Case-based reasoning(CBR) is one of the best methods for generating an effective solution in an emergency. In recent years, some methods for generating emergency alternatives have been included in practical CBR applic...Case-based reasoning(CBR) is one of the best methods for generating an effective solution in an emergency. In recent years, some methods for generating emergency alternatives have been included in practical CBR applications, but there have been no in-depth studies of these processes. In this study,we propose a new method for dynamic case retrieval with subjective preferences and objective information, which considers the personal preferences of the decision makers and changes in the attributes of the emergency as the situation develops. First,we present a formula for calculating the case similarity and changing trends in the case considered, where similar cases are obtained. Next, we describe a method for measuring the overall assessment value with respect to similar historical cases, which is obtained by aggregating the case similarity, the utility case similarity, the first response time, and the implementation effect.The subjective preferences and objective information are also integrated in the decision-making process. Finally, we present a case study based on the emergency response to a fire in a highrise building, which illustrates the applicability and feasibility of the proposed method.展开更多
Case retrieval(CR) is critically an important part of case-based design. However few studies attempt to research CR for customer-driven design and analyze the eect of other production factors besides similarity comput...Case retrieval(CR) is critically an important part of case-based design. However few studies attempt to research CR for customer-driven design and analyze the eect of other production factors besides similarity computation. This paper proposes a new CR method for customer-driven design,and requirement-weighting analysis. Fuzzy set theory are integrated into CR process to deal with the fuzzy and imprecision customer requirements. So the proposed method is called weighted fuzzy case retrieval(WFCR). Furthermore,similar case evaluation is added into CR process to demonstrate that the best case is selected not only on the basis of satisifaction for the given requriements,but also on the degree of preference over other cases according to multiple evaluation criteria. Meanwhile,WFCR system is developed and applied to power transformer design to validate its scientificity and practicality. Finally,the paper statistically validated the supriority of WFCR by comparing it with traditional fuzzy case retrieval methods(FCRs),and the comparison indicates that WFCR is more accurate than other FCRs.展开更多
The paper studies on case-based reasoning of uncertain product attributes in configuration design of a product family. Interval numbers characterize uncertain product attributes. By interpolating a number of certain v...The paper studies on case-based reasoning of uncertain product attributes in configuration design of a product family. Interval numbers characterize uncertain product attributes. By interpolating a number of certain values randomly to replace interval numbers and making projection pursuit analysis on source cases and target cases of expanded numbers, we can get a projection value in the optimal projection direction. Based on projection value, we can construct a case retrieval model of projection pursuit that can handle coexisting certain and uncertain product attributes. The application examples of chainsaw configuration design show that case retrieval is highly sensitive to reliable results.展开更多
As a basic external manifestation of judicial justice in judicial practice,‘same cases with same judgements'and‘similar cases with same judgements'are the psychological expectations of human society for the ...As a basic external manifestation of judicial justice in judicial practice,‘same cases with same judgements'and‘similar cases with same judgements'are the psychological expectations of human society for the pursuit of fairness and justice.Although the similar case retrieval system was endowed with this‘sacred mission'at the beginning of the system's establishment,no matter from the logical nature of the system's operation and the limitations of the formation basis of similar cases,or whether it has a mandatory application to judges even in terms of the limited binding force of similar cases on judges'judgements under the mandatory search obligation,it should be rationally recognized that the search mechanism for similar cases is limited in realizing the function of‘ame cases with same judgements'.The retrieval mechanism for similar cases can realize the interpretation function and the coordination function of the rule of law under the background of current regional development differences in China through differentiated functional positioning.展开更多
The purpose of this paper is to explore the application of large language models(LLMs)in legal case retrieval and to evaluate their potential for providing legal professionals with more efficient work aids.Currently,a...The purpose of this paper is to explore the application of large language models(LLMs)in legal case retrieval and to evaluate their potential for providing legal professionals with more efficient work aids.Currently,although pre-trained models have made great progress in legal case retrieval,they are often limited to specific types of law(e.g.,criminal law,civil law,etc.)and lack the ability to generalize across different types of law.Moreover,most models can only deal with a single task,whereas the legal case retrieval task requires a model to have a superb comprehension of legal texts,involving multiple subtasks and requiring multitasking capabilities.Therefore,the large language model,which has super generalization and multitasking ability,can solve the above problems.In order to explore the application of large language models for legal case retrieval in the legal domain,this paper evaluates a series of emerging large language models,including multilingual models,homegrown large models,and models specifically designed for the legal domain.These models are used to retrieve legal cases and its associated subtasks.Based on the Supreme People’s Court definition,the legal case retrieval task is broken down into seven subtasks:event detection,fact generation,trigger word extraction,keyword extraction,summarization,dispute focus identification,and reasoning generation.Using a variety of evaluation metrics,the experiments demonstrated that these emerging models have significant potential in the field of legal case retrieval,even with few shot samples.The research in this paper not only introduces new ideas in the field of legal case retrieval,but also empirically verifies the potential of LLMs to improve the quality and efficiency of retrieval.It proves the value of large language models in this field and is expected to significantly enhance the efficiency of legal practitioners,as well as promote the consistency and fairness of legal judgments through the use of emerging technologies.展开更多
