دانلود مقاله ISI انگلیسی شماره 21010
عنوان فارسی مقاله

سیستم هوشمند تشخیص عیب مبتنی بر وب برای پشتیبانی از خدمات مشتری

کد مقاله سال انتشار مقاله انگلیسی ترجمه فارسی تعداد کلمات
21010 2001 12 صفحه PDF سفارش دهید محاسبه نشده
خرید مقاله
پس از پرداخت، فوراً می توانید مقاله را دانلود فرمایید.
عنوان انگلیسی
A web-based intelligent fault diagnosis system for customer service support
منبع

Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)

Journal : Engineering Applications of Artificial Intelligence, Volume 14, Issue 4, August 2001, Pages 537–548

کلمات کلیدی
میز کمک مبتنی بر وب - تشخیص عیب هوشمند - رویکرد ترکیبی - استدلال مبتنی بر مورد - شبکه های عصبی مصنوعی
پیش نمایش مقاله
پیش نمایش مقاله سیستم هوشمند تشخیص عیب مبتنی بر وب برای پشتیبانی از خدمات مشتری

چکیده انگلیسی

In traditional help desk service centres, service engineers provide a world-wide customer support service through the use of long-distance telephone calls. Such a mode of support is found to be inefficient, ineffective and generally results in high costs, long service cycles, and poor quality of service. With the advent of the Internet technology, it is possible to deliver customer service support over the World Wide Web. This paper describes a Web-based intelligent fault diagnosis system, known as WebService, to support customer service over the Web. In the WebService system, a hybrid case-based reasoning (CBR) and artificial neural network (ANN) approach is adopted as the intelligent technique for machine fault diagnosis. Instead of using traditional CBR technique for indexing, retrieval and adaptation, the hybrid CBR–ANN approach integrates ANN with the CBR cycle to extract knowledge from service records of the customer service database and subsequently recall the appropriate service records using this knowledge during the retrieval phase.

مقدمه انگلیسی

A multinational corporation in Singapore manufactures and supplies insertion and surface mount machines widely used in the electronics industry. Its customer support department services its world-wide customers and provides installation, inspection and maintenance support for its customers. Insertion and surface mount machines are expensive and require efficient maintenance during machine down time. Although most customers have some engineers to handle day-to-day maintenance and small-scale troubleshooting, expert advice is often required for more complex maintenance and repair jobs. Prompt response to request from customers is needed to maintain customer satisfaction. Therefore, the multinational corporation has set up a hotline service centre (or help desk) to answer frequently encountered problems. The hotline service centre is responsible for receiving reports on faulty machines or inquiries from their customers via telephone calls. When a problem is reported, a service engineer will suggest a series of checkpoints to the customers to implement or check as a means to rectify the reported problem. Such suggestions are based on past experience or extracted through a customer service database that contains previous service records that are identical or similar to the current one. With these checkpoints, the customer attempts problem solving and subsequently confirms with the service centre if the problem is resolved. If the problem still persists after all the suggested checkpoints are exhausted, the centre will dispatch the service engineers to the customer's premise for an on-site repair. During such trips, the service engineers will carry along with them past records of the customer's machine, related manuals and spare parts that may be required to carry out the repair. Such a process is inconvenient and often involves bringing redundant materials. At the end of each service cycle, a customer service report is used to record the reported problem and proposed remedies or suggestions taken to rectify the problem. This is for billing purposes, as well as maintaining a corporate knowledge base. The service centre then updates the customer service report in the customer service database. This traditional customer support process suffers from a number of disadvantages: • The process is time-consuming and expensive. More often than not, service engineers are required to travel to a customer's site for an on-site service even for a small problem. As a result, the problem cannot be resolved efficiently and the machine down time can be significant. In addition, as the customers communicate with the help desk centre via telephone calls, they incur long distance telephone charges as most of them are located overseas. • A certain number of service engineers are maintained in order to provide the service support. It needs to keep on training new service engineers, and at the same time, come up with new incentive scheme to retain experienced service engineers. • Expert advice to the problem is given either through the experience of the service engineers or the available past service information in the service database. No automatic provision of expert advice is available. As can be seen from this mode of operation, the identification of machine faults relies heavily on the service support engineers’ past experience or the information drawn from the service database. This method has a problem of training and maintaining a pool of expert service engineers. Thus, instead of relying on the knowledge of service engineers, an intelligent fault diagnosis system that captures the expert knowledge of machine diagnosis to assist customers identify machine faults becomes extremely useful. This system should be able to generate suggested remedial actions automatically or through user-interaction based on the observed fault-conditions. In addition, the advancement of the Internet technology has made it possible to deliver customer service support over the World Wide Web (or Web). Therefore, as a collaborative project between the multinational corporation and the School of Applied Science, Nanyang Technological University, Singapore, a Web-based intelligent fault diagnosis system, known as WebService, has been developed in order to enhance the customer service support over the Web. In this research, a hybrid case-based reasoning (CBR) and artificial neural network (ANN) approach (Lees and Corchado, 1997; Papagni et al., 1997) is adopted as the intelligent technique for fault-diagnosis. The hybrid CBR-ANN approach is operated as follows. Instead of using traditional CBR technique for indexing, retrieval and adaptation, ANN is incorporated into the CBR cycle to extract knowledge from service reports of the customer service database and subsequently recall the appropriate service reports using this knowledge during the retrieval phase. The rest of the paper is organised as follows. Section 2 discusses the on-line customer service support. Section 3 reviews the intelligent techniques for fault diagnosis. The system architecture of WebService is given in Section 4. Section 5 describes the structure of the customer service database. Section 6 outlines the proposed hybrid CBR–ANN technique for intelligent fault diagnosis. Section 7 gives the performance evaluation of the hybrid approach. Finally, conclusion is given in Section 8.

نتیجه گیری انگلیسی

Traditional help desk service centres are inefficient and ineffective in providing customer service support. This research has proposed a Web-based intelligent fault diagnosis system to support customer service over the Web. It is an on-going research between NTU and a multinational company. The system has been deployed and is used by the company for their fault diagnosis. Users can access WebService through any Web browsers such as Netscape Navigator or Microsoft's Internet Explorer. The main component of the WebService system is the fault diagnosis engine, which has adopted a hybrid case-based reasoning and artificial neural network approach for intelligent fault diagnosis. In the hybrid CBR–ANN approach, ANN is incorporated into the CBR cycle for indexing, retrieval and adaptation instead of using traditional nearest-neighbour technique. Performance evaluation has been carried out which has shown that the hybrid CBR–ANN approach outperforms the traditional kNN technique in both accuracy and efficiency.

خرید مقاله
پس از پرداخت، فوراً می توانید مقاله را دانلود فرمایید.