摘要
Service providers - from public institutions to primary care facilities - need to constantly attend toclients＇ inquiries to provide useful information and directive guidelines. Ensuring high quality serviceis challenging as it not only demands detailed domain-specific knowledge, but also the ability toquickly understand the clients＇ issues through their diverse - and often casual - descriptions. Thispaper aims to provide a framework for the development of an automated information broker agent whoperforms the task of a helper. The main task of the agent is to interact with the client and direct them toobtain further services that cater their personalized need. To do so, the agent should accomplish asequence of tasks that include natural language inquiry, knowledge gathering, reasoning, and givingfeedback; in this way, it simulates a human helper to engage in interaction with the client. Theframework combines a question-answering reasoning mechanism while utilizing domain-specificknowledge base. When the users cannot describe clearly their needs, the system tries to narrow downthe possibilities by an iterative question-answering process, until it eventually identifies the target. Inrealizing our framework, we make a proof-of-concept project, M andy, a primary care chatbot systemcreated to assist healthcare staffs by automating the patient intake process. We describe in detail thesystem functionalities and design of the system, and evaluate our proof-of-concept on benchmark casestudies.
Service providers - from public institutions to primary care facilities - need to constantly attend toclients＇ inquiries to provide useful information and directive guidelines. Ensuring high quality serviceis challenging as it not only demands detailed domain-specific knowledge, but also the ability toquickly understand the clients＇ issues through their diverse - and often casual - descriptions. Thispaper aims to provide a framework for the development of an automated information broker agent whoperforms the task of a helper. The main task of the agent is to interact with the client and direct them toobtain further services that cater their personalized need. To do so, the agent should accomplish asequence of tasks that include natural language inquiry, knowledge gathering, reasoning, and givingfeedback; in this way, it simulates a human helper to engage in interaction with the client. Theframework combines a question-answering reasoning mechanism while utilizing domain-specificknowledge base. When the users cannot describe clearly their needs, the system tries to narrow downthe possibilities by an iterative question-answering process, until it eventually identifies the target. Inrealizing our framework, we make a proof-of-concept project, M andy, a primary care chatbot systemcreated to assist healthcare staffs by automating the patient intake process. We describe in detail thesystem functionalities and design of the system, and evaluate our proof-of-concept on benchmark casestudies.
