Design of knowledge for conversational recommender system based on product functional requirements

Conversational recommender system (CRS) has been developed to simulate conversation between a customer with a professional sales support. For most customers, specifying needs based on product functional requirements is more natural way rather than technical features, especially for high-tech products. Thus, the CRS requires a knowledge design that is able to generate interactions based on product functional requirements appropriately. This paper proposes a design of knowledge by using ontology to overcome this issue. The nature of ontology structure allows us to map functional requirements with technical features of the product. Based on our user study, most of expert users (familiar with product technical features) and novice users (not familiar with product technical features) perceive that the CRS based on our proposed knowledge design is more useful than that of the recommender system based on the technical features.