Task node allocation method, device and related equipment based on multi-point output model

Abstract

The invention discloses a task node allocation method based on a multi-point output model, which is applied in the technical field of artificial intelligence and used to solve the technical problem of low efficiency of task node allocation in the existing system. The method provided by the present invention includes: receiving at least one target prediction object carrying employee characteristic information and forecast events; obtaining a pre-trained regression model and a plurality of target parameter values ​​obtained through training; using the regression model to utilize each target parameter value Each of the target predictors is predicted respectively to obtain the forecast results of the target predictors corresponding to the target parameter values ​​for the forecast event; the average value of the forecast results corresponding to each of the target parameter values ​​is determined as Corresponding to the prediction result of the target prediction object; when the prediction result is greater than the preset probability, it is judged that the target prediction object can complete the prediction event; sending the task node corresponding to the prediction event to the target prediction object capable of completing the prediction event.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a task node assignment method, device, computer equipment and storage medium based on a multi-point output model. Background technique [0002] Our common prediction tasks are generally completed by machine learning models, that is, Y=F(X), by inputting known X, and obtaining the prediction result Y through the model F, and common predictions are generally point predictions, that is, the predicted results are A certain value, usually also called the prediction of the maximum expected value. This kind of point prediction method requires a large amount of sample data as the basic condition to train the model, that is, sufficient historical data is required to support it. At the same time, the parameters of the model are obtained entirely by learning the existing data set and cannot be adjusted flexibly. [0003] In the process of training the model, the act...

AI Technical Summary

Problems solved by technology

[0006] Embodiments of the present invention provide a task node allocation method, device, computer equipment, and storage medium based on a multi-point output model to solve the technical problem of low efficiency of task node allocation in existing systems

Images