Patents by Inventor Shubham Mehrotra

Shubham Mehrotra 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: 12019984
    Abstract: A method that includes receiving an input at an interactive conversation service that uses an intent classification model. The method may further include generating, using an encoder model of the intent classification model, a set of output vectors corresponding to the input, where the encoder model is configured to determine a set of metrics corresponding to intent classifications. The method may further include determining, using an outlier detection model of the intent classification model, whether the input is in-domain or out-of-domain (OOD) based on a first vector of the set of output vectors satisfying a domain threshold relative to one or more of the intent classifications. The method may further include outputting, by the intent classification model, a second vector of the set of output vectors that indicates the set of metrics corresponding to the intent classifications or an indication that the input is OOD.
    Type: Grant
    Filed: September 20, 2021
    Date of Patent: June 25, 2024
    Assignee: Salesforce, Inc.
    Inventors: Shilpa Bhagavath, Shubham Mehrotra, Abhishek Sharma, Shashank Harinath, Na Cheng, Zineb Laraki
  • Publication number: 20240143945
    Abstract: Embodiments described herein provide a cross-lingual intent classification model that predicts in multiple languages without the need of training data in all the multiple languages. For example, data requirement for training can be reduced to just one utterance per intent label. Specifically, when an utterance is fed to the intent classification model, the model checks whether the utterance is similar to any of the example utterances provided for each intent. If any such utterance(s) are found, the model returns the specified intent, otherwise, it returns out of domain (OOD).
    Type: Application
    Filed: January 30, 2023
    Publication date: May 2, 2024
    Inventors: Shubham Mehrotra, Zachary Alexander, Shilpa Bhagavath, Gurkirat Singh, Shashank Harinath, Anuprit Kale
  • Patent number: 11961220
    Abstract: Apparatuses and methods are disclosed for handling integrated circuits in automated testing. The handler apparatus includes an upper assembly that is selectively translatable above a testing surface and a lower bracket extending from and positioned below the upper assembly. The lower bracket forms a first opening, is selectively moveable upward and downward, and includes a rotatable finger extending downward to pick up and place an integrated circuit in a socket. The handier may further include an image sensor to detect potential error conditions, and a tool extending from the lower bracket to open and close a lid on the socket. The methods include sensing an image of an integrated circuit during certain phases of testing, analyzing the image to determine if the integrated circuit is positioned correctly, and correcting any detected error conditions before continuing with the automated testing.
    Type: Grant
    Filed: March 19, 2018
    Date of Patent: April 16, 2024
    Assignee: TEXAS INSTRUMENTS INCORPORATED
    Inventors: Neeraj Bhardwaj, Neha Vernekar, Janardhan Venkata Raju, Shubham Mehrotra, Arun Adoni, Mahit Arun Warhadpande, Shimee Gupta, Goda Devi Addanki, Pavinkumar Ramasamy, Binoy Jose Maliakal
  • Patent number: 11853699
    Abstract: A method and system for extracting and labeling Named-Entity Recognition (NER) data in a target language for use in a multi-lingual software module has been developed. First, a textual sentence is translated to the target language using a translation module. A named entity is identified and extracted within the translated sentence. The named entity is identified by either: exact mapping; a semantically similar translated named entity that meets a predetermined minimum threshold of similarity; or utilizing a rule-based library for the target language. Once identified, the named entity is labeled with a pre-determined category and stored in a retrievable electronic database.
    Type: Grant
    Filed: January 29, 2021
    Date of Patent: December 26, 2023
    Inventors: Shubham Mehrotra, Ankit Chadha
  • Publication number: 20230401387
    Abstract: The system receives a base machine learning model trained using a generic dataset. For example, the base machine learning model may be an off-the-shelf machine learning based model. The base machine learning model is trained to receive an input and generate a feature vector representing the input. The input may be a natural language expression, an image, or any other type of input. The system receives a domain specific training dataset based on known categories for input values. The system determines an orthogonal transformation for reducing the dimensions of the base machine learning model using on the domain specific training dataset. The system applies the orthogonal transformation to the base machine learning model to obtain a domain specific machine learning model. The system uses the domain specific machine learning model for processing inputs, for example, in a production environment.
    Type: Application
    Filed: June 9, 2022
    Publication date: December 14, 2023
    Inventors: Zachary Alexander, Shubham Mehrotra
  • Publication number: 20230086302
    Abstract: A method that includes receiving an input at an interactive conversation service that uses an intent classification model. The method may further include generating, using an encoder model of the intent classification model, a set of output vectors corresponding to the input, where the encoder model is configured to determine a set of metrics corresponding to intent classifications. The method may further include determining, using an outlier detection model of the intent classification model, whether the input is in-domain or out-of-domain (OOD) based on a first vector of the set of output vectors satisfying a domain threshold relative to one or more of the intent classifications. The method may further include outputting, by the intent classification model, a second vector of the set of output vectors that indicates the set of metrics corresponding to the intent classifications or an indication that the input is OOD.
    Type: Application
    Filed: September 20, 2021
    Publication date: March 23, 2023
    Inventors: Shilpa Bhagavath, Shubham Mehrotra, Abhishek Sharma, Shashank Harinath, Na Cheng, Zineb Laraki
  • Publication number: 20220245346
    Abstract: A method and system for extracting and labeling Named-Entity Recognition (NER) data in a target language for use in a multi-lingual software module has been developed. First, a textual sentence is translated to the target language using a translation module. A named entity is identified and extracted within the translated sentence. The named entity is identified by either: exact mapping; a semantically similar translated named entity that meets a predetermined minimum threshold of similarity; or utilizing a rule-based library for the target language. Once identified, the named entity is labeled with a pre-determined category and stored in a retrievable electronic database.
    Type: Application
    Filed: January 29, 2021
    Publication date: August 4, 2022
    Applicant: salesforce.com, inc.
    Inventors: Shubham Mehrotra, Ankit Chadha
  • Publication number: 20190227117
    Abstract: Apparatuses and methods are disclosed for handling integrated circuits in automated testing. The handler apparatus includes an upper assembly that is selectively translatable above a testing surface and a lower bracket extending from and positioned below the upper assembly. The lower bracket forms a first opening, is selectively moveable upward and downward, and includes a rotatable finger extending downward to pick up and place an integrated circuit in a socket. The handier may further include an image sensor to detect potential error conditions, and a tool extending from the lower bracket to open and dose a lid on the socket. The methods include sensing an image of an integrated circuit during certain phases of testing, analyzing the image to determine if the integrated circuit is positioned correctly, and correcting any detected error conditions before continuing with the automated testing.
    Type: Application
    Filed: March 19, 2018
    Publication date: July 25, 2019
    Inventors: Neeraj Bhardwaj, Neha Vernekar, Janardhan Venkata Raju, Shubham Mehrotra, Arun Adoni, Mahit Arun Warhadpande, Shimee Gupta, Goda Devi Addanki, Pavinkumar Ramasamy, Binoy Jose Maliakal