Identifying candidate tasks for robotic process automation in textual process descriptions

Henrik Leopold, Han van der Aa, Hajo A. Reijers

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

The continuous digitization requires organizations to improve the automation of their business processes. Among others, this has lead to an increased interest in Robotic Process Automation (RPA). RPA solutions emerge in the form of software that automatically executes repetitive and routine tasks. While the benefits of RPA on cost savings and other relevant performance indicators have been demonstrated in different contexts, one of the key challenges for RPA endeavors is to effectively identify processes and tasks that are suitable for automation. Textual process descriptions, such as work instructions, provide rich and important insights about this matter. However, organizations often maintain hundreds or even thousands of them, which makes a manual analysis unfeasible for larger organizations. Recognizing the large manual effort required to determine the current degree of automation in an organization’s business processes, we use this paper to propose an approach that is able to automatically do so. More specifically, we leverage supervised machine learning to automatically identify whether a task described in a textual process description is manual, an interaction of a human with an information system or automated. An evaluation with a set of 424 activities from a total of 47 textual process descriptions demonstrates that our approach produces satisfactory results.

Original languageEnglish
Title of host publicationEnterprise, Business-Process and Information Systems Modeling - 19th International Conference, BPMDS 2018, 23rd International Conference, EMMSAD 2018, Held at CAiSE 2018, Proceedings
PublisherSpringer/Verlag
Pages67-81
Number of pages15
ISBN (Print)9783319917030
DOIs
Publication statusPublished - 2018
Event19th International Conference on Business Process Modeling, Development and Support, BPMDS 2018 and 23rd International Conference on Evaluation and Modeling Methods for Systems Analysis and Development, EMMSAD 2018 Held at 30th International Conference on Advanced Information Systems Engineering, CAiSE 2018 - Tallinn, Estonia
Duration: 11 Jun 201812 Jun 2018

Publication series

NameLecture Notes in Business Information Processing
Volume318
ISSN (Print)1865-1348

Conference

Conference19th International Conference on Business Process Modeling, Development and Support, BPMDS 2018 and 23rd International Conference on Evaluation and Modeling Methods for Systems Analysis and Development, EMMSAD 2018 Held at 30th International Conference on Advanced Information Systems Engineering, CAiSE 2018
CountryEstonia
CityTallinn
Period11/06/1812/06/18

Fingerprint

Automation
Robotics
Business Process
Analog to digital conversion
Digitization
Performance Indicators
Supervised Learning
Learning systems
Industry
Leverage
Information systems
Information Systems
Machine Learning
Software
Evaluation
Costs
Interaction
Demonstrate

Cite this

Leopold, H., van der Aa, H., & Reijers, H. A. (2018). Identifying candidate tasks for robotic process automation in textual process descriptions. In Enterprise, Business-Process and Information Systems Modeling - 19th International Conference, BPMDS 2018, 23rd International Conference, EMMSAD 2018, Held at CAiSE 2018, Proceedings (pp. 67-81). (Lecture Notes in Business Information Processing; Vol. 318). Springer/Verlag. https://doi.org/10.1007/978-3-319-91704-7_5
Leopold, Henrik ; van der Aa, Han ; Reijers, Hajo A. / Identifying candidate tasks for robotic process automation in textual process descriptions. Enterprise, Business-Process and Information Systems Modeling - 19th International Conference, BPMDS 2018, 23rd International Conference, EMMSAD 2018, Held at CAiSE 2018, Proceedings. Springer/Verlag, 2018. pp. 67-81 (Lecture Notes in Business Information Processing).
@inproceedings{b871f51df83e4b94b2c0678d65a0847c,
title = "Identifying candidate tasks for robotic process automation in textual process descriptions",
abstract = "The continuous digitization requires organizations to improve the automation of their business processes. Among others, this has lead to an increased interest in Robotic Process Automation (RPA). RPA solutions emerge in the form of software that automatically executes repetitive and routine tasks. While the benefits of RPA on cost savings and other relevant performance indicators have been demonstrated in different contexts, one of the key challenges for RPA endeavors is to effectively identify processes and tasks that are suitable for automation. Textual process descriptions, such as work instructions, provide rich and important insights about this matter. However, organizations often maintain hundreds or even thousands of them, which makes a manual analysis unfeasible for larger organizations. Recognizing the large manual effort required to determine the current degree of automation in an organization’s business processes, we use this paper to propose an approach that is able to automatically do so. More specifically, we leverage supervised machine learning to automatically identify whether a task described in a textual process description is manual, an interaction of a human with an information system or automated. An evaluation with a set of 424 activities from a total of 47 textual process descriptions demonstrates that our approach produces satisfactory results.",
author = "Henrik Leopold and {van der Aa}, Han and Reijers, {Hajo A.}",
year = "2018",
doi = "10.1007/978-3-319-91704-7_5",
language = "English",
isbn = "9783319917030",
series = "Lecture Notes in Business Information Processing",
publisher = "Springer/Verlag",
pages = "67--81",
booktitle = "Enterprise, Business-Process and Information Systems Modeling - 19th International Conference, BPMDS 2018, 23rd International Conference, EMMSAD 2018, Held at CAiSE 2018, Proceedings",

