Home
Chatbot system attracts huge interest in recent years in many different fields in an attempt to increase the efficiency and shortens the business process execution time replacing the human-human communication with human-machine conversations and queries in natural languages. Chatbots today have varying levels of capabilities as general-purpose conversational agents or task-oriented chatbots as well as open-domain and domain-specific agent systems. While basic chatbots may be adequate for most scenarios, some scenarios require more advanced chatbots. The paper presents a distributed chatbot system for the supply chain. The system comprises several services: chat service, bot service, natural language processing service as well as supply chain service. It uses web socket communication between the user interface and the bot, analyzes the user's query and provides information about the queried orders and supplies.
The system architecture of the distributed chatbot for the supply chain suggested in the paper is shown in Fig. The system consists of five microservices:
- Chat Service: responsible for web socket communication between the user interface and bot.
- Bot Service: analyzes the user's message, constructs a request to retrieve the necessary information, and provides the user in a comprehensible manner.
- NLU Service: analyzes the user's message, extracts information about the intent of the user and the objects that enrich the information about the intent.
- Supply Chain Service: contains information about orders and supplies to users.