Abstract: A graph database stores a knowledge graph, with nodes of the knowledge graph corresponding to components of an engineered system and edges of the knowledge graph specifying connections between the components. A reasoning module is equipped with a first agent and a second agent. The agents have been trained with opposing goals and extract paths from the knowledge graph beginning with a node that corresponds to a first component of the engineered system. A prediction module uses a classifier to classify the extracted paths in order to produce a classification result, which indicates consistency, and in particular compatibility, of the first component in relation to the engineered system. This information is provided to an engineer, supporting him in validating the engineered system, for example an industrial automation solution. The method and system provide an automated data-driven algorithm that leverages a large collection of historical examples for consistency checking of components.

Abstract: A computer-implemented method for providing recommendations, REC, concerning a configuration process is provided to configure an industrial system, SYS, the method including the steps of calculating by a trained graph neural network, GNN, scores, s, for components, c, of a set, C, of configurable component types, ct; generating recommendations, REC, for introducing at least one additional component, c, into the industrial system, SYS, on the basis of the calculated scores, s; and outputting the generated recommendations, REC, to a user by a user interface or executing the generated recommendations.

Abstract: For anomaly detection in a network, a temporal knowledge graph represents the network including interactions between network modules with a set of entities, a set of relations, and a set of timestamps. In a first step, temporal random walks are sampled from the temporal knowledge graph. These are transformed in a second step into temporal logical rules. After observing an event in the network—or in a different network—the observed event is classified in a third step regarding an anomaly, using the temporal logical rules. The temporal knowledge graph is used as a stream-based data structure to extract rules that identify typical temporal behavior of the network and is used to identify anomalies in a human-interpretable way. The anomaly detection task is framed as a quadruple classification problem, using the temporal logical rules and their respective groundings in the temporal knowledge graph to support the classification.

Abstract: A recommender system to be used in the context of an engineering tool is provided. By using the recommender, a list of items is provided in the engineering tool which are likely to be connected in a next step to an engineering project designed in the engineering tool.

Abstract: Based on a graph storing a current state of an engineering project consisting of modules, a graph neural network computes an embedding for each node. For each node embedding, a classifier determines a preliminary confidence score for each class, which represents a type of module that could be added to the engineering project. A topology-based measure is calculated at least for a current center node. A blank node is assigned to a bin depending on the topology-based measure that has been computed for the current center node. A post-processor calibrates all preliminary confidence scores for the blank node by applying a scaling factor depending on the assigned bin. Finally, a user interface outputs at least the class with the highest calibrated confidence score for the blank node as well as the respective calibrated confidence score. The binning scheme takes the graph structure into account and allows for adaptive calibration.

Abstract: A database stores a set of items, with each item having technical attributes, and with each item representing a module that can be used in an engineering project of a first user, u1. A feature encoder embeds each item based on its technical attributes into a low-dimensional vector space. Then, in a second step, a graph neural network pools over these item embeddings to compute an updated user embedding for the first user A decoder mapping then addresses the recommendation task by outputting recommendation scores for each item. That means, heuristically speaking, that the method and system lift the recommendation task to the level of technical attributes to overcome the sparsity problem caused by item sets that are not overlapping between user groups. Thus, when matching similar users, the method does not rely on users configuring exactly the same modules but rather on configured modules that are similar from a technical point of view.

Abstract: An initially trained machine learning model is used by an active learning module to generate candidate triples, which are fed into an expert system for verification. As a result, the expert system outputs novel facts that are used for retraining the machine learning model. This approach consolidates expert systems with machine learning through iterations of an active learning loop, by bringing the two paradigms together, which is in general difficult because training of a neural network (machine learning) requires differentiable functions and rules (used by expert systems) tend not to be differentiable. The method and system provide a data augmentation strategy where the expert system acts as an oracle and outputs the novel facts, which provide labels for the candidate triples. The novel facts provide critical information from the oracle that is injected into the machine learning model at the retraining stage, thus allowing to increase its generalization performance.

Abstract: An initial sequence representing a partially configured engineering project is processed by a recurrent neural network to generate recommendations being a sequence of complementary items that completes an engineering project. A feature predictor component computes a set of features for each recommendation. A bisection component selects a feature from the sets of features that distinguishes some of the recommendations and forms pruned recommendations by choosing all instances from the recommendations that have the selected feature. A user interface displays the selected feature, detects a user interaction indicating that the selected feature is required, outputs the pruned recommendations. The engineering project is completed by combining the initial sequence with the chosen pruned recommendation. As a result, a user is supported in choosing optimal modules, as the selected feature can distinguish the recommendations that have the desired technical properties or target system KPI.

