Information pushing method and device

Abstract

The invention discloses an information pushing method and device, and the method comprises the steps: generating corresponding product data and a state identification of the product data according tothe product information of a shopping cart added by a user in a preset historical time period and the order data generated in the historical time period; training a preset machine learning model according to the product data and the state identifier of the product data; for each product added into the shopping cart by the user in a recently preset first time period, predicting whether the productis ordered by the user or not by utilizing the machine learning model obtained by training; and matching corresponding product push information for the user according to the prediction result, and sending the product push information to the user. By adopting the method and the device, the information pushing accuracy can be improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to an information push method and device. Background technique [0002] At present, in the data mining scheme of the e-commerce platform based on the commodity data of the user's shopping cart, it is usually to directly extract the commodity data of the user's shopping cart, and based on the data to make personalized recommendation of information, or to analyze and position the favorite commodity of the user, or Perform profile analysis on users, etc. [0003] In the process of realizing the present invention, the inventor found that the above-mentioned existing data mining scheme based on shopping cart data has at least the following problems: [0004] 1. The products that the user added to the shopping cart during a certain period of time may not be equivalent to the products that the user is really interested in to a certain extent. It may be that the product is in a s...

AI Technical Summary

Problems solved by technology

[0004] 1. The products that the user added to the shopping cart during a certain period of time may not be equivalent to the products that the user is really interested in to a certain extent. It may be that the product is in a state of waiting to be selected, or it may be that the product has been purchased through other channels and the shopping cart has not been cleared in time.

Therefore, the accuracy of data mining for personalized recommendation directly based on user shopping cart data is limited.

[0005] 2. The products that users are interested in are not static and often change with time. However, the existing data mining schemes based on shopping carts do not consider the potential of certain types of products that users need in a certain period of time according to the time dimension. Regularity, like this, will also affect the accuracy of data mining

[0006] It can be seen that the existing data mining schemes based on shopping cart data are not accurate enough, and thus cannot accurately match and push information based on data mining results

Images