Business Process Management Workshops

Inhaltsverzeichnis

1. Frontmatter

2. 1st International Workshop on Business Process Innovation with Artificial Intelligence (BPAI 2017)

   1. Frontmatter

   2. What Automated Planning Can Do for Business Process Management

      Andrea Marrella

      Abstract

      Business Process Management (BPM) is a central element of today organizations. Despite over the years its main focus has been the support of processes in highly controlled domains, nowadays many domains of interest to the BPM community are characterized by ever-changing requirements, unpredictable environments and increasing amounts of data that influence the execution of process instances. Under such dynamic conditions, BPM systems must increase their level of automation to provide the reactivity and flexibility necessary for process management. On the other hand, the Artificial Intelligence (AI) community has concentrated its efforts on investigating dynamic domains that involve active control of computational entities and physical devices (e.g., robots, software agents, etc.). In this context, Automated Planning, which is one of the oldest areas in AI, is conceived as a model-based approach to synthesize autonomous behaviours in automated way from a model. In this paper, we discuss how automated planning techniques can be leveraged to enable new levels of automation and support for business processing, and we show some concrete examples of their successful application to the different stages of the BPM life cycle.

   3. Structural Feature Selection for Event Logs

      Markku Hinkka, Teemu Lehto, Keijo Heljanko, Alexander Jung

      Abstract

      We consider the problem of classifying business process instances based on structural features derived from event logs. The main motivation is to provide machine learning based techniques with quick response times for interactive computer assisted root cause analysis. In particular, we create structural features from process mining such as activity and transition occurrence counts, and ordering of activities to be evaluated as potential features for classification. We show that adding such structural features increases the amount of information thus potentially increasing classification accuracy. However, there is an inherent trade-off as using too many features leads to too long run-times for machine learning classification models. One way to improve the machine learning algorithms’ run-time is to only select a small number of features by a feature selection algorithm. However, the run-time required by the feature selection algorithm must also be taken into account. Also, the classification accuracy should not suffer too much from the feature selection. The main contributions of this paper are as follows: First, we propose and compare six different feature selection algorithms by means of an experimental setup comparing their classification accuracy and achievable response times. Second, we discuss the potential use of feature selection results for computer assisted root cause analysis as well as the properties of different types of structural features in the context of feature selection.

   4. Towards Intelligent Process Support for Customer Service Desks: Extracting Problem Descriptions from Noisy and Multi-lingual Texts

      Jana Koehler, Etienne Fux, Florian A. Herzog, Dario Lötscher, Kai Waelti, Roland Imoberdorf, Dirk Budke

      Abstract

      Customer service is a differentiating capability for companies, but it faces significant challenges due to the growing individualization and connectivity of products, the increasing complexity of knowledge that service employees need to deal with, and steady cost pressure. Artificial intelligence (AI) can support service processes in a variety of ways, however, many projects simply propose replacing employees with chat bots. In contrast to pure automation focusing on customer self-service, we introduce three intelligent assistants that support service employees in their complex tasks: the scribe, the skill manager, and the background knowledge worker.

      In this paper, we discuss the technology and architecture underlying the skill manager in more detail. We present the results from an evaluation of commercial cognitive services from IBM and Microsoft on comprehensive real-world data that comprises over 80,000 tickets from a major IT service provider, where problem reports often comprise an email-based conversation in multiple languages. We demonstrate how today’s commercially available cognitive services struggle to correctly analyze this data unless they use background ontological knowledge. We further discuss a pattern- and machine-learning based approach that we developed to extract problem descriptions from multi-lingual ticket texts, which is key to the successful application of AI-based services.

   5. Towards an Entropy-Based Analysis of Log Variability

      Christoffer Olling Back, Søren Debois, Tijs Slaats

      Abstract

      Process mining algorithms can be partitioned by the type of model that they output: imperative miners output flow-diagrams showing all possible paths through a process, whereas declarative miners output constraints showing the rules governing a process. For processes with great variability, the latter approach tends to provide better results, because using an imperative miner would lead to so-called “spaghetti models” which attempt to show all possible paths and are impossible to read. However, studies have shown that one size does not fit all: many processes contain both structured and unstructured parts and therefore do not fit strictly in one category or the other. This has led to the recent introduction of hybrid miners, which aim to combine flow- and constraint-based models to provide the best possible representation of a log. In this paper we focus on a core question underlying the development of hybrid miners: given a log, can we determine a priori whether the log is best suited for imperative or declarative mining? We propose using the concept of entropy, commonly used in information theory. We consider different measures for entropy that could be applied and show through experimentation on both synthetic and real-life logs that these entropy measures do indeed give insights into the complexity of the log and can act as an indicator of which mining paradigm should be used.

