Patents by Inventor Salman MOHAMMAD

Salman MOHAMMAD 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: 20250138909
    Abstract: A technique sends a first prompt to a language model that specifies selector information. The selector information provides a summary of a group of functions that are capable of being invoked. The language model responds by choosing one or more functions from the group of functions. The technique then sends a second prompt to the language model that specifies more detailed information regarding just the function(s) that have been identified by the language model. The language model responds by providing invocation information for each of the functions, such as properly formatted API messages. The technique then invokes the function(s) based on the invocation information. The technique reduces the size of each prompt sent to the language model, which makes efficient use of resources and improves the quality of the language model's output results.
    Type: Application
    Filed: December 29, 2023
    Publication date: May 1, 2025
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Girish Milind MAHAJAN, Sayan Dev PATHAK, Michael Anthony TAYLOR, Salman Mohammad QUAZI, Christopher Hakan BASOGLU, Prashanth SRIKANTHAN
  • Publication number: 20250139136
    Abstract: A technique partitions a user's original query into plural smaller component queries, each of which has a common part and an instance-specific part. The technique distributes the component queries to plural processor instances of a processor. The plural processor instances transform the respective component queries into query-component responses by acting in parallel, independent of each other. The technique generates a final response based on the query-component responses, e.g., by assembling the component-query responses into the final response. The technique reduces latency because the processor instances work on parts of the user's original query at the same time, rather than as a single stream of consecutive tokens. The plural processor instances have access to a shared cache memory, and utilize relevant data that has been computed in response to previous queries.
    Type: Application
    Filed: October 31, 2023
    Publication date: May 1, 2025
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Sayan Dev PATHAK, Osama ABUELSOROUR, Christopher Hakan BASOGLU, Harini KESAVAMOORTHY, Girish Milind MAHAJAN, Salman Mohammad QUAZI, Valeriy Viktorovich KIRSHIN
  • Patent number: 12287816
    Abstract: A technique partitions a user's original query into plural smaller component queries, each of which has a common part and an instance-specific part. The technique distributes the component queries to plural processor instances of a processor. The plural processor instances transform the respective component queries into query-component responses by acting in parallel, independent of each other. The technique generates a final response based on the query-component responses, e.g., by assembling the component-query responses into the final response. The technique reduces latency because the processor instances work on parts of the user's original query at the same time, rather than as a single stream of consecutive tokens. The plural processor instances have access to a shared cache memory, and utilize relevant data that has been computed in response to previous queries.
    Type: Grant
    Filed: October 31, 2023
    Date of Patent: April 29, 2025
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Sayan Dev Pathak, Osama Abuelsorour, Christopher Hakan Basoglu, Harini Kesavamoorthy, Girish Milind Mahajan, Salman Mohammad Quazi, Valeriy Viktorovich Kirshin
  • Publication number: 20240394479
    Abstract: A technique for interacting with a machine-trained language model uses dynamic prompt management. The technique includes: receiving an input query and creating prompt information that expresses the input query and targeted context information. The targeted context information is selected from candidate context information. Further, a part of the prompt information is formed by compressing source information by reducing a number of content units in the source information (where the source information includes the input query and/or the candidate context information). The method further includes submitting the prompt information to the machine-trained language model, and receiving a response from the machine-trained language model based on the prompt information. The technique has the overall effect of reducing the number of content units submitted to the language model, which, in turn, reduces the amount of resources and time required by the language model to process the input query.
    Type: Application
    Filed: June 19, 2023
    Publication date: November 28, 2024
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Sayan Dev PATHAK, Harini KESAVAMOORTHY, Zoltan ROMOCSA, Christopher Hakan BASOGLU, Girish Milind MAHAJAN, Salman Mohammad QUAZI
  • Publication number: 20240394477
    Abstract: A technique for interacting with a machine-trained language model uses dynamic prompt management. The technique includes: receiving an input query; accessing a state data store that provides candidate context information; partitioning the candidate context information into plural parts; selecting targeted context information from the candidate context information by determining a semantic relevance of the input query to each of the plural parts by performing vector-based analysis; creating prompt information that includes the input query and the targeted context information; submitting the prompt information to the machine-trained language model; and receiving a response from the machine-trained language model based on the prompt information. The technique has the overall effect of reducing the number of content units submitted to the language model, which, in turn, reduces the amount of resources and time required by the language model to process the input query.
