Patents by Inventor Fabian Moerchen

Fabian Moerchen 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: 10937413
    Abstract: Techniques are provided for training a target language model based at least in part on data associated with a reference language model. For example, language data utilized to train an English language model may be translated and provided as training data to train a German language model to recognize utterances provided in German. By utilizing the techniques herein, the efficiency of training a new language model may be improved due at least in part to replacing labor-intensive operations conventionally performed by specialized personnel with machine-generated data. Additionally, techniques discussed herein provide for reducing the time required for training a new language model by leveraging information associated with utterances of one language to train the new language model associated with a different language.
    Type: Grant
    Filed: September 24, 2018
    Date of Patent: March 2, 2021
    Assignee: Amazon Technologies, Inc.
    Inventors: Jonathan B. Feinstein, Alok Verma, Amina Shabbeer, Brandon Scott Durham, Catherine Breslin, Edward Bueche, Fabian Moerchen, Fabian Triefenbach, Klaus Reiter, Toby R. Latin-Stoermer, Panagiota Karanasou, Judith Gaspers
  • Patent number: 10854189
    Abstract: Techniques are provided for training a language recognition model. For example, a language recognition model may be maintained and associated with a reference language (e.g., English). The language recognition model may be configured to accept as input an utterance in the reference language and to identify a feature to be executed in response to receiving the utterance. New language data (e.g., other utterances) provided in a different language (e.g., German) may be obtained. This new language data may be translated to English and utilized to retrain the model to recognize reference language data as well as language data translated to the reference language. Subsequent utterances (e.g., English utterances, or German utterances translated to English) may be provided to the updated model and a feature may be identified. One or more instructions may be sent to a user device to execute a set of instructions associated with the feature.
    Type: Grant
    Filed: September 24, 2018
    Date of Patent: December 1, 2020
    Assignee: Amazon Technologies, Inc.
    Inventors: Jonathan B. Feinstein, Alok Verma, Amina Shabbeer, Brandon Scott Durham, Catherine Breslin, Edward Bueche, Fabian Moerchen, Fabian Triefenbach, Klaus Reiter, Toby R. Latin-Stoermer, Panagiota Karanasou, Judith Gaspers
  • Publication number: 20200098352
    Abstract: Techniques are provided for training a target language model based at least in part on data associated with a reference language model. For example, language data utilized to train an English language model may be translated and provided as training data to train a German language model to recognize utterances provided in German. By utilizing the techniques herein, the efficiency of training a new language model may be improved due at least in part to replacing labor-intensive operations conventionally performed by specialized personnel with machine-generated data. Additionally, techniques discussed herein provide for reducing the time required for training a new language model by leveraging information associated with utterances of one language to train the new language model associated with a different language.
    Type: Application
    Filed: September 24, 2018
    Publication date: March 26, 2020
    Inventors: Jonathan B. Feinstein, Alok Verma, Amina Shabbeer, Brandon Scott Durham, Catherine Breslin, Edward Bueche, Fabian Moerchen, Fabian Triefenbach, Klaus Reiter, Toby R. Latin-Stoermer, Panagiota Karanasou, Judith Gaspers
  • Publication number: 20200098351
    Abstract: Techniques are provided for training a language recognition model. For example, a language recognition model may be maintained and associated with a reference language (e.g., English). The language recognition model may be configured to accept as input an utterance in the reference language and to identify a feature to be executed in response to receiving the utterance. New language data (e.g., other utterances) provided in a different language (e.g., German) may be obtained. This new language data may be translated to English and utilized to retrain the model to recognize reference language data as well as language data translated to the reference language. Subsequent utterances (e.g., English utterances, or German utterances translated to English) may be provided to the updated model and a feature may be identified. One or more instructions may be sent to a user device to execute a set of instructions associated with the feature.
