Patents by Inventor Saurabh Misra

Saurabh Misra 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: 11489559
    Abstract: Described are devices, systems and methods for scheduling multi-user (MU) multiple input multiple output (MIMO) transmissions in a fixed wireless access (FWA) system. One method for scheduling a large number of user devices in a wireless communication system includes a preselection process to pare down the number of user devices to be simultaneously scheduled, and then scheduling that subset of users. In an example, and assuming each user device communicates over a corresponding wireless channel, the preselection process includes determining a number of sets based on a first characteristic of the wireless channels, where each set includes at least one user device, and then determining a subset of user devices by selecting at most one user device from each of the sets. The scheduling of the selected subset of users is based on a scheduling algorithm and a second characteristic of the wireless channels.
    Type: Grant
    Filed: March 8, 2019
    Date of Patent: November 1, 2022
    Assignee: Cohere Technologies, Inc.
    Inventors: Andreas Molisch, Robert Fanfelle, Saurabh Misra, Paul Lind, James Delfeld
  • Patent number: 11157695
    Abstract: A conversation may be monitored in real time using a trained machine learning model to identify a desired outcome of a conversation and generate one or more phrases for accomplishing the desired outcome. A confidence score may also be determined for one or more phrases that indicates a likelihood that the one or more phrases may help accomplish the desired outcome of the conversation. In some examples, a confidence score may be based on whether an agent, a caller, or both responded unfavorably to a similar phrase used previously in another conversation. In other examples, a confidence score corresponding to one or more phrases may be based on whether a prior conversation in which one or more similar phrases was used resulted in the desired outcome being accomplished.
    Type: Grant
    Filed: March 19, 2021
    Date of Patent: October 26, 2021
    Assignee: CRESTA INTELLIGENCE INC.
    Inventors: Tianlin Shi, Saurabh Misra, Motoki Dean Wu
  • Patent number: 10970485
    Abstract: A conversation may be monitored in real time using a trained machine learning model to identify a desired outcome of a conversation and generate one or more phrases for accomplishing the desired outcome. A confidence score may also be determined for one or more phrases that indicates a likelihood that the one or more phrases may help accomplish the desired outcome of the conversation. In some examples, a confidence score may be based on whether an agent, a caller, or both responded unfavorably to a similar phrase used previously in another conversation. In other examples, a confidence score corresponding to one or more phrases may be based on whether a prior conversation in which one or more similar phrases was used resulted in the desired outcome being accomplished.
    Type: Grant
    Filed: July 31, 2020
    Date of Patent: April 6, 2021
    Assignee: CRESTA INTELLIGENCE INC.
    Inventors: Tianlin Shi, Saurabh Misra, Motoki Dean Wu
  • Publication number: 20210058114
    Abstract: Described are devices, systems and methods for scheduling multi-user (MU) multiple input multiple output (MIMO) transmissions in a fixed wireless access (FWA) system. One method for scheduling a large number of user devices in a wireless communication system includes a preselection process to pare down the number of user devices to be simultaneously scheduled, and then scheduling that subset of users. In an example, and assuming each user device communicates over a corresponding wireless channel, the preselection process includes determining a number of sets based on a first characteristic of the wireless channels, where each set includes at least one user device, and then determining a subset of user devices by selecting at most one user device from each of the sets. The scheduling of the selected subset of users is based on a scheduling algorithm and a second characteristic of the wireless channels.
    Type: Application
    Filed: March 8, 2019
    Publication date: February 25, 2021
    Inventors: Andreas Molisch, Robert Fanfelle, Saurabh Misra, Paul Lind, James Delfeld