基于Agent的信任的情感劝说决策模型

Emotional persuasion decision model based on Agent's trust

基于智能体(Agent)的信任的情感劝说能更好地发挥Agent的各项人工智能优势。针对其中决策模型建立不够的现状,首先基于Agent的自身性格、情感衰减及外界刺激,运用大五性格、OCC情感模型及情感强度第一定律等,构建了相应的情感强度算法;其次考虑交易质量对信任的反馈,综合运用语言评价法、三角模糊数及将模糊数转换为具体分数(CFCS)算法,对Agent的交易质量进行模糊化和去模糊化处理,构建了相应的交易质量算法;再次对已有的信任更新因子进行改进后,构建了Agent的信任更新算法;最后在构建以上算法的基础上,采用交互式多准则决策(TODIM)法建立了基于Agent的信任的情感劝说决策模型,并采用熵权法对模型中的属性权重进行设定。为验证以上研究的合理性和有效性,设计了相应算例进行阐述,分析了不同参数取不同值得到的决策结果,并与相关研究进行了比较分析,得出了相应结论和管理启示,进一步归纳了不足之处和未来研究方向。

Emotional persuasion based on an Agent's trust can better utilize a variety of artificial intelligence advantages of an Agent.Aiming at the currently insufficient research on decision models,based on an Agent's own character,emotion decay and external stimulation,the algorithm of emotional intensity was constructed by using the big five characters,the OCC(Ortony,Clore,Collins)emotion model and the first law of emotional intensity.Considering the effects of transaction quality on trust,fuzzification and defuzzification were carried out on the transaction quality of an Agent by using the language evaluation method,the triangular fuzzy number and the Converting Fuzzy data into Crisp Scores Converting Fuzzy data into Crisp Scores(CFCS)algorithm,and then the algorithm of the transaction quality was correspondingly constructed.After the existing updating factor of trust is improved,the updating algorithm of an Agent's trust was developed.On the basis of the aforementioned algorithms,the emotional persuasion decision model based on an Agent's trust was established with TOmada de Decisao Interativa e Multicritévio(TODIM)method,and the attribute weights in the model were determined by the entropy weight method.To show the appropriateness and validity of the proposed model,a numerical example was designed for illustration,and the decision results obtained from different combinations of parameter values were analyzed and compared with those of the related research.Conclusions and managerial insights were drawn accordingly and then limitations and future research directions were further summarized.