Patents by Inventor Imre Attila Kiss
Imre Attila Kiss 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).
-
Publication number: 20220148590Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.Type: ApplicationFiled: November 12, 2021Publication date: May 12, 2022Inventors: Lambert Mathias, Ying Shi, Imre Attila Kiss, Ryan Paul Thomas, Frederic Johan Georges Deramat
-
Patent number: 11307885Abstract: Techniques for a service provider network to generate suitability scores that indicate how well VM instance types are performing given the workloads they are running. Using these suitability scores, users are able to easily determine the suitability of VM instance types for supporting their workloads, and diagnose potential issues with the pairings of VM instance types and workloads, such as over-utilization and under-utilization of VM instances. Further, the techniques include training a model to determine VM instance types recommended for supporting workloads. The model may receive utilization data representing resource-usage characteristics of the workload as input, and be trained to output one or more recommended VM instance types that are optimized or suitable to host the workload. Thus, the service provider network may provide users with easily-digestible suitability scores indicating the suitability of VM instance types for workloads along with VM instance types recommended for their workloads.Type: GrantFiled: September 19, 2019Date of Patent: April 19, 2022Assignee: Amazon Technologies, Inc.Inventors: Lorenzo Luciano, Peter William Beardshear, Imre Attila Kiss, Esther Kadosh
-
Patent number: 11189277Abstract: In speech processing systems personalization is added in the Natural Language Understanding (NLU) processor by incorporating external knowledge sources of user information to improve entity recognition performance of the speech processing system. Personalization in the NLU is effected by incorporating one or more dictionaries of entries, or gazetteers, with information personal to a respective user, that provide the user's information to permit disambiguation of semantic interpretation for input utterances to improve quality of speech processing results.Type: GrantFiled: February 13, 2019Date of Patent: November 30, 2021Assignee: Amazon Technologies, Inc.Inventors: Imre Attila Kiss, Arthur Richard Toth, Lambert Mathias
-
Patent number: 11176936Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.Type: GrantFiled: May 1, 2019Date of Patent: November 16, 2021Assignee: Amazon Technologies, Inc.Inventors: Lambert Mathias, Ying Shi, Imre Attila Kiss, Ryan Paul Thomas, Frederic Johan Georges Deramat
-
Patent number: 10970123Abstract: Techniques for a service provider network to generate suitability scores that indicate how well VM instance types are performing given the workloads they are running. Using these suitability scores, users are able to easily determine the suitability of VM instance types for supporting their workloads, and diagnose potential issues with the pairings of VM instance types and workloads, such as over-utilization and under-utilization of VM instances. Further, the techniques include training a model to determine VM instance types recommended for supporting workloads. The model may receive utilization data representing resource-usage characteristics of the workload as input, and be trained to output one or more recommended VM instance types that are optimized or suitable to host the workload. Thus, the service provider network may provide users with easily-digestible suitability scores indicating the suitability of VM instance types for workloads along with VM instance types recommended for their workloads.Type: GrantFiled: September 19, 2019Date of Patent: April 6, 2021Assignee: Amazon Technologies, Inc.Inventors: Lorenzo Luciano, Imre Attila Kiss, Esther Kadosh, Peter William Beardshear
-
Publication number: 20190325873Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.Type: ApplicationFiled: May 1, 2019Publication date: October 24, 2019Inventors: Lambert Mathias, Ying Shi, Imre Attila Kiss, Ryan Paul Thomas, Frederic Johan Georges Deramat
-
Patent number: 10453117Abstract: A system capable of performing natural language understanding (NLU) using different application domains in parallel. A model takes incoming query text and determines a list of potential supplemental intent categories corresponding to the text. Supplemental applications within those categories are then identified as likely candidates for responding to the query. Application specific domains, including NLU components for the particular supplemental applications, are then activated and process the query text in parallel. Further, certain system default domains may also process incoming queries substantially in parallel with the supplemental applications. The different results are scored and ranked to determine highest scoring NLU results.Type: GrantFiled: June 29, 2016Date of Patent: October 22, 2019Assignee: AMAZON TECHNOLOGIES, INC.Inventors: Simon Peter Reavely, Rohit Prasad, Imre Attila Kiss, Manoj Sindhwani
-
Publication number: 20190318737Abstract: In speech processing systems personalization is added in the Natural Language Understanding (NLU) processor by incorporating external knowledge sources of user information to improve entity recognition performance of the speech processing system. Personalization in the NLU is effected by incorporating one or more dictionaries of entries, or gazetteers, with information personal to a respective user, that provide the user's information to permit disambiguation of semantic interpretation for input utterances to improve quality of speech processing results.Type: ApplicationFiled: February 13, 2019Publication date: October 17, 2019Inventors: Imre Attila Kiss, Arthur Richard Toth, Lambert Mathias
-
Patent number: 10283119Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.Type: GrantFiled: April 30, 2018Date of Patent: May 7, 2019Assignee: Amazon Technologies, Inc.Inventors: Lambert Mathias, Ying Shi, Imre Attila Kiss, Ryan Paul Thomas, Frederic Johan Georges Deramat
-
