Integrating knowledge flow mining and collaborative filtering to support document recommendation

Knowledge is a critical resource that organizations use to gain and maintain competitive advantages. In the constantly changing business environment, organizations must exploit effective and efficient methods of preserving, sharing and reusing knowledge in order to help knowledge workers find task-relevant information. Hence, an important issue is how to discover and model the knowledge flow (KF) of workers from their historical work records. The objectives of a knowledge flow model are to understand knowledge workers’ task-needs and the ways they reference documents, and then provide adaptive knowledge support. This work proposes hybrid recommendation methods based on the knowledge flow model, which integrates KF mining, sequential rule mining and collaborative filtering techniques to recommend codified knowledge. These KF-based recommendation methods involve two phases: a KF mining phase and a KF-based recommendation phase. The KF mining phase identifies each worker’s knowledge flow by analyzing his/her knowledge referencing behavior (information needs), while the KF-based recommendation phase utilizes the proposed hybrid methods to proactively provide relevant codified knowledge for the worker. Therefore, the proposed methods use workers’ preferences for codified knowledge as well as their knowledge referencing behavior to predict their topics of interest and recommend task-related knowledge. Using data collected from a research institute laboratory, experiments are conducted to evaluate the performance of the proposed hybrid methods and compare them with the traditional CF method. The results of experiments demonstrate that utilizing the document preferences and knowledge referencing behavior of workers can effectively improve the quality of recommendations and facilitate efficient knowledge sharing.     

Distributed recommender for peer-to-peer knowledge sharing

A novel model of distributed knowledge recommender system is proposed to facilitate knowledge sharing among collaborative team members. Different from traditional recommender systems in the client-server architecture, our model is oriented to the peer-to-peer (P2P) environment without the centralized control. Among the P2P network of collaborative team members, each peer is deployed with one distributed knowledge recommender, which can supply proper knowledge resources to peers who may need them. This paper investigates the key techniques for implementing the distributed knowledge recommender model. Moreover, a series of simulation-based experiments are conducted by using the data from a real-world collaborative team in an enterprise. The experimental results validate the efficiency of the proposed model. This research paves the way for developing platforms that can share and manage large-scale distributed knowledge resources. This study also provides a new framework for simulating and studying individual or organizational behaviors of knowledge sharing in a collaborative team.     

A knowledge grid model and platform for global knowledge sharing

This paper proposes a knowledge grid model for sharing and managing globally distributed knowledge resources. The model organizes knowledge in a three-dimensional knowledge space, and provides a knowledge grid operation language, KGOL. Internet users can use the KGOL to create their knowledge grids, to put knowledge to them, to edit knowledge, to partially or wholly open their grids to all or some particular grids, and to get the required knowledge from the open knowledge of all the knowledge grids. The model enables people to conveniently share knowledge with each other when they work on the Internet. A software platform based on the proposed model has been implemented and used for knowledge sharing in research teams.     

Conference assistant system for supporting knowledge sharing in academic communities

This paper describes our ongoing attempts to build a communityware system by presenting a project of providing digital assistants to support participants in an academic conference. We provided participants at the conference with a personal assistant system with mobile and ubiquitous computing technologies and facilitated communication among the participants. We also made online services available via the Web to encourage the participants to continue their relationships even after the conference. In this paper, we show the system we provided for the project and report the results.     

