Promotion resource configuration method, system and device and storage medium

Abstract

The invention discloses a promotion resource configuration method, system and device and a storage medium, and relates to the field of artificial intelligence, and the method comprises the following steps: obtaining a first data set and a second data set of a plurality of promotion accounts, inputting the first data set of each promotion account into a first model, respectively obtaining a first prediction result of each promotion account, wherein the first model is used for predicting the promotion message delivery capability of the promotion account; inputting the second data set of each promotion account to a second model to obtain a second prediction result, the second model being used for predicting the probability that the promotion account is a target account; determining a plurality of target accounts according to the first prediction result and the second prediction result of each promotion account; and improving the ranking of at least part of the target accounts in the advertisement putting sequence. According to the invention, the prediction accuracy of high potential customers can be improved, so that the resource configuration of the promotion message delivery system is optimized.

Description

Technical field [0001] The present application relates to artificial intelligence technology, in particular a method of promoting resource allocation, systems, devices and storage media. Background [0002] In the modern promotion message delivery system, the promotion user in the promotion message delivery system generally adopts the prepaid method, the promotion user by setting certain delivery conditions, such as setting the characteristics of the delivery crowd, bidding, etc., the promotion message delivery system is based on the conditions set by the promotion user, and based on the results of the operation to adjust the promotion user's promotion message placement location, time and other parameters, so as to improve the profit of the promotion message delivery system and the promotion user's delivery effect. [0003] However, due to various reasons, such as the low bid set by the customer, the characteristics of the delivery crowd, etc., the delivery effect of the promotio...

AI Technical Summary

Problems solved by technology

[0004] In related technologies, the RFM (recency of the latest consumption, the frequency of promotion message delivery Frequency, the abbreviation of resource consumption of promotion message delivery Monetary) model is usually used to measure the potential value of customers, but the RFM model is used in the prediction of promotion user potential The performance is not good. The reason is that the promotion message delivery belongs to the type of recharging first and then consumption, and the consumption is lagging information. This model is easy to mistakenly filter out a large number of promotion users who recharge but do not consume, and the traditional RFM model only has three dimensions. Data, lack of mining of deep information of promotion users, resulting in poor recall rate of the model on the task of predicting the consumption potential of promotion users

Due to the inaccurate screening results of high-potential promotion users, the promotion message delivery system incorrectly allocates resources, resulting in increased operating costs

Images