Business data pushing method and device and server

Abstract

The invention provides a business data pushing method and device and a server. Based on the method, in combination with an artificial intelligence technology, the pushing success rate of the data objects is predicted by utilizing a preset pushing result prediction model, a correspondingly sorted first pushing list is generated based on the pushing success rate, and then the difference degree of pushing effects among different data object type groups is further determined; and the sequence in the first pushing list is adjusted by utilizing the data according to the pushing rule and the unbiased estimator of the relevance between the pushing rule and the data object, thus errors caused by the fact that the fairness between different data object type groups and the relevance between the data objects and the pushing rules are not considered in a preset pushing result prediction model can be eliminated, and a second pushing list which is relatively more accurate in sorting is obtained; then the target business data can be pushed to the plurality of data objects according to the second push list so that a relatively good push effect can be obtained.

Description

technical field [0001] This manual belongs to the field of artificial intelligence technology, and in particular relates to a method, device and server for pushing business data. Background technique [0002] When pushing business data to customers, the predictive model trained based on artificial intelligence technology (for example, supervised learning algorithm) is often used to predict the success rate of the customer's push; Sorting is performed to generate a push list of customers; furthermore, corresponding business data can be pushed to customers according to the push list. [0003] However, due to the limitation of the training mechanism and the factors considered, the above prediction model itself will have deviations in the process of learning and training. As a result, there will also be errors in the push list generated by sorting based on the push success rate predicted by the above prediction model, which will affect the subsequent push effect. [0004] For ...

AI Technical Summary

Problems solved by technology

[0003] However, due to the limitations of the training mechanism and the factors considered, the above-mentioned prediction model itself will have deviations in the process of learning and training.

As a result, there will also be errors in the push list generated by sorting the push success rate based on the prediction model above, which will affect the subsequent push effect

[0004] For the above problems, no effective solution has been proposed

Images