基于模糊相关的Web文档分类方法

面对Internet上不断增长的巨大信息量,如何使用户获得有趣的和有用的信息已成为信息检索急需解决的问题。由于Web文档往往具有不确定的特征,使得利用模糊集合理论对信息检索过程的不确定性建立模型成为可能。文章提出了一种基于模糊相关技术的Web文档分类方法,实验结果表明,该方法比基于向量空间模型的Web分类方法有较高的分类精度。     

基于本体的文档自动分类系统的研究

讨论了基于本体的文档自动分类系统的意义,给出了系统的框架。利用现有的文档自动分类技术,结合领域本体的分类词汇为文档建立索引。研究人工分类、机器学习分类的结合方法,提出基于“分类一使用一调整”逐步求精的分类方法。结合企业知识管理需求,开发了原型系统,进行了初步验证。     

Managing knowledge sharing: Emergent and engineering approaches

We wished to determine how the process of knowledge sharing could be managed, seeing that it is a knowledge management dilemma. If knowledge sharing is crucial to an organization’s interests, but is inherently emergent in nature, how can the organization still manage the process? In order to answer this question, a distinction was made between two approaches towards managing knowledge sharing: an emergent approach, focusing on the social dynamics between organizational members and the nature of their daily tasks, and an engineering approach, focusing on management interventions to facilitate knowledge transfer. While the first is central to today’s thinking about knowledge, we used a field study in six organizations to show that both approaches have value in explaining knowledge sharing. Instruments that are part of the engineering approach create conditions for variables in the emergent approach, which in turn also exert a direct influence on knowledge sharing.     

Multiple-vector user profiles in support of knowledge sharing

This paper describes an algorithm to automatically construct expertise profiles for company employees, based on documents authored and read by them. A profile consists of a series of high dimensional vectors, each describing an expertise domain, and provides a hierarchy between these vectors, enabling a structured view on an employee’s expertise. The algorithm is novel in providing this layered view, as well as in its high degree of automation and its generic approach ensuring applicability in an industrial setting.The profiles provide support for several knowledge management functionalities that are difficult or impossible to achieve using existing methods. This paper in particular presents the initialization of communities of practice, bringing together both experts and novices on a specific topic. An algorithm to automatically discover relationships between employees based on their profiles is described. These relationships can be used to initiate communities of practice. The algorithms are validated by means of a realistic dataset.     

Health-guided recipe recommendation over knowledge graphs

While the availability of large-scale online recipe collections presents opportunities for health consumers to access a wide variety of recipes, it can be challenging for them to discover relevant recipes. Whereas most recommender systems are designed to offer selections consistent with users’ past behavior, it remains an open problem to offer selections that can help users’ transition from one type of behavior to another, intentionally. In this paper, we introduce health-guided recipe recommendation as a way to incrementally shift users towards healthier recipe options while respecting the preferences reflected in their past choices. Introducing a knowledge graph (KG) into recommender systems as side information has attracted great interest, but its use in recipe recommendation has not been studied. To fill this gap, we consider the task of recipe recommendation over knowledge graphs. In particular, we jointly learn recipe representations via graph neural networks over two graphs extracted from a large-scale Food KG, which capture different semantic relationships, namely, user preferences and recipe healthiness, respectively. To integrate the nutritional aspects into recipe representations and the recommendation task, instead of simple fusion, we utilize a knowledge transfer scheme to enable the transfer of useful semantic information across the preferences and healthiness aspects. Experimental results on two large real-world recipe datasets showcase our model’s ability to recommend tasty as well as healthy recipes to users.     

文本数字水印技术研究

随着计算机技术和网络技术的飞速发展,数字文本的传播、拷贝、分发更加容易,同时也面临着非法传播和随意篡改的问题。文本数字水印技术可以保护数字作品的版权,防止盗版和侵权行为。该文分析了基于格式文本的数字水印技术的算法和研究现状,并重点讨论了针对当今比较流行的PDF格式化文档的数字水印算法,最后探讨了今后研究的发展趋势。     

Special knowledge sharing incentive mechanism for two clients with complementary knowledge: A principal-agent perspective

In this paper, we study how the firm share the special knowledge of two knowledge-complementarity clients by implementing a large and complex project which the firm out-sourced. Firstly, incentive mechanism for complementarity special knowledge sharing are designed for clients being risk-neutral and risk-averse respectively under the asymmetric information. Further, knowledge complementary effects and other relevant factors on the optimal incentive coefficient are analyzed. Lastly, the numerical results are reported.     

