Patents by Inventor Melanie C B Gens

Melanie C B Gens 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: 20250182757
    Abstract: Techniques for enabling access in a multi-assistant speech processing system are described, where a first assistant system may use components of a second assistant system as data processing components. Runtime operational data and user input data related to the first assistant may be kept separate from the processing data and input data related to the second assistant by propagating a first account ID, for user inputs directed to the first assistant, through the processing pipeline, and using a second account for user inputs directed to the second assistant. A mapping between the first account ID and the second account ID may be accessible to a select number of system components. Handoffs between the two assistants are handled in a manner where data related to one assistant is not accessible by the other assistant.
    Type: Application
    Filed: February 6, 2025
    Publication date: June 5, 2025
    Inventors: Ramya Chaganti, Mark Lawrence, Ryan McCrate, Melanie C B Gens, Andrew Smith, Raja Bose, Zexiong Yan, Jyoti Chhabra
  • Patent number: 12254879
    Abstract: Techniques for enabling access in a multi-assistant speech processing system are described, where a first assistant system may use components of a second assistant system as data processing components. Runtime operational data and user input data related to the first assistant may be kept separate from the processing data and input data related to the second assistant by propagating a first account ID, for user inputs directed to the first assistant, through the processing pipeline, and using a second account for user inputs directed to the second assistant. A mapping between the first account ID and the second account ID may be accessible to a select number of system components. Handoffs between the two assistants are handled in a manner where data related to one assistant is not accessible by the other assistant.
    Type: Grant
    Filed: September 26, 2022
    Date of Patent: March 18, 2025
    Assignee: Amazon Technologies, Inc.
    Inventors: Ramya Chaganti, Mark Lawrence, Ryan McCrate, Melanie C B Gens, Andrew Smith, Raja Bose, Zexiong Yan, Jyoti Chhabra
  • Patent number: 12197871
    Abstract: Techniques for evaluating a natural language understanding (NLU) component and determining an action to resolve an issue processing a user input are described. The system determines which component is invoked by a baseline NLU component is processing the user input, and which component is invoked by an updated NLU component. Based on that information, the system selects the action to resolve the updated NLU component generating an undesired response to the user input.
    Type: Grant
    Filed: October 26, 2022
    Date of Patent: January 14, 2025
    Assignee: Amazon Technologies, Inc.
    Inventors: Pavel Bhowmik, Melanie C B Gens, Sachin Midha, Rahul Gupta, Sriram Venkatapathy, Xinhong Zhang, Anoop Kumar, Pooja Sanjay Sonawane, Samuel Harry Ingbar
  • Publication number: 20250006196
    Abstract: Techniques for generating a prompt for a language model to determine an action responsive to a user input, are described. In some embodiments, the system receives a user input, determines one or more application programming interfaces (APIs) configured to perform actions that are relevant to the user input and exemplars representing examples of using the APIs with respect to user inputs similar to the current user input. The system further determines device states of devices that are determined to be related to the user input and also determines other contextual information (e.g., weather information, time of day, geographic location, etc.). The system generates a prompt including the user input, the APIs, the exemplars, the device states, and the other contextual information. A language model processes the prompt to determine an action responsive to the user input and the system causes performance of the action.
    Type: Application
    Filed: June 30, 2023
    Publication date: January 2, 2025
    Inventors: Hann Wang, Angeliki Metallinou, Melanie C B Gens, Arijit Biswas, Ying Shi
  • Patent number: 12112752
    Abstract: Devices and techniques are generally described for cohort determination in natural language processing. In various examples, a first natural language input to a natural language processing system may be determined. The first natural language input may be associated with a first account identifier. A first machine learning model may determine first data representing one or more words of the first natural language input. A second machine learning model may determine second data representing one or more acoustic characteristics of the first natural language input. Third data may be determined, the third data including a predicted performance for processing the first natural language input by the natural language processing system. The third data may be determined based on the first data representation and the second data representation.
    Type: Grant
    Filed: March 7, 2022
    Date of Patent: October 8, 2024
    Assignee: AMAZON TECHNOLOGIES, INC.
    Inventors: Rahul Gupta, Jwala Dhamala, Apurv Verma, Qingwen Ye, Mayur Himmatbhai Dabhi, Srinivasan Rengarajan Veeravanallur, Spyridon Matsoukas, Melanie C B Gens, Seyed Omid Razavi, Avni Khatri, Premkumar Natarajan
  • Publication number: 20240105171
    Abstract: Techniques for enabling access in a multi-assistant speech processing system are described, where a first assistant system may use components of a second assistant system as data processing components. Runtime operational data and user input data related to the first assistant may be kept separate from the processing data and input data related to the second assistant by propagating a first account ID, for user inputs directed to the first assistant, through the processing pipeline, and using a second account for user inputs directed to the second assistant. A mapping between the first account ID and the second account ID may be accessible to a select number of system components. Handoffs between the two assistants are handled in a manner where data related to one assistant is not accessible by the other assistant.
    Type: Application
    Filed: September 26, 2022
    Publication date: March 28, 2024
    Inventors: Ramya Chaganti, Mark Lawrence, Ryan McCrate, Melanie C. B. Gens, Andrew Smith, Raja Bose, Zexiong Yan, Jyoti Chhabra
  • Patent number: 11869490
    Abstract: Techniques for tuning parameters for machine learning models are described. Different values for a parameter are tested to determine the value that results in an optimized model. A parameter value may be selected for testing using a search algorithm based on how the model performs with respect to other values for the parameter. Different values may be tested until a stopping criterion (such as time for testing, number of trials, amount of enhancement in performance, etc.) is met. In some embodiments, the techniques may be used to determine parameter values for natural language processing models.
    Type: Grant
    Filed: August 14, 2020
    Date of Patent: January 9, 2024
    Assignee: Amazon Technologies, Inc.
    Inventors: Rahul Gupta, Jwala Dhamala, Melanie C B Gens, Sachin Midha, Jennifer Yuen, Dewan Muhammed Ibtesham, Wael Hamza, Xinhong Zhang, Md Humayun Arafat
  • Publication number: 20230142272
    Abstract: Techniques for evaluating a natural language understanding (NLU) component and determining an action to resolve an issue processing a user input are described. The system determines which component is invoked by a baseline NLU component is processing the user input, and which component is invoked by an updated NLU component. Based on that information, the system selects the action to resolve the updated NLU component generating an undesired response to the user input.
    Type: Application
    Filed: October 26, 2022
    Publication date: May 11, 2023
    Inventors: Pavel Bhowmik, Melanie C B Gens, Sachin Midha, Rahul Gupta, Sriram Venkatapathy, Xinhong Zhang, Anoop Kumar, Pooja Sanjay Sonawane, Samuel Harry Ingbar
  • Patent number: 11507752
    Abstract: Techniques for evaluating a natural language understanding (NLU) component and determining an action to resolve an issue processing a user input are described. The system determines which component is invoked by a baseline NLU component is processing the user input, and which component is invoked by an updated NLU component. Based on that information, the system selects the action to resolve the updated NLU component generating an undesired response to the user input.
    Type: Grant
    Filed: August 26, 2020
    Date of Patent: November 22, 2022
    Assignee: Amazon Technologies, Inc.
    Inventors: Pavel Bhowmik, Melanie C B Gens, Sachin Midha, Rahul Gupta, Sriram Venkatapathy, Xinhong Zhang, Anoop Kumar, Pooja Sanjay Sonawane, Samuel Harry Ingbar