Fixture is an important manufacturing activity. A fixture design system based on case-based reasoning (CBR) is proposed in this paper. A new method of case representation on the basis of fixture function is presented,...Fixture is an important manufacturing activity. A fixture design system based on case-based reasoning (CBR) is proposed in this paper. A new method of case representation on the basis of fixture function is presented, where the case representation is constituted of workpiece knowledge, processing feature knowledge, and fixture feature knowledge. Running the prototype system shows that the knowledge representation method, using cases, s a better way to transform and explain the design knowledge.展开更多
Product customization is a trend in the current market-oriented manufacturing environment. However, deduction from customer requirements to design results and evaluation of design alternatives are still heavily relian...Product customization is a trend in the current market-oriented manufacturing environment. However, deduction from customer requirements to design results and evaluation of design alternatives are still heavily reliant on the designer＇s experience and knowledge. To solve the problem of fuzziness and uncertainty of customer requirements in product configuration, an analysis method based on the grey rough model is presented. The customer requirements can be converted into technical characteristics effectively. In addition, an optimization decision model for product planning is established to help the enterprises select the key technical characteristics under the constraints of cost and time to serve the customer to maximal satisfaction. A new case retrieval approach that combines the self-organizing map and fuzzy similarity priority ratio method is proposed in case-based design. The self-organizing map can reduce the retrieval range and increase the retrieval efficiency, and the fuzzy similarity priority ratio method can evaluate the similarity of cases comprehensively. To ensure that the final case has the based on grey correlation analysis is proposed to evaluate similar cases best overall performance, an evaluation method of similar cases to select the most suitable case. Furthermore, a computer-aided system is developed using MATLAB GUI to assist the product configuration design. The actual example and result on an ETC series machine tool product show that the proposed method is effective, rapid and accurate in the process of product configuration. The proposed methodology provides a detailed instruction for the product configuration design oriented to customer requirements.展开更多
In this paper, the method of tmderstanding GIS Chinese query based on CBR （case-based reasoning） is proposed. The CaseBase is designed on the grammar rule of Chinese query sentences, the cases that pick up the chara...In this paper, the method of tmderstanding GIS Chinese query based on CBR （case-based reasoning） is proposed. The CaseBase is designed on the grammar rule of Chinese query sentences, the cases that pick up the character of standard query language （SQL） and are expressed in form semantics. In retrieval, the concepts of target comparability, structure comparability and individual comparability are given. The algorithm of case retrieval searches first the case of structure comparability and then individual comparability. The SQL reasoning algorithm that first parses form semantics, then reasons on structure comparability, and finally reasons on individual comparability is realized. In the actual GIS, the structure comparability and individual comparability are tested respectively. The experiment results show that the strategy of CBR is correct and feasible. With the size of CaseBase increasing through studies, the CaseBase will eventually be perfected. The effect of retrieval and reasoning will become better and better.展开更多
基金supported by the National Science Foundation for Outstanding Youth of China(70925004)Fujian Province Transportation Hall of Science and Technology Development Projects,China(201319)the Science and Technology Project in Fujian Province Department of Education,China(JB14122)
文摘Case-based reasoning(CBR) is one of the best methods for generating an effective solution in an emergency. In recent years, some methods for generating emergency alternatives have been included in practical CBR applications, but there have been no in-depth studies of these processes. In this study,we propose a new method for dynamic case retrieval with subjective preferences and objective information, which considers the personal preferences of the decision makers and changes in the attributes of the emergency as the situation develops. First,we present a formula for calculating the case similarity and changing trends in the case considered, where similar cases are obtained. Next, we describe a method for measuring the overall assessment value with respect to similar historical cases, which is obtained by aggregating the case similarity, the utility case similarity, the first response time, and the implementation effect.The subjective preferences and objective information are also integrated in the decision-making process. Finally, we present a case study based on the emergency response to a fire in a highrise building, which illustrates the applicability and feasibility of the proposed method.