一种基于本体论的文本特征选取方法

针对文本特征向量高维数的问题,给出了一种基于本体论的文本特征选取方法.通过由专业领域本体所建立的概念树,把文本的特征项映射到概念,同时进行了特征项频度到概念频度的转换,使得选取得到的特征概念能够很好表征文本的内容.实验结果表明,与未进行特征概念选取相比,采用此方法选取得到的特征概念能够在尽可能减少对文本分类精度的影响下,达到降低特征维数的目的.     

Collaboration and knowledge sharing in network organizations

A network organization comprises a new type of environment around which people organize themselves so as to reach a common objective. A network organization enables the recommended interaction among people with different backgrounds, which happens when the problems they deal with are complex and multidisciplinary. Most network organizations require interactions in a geographically distributed fashion, fostering the serious challenge of displaying coherence of purpose necessary for global efficacy as from local activity: these features require an environment with special functionality. This paper describes and analyzes a collaborative environment for support to knowledge sharing and coordination of actions in geographically distributed network organizations. A case-study using the collaborative environment is presented, and the results obtained by using this environment are discussed.     

Inter-organizational networks for knowledge sharing and trading

Although companies are increasingly developing complex networks of connections with their partners and customers and shifting their focus towards expanding the knowledge management concept externally, research addressing the management of knowledge across organizational borders is rather sparse. Our aim in the present paper is to develop a typology of cross-organizational networks of information and knowledge flows. In order to arrive at such a typology we examine two issues. The first concerns the locus of control on the processes that enable knowledge flow. The second refers to the tradability of the streams of knowledge that flow among organizational entities. We examine four types of knowledge networks: “knowledge communities”, “knowledge chains”, “knowledge supplies” and “knowledge markets”. For each type of knowledge network, we examine its distinct characteristics, study related examples, consider the associated research challenges and analyze an indicative case.     

Predicting knowledge sharing practices through intention: A test of competing models

In knowledge management (KM)-related research, effective knowledge sharing is considered to be one of the most critical components of KM success. For the present research, the authors conducted a longitudinal, two-phased study to evaluate if the Theory of Reasoned Action (TRA) and three variations of the Theory of Planned Behavior—namely, TPB, decomposed TPB (DTPB), and revised TPB (RTPB)—can adequately predict knowledge sharing behaviors. The first TRA-based study shows a severe limitation in the ability of the intention to predict actual knowledge sharing behaviors collected from a knowledge management platform. In a subsequent study, three variations of TPB-based models were employed to show that, although the independent variables (i.e., attitude, subjective norm, and perceived behavior control that is decomposed into controllability and self-efficacy) give satisfactory explanations of variance in intention (R² > 42%), the intention–behavior gap still exists in each of the three models. Only the perceived self-efficacy in the revised TPB can directly predict knowledge sharing behaviors. This gap highlights the importance of knowledge sharing as a fundamentally social activity for which the actualization of intention into actions may be interrupted due to barriers such as a mistake-free culture or others’ deliberate misinterpretations that may in turn cause unanticipated negative consequences to the person. The theoretical implication of this study is that in applying TPB to study knowledge sharing practices, researchers must focus on control beliefs that reflect people’s capacity to overcome possible environmental challenges encountered in carrying out their knowledge sharing intentions.     

