=Paper=
{{Paper
|id=Vol-2567/paper6
|storemode=property
|title=Ontology-based transfer learning in the airport and warehouse logistics domains
|pdfUrl=https://ceur-ws.org/Vol-2567/paper6.pdf
|volume=Vol-2567
|authors=Miriam Herold,Mirjam Minor
|dblpUrl=https://dblp.org/rec/conf/iccbr/HeroldM19
}}
==Ontology-based transfer learning in the airport and warehouse logistics domains==
https://ceur-ws.org/Vol-2567/paper6.pdf
Ontology-based transfer learning in the airport
and warehouse logistics domains
Miriam Herold and Mirjam Minor
Goethe University, Frankfurt am Main 60325, Germany
http://www.wi.cs.uni-frankfurt.de
{herold,minor}@cs.uni-frankfurt.de
Abstract. This work is a position paper for the examination of ontology-
based transfer learning in the context of business processes. We continue
our preliminary work on transfering process-oriented knowledge from a
well-known source domain to a less specified target domain. We outline
our ideas on workflows from two specific contexts: passenger and baggage
logistics at the airport on one hand and warehouse management logistics
on the other hand. In the first step we automatically transform BPMN
files from these two domains in two separate ontologies. In the next step
we intend to use ontology mapping as a means for the transfer. We plan
to examine the concepts of generalization and abstraction to ease the
transfer. We claim that the mentioned domains are feasible candidates
for transfer learning, as we find several analogies between the airport
handling and warehouse management workflows. Additionally we dis-
cuss possible utilization resp. benefits of the transfer learning within this
two particular domains and draft the next steps for the future research.
Keywords: transfer learning · process-oriented case-based reasoning ·
ontology
1 Introduction
Transfer learning - as a method for using the knowledge from one well-known
domain and adapting and re-using it in another one [4] - is currently a very
relevant topic in di↵erent research contexts, mainly in data mining [13] or ma-
chine learning [19], [7]. Neural networks can benefit from transfer learning, as
pretrained networks can be adapted to another related tasks and reduce signifi-
cantly the training costs [12].
Aside from the scientific world there are manyfold practice-oriented areas,
where transfer learning can o↵er a considerable support. One of them is the
management of business processes. Many enterprises face the challenge of digi-
tal transformation. Digitization not only a↵ects production, but also processes,
management concepts and the whole organization structure [8]. The changes
require a reasonable level of automation as well as flexibility in modeling and
adaptation of workflows. Modeling business processes from scratch usually binds
Copyright © 2019 for this paper by its authors. Use permitted under Creative Commons License Attribution
4.0 International (CC BY 4.0).
resources and can cause substantial costs. Sometimes enterprises simply su↵er
from lack of expertise and workflows can not be modelled in an appropriate
quality. At this point case-based reasoning (CBR) methods might support the
e↵ort of an enterprise. CBR is based on the intuition that similar problems tend
to have similar solutions [16]. Already modelled business processes represent ex-
periential knowledge and, after an adaption, they can be re-used in modeling
of new workflow models. In the context of process-oriented case-based reasoning
(POCBR), particular process model can be seen as a solution for the problem
of reaching a certain outcome, completing a set of activities, typically described
as a sequence of tasks with a clear assignment of responsibilities. This problem-
solution pairs are cases and build a case-base, which can be queried on the basis
of specified features of a new reqested process model. Workflows retrieved from
the case-base can represent a solution for the new upcoming problem, usually
after an adaptation to the specific needs of the new request.
In the past decade reasonable amount of research was done in POCBR. But
there is still less literature about using transfer learning methods for transfering
process-oriented knowledge. In our project EVER21 we force these ideas and ex-
plore the transferability of workflows. According to our previous research there
is an evidence that workflows are transferable from one well-known domain into
another domain, where the knowledge is sparse. We are convinced that the trans-
fer is possible and also meaningful, if there is some overlap between the domains
and the target domain can benefit from the transferred workflows in various ways
[9]. In our work we examine ontologies as a means for the transfer, since they
are a suitable tool for describing relations between the parts of a workflow and
allow ontology mapping. Additionaly, we intend to accommodate the concepts
of abstraction and generalization for workflows in an ontology. These concepts
are able to ease the transfer as stated in [9].
