Siemens Aktiengesellschaft

Sonja Zillner

Heiner Oberkampf

Michal Skubacz

Alexey Tsymbal

Stephan Grimm

Andreas Hölzl

Claudia Bretschneider

Huber Martin

Anna Himmelhuber

Production logs and industrial ontologies are processed with an inductive logic program performing class expression learning in order to create class expressions, with each class expression representing a constraint or property of a skill of a production module. The resulting class expressions are ordered by a metric to form an ordered recommender list and displayed to a user for postprocessing. The user selects suitable class expressions from the ordered recommender list, so that the system can build a machine-readable skill description with the selected class expressions. This approach to generating formal, machine-readable skill descriptions minimizes the labor time and domain expertise needed to equip production modules with their skill description. Selecting the correct class expression from the automatically generated ordered recommender list is a much lower effort than manual labeling from scratch.

Method and system for semi-automated generation of machine-readable skill descriptions of production modules

Provided is a system for feedback-improved automatic solving of production facility related tasks, including: an input interface being adapted to receive production facility related data; a semantic data enhancement module being adapted to generate semantically enhanced data based on the production facility related data; a semantic-based reasoning module being adapted to automatically provide an explainable artificial intelligence model, using the semantically enhanced data, wherein the artificial intelligence model relates to a predetermined production facility related task; a user interaction interface being adapted to output explanation data regarding the explainable artificial intelligence model to a user; and a feedback module adapted to receive feedback from the user in response to the outputted explanation data and adapted to adjust the semantic-based reasoning module and/or the user interaction interface based on the received feedback.

Apparatus for the semantic-based optimization of production facilities with explainability

Provided is a method for computer-implemented determination of a data-driven prediction model. The method processes digital input data having input and output variables and being semantically annotated based on a digital semantic representation having a hierarchical tree structure where each tree in the structure represents an input variable of the data, the leaf nodes of the respective tree being the discrete values of the input variable. The method of the embodiment provides a recoding of those discrete values by cutting off hierarchical levels of the respective trees. Based on this recoding, a plurality of data modifications is determined for the input data. Those data modifications are trained by a machine learning method where the trained machine learning method with the highest prediction quality is derived from the trained machine learning methods.

Method for computer-implemented determination of a data-driven prediction model

Provided is an apparatus and method for providing an instantiated industrial semantic model, iISM, for an industrial infrastructure having data generation components, the apparatus including: an interface unit adapted to receive from an industrial infrastructure data generated by data generation components provided within the industrial infrastructure, a context management unit adapted to derive types of data generation components provided within the industrial infrastructure depending on characteristics of the received data and adapted to map each derived type of data generation component to an associated context model specified in the industrial semantic model, ISM, stored in a repository, and an instantiating unit adapted to instantiate the stored industrial semantic model, ISM, with predefined industrial instance models, IIMs, of data generation components on the basis of the mapped context models to generate the instantiated industrial semantic model, iISM, of the industrial infrastructure.

Method and apparatus for providing an instantiated industrial semantic model for an industrial infrastructure

A method and system for supporting a clinical diagnosis is provided, the method including the steps of representing a patient by a plurality of initial symptoms, the symptoms including characteristics of the patient; determining, by querying and reasoning in a disease-symptom knowledge model, at least one likely disease for each of the plurality of initial symptoms; mapping the plurality of initial symptoms onto a set of said likely diseases; determining for each disease of said set of likely diseases a plurality of associated symptoms, the associated symptoms being associated to a respective disease of said set of likely diseases in said disease-symptom knowledge model; categorizing each of the plurality of associated symptoms into disjoint categories by mapping associated symptoms with initial symptoms; and representing likely diseases in the context of said categories of associated symptoms.

Method and system for supporting a clinical diagnosis

Methods and systems may support conclusions of a clinician by enabling the clinician to arbitrarily define the symptoms according to the patient's record. The method may comprise: (a) determining a plurality of symptoms representing a patient and including characteristics of the patient, the symptoms being categorized as present symptoms, absent symptoms or open symptoms; (b) establishing a multi-tier relationship between said symptoms and a plurality of diseases based on a knowledge model; (c) adjusting weighting factor(s) for at least one multi-tier relationship based on said knowledge model; (d) optionally adjusting at least one weighting factor of step (c) by an expert; and (e) building a ranking of diseases from said multi-tier relationship based on said weighting factors. The method may provide an efficient ranking of disease information, thereby supporting a clinical diagnosis that may consider multiple symptoms while emphasizing particular symptoms in view of the clinician's expertise.

A method for processing medical reports includes applying natural language processing methods to perform an initial segmentation of at least parts of textual contents of each medical report into information units, thereby identifying information units, such as text fragments, sentences or text passages, within the medical reports. The information units are classified into at least one context class to determine their appropriate context classes for a particular situation or application. The context classifications are created using a grammar, e.g., a context-free grammar, and can then be used for automatically assigning each information unit to an appropriate context meta-information. The medical report may be annotated by assigning the information units to context meta-information determined by the context class, and the context meta-information may be used by other applications, e.g., dedicated mechanisms for clinical data integration, how to efficiently handle the available information units within medical reports.

Method for processing medical reports

A method and system for providing instance information data of at least one instance. The method has the steps of generating a semantic representation of the instance on the basis of at least one instance data source, providing a semantic representation of a domain on the basis of at least one structured domain data source, performing an integration of the semantic instance and domain representations to provide an integrated semantic representation and deriving automatically instance information data from the provided integrated semantic representation. The method and system allow to provide efficiently instance information data of a wide range of instances with technical entities and persons, in a particular patients in different domains such as radiology or anatomy.

System and method for providing instance information data of an instance

A modular method of composing an ontology alignment provides a set of correspondences between at least two ontologies thereby allowing a composition of an optimal alignment by balancing a recall value and a precision of the alignment. A two-fold strategy is followed. By means of mapping functions a set of alignment correspondences is determined. Depending on a particular mapping function a recall value of the alignment can be improved by an extension of the set of correspondences. By filtering functions particularities of the domain are reflected and incorrect mappings are avoided. Depending on a particular filtering function a precision value of the alignment can be improved by restricting the set of correspondences.

Method of composing an ontology alignment

The method of administering a knowledge repository described herein establishes combining data input with concurrent data analytics in order to improve the quality and relevance of data entries.

Method of administering a knowledge repository

A medical ontology may be used for computer assisted clinical decision support. Multi-level and/or semantically grouped medical ontology is incorporated into a machine learning algorithm. The resulting machine-learnt algorithm outputs information to assist in clinical decisions. For example, a patient record is input to the algorithm. Based on the incorporated medical ontology, similarities are aggregated in different groups. An aggregate similarity of at least one group is a function of an aggregate similarity of at least another group. One or more similar patients and/or outcomes are identified based on similarity. Probability based outputs may be provided.

Growing community of inventors

Munich, Germany

Sonja Zillner