): G06Q30/02G06F17/30G06N3/08
CPCG06N3/084G06Q30/02
Inventor 叶生晅
Owner 帷幄匠心科技(杭州)有限公司