ISD-An Intelligent Service Desk

A knowledge base is where an organization documents communal knowledge that the teams are acquiring through hard experience. Customers are the main reason an organization need to use a knowledge base. The turn-around time of the query resolution and correctness is of utmost importance. It is also important to be able to retain the knowledge the employees acquire, rather than letting it walk out the door with them when they eventually move on to another job. The information in a knowledge base can be used to solve the issues which were earlier solved with customer representative help. Many companies use text based or case-based service desk systems to improve customer service quality. But most of the existing knowledge base systems use matching based on the keywords in the cases and rank the cases based on those keyword matches. This method of case retrieval in inefficient and has difficulty in understanding the exact meanings of the cases. The results based on keyword-based retrieval, are inaccurate and incomplete in cases where different keywords are used for the description of similar concepts in artifacts and queries. To address this challenge, ISD, an Intelligent Service Desk, is proposed, to find problem–solution patterns from the past customer–representative interactions automatically. The main aim of the paper is to bring in semantic analysis of the cases in case retrieval. When a new query from the customer arrives, ISD searches the previous cases in the knowledge base and ranks it based on the semantic relevance of the incoming request and the knowledge base cases. A new way is formulated to understand the semantic meanings of the cases. This method can be used to trance the exact meanings of the cases. The proposed system uses tokenization to remove the stop words, part of speech tagging, word sense disambiguation and finally a path length based similarity measurement to capture the semantic similarity between the sentences. ISD calculates a score for the sentence searched for and the reference solutions in the knowledge base using the proposed method and displays the results in the decreasing order of the score. The experimental result and case studies presented in the paper show that the proposed method has high precision of retrieval when compared to case based systems.