Interactive outpatient quantity prediction visual analysis method and system based on CatBoost model

Abstract

The invention discloses an interactive outpatient quantity prediction visual analysis method and system based on a CatBoost model. The method comprises the following steps: constructing an interactivevisual interface which is provided for a user and is used for analyzing data, selecting data and characteristics; after a user selects data and features on a front-end interface, transmitting information to a rear end according to a preset time interval, enabling the rear end to change original input features, and establishing a regression model based on CatBoost; and after the model is established, transmitting information back to the front-end interface, and updating the characteristic importance degree analysis and prediction result in the visual interface, so that a user is helped to understand the prediction result and interactively mine information behind the data. According to the method, the machine learning model is combined with the front-end visual content, so that the defectsthat a traditional method is single in feature and insufficient in interpretability, is difficult to use by non-professionals, cannot perform interactive analysis and the like can be overcome.

Description

technical field [0001] The invention belongs to the technical field of outpatient volume forecasting, in particular to an interactive outpatient volume forecasting visual analysis method and system based on a CatBoost model. Background technique [0002] With the continuous development of computer technology, the medical field is also developing in the direction of intelligence and informatization. Reasonable outpatient forecast is one of the important prerequisites for intelligent management of medical resources in modern hospitals. Accurate outpatient quantity forecast can Help hospitals rationally allocate manpower and medical resources in different departments. [0003] Existing prediction methods for the number of outpatients in hospitals are often only based on certain specific features and data sets, or ignore the interpretability of the results; the previous prediction system for the number of outpatients is difficult to operate for non-computer users such as doctors...

AI Technical Summary

Problems solved by technology

[0012] The purpose of the present invention is to provide an interactive visual analysis method and system for forecasting outpatient volume based on the CatBoost model to solve the problem that the traditional forecasting method has large errors and weak interpretability, which is difficult for users in non-computer fields such as doctors technical problem

Images