   6. Objective Coordination with Business Artifacts and Social Engagements

      Matteo Baldoni, Cristina Baroglio, Federico Capuzzimati, Roberto Micalizio

      Abstract

      This work studies business artifacts by tackling a limit that we see in the current model, which is: business artifacts are not devised as natural means of coordination in their own right, despite the fact that they have the potential of being natural means of coordination in their own right. Coordination issues are transfered (e.g. by BALSA) to solutions that are already available in the literature on choreography and choreography languages. Instead, we propose to enrich business artifacts with a normative layer that accounts for the social engagements of the parties which interact by using a same business artifact. We explain the advantages, also from a software engineering perspective, and propose an approach that relies on the notion of social commitment.

   7. Enhancing Workflow-Nets with Data for Trace Completion

      Riccardo De Masellis, Chiara Di Francescomarino, Chiara Ghidini, Sergio Tessaris

      Abstract

      The growing adoption of IT-systems for modeling and executing (business) processes or services has thrust the scientific investigation towards techniques and tools which support more complex forms of process analysis. Many of them, such as conformance checking, process alignment, mining and enhancement, rely on complete observation of past (tracked and logged) executions. In many real cases, however, the lack of human or IT-support on all the steps of process execution, as well as information hiding and abstraction of model and data, result in incomplete log information of both data and activities. This paper tackles the issue of automatically repairing traces with missing information by notably considering not only activities but also data manipulated by them. Our technique recasts such a problem in a reachability problem and provides an encoding in an action language which allows to virtually use any state-of-the-art planning to return solutions.

   8. Optimal Paths in Business Processes: Framework and Applications

      Marco Comuzzi

      Abstract

      We present an innovative framework for calculating optimal execution paths in business processes using the abstraction of workflow hypergraphs. We assume that information about the utility associated with the execution of activities in a process is available. Using the workflow hypergraph abstraction, finding a utility maximising path in a process becomes a generalised shortest hyperpath problem, which is NP-hard. We propose a solution that uses ant-colony optimisation customised to the case of hypergraph traversal. We discuss three possible applications of the proposed framework: process navigation, process simulation, and process analysis. We also present a brief performance evaluation of our solution and an example application.

   9. An Agent-Based Model of a Business Process: The Use Case of a Hospital Emergency Department

      Emilio Sulis, Antonio Di Leva

      Abstract

      An application of Artificial Intelligence is computational simulation which reproduces the behavior of a system, such as an organization. Simulations provide benefits into business process management, also by combining scenarios and what-if analysis. This study explores the adoption of agent-based modeling technique, in addition to traditional discrete event simulations. The focus is on a real case study of an hospital emergency department. Following the construction of a new hospital, managers are interested in simulating the actual flows in the new configuration before the moving. In our model, patients and operators are agents, acting due to simple behavioral rules in the environment. The different activities are placed on the map of the department, to provide immediate understanding of bottlenecks and queues. While first results were validated from managers, next steps include the comparison of resulting flows between the new and the old department. Logistics analysis includes the time for moving agents between different wards.

   10. Constraint-Based Composition of Business Process Models

       Piotr Wiśniewski, Krzysztof Kluza, Mateusz Ślażyński, Antoni Ligęza

       Abstract

       Process models help organizations to visualize and optimize their activities, and achieve their business goals in a more efficient way. Modeling a business process requires exact information about possible execution sequences of the activities as well as process modeling notation knowledge. We present a method of business process composition based on the constraint programming technique. Taking task specifications as the input, our solution can generate a workflow log which can be used to discover the model using any process mining technique.

   11. Semantically-Oriented Business Process Visualization for a Data and Constraint-Based Workflow Approach

       Eric Rietzke, Ralph Bergmann, Norbert Kuhn

       Abstract

       This paper introduces a novel approach which unifies a data-centric and a constraint-based workflow principle to support the requirements of knowledge intensive business processes. By the integration of a knowledge-based system, process definition and execution relevant data coincide on an ontology-based semantic net. The data, mainly driving the process, can be delivered by different sources or can be the result of an inference step by the underlying ontology. In such a case, AI technology plays an active role during the process execution and result in a division of labor with human actors. This paper presents a concept for a semantically-oriented process visualization for the introduced unified approach.

   12. Abduction for Generating Synthetic Traces

       Federico Chesani, Anna Ciampolini, Daniela Loreti, Paola Mello

       Abstract

       In this paper we report our preliminary experience on the design of a generator of synthetic logs. Sometimes real logs might not be available, or their quality might not be good enough: synthetic logs instead can be generated with all the desired features and characteristics. Our tool takes as input a structured workflow model, encoded in the abductive declarative language SCIFF, and provides as output a log containing positive traces, i.e. traces deemed as conformant w.r.t. the model. Distinctive features of our approach are the capability of generating trace templates as well as grounded traces, the possibility of taking into account user-specified constraints on data and timestamps, and the capability of generating traces starting from a user-specified partial trace. Although our tool is still in its preliminary version, we have successfully exploited it to generate synthetic logs of different dimension, thus proving the viability of our approach.