Task allocation method based on MAS-Q-Learning

Abstract

The invention discloses a task allocation method based on MAS-Q-Learning, and the method comprises the steps: obtaining user data in a real application scene, carrying out the modeling of the user data through a Markov decision, designing crowdsourcing personnel into an agent quintuple, and calculating the global income of the crowdsourcing personnel through adoption of a Q value learning method; and positioning the state of an adjacent agent and the next state, wherein a Laplacian matrix is used for describing the incidence relation between all agent members, a multi-attribute decision method is adopted for calculation, and calculation results are subjected to weight distribution and aggregation. A time difference method is adopted to estimate an action-value function, and meanwhile, an intelligent agent state function meeting rationality and integrity conditions is given. The method not only has good robustness, but also has good adaptability.

Description

technical field [0001] The invention relates to the field of task allocation, is mainly applied in crowdsourcing scenarios, and specifically relates to the cost optimization problem of complex task allocation in crowdsourcing scenarios. Background technique [0002] The design motivation of the present invention comes from the emerging application of software testing work in current crowdsourcing. In the general crowdsourcing process, task allocation is not clear, and crowdsourcing workers cannot maximize their personal benefits. Contents of the invention [0003] Purpose of the invention: In order to avoid problems such as unclear assignment of tasks in the process of crowdsourcing and the inability of crowdsourcing workers to maximize their personal income, the present invention provides a task assignment method based on MAS-Q-Learing, which is different from the traditional discrete data structure Unlike graphs, the crowdsourcing process is continuous in the time dimens...

AI Technical Summary

Problems solved by technology

[0003] Purpose of the invention: In order to avoid problems such as unclear assignment of tasks in the process of crowdsourcing and the inability of crowdsourcing workers to maximize their personal income, the present invention provides a task assignment method based on MAS-Q-Learing, which is different from traditional discrete data structures Unlike graphs, the crowdsourcing process is continuous in the time dimension, thus requiring a variable and uncertain time domain to guide the agent

Images