Service selection model based on user intention and context

Abstract

The internet interconnects billions of objects and services. Real-world services are offered by entities with various functions communicating with one another. The selection of services based on their functionality is a complex process because as the number of services rises, so does the number of services that offer the same functionality. Quality of service (QoS) can be a criterion for selecting a suitable service. However, QoS' relative significance fluctuates due to changing user preferences, and users may exhibit various behaviors depending on their contexts and intentions. Defining a user's preference based on user intentions and context is similarly challenging; nonetheless, scholars have paid little attention to this topic. This study provides a new model for service selection based on user intentions and context. The model dynamically selects the appropriate set of QoS with their importance to specify a user preference for various behaviors. The issue of assessing user preference to select the desired service is resolved by calculating the QoS importance based on the user's behavior history and context. The study proposed a dynamic K-Skyline method to optimize a search space and a multi-criteria decision-making technique to select and rank services efficiently. A case study and an experiment demonstrating the proposed model are presented, in which real-world datasets are utilized. The experimental results of the proposed model validate the model's efficiency and robustness.

Keywords

• Service selection
• User preference
• Internet of Things
• User intention and context
• Entropy
• Skyline services