基金the National Natural Science Foundation of China (Nos. 50775140, 50575142 and 60304015)the National High Technology Research and Development Program (863) of China (No. 2008AA04Z113)+1 种基金the National Basic Research Program (973) of China (No. 2006CB705400)the Shanghai Committee of Science and Technology (No. 08JC1412000)
文摘Case retrieval(CR) is critically an important part of case-based design. However few studies attempt to research CR for customer-driven design and analyze the eect of other production factors besides similarity computation. This paper proposes a new CR method for customer-driven design,and requirement-weighting analysis. Fuzzy set theory are integrated into CR process to deal with the fuzzy and imprecision customer requirements. So the proposed method is called weighted fuzzy case retrieval(WFCR). Furthermore,similar case evaluation is added into CR process to demonstrate that the best case is selected not only on the basis of satisifaction for the given requriements,but also on the degree of preference over other cases according to multiple evaluation criteria. Meanwhile,WFCR system is developed and applied to power transformer design to validate its scientificity and practicality. Finally,the paper statistically validated the supriority of WFCR by comparing it with traditional fuzzy case retrieval methods(FCRs),and the comparison indicates that WFCR is more accurate than other FCRs.
文摘The paper studies on case-based reasoning of uncertain product attributes in configuration design of a product family. Interval numbers characterize uncertain product attributes. By interpolating a number of certain values randomly to replace interval numbers and making projection pursuit analysis on source cases and target cases of expanded numbers, we can get a projection value in the optimal projection direction. Based on projection value, we can construct a case retrieval model of projection pursuit that can handle coexisting certain and uncertain product attributes. The application examples of chainsaw configuration design show that case retrieval is highly sensitive to reliable results.
基金an interim result of the University-Level Special Project of Southwest University of Political Science and Law,entitled Studying and Implementing the Guiding Principles of the Fourth Plenary Session of the 20th CPC Central Committee。
文摘As a basic external manifestation of judicial justice in judicial practice,‘same cases with same judgements'and‘similar cases with same judgements'are the psychological expectations of human society for the pursuit of fairness and justice.Although the similar case retrieval system was endowed with this‘sacred mission'at the beginning of the system's establishment,no matter from the logical nature of the system's operation and the limitations of the formation basis of similar cases,or whether it has a mandatory application to judges even in terms of the limited binding force of similar cases on judges'judgements under the mandatory search obligation,it should be rationally recognized that the search mechanism for similar cases is limited in realizing the function of‘ame cases with same judgements'.The retrieval mechanism for similar cases can realize the interpretation function and the coordination function of the rule of law under the background of current regional development differences in China through differentiated functional positioning.
基金supported by the Large-scale Industry Model Evaluation Capability Development(CXFZ2024004)the National Social Science Foundation of China(22ZD035)the Research Innovation Project Plan of China University of Political Science and Law(24KYGH021).
