知识云及其在知识获取中的意义

如何有效地获取领域专家的知识一直被视为人工智能中的难题．本文的目的在于提出一种关于知识获取的基本观点，并以此观点为基础来研究知识获取问题．这个观点的基本内容是：象波尔的原于模型一样，在专家的知识周围有一些知识层．它们是认识和获取专家知识的突破口或入口．本文将这些知识层看成是知识云，同时将上述观点视作知识云假设．我们将讨论知识云的内涵，研究知识云假设的合理性，最后将阐述知识云这一概念在知识获取中的意义．     

基于面向对象模型的自动知识获取方法

本文提出了一个以自然语言为通讯媒介的自动知识获取系统,它不仅能理解用自然语言描述的专家知识,还能按照面向对象模型诱导人类专家系统地、结构化地描述其知识。这种诱导既降低了自然语言理解的复杂度,又为人类专家提供了自然的知识描述方式,避免了知识遗漏与散杂。面向对象模型与目标知识表示风格的统一则大大简化了知识获取过程,提高了知识获取的效率。     

基于广义遗传粒子群优化算法的供应链优化求解

供应链优化研究是供应链管理中的一个重要问题,也是一个难题,首先提出了一个新型供应链优化模型,针对该优化问题的求解,构造了融入特殊自然演化规则的广义遗传算法(GA),并且与粒子群优化结合,得到了广义遗传粒子群优化算法,克服了粒子群优化算法局部收敛的缺陷,提高了其全局收敛的能力。实验表明,对供应链优化问题的求解,广义遗传粒子群优化算法优于传统的遗传算法、粒子群优化算法和分枝界定法。     

基于共识标准的语言标度颗粒优化模型

研究语言偏好信息下的群决策问题.定义了反映群体共识的两个测度指标,分别反映群体内所有专家的一致性水平及专家的个人观点与群体观点的分歧程度;基于共识测度指标构建一种语言标度的颗粒优化模型,提出了求解语言标度颗粒最佳分界点的改进PSO算法,并给出一种对方案排序进行择优的群决策方法. 最后,通过一个算例说明了所提出方法的可行性和有效性.     

广义多尺度决策系统中基于可变精度的最优尺度组合

针对广义多尺度决策系统的知识表示与知识获取问题,讨论广义多尺度决策系统中基于对偶概率粗糙集模型的最优尺度组合选择问题.定义广义多尺度决策系统中β下近似最优尺度组合、 β上近似最优尺度组合、 β信任分布最优尺度组合与β似然分布最优尺度组合概念,分析不同最优尺度组合之间的关系与特征,证明当β在特殊的阈值范围内时, β下近似最优尺度组合与最大分布最优尺度组合等价,而β上近似最优尺度组合与广义决策最优尺度组合等价.     

不协调广义决策多尺度序信息系统的最优尺度选择与规则提取

粒计算模拟人类思考问题的模式,在大数据挖掘和知识发现方面有独特优势。针对不协调的广义决策多尺度序信息系统的知识获取问题,利用证据理论来研究不协调的广义决策多尺度序信息系统的最优尺度选择与规则提取。首先,将优势关系引入决策多尺度信息系统中,并介绍广义决策多尺度序信息系统的相关概念;其次,通过引入不协调广义决策多尺度序信息系统的尺度组合概念,给出不同尺度组合下信息粒和集合的下近似与上近似的表示及其相互关系,并进一步定义了几种针对不同决策的不协调广义决策多尺度序信息系统的最优尺度组合概念,讨论了它们之间的关系;最后,给出了基于广义优势决策函数的辨识矩阵属性约简与规则提取方法。     

根据观察获取知识

本文介绍一种建立知识库的学习方法。从人类专家吸取知识的知识获取系统有两种类型:交互式和非交互式的。本文介绍非交互式知识获取系统,它依据观察从人类专家获得知识。这种知识获取系统学习人类专家用以解决问题的策略和从瞬时序列数据中抽取逻辑规则,其学习方法是基于翻译的学习(IBL),在学习过程中要用到预备知识。IBL 有两个子系统:翻译系统和学习系统。前者负责把现实世界的信息翻译成内部规则形式,而规则维护系统负责生成和界定知识。本文将介绍翻译系统和规则生成的预处理过程。     

基于模型的知识工程方法

知识工程技术中,基于知识的系统(KBS)的构造可看成一种知识转换过程:知识工程师从领域专家那里获取知识,并将其转化为KBS所采用的知识表达形式。例如知识工程师询问专家解决问题时使用哪些规则,再将这些以自然语言表示的规则转化为合适的KBS知识表达形式。这种方法要求知识工程师和专家从相同角度,采用共同的术语描述问题求解过程,然而,实际中知识工程师和专家所处的地位,看问题的角度是不同的。上述要求限制了基于转换观点的方法     

基于群广义直觉模糊软集的空袭目标威胁评估方法

空袭目标威胁评估是提高防空武器系统应对多目标的基础. 针对威胁评估的实时性、多因素和信息不确定性问题, 构建一种基于群广义直觉模糊软集的多属性威胁评估模型. 在选择合适的威胁评估指标和量化方法的基础上, 引入多专家参量集来弥补传统广义直觉模糊软集中单个专家的评估不准确性和知识局限性等缺陷. 通过应用实例分析并与其他最新决策评估方法进行比较, 验证了该方法的可行性和有效性.

