Process-oriented Case-based Reasoning Research Articles

Ranking-Based Case Retrieval with Graph Neural Networks in Process-Oriented Case-Based Reasoning

In Process-Oriented Case-Based Reasoning (POCBR), experiential knowledge from previous problem-solving situations is retrieved from a case base to be reused for upcoming problems. The task of retrieval is approached in previous work by using Graph Neural Networks (GNNs) to learn workflow similarities which are, in turn, used to find similar workflows w.r.t. a query workflow. This paper is motivated by the fact that these GNNs are mostly used for predicting the similarity between two workflows (query and case), while the retrieval in CBR is only concerned with the ranking of the most similar workflows from the case base w.r.t. the query. Thus, we propose a novel approach to extend the GNN-based workflow retrieval by a Learning-to-Rank (LTR) component where rankings instead of similarities between cases are predicted. The main contribution of this paper addresses the changes to the GNNs from previous work, such that their model architecture predicts pairwise preferences between cases w.r.t. a query and that they can be trained using labeled preference data. In order to transform these preferences into a case ranking, we also describe rank aggregation methods with different levels of computational complexity. The experimental evaluation compares different models for predicting similarities and rankings in case retrieval scenarios. The results indicate the potential of our ranking-based approach in significantly improving retrieval quality with only small impacts on the performance.

Considering Inter-Case Dependencies During Similarity-Based Retrieval in Process-Oriented Case-Based Reasoning

In Case-Based Reasoning (CBR), knowledge gained from previously experienced problem-solving situations is stored as cases that can be used to solve similar upcoming problems. Although these cases act as independent knowledge entities, dependencies between cases are common in real-world scenarios, despite being only rarely considered during case retrieval or other CBR phases. In this paper, we introduce so-called inter-case dependencies, which are considered in the context of Process-Oriented CBR (POCBR). Therefore, we 1) derive requirements that must be satisfied for considering dependencies during the retrieval phase, 2) analyze which knowledge representations are suitable for representing dependencies between cases, and, 3) present our approach for Dependency-Guided Retrieval (DGR) that considers these dependencies between cases during the retrieval phase. In the experimental evaluation, the proposed DGR approach is compared to a regular CBR approach in case retrieval scenarios from the cooking domain. The results demonstrate that the use of the DGR approach leads to significantly reduced times for human problem-solving compared to regular CBR.

Using Graph Embedding Techniques in Process-Oriented Case-Based Reasoning

Similarity-based retrieval of semantic graphs is a core task of Process-Oriented Case-Based Reasoning (POCBR) with applications in real-world scenarios, e.g., in smart manufacturing. The involved similarity computation is usually complex and time-consuming, as it requires some kind of inexact graph matching. To tackle these problems, we present an approach to modeling similarity measures based on embedding semantic graphs via Graph Neural Networks (GNNs). Therefore, we first examine how arbitrary semantic graphs, including node and edge types and their knowledge-rich semantic annotations, can be encoded in a numeric format that is usable by GNNs. Given this, the architecture of two generic graph embedding models from the literature is adapted to enable their usage as a similarity measure for similarity-based retrieval. Thereby, one of the two models is more optimized towards fast similarity prediction, while the other model is optimized towards knowledge-intensive, more expressive predictions. The evaluation examines the quality and performance of these models in preselecting retrieval candidates and in approximating the ground-truth similarities of a graph-matching-based similarity measure for two semantic graph domains. The results show the great potential of the approach for use in a retrieval scenario, either as a preselection model or as an approximation of a graph similarity measure.

Bioinformatic workflow extraction from scientific texts based on word sense disambiguation and relation extraction.

This paper introduces a method for automatic workflow extraction from texts using Process-Oriented Case-Based Reasoning (POCBR). While the current workflow management systems implement mostly different complicated graphical tasks based on advanced distributed solutions (e.g. cloud computing and grid computation), workflow knowledge acquisition from texts using case-based reasoning represents more expressive and semantic cases representations. We propose in this context, an ontology-based workflow extraction framework to acquire processual knowledge from texts. Our methodology extends classic NLP techniques to extract and disambiguate tasks and relations in texts. Using a graph-based representation of workflows and a domain ontology, our extraction process uses a context-aware approach to recognize workflow components: data and control flows. We applied our framework in a technical domain in bioinformatics: i.e. phylogenetic analyses. An evaluation based on workflow semantic similarities on a gold standard proves that our approach provides promising results in the process extraction domain. Both data and implementation of our framework are available in: http://labo.bioinfo.uqam.ca/tgrowler.