Abstract: A computer-implemented method and system for assigning at least one query triplet to at least one respective class. The at least one respective class is true or false. The method includes the steps of providing the at least one query triplet and a knowledge graph with a plurality of triples and extracting at least one affirmative argument using reinforcement learning on the basis of the at least one query triplet and the knowledge graph. The at least one affirmative argument indicates that the at least one query triplet is true. The method further includes extracting at least one opposing argument using reinforcement learning on the basis of the at least one query triplet and the knowledge graph. The at least one opposing argument indicates that the at least one query triplet is false. The method further includes assigning the at least one query triplet to the at least one respective class using supervised machine learning depending on the at least two arguments.

Abstract: A computer-implemented method for generating an adapted task graph, including the steps of providing a first input data set with at least one task graph and at least one task context and/or a second input data set with at least one constraint and at least one task context, generating an adapted task graph using a trained neural network based on the first input data set and/or the second input data set, and providing the adapted task graph.

Abstract: Provided is a recommendation engine to provide automatically recommendations for the completion of an engineering project, the recommendation engine including: a first artificial intelligence, AI, module adapted to provide latent representations of a sequence of selected items; and a second artificial intelligence, AI, module adapted to process the latent representations of the sequence of selected items provided by the first artificial intelligence, AI, module to generate at least one sequence of complementary items required to complement the sequence of selected items to provide a complete sequence of items output via an interface as a recommendation to complete the engineering project.

Abstract: The invention is directed to a computer-implemented method for determining at least one completed item of at least one product solution, comprising the steps of: a. Providing at least one input data set with at least one partial item of the at least one product solution; wherein b. the at least one partial item comprises at least one initial feature; c. Complementing the at least one partial item of the at least one product solution with at least one additional alternative feature using a trained machine learning model on the basis of at least one partial item of the at least one product solution to determine a plurality of alternative complete items of the at least one product solution; and d. Determining at least one evaluated complete item of the plurality of alternative items of the at least one product solution as output data set using a market impact evaluation. Further, the invention relates to a corresponding computer program product and system.

Abstract: Provided is an assistance apparatus for localizing errors in a monitored technical system consisting of devices and/or transmission lines, including at least one processor configured to obtain values of actual attributes of the devices and/or of the transmission lines, determine an error probability for each device and/or transmission line by processing a graph neural network with the obtained actual values of attributes as input, wherein the graph neural network is trained by training attributes assigned to an attributed graph representation of the technical system, and output an indication for such devices and/or transmission lines, whose error probability is higher than a predefined threshold.

Abstract: A computer-implemented method for efficient processing of pooled data shared by users of a cloud platform, the method includes the steps of uploading at least one dataset by a client device of a user to said cloud platform; calculating similarity scores indicating a degree of similarity between the current uploaded dataset and datasets previously uploaded by client devices of other users; and performing a procedure selected by a user on the cloud platform based on pooled data including the current dataset of the respective user and the datasets previously uploaded from client devices of other users stored in a database of the cloud platform having calculated similarity scores in relation to the current uploaded dataset of the respective user exceeding a configurable similarity score threshold, is provided.

Abstract: Provided is a computer-implemented method and platform for context aware sorting of items available for configuration of a system during a selection session, the method including the steps of providing a numerical input vector, V, representing items selected in a current selection session as context; calculating a compressed vector, Vcomp, from the numerical input vector, V, using an artificial neural network, ANN, adapted to capture non-linear dependencies between items; multiplying the compressed vector, Vcomp, with a weight matrix, EI, derived from a factor matrix, E, obtained as a result of a tensor factorization of a stored relationship tensor, Tr, representing relations, r, between selections of items performed in historical selection sessions, available items and their attributes to compute an output score vector, S; and sorting automatically the available items for selection in the current selection session according to relevance scores of the computed output score vector, S.

Abstract: A plurality of basic simulations independent of one another are carried out, which determine respective remaining service life predictions for the machine. The remaining service life predictions and characteristic data are fed to a neural network, which outputs weights for the remaining service life predictions. A final prediction is calculated from the remaining service life predictions by weighting the remaining service life predictions relative to one another. A hybrid model is produced, which results from the combination of the basic simulations with the neural network. The remaining service life can be predicted not only for a small number of machines for which a specific simulation model has been manually created. The hybrid model enables condition monitoring for any further types and configurations of machines that merely belong to the same machine class. The basic simulations can therefore also be applied to previously unknown machines.

Abstract: A plurality of basic simulations independent of one another are carried out, which determine respective remaining service life predictions for the machine. The remaining service life predictions and characteristic data are fed to a neural network, which outputs weights for the remaining service life predictions. A final prediction is calculated from the remaining service life predictions by weighting the remaining service life predictions relative to one another. A hybrid model is produced, which results from the combination of the basic simulations with the neural network. The remaining service life can be predicted not only for a small number of machines for which a specific simulation model has been manually created. The hybrid model enables condition monitoring for any further types and configurations of machines that merely belong to the same machine class. The basic simulations can therefore also be applied to previously unknown machines.