Workflows often consist of very domain-specific tasks. When transfering into
the target domain in the initial form, it might be difficult to find corresponden-
cies. Generalization can ease the problem without changing the original structure
of a workflow. We assume that if the descriptions of activities are replaced with
another, more general terms, it will facilitate the finding of analogies with the
target domain. After the transfer, generalized workflows have to be specified to
the original form and usually also adapted according to the needs of the target
domain. We plan to examine, if a developed hierarchy of tasks can be used for
automated generalization of workflows and if the method utilizes transfer learn-
ing, as stated in [9].
In this paper we introduce two domains as possible candidates for transfer-
ing process models. One domain is passenger and baggage handling at the airport
and the second one is warehouse management. Our hypothesis for this position
1
funded by Deutsche Forschungsgemeinschaft (DFG) under the project number MI
1455-2-3
paper is that the two introduced domains are feasible candidates for transfer
learning. We transformed the available workflows from this two domain repos-
itories into the BPMN 2.0 format. In the past years BPMN became de facto
standard in modeling of business processes and the underlying XML format pro-
vides a good base for further automation in processing of workflows. It allows
a good transformation in an ontology as well as retrieval without any losses of
information. The steps of building a domain-independent ontology from BPMN
workflows are matter of our previous publication [3].
This paper is structured as follows: In the next section we provide an overview
about the related work. Third section describes the data foundation and where
we currently stand in our project. Section four o↵ers a proposal for further de-
velopment of transfer learning methods, such as generalization and abstraction.
In section five we discuss the mentioned domains as potential transfer learning
use cases and motivate, why we believe they are good candidates for transfering
workflows. At the end we summarize our paper and draw some conlusions.
2 Related Work
Up to now there has been done a considerable amount of research on case-
based reasoning. Generally speaking, CBR systems contain problem-solution
pairs (cases), which are collected in a case-base. The cases can be retrieved,
adapted and re-used for new upcoming problems. If the suggested solution is
able solve the new problem, CBR system adds the new problem-solution pair
into the case-base. If not, the retrieval result will be rejected and the system
stores this information as well. Due to this learning ability some authors de-
scribe CBR as a transfer learning method [4]. Our research is a contribution to
this topic and we extend it to procedural knowledge. First literature on transfer-
ability of process-oriented cases indicates that workflows are transferable [9]. We
plan to enhance this e↵orts and automate transfering of procedural knowledge.
So far there is still little research on transfer learning for process-oriented
case-based reasoning (POCBR). Our goal is to examine POCBR methods for
transfering process knowledge from one domain into another one. One of the
valuable methods are analogical models. Analogy can be used for di↵erent kind
of scientific questions on transfer learning and there is a substantial amount of
literature on analogical models [1], [6], [14], [5]. To be able to transfer proce-
dural knowledge there has to exist some overlap between the source and the
target domain. This overlap can be represented by analogy. Therefore, one of
the directions for our research is finding analogies between workflows, or at least
between their parts.
In the literature there are some approaches for building of process-oriented
ontologies, as for example the POBA-approach [2]. Compared to our goal of
transfering workflows, their idea is to disambiguate and improve the quality in
modeling of workflows. There also exists literature on BPMN-ontologies [11],
[17]. They focus on capturing all BMPN elements and the relations between
them. As we only use a small part of the BPMN vocabulary, we decided not to
utilize a whole BPMN ontology but only successively add the required elements.
3 Data Foundation
In this section we would like to describe the current state of our project and
the preliminary results along with some data foundations. As mentioned in the
introductory section, we propose two di↵rent domains for transfer learning in
business processes. The first domain is passenger and baggage handling at the
airport. Second domain is SAP warehouse management. Below we show some
typical workflow examples and snippets from the ontologies built for the two
domains. We used Camunda Modeler as a modeling tool and generated in total
50 XML files. For creating ontologies we used Protégé. It is a publicly available
tool and so far it covers all functionalities we need for our purposes.
For the repository in the airport passenger and baggage handling domain we
extracted 30 workflows, mainly di↵erent kinds of passenger check-in, baggage
handling, security checks (for passengers and baggage), customs clearance and
various workflows for transport and loading of baggage into the aircraft. Most
of the workflows are based on a textbook [15] and modelled in BMPN 2.0. Fig.
1 shows an example of a workflow from the airport domain.
Fig. 1. Workflow ’Passenger Handling Check-In the Evening Before’
In the SAP warehouse management domain we extracted 20 di↵erent work-
flows from the SAP website [18]. The website is a collection of best practices
for integration of SAP Extended Warehouse Management and SAP S/4HANA
rapid deployment solution. It contains di↵erent process models, primarily de-
signed for the integration of SAP modules, but they o↵er a solid amount of
business procedures to extract workflows with the appropriate control flow. The
processes cover e.g. inbound and outbound of products in/from various kinds
of warehouses, replenishment, scrapping, inventory as well as consumption of
products during production. We also transformed these workflows into BPMN.
