Wm M. Wang

Knowledge-based extraction of intellectual capital-related information from unstructured data

Nowadays, there is an increasing demand for the identification of an organizations intellectual capital (IC) for decision support and providing important managerial insights in knowledge-intensive industries. In traditional approaches, identification of an organizations IC is usually done manually through interviews, surveys, workshops, etc. These methods are labor and time intensive and the quality of the results is highly dependent on, among other things, the experience of the investigators. This paper presents a Knowledge-based Intellectual Capital Extraction (KBICE) algorithm which incorporates the technologies of computational linguistics and artificial intelligence (AI) for automatic processing of unstructured data and extraction of important IC-related information. The performance of KBICE was assessed through a series of experiments conducted by using publicly available financial reports from the banking industry as the testing batch and encouraging results have been obtained. The results showed that, through the use of hybrid intelligent matching strategies, it is possible to extract commonly referred IC-related information from unstructured data automatically. IC information analyst can rely on this method as an additional mean to identify and extract the commonly sought IC information from financial reports in a fast, systematic and reliable manner.

An unstructured information management system (UIMS) for emergency management

Emergency management has drawn the attention of governments worldwide. It is an emerging realm for governments and organizations to respond to sudden catastrophic events rapidly and effectively during a crisis, e.g. social unrest, natural disaster, unforeseen event, and so on. There is a lot of information and knowledge involved in emergency management. The key question is how to search for the appropriate information and knowledge quickly and accurately from the massive information and knowledge based on the nature, characteristics, status and situations of the unexpected emergency in order to support the intelligent decision-making process in handling emergencies. In this paper, an unstructured information management system (UIMS) is presented for emergency management. A concept relationship model (CRM) and a dynamic knowledge flow model (DKFM) of the emergency incidence have been built to organize and represent emergency knowledge. The models can support decision-makers to have better understanding of the dependence and degree of correlation between different concepts about the emergency in order to make the appropriate decisions. The system is trial implemented in a city emergency management system and its performance is evaluated and discussed.

A knowledge‐based service automation system for service logistics

Purpose – Effective service logistics can lower the cost and increase service value by improving customer satisfaction and loyalty. However, the conventional ways of the service logistics are information driven instead of knowledge‐driven which are insufficient to meet the current needs. The purpose of this paper is to present a knowledge‐based service automation system (KBSAS) to enhance the competitiveness for manufacturing enterprises in service logistics.Design/methodology/approach – The KBSAS incorporates various artificial intelligence technologies such as case‐based reasoning which is used for achieving four perspectives of knowledge acquisition, service logistics, service automation and performance measurement, respectively.Findings – A prototype customer service portal has been built based on the KBSAS and implemented successfully in a semi‐conductor equipment manufacturing company. It is verified that the KBSAS provides high quality customer services with fast and efficient customer responses. I...

Knowledge-based inventory management in production logistics: A multi-agent approach:

Abstract With the rapidly changing market conditions, an accurate and highly dynamic inventory management model is much needed for making an enterprise more predictable to the global competition. However, traditional inventory management in production logistics is inadequate in managing inventories with high fluctuation in demand and value. To establish effective inventory management strategy, this paper presents a knowledge-based inventory management system for active inventory replenishment based on multi-agent dynamic forecasting and knowledge-based system technologies. The system dynamically forecasts the fluctuation of the demand and updates price of its raw materials. Hence, appropriate inventory management strategies are derived to respond and adapt to the rapid market changes and the material requirement. A prototype system has been built and successfully trial implemented in a manufacturing enterprise.

A pilot study on a knowledge-based case library to support suicide risk assessment

This article describes the system development processes for an electronic case library, built to facilitate and support the suicide prevention service provided by a social service organization in Hong Kong. It is a knowledge management system in which both ‘rule-based reasoning’ (RBR) and ‘case-based reasoning’ (CBR) are adopted. Initial test results, potentials and limitations of this knowledge management approach are discussed.

Enacting Personal Knowledge Management & learning with web services interoperability tools

Nowadays, learning is continuing and seeks to selecting suitable tools to support better learning. Learners are discovering new uses of the technologies for their learning by building their own personal learning environment and network (PLE&N). Many of these tools are Web 2.0 tools, including discussion forums, file/video sharing, RSS feeds and social networks. However, the existing tools are loosely connected. It is time consuming to manage them. This paper discusses the use of PLE&N with a web services interoperability tool, IFTTT (aka If This Then That), which bridges the web services. The benefits of how a PLE&N with IFTTT is discussed to support personal knowledge management for better learning. Individual knowledge workers are continuing being empowered by such Web 2.0 tools in the cloud to pursue personal goals and aspirations.

A Computational Knowledge Elicitation and Sharing System for mental health case management of the social service industry

Narrative data provide rich information and knowledge to the workers. However, existing systems mainly served as a workflow system, a reporting system, or a database system for storing this kind of information. The massive amount of unstructured narrative data makes it extremely difficult to be shared and reused. Actual knowledge sharing and reuse among the workers is still limited. This paper presents a Computational Knowledge Elicitation and Sharing System which attempts to elicit knowledge from individuals as well as a team and converts it into a structured format and shared among the team. The proposed system accomplishes several current technologies in knowledge-based system, artificial intelligence and natural language processing, which converts the narrative knowledge of knowledge workers into a concept mapping representation. With a sufficient number of narratives, patterns are revealed and an aggregate concept map for all participating members is produced. It converts the unstructured text into a more structured format which helps to summarize and share the knowledge that can be taken in handling different case management issues. Such integration is considered to be novel. A prototype system has been implemented based on the method successfully in the mental healthcare of a social service organization for handling their case management issues. An experiment has been carried out for measuring the accuracy for converting the unstructured data into the structured format. The theoretical results are found to agree well with the experimental results.

A knowledge-Based Infotronics Supervisory System for Intelligent Service Automation

Abstract With the effect of globalization, todays physical asset management (PAM) activities are becoming more and more complex and it is essential to make optimal use of knowledge of PAM. However, conventional methods of PAM relying on condition-based maintenance are inadequate to attain the multi-perspective of an enterprise for accomplishing knowledge management, proactive maintenance planning, and intelligent service automation in order to drive the continuous improvement of the enterprise. This paper presents a knowledge-based infotronics supervisory system (KISS) that integrates Infotronics, automatic supervision, and multi-agent and various artificial intelligence technologies to achieve these purposes. A prototype system has been built and evaluated through a trial implementation in a semiconductor industry.

A knowledge-based system for assessing and managing intellectual property managerial risks for small-and-medium sized technological enterprises

Managing intellectual property (IP) is a critical issue that almost no company can avoid. This is particularly true for small and medium sized technological enterprises (SMTEs). Due to their limited resources, SMTEs typically do not devote sufficient effort to managing intellectual property (IP) risks. This may lead to serious financial and other losses for such companies. In this paper, a knowledge-based intellectual property managerial risk system (KIPMRS) has been developed to assess and manage IP managerial risk for SMTEs. The KIPMRS is a new method for managing intellectual property risk, which incorporates both rule-based reasoning (RBR) and case-based reasoning (CBR). These two features enable the achievement of continuous improvement of the system. Two real life SMTEs participated in the trial implementation of the KIPMRS described here. The SMTEs each used the system to help determine their IP managerial risks and hence to improve their practice for better managing their IP.