Gilbert Müller

Workflow Streams: A Means for Compositional Adaptation in Process-Oriented CBR

This paper presents a novel approach to compositional adaptation of workflows, thus addressing the adaptation step in processoriented case-based reasoning. Unlike previous approaches to adaptation, the proposed approach does not require additional adaptation knowledge. Instead, the available case base of workflows is analyzed and each case is decomposed into meaningful subcomponents, called workflow streams. During adaptation, deficiencies in the retrieved case are incrementally compensated by replacing fragments of the retrieved case by appropriate workflow streams. An empirical evaluation in the domain of cooking workflows demonstrates the feasibility of the approach and shows that the quality of adapted cases is very close to the quality of the original cases in the case base.

Learning and Applying Adaptation Operators in Process-Oriented Case-Based Reasoning

This paper presents a novel approach to the operator-based adaptation of workflows, which is a specific type of transformational adaptation. We introduce the notion of workflow adaptation operators which are partial functions transforming a workflow into a successor workflow, specified by workflow fractions to be inserted and/or deleted. The adaptation process itself chains adaptation operators during a local search process aiming at fulfilling the query as best as possible. Further, the paper presents an algorithm that learns workflow adaptation operators from the case base automatically, thereby addressing the common problem of adaptation knowledge acquisition. An empirical evaluation in the domain of cooking workflows was conducted which demonstrates convincing adaptation capabilities without a significant reduction of the workflows’ quality.

The Collaborative Agile Knowledge Engine CAKE

The Collaborative Agile Knowledge Engine (CAKE) is a prototypical generic software system for integrated process and knowledge management. CAKE integrates recent research results on agile workflows, process-oriented case-based reasoning, and web technologies into a common platform that can be configured to different application domains and needs. We describe the main concepts and the architecture of CAKE and sketch three example applications.

A cluster-based approach to improve similarity-based retrieval for process-oriented case-based reasoning

In case-based reasoning, improving the performance of the retrieval phase is still an important research issue for complex case representations and computationally expensive similarity measures. This holds particularly for the of retrieval workflows, which is a recent topic in process-oriented case-based reasoning. While most index-based retrieval methods are restricted to attribute-value representations, the application of a MAC/FAC retrieval approach introduces significant additional domain-specific development effort due to design the MAC phase. In this paper, we present a new index-based retrieval algorithm, which is applicable beyond attribute-value representations without introducing additional domain-specific development effort. It consists of a new clustering algorithm that constructs a cluster-based index structure based on case similarity, which helps finding the most similar cases more efficiently. The approach is developed and analyzed for the retrieval of semantic workflows. It significantly improves the retrieval time compared to a linear retriever, while maintaining a high retrieval quality. Further, it achieves a similar performance than the MAC/FAC retriever if the case base has a cluster structure, i.e., if it contains groups of similar cases.

Workflow Clustering Using Semantic Similarity Measures

The problem of clustering workflows is a relatively new research area of increasing importance as the number and size of workflow repositories is getting larger. It can be useful as a method to analyze the workflow assets accumulated in a repository in order to get an overview of its content and to ease navigation. In this paper, we investigate workflow clustering by adapting two traditional clustering algorithms (k-medoid and AGNES) for workflow clustering. Clustering is guided by a semantic similarity measure for workflows, originally developed in the context of case-based reasoning. Further, a case study is presented that evaluates the two algorithms on a repository containing cooking workflows automatically extracted from an Internet source.

Similarity-Based Retrieval and Automatic Adaptation of Semantic Workflows

The increasing demand for individual and more flexible process models and workflows asks for new intelligent process-oriented information systems. Such systems should, among other things, support domain experts in the creation and adaptation of process models or workflows. For this purpose, repositories of best practice workflows are an important means as they collect valuable experiential knowledge that can be reused in various ways. In this chapter we present process-oriented case-based reasoning (POCBR) as a method to support the creation and adaptation of workflows based on such knowledge. We provide a general introduction to process-oriented case-based reasoning and present a concise view of the POCBR methods we developed during the past ten years. This includes graph-based representation of semantic workflows, semantic workflow similarity, similarity-based retrieval, and workflow adaptation based on automatically learned adaptation knowledge. Finally, we sketch several application domains such as traditional business processes, social workflows, and cooking workflows.

Conversational Process-Oriented Case-Based Reasoning

Current approaches for retrieval and adaptation in process-oriented case-based reasoning (POCBR) assume a fully elaborated query given by the user. However, users may only have a vague idea of the workflow they desire or they lack the required domain knowledge. Conversational case-based reasoning (CCBR) particularly addresses this problem by proposing methods which incrementally elicit the relevant features of the target problem in an interactive dialog. However, no CCBR approaches exist that are capable of automatically creating questions from the case descriptions that go beyond attribute-value representations. In particular, no approaches exist that are applicable to workflow cases in graph representation. This paper closes this gap and presents a conversational POCBR approach (C-POCBR) in which questions related to structural properties of the workflow cases are generated automatically. An evaluation in the domain of cooking workflows reveals that C-POCBR can reduce the communication effort for users during retrieval.

Complexity-Aware Generation of Workflows by Process-Oriented Case-Based Reasoning

One of the biggest challenges in business process management is the creation of appropriate and efficient workflows. This asks for intelligent, knowledge-based systems that assist domain experts in this endeavor. In this paper we investigate workflow creation by applying Process-Oriented Case-Based Reasoning (POCBR). We introduce POCBR and describe how it can be applied to the experience-based generation of workflows by retrieval and adaptation of available best-practice workflow models. While existing approaches have already demonstrated their feasibility in principle, the generated workflows are not optimized with respect to complexity requirements. However, there is a high interest in workflows with a low complexity, e.g., to ensure the appropriate enactment as well as the understandability of the workflow. The main contribution of this paper is thus a novel approach to consider the workflow complexity during the workflow generation. Therefore, a complexity measure for workflows is proposed and integrated into the retrieval and adaptation process. An experimental evaluation with real cooking recipes clearly demonstrates the benefits of the described approach.

A Conversational Approach to Process-oriented Case-based Reasoning

Process-oriented case-based reasoning (POCBR) supports workflow modeling by retrieving and adapting workflows that have proved useful in the past. Current approaches typically require users to specify detailed queries, which can be a demanding task. Conversational case-based reasoning (CCBR) particularly addresses this problem by proposing methods that incrementally elicit the relevant features of the target problem in an interactive dialog. However, no CCBR approaches exist that are applicable for workflow cases that go beyond attribute-value representations such as labeled graphs. This paper closes this gap and presents a conversational POCBR approach (C-POCBR) in which questions related to structural properties of the workflow cases are generated automatically. An evaluation with cooking workflows indicates that C-POCBR can reduce the communication effort for users during retrieval.

Considering Nutrients During the Generation of Recipes by Process-Oriented Case-Based Reasoning

This paper investigates the generation of recipes in consideration of user-defined nutrient contents. For this purpose, we extend our previous case-based reasoning approach that already covers the formulation of user queries with various dietary practices. More precisely, this work augments the domain ontology with nutritional information and introduces a novel nutrition concept fulfillment into the retrieval and adaptation process. An experimental evaluation with real cooking recipes demonstrates the applicability of the approach and systematically investigates the influence of various adaptation methods on the query fulfillment with multiple constraints. It is shown, that all adaptation methods are able to optimize generated recipes according to certain nutritional constraints as well as ingredient and cooking step preferences and that the adaptation outperforms the sole retrieval of available recipes.