The role of knowledge sharing self-efficacy in sharing Open Educational Resources

In the current paper we report on a study regarding teachers’ sharing behavior regarding their Open Educational Resources (OER) in the Netherlands. Little is known about how many teachers actually share their learning materials and, therefore, an attempt was made to estimate the number of Dutch teachers and the types of OER they share. Second, we tried to find out whether knowledge sharing self-efficacy facilitated, and evaluation apprehension and trust inhibited teachers to share OER in two different contexts of sharing behavior; sharing with colleagues at their school (interpersonal sharing) and sharing with the public through Internet (Internet sharing). A survey among 1568 teachers from primary to higher education was undertaken to test the relative importance of knowledge sharing self-efficacy, evaluation apprehension and trust in determining Dutch teachers’ intention to share. The results showed that a large proportion of the Dutch teachers shared their OER, but that this sharing was limited to learning materials with low complexity (e.g., texts or images). Moreover, sharing occurred twice as much interpersonally than via websites. Our hypothesis that evaluation apprehension is significantly related to sharing behavior as well as the intention to share was not confirmed. Self-efficacy to share knowledge did, however, explain some of the differences in sharing behavior and in the intention to share of Dutch teachers, although the variables under study accounted only for a small amount of variance. Our findings should thus be replicated in further studies and other variables should be considered that could effectively predict OER sharing behavior of teachers.     

A fuzzy trust evaluation method for knowledge sharing in virtual enterprises

The success of virtual enterprises (VEs) depends on the effective sharing of related resources between various enterprises or workers who perform related activities. Specifically, VE success hinges on the integration and sharing of information and knowledge. Trust is an important facilitator of knowledge sharing. However, the trustworthiness of a peer is a vague concept that is dynamic and that often shifts over time or with environmental changes. This study designs a trust-based knowledge-sharing model based on characteristics of VEs and the knowledge structure model to express knowledge associated with VE activities. Subsequently, the factors that affect the trust evaluation are identified based on the characteristics of trust and VEs. Finally, this study develops a knowledge sharing, decision-making framework in which a fuzzy trust evaluation method for sharing knowledge is proposed based on VE activities and the interactions among workers in allied enterprises. The method consists of three sub-methods, including an activity correlation evaluation method, a current trust evaluation method, and an integral trust evaluation method. Under the premises of secure VE knowledge and reasonable access authorization, the proposed knowledge-sharing method provides the trust level between a knowledge-requesting enterprise and a knowledge-supplying enterprise to improve the willingness of the latter to share more valuable knowledge, ultimately increasing the efficiency and competitiveness of VEs.     

一种支持软件知识共享的本体模型研究

为了支持分布式环境下项目团队成员之间软件开发知识有效的共享,需要对软件开发知识以及它们之间的关系进行分析和定义。根据软件开发知识的内容、特点以及它们之间的关系,对软件开发知识进行了形式化的表示,并创建了软件开发知识本体和软件开发知识本体规则。通过protégé 和Jena实现对此本体的创建、存储和对此本体规则的SPARQL形式转换,据此形成知识本体库来支持软件开发知识共享。     

An angle-based interest model for text recommendation

Building an interest model is the key to realize personalized text recommendation. Previous interest models neglect the fact that a user may have multiple angles of interest. Different angles of interest provide different requests and criteria for text recommendation. This paper proposes an interest model that consists of two kinds of angles: persistence and pattern, which can be combined to form complex angles. The model uses a new method to represent the long-term interest and the short-term interest, and distinguishes the interest in object and the interest in the link structure of objects. Experiments with news-scale text data show that the interest in object and the interest in link structure have real requirements, and it is effective to recommend texts according to the angles.     

Facilitating educators’ knowledge sharing with dedicated Information Systems

The process of knowledge sharing can be seen as the lifeblood for the establishment of a true Knowledge Society. Such a society must be grounded on an iterative process whereby existing knowledge is constantly shared, consolidated and – crucially – enriched with new knowledge. And knowledge sharing is the means by which that enrichment can take place. Without doubt, these processes play a vital role in the context of education, which ultimately has a strong bearing on the formation of the Knowledge Society. In this paper, knowledge sharing among educators is discussed within the context of long-term research work that the authors have carried out in the field. The paper reports on the design and development of a series of Information Systems conceived for the sharing of practices among educational practitioners. It discusses the thinking behind these different but related systems and examines how this is borne out in the implementation of key system features.