As we found some inconsistencies in the proprietary format, it was necessary to
define rules for modeling them in BPMN. Fig. 2 shows a snippet of a workflow
from the warehouse management domain.
Fig. 2. Part of the workflow ’Inbound from Vendor to Narrow Aisle Storage/Mezzanine’
In the next step of our project we created ontologies for both domains. Their
development follows the instructions according to our previous publication [3].
The steps capture all elements and relations of a workflow, so it is completely
covered in an ontology. According to this procedure it is possible to create work-
flow ontologies independent of any underlying domain. In Protégé we created
basic classes for BPMN elements and also some basic properties to be able to
cover all necessary relations. In our work we don’t focus on covering the entire
BPMN vocabulary. We are aware that there are existing BPMN ontologies, but
for the sake of simplicity we only add elements, that really occurs in our work-
flows.
As next, we imported workflows into the ontology in an automated manner
and developed a JAVA-based tool for this purposes. Using a DOM parser we
are able to transform all XML files into an OWL format and create a workflow
ontology according to the predefined rules. We evaluated this procedure and de-
veloped a SPARQL filter for retrieving particular workflows from an ontology.
The results show, that we are able to retrieve a workflow from the ontology
wihtout any loss of information. The query filters out all elements assigned to a
workflow, e.g. lanes, actors, tasks and also the control flow, so the initial work-
flow can be completely restored, if necessary. In Fig. 3 we demonstrate a result
of the SPARQL query for the the workflow drawn in Fig. 1, after was added
and retrieved from an ontology. The sample does not contain any documents or
gateways, but of course they can be restored as any other part of a workflow.
Another contribution to our project is building of a task hierarchy in the
airport domain. The reason why we created the hierarchy is the idea of general-
ization of workflows. In the next section we will go into this in more detail, and
explain how generalization can be used in transfer learning. During the model-
ing of the airport workflows, we realized that there are various tasks with a very
similar meaning, e.g. movement of pieces of luggage. Baggage can be moved by
the airport sta↵, baggage conveyor system or transported in dollies or containers
through the airport. These tasks can be sorted in classes, depending on the type
of the movement. Building the task hierarchy still needs to be done manually.
At this stage of our project, the tool wouldn’t be able to recognize the exact
meaning of tasks yet and group them automatically in classes. In total we have
about 125 di↵erent tasks and they are classified in four di↵erent hierarchy levels.
The hierarchy can easily be added to the airport ontology and serves as a basis
for the generalization of workflows. Fig. 4 demonstrates a small excerpt of the
task hierarchy for the airport domain.
4 Further development of methods for the transfer
learning process
Transfer learning is useful in cases where workflows can not be transferred di-
rectly in the original form. If there is a relevant overlap between the domains,
workflows can be transferred in the original structure, but by using of more
general terms. In our previous work we already showed on manual basis that
generalization of workflows can ease the identification of correspondencies [9].
In case the overlap between the domains is considerably smaller, the ideas of
analogical mapping can be considered as a means for the transfer.
We plan to extend our previous work and automate the creation of gen-
eralized workflows. During the phase of modeling in BPMN we found several
analogies between the tasks in both domains, e.g. movement of goods, check-in
procedure etc. For the aiport domain we already developed a task hierarchy and
accommodated it into the ontology. We intend to build a task hierarchy and then
produce generalized workflows also for the warehouse domain. Up to now we are
able to capture all necessary relations of a workflow in an ontology. So we are
optimistic about using ontologies for the automated generalization of workflows.
Once a generalized workflow is transferred, it has to be specified and/or adapted
according to the requirements of the target domain.
