Abstract: The sustained participation and service reliability provided by the node are essential to the data collection service provided by the social and community intelligence system. This paper proposes a reputation-based participatory incentive mechanism (RPIM) to promote the reliability of the collecting data and ensure the enthusiasm and persistence on the participation of the nodes. The proposed mechanism evaluates participants in terms of data reliability and bidding reliability to create a reputation model based on game theory. The incentive mechanism based on such reputation model motivates participants to collect reliable data in social and community intelligence systems, while minimizing incentive cost for maintaining the sufficient number of reliable participants. Simulations are conducted in different scenarios to test the performance of RPIM. The results show that RPIM remarkably increases the winning probability of participants who provide accurate data and reduces the cost for retaining the sufficient number of participants.

Key words: social and community intelligence, reputation model, participatory incentive, multidimensional reverse auction, game theory

摘要： 在社群智能系统中，参与节点的可靠性和积极性是系统提供有效数据采集服务的保证。为了提高用户采集数据的可靠性和服务的可持续性，提出了一种基于用户信誉度的参与式激励机制。该机制基于博弈论从数据可靠性和竞标可靠性两方面构建用户的信誉度模型，在此基础上通过多维反向拍卖机制建立参与式激励机制，使社群智能系统中保持充足的具有信誉的参与者持续提供服务，同时减少系统激励开销。通过不同场景下的仿真实验验证了该激励机制明显增加了具有信誉度的用户参与系统服务的数量，保证了充足数量的用户为系统实现可靠的服务，同时减少了系统的激励开销。

关键词: 社群智能, 信誉度模型, 参与式激励, 多维反向拍卖, 博弈论