Patents by Inventor KUMAR

KUMAR 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: 20250114163
    Abstract: A method for tracking surgical items with a system including an imaging system, a display, and one or more processors is provided. The method includes capturing a video that depicts a user handling the surgical items, and performing computational analysis of the video to detect a characteristic arm motion of the user which is indicative of the user moving the surgical item to be counted in to a surgical procedure. The method further includes, in response to each instance of the characteristic arm motion being detected, updating a count of surgical items and displaying the updated count on the display.
    Type: Application
    Filed: December 20, 2024
    Publication date: April 10, 2025
    Applicant: Stryker Corporation
    Inventors: Siddarth Satish, Mayank Kumar, Kevin J. Miller, Sheetal D. Jantikar, Daniel Goodman, Andrew T. Hosford, Charles Peterson Carroll
  • Publication number: 20250117336
    Abstract: A data access method and apparatus for a heterogeneous processing system includes a host processor, a first processor coupled to a first memory, a second processor coupled to a second memory, and switch and bus circuitry that communicatively couples the host processor, the first processor, and the second processor. The host processor maps virtual addresses of the second memory to physical addresses of the switch and bus circuitry. The first processor is configured to directly access the second memory using the mapped physical addresses, and may be configured to directly access the second memory for reading and writing data while executing an application.
    Type: Application
    Filed: December 17, 2024
    Publication date: April 10, 2025
    Applicant: SambaNova Systems, Inc.
    Inventors: Arnav GOEL, Neal SANGHVI, Jiayu BAI, Qi ZHENG, Ravinder KUMAR
  • Publication number: 20250117513
    Abstract: A data privacy system and method is disclosed. The method includes providing at least one processor, at least one memory device including computer-readable instructions, and at least one user device in communication with the at least one processor via a network connection. The at least one processor, upon execution of the computer-readable instructions, is configured to generate a predictive model during training of a machine learning program using a training data set including a personal data set of one or more users. The predictive model is configured to predict at least one predicted data privacy and/or data portability measure of at least one of the users. At least one quick response code embedded with data or a link to the data based upon the at least one predicted data privacy and/or data portability measure is generated to provide enhanced data privacy protection and data portability.
    Type: Application
    Filed: October 5, 2023
    Publication date: April 10, 2025
    Applicant: Truist Bank
    Inventors: Uday Gore, Josephine Middleton-Saulny, Phani Kumar Ankani, Joseph Matthew Law, Giridhar Polur, Seshadri Chintalapati
  • Publication number: 20250119413
    Abstract: Systems, computer program products, and methods are described for secure data transmission. An example system includes a first end-point device, an intermediate device, and a second-end point device. The first end-point device determines the format requirements of the communication link between the first end-point device and the intermediate device, and the communication link intermediate device and the second end-point device. Based on the format requirements, the first end-point device configures the data packet for transmission, such that the data packet, when received at the intermediate device, is re-configured and routed to the second end-point device. When the second end-point device receives the data packet, it verifies the data packet to confirm that the packet has maintained its integrity throughout transit.
    Type: Application
    Filed: August 20, 2024
    Publication date: April 10, 2025
    Applicant: NVIDIA CORPORATION
    Inventors: Stephen David GLASER, Jonathon EVANS, Vidhya KRISHNAN, Naveen Kumar NARRISHETTI, Peter PANEAH, Vladimir VAINER, Ariel SHAHAR, Ofir EVEN CHEN
  • Publication number: 20250119437
    Abstract: A system and method for detecting unauthorized relocation of endpoint devices are disclosed. The system comprises one or more network security appliances and one or more servers. The one or more network security appliances is configured to collect network environment data associated with each endpoint device of the one or more endpoint devices. The one or more servers is configured to obtain the network environment data from the one or more network security appliances for generating one or more hash values for the network environment data of each endpoint device of the one or more endpoint devices. The system performs a comparative analysis between the one or more hash values to generate a Paranoia-Diff-Score (PDS) for each endpoint device of the one or more endpoint devices to detect the unauthorized relocation of the one or more endpoint devices.
