Task distribution method considering user heteroplasmy and user preference in crowdsourcing system

Abstract

The invention discloses a task distribution method considering user heteroplasmy and user preference in a crowdsourcing system; the method considers task budget, user heteroplasmy and user preference, and uses a multi-to-one matching mechanism to find the best user-task match; the core of the method is that in the whole algorithm operation process, quality sum non-reduction of each task can be completed; the method provides a novel distribution thinking and specific scheme for the crowdsourcing system, thus solving the problems that an existing crowdsourcing system task distribution strategy cannot consider user heteroplasmy and user preference; the matching result by the algorithm has individual rationality and fairness, and has no wasteness.

Description

technical field [0001] The invention relates to the technical field of crowdsourcing, in particular to a task assignment method in a crowdsourcing system that takes into account user heterogeneity and user preference. Background technique [0002] With the advancement of globalization, many network platforms have emerged as the times require, and the group power of the network has exploded with unprecedented influence. The diverse knowledge background and collaboration concept in the group provide a source of strength for the successful completion of large-scale tasks. "Creating value with users" is the core of the crowdsourcing system. Crowdsourcing can reduce costs and improve efficiency. In the crowdsourcing system, there is great potential for cross-professional innovation and cooperation, which can achieve a win-win situation for both task issuers and task participants. Using the group power of the Internet, crowdsourcing can accomplish difficult problems that cannot b...

AI Technical Summary

Problems solved by technology

[0007] Among the existing allocation strategies, strategy (1) does not consider user heterogeneity and user preference; strategy (2) mainly considers user recruitment in the mobile environment; strategy (3) pays attention to the data quality and budget submitted by users, However, user preferences are not considered; strategy (4) focuses on the uncertainty of user movement and task completion; strategy (5) does not consider budget and user preferences, so these strategies in the prior art are not suitable for the aforementioned tasks distribution problem

Images