Joseph Willrich Lutalo, Tonny J. Oyana, Makerere University, Uganda

Current research shows that offering customer support in any form is a guaranteed means to boost and sustain business growth. Modern support services are steadily embracing automation to improve effec- tiveness, support scalability, and reduce costs, with the most promis- ing approaches leveraging artificial assistants in the form of chatbots and interactive support services. In this paper, we employ the Design Science Research method to explore and then practically implement an original, reusable, re-configurable chatbot platform for designing and delivering autonomous product and customer support services leveraging voice interactions. Further, additional focus was placed on leveraging a scan-to-know information access model, and we especially considered users operating on mobile computers such as smartphones, with active connectivity. The implemented chatbot platform was ex- plored and evaluated from the context of two practical cases; banking and hotel customer support. Important results obtained included; an original architecture of an autonomous, natural-interface, reusable and reconfigurable personal assistant chatbot platform; a working proof- of-concept reference implementation of the VOSAC, currently pub- lished and accessible via the Google Play Store; a simple and effica- cious method of encoding and expressing knowledge in the form of QAKBs, useful in extending/reconfiguring QAKB-compliant personal assistants such as the VOSAC, and finally, the realization of a Scan-to- Know information retrieval method for making access to autonomous support services more scalable and cheaper to implement.

conversational agents, human-computer interaction, question- answering system, chatbots, knowledgebases, digital voice assistants.