    Type: Application
    Filed: September 13, 2024
    Publication date: April 10, 2025
    Inventors: Vijay Sankar Veeriah, Srinivasan Krishnamoorthy, Anil Kumar Chaudhury, Rajesh Kumar Sahoo
  • Publication number: 20250119563
    Abstract: Systems and techniques are provided for caching misaligned pixel tiles. A method includes determining a first codec region including a first region of a frame; determining whether pixels of a first version of a pixel tile were stored in a cache while coding blocks from a second codec region, the pixel tile corresponding to a location within the frame; based on whether the pixels were stored in the cache, determining whether to read the first version of the pixel tile from the cache or retrieve a second version of the pixel tile from a memory device, the second version of the pixel tile including pixels from the first codec region that are not in the first version of the pixel tile; and coding a block based on the first version of the pixel tile read from the cache or second version of the pixel tile retrieved from the memory device.
    Type: Application
    Filed: October 16, 2024
    Publication date: April 10, 2025
    Inventors: Sriganesh BALAKUMAR, Kapil GARG, Gaurav Avinash PATIL, Rajesh Chowdary CHITTURI, Prasanth GOMATAM, Sravan Kumar GOPANAPALLE
  • Publication number: 20250119594
    Abstract: A server of a livestreaming platform includes a circuitry configured to: hold, in a holding unit, a user ID for identifying a user on the livestreaming platform and livestreamer-of-interest IDs for identifying livestreamers of interest registered by the user as livestreamers that the user is interested in, in association with each other; and divide, in a processing unit, the livestreamers of interest into notification-allowed livestreamers of interest and other livestreamers of interest, a predetermined activity by the notification-allowed livestreamers of interest on the livestreaming platform triggering transmission of a notification to the user by the server.
    Type: Application
    Filed: February 14, 2024
    Publication date: April 10, 2025
    Inventors: Jayneel PAWAR, Hemant MEHTA, Uday Kumar EDUDULA, Ajay Prakash MANGALE
  • Publication number: 20250119625
    Abstract: Methods, computer systems, computer-storage media, and graphical user interfaces are provided for efficiently generating video insights based on text representations of videos. In embodiments, text data associated with a video is obtained. Thereafter, a model prompt to be input into a large language model is generated. The model prompt includes the text data associated with the video. As output from the large language model, a text representation that represents the video in natural language based on the text data is obtained. The text representation is provided as input into a machine learning model to generate a video insight that indicates context of the video.
    Type: Application
    Filed: October 5, 2023
    Publication date: April 10, 2025
    Inventors: Aanisha BHATTACHARYYA, Yaman Kumar
  • Publication number: 20250117766
    Abstract: Systems and methods include automatically identifying items from images of items positioned at a POS system. Cameras capture images of the items in which each camera captures images with different FOVs of the items thereby capturing different item parameters of each item. The items are identified when item parameters of the items match item parameters previously identified and the items are failed to be identified when item parameters fail to match item parameters previously identified. Image pixels associated with each unknown item are extracted and mapped to real world coordinates associated with each unknown item as positioned at the POS system. A bounding polygon for each unknown item is generated that encapsulates each unknown item based on the image pixels mapped to the real world coordinates. The bounding polygon is projected onto each unknown item thereby providing feedback for each unknown item positioned at the POS system.
    Type: Application
    Filed: October 4, 2024
    Publication date: April 10, 2025
    Inventors: Abhinav Yarlagadda, Enis Dengi, Sai Krishna Bashetty, Rahul Santhosh Kumar Varma, Daniel King, Kamalesh Kalirathinam, Nathan Kelly, Sri Priyanka Madduluri, Thomas Strich
  • Publication number: 20250119432
    Abstract: Systems and methods for utilizing Large Language Models (LLMs) for improving machine learning models in network and computer security include obtaining tabular data related to an aspect of networking and computer security; converting the tabular data to natural language for each row in the tabular data; inputting the natural language for each row in the tabular data into a Large Language Model (LLM); obtaining an output from the LLM for each row in the tabular data with embedded data therewith; and utilizing the output to train a machine learning model related to the aspect of networking and computer security
    Type: Application
    Filed: November 29, 2023
    Publication date: April 10, 2025
    Applicant: Zscaler, Inc.
