Data recommendation method and device, equipment and storage medium

Abstract

The embodiment of the invention relates to the field of artificial intelligence, and discloses a data recommendation method and device, equipment and a storage medium, and the method comprises the steps: obtaining portrait information of a user in a target business scene, the portrait information comprising a user portrait and a content portrait; extracting feature information from the portrait information, wherein the feature information comprises user features and content features; classifying the user features and the content features, and expanding the classified user features and content features to obtain an expanded feature set; inputting the user features and the content features in the extended feature set into a trained recall model, obtaining a content candidate set, wherein the content candidate set comprises a plurality of candidate text contents; according to the data recommendation method and device, sorting the multiple candidate text contents by using the specified sorting algorithm, and sending the multiple candidate text contents to the user terminal according to the sorted sequence, so that the efficiency and accuracy of data recommendation are improved. The invention relates to a block chain technology, for example, portrait information can be written into a block chain so as to be used for scenes such as data evidence obtaining.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular to a data recommendation method, device, equipment and storage medium. Background technique [0002] The recommendation system is to recommend the information that the user is interested in to the user according to the user's information needs, interests, etc. At present, the mainstream recommendation system usually includes the indexing stage, the recalling stage and the sorting stage. Among them, the recalling stage is mainly through the limited response Select content directly from the content candidate set obtained in the indexing stage in real time, and send the selected content to the sorting stage. However, this method is limited by the huge candidate set and real-time requirements, as well as the complexity, and the recommendation processing logic is difficult to achieve better recommendation results. Contents of the invention [0003] Embodiments of the pre...

AI Technical Summary

Problems solved by technology

However, this method is limited by the huge candidate set and real-time requirements, as well as the complexity, and the recommendation processing logic is difficult to achieve better recommendation results

Images