Social workflows—Vision and potential study

Social workflows pervade peoples׳ everyday life. Whenever a group of persons works together on a challenging or multifaceted task, a social workflow begins. Unlike traditional business workflows, such social workflows aim at supporting processes that contain personal tasks and data. In this work, we envision a social workflow service as part of a social network that enables private individuals to construct social workflows according to their specific needs and to keep track of the workflow execution. The proposed features for a social workflow service could help individuals to accomplish their private goals. The presented idea is contrasted with established research areas and applications to show the degree of novelty of this work. It is shown how novel ideas for knowledge management, facilitated by a process-oriented case-based reasoning approach, support private individuals and how they can obtain an appropriate social workflow through sharing and reuse of respective experience. Two empirical studies confirm the potential benefits of a social workflow service in general and the core features of the developed concept.

CBR in the service of accident cases evaluating

This paper introduces a research aiming at the development of a decision support system concerning the approval of automated railway transportation systems. The objective is to implement a valuation method for the degree of compliance of the automated transportation system in-group of safety standards by the analysis of the scenarios of accident. To reach this target, we envisaged an approach Rex (Return of experience) who draws the lessons of accidents / incidents lived and/or imagined by the experts of the analysis of security in the IFSTAAR. Our approach consists in offering a decision support in the side of the experts of the certification based on a reuse of the scenarios of accidents already validated historically on other approved transportation systems. This approach Rex is very useful since it provides to the experts a class of scenarios of accidents similar to the new case treated and getting closer to the context of new case. The Case-based reasoning is then exploited as a mode of reasoning by analogy allowing to choose and to recollect one under group of historical cases that can help in the resolution of the new case introduced by the experts. Process-Oriented Case-Based Reasoning (PO-CBR) is a growing application area in which CBR is used to address problems involving process data in a variety of specialized domains. PO-CBR systems often use structured cases. Our approach is characterized by a two-phased retrieval strategy. A first phase consists in retrieving a set of cases to be considered (a class of cases most similar to a problem to resolve). In a second phase, a more fine grained strategy is then applied to the pool of candidate cases already selected by the mean of similarity measures. This approach can enhance the process of retrieving cases compared to an exhaustive case-by-case comparison.

Automatic case acquisition from texts for process-oriented case-based reasoning

This paper introduces a method for the automatic acquisition of a rich case representation from free text for process-oriented case-based reasoning. Case engineering is among the most complicated and costly tasks in implementing a case-based reasoning system. This is especially so for process-oriented case-based reasoning, where more expressive case representations are generally used and, in our opinion, actually required for satisfactory case adaptation. In this context, the ability to acquire cases automatically from procedural texts is a major step forward in order to reason on processes. We therefore detail a methodology that makes case acquisition from processes described as free text possible, with special attention given to assembly instruction texts. This methodology extends the techniques we used to extract actions from cooking recipes. We argue that techniques taken from natural language processing are required for this task, and that they give satisfactory results. An evaluation based on our implemented prototype extracting workflows from recipe texts is provided.

Similarity assessment and efficient retrieval of semantic workflows

In the recent years, the use of workflows has significantly expanded from its original domain of business processes towards new areas. The increasing demand for individual and more flexible workflows asks for new methods that support domain experts to create, monitor, and adapt workflows. The emergent field of process-oriented case-based reasoning addresses this problem by proposing methods for reasoning with workflows based on experience. New workflows can be constructed by reuse of already available similar workflows from a repository. Hence, methods for the similarity assessment of workflows and for the efficient retrieval of similar workflows from a repository are of core importance. To this end, we describe a new generic model for representing workflows as semantically labeled graphs, together with a related model for knowledge intensive similarity measures. Further, new algorithms for workflow similarity computation, based on A⁎ search are described. A new retrieval algorithm is introduced that goes beyond traditional sequential retrieval for graphs, interweaving similarity computation with case selection. We describe the application of this model and several experimental evaluations of the algorithms in the domain of scientific workflows and in the domain of business workflows, thereby showing its broad applicability.