A Decision Making Approach Based On Incomplete Hesitant Fuzzy Linguistic-Valued Credibility Reasoning

With the rapid development of mobile internet technology and the proposal of smart cities,the development of artificial intelligence is also becoming more and more rapid.As the core research field of artificial intelligence,uncertainty reasoning plays an irreplaceable role.In daily life,computers can effectively deal with reasoning and decision making expressed in natural language,which is the embodiment of the deep-intelligence of computers.In recent years,credibility reasoning has attracted much attention due to its better ability and efficiency in expressing uncertainty and ambiguity within the process of reasoning and decision-making.Computers can effectively deal with the reasoning and decision-making problems expressed in natural language in daily life,which is the embodiment of the deep intelligence of computers.This paper studies linguistic knowledge acquisition and uncertainty reasoning based on hesitant fuzzy set providing a theory and method for automatic reasoning with linguistic values in the field of artificial intelligence.Combining uncertainty reasoning with hesitant fuzzy linguistic term set,this paper deeply studies the rational decision-making method based on the hesitant fuzzy linguistic-valued credibility uncertainty reasoning.It can handle both quantitative and qualitative information,and has the ability to model fuzzy uncertainty or probability uncertainty.The main research results are as follows:(1)Aiming at the problem of inaccurate credibility estimation in uncertainty reasoning and making experts to express hesitant preferences better in evaluation reasoning process,this paper introduces hesitant fuzzy linguistic term set into credibility uncertainty reasoning.First,we propose the hesitant fuzzy linguistic-valued credibility(HLCF),and establish the knowledge representation model of the hesitant fuzzy linguistic-valued credibility.Then,in order to solve the problem of incomplete information in the evaluation reasoning process,an information complement algorithm based on maximum similarity is constructed.(2)In order to avoid the influence of subjective factors that experts artificially give the premise credibility and reasoning rules,this paper performs multiple iterations by increasing the frequency fr,then calculates the promote factors(PF)and the hesitant fuzzy linguistic-valued credibility promote factors(PHLCF)of conditional attributes,thereby obtaining a more accurate and objective premise credibility.The conditional attribute weights are calculated by the idea of pre-order entropy in granular computing,to avoid the bias causedby the subjective influence caused by artificially setting the weight of each condition attribute under the same reasoning rule.(3)The paper studies the algorithms of single rule and multiple rules of parallel relationship of the hesitant fuzzy linguistic-valued credibility.At the same time,they consider the impact of the credibility of the premises and the rules on the reasoning results,so as to avoid the reasoning rules being too single and make the results more accurate.Furthermore,we define the positive and negative ideal conclusion sets.Then,the closeness between the conclusion set of each alternative and the positive and negative ideal conclusion sets after reasoning is separately proposed,and the satisfaction of each alternative is calculated.So,we can select the most suitable alternative.Finally,the corresponding rational decision making model and algorithm based on hesitant fuzzy linguistic-valued credibility reasoning are constructed and a practical example which concerned the social risk analysis is given to illustrate the applicability and effectiveness of the proposed approach.