Information recommendation method, device, and electronic device based on artificial intelligence

Abstract

The present invention provides an artificial intelligence-based information method, device, electronic equipment, and computer-readable storage medium; the method includes: determining the corresponding first click-through rate based on multiple logistic regression features of each information in the first information set , and from the descending sorting results of the first click rate, select a plurality of information sorted in front to form a second information set; perform compression processing on multiple logistic regression features of each information in the second information set , to obtain multiple shared features corresponding to each of the information; based on the multiple shared features of each information in the second information set, determine the corresponding second click rate; based on each information in the second information set Sort the results in descending order of the second click-through rate, perform the recommended action. Through the present invention, the complexity of feature engineering can be reduced and the recommendation response speed can be improved.

Description

technical field [0001] The present invention relates to artificial intelligence technology, in particular to an information recommendation method, device, electronic equipment and computer-readable storage medium based on artificial intelligence. Background technique [0002] Cloud technology refers to a hosting technology that unifies a series of resources such as hardware, software, and network in a wide area network or a local area network to realize data calculation, storage, processing, and sharing. [0003] Artificial Intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. [0004] Information recommendation is an important application of artificial intelligence. The ranking module in the recommendation system is usually based on the machine l...

AI Technical Summary

Problems solved by technology

Various efforts have been made in related technologies to improve the prediction accuracy of the click-through rate of the machine learning model. For example, a large amount of feature data is constructed in the feature engineering stage to enable the machine learning model to fully learn. The lack of feature data will affect the click-through rate prediction accuracy and further Affects the accuracy of information recommendation

[0005] Therefore, the contradiction between the lack of feature data and the accuracy of information recommendation has become a technical problem that is difficult to solve in related technologies

Images