    Type: Application
    Filed: September 24, 2018
    Publication date: March 26, 2020
    Inventors: Jonathan B. Feinstein, Alok Verma, Amina Shabbeer, Brandon Scott Durham, Catherine Breslin, Edward Bueche, Fabian Moerchen, Fabian Triefenbach, Klaus Reiter, Toby R. Latin-Stoermer, Panagiota Karanasou, Judith Gaspers
  • Patent number: 10579928
    Abstract: A method of building a model for predicting failure of a machine, including parsing (41) daily machine event logs of one or more machines to extract data for a plurality of features, parsing (42) service notifications for the one or more machine to extract failure information data, creating (43) bags from the daily machine event log data and failure information data for multiple instance learning by grouping daily event log data into the bags based on a predetermined predictive interval, labeling each bag with a with a known failure as positive, and bags without known failures as negative, where a bag is a set of feature vectors and an associated label, where each feature vector is an n-tuple of features, transforming (44) the multiple instance learning bags into a standard classification task form, selecting (45) a subset of features from the plurality of features, and training (46) a failure prediction model using the selected subset of features.
    Type: Grant
    Filed: September 16, 2013
    Date of Patent: March 3, 2020
    Assignee: Siemens Aktiengesellschaft
    Inventors: Zhuang Wang, Fabian Moerchen, Dmitriy Fradkin
  • Patent number: 10163451
    Abstract: Techniques for accent translation are described herein. A plurality of audio samples may be received, and each of the plurality of audio samples may be associated with at least one of a plurality of accents. Audio samples associated with at least a first accent of the plurality of accents may be compared to audio samples associated with at least one other accent of the plurality of accents. A translation model between the first accent and a second accent may be generated. An input audio portion in a first spoken language may be received. It may be determined whether the input audio portion is substantially associated with the first accent, and if so, an output audio portion substantially associated with the second accent in the first spoken language may be outputted based, at least in part, on the translation model.
    Type: Grant
    Filed: December 21, 2016
    Date of Patent: December 25, 2018
    Assignee: Amazon Technologies, Inc.
    Inventors: Leo Parker Dirac, Fabian Moerchen, Edo Liberty
  • Patent number: 10162697
    Abstract: A method to build a failure predictive model includes: receiving an input of a set of event sequences, where each sequence is labeled as representing a failure or not representing a failure, extracting a single predictive closed pattern from among the input sequences that represents a failure, creating a root node with the single closed pattern, splitting the set of event sequences into a first set that includes the single closed pattern and a second set that excludes the single pattern, and processing each of the first and second sets until at least one child node is created that is labeled as either representing a failure or not representing a failure.
    Type: Grant
    Filed: July 23, 2013
    Date of Patent: December 25, 2018
    Assignee: Siemens Aktiengesellschaft
    Inventors: Dmitriy Fradkin, Fabian Moerchen
  • Publication number: 20180174595
    Abstract: Techniques for accent translation are described herein. A plurality of audio samples may be received, and each of the plurality of audio samples may be associated with at least one of a plurality of accents. Audio samples associated with at least a first accent of the plurality of accents may be compared to audio samples associated with at least one other accent of the plurality of accents. A translation model between the first accent and a second accent may be generated. An input audio portion in a first spoken language may be received. It may be determined whether the input audio portion is substantially associated with the first accent, and if so, an output audio portion substantially associated with the second accent in the first spoken language may be outputted based, at least in part, on the translation model.
    Type: Application
    Filed: December 21, 2016
    Publication date: June 21, 2018
    Inventors: Leo Parker Dirac, Fabian Moerchen, Edo Liberty
  • Publication number: 20150309854
    Abstract: A method to build a failure predictive model includes: receiving an input of a set of event sequences, where each sequence is labeled as representing a failure or not representing a failure, extracting a single predictive closed pattern from among the input sequences that represents a failure, creating a root node with the single closed pattern, splitting the set of event sequences into a first set that includes the single closed pattern and a second set that excludes the single pattern, and processing each of the first and second sets until at least one child node is created that is labeled as either representing a failure or not representing a failure.
    Type: Application
    Filed: July 23, 2013
    Publication date: October 29, 2015
    Inventors: Dmitriy FRADKIN, Fabian MOERCHEN
  • Publication number: 20150227838
    Abstract: A method of building a model for predicting failure of a machine, including parsing (41) daily machine event logs of one or more machines to extract data for a plurality of features, parsing (42) service notifications for the one or more machine to extract failure information data, creating (43) bags from the daily machine event log data and failure information data for multiple instance learning by grouping daily event log data into the bags based on a predetermined predictive interval, labeling each bag with a with a known failure as positive, and bags without known failures as negative, where a bag is a set of feature vectors and an associated label, where each feature vector is an n-tuple of features, transforming (44) the multiple instance learning bags into a standard classification task form, selecting (45) a subset of features from the plurality of features, and training (46) a failure prediction model using the selected subset of features.
