Patents by Inventor Jaakob Kind

Jaakob Kind has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 10915391
    Abstract: Some embodiments include reception of a time-series of a respective data value generated by each of a plurality of sensors, calculation of a regression associated with a first sensor of the plurality of sensors based on the received plurality of time-series, the regression being a function of the respective data values of the others of the plurality of data sources, reception of respective data values associated with a time from and generated by each the plurality of respective sensors, determination of a predicted value associated with the time for the first sensor based on the regression associated with the first sensor and on the respective data values associated with the time, comparison of the predicted value with the received value associated with the time and generated by the first sensor, and determination of a value indicating a likelihood of an anomaly based on the comparison.
    Type: Grant
    Filed: June 27, 2019
    Date of Patent: February 9, 2021
    Assignee: SAP SE
    Inventors: Robert Meusel, Jaakob Kind, Atreju Florian Tauschinsky, Janick Frasch, Minji Lee, Michael Otto
  • Patent number: 10824498
    Abstract: A method for multimodal failure analysis is provided herein. A multimodal failure analysis request may be received. An asset type may be determined based on the multimodal failure analysis request. Asset records for the asset type may be obtained. The asset records may include data on asset failures across multiple failure modes. A multimodal failure analytical model may be executed based on the asset records. Executing the multimodal failure analytical model may include calculating a distribution of failure intervals over time, probabilities of failure respectively associated with the failure intervals, and intervention scores respectively associated with the failure intervals. An intervention interval and an intervention score associated with the intervention interval may be selected based on the associated probabilities of failure. The selected intervention interval and intervention score may be provided in response to the multimodal failure analysis request.
    Type: Grant
    Filed: December 14, 2018
    Date of Patent: November 3, 2020
    Assignee: SAP SE
    Inventors: Jaakob Kind, Uta Maria Loesch, Atreju Florian Tauschinsky
  • Publication number: 20200192737
    Abstract: A method for multimodal failure analysis is provided herein. A multimodal failure analysis request may be received. An asset type may be determined based on the multimodal failure analysis request. Asset records for the asset type may be obtained. The asset records may include data on asset failures across multiple failure modes. A multimodal failure analytical model may be executed based on the asset records. Executing the multimodal failure analytical model may include calculating a distribution of failure intervals over time, probabilities of failure respectively associated with the failure intervals, and intervention scores respectively associated with the failure intervals. An intervention interval and an intervention score associated with the intervention interval may be selected based on the associated probabilities of failure. The selected intervention interval and intervention score may be provided in response to the multimodal failure analysis request.
    Type: Application
    Filed: December 14, 2018
    Publication date: June 18, 2020
    Applicant: SAP SE
    Inventors: Jaakob Kind, Uta Maria Loesch, Atreju Florian Tauschinsky
  • Publication number: 20190317848
    Abstract: Some embodiments include reception of a time-series of a respective data value generated by each of a plurality of sensors, calculation of a regression associated with a first sensor of the plurality of sensors based on the received plurality of time-series, the regression being a function of the respective data values of the others of the plurality of data sources, reception of respective data values associated with a time from and generated by each the plurality of respective sensors, determination of a predicted value associated with the time for the first sensor based on the regression associated with the first sensor and on the respective data values associated with the time, comparison of the predicted value with the received value associated with the time and generated by the first sensor, and determination of a value indicating a likelihood of an anomaly based on the comparison.
    Type: Application
    Filed: June 27, 2019
    Publication date: October 17, 2019
    Inventors: Robert Meusel, Jaakob Kind, Atreju Florian Tauschinsky, Janick Frasch, Minji Lee, Michael Otto
  • Patent number: 10379933
    Abstract: Some embodiments include reception of a time-series of a respective data value generated by each of a plurality of sensors, calculation of a regression associated with a first sensor of the plurality of sensors based on the received plurality of time-series, the regression being a function of the respective data values of the others of the plurality of data sources, reception of respective data values associated with a time from and generated by each the plurality of respective sensors, determination of a predicted value associated with the time for the first sensor based on the regression associated with the first sensor and on the respective data values associated with the time, comparison of the predicted value with the received value associated with the time and generated by the first sensor, and determination of a value indicating a likelihood of an anomaly based on the comparison.
