Self-learning recommendation method and device, computer equipment and storage medium

Abstract

The invention discloses a self-learning recommendation method and device, computer equipment and a storage medium, and relates to the technical field of artificial intelligence. The self-learning recommendation method comprises the steps of acquiring training fields from a business system database, wherein the training fields comprise field features; calculating the correlation between the field features; collecting historical questioning information input by a user, obtaining target field features from the historical questioning information based on the field features, wherein the field features comprise the target field features; carrying out feature selection preprocessing on the target field features, inputting the target field features subjected to feature selection preprocessing intoan automatic machine learning model, and determining combined field features in a recursive feature elimination mode; and obtaining questioning information input by the user, and outputting recommended answers according to the correlation between the field features and the combined field features. By adopting the self-learning recommendation method, deep mining analysis can be effectively carriedout on the feature variables.

Description

【Technical field】 [0001] The invention relates to the technical field of artificial intelligence, in particular to a self-learning recommendation method, device, computer equipment and storage medium. 【Background technique】 [0002] At present, the mainstream business analysis software in the market is based on a fixed dashboard, and is analyzed through dragging, drilling, and linkage. This method mainly relies on the understanding of the business of the person who stitches the dashboard. If the user does not realize that there may be a connection between two characteristic variables, further analysis cannot be performed, and important influencing factors in the business analysis process may be missed, and in-depth mining and analysis of characteristic variables cannot be performed. 【Content of invention】 [0003] In view of this, the embodiment of the present invention provides a self-learning recommendation method, device, computer equipment and storage medium to solve ...

AI Technical Summary

Problems solved by technology

[0003] In view of this, the embodiment of the present invention provides a self-learning recommendation method, device, computer equipment and storage medium to solve the problem that it is currently impossible to conduct in-depth mining and analysis of characteristic variables during business analysis

Images