Patents by Inventor Suman Sundaresh

Suman Sundaresh 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: 20250238443
    Abstract: Embodiments of the disclosed technologies include generating a search prompt based on an input portion of an online dialog involving a user of a computing device. The search prompt includes a dialog summarization instruction configured to instruct a generative artificial intelligence model to generate and output a dialog summary. The search prompt is sent to a first generative model. In response to the search prompt, a search query is generated and output by the first generative model based on the dialog summary. The search query is sent to a search system. Search result data is determined based on an execution of the search query by the search system. At least some of the search result data is included in an output portion of the online dialog. The output portion is configured to be displayed at the computing device in response to the input portion of the online dialog.
    Type: Application
    Filed: April 10, 2025
    Publication date: July 24, 2025
    Inventors: Aparna Krishnan, Christopher Wright Lloyd, II, Jeremy K. Owen, Christopher J. Fong, Suman Sundaresh, Lavish Shah, Muhammad Basit Khurram, Michaela Jillings
  • Patent number: 12299015
    Abstract: Embodiments of the disclosed technologies include generating a search prompt based on an input portion of an online dialog involving a user of a computing device. The search prompt includes a dialog summarization instruction configured to instruct a generative artificial intelligence model to generate and output a dialog summary. The search prompt is sent to a first generative model. In response to the search prompt, a search query is generated and output by the first generative model based on the dialog summary. The search query is sent to a search system. Search result data is determined based on an execution of the search query by the search system. At least some of the search result data is included in an output portion of the online dialog. The output portion is configured to be displayed at the computing device in response to the input portion of the online dialog.
    Type: Grant
    Filed: June 29, 2023
    Date of Patent: May 13, 2025
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Aparna Krishnan, Christopher Wright Lloyd, II, Jeremy K. Owen, Christopher J. Fong, Suman Sundaresh, Lavish Shah, Muhammad Basit Khurram, Michaela Jillings
  • Publication number: 20250005050
    Abstract: Embodiments of the disclosed technologies include generating a search prompt based on an input portion of an online dialog involving a user of a computing device. The search prompt includes a dialog summarization instruction configured to instruct a generative artificial intelligence model to generate and output a dialog summary. The search prompt is sent to a first generative model. In response to the search prompt, a search query is generated and output by the first generative model based on the dialog summary. The search query is sent to a search system. Search result data is determined based on an execution of the search query by the search system. At least some of the search result data is included in an output portion of the online dialog. The output portion is configured to be displayed at the computing device in response to the input portion of the online dialog.
    Type: Application
    Filed: June 29, 2023
    Publication date: January 2, 2025
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Aparna Krishnan, Christopher Wright Lloyd, II, Jeremy K. Owen, Christopher J. Fong, Suman Sundaresh, Lavish Shah, Muhammad Basit Khurram, Michaela Jillings
  • Publication number: 20240378424
    Abstract: Embodiments of the disclosed technologies include configuring a first machine learning model to generate and output suggested message content based on first correlations between message content and message acceptance data, where the first machine learning model includes a first encoder-decoder model architecture, configuring a second machine learning model to generate and output message evaluation data based on second correlations between the message content and the message acceptance data, where the second machine learning model includes a second encoder-decoder model architecture, coupling an output of the first machine learning model to an input of the second machine learning model, and coupling an output of the second machine learning model to an input of the first machine learning model.
    Type: Application
    Filed: June 27, 2023
    Publication date: November 14, 2024
    Inventors: Praveen Kumar Bodigutla, Suman Sundaresh, Souvik Ghosh, Saurabh Gupta, Sai Krishna Bollam, Arya Ghatak Choudhury, Weiheng Qian, Jiarui Wang
  • Publication number: 20240378425
    Abstract: Embodiments of the disclosed technologies include receiving first message attribute data and inputting the first message attribute data to a first machine learning model. The first machine learning model is configured to generate and output suggested message content based on first correlations between message content and message acceptance data. The first machine learning model generates a first set of message content suggestions based on the first message attribute data, and selects at least one message content suggestion from the first set of message content suggestions based on message evaluation data. Feedback data related to the selected at least one message content suggestion is received. The first machine learning model is tuned based on the feedback data. The tuned first machine learning model generates a second set of message content suggestions based on the first message attribute data.
