Research The Linguistic Multi-criteria Group Decision-making Methods Based On Cloud Model

In the social and economies life, there are a large number of linguistic multi-criteria group decision-making (LMCGDM) problems, that the optimization and ordering of the alternatives which the preferences values giving by experts are linguistic variables. Based on researching and summarizing the relevant the critical literature, cloud model has been introduced into the LMCGDM field in order to solve the transformation between qualitative concepts and quantitative values. Knowledge representation and reasoning methods based on the cloud model can fully express the randomness and fuzziness of the uncertainty knowledge, which is objective and can resolve the problem of information loss in the decision-making process to a certain extent. At present, there is few related research with respect to the LMCGDM problems, which cannot meet the pragmatic needs. Therefore, LMCGDM problems based on cloud model are investigated systematically in this thesis, a series of decision models and methods are proposed, and some examples are given to illustrate the feasibility and effectiveness of the developed methods. The main work of this thesis includes the following aspects:(1) We define a new cloud distance and a cloud support degree, which is on the basis of the power average operator and cloud model, and develop some new cloud generalized aggregation operators such as a cloud generalized power average (CGPA) operator, a weighted cloud generalized power average (WCGPA) operator and a cloud generalized power ordered weighted average (CGPOWA) operator. These cloud aggregation operators not only take into account all the decision arguments and their relationships, but also completely reflects the fuzziness and randomness inherent in natural languages. With respect to LMCGDM problems in which the weight information of criteria and experts is all completely unknown, a new group decision making method based on the CGPOWA operator is proposed. In addition, with regard to LMCGDM problems in which criteria values take the form of two-tuple linguistic, a new group decision making method based on the cloud model is developed, which fully considers the uncertainty of decision-making information and makes the decision result more reasonable.(2) We first propose a new method for transformation between the interval-valued intuitionistic uncertain linguistic variables and trapezium clouds, and define trapezium cloud possibility degree and trapezium cloud support degree, which can be used to compare the trapezium clouds and determine the weights. Based on the trapezium cloud support degree, we develop a new trapezium cloud aggregation operator named as the trapezium cloud generalized power ordered weighted average (TCGPOWA) operator and investigate its properties. With respect to LMCGDM problems where the weight information of criteria and experts is all completely unknown and the criteria values take the form of interval-valued intuitionistic uncertain linguistic variables, a new group decision making method based on the TCGPOWA operator is proposed.(3) By using the Choquet integral, some new cloud Choquet operators are introduced, including the cloud correlated averaging operator and the cloud correlated geometric operator. These operators not only consider the importance of the arguments or their ordered positions, but also can reflect the correlations among the arguments or their ordered positions. After investigating properties of these operators, a new approach for LMCGDM based on the cloud Choquet operators is proposed. The approach not only considers the fuzziness and randomness of language information, but also solves the problem that the criteria are usually inter-dependent or correlated, which makes the decision result more practicability.