A Unified Conversational Assistant Framework for Business Process Automation

Business process automation is a booming multi-billion-dollar industry that promises to remove menial tasks from workers' plates -- through the introduction of autonomous agents -- and free up their time and brain power for more creative and engaging tasks. However, an essential component to the successful deployment of such autonomous agents is the ability of business users to monitor their performance and customize their execution. A simple and user-friendly interface with a low learning curve is necessary to increase the adoption of such agents in banking, insurance, retail and other domains. As a result, proactive chatbots will play a crucial role in the business automation space. Not only can they respond to users' queries and perform actions on their behalf but also initiate communication with the users to inform them of the system's behavior. This will provide business users a natural language interface to interact with, monitor and control autonomous agents. In this work, we present a multi-agent orchestration framework to develop such proactive chatbots by discussing the types of skills that can be composed into agents and how to orchestrate these agents. Two use cases on a travel preapproval business process and a loan application business process are adopted to qualitatively analyze the proposed framework based on four criteria: performance, coding overhead, scalability, and agent overlap.

[1]  Hajo A. Reijers,et al.  Identifying Candidate Tasks for Robotic Process Automation in Textual Process Descriptions , 2018, BPMDS/EMMSAD@CAiSE.

[2]  Kyoung Jun Lee,et al.  Chatbot as a New Business Communication Tool: The Case of Naver TalkTalk , 2018 .

[3]  Miklos A. Vasarhelyi,et al.  Robotic Process Automation for Auditing , 2018, Journal of Emerging Technologies in Accounting.

[4]  Peter Fettke,et al.  Robotic Process Automation in Public Administrations , 2019, FTVI/FTRI.

[5]  Wil M. P. van der Aalst,et al.  Automated Robotic Process Automation: A Self-Learning Approach , 2019, OTM Conferences.

[6]  Diptikalyan Saha,et al.  Tooling Framework for Instantiating Natural Language Querying System , 2018, Proc. VLDB Endow..

[7]  Jin Xiao,et al.  Quark: A Methodology to Transform People-Driven Processes to Chatbot Services , 2017, ICSOC.

[8]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[9]  Aini Aman,et al.  Impacts of Robotic Process Automation on Global Accounting Services , 2018 .

[10]  Diptikalyan Saha,et al.  Functional Partitioning of Ontologies for Natural Language Query Completion in Question Answering Systems , 2018, IJCAI.

[11]  Yasaman Khazaeni,et al.  Online Semi-Supervised Learning with Bandit Feedback , 2019, ArXiv.

[12]  Christoph Matthies,et al.  An Additional Set of (Automated) Eyes: Chatbots for Agile Retrospectives , 2019, 2019 IEEE/ACM 1st International Workshop on Bots in Software Engineering (BotSE).

[13]  Tathagata Chakraborti,et al.  Planning for Goal-Oriented Dialogue Systems , 2019, ArXiv.

[14]  C·巴塔尔勒,et al.  Robotic process automation , 2016 .

[15]  Abdul Quamar,et al.  Natural Language Querying of Complex Business Intelligence Queries , 2019, SIGMOD Conference.

[16]  Leslie P. Willcocks,et al.  Robotic process automation: mature capabilities in the energy sector , 2015 .

[17]  Bendik Bygstad,et al.  LIGHTWEIGHT IT AND THE IT FUNCTION: EXPERIENCES FROM ROBOTIC PROCESS AUTOMATION IN A NORWEGIAN BANK , 2017 .

[18]  Yasaman Khazaeni,et al.  A Bandit Approach to Posterior Dialog Orchestration Under a Budget , 2019, ArXiv.

[19]  Tomasz Stanislawek,et al.  Robotic Process Automation of Unstructured Data with Machine Learning , 2018, FedCSIS.

[20]  Akihiro Kishimoto,et al.  Generating Dialogue Agents via Automated Planning , 2019, ArXiv.

[21]  Andrea Marrella,et al.  What Automated Planning Can Do for Business Process Management , 2017, Business Process Management Workshops.