    Type: Grant
    Filed: March 20, 2017
    Date of Patent: August 13, 2019
    Assignee: SAP SE
    Inventors: Robert Meusel, Jaakob Kind, Atreju Florian Tauschinsky, Janick Frasch, Minji Lee, Michael Otto
  • Publication number: 20180239662
    Abstract: Some embodiments include reception of a time-series of a respective data value generated by each of a plurality of sensors, calculation of a regression associated with a first sensor of the plurality of sensors based on the received plurality of time-series, the regression being a function of the respective data values of the others of the plurality of data sources, reception of respective data values associated with a time from and generated by each the plurality of respective sensors, determination of a predicted value associated with the time for the first sensor based on the regression associated with the first sensor and on the respective data values associated with the time, comparison of the predicted value with the received value associated with the time and generated by the first sensor, and determination of a value indicating a likelihood of an anomaly based on the comparison.
    Type: Application
    Filed: March 20, 2017
    Publication date: August 23, 2018
    Inventors: Robert Meusel, Jaakob Kind, Atreju Florian Tauschinsky, Janick Frasch, Minji Lee, Michael Otto
  • Publication number: 20160146709
    Abstract: A method includes receiving, at computing system, sensor data from a machine, preparing the sensor data for use by data mining algorithms, generating an analysis table based on the prepared sensor data, the analysis table including information and data for a plurality of instances for the machine, and using the information and data included in the analysis table to predict a failure of the machine.
    Type: Application
    Filed: November 21, 2014
    Publication date: May 26, 2016
    Inventors: Satyadeep DEY, Markus DOEHRING, Martin KATO, Jaakob KIND, Gudrun KLOSE, Robert LANG, Uta Maria LOESCH, Christine PREISACH, Christian THEILEMANN
  • Patent number: 8275645
    Abstract: A method and a system for fast recursion check and low-level code generation for directed graph. In a directed graph each vertex is connected to at least one other vertex with a directed edge to form an ordered pair of a source vertex and a target vertex. Low-level codes are assigned to the vertices of the directed graph, where for each ordered pair the low-level code of the target vertex is bigger than the low-level code of the source vertex. A new edge is added to connect a first vertex and a second vertex of the graph, where the first vertex is the source vertex and the second vertex is the target vertex of the new ordered pair. The low-level code of the target vertex of the new ordered pair is not bigger than the low-level code of the source vertex. For the new ordered pair and all ordered pairs that descend from the new ordered pair, the low-level codes of the target nodes are changed to values bigger than the low-level codes of the corresponding source vertices, when necessary.
    Type: Grant
    Filed: December 17, 2008
    Date of Patent: September 25, 2012
    Assignee: SAP AG
    Inventor: Jaakob Kind
  • Publication number: 20110307353
    Abstract: A business object model, which reflects data that is used during a given business transaction, is utilized to generate interfaces. This business object model facilitates commercial transactions by providing consistent interfaces that are suitable for use across industries, across businesses, and across different departments within a business during a business transaction. In some operations, software creates, updates, or otherwise processes information related to a goods tag, a production bill of material hierarchy, and/or a release order template business object.
    Type: Application
    Filed: June 15, 2010
    Publication date: December 15, 2011
    Inventors: Benjamin Ringl, Michael Hartel, Thomas Friedrich, Stefan Moeller, Sabine Seelenmeyer, Martin Schmidt, Frank O. Schulz, Sergio Rozenszajn, Martin J. Wilmes, Thilo Kraehmer, Werner Gnan, Michael Seubert, Jaakob Kind, Anna Kabala, Petra Meyer, Ingo Siebeking, Stefan Siebert, Rainer Tomski, Stephan Hetzer, Jochen Steinbach, Thomas Hammer
  • Patent number: 7894922
    Abstract: Computer-implemented methods, and associated computer program products and systems, are disclosed for generating electronic data for use in planning the execution of a manufacturing process. The methods, generally, are used in the structural transformation of execution-level routings for manufacturing processes into planning-level routings. The methods applies various transformation techniques when a planning-level routing includes alternative paths, and different transformation techniques when a planning-level routing includes parallel paths. Planning modes are created in the case of alternative paths, and parallel paths generally do not cause multiple modes to be created. Parallel and alternative paths in a planning-level operation also has impacts on how the a planned duration formula is determined.
