AI Chatbot Providing Real-Time Public Transportation and Route Information

Abstract

As the artificial intelligence technology has developed recently, researches on chatbots that provide information and contents desired by users through an interactive interface have become active. Since chatbots require a variety of natural language processing technology and domain knowledge including typos and slang, it is currently limited to develop chatbots that can carry on daily conversations in a general-purpose domain. In this study, we propose an artificial intelligence chatbot that can provide real-time public traffic information and route information. The proposed chatbot has an advantage that it can understand the intention and requirements of the user through the conversation on the messenger platform without map application.

Fig. 1. System Configuration Of Chatbot

Fig. 2. Validity Check

Fig. 3. Validity Check Example

Fig. 4. Results From DialogflowWhen Validation Result Is TRUE

Fig. 5. Results From Dialogflow WhenValidation Result Is FALSE

Fig. 6. Some of Results From ODSay API whenSearching Route

Fig. 7. Intent Name And Entity Identified By Dialogflow

Fig. 8. URL To The Real-time Subway Location API Of Seoul Metro

Fig. 9. Real-time Subway ArrivalInformation Simple Message Result

Fig. 10. Real-time Subway Arrival Information Detail Message Result(Web Page)

Fig. 11. The result of the accuracy test of the chatbot obtained by Dialogflow

Table 1. Intents Learned In Dialogflow

Table 2. Entities Learned In Dialogflow

Table 3. Intent And Required And Basic Entity

Table 4. URL For Each Function In ODSay API

Table 5. Route Search Sentences Learned In Dialogflow

Table 6. Sentences Getting Real-time Bus Number Location Information

Table 7. Sentences Getting Real-time Bus Station Location Information