The accomplishment of a complex problem usually involves cooperation between participators with different knowledge background concerned. This paper identifies inter-dependency between different sub problems (through problem decomposition) as the major factor that influences cooperative relations in multi-Agent systems, based on which we propose an efficient means to measure cooperation coefficient (degree) between different Agents. Then cognitive cooperation between Agents is analyzed which aims at collecting the wisdom of the cognitive community for a systematic solution to the overall problem.
Web service composition lets developers create appli-cations on top of service-oriented computing and its native de-scription,discovery,and communication capabilities. This paper mainly focuses on the QoS when the concrete composition struc-ture is unknown. A QoS model of service composition is presented based on the fuzzy directed graph theory. According to the model,a recursive algorithm is also described for calculating such kind of QoS. And,the feasibility of this QoS model and the recursive al-gorithm is verified by a case study. The proposed approach en-ables customers to get a possible value of the QoS before they achieve the service.