Generalization does not change the original structure of a workflow. The
business processes in our repositories indicate that some of the workflows might
be too complex for the transfer via generalizatio only. According to the previous
|%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%|
|--------------------------------------------------------------------------------------|
|--------------Type and name of all BPMN-elements--------------------------------------|
|--------------------------------------------------------------------------------------|
|Security_Area----->Actors |
|Passenger----->Actors |
|Go_to_Security_Area----->User_Tasks |
|Enter_the_Terminal----->User_Tasks |
|Enter_the_Terminal----->Tasks |
|End----->Events |
|Start----->Events |
|Process_Security_Area----->Processes |
|--------------------------------------------------------------------------------------|
|------------Assignment of all BPMN-elements to a particular lane----------------------|
|--------------------------------------------------------------------------------------|
|Lane: Security_Area |
|-End |
|-Process_Security_Area |
|--------------------------------------------------------------------------------------|
|Lane: Passenger |
|-End |
|-Start |
|-Go_to_Security_Area |
|-Enter_the_Terminal |
|--------------------------------------------------------------------------------------|
|----------Order of all elements and information relevant for decisions----------------|
|--------------------------------------------------------------------------------------|
|(1)Start-->Enter_the_Terminal |
|(2)Enter_the_Terminal-->Go_to_Security_Area |
|(3)Go_to_Security_Area-->Process_Security_Area |
|(4)Process_Security_Area-->End |
|--------------------------------------------------------------------------------------|
|------------Assignment of all documents as input or output of a task------------------|
|--------------------------------------------------------------------------------------|
|%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%|
Fig. 3. Screenshot of the retrieved workflow drawn in Fig. 1
Fig. 4. Part of the task hierarchy in Protégé
work on transferability of process-oriented cases, worklows are better transfer-
able on a higher abstraction level [9]. At this point the method of compositional
adaption could help to reduce the complexity of workflows and help to find analo-
gies. One way to realize compositional adaptation for workflows is to decompose
them into meaningful parts, called workflow streams [10]. A workflow stream
can be represented and replaced by an abstract task, so it o↵ers an immediate
method for abstraction [9]. The rules for identifying of workflow streams accord-
ing to the existing literature [10] are mostly based on documents consumed or
produced by tasks. The workflows in our two domains are less document-driven,
so we need to define another rules for identifying of workflow parts suitable for
abstraction. We intend to accommodate this rules and also the abstracted work-
flows in the ontology. To make transferred workflows executable, the abstraction
has to be reversed and the workflows adapted in the target domain.
5 Potential transfer learning use cases and benefit
discussion
In this section we would like to outline, why we believe the proposed two domains
are feasible candidates for transfer learning. During the workflow modeling we
detected analogies in tasks and partially also in the control flow. Fig. 5 shows
some examples of these analogies. Left column describes tasks from check-in and
baggage handling processes at the airport. In most cases these tasks are executed
in the same order as in the table. Right column represents their correspondencies
in the warehouse domain. It illustrates the workflow snippet drawn in Fig. 2. It
is obvious that both, the tasks themselves as well as the order of tasks are quite
similar. This is a clear indicator that the two domains are extremely promising
for further examination of transfer learning.
Fig. 5. Example of analogical tasks from both domains
At this point we sketch some ideas for possible applications of workflow trans-
fer between the introduced domains. We are convinced that workflows from one
domain can support the workflow modeling in the other domain. Sometimes
enterprises su↵er from lack of expertise or the modelers need instant help in
creating workflow models. Transferred workflows or at least parts of them can
be used as a template and help in the creation of models in the target domain,
given the sufficient overlap.
Transferred workflows can also be used as additional knowledge for excep-
tion handling. For instance when after a flight delay the passenger misses the
connecting flight. Instead of transiting his/her baggage from one aircraft into
the connecting one directly on the airfield, it has to be checked out and later
checked in. For all these scenarios we posses workflow models in our repository.
A similar situation can occur in the warehouse domain. Many warehouses serve
as distribution centers and are spread in a star-shape through the countries.
They usually do not store goods but load them from one truck into another one
for further distribution. Once a truck has a delay and the connecting one can
not wait, the goods have to be stored until further distribution. This requires
exception handling, such as inbound and outbound of products. We believe that
with the workflows from the airport domain we would be able to handle this
exception and model or apply addapted workflows in the warehouse domain.
Another potential use case might be the enrichment with sensory capabilities,
for example based on RFID technology. Airports normally use bar code sensor-
ing. Baggage tags contain bar codes that can be read out at di↵erent points of
the airport. This technology is quite limited as bar codes are not able to store
as much of the information as RFID codes. Airport operators are aware of this
limitations but they often hesitate to implement RFID technology as it is very
cost-intensive. Compared to this, in the logistics and warehouse domain RFID
technology is widespread. RFID codes can store extensive information, e.g. ob-
servation of the cold chain etc. Potentially, experiences from utilizing RFID in
the logistics and warehouse domain might be transferred to the aiport domain,
and help for example with finding of best positioning for RFID scanners. But
at this stage of our project, this idea is only a skech and a matter of further
examination.
