Data processing method, device and equipment

Abstract

The embodiments of the present application disclose a data processing method, device and device, which belong to the field of cloud technology-artificial intelligence services. The method includes: acquiring a sample data set, where the sample data set includes sample interest degrees of at least two sample objects and a distinguishing parameter used to distinguish the at least two sample objects, and extracting the predicted attribute feature vectors of the at least two sample objects by using a recommendation model, According to the prediction and recognition of the predicted attribute feature vector, the predicted interest degree of at least two sample objects is obtained, and the recommendation model is adjusted according to the predicted attribute feature vector, the distinguishing parameter, the predicted interest degree and the sample interest degree, and the adjusted recommendation model is used as the target recommendation model. , the degree of discrimination between the updated prediction attribute feature vectors output by the target recommendation model for at least two sample objects matches the degree of discrimination corresponding to the discrimination parameter. Through the example of the present application, the degree of discrimination of objects by the recommendation model can be improved, and accurate recommendation can be realized.

Description

technical field [0001] The present application relates to the field of cloud technology-artificial intelligence services, and in particular, to a data processing method, apparatus and device. Background technique [0002] With the development of the Internet and e-commerce, more and more merchants use online sales to sell goods, that is, merchants publish relevant information of goods (such as the type and price of goods) on the website, and users buy through the website. desired product. However, there are usually a large number of products on the website, and it takes a long time for users to find the products they want. Based on this, at present, products are mainly recommended for users according to their purchasing behaviors, so as to assist users to quickly find the products they want to buy. . For example, user A has purchased beer and diapers on the website, and the recommendation terminal determines that beer and diapers are similar, and will recommend beer and di...

AI Technical Summary

Problems solved by technology

However, the points of interest of different users are different, that is, the products that different users want to buy are inconsistent. Therefore, the accuracy of the product recommendation method based on user purchase behavior is relatively low.

Images