    Inventors: Manikya Bardhan, Raimi Shah, Chenhui Hu, Hanchen Xiong, Nikhil Saini, Aayush Kumar
  • Publication number: 20250113989
    Abstract: The present invention provides a video laryngoscope (100) to perform the intubation process. The video laryngoscope (100) includes a handle (10), a blade (20), a display unit (30), and an attachment assembly (25). The handle (10) includes a camera housing (16) with an image sensor (161) and a light source (162) arranged therein. The image sensor (161) is attached to the handle (10) through a camera channel (15) to visualise the path of the endotracheal tube. The camera housing (16) has a deflector (18) to avoid the blurry and distorted visuals generated due to the scattering of the light from the light source (162). The blade (20) is arranged on the handle (10) to cover the handle (10) and the camera channel (15). Further, the display unit (30) is provided for better visibility of the display screen (34) to visualise the path of the endotracheal tube.
    Type: Application
    Filed: October 7, 2024
    Publication date: April 10, 2025
    Inventor: Sujit Kumar
  • Publication number: 20250118398
    Abstract: Techniques are disclosed for automatically generating Subjective, Objective, Assessment and Plan (SOAP) notes. Particularly, techniques are disclosed for training data collection and evaluation for automatic SOAP note generation. Training data is accessed, and evaluation process is performed on the training data to result in evaluated training data. A fine-tuned machine-learning model is generated using the evaluated training data. The fine-tuned machine-learning model can be used to perform a task associated with generating a SOAP note.
    Type: Application
    Filed: September 13, 2024
    Publication date: April 10, 2025
    Applicant: Oracle International Corporation
    Inventors: Shubham Pawankumar Shah, Syed Najam Abbas Zaidi, Xu Zhong, Poorya Zaremoodi, Srinivasa Phani Kumar Gadde, Arash Shamaei, Ganesh Kumar, Thanh Tien Vu, Nitika Mathur, Chang Xu, Shiquan Yang, Sagar Kalyan Gollamudi
  • Publication number: 20250119159
    Abstract: Systems and techniques are provided for compressing data. A process can include generating a compressed sub-packet by removing one or more sparsity bytes from a sequence of values corresponding to a sub-packet, the sequence of values including one or more sparsity bytes each equal to a configured sparsity value and one or more non-sparsity bytes each corresponding to a respective data value different from the configured sparsity value. A sub-packet header can be generated for the compressed sub-packet, and indicative of a respective location within the sequence of values of each non-sparsity byte. A packet header can be generated for a plurality of compressed sub-packets, and indicative of the configured sparsity value and respective coding information for each compressed sub-packet. A compressed data packet can be generated to include at least the packet header, the sub-packet header, and the one or more non-sparsity bytes included in the sequence of values.
    Type: Application
    Filed: October 15, 2024
    Publication date: April 10, 2025
    Inventors: Haoping XU, Prajakt KULKARNI, Suze BALATSOS, Zhaohui DU, Shiqi SUN, Xiaoxuan YU, Nanda Kumar ASWATHA KUMAR, Sheng ZHAN
  • Publication number: 20250119418
    Abstract: Example methods and systems for connection establishment in a global server load balancer (GSLB) environment are described. In one example, a computer system may establish a first connection with a first entity and a second connection with the second entity. The first connection may be established based on first parameter information that includes a shared certificate and a first identifier (ID). The second connection may be established based on second parameter information that includes the shared certificate and a second ID. The shared certificate may be shared by multiple entities that include the first entity and a second entity. In response to receiving a first request, a first response may be generated and sent towards the first entity via the first connection. In response to receiving a second request, a second response may be generated and sent towards the second entity via the second connection.
    Type: Application
    Filed: October 8, 2023
    Publication date: April 10, 2025
    Applicant: VMware, Inc.
    Inventors: Ravi Kumar Reddy KOTTAPALLI, Sudarshana KANDACHAR SRIDHARA RAO, Venkata Swamy Babu BUDUMURU, Dinesh Kumar KAMALAKANNAN, Prasanna Kumar SUBRAMANYAM, Vidya KOTEESWARAN, Prashant MISHRA, Santosh SINGH
  • Publication number: 20250114156
    Abstract: The embodiments disclosed herein relate to various medical device components, including components that can be incorporated into robotic and/or in vivo medical devices. Certain embodiments include various modular medical devices for in vivo medical procedures.
    Type: Application
    Filed: October 23, 2024
    Publication date: April 10, 2025
    Inventors: John Wilson, Jeffrey Shasho, Nishant Kumar, Matt Mahin, Chris Santoro, Erik Mumm, Jason Herman, Shane Farritor
  • Publication number: 20250119455
    Abstract: A system for performing secured operations includes a user device and a server. The user device generates a first operation data that comprises the origin of the operation and a unique identifier of a user. The user device communicates the operation data to the server. The server generates, based on the first operation data, one or more first conditional rules that comprise a first rule that indicates the operation is to be executed when a second user requesting to receive a data item is identified. The server determines that one or more first conditional rules are met. In response, the server communicates a signal to the user device, where the signal indicates to transfer the data item to a second user device associated with the second user.
