Product recommendation method and device, server and storage medium

Abstract

The embodiment of the invention discloses a product recommendation method and device, a server and a storage medium. The method comprises the steps: obtaining the user data of a target customer, and determining a user feature vector X = (x1, x2,..., xn) T according to the user data; calculating according to the user feature vector X = (x1, x2,..., xn) T and the weight vector Wi = (wi1, wi2,..., win) T of the ith product in the products to obtain a recommended predicted value zi = WiT * X of the target client for the ith product; converting the recommendation prediction value of the ith productinto a probability, obtaining a recommendation success probability value of the target client for the ith product, and determining the product corresponding to the maximum recommendation success probability value of each product as the target product; obtaining customer service corpora of the target product from a customer service corpus; and when the recommendation triggering condition is met, sending customer service corpus to the target client. By adopting the method, the product recommendation success rate can be improved.

Description

technical field [0001] The present application relates to the technical field of intelligent recommendation, in particular to a product recommendation method and device, a server, and a storage medium. Background technique [0002] At present, with the enrichment of product lines and the increase of product types of major financial institutions, it is necessary to carry out multi-product recommendation activities to customers. In view of the large number of customers of each financial institution, the cost of effective recommendation to customers is also high, resulting in a smaller coverage of product recommendations, often only a part of customers can be randomly selected from a large number of customer groups for product recommendation, resulting in product recommendation The success rate is not high. Contents of the invention [0003] Embodiments of the present application provide a product recommendation method and device, a server, and a storage medium, in order to ...

AI Technical Summary

Problems solved by technology

In view of the large number of customers of each financial institution, the cost of effective recommendation to customers is also high, resulting in a smaller coverage of product recommendations, often only a part of customers can be randomly selected from a large number of customer groups for product recommendation, resulting in product recommendation low success rate

Images