    Type: Application
    Filed: September 16, 2013
    Publication date: August 13, 2015
    Applicant: Siemens Corporation
    Inventors: Zhuang WANG, Fabian MOERCHEN, Dmitriy FRADKIN
  • Patent number: 9026550
    Abstract: A method for identifying a plurality of patterns of events from within event log file data includes receiving a query comprising a plurality of patterns, each of the patterns comprising a plurality of events. One or more key events is determined from the plurality of patterns of events. The one or more key events is located within a database of stored event log file data. An event stream comprising the key events and all other events of the event log file data occurring within a predetermined time span from the time of the located one or more events is generated. Each of the plurality of patterns of the received query are searched for from within the event stream.
    Type: Grant
    Filed: January 9, 2013
    Date of Patent: May 5, 2015
    Assignee: Siemens Aktiengesellschaft
    Inventors: Dmitriy Fradkin, Fabian Moerchen
  • Patent number: 9020874
    Abstract: In a support vector regression approach to forecasting power load in an electrical grid, a feature learning scheme weights each feature in the input data with its correlation with the predicted load, increasing the prediction accuracy. The kernel matrix for the input training data is computed such that features that align better with the target variable are given greater weight. The resulting load forecast may be used to compute commands sent to demand response modules.
    Type: Grant
    Filed: October 26, 2012
    Date of Patent: April 28, 2015
    Assignee: Siemens Aktiengesellschaft
    Inventors: Kai Zhang, Fabian Moerchen, Amit Chakraborty
  • Patent number: 8645311
    Abstract: Systems and methods for determining critical thresholds on a number of events (k) and a window length (t) for properly defining a burst of events in a data stream. A new coverage metric Ck,t is defined and used in the determination, where the coverage metric Ck,t is defined for a particular pair (k,t) as a fraction, with the numerator defined a number of events that occur within some (k,t)-bursty window and the denominator defined as the total number of events (n) that occurred along the entire time span being analyzed. Coverage metric Ck,t is monotonic non-increasing in k and monotonic non-decreasing in t, allowing for a divide-and-conquer search strategy to be used to find the critical threshold pairs (k*, t*).
    Type: Grant
    Filed: November 1, 2011
    Date of Patent: February 4, 2014
    Assignee: Siemens Aktiengesellschaft
    Inventors: Bibudh Lahiri, Fabian Moerchen, Ioannis Akrotirianakis
  • Patent number: 8527251
    Abstract: A method and system for generating a patient specific anatomical heart model is disclosed. Volumetric image data, such as computed tomography (CT), echocardiography, or magnetic resonance (MR) image data of a patient's cardiac region is received. Individual models for multiple heart components, such as the left ventricle (LV) endocardium, LV epicardium, right ventricle (RV), left atrium (LA), right atrium (RA), mitral valve, aortic valve, aorta, and pulmonary trunk, are estimated in said volumetric cardiac image data. A multi-component patient specific anatomical heart model is generated by integrating the individual models for each of the heart components. Fluid Structure Interaction (FSI) simulations are performed on the patient specific anatomical model, and patient specific clinical parameters are extracted based on the patient specific heart model and the FSI simulations. Disease progression modeling and risk stratification are performed based on the patient specific clinical parameters.
    Type: Grant
    Filed: April 30, 2010
    Date of Patent: September 3, 2013
    Assignee: Siemens Aktiengesellschaft
    Inventors: Razvan Ioan Ionasec, Puneet Sharma, Bogdan Georgescu, Andrey Torzhkov, Fabian Moerchen, Gayle M. Wittenberg, Dmitriy Fradkin, Dorin Comaniciu
  • Publication number: 20130198227
    Abstract: A method for identifying a plurality of patterns of events from within event log file data includes receiving a query comprising a plurality of patterns, each of the patterns comprising a plurality of events. One or more key events is determined from the plurality of patterns of events. The one or more key events is located within a database of stored event log file data. An event stream comprising the key events and all other events of the event log file data occurring within a predetermined time span from the time of the located one or more events is generated. Each of the plurality of patterns of the received query are searched for from within the event stream.