    Type: Application
    Filed: October 6, 2023
    Publication date: April 10, 2025
    Inventors: Abhijit Behera, Gowri Sundar Suriyanarayanan, Maneesh Kumar Sethia
  • Publication number: 20250117763
    Abstract: A computer-implemented real-time payment system for clearing and settlement of transactions is described. The real-time payment system is adapted to implement a method of automated liquidity maintenance. The real-time payment system receives transactions for clearing and settlement from a plurality of participants, each of which has a liquidity position in the real-time payment system. At least some of the participants have a funded liquidity position in a central bank. The real-time payment system determines whether the liquidity position of each of the participants meets predetermined rules. If the liquidity position of any of the participants does not meet a predetermined rule applicable when the determination is made, the system requests an adjustment for that liquidity position so that it complies with that predetermined rule. The real-time payment system also coordinates with the central bank to use one of the funded liquidity positions to support that adjustment to a liquidity position.
    Type: Application
    Filed: October 4, 2024
    Publication date: April 10, 2025
    Inventors: Prasanth Kuruvilla John, German Blanco Gutierrez, Stephen Richard Wright, Vimal Kumar Rajasekaran
  • Publication number: 20250119054
    Abstract: In one embodiment, a method includes receiving DC bus voltage conditions of multiple AC to DC converters of an Input-Series-Output-Parallel power converter during a rectification stage; detecting a peak voltage of each of the DC bus of the multiple AC to DC converters has reached a first threshold voltage, and a Phase Loop Lock locked signal; upon detecting that the PLL locked signal, enabling a first voltage regulation to charge an AC to DC output of each of the multiple AC to DC converters to reach a first reference voltage; determining operating conditions including a load condition and an output voltage condition of multiple Dual Active Bridge (DAB) converters, and a monitored voltage of each of the multiple AC to DC converters; enabling a second voltage regulation of each of the multiple DAB converters to charge a DAB output to reach a second reference voltage based on the operating condition.
    Type: Application
    Filed: December 17, 2024
    Publication date: April 10, 2025
    Inventors: Garry Jean-Pierre, Vijay Bhavaraju, Awneesh Kumar Tripathi, Vasishta Burugula
  • Publication number: 20250119224
    Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may communicate signaling with a network entity, the signaling indicating a first bandwidth size and a second bandwidth size associated with a projection parameter (W1) and a compression parameter (W2), respectively. The second bandwidth size may be less than the first bandwidth size. In some cases, the UE may determine W1 and W2 based on a first machine learning (ML) model and a second ML model, respectively. The UE may project a portion of received channel state information (CSI) associated with the first bandwidth size onto a sub-space defined by W1 and may compress a portion of the projection associated with the second bandwidth size based on W2. The UE may transmit channel state feedback including the projection, the compression of the projection, a compression of W1, a compression of W2, or any combination thereof.
    Type: Application
    Filed: October 10, 2023
    Publication date: April 10, 2025
    Inventors: Pavan Kumar VITTHALADEVUNI, Jay Kumar SUNDARARAJAN, Taesang YOO, Naga BHUSHAN, Krishna Kiran MUKKAVILLI
  • Publication number: 20250117902
    Abstract: In various examples, disclosed techniques use a banding detector neural network to identify the locations and sizes of banding artifacts in pixel regions of an input image. The neural network generates a band size map that identifies at least one banding artifact in the input image. The band size map can include a set of predicted band size values, each of which corresponds to a respective pixel of the input image and represents a distance between edges of a banding artifact. The band size map and the input image are provided as input to a stochastic bilateral blur filter, which generates a de-banded image by applying blurring effects to the input image at the band locations indicated by the band size map. An inverse tone mapping operation is then performed to convert the de-banded image to an image that does not have banding artifacts.
    Type: Application
    Filed: October 6, 2023
    Publication date: April 10, 2025
    Inventors: Donald Lee BRITTAIN, Andrew Ian RUSSELL, Anjul PATNEY, Yinghao XU, Shaveen KUMAR