文摘The purpose of this paper is to explore the application of large language models(LLMs)in legal case retrieval and to evaluate their potential for providing legal professionals with more efficient work aids.Currently,although pre-trained models have made great progress in legal case retrieval,they are often limited to specific types of law(e.g.,criminal law,civil law,etc.)and lack the ability to generalize across different types of law.Moreover,most models can only deal with a single task,whereas the legal case retrieval task requires a model to have a superb comprehension of legal texts,involving multiple subtasks and requiring multitasking capabilities.Therefore,the large language model,which has super generalization and multitasking ability,can solve the above problems.In order to explore the application of large language models for legal case retrieval in the legal domain,this paper evaluates a series of emerging large language models,including multilingual models,homegrown large models,and models specifically designed for the legal domain.These models are used to retrieve legal cases and its associated subtasks.Based on the Supreme People’s Court definition,the legal case retrieval task is broken down into seven subtasks:event detection,fact generation,trigger word extraction,keyword extraction,summarization,dispute focus identification,and reasoning generation.Using a variety of evaluation metrics,the experiments demonstrated that these emerging models have significant potential in the field of legal case retrieval,even with few shot samples.The research in this paper not only introduces new ideas in the field of legal case retrieval,but also empirically verifies the potential of LLMs to improve the quality and efficiency of retrieval.It proves the value of large language models in this field and is expected to significantly enhance the efficiency of legal practitioners,as well as promote the consistency and fairness of legal judgments through the use of emerging technologies.
文摘Fixture is an important manufacturing activity. A fixture design system based on case-based reasoning (CBR) is proposed in this paper. A new method of case representation on the basis of fixture function is presented, where the case representation is constituted of workpiece knowledge, processing feature knowledge, and fixture feature knowledge. Running the prototype system shows that the knowledge representation method, using cases, s a better way to transform and explain the design knowledge.
基金Supported by State Science and Technology Support Program of China(Grant No.2012BAF12B08-04)Liaoning Provincial Key Scientific and Technological Project of China(Grant Nos.2011216010,2010020076-301)
文摘Product customization is a trend in the current market-oriented manufacturing environment. However, deduction from customer requirements to design results and evaluation of design alternatives are still heavily reliant on the designer＇s experience and knowledge. To solve the problem of fuzziness and uncertainty of customer requirements in product configuration, an analysis method based on the grey rough model is presented. The customer requirements can be converted into technical characteristics effectively. In addition, an optimization decision model for product planning is established to help the enterprises select the key technical characteristics under the constraints of cost and time to serve the customer to maximal satisfaction. A new case retrieval approach that combines the self-organizing map and fuzzy similarity priority ratio method is proposed in case-based design. The self-organizing map can reduce the retrieval range and increase the retrieval efficiency, and the fuzzy similarity priority ratio method can evaluate the similarity of cases comprehensively. To ensure that the final case has the based on grey correlation analysis is proposed to evaluate similar cases best overall performance, an evaluation method of similar cases to select the most suitable case. Furthermore, a computer-aided system is developed using MATLAB GUI to assist the product configuration design. The actual example and result on an ETC series machine tool product show that the proposed method is effective, rapid and accurate in the process of product configuration. The proposed methodology provides a detailed instruction for the product configuration design oriented to customer requirements.
基金Supported by the Key Laboratory of Geo-Informatics of State Bureau of Surveying and Mapping (200626)
文摘In this paper, the method of tmderstanding GIS Chinese query based on CBR （case-based reasoning） is proposed. The CaseBase is designed on the grammar rule of Chinese query sentences, the cases that pick up the character of standard query language （SQL） and are expressed in form semantics. In retrieval, the concepts of target comparability, structure comparability and individual comparability are given. The algorithm of case retrieval searches first the case of structure comparability and then individual comparability. The SQL reasoning algorithm that first parses form semantics, then reasons on structure comparability, and finally reasons on individual comparability is realized. In the actual GIS, the structure comparability and individual comparability are tested respectively. The experiment results show that the strategy of CBR is correct and feasible. With the size of CaseBase increasing through studies, the CaseBase will eventually be perfected. The effect of retrieval and reasoning will become better and better.