}

Leopold, H, van der Aa, H & Reijers, HA 2018, Identifying candidate tasks for robotic process automation in textual process descriptions. in Enterprise, Business-Process and Information Systems Modeling - 19th International Conference, BPMDS 2018, 23rd International Conference, EMMSAD 2018, Held at CAiSE 2018, Proceedings. Lecture Notes in Business Information Processing, vol. 318, Springer/Verlag, pp. 67-81, 19th International Conference on Business Process Modeling, Development and Support, BPMDS 2018 and 23rd International Conference on Evaluation and Modeling Methods for Systems Analysis and Development, EMMSAD 2018 Held at 30th International Conference on Advanced Information Systems Engineering, CAiSE 2018, Tallinn, Estonia, 11/06/18. https://doi.org/10.1007/978-3-319-91704-7_5

Identifying candidate tasks for robotic process automation in textual process descriptions. / Leopold, Henrik; van der Aa, Han; Reijers, Hajo A.

Enterprise, Business-Process and Information Systems Modeling - 19th International Conference, BPMDS 2018, 23rd International Conference, EMMSAD 2018, Held at CAiSE 2018, Proceedings. Springer/Verlag, 2018. p. 67-81 (Lecture Notes in Business Information Processing; Vol. 318).

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Identifying candidate tasks for robotic process automation in textual process descriptions

AU - Leopold, Henrik

AU - van der Aa, Han

AU - Reijers, Hajo A.

PY - 2018

Y1 - 2018

N2 - The continuous digitization requires organizations to improve the automation of their business processes. Among others, this has lead to an increased interest in Robotic Process Automation (RPA). RPA solutions emerge in the form of software that automatically executes repetitive and routine tasks. While the benefits of RPA on cost savings and other relevant performance indicators have been demonstrated in different contexts, one of the key challenges for RPA endeavors is to effectively identify processes and tasks that are suitable for automation. Textual process descriptions, such as work instructions, provide rich and important insights about this matter. However, organizations often maintain hundreds or even thousands of them, which makes a manual analysis unfeasible for larger organizations. Recognizing the large manual effort required to determine the current degree of automation in an organization’s business processes, we use this paper to propose an approach that is able to automatically do so. More specifically, we leverage supervised machine learning to automatically identify whether a task described in a textual process description is manual, an interaction of a human with an information system or automated. An evaluation with a set of 424 activities from a total of 47 textual process descriptions demonstrates that our approach produces satisfactory results.

AB - The continuous digitization requires organizations to improve the automation of their business processes. Among others, this has lead to an increased interest in Robotic Process Automation (RPA). RPA solutions emerge in the form of software that automatically executes repetitive and routine tasks. While the benefits of RPA on cost savings and other relevant performance indicators have been demonstrated in different contexts, one of the key challenges for RPA endeavors is to effectively identify processes and tasks that are suitable for automation. Textual process descriptions, such as work instructions, provide rich and important insights about this matter. However, organizations often maintain hundreds or even thousands of them, which makes a manual analysis unfeasible for larger organizations. Recognizing the large manual effort required to determine the current degree of automation in an organization’s business processes, we use this paper to propose an approach that is able to automatically do so. More specifically, we leverage supervised machine learning to automatically identify whether a task described in a textual process description is manual, an interaction of a human with an information system or automated. An evaluation with a set of 424 activities from a total of 47 textual process descriptions demonstrates that our approach produces satisfactory results.

UR - http://www.scopus.com/inward/record.url?scp=85048552868&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048552868&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-91704-7_5

DO - 10.1007/978-3-319-91704-7_5

M3 - Conference contribution

SN - 9783319917030

T3 - Lecture Notes in Business Information Processing

SP - 67

EP - 81

BT - Enterprise, Business-Process and Information Systems Modeling - 19th International Conference, BPMDS 2018, 23rd International Conference, EMMSAD 2018, Held at CAiSE 2018, Proceedings

PB - Springer/Verlag

ER -

Leopold H, van der Aa H, Reijers HA. Identifying candidate tasks for robotic process automation in textual process descriptions. In Enterprise, Business-Process and Information Systems Modeling - 19th International Conference, BPMDS 2018, 23rd International Conference, EMMSAD 2018, Held at CAiSE 2018, Proceedings. Springer/Verlag. 2018. p. 67-81. (Lecture Notes in Business Information Processing). https://doi.org/10.1007/978-3-319-91704-7_5