    Type: Application
    Filed: June 27, 2023
    Publication date: November 14, 2024
    Inventors: Praveen Kumar Bodigutla, Suman Sundaresh, Souvik Ghosh, Saurabh Gupta, Sai Krishna Bollam, Arya Ghatak Choudhury, Weiheng Qian, Jiarui Wang
  • Patent number: 11797891
    Abstract: The instant systems and methods are directed to a contextual bandits machine learning model configured to enable granular synchronized ecosystem personalization and optimization. The system and methods determine an objective and feed the objective and one more lifecycle model propensity scores as inputs to the contextual bandits machine learning model. The contextual bandits machine learning model then generates one or more potential weighted model rewards, wherein each potential weighted model reward includes at least a desired user action, a weight, a channel, and an expected change to the objective, and selects a weighted model reward that optimizes the objective. An action recommendation is subsequently transmitted to a user device based on the weighted model reward, wherein the action recommendation is presented in a selected channel associated with the weighted model reward. Feedback associated with the action recommendation is collected and used in training and fine-tuning of the model.
    Type: Grant
    Filed: October 24, 2022
    Date of Patent: October 24, 2023
    Assignee: INTUIT INC.
    Inventors: Yashwanth Musiboyina, Dawn-Marie Chantel Miesner, Mustapha Harb, Nan Jiang, Shahram Mohrehkesh, Zachary Dorsch, Suman Sundaresh, Grace Wu
  • Publication number: 20180315132
    Abstract: Among other things, embodiments of the present disclosure discussed herein help to identify peers of various individuals and organizations who are members of an online social network. Groups of peers may be identified based on various criteria, and some embodiments may generate a probability score reflecting a confidence level that two or more members of the online social network are peers of one another.
    Type: Application
    Filed: April 28, 2017
    Publication date: November 1, 2018
    Inventors: Aibo Tian, Varun Mithal, Suman Sundaresh, Cissy Chen, Bowen Meng, Lanxiao Xu
  • Publication number: 20180060822
    Abstract: A system and method includes obtaining, from a database, member characteristics of a member of an online social networking system, obtaining, from the database, job characteristics of a job posted to the online social networking system, and determining, characteristic scores including, for each member characteristic, a characteristic score based on a relationship between the member characteristic and an associated one of the job characteristics. A processor combines the characteristic scores to obtain an aggregate job score, combines a subset of the characteristic scores to obtain a category score, obtains, from the database, aggregate job scores and category scores associated with the job from other members of the online social networking system, and determines an aggregate rank of the aggregate job score in relation to the aggregate job scores and a category rank of the category score in relation to the category scores.
    Type: Application
    Filed: August 31, 2016
    Publication date: March 1, 2018
    Inventors: Chenying Hou, Aibo Tian, Suman Sundaresh, Lee Mallabone, Thogori C. Karago
  • Publication number: 20160275634
    Abstract: A system and method for using large data sets to improve candidate analysis in social networking applications is disclosed. A social networking system stores member data for a plurality of members of a social networking system in a database. The social networking system receives a potential applicant information request from a computer system associated with a first education institution. In response to receiving a potential applicant information request from a computer system associated with the first education institution, the social networking system generates potential applicant data based, at least in part, on the stored member data in the database associated with the social networking system and transmits the generated potential applicant data to the computer system associated with the first education institution. The social networking system receives, associated with the first education institution, an applicant offer message intended for display to at least one member of the social networking system.
    Type: Application
    Filed: March 18, 2015
    Publication date: September 22, 2016
    Inventors: Satpreet Harcharan Singh, Suman Sundaresh
  • Publication number: 20160232224
    Abstract: The present invention relates to methods, systems and apparatus for capturing, integrating, organizing, navigating and querying large-scale data from high-throughput biological and chemical assay platforms. It provides a highly efficient meta-analysis infrastructure for performing research queries across a large number of studies and experiments from different biological and chemical assays, data types and organisms, as well as systems to build and add to such an infrastructure. According to various embodiments, methods, systems and interfaces for associating experimental data, features and groups of data related by structure and/or function with chemical, medical and/or biological terms in an ontology or taxonomy are provided. According to various embodiments, methods, systems and interfaces for filtering data by data source information are provided, allowing dynamic navigation through large amounts of data to find the most relevant results for a particular query.
