One-Match and All-Match Categories for Keywords Matching in Chatbot

Abstract

Problem statement: Artificial intelligence chatbot is a technology that makes interactions between men and machines using natural language possible. From literature of chatbot’s keywords/pattern matching techniques, potential issues for improvement had been discovered. The discovered issues are in the context of keywords arrangement for matching precedence and keywords variety for matching flexibility. Approach: Combining previous techniques/mechanisms with some additional adjustment, new technique to be used for keywords matching process is proposed. Using newly developed chatbot named ViDi (abbreviation for Virtual Diabetes physician which is a chatbot for diabetes education activity) as a testing medium, the proposed technique named One-Match and All-Match Categories (OMAMC) is being used to test the creation of possible keywords surrounding one sample input sentence. The result for possible keywords created by this technique then being compared to possible keywords created by previous chatbot’s techniques surrounding the same sample sentence in matching precedence and matching flexibility context. Results: OMAMC technique is found to be improving previous matching techniques in matching precedence and flexibility context. This improvement is seen to be useful for shortening matching time and widening matching flexibility within the chatbot’s keywords matching process. Conclusion: OMAMC for keywords matching in chatbot is shown to be an improvement over previous techniques in the context of keywords arrangement for matching precedence and keywords variety for matching flexibility.