Efficient user assignment in crowd sourcing applications

Abstract

Recent technological advancement in hand-held computing devices such as smart phones/PDA integrates cyber and physical worlds altogether. This interaction creates a new paradigm called mobile crowd sourcing which takes advantages of human intellect and a large pool on internet users to perform various task more efficiently. In such applications, users are generally recruited in ad hoc manner to do a task and often receive some incentive. Such ad hoc nature provides flexibility for users to do any job but often decreases their reliability and output quality. Quality control is generally done by increasing the workforce which increases cost. To solve this issue, we proposed a user assignment framework which pushes the task to the right set of users which can perform the task in more economically efficient way. These framework first rank users by performing semantic comparison among task's requirements and user's attributes. Then it tries to assign minimum, yet most efficient users for each task in mutually exclusive manner. This framework ensures the allocation of most efficient users for each task while keeping the reward cost as minimum as possible, hence allows application developers and end users to enjoy the power of crowd in more effective way.