     

广义不完备信息系统的知识约简 *

以同时具有丢失型和遗漏型未知属性值的广义不完备信息系统为研究对象,提出了一种新的二元关 系,并基于此关系讨论了其中的知识约简问题。在广义不完备信息系统中,引入了约简、广义区分矩阵等概念, 并给出了约简的判定定理和知识约简算法。最后,通过一个具体的例子,说明了约简算法在广义不完备信息系 统中处理模糊和不确定性知识是可行、有效的,为从复杂的不完备信息系统中获取知识提供了新的理论基础与 技术手段。     

Weighted‐selective aggregated majority‐OWA operator and its application in linguistic group decision making

This paper focuses on the aggregation operations in the group decision‐making model based on the concept of majority opinion. The weighted‐selective aggregated majority‐OWA (WSAM‐OWA) operator is proposed as an extension of the SAM‐OWA operator, where the reliability of information sources is considered in the formulation. The WSAM‐OWA operator is generalized to the quantified WSAM‐OWA operator by including the concept of linguistic quantifier, mainly for the group fusion strategy. The QWSAM‐IOWA operator, with an ordering step, is introduced to the individual fusion strategy. The proposed aggregation operators are then implemented for the case of alternative scheme of heterogeneous group decision analysis. The heterogeneous group includes the consensus of experts with respect to each specific criterion. The exhaustive multicriteria group decision‐making model under the linguistic domain, which consists of two‐stage aggregation processes, is developed in order to fuse the experts’ judgments and to aggregate the criteria. The model provides greater flexibility when analyzing the decision alternatives with a tolerance that considers the majority of experts and the attitudinal character of experts. A selection of investment problem is given to demonstrate the applicability of the developed model.     

An integrated decision model for evaluating educational web sites from the fuzzy subjective and objective perspectives

With advances in information and network technologies, lots of data have been digitized to reveal information for users by the construction of Web sites. Unfortunately, they are both overloading and overlapping in Internet so that users cannot distinguish their quality. To address this issue in education, Hwang, Huang, and Tseng proposed a group decision system to evaluate the quality of educational Web sites by users’ and experts’ opinions. Their investigative source is solely stemmed from human intention, called the subjective perspective, to make judgments on the quality of Web sites. However, the nature of human beings in making decisions has a gap between intention and behavior. Asking people for eliciting thought is arduous to cause this gap. Human behavior, namely the objective perspective, is the other essential source to obtain human thinking and real doings. For this reason, we can use data mining approaches to acquire the objective source. In this research, we propose an integrated decision model applied in evaluating educational Web sites from the fuzzy subjective and objective perspectives. The former source is extracted by inquiring human opinion using a questionnaire, while the latter is gained automatically by a data mining technique, fuzzy clustering. An empirical study is carried out to validate the model capability.     

基于Internet的Web Services收集方法

Web Services作为一种部署在Internet上的新型的可复用软件资源,得到广泛的重视和应用。但是,现有通用搜索引擎并不能很好地支持Web Services的发现,这使得软件开发人员需要花费很大的代价寻找合适的Web Services。鉴于此,提出了一种基于Internet的Web Services获取方法,采用通用搜索引擎和特定Web Services信息发布网站相结合的方法,从Internet上收集Web Services,并从Web Services的相关网页中抽取相关描述信息。利用收集到的Web Services数据,对当前互联网上的WebServices现状进行了统计分析。这些统计结果一定程度上反映了WebServices的发展现状。     

Generalized intuitionistic fuzzy geometric aggregation operator and its application to multi-criteria group decision making

In general, for multi-criteria group decision making problem, there exist inter-dependent or interactive phenomena among criteria or preference of experts, so that it is not suitable for us to aggregate them by conventional aggregation operators based on additive measures. In this paper, based on fuzzy measures a generalized intuitionistic fuzzy geometric aggregation operator is investigated for multiple criteria group decision making. First, some operational laws on intuitionistic fuzzy values are introduced. Then, a generalized intuitionistic fuzzy ordered geometric averaging (GIFOGA) operator is proposed. Moreover, some of its properties are given in detail. It is shown that GIFOGA operator can be represented by special t-norms and t-conorms and is a generalization of intuitionistic fuzzy ordered weighted geometric averaging operator. Further, an approach to multiple criteria group decision making with intuitionistic fuzzy information is developed where what criteria and preference of experts often have inter-dependent or interactive phenomena among criteria or preference of experts is taken into account. Finally, a practical example is provided to illustrate the developed approaches.     