    Type: Application
    Filed: August 17, 2015
    Publication date: August 11, 2016
    Inventors: Ilya Kupershmidt, Qiaojuan Jane Su, Qingdi Liu, Satnam Alag, Suman Sundaresh
  • Publication number: 20160127429
    Abstract: A method and system for conducting applicant analytics for a multiuser social networking system is disclosed. A social networking system stores member qualification data for a plurality of members of a social networking system. The social networking system receives an education institution interest indication. The social networking system receives an analytics data request from the client system, wherein the analytics request indicates a first education institution. The social networking system determines a list of other members of the social networking system that have indicated interest in the first education institution. The social networking system generates comparison data for the first member and the determined list of other members, wherein comparison data compares member qualification data of the first member and the determined list of other members. The social networking system transmits the generated comparison data to the client system.
    Type: Application
    Filed: December 23, 2014
    Publication date: May 5, 2016
    Inventors: Satpreet Harcharan Singh, Suman Sundaresh
  • Publication number: 20160125560
    Abstract: A system and method for generating an admittance prediction based on historical admittance data that predicts whether a particular member of a social networking system will be admitted to a particular education institution is disclosed. A social networking system stores admittance data for a plurality of education institutions. The social networking system receives a request for a prediction concerning whether a first member of a social networking service will be admitted to a first education institution in the plurality of education institutions. The social networking system compares qualification data associated with the first member to admittance data stored in memory of the social networking server. The social networking system generates an admittance prediction based on the comparison of the qualification data associated with the first member with historic admittance data. The social networking system transmits the admittance prediction to the client system for display.
    Type: Application
    Filed: December 31, 2014
    Publication date: May 5, 2016
    Inventors: Satpreet Harcharan Singh, Suman Sundaresh
  • Publication number: 20150339404
    Abstract: An inferred seniority system, in one example embodiment, may be configured to determine seniority levels for member profiles maintained by an on-line social network system, based on information stored in the member profiles, and also based on a hierarchical structure termed a seniority pyramid. The system may first determine seniority labels for each of the profiles in a group of member profiles based on information in respective member profiles. The system then determines, for groups of profiles that are given their respective seniority labels, percentages of profiles associated with respective seniority labels. Respective seniority levels for the groups of profiles are determined based on respective percentages of profiles associated with respective seniority labels and the percentage ranges associated with seniority levels that are stored in the seniority pyramid structure.
    Type: Application
    Filed: May 23, 2014
    Publication date: November 26, 2015
    Applicant: LinkedIn Corporation
    Inventors: Suman Sundaresh, Trevor Walker, Deepak Kumar, Vaibhav Goel
  • Publication number: 20150317609
    Abstract: A system maintains one or more of member profiles, company profiles, and job postings on a social networking service. The system identifies a business organization using the one or more of member profiles, company profiles, and job postings. The system identifies a job title or a job function at the business organization using the one or more of member profiles, company profiles, and job postings. The system also identifies a number of employees in the job title or job function at the business organization using one or more of the member profiles and the company profiles. The system determines a number of years that each employee has been employed in the job title or job function for the business organization using at least the member profiles, and calculates an average time period that a typical employee has been in the job title or job function for the business organization.
    Type: Application
    Filed: June 10, 2014
    Publication date: November 5, 2015
    Inventors: Vaibhav Goel, Suman Sundaresh, Satpreet Harcharan Singh
  • Publication number: 20150317753
    Abstract: A system maintains data relating to members and business organizations on a social networking service. The system analyzes the data to identify attributes of employees at a first business organization, creates an employee profile for the first business organization using the identified attributes of the employees, compares the employee profile for the first business organization to a profile of a member, and recommends to the member a job posted by the first business organization when the employee profile for the first business organization is similar to the profile of the member.
