The IKBALS project: Multi-modal reasoning in legal knowledge based systems

In attempting to build intelligent litigation support tools, we have moved beyond first generation, production rule legal expert systems. Our work integrates rule based and case based reasoning with intelligent information retrieval.When using the case based reasoning methodology, or in our case the specialisation of case based retrieval, we need to be aware of how to retrieve relevant experience. Our research, in the legal domain, specifies an approach to the retrieval problem which relies heavily on an extended object oriented/rule based system architecture that is supplemented with causal background information. We use a distributed agent architecture to help support the reasoning process of lawyers.Our approach to integrating rule based reasoning, case based reasoning and case based retrieval is contrasted to the CABARET and PROLEXS architectures which rely on a centralised blackboard architecture. We discuss in detail how our various cooperating agents interact, and provide examples of the system at work. The IKBALS system uses a specialised induction algorithm to induce rules from cases. These rules are then used as indices during the case based retrieval process.Because we aim to build legal support tools which can be modified to suit various domains rather than single purpose legal expert systems, we focus on principles behind developing legal knowledge based systems. The original domain chosen was theAccident Compensation Act 1989 (Victoria, Australia), which relates to the provision of benefits for employees injured at work. For various reasons, which are indicated in the paper, we changed our domain to that ofCredit Act 1984 (Victoria, Australia). This Act regulates the provision of loans by financial institutions.The rule based part of our system which provides advice on the Credit Act has been commercially developed in conjunction with a legal firm. We indicate how this work has lead to the development of a methodology for constructing rule based legal knowledge based systems. We explain the process of integrating this existing commercial rule based system with the case base reasoning and retrieval architecture.     

A Framework for the E-Discovery of Social Media Content in the United States

People are using social networking sites (SNS) for day-to-day communications, outpacing email and texts. SNS are evidence gold mines subject to discovery in investigations, audits, and litigation. This paper examines the Federal Rules of Civil Procedure (FRCP), which specifically address electronically stored information (ESI), but not social content, as a unique form of evidence. A framework is presented to categorize legal cases according to the degree of e-discovery access granted. One conclusion is caveat usor.     

Rule-based XML

Legal contracts and litigation documents common to the American legal system were encoded in the eXtensible Markup Language (XML). XML also represents rules about the contracts and litigation procedure. In addition to an expert system tool that allows one to make inferences with that engine, a Graphical User Interface (GUI) generates the XML representing the rules. A rulebase is developed by marking up examples of the XML to be interpreted and the XML to be generated, analogously to Query By Example. This article provides a broader context of the synergy between XML and artificial intelligence by including discussions of: (1) the role of Artificial Intelligence in handling routine litigation; (2) how the use of XML enables legal expert systems to get their `input' without the user having to enter the same information again for the expert system;(3) the advantages of XML markup over other forms of markup for documents; (4) the relationship between XML and ontologies; (5) other projects using XML with rules or legal affairs.     

Insights from consumer interactions on a social networking site: Findings from six apparel retail brands

Consumer social interactions on a social networking site have been discussed in the literature as information sources on consumer negative voice, product market research, and trend forecasting. The present study contributes to this line of research by identifying insights that a retail brand can derive from consumer social interactions about a competing retail brand. Based on 2,573,620 consumer social interactions related to six apparel retailers on the social networking site Facebook, this study analyzes the fan number, brand posting and response behavior, and consumer activities. The number of fans correlates with retail sales and the number of stores. However, the fan number is not an indicator of (social) displeasure. Consumer activities such as commenting, liking, and sharing, provide significant indications of these situations. As posting and response behavior reflect central elements of brand strategies on social networking sites, this study proposes a framework for identifying these strategies and the positioning of competing brands. For the six apparel retail brands, we identified a prototypical representative for three of four social interaction strategies.     