6 Conclusion
In this paper we describe the progress of our project on transfer learning for case-
based reasoning. We gained two workflow repositories from the domains airport
passenger/baggage handling and warehouse management in BPMN format. We
developed tools for transforming these workflow models into ontologies and also
for retrieving of workflow models from an ontology. We created a task hierarchy
in one of those two domains as a base for workflow generalization. Then we
outline the next steps for the research on using ontologies for generalization and
abstraction. We explain the background of these methods and outline how we
plan to utilize them for our purposes. We have elaborated sample analogies that
are a strong indicator that our hypothesis can be confirmed and the two proposed
domains provide valuable use cases for transfer learning. We introduce some
potential application scenarios for transfer learning and discuss why we believe
the introduced domains are feasible candidates for transferring workflows.
Acknowledgement
We would like to thank Jan Höcher for his support in the development of tools
described in the third section.
References
1. B. Falkenhainer, K. D. Forbus, and D. Gentner. The structure-mapping engine:
Algorithm and examples. Artificial intelligence, 41(1):1–63, 1989.
2. S. Fan, Z. Hua, V. C. Storey, and J. L. Zhao. A process ontology based approach
to easing semantic ambiguity in business process modeling. Data & Knowledge
Engineering, 102:57–77, 2016.
3. M. Herold and M. Minor. Ontology-based representation of workflows for transfer
learning. In Proceeding of the Conference ”Lernen, Wissen, Daten, Analysen”,
Mannheim, Germany, August 22-24, 2018, pages 139–149, 2018.
4. M. Klenk, D. W. Aha, and M. Molineaux. The case for case-based transfer learning.
AI Magazine, 32(1):54–54, 2011.
5. M. Klenk and K. Forbus. Exploiting persistent mappings in cross-domain analog-
ical learning of physical domains. Artificial intelligence, 195:398–417, 2013.
6. T. Könik, P. O’Rorke, D. Shapiro, D. Choi, N. Nejati, and P. Langley. Skill
transfer through goal-driven representation mapping. Cognitive Systems Research,
10(3):270–285, 2009.
7. D. Kudenko. Special issue on transfer learning. KI - Künstliche Intelligenz, 28:5–6,
02 2014.
8. C. Matt, T. Hess, and A. Benlian. Digital transformation strategies. Business &
Information Systems Engineering, 57(5):339–343, 2015.
9. M. Minor, R. Bergmann, J.-M. Müller, and A. Spät. On the Transferability of
Process-Oriented Cases. In A. K. Goel, M. B. Dı́az-Agudo, and T. Roth-Berghofer,
editors, Case-Based Reasoning Research and Development - 24th International
Conference, ICCBR 2016, Atlanta, GA, USA, October 31 - November 2, 2016,
Proceedings, volume 9969 of Lecture Notes in Computer Science, pages 281–294.
Springer, 2016.
10. G. Müller and R. Bergmann. Generalization of workflows in process-oriented case-
based reasoning. In The Twenty-Eighth International Flairs Conference, 2015.
11. C. Natschläger. Towards a bpmn 2.0 ontology. In International Workshop on
Business Process Modeling Notation, pages 1–15. Springer, 2011.
12. M. Oquab, L. Bottou, I. Laptev, and J. Sivic. Learning and transferring mid-
level image representations using convolutional neural networks. In Proceedings of
the IEEE conference on computer vision and pattern recognition, pages 1717–1724,
2014.
13. S. J. Pan and Q. Yang. A survey on transfer learning. IEEE Transactions on
knowledge and data engineering, 22(10):1345–1359, 2009.
14. M. Ragni and G. Strube. Cognitive complexity and analogies in transfer learning.
KI-Künstliche Intelligenz, 28(1):39–43, 2014.
15. A. Richter. Gepäcklogistik auf Flughäfen: Grundlagen, Systeme, Konzepte und
Perspektiven. Springer-Verlag, 2012.
16. M. M. Richter and R. O. Weber. Case-based reasoning. Springer, 2016.
17. M. Rospocher, C. Ghidini, and L. Serafini. An ontology for the business process
modelling notation. In FOIS, pages 133–146, 2014.
18. SAP. Sap best practices explorer, 2019 (accessed July 7, 2019).
https://rapid.sap.com/bp/#/browse/categories/sap_s%254hana/areas/
on-premise/packageversions/RDS_EWM_S4.
19. M. E. Taylor and P. Stone. Transfer learning for reinforcement learning domains:
A survey. Journal of Machine Learning Research, 10(Jul):1633–1685, 2009.