    Type: Application
    Filed: June 10, 2014
    Publication date: November 5, 2015
    Inventors: Vaibhav Goel, Suman Sundaresh, Satpreet Harcharan Singh
  • Publication number: 20150317754
    Abstract: A system maintains member profiles and job profiles on a social networking service, identifies a first business organization using one or more of the member profiles and the job profiles, identifies a job title or a job function at the first business organization using one or more of the member profiles and the job profiles, and creates a job profile for the job title or job function at the first business organization using the member profiles and the job profiles.
    Type: Application
    Filed: June 10, 2014
    Publication date: November 5, 2015
    Inventors: Vaibhav Goel, Suman Sundaresh, Satpreet Harcharan Singh
  • Patent number: 9141913
    Abstract: The present invention relates to methods, systems and apparatus for capturing, integrating, organizing, navigating and querying large-scale data from high-throughput biological and chemical assay platforms. It provides a highly efficient meta-analysis infrastructure for performing research queries across a large number of studies and experiments from different biological and chemical assays, data types and organisms, as well as systems to build and add to such an infrastructure. According to various embodiments, methods, systems and interfaces for associating experimental data, features and groups of data related by structure and/or function with chemical, medical and/or biological terms in an ontology or taxonomy are provided. According to various embodiments, methods, systems and interfaces for filtering data by data source information are provided, allowing dynamic navigation through large amounts of data to find the most relevant results for a particular query.
    Type: Grant
    Filed: March 4, 2009
    Date of Patent: September 22, 2015
    Assignee: NextBio
    Inventors: Ilya Kupershmidt, Qiaojuan Jane Su, Qingdi Liu, Satnam Alag, Suman Sundaresh
  • Publication number: 20150248647
    Abstract: An online social networking system receives a message from a member of an online social networking service indicating an interest in applying for an employment position. The online social networking system compares a profile of the member against requirements for the employment position, other members of the online social networking service currently employed in the employment position, and profiles of other members who have indicated an interest in the employment position. The online social networking system computes a rank of the member based on the comparison of the profile of the member to the requirements for the employment position, the comparison of the profile of the member to the one or more members currently employed in the employment position, or the comparison of the profile of the member to the profiles of other members. The online social networking system transmits a message to the member regarding the rank of the member.
    Type: Application
    Filed: February 28, 2014
    Publication date: September 3, 2015
    Applicant: Linkedln Corporation
    Inventors: Vaibhav Goel, Suman Sundaresh, Parker R. Barrile
  • Publication number: 20150112765
    Abstract: Techniques for identifying members of a social network service that exhibit recruiting intent are described. According to various embodiments, a set of members of an online social network service that self-identify as recruiters may be identified. The set of members that self-identify as recruiters may then be clustered into a group of engaged recruiters and a second group of non-engaged recruiters, and the group of engaged recruiters may be categorized as members exhibiting recruiting intent. Behavioral log data associated with the members exhibiting recruiting intent may then be accessed and classified as recruiting intent signature data. Thereafter, prediction modeling may be performed based on the recruiting intent signature data and a prediction model, to identify members of the online social network service that are associated with behavioral log data matching the recruiting intent signature data.
    Type: Application
    Filed: October 22, 2013
    Publication date: April 23, 2015
    Applicant: Linkedln Corporation
    Inventors: Suman Sundaresh, Andrew P. Hill, Deepak Kumar, Anmol Bhasin
  • Publication number: 20090222400
    Abstract: The present invention relates to methods, systems and apparatus for capturing, integrating, organizing, navigating and querying large-scale data from high-throughput biological and chemical assay platforms. It provides a highly efficient meta-analysis infrastructure for performing research queries across a large number of studies and experiments from different biological and chemical assays, data types and organisms, as well as systems to build and add to such an infrastructure. According to various embodiments, methods, systems and interfaces for associating experimental data, features and groups of data related by structure and/or function with chemical, medical and/or biological terms in an ontology or taxonomy are provided. According to various embodiments, methods, systems and interfaces for filtering data by data source information are provided, allowing dynamic navigation through large amounts of data to find the most relevant results for a particular query.
    Type: Application
    Filed: March 4, 2009
    Publication date: September 3, 2009
    Applicant: NextBio
    Inventors: Ilya Kupershmidt, Qiaojuan Jane Su, Qingdi Liu, Satnam Alag, Suman Sundaresh