    Type: Application
    Filed: June 19, 2023
    Publication date: November 28, 2024
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Sayan Dev PATHAK, Harini KESAVAMOORTHY, Zoltan ROMOCSA, Christopher Hakan BASOGLU, Girish Milind MAHAJAN, Salman Mohammad QUAZI
  • Patent number: 11009995
    Abstract: Various embodiments include methods and devices for implementing refining of user interface (UI) behavior. Embodiments may include creating a touch-profile of a touch-panel of a computing device from results of a self-diagnostic test measuring capacitance of capacitive sensors of the touch-panel, embedding the touch-profile in a framework of an operating system of the computing device, determining an unusable area of the touch-panel from the touch-profile, and determining a UI modification based on the unusable area of the touch-panel.
    Type: Grant
    Filed: October 16, 2019
    Date of Patent: May 18, 2021
    Assignee: QUALCOMM Incorporated
    Inventors: Shantanu Jain, Aditya Parulkar, Salman Mohammad, Vevek Venkatesan, Aditya Prakash, Jonathan Kies, Douglas Brems, Robyn Teresa Oliver
  • Publication number: 20210117038
    Abstract: Various embodiments include methods and devices for implementing refining of user interface (UI) behavior. Embodiments may include creating a touch-profile of a touch-panel of a computing device from results of a self-diagnostic test measuring capacitance of capacitive sensors of the touch-panel, embedding the touch-profile in a framework of an operating system of the computing device, determining an unusable area of the touch-panel from the touch-profile, and determining a UI modification based on the unusable area of the touch-panel.
    Type: Application
    Filed: October 16, 2019
    Publication date: April 22, 2021
    Inventors: Shantanu JAIN, Aditya PARULKAR, Salman MOHAMMAD, Vevek VENKATESAN, Aditya PRAKASH, Jonathan KIES, Douglas BREMS, Robyn Teresa OLIVER
  • Patent number: 10697164
    Abstract: A sanitizing device for a handheld bidet sprayer includes a housing for holding a handheld bidet sprayer on a spray head mount, an optical sensor used to detect the presence or absence of the sprayer in the housing, an odoriferous substance sensor used to sense odoriferous conditions or indications of a significant presence of microbes, a chemical discharge module, an ultraviolet light source, and a control module. The chemical discharge module includes a chemical supply holder and a plurality of conduits extending from the chemical supply holder. The chemical supply holder includes at least one container of fragrance and at least one container of sanitizer. Upon sensing odoriferous conditions or indications of a significant presence of microbes, the control module causes the discharge of the sanitizer and/or fragrance.
    Type: Grant
    Filed: January 3, 2020
    Date of Patent: June 30, 2020
    Inventors: Sabah Thamer Abdullah S. Al-Sabah, Mohammad Salman Mohammad Salman Al-Sabah, Fahad S. F. S. A. Al-Sahli
  • Patent number: 10557257
    Abstract: A sanitizing device for a handheld bidet sprayer includes a housing for holding a handheld bidet sprayer on a spray head mount, an optical sensor used to detect the presence or absence of the sprayer in the housing, an odoriferous substance sensor used to sense odoriferous conditions or indications of a significant presence of microbes, a chemical supply holder, an ultraviolet light source, and a control module. The chemical supply holder includes at least one container of fragrance and at least one container of sanitizer. Upon sensing odoriferous conditions or indications of a significant presence of microbes, the control module causes the discharge of the sanitizer and/or fragrance.
    Type: Grant
    Filed: July 30, 2019
    Date of Patent: February 11, 2020
    Inventors: Sabah Thamer Abdullah S. Al-Sabah, Mohammad Salman Mohammad Salman Al-Sabah, Fahad S. F. S. A. Al-Sahli