Feedback Matching Framework for Semantic Interoperability of Product Data

There is a need to promote drastically increased levels of interoperability of product data across a broad spectrum of stakeholders, while ensuring that the semantics of product knowledge are preserved, and when necessary, translated. In order to achieve this, multiple methods have been proposed to determine semantic maps across concepts from different representations. Previous research has focused on developing different individual matching methods, i.e., ones that compute mapping based on a single matching measure. These efforts assume that some weighted combination can be used to obtain the overall maps. We analyze the problem of combination of multiple individual methods to determine requirements specific to product development and propose a solution approach called FEedback Matching Framework with Implicit Training (FEMFIT). FEMFIT provides the ability to combine the different matching approaches using ranking Support Vector Machine (ranking SVM). The method accounts for nonlinear relations between the individual matchers. It overcomes the need to explicitly train the algorithm before it is used, and further reduces the decision-making load on the domain expert by implicitly capturing the expert's decisions without requiring him to input real numbers on similarity. We apply FEMFIT to a subset of product constraints across a commercial system and the ISO standard. We observe that FEMIT demonstrates better accuracy (average correctness of the results) and stability (deviation from the average) in comparison with other existing combination methods commonly assumed to be valid in this domain. Note to Practitioners-This paper was motivated by the problem of automating the exchange of meaning associated with the data, among different software systems or information resources in product development. More specifically, it focuses on automatically determining the maps between the concepts from participating system, which is required to ensure that the final physical translation is accurate. Existing approaches either focus on one aspect of product information or a weighted sum of different aspects. However, there is no formal ground to choose a specific method. Furthermore, as we show in this paper, these approaches are unlikely to find the correct matches because of the inherent nonlinearity. We propose a framework, FEMFIT, in which multiple matching methods are automatically combined using inputs from experts obtained through an intuitive, Google search-like, interface. It is evaluated by comparing with known matching methods and FEMFIT shows better matching accuracy on the example cases. Future work focuses on extending the work to handle m:n matches.