A Crowdsourcing Task Assignment Method Based on User Reliability

Abstract

The present invention discloses a crowdsourcing task allocation method based on user reliability, the method comprising: S1, input user set W and task set T; S2, start task allocation, and initialize related tasks and user set; S3 , for each task t in the task set T to be assigned i , select eligible users to join task t i user set W r，i Middle; S4, start the first round of user allocation, and traverse each task in the task set T to be allocated; S5, continue the second round to the first round of user allocation, and traverse each task t in the task set T to be allocated i ; S6, the assignment of tasks ends, according to the set W r The quality of the tasks completed by the users in the middle, and update the reputation value of the users. The invention can not only ensure the reliability of users, the heterogeneity of users and the heterogeneity of tasks, but also improve the actual income of tasks and encourage more users to complete tasks with high quality.

Description

Technical field[0001]The present invention relates to the field of computer networks and communication technologies, and more particularly to a pre-package task allocation method based on user reliability.Background technique[0002]The public bag refers to a company or agency to put the work of the work in the past by employee, with free voluntary forms to non-specific (and usually large) mass networks. Personnel on the platform platform are divided into two categories: the person who publishes the task on the platform is called the task publisher, and the person who completes the task is called the user. The task publisher release tasks on the platform, and users obtain certain compensation by completing tasks. The typical task of the package has design graphics, collecting marketing programs, image tags, and data collection.[0003]The working method of the public can help the task publisher get a large number of free users, and solve practical problems by using the wisdom of these u...

AI Technical Summary

Problems solved by technology

[0004] However, existing discussions on user service quality differences only exist in pure task assignment methods, and do not provide a reasonable incentive mechanism to attract users to participate in tasks

Moreover, most of the existing research focuses on the single-user single-task model, that is, each task is only assigned to one user to complete, and the reliability of the user, the heterogeneity of the user, and the heterogeneity of the task are not fully considered. The problem is that for the same task, the quality completed by different users is different; and for the same user, the quality completed by different tasks is also different

It can be seen that there are still defects in the design of the crowdsourcing working method and incentive mechanism, which cannot meet the actual needs of the crowdsourcing system.

Images