To address the confrontation decision-making issues in multi-round air combat,a dynamic game decision method is proposed based on decision tree for the confrontation of unmanned aerial vehicle(UAV)air combat.Based on ...To address the confrontation decision-making issues in multi-round air combat,a dynamic game decision method is proposed based on decision tree for the confrontation of unmanned aerial vehicle(UAV)air combat.Based on game the-ory and the confrontation characteristics of air combat,a dynamic game process is constructed including the strategy sets,the situation information,and the maneuver decisions for both sides of air combat.By analyzing the UAV’s flight dyna-mics and the both sides’information,a payment matrix is estab-lished through the situation advantage function,performance advantage function,and profit function.Furthermore,the dynamic game decision problem is solved based on the linear induction method to obtain the Nash equilibrium solution,where the decision tree method is introduced to obtain the optimal maneuver decision,thereby improving the situation advantage in the next round of confrontation.According to the analysis,the simulation results for the confrontation scenarios of multi-round air combat are presented to verify the effectiveness and advan-tages of the proposed method.展开更多
This paper presents a Game-theoretic optimization via Parallel Min-Max Ant System(PMMAS)algorithm is used in practice to determine the Nash equilibrium value to resolve the confusion in choosing appropriate bidders of...This paper presents a Game-theoretic optimization via Parallel Min-Max Ant System(PMMAS)algorithm is used in practice to determine the Nash equilibrium value to resolve the confusion in choosing appropriate bidders of multi-round procurement problem in software project management.To this end,we introduce an approach that proposes:(i)A Game-theoretic model of multiround procurement problem(ii)A Nash equilibrium strategy corresponds to multi-round strategy bid(iii)An application of PSO for the determination of global Nash equilibrium.The balance point in Nash Equilibrium can help to maintain a sustainable structure not only in terms of project management but also in terms of future cooperation.As an alternative of procuring entities subjectively,a methodology to support decision making has been studied using Nash equilibrium to create a balance point on benefit in procurement where buyers and suppliers need multiple rounds of bidding.Our goal focus on the balance point in Nash Equilibrium to optimizing bidder selection in multi-round procurement which is the most beneficial for both investors and selected tenderers.Our PMMAS algorithm is implemented based on MPI(message passing interface)to find the approximate optimal solution for the question of how to choose bidders and ensure a path for a win-win relationship of all participants in the procurement process.We also evaluate the speedup ratio and parallel efficiency between our algorithm and other proposed algorithms.As the experiment results,the high feasibility and effectiveness of the PMMAS algorithm are verified.展开更多
大模型在医疗、法律、金融等多个领域都有广阔的应用前景,同时这些领域也对大模型的专业性、准确性、可解释性、安全性提出了更高的要求。目前公开数据集大都以结论性回答为主,缺少在复杂咨询场景中对专家决策形成过程的可解释推理表达...大模型在医疗、法律、金融等多个领域都有广阔的应用前景,同时这些领域也对大模型的专业性、准确性、可解释性、安全性提出了更高的要求。目前公开数据集大都以结论性回答为主,缺少在复杂咨询场景中对专家决策形成过程的可解释推理表达,不能高效支持大模型进行长上下文、多轮次交互推理。为此,本研究构建了MPCCD-MLF数据集(Multi-round Professional Consulting Conver sation Dataset in Medical,Legal and Financial Domains,简称MPCCD-MLF),包含医疗、法律、金融三个专业领域的多轮对话语料。数据来源于好大夫在线、中国法律服务网(12348)、雪球网等专业平台,时间范围为2023年1月至2024年12月。数据集经过网络爬取、指令工程、结构重组过程,采用专门设计的多维度约束指令模板,以专家原始回答中的事实判断和结论性信息为锚点,辅助生成结构化、可解释的推理表达,并在多轮对话中进行呈现。经清洗、脱敏之后得到31,745条三轮问答数据,约181 MB,用JSON格式保存。每条对话都采用用户提问、专家回答、用户追问、专家再回答的多轮交互方式。质量控制采用自动模型评分和专家人工核验的双盲评定方式,综合质量4.75分(满分5分)。本数据集可为垂直领域大语言模型在复杂逻辑推理、长对话交互的场景提供高质量和高可解释性的语料。展开更多
基金supported by the Major Projects for Science and Technology Innovation 2030(2018AAA0100805).
