Address recommendation method and device, equipment and storage medium

Abstract

The invention provides an address recommendation method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining address information, extracting the features of the address information, and outputting the feature scalar of each piece of address information, and comprehensively evaluating different features of the input feature scalar by using the structural advantages of a binary tree and the interpretability of a tree model through a pre-trained training model, outputting the confidence coefficient of the address information, sorting the address information according to the confidence coefficient, and outputting an address list. According to the method and device, multivariate features of the address information are introduced, a diversified feature set is adopted, all features are comprehensively referenced, the revenue masses are expanded into a whole, the recommendation effect can serve users of different behavior modes, the calculation result is more comprehensive, and sorting is more intelligent and flexible.

Description

Technical field [0001] The present application relates to the field of Internet technology, and in particular, in particular, in particular, to an address recommendation method, a device, a device, and a storage medium. Background technique [0002] In recent years, the development of the Internet has facilitated people's lives. With the development of technology and the improvement of people's living standards, e-commerce has developed rapidly, and more and more people are used to buying goods to buy online, facilitate people's lives. With the popularity of smartphones, users who use mobile shopping are more and more. Whether it is traditional e-commerce or offline O2O trading behavior, the classic e-commerce transaction model of "Buying - Fill in Address - Payment - Completed Transaction". However, each time you fill in the address for a group of fixed addresses is very unfriendled, because each time you need an additional click to enter your destination, it also increases the ...

AI Technical Summary

Problems solved by technology

[0013] The purpose of the embodiments of the present application is to propose an address recommendation method, device, device and storage medium. By adopting a more diversified set of address features, the beneficiary population can be expanded to the whole, so that the recommendation effect can serve users with different behavior patterns. , which is used to solve the technical problem of recommending delivery addresses based on only a single behavior feature in the prior art

Images