Facilitating construction of safety cases from formal models in Event-B

ContextCertification of safety–critical software systems requires submission of safety assurance documents, e.g., in the form of safety cases. A safety case is a justification argument used to show that a system is safe for a particular application in a particular environment. Different argumentation strategies (informal and formal) are applied to determine the evidence for a safety case. For critical software systems, application of formal methods is often highly recommended for their safety assurance.ObjectiveThe objective of this paper is to propose a methodology that combines two activities: formalisation of system safety requirements of critical software systems for their further verification as well as derivation of structured safety cases from the associated formal specifications.MethodWe propose a classification of system safety requirements in order to facilitate the mapping of informally defined requirements into a formal model. Moreover, we propose a set of argument patterns that aim at enabling the construction of (a part of) a safety case from a formal model in Event-B.ResultsThe results reveal that the proposed classification-based mapping of safety requirements into formal models facilitates requirements traceability. Moreover, the provided detailed guidelines on construction of safety cases aim to simplify the task of the argument pattern instantiation for different classes of system safety requirements. The proposed methodology is illustrated by numerous case studies.ConclusionFirstly, the proposed methodology allows us to map the given system safety requirements into elements of the formal model to be constructed, which is then used for verification of these requirements. Secondly, it guides the construction of a safety case, aiming to demonstrate that the safety requirements are indeed met. Consequently, the argumentation used in such a constructed safety case allows us to support it with formal proofs and model checking results used as the safety evidence.     

Discovery-led refinement in e-discovery investigations: sensemaking,cognitive ergonomics and system design

Given the very large numbers of documents involved in e-discovery investigations, lawyers face a considerable challenge of collaborative sensemaking. We report findings from three workplace studies which looked at different aspects of how this challenge was met. From a sociotechnical perspective, the studies aimed to understand how investigators collectively and individually worked with information to support sensemaking and decision making. Here, we focus on discovery-led refinement; specifically, how engaging with the materials of the investigations led to discoveries that supported refinement of the problems and new strategies for addressing them. These refinements were essential for tractability. We begin with observations which show how new lines of enquiry were recursively embedded. We then analyse the conceptual structure of a line of enquiry and consider how reflecting this in e-discovery support systems might support scalability and group collaboration. We then focus on the individual activity of manual document review where refinement corresponded with the inductive identification of classes of irrelevant and relevant documents within a collection. Our observations point to the effects of priming on dealing with these efficiently and to issues of cognitive ergonomics at the human–computer interface. We use these observations to introduce visualisations that might enable reviewers to deal with such refinements more efficiently.     

A Methodology to Create Legal Ontologies in a Logic Programming Based Web Information Retrieval System

Web legal information retrieval systems need the capability to reason with the knowledge modeled by legal ontologies. Using this knowledge it is possible to represent and to make inferences about the semantic content of legal documents. In this paper a methodology for applying NLP techniques to automatically create a legal ontology is proposed. The ontology is defined in the OWL semantic web language and it is used in a logic programming framework, EVOLP+ISCO, to allow users to query the semantic content of the documents. ISCO allows an easy and efficient integration of declarative, object-oriented and constraint-based programming techniques with the capability to create connections with external databases. EVOLP is a dynamic logic programming framework allowing the definition of rules for actions and events. An application of the proposed methodology to the legal web information retrieval system of the Portuguese Attorney General’s Office is described.     

Understanding the law: improving legal knowledge dissemination by translating the contents of formal sources of law

Considerable attention has been given to the accessibility of legal documents, such as legislation and case law, both in legal information retrieval (query formulation, search algorithms), in legal information dissemination practice (numerous examples of on-line access to formal sources of law), and in legal knowledge-based systems (by translating the contents of those documents to ready-to-use rule and case-based systems). However, within AI & law, it has hardly ever been tried to make the contents of sources of law, and the relations among them, more accessible to those without a legal education. This article presents a theory about translating sources of law into information accessible to persons without a legal education. It illustrates the theory by providing two elaborated examples of such translation ventures. In the first example, formal sources of law in the domain of exchanging police information are translated into rules of thumb useful for policemen. In the second example, the goal of providing non-legal professionals with insight into legislative procedures is translated into a framework for making available sources of law through an integrated legislative calendar. Although the theory itself does not support automating the several stages described, in this article some hints are given as to what such automation would have to look like.

An Australian Perspective on Research and Development Required for the Construction of Applied Legal Decision Support Systems

At the Donald Berman Laboratory for Information Technology and Law, La TrobeUniversity Australia, we have been building legal decision support systems for a dozenyears. Whilst most of our energy has been devoted to conducting research in ArtificialIntelligence and Law, over the past few years we have increasingly focused uponbuilding legal decision support systems that have a commercial focus.In this paper we discuss the evolution of our systems. We begin with a discussion ofrule-based systems and discuss the transition to hybrid rule-based/case-based systems.We next discuss how we have used machine learning in building legal decision supportsystems. Our focus on using machine learning led us to investigate the domains ofexplanation and argumentation. We conclude by discussing our current work onbuilding negotiation support systems and tools for constructing web-based legaldecision support systems.     