Patent number: 10224030Abstract: In speech processing systems personalization is added in the Natural Language Understanding (NLU) processor by incorporating external knowledge sources of user information to improve entity recognition performance of the speech processing system. Personalization in the NLU is effected by incorporating one or more dictionaries of entries, or gazetteers, with information personal to a respective user, that provide the user's information to permit disambiguation of semantic interpretation for input utterances to improve quality of speech processing results.Type: GrantFiled: March 14, 2013Date of Patent: March 5, 2019Assignee: AMAZON TECHNOLOGIES, INC.Inventors: Imre Attila Kiss, Arthur Richard Toth, Lambert Mathias
-
Patent number: 10140581Abstract: Features are disclosed for generating models, such as conditional random field (“CRF”) models, that consume less storage space and/or transmission bandwidth than conventional models. In some embodiments, the generated CRF models are composed of fewer or alternate components in comparison with conventional CRF models. For example, a system generating such CRF models may forgo the use of large dictionaries or other cross-reference lists that map information extracted from input (e.g., “features”) to model parameters; reduce in weight (or exclude altogether) certain model parameters that may not have a significant effect on model accuracy; and/or reduce the numerical precision of model parameters.Type: GrantFiled: December 22, 2014Date of Patent: November 27, 2018Assignee: Amazon Technologies, Inc.Inventors: Imre Attila Kiss, Wei Chen, Anjishnu Kumar
-
Publication number: 20180315425Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.Type: ApplicationFiled: April 30, 2018Publication date: November 1, 2018Inventors: Lambert Mathias, Ying Shi, Imre Attila Kiss, Ryan Paul Thomas, Frederic Johan Georges Deramat
-
Patent number: 10102851Abstract: Incremental speech recognition results are generated and used to determine a user's intent from an utterance. Utterance audio data may be partitioned into multiple portions, and incremental speech recognition results may be generated from one or more of the portions. A natural language understanding module or some other language processing module can generate semantic representations of the utterance from the incremental speech recognition results. Stability of the determined intent may be determined over the course of time, and actions may be taken in response to meeting certain stability thresholds.Type: GrantFiled: August 28, 2013Date of Patent: October 16, 2018Assignee: Amazon Technologies, Inc.Inventors: Imre Attila Kiss, Hugh Evan Secker-Walker
-
Patent number: 9959869Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.Type: GrantFiled: September 4, 2017Date of Patent: May 1, 2018Assignee: Amazon Technologies, Inc.Inventors: Lambert Mathias, Ying Shi, Imre Attila Kiss, Ryan Paul Thomas, Frederic Johan Georges Deramat
-
Publication number: 20180012597Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.Type: ApplicationFiled: September 4, 2017Publication date: January 11, 2018Inventors: Lambert Mathias., Ying Shi., Imre Attila Kiss., Ryan Paul Thomas., Frederic Johan Georges Deramat.
-
Patent number: 9754589Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.Type: GrantFiled: September 2, 2016Date of Patent: September 5, 2017Assignee: Amazon Technologies, Inc.Inventors: Lambert Mathias, Ying Shi, Imre Attila Kiss, Ryan Paul Thomas, Frederic Johan Georges Deramat
-
Publication number: 20170116985Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.Type: ApplicationFiled: September 2, 2016Publication date: April 27, 2017Inventors: Lambert Mathias, Ying Shi, Imre Attila Kiss, Ryan Paul Thomas, Frederic Johan Georges Deramat
-
Patent number: 9436678Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.Type: GrantFiled: June 29, 2015Date of Patent: September 6, 2016Assignee: Amazon Technologies, Inc.Inventors: Lambert Mathias, Ying Shi, Imre Attila Kiss, Ryan Paul Thomas, Frederic Johan Georges Deramat
-
Patent number: 9190055Abstract: Features are disclosed for generating and using personalized named entity recognition models. A personalized model can be trained for a particular user, and then interpolated with a general model for use in named entity recognition. In some embodiments, a model may be trained for a group of users, where the users share some similarity relevant to language processing. In some embodiments, various base models may be trained so as to provide better accuracy for certain types of language input than a general model. Users may be associated with any number of base models, and the associated based models may then be interpolated for use in named entity recognition on input from the corresponding user.Type: GrantFiled: March 14, 2013Date of Patent: November 17, 2015Assignee: Amazon Technologies, Inc.Inventors: Imre Attila Kiss, Lambert Mathias, Jeffrey Penrod Adams
-
Publication number: 20150302002Abstract: Features are disclosed for processing a user utterance with respect to multiple subject matters or domains, and for selecting a likely result from a particular domain with which to respond to the utterance or otherwise take action. A user utterance may be transcribed by an automatic speech recognition (“ASR”) module, and the results may be provided to a multi-domain natural language understanding (“NLU”) engine. The multi-domain NLU engine may process the transcription(s) in multiple individual domains rather than in a single domain. In some cases, the transcription(s) may be processed in multiple individual domains in parallel or substantially simultaneously. In addition, hints may be generated based on previous user interactions and other data. The ASR module, multi-domain NLU engine, and other components of a spoken language processing system may use the hints to more efficiently process input or more accurately generate output.Type: ApplicationFiled: June 29, 2015Publication date: October 22, 2015Inventors: Lambert Mathias, Ying Shi, Imre Attila Kiss, Ryan Paul Thomas, Frederic Johan Georges Deramat