    Type: Grant
    Filed: December 21, 2006
    Date of Patent: February 22, 2011
    Assignee: SAP AG
    Inventors: Jochen Steinbach, Jaakob Kind
  • Publication number: 20100161366
    Abstract: In various implementations, sales orders are received and product requirement specifications is generated based on the sales orders. Planning for the production of the goods occurs based on the product requirement specification and the goods are produced based on the plan.
    Type: Application
    Filed: December 19, 2008
    Publication date: June 24, 2010
    Inventors: Achim Clemens, Bernhard Lokowandt, Thomas John, Michael Segler, Jaakob Kind
  • Publication number: 20100153152
    Abstract: A method and a system for fast recursion check and low-level code generation for directed graph. In a directed graph each vertex is connected to at least one other vertex with a directed edge to form an ordered pair of a source vertex and a target vertex. Low-level codes are assigned to the vertices of the directed graph, where for each ordered pair the low-level code of the target vertex is bigger than the low-level code of the source vertex. A new edge is added to connect a first vertex and a second vertex of the graph, where the first vertex is the source vertex and the second vertex is the target vertex of the new ordered pair. The low-level code of the target vertex of the new ordered pair is not bigger than the low-level code of the source vertex. For the new ordered pair and all ordered pairs that descend from the new ordered pair, the low-level codes of the target nodes are changed to values bigger than the low-level codes of the corresponding source vertices, when necessary.
    Type: Application
    Filed: December 17, 2008
    Publication date: June 17, 2010
    Inventor: Jaakob Kind
  • Patent number: 7617015
    Abstract: Methods, computer program products and systems are disclosed for generating a planned time duration for a manufacturing process operation defined for planning purposes that includes an aggregation of multiple defined execution operations. Electronic information is received that specifies a production demand that requires use of the manufacturing process for fulfillment. A linear approximation is electronically generated of an overall time duration measure for the defined manufacturing process planning operation. The overall time duration measure is a sum of time components comprising at least a calculated measure for a variable time component for the longest of the multiple execution operations for the received production demand, and a fixed time duration measure for one send-ahead quantity for each of the multiple execution operations that is not the longest. The generated overall time duration measure is then returned.
    Type: Grant
    Filed: December 21, 2006
    Date of Patent: November 10, 2009
    Assignee: SAP AG
    Inventors: Jochen Steinbach, Jaakob Kind
  • Patent number: 7551975
    Abstract: Generating data used in planning the execution of a manufacturing process includes consistency checks that are performed on proposed groupings of manufacturing operations to make sure that the groupings are defined in a way that enables the information to be aggregated for use in planning. To do this, defined groupings are received for multiple execution-level manufacturing operations that are defined in a manufacturing process execution-level electronic data model and that define a process flow to produce a product. In one aspect, for each of the defined groupings, it is determined whether the defined grouping includes multiple occurrences of a process step definition that has multiple different defined alternative steps, and if so, the defined groupings are changed so that each defined grouping of the defined groupings has no more than a single occurrence of a process step definition that has multiple different defined alternative steps.
    Type: Grant
    Filed: December 21, 2006
    Date of Patent: June 23, 2009
    Assignee: SAP AG
    Inventors: Jochen Steinbach, Jaakob Kind
  • Publication number: 20080154412
    Abstract: Computer-implemented methods, and associated computer program products and systems, are disclosed for generating electronic data for use in planning the execution of a manufacturing process. The methods, generally, are used in the structural transformation of execution-level routings for manufacturing processes into planning-level routings. The methods applies various transformation techniques when a planning-level routing includes alternative paths, and different transformation techniques when a planning-level routing includes parallel paths. Planning modes are created in the case of alternative paths, and parallel paths generally do not cause multiple modes to be created. Parallel and alternative paths in a planning-level operation also has impacts on how the a planned duration formula is determined.
    Type: Application
    Filed: December 21, 2006
    Publication date: June 26, 2008
    Inventors: Jochen Steinbach, Jaakob Kind
  • Publication number: 20080154411
    Abstract: Generating data used in planning the execution of a manufacturing process includes consistency checks that are performed on proposed groupings of manufacturing operations to make sure that the groupings are defined in a way that enables the information to be aggregated for use in planning. To do this, defined groupings are received for multiple execution-level manufacturing operations that are defined in a manufacturing process execution-level electronic data model and that define a process flow to produce a product. In one aspect, for each of the defined groupings, it is determined whether the defined grouping includes multiple occurrences of a process step definition that has multiple different defined alternative steps, and if so, the defined groupings are changed so that each defined grouping of the defined groupings has no more than a single occurrence of a process step definition that has multiple different defined alternative steps.
