PRISENIT - a probabilistic search recommendation algorithm to improe search efficiency for network intelligence and troubleshooting

Abstract

When searching for data in a telecommunications network management application, large search result sets are common. In order to refine the results to retrieve useful information existing systems normally require additional user intervention such as appending or removing a search keyword, adding a filter, grouping results, etc. This work proposes a Probabilistic Search Recommendation Algorithm to Improve Search Efficiency for Network Intelligence and Troubleshooting (PRISENIT). PRISENIT is a query-based recommendation algorithm intended to improve search efficiency and usability for telecommunication system management. PRISENIT is an extension of an item-based collaborative filtering algorithm. It uses correlation-based similarity and users' implicit feedback in order to improve search efficiency. It learns from previous experiences in order to optimize decision-making. Currently there exists no known query-based recommender adaptation mechanism for network management. Existing search engines use previous user searches to make a suggestion based on the keyword. PRISENIT not only considers search terms, it also considers the influence of filters and features in order to makes network searches more efficient as it removes the necessity for users to manually choose search features or search filters. Experimental results show that PRISENIT can improve user experience in a telecommunications management environment.