以加盟商的视角谈品牌服装的商品组合

以品牌为主导的国内服装产业,目前正在以品牌特许经营的方式,在中国服装市场上到处建设销售网络。同时,作为拥有一定知名度和市场占有率的品牌服装,订货也由最初的代理制转变为买断制,这就给加盟商带来了一定程度的压力和风险,因此作为加盟商如何组织自己的商品组合就变得十分重要,本文将站在加盟商的角度,对商品组合的构成进行详细的分析,以希望能在提升品牌形象的基础上实现利益的最大化。     

Designing intelligent litigation support tools: The IKBALS perspective

In the legal domain, it is rare to find solutions to problems by simply applying algorithms or invoking deductive rules in some knowledge‐based program. Instead, expert practitioners often supplement domain‐specific knowledge with field experience. This type of expertise is often applied in the form of an analogy. This research proposes to combine both reasoning with precedents and reasoning with statutes and regulations in a way that will enhance the statutory interpretation task. This is being attempted through the integration of database and expert system technologies. Case‐based reasoning is being used to model legal precedents while rule‐based reasoning modules are being used to model the legislation and other types of causal knowledge. It is hoped to generalise these findings and to develop a formal methodology for integrating case‐based databases with rule‐based expert systems in the legal domain.     

Emerging AI & Law approaches to automating analysis and retrieval of electronically stored information in discovery proceedings

This article provides an overview of, and thematic justification for, the special issue of the journal of Artificial Intelligence and Law entitled “E-Discovery”. In attempting to define a characteristic “AI & Law” approach to e-discovery, and since a central theme of AI & Law involves computationally modeling legal knowledge, reasoning and decision making, we focus on the theme of representing and reasoning with litigators’ theories or hypotheses about document relevance through a variety of techniques including machine learning. We also identify two emerging techniques for enabling users’ document queries to better express the theories of relevance and connect them to documents: social network analysis and a hypothesis ontology.     

商誉影响下的双渠道供应链竞争广告策略研究

随着网络技术的发展,电子网络销售品台走进消费者的世界,冲击着传统的零售市场,越来越多的企业开始在新的市场结构中寻找更为广阔的商机,如何在新的消费市场结构中合理的进行资源配置成为当下企业的一个难题,为研究电子直销和传统零售混合双渠道供应链中两个零售商品牌竞争的广告投入问题,构建了一个商誉影响下的双渠道供应链品牌竞争广告策略模型,运用汉密尔顿-雅克比-贝尔曼方程,分析竞争条件下的广告投入和影响因子。研究结果表明：存在竞争关系的两个零售商在混合双渠道供应链下的广告投入不仅跟当前的市场份额相关,同时还取决于商誉对市场竞争的影响力;最后利用数值算例分析论证了理论结果。     

Legal complicance by design: technical solutions for future distributed electronic markets

A novel challenge for Internet-based electronic market platforms constitutes trading of short-lived or non-material goods (e.g., electrical power, bandwidth-on- demand). In such a scenario, distributed market platforms are superior to centralized market platforms in many respects, e.g., because of lower transaction costs, more flexible options for contract negotiations, scalability, and robustness. However, they lack legal certainty since they are not operated by a trusted third party. This paper discuses how the SESAM framework for distributed electronic markets provides legal certainty conforming to European regulations based on three building blocks: First, it models juristic expertise as a formal workflow. Second, it includes a legal advisor consulting the users that are often legal laities. Third, it provides provableness and verifiability. Besides other mechanisms, the last building block comprises a novel solution for adducing the reception of electronic documents in a distributed setting. The real life example of trading energy on an electronic market platform is used to illustrate the interworking of all building blocks.     

E-Discovery: Identifying and Mitigating Security Risks during Litigation

When producing electronically stored information (ESI) in response to lawsuits, businesses face several security risks as well as legal requirements they must satisfy. Customized document management programs and e-discovery policies are key tools in protecting against inadvertent disclosure as well as meeting business and legal needs.     