文摘To address the confrontation decision-making issues in multi-round air combat,a dynamic game decision method is proposed based on decision tree for the confrontation of unmanned aerial vehicle(UAV)air combat.Based on game the-ory and the confrontation characteristics of air combat,a dynamic game process is constructed including the strategy sets,the situation information,and the maneuver decisions for both sides of air combat.By analyzing the UAV’s flight dyna-mics and the both sides’information,a payment matrix is estab-lished through the situation advantage function,performance advantage function,and profit function.Furthermore,the dynamic game decision problem is solved based on the linear induction method to obtain the Nash equilibrium solution,where the decision tree method is introduced to obtain the optimal maneuver decision,thereby improving the situation advantage in the next round of confrontation.According to the analysis,the simulation results for the confrontation scenarios of multi-round air combat are presented to verify the effectiveness and advan-tages of the proposed method.
基金Vietnam National Foundation for Science and TechnologyDevelopment(NAFOSTED)under grant number 102.03-2019.10.
文摘This paper presents a Game-theoretic optimization via Parallel Min-Max Ant System(PMMAS)algorithm is used in practice to determine the Nash equilibrium value to resolve the confusion in choosing appropriate bidders of multi-round procurement problem in software project management.To this end,we introduce an approach that proposes:(i)A Game-theoretic model of multiround procurement problem(ii)A Nash equilibrium strategy corresponds to multi-round strategy bid(iii)An application of PSO for the determination of global Nash equilibrium.The balance point in Nash Equilibrium can help to maintain a sustainable structure not only in terms of project management but also in terms of future cooperation.As an alternative of procuring entities subjectively,a methodology to support decision making has been studied using Nash equilibrium to create a balance point on benefit in procurement where buyers and suppliers need multiple rounds of bidding.Our goal focus on the balance point in Nash Equilibrium to optimizing bidder selection in multi-round procurement which is the most beneficial for both investors and selected tenderers.Our PMMAS algorithm is implemented based on MPI(message passing interface)to find the approximate optimal solution for the question of how to choose bidders and ensure a path for a win-win relationship of all participants in the procurement process.We also evaluate the speedup ratio and parallel efficiency between our algorithm and other proposed algorithms.As the experiment results,the high feasibility and effectiveness of the PMMAS algorithm are verified.
文摘大模型在医疗、法律、金融等多个领域都有广阔的应用前景,同时这些领域也对大模型的专业性、准确性、可解释性、安全性提出了更高的要求。目前公开数据集大都以结论性回答为主,缺少在复杂咨询场景中对专家决策形成过程的可解释推理表达,不能高效支持大模型进行长上下文、多轮次交互推理。为此,本研究构建了MPCCD-MLF数据集(Multi-round Professional Consulting Conver sation Dataset in Medical,Legal and Financial Domains,简称MPCCD-MLF),包含医疗、法律、金融三个专业领域的多轮对话语料。数据来源于好大夫在线、中国法律服务网(12348)、雪球网等专业平台,时间范围为2023年1月至2024年12月。数据集经过网络爬取、指令工程、结构重组过程,采用专门设计的多维度约束指令模板,以专家原始回答中的事实判断和结论性信息为锚点,辅助生成结构化、可解释的推理表达,并在多轮对话中进行呈现。经清洗、脱敏之后得到31,745条三轮问答数据,约181 MB,用JSON格式保存。每条对话都采用用户提问、专家回答、用户追问、专家再回答的多轮交互方式。质量控制采用自动模型评分和专家人工核验的双盲评定方式,综合质量4.75分(满分5分)。本数据集可为垂直领域大语言模型在复杂逻辑推理、长对话交互的场景提供高质量和高可解释性的语料。
