Task allocation method, device, computer-readable storage medium and electronic device

Abstract

The embodiment of the present invention discloses a task allocation method, device, computer-readable storage medium, and electronic equipment, which can balance task allocation efficiency and platform resource consumption. The method includes: assigning tasks to workers in the current time slice based on the matching relationship between workers and tasks; obtaining the amount of remaining tasks and the number of remaining workers that have not yet been allocated after the task assignment is completed in the current time slice; using a machine learning model, based on The amount of remaining tasks and the number of workers left in the current time slice, the amount of previous tasks and the number of workers who arrived in the current time slice and at least one time slice before it, and the historical same period that arrived within the next preset time threshold The amount of tasks and the number of workers in the same period in history are used to predict the amount of tasks and the number of workers that will come within the next preset time threshold; at least based on the amount of tasks and the number of workers predicted, the length of the next time slice is adjusted. The present invention is suitable for distributing crowdsourcing tasks.

Description

technical field [0001] The present invention relates to crowdsourcing technology, in particular to a method, device, storage medium and electronic equipment for assigning tasks to workers in a crowdsourcing mode based on time slices. Background technique [0002] With the development of Internet technology, crowdsourcing technology has been applied to more and more fields, for example, various task assignment scenarios such as food order delivery, online car-hailing order delivery, and data crowdsourcing services. [0003] Most of the existing research on crowdsourcing allocation mechanism is based on the offline situation, and there is no practical solution for the task allocation mechanism in the online situation. Moreover, in the actual crowdsourcing application, the tasks and the workers who complete the tasks arrive in real time, that is to say, the information of the tasks and workers that have not arrived is unknown to the platform that assigns the tasks. In this case...

AI Technical Summary

Problems solved by technology

[0003] Most of the existing research on crowdsourcing allocation mechanism is based on the offline situation, and there is no practical solution for the task allocation mechanism in the online situation.

Moreover, in the actual crowdsourcing application, the tasks and the workers who complete the tasks arrive in real time, that is to say, the information of the tasks and workers that have not arrived is unknown to the platform that assigns the tasks. In this case The matching is easy to cause local optimum, but the result of poor global matching effect

The above problems have become obstacles to real-time task distribution, and have also affected the development of crowdsourcing platforms.

Images