A modified Lotka–Volterra model for competition forecasting in Taiwan’s retail industry

The retail industry is an important component of the supply chain of the goods and services that are consumed daily and competition has been increasing among retailers worldwide. Thus, forecasting the degree of retail competition has become an important issue. However, seasonal patterns and cycles in the level of retail activity dramatically reduce forecasting accuracy. This paper attempts to develop an improved forecasting methodology for retail industry competition subject to seasonal patterns and cycles. Using market share data and the moving average method, a modified Lotka–Volterra model with an additional constraint on the summation of market share is proposed. Furthermore, the mean absolute error is used to measure the forecasting accuracy of the market share. Real Taiwanese retail data from 1999 is used to validate the forecasting accuracy of our modified Lotka–Volterra model. Our methodology successfully mitigates errors from seasonal patterns and cycles and outperforms other benchmark models. These benchmarks include the Bass and Lotka–Volterra models for revenue or market share data, with or without using the moving average method. Our methodology assists the retail industry in the development of management strategies and the determination of investment timing. We also demonstrate how the Lotka–Volterra model can be used to forecast the degree of industry competition.     

基于知识图谱的盗窃案件法律文书智能推理研究

在检察官办案过程中对盗窃案件性质把握不准确,对量刑建议给出缺乏经验,导致给出的量刑建议准确性不足.为了使检察官给出更加准确的量刑建议,提供辅助量刑参考,通过对盗窃案件法律文书理论和知识体系进行整理和分析,对其中的隐式关系、深层关系进行挖掘、推理,通过搭建本体模型,提出了基于本体的盗窃案件法律文书知识图谱构建方法,并且设计自定义推理规则,实现了盗窃案件法律文书知识图谱在相似量刑类案推送测试功能,得到了理想的测试结果.研究证明,构建基于本体的盗窃案件法律文书知识图谱,利用智能推理技术,给检察官提供相似案件量刑参考,辅助了检察官给出更加合理的量刑建议.     

不确定条件下报废汽车回收率云模型仿真研究

报废汽车回收与再制造是节约资源的重要途径,回收率是其中的关键指标之一。影响回收率的因素很多,尤其是回收系统中不确定性因素对回收率具有重要影响。因此,首先从系统工程角度出发,分析消费者行为、企业意愿、政府政策等影响回收率的不确定因素,建立报废汽车回收率系统递阶结构模型,运用模糊语言概念进行定性评价,并借助云模型工具,构建定性规则描述系统因素之间逻辑因果关系,得到报废汽车回收与再制造多维多规则不确定性推理系统,进而通过系统仿真,分析了国家法律法规、财政投入、消费者对再制造品购买态度等不确定性因素对回收率的影响。结果表明,模型直观地揭示了相关不确定性因素对回收率的影响机理,对政府和相关行业具有重要的参考价值。     

PRILJ: an efficient two-step method based on embedding and clustering for the identification of regularities in legal case judgments

In an era characterized by fast technological progress that introduces new unpredictable scenarios every day, working in the law field may appear very difficult, if not supported by the right tools. In this respect, some systems based on Artificial Intelligence methods have been proposed in the literature, to support several tasks in the legal sector. Following this line of research, in this paper we propose a novel method, called PRILJ, that identifies paragraph regularities in legal case judgments, to support legal experts during the redaction of legal documents. Methodologically, PRILJ adopts a two-step approach that first groups documents into clusters, according to their semantic content, and then identifies regularities in the paragraphs for each cluster. Embedding-based methods are adopted to properly represent documents and paragraphs into a semantic numerical feature space, and an Approximated Nearest Neighbor Search method is adopted to efficiently retrieve the most similar paragraphs with respect to the paragraphs of a document under preparation. Our extensive experimental evaluation, performed on a real-world dataset provided by EUR-Lex, proves the effectiveness and the efficiency of the proposed method. In particular, its ability of modeling different topics of legal documents, as well as of capturing the semantics of the textual content, appear very beneficial for the considered task, and make PRILJ very robust to the possible presence of noise in the data.

     

An analysis of some problems in managing virtual memory systemswith fast secondary storage devices

Some of the problems that are expected to be encountered in managing virtual memory systems using the newer-technology secondary storage devices are address. The difficulties that two proposed policies have in choosing the most economical program localities of reference to assign to primary memory are analyzed. K. Koh's (1981) criterion for examining the cyclic locality interval (CLI) hierarchy of a program and choosing the least-cost pathway is examined. Koh's criterion is designed for the case of a CLI containing a single inner CLI. The decision to descend the hierarchy is based on the cycle time of the outer CLI. If the outer CLI has two or more inner CLIs, it is possible for Koh's criterion to indicate that it is more economical to descend to one of the inner CLIs without that actually being the case. Choosing which CLI to descend to requires knowledge of its duration, and this is not generally available to the memory management system. An attempt to use Koh's criterion with the loop structure of a program in order to reduce space-time execution cost was not successful