When many users consult service desks simultaneously, these typically saturate. This causes the customer attention is delayed more than usual. The service is perceived as lousy from the point of view of the customer. Increase the amount of human agents is a costly process for organizations. In addition, the amount of sta turnover in this type of service is very high, which means make frequent training. All this has motivated the design of a knowledge-based system that automatically assists both customers and human agents at the service desk. Web technology was used to enable clients to communicate with a software agent via chat. Techniques of Natural Language Processing were used in order the software agent understands the customer requests. The domain knowledge used by the software agent to understand customer requests has been codi ed in an ontology. A rule-based expert system was designed to perform the diagnostic task. This paper presents a knowledge-based system allowing client to communicate with the service desk through a chat system using free text. A software agent automatically executes the customer request. The agent software attempts to reach a conclusion using expert system and ontology. If achieved success, returns the response to the customer, otherwise the request is redirected to a human agent. Evaluations conducted with users have shown an improvement in the attention of service desks when the software developed is used. On the other hand, since the most frequent requests are handled automatically, the workload of human agents decreases considerably. The software has also been used to train new human agents which facilitates and reduces the cost of training. / Tesis

When many users consult service desks simultaneously, these typically saturate. This causes the customer attention is delayed more than usual. The service is perceived as lousy from the point of view of the customer. Increase the amount of human agents is a costly process for organizations. In addition, the amount of sta turnover in this type of service is very high, which means make frequent training. All this has motivated the design of a knowledge-based system that automatically assists both customers and human agents at the service desk. Web technology was used to enable clients to communicate with a software agent via chat. Techniques of Natural Language Processing were used in order the software agent understands the customer requests. The domain knowledge used by the software agent to understand customer requests has been codi ed in an ontology. A rule-based expert system was designed to perform the diagnostic task. This paper presents a knowledge-based system allowing client to communicate with the service desk through a chat system using free text. A software agent automatically executes the customer request. The agent software attempts to reach a conclusion using expert system and ontology. If achieved success, returns the response to the customer, otherwise the request is redirected to a human agent. Evaluations conducted with users have shown an improvement in the attention of service desks when the software developed is used. On the other hand, since the most frequent requests are handled automatically, the workload of human agents decreases considerably. The software has also been used to train new human agents which facilitates and reduces the cost of training. / Tesis