    Type: Application
    Filed: January 9, 2013
    Publication date: August 1, 2013
    Applicant: Siemens Corporation
    Inventors: Dmitriy Fradkin, Fabian Moerchen
  • Patent number: 8423493
    Abstract: An approach is provided for condition monitoring from log messages and sensor trends based on time semi-intervals. The approach may be applied to machine condition monitoring. Patterns are mined from symbolic interval data that extends previous approaches by allowing semi-intervals and partially ordered patterns. The semi-interval patterns and semi-interval partial order patterns are less restrictive than patterns using Allen's relations. Combinations and adaptations of efficient algorithms from sequential pattern and itemset mining for discovery of semi-interval patterns are described.
    Type: Grant
    Filed: April 8, 2010
    Date of Patent: April 16, 2013
    Assignee: Siemens Corporation
    Inventors: Fabian Moerchen, Dmitriy Fradkin
  • Publication number: 20120246109
    Abstract: Systems and methods for determining critical thresholds on a number of events (k) and a window length (t) for properly defining a burst of events in a data stream. A new coverage metric Ck,t is defined and used in the determination, where the coverage metric Ck,t is defined for a particular pair (k,t) as a fraction, with the numerator defined a number of events that occur within some (k,t)-bursty window and the denominator defined as the total number of events (n) that occurred along the entire time span being analyzed. Coverage metric Ck,t is monotonic non-increasing in k and monotonic non-decreasing in t, allowing for a divide-and-conquer search strategy to be used to find the critical threshold pairs (k*, t*).
    Type: Application
    Filed: November 1, 2011
    Publication date: September 27, 2012
    Applicant: Siemens Corporation
    Inventors: Bibudh Lahiri, Fabian Moerchen, Ioannis Akrotirianakis
  • Publication number: 20100332540
    Abstract: An approach is provided for condition monitoring from log messages and sensor trends based on time semi-intervals. The approach may be applied to machine condition monitoring. Patterns are mined from symbolic interval data that extends previous approaches by allowing semi-intervals and partially ordered patterns. The semi-interval patterns and semi-interval partial order patterns are less restrictive than patterns using Allen's relations. Combinations and adaptations of efficient algorithms from sequential pattern and itemset mining for discovery of semi-interval patterns are described.
    Type: Application
    Filed: April 8, 2010
    Publication date: December 30, 2010
    Applicant: Siemens Corporation
    Inventors: Fabian Moerchen, Dmitriy Fradkin
  • Publication number: 20100280352
    Abstract: A method and system for generating a patient specific anatomical heart model is disclosed. Volumetric image data, such as computed tomography (CT), echocardiography, or magnetic resonance (MR) image data of a patient's cardiac region is received. Individual models for multiple heart components, such as the left ventricle (LV) endocardium, LV epicardium, right ventricle (RV), left atrium (LA), right atrium (RA), mitral valve, aortic valve, aorta, and pulmonary trunk, are estimated in said volumetric cardiac image data. A multi-component patient specific anatomical heart model is generated by integrating the individual models for each of the heart components. Fluid Structure Interaction (FSI) simulations are performed on the patient specific anatomical model, and patient specific clinical parameters are extracted based on the patient specific heart model and the FSI simulations. Disease progression modeling and risk stratification are performed based on the patient specific clinical parameters.
    Type: Application
    Filed: April 30, 2010
    Publication date: November 4, 2010
    Applicant: Siemens Corporation
    Inventors: Razvan Ioan Ionasec, Puneet Sharma, Bogdan Georgescu, Andrey Torzhkov, Fabian Moerchen, Gayle M. Wittenberg, Dmitriy Fradkin, Dorin Comaniciu
  • Patent number: 7809718
    Abstract: Documents in a high density data stream are clustered. Incoming documents are analyzed to find metadata, such as words in a documents headline or abstract and people, places, and organizations discussed in the document. The metadata is emphasized as compared to other words found in the document. A single feature vector for each document determined based on the emphasized metadata will accordingly take into account the importance of such words and clustering efficacy and efficiency are improved.
    Type: Grant
    Filed: January 15, 2008
    Date of Patent: October 5, 2010
    Assignee: Siemens Corporation
    Inventors: Klaus Brinker, Fabian Moerchen