基于Internet的群决策研讨平台的研究与实现

比较选择了Internet环境下群决策的研讨方式,设计了合理的、动态的研讨流程;提出了一种基于向量相似度的衡量专家间一致性的方法,并在此基础上研究选取了合适的专家群体一致性判断算法;最后通过实例对该平台的实用性加以验证.     

Semi-automatic construction of domain ontology for agent reasoning

One of the key elements of the Semantic Web technologies is domain ontologies and those ontologies are important constructs for multi-agent system. The Semantic Web relies on domain ontologies that structure underlying data enabling comprehensive and transportable machine understanding. It takes so much time and efforts to construct domain ontologies because these ontologies can be manually made by domain experts and knowledge engineers. To solve these problems, there have been many researches to semi-automatically construct ontologies. Most of the researches focused on relation extraction part but manually selected terms for ontologies. These researches have some problems. In this paper, we propose a hybrid method to extract relations from domain documents which combines a named relation approach and an unnamed relation approach. Our named relation approach is based on the Hearst’s pattern and the Snowball system. We merge a generalized pattern scheme into their methods. In our unnamed relation approach, we extract unnamed relations using association rules and clustering method. Moreover, we recommend candidate relation names of unnamed relations. We evaluate our proposed method by using Ziff document set offered by TREC.     

基于可加一致性的不完全偏好信息估算方法

针对基于方案对比较的不完全模糊偏好信息的方案优选群决策问题,通过引入模糊偏好关系中的可加一致性概念,提出了一种估算评估专家缺失的偏好信息的迭代估算方法。该方法仅仅依赖专家在可加一致性基础上提供的信息,而不用考虑其他专家的信息,因而估算出来的偏好信息能够与专家原始偏好信息保持良好的一致性,从而提高了估算结果的可信度。最后给出了一个算例。     

基于Web GIS的虚拟校园综合体系研究

随着虚拟现实技术、计算机图形图像技术的不断发展进步和互联网的日益普及,虚拟校园将成为各教育教学机构展示自己教学、科研水平和对外宣传的主要渠道之一。在简单分析当前虚拟校园相关发展技术的基础上着力论述基于Web GIS的虚拟校园综合体系,提出了Web GIS环境下对虚拟校园景观进行群组图片特效展示、全景展示、虚拟仿真展示等多种方式进行综合展示的思路,并进行了必要的实践。     

Team formation in social networks based on collective intelligence – an evolutionary approach

The tremendous growth of the social web has inspired research communities to discover social intelligence, which encompasses a wide spectrum of knowledge characterized by human interaction, communication and collaboration, thereby exploiting collective intelligence (CI) to support the successful existence of social communities on the Web. In this work, we address the team formation problem for generalized tasks where a set of experts is to be discovered from an expertise social network that can collaborate effectively to accomplish a given task. The concept of CI that emerges from these collaborations attempts to maximize the potential of the team of experts, rather than only aggregating individual potentials. Because the team formation problem is NP-hard, a genetic algorithm-based approach is applied to optimize computational collective intelligence in web-based social networks. To capture the essence of CI, a novel quantitative measure Collective Intelligence Index (CII) is proposed that takes two factors into account –the “enhanced expertise score” and the “trust-based collaboration score”. This measure relates to the social interactions among experts, reflecting various affiliations that form a network of experts that help to drive creativity by deepening engagements through collaboration and the exchange of ideas and expertise, thereby enriching and enhancing the knowledge base of experts. The presented model also captures the teams’ dynamics by considering trust, which is essential to effective interactions between the experts. The computational experiments are performed on a synthetic dataset that bears close resemblance to real-world expertise networks, and the results clearly establish the effectiveness of our proposed model.     

基于决策树和马尔可夫链的问答对自动提取

问答系统能用准确、简洁的答案回答用户用自然语言提出的问题,很明显系统中问答对的规模是影响问答系统最终性能的主要因素。为了提高问答对的规模、充分利用互联网资源,本文提出了一种基于决策树和马尔科夫链的在互联网上自动抽取问答对的算法。先根据网页中的HTML标记把网页表示成一棵DOM树;然后利用树中每个节点的结构和文字信息,抽取相应的特征;最后将得到的节点特征通过由决策树和一阶马尔可夫链结合得出的分类模型进行分类。试验结果表明准确率达到了90.398%,召回率达到了86.032%。对大量网页抽取的结果表明该分类模型能够适应对各种各样的网页的抽取。