    Type: Application
    Filed: December 21, 2006
    Publication date: June 26, 2008
    Inventors: Jochen Steinbach, Jaakob Kind
  • Publication number: 20080154660
    Abstract: Methods, computer program products and systems are disclosed for generating a planned time duration for a manufacturing process operation defined for planning purposes that includes an aggregation of multiple defined execution operations. Electronic information is received that specifies a production demand that requires use of the manufacturing process for fulfillment. A linear approximation is electronically generated of an overall time duration measure for the defined manufacturing process planning operation. The overall time duration measure is a sum of time components comprising at least a calculated measure for a variable time component for the longest of the multiple execution operations for the received production demand, and a fixed time duration measure for one send-ahead quantity for each of the multiple execution operations that is not the longest. The generated overall time duration measure is then returned.
    Type: Application
    Filed: December 21, 2006
    Publication date: June 26, 2008
    Inventors: Jochen Steinbach, Jaakob Kind
  • Publication number: 20080120129
    Abstract: A business object model, which reflects data that is used during a given business transaction, is utilized to generate interfaces. This business object model facilitates commercial transactions by providing consistent interfaces that are suitable for use across industries, across businesses, and across different departments within a business during a business transaction.
    Type: Application
    Filed: May 11, 2007
    Publication date: May 22, 2008
    Inventors: Michael Seubert, Achim Heger, Adam Polly, Alexander Adam, Alexander Zaichenko, Alexandra Mark, Andre Doerfler, Andre Wachholz-Prill, Andre Wagner, Andrea Pluemper, Andreas Bold, Andreas Brossler, Andreas Huppert, Andreas Leukert-Knapp, Andreas Morsch, Andreas Neumann, Andreas Poth, Andreas Reccius, Andreas Wolber, Antje Fuchs, Antonia Gross, Arno Eifel, Artur Butucel, Arunava Banerjee, Ashwin Yeddula, Axel Kuehl, Benjamin Klehr, Bernd Schmitt, Bjoern Eike, Boris Krems, Christian Auth, Christian Fuhlbruegge, Christiane Cramer, Christiane Schauerte, Christopher Engler, Cristina Buchholz, Damian Theil, Daniel Bock, Daniel Zimmermann, Danny Pannicke, Dieter Krisch, Dietmar Nowotny, Dirk Henrich, Dirk Richtsteiger, Dirk Schindewolf, Doris Karbach, Frank Damaschke, Frank Hastrich, Frank Krueger, Frank Lindqvist, Frank Milpetz, Frank Reinemuth, Galina Pacher, Georg Dopf, Georg Podhajsky, Giovanni Deledda, Guimei Zhang, Gunther Liebich, Heike Berger, Hendrik Geipel, Horst Schaude, Ingo Bruss, Ingo Pfitzner, Jaakob Kind, Jan Hrastnik, Jan Richert, Joachim Liebler, Joachim Puteick, Jochen Steinbach, Joerg Goetting, Johannes Bechtold, Julian Schmidt-Kluegmann, Kai-Michael Roesner, Karsten Kimme, Karsten Koetter, Kathrin Nos, Klaus Herter, Klaus Reinelt, Klaus Schlappner, Kristina Grunewald, Levente Sara, Markus Juchem, Martin Gaub, Martin Hermes, Martin Rogge, Martin Schorr, Mathias Schoenecker, Matthias Asal, Matthias Heinrichs, Matthias Schmitt, Michael Bauer, Michael Conrad, Michael Hartel, Michael Jung, Michael Schier, Michael Segler, Michael Sylvester, Naci Kalyoncu, Olaf Meincke, Oliver Grande
  • Publication number: 20050071146
    Abstract: Embodiments of the present invention relate to a method and system for evaluating selection conditions associated with variants of components of a multi-component configurable product for consistency and completeness
    Type: Application
    Filed: September 26, 2003
    Publication date: March 31, 2005
    Inventor: Jaakob Kind