Artificial intelligence-driven carbon dioxide sequestration in the atmosphere

    公开(公告)号:US11927718B2

    公开(公告)日:2024-03-12

    申请号:US17749400

    申请日:2022-05-20

    Applicant: Kyndryl, Inc.

    CPC classification number: G01W1/18 B64C39/024 G08G5/003 B64U2101/35

    Abstract: Aspects of the present disclosure relate generally to reduction in environmental pollution and, more particularly, to systems and method of carbon dioxide (CO2) sequestration in the atmosphere. For example, a computer-implemented method includes receiving, by a computing device, locations of an atmospheric pollutant; determining, by a computing device, a location of a target area of the atmospheric pollutant for sequestration; determining, by the computing device, positioning and flight path data for airborne sequestration devices to sequester the atmospheric pollutant at the location of the target area of the atmospheric pollutant; and deploying, by the computing device, the airborne sequestration devices with reagent according to the positioning and the flight path data to sequester the atmospheric pollutant at the location of the target area of the atmospheric pollutant.

    DYNAMIC NETWORK MANAGEMENT BASED ON PREDICTED USAGE

    公开(公告)号:US20230379267A1

    公开(公告)日:2023-11-23

    申请号:US17749403

    申请日:2022-05-20

    Applicant: Kyndryl, Inc.

    CPC classification number: H04L47/762 H04L47/781 H04L47/822 G06N20/00

    Abstract: A system and method for bandwidth management are provided. In embodiments, a method includes: training, by a computing device, a predictive machine learning (ML) model based on historic network usage data of software applications in a cloud environment and historic business context data; assigning, by the computing device, priority rankings to software application activities of the cloud environment using the predictive ML model based on predicted resource requirements for the software application activities of the cloud environment and predicted contextual scenarios that impact the predicted resource requirements using an input of real-time network usage data of the cloud environment and real-time business context data; and initiating, by the computing device, scheduling of the software application activities based on the priority rankings.

    SCROLLABLE REAL-TIME PRESENTATION DOCUMENT TWIN

    公开(公告)号:US20230273720A1

    公开(公告)日:2023-08-31

    申请号:US17682260

    申请日:2022-02-28

    Applicant: Kyndryl, Inc.

    CPC classification number: G06F3/0485 H04L65/403 H04L65/1096

    Abstract: A method includes: hosting, by a computing device, a videoconference among plural users; receiving, by the computing device, input from a sharing user of the plural users, wherein the input initiates a screenshare in the videoconference; creating, by the computing device, document twins of a document shown in the screenshare; and providing, by the computing device and to other users of the plural users, access to respective ones of the document twins in an interface of the videoconference; wherein each of the other users may scroll within a respective one of the document twins independently of other ones of the other users and independently of the screenshare.

    Data exhaust logging
    56.
    发明授权

    公开(公告)号:US11630867B2

    公开(公告)日:2023-04-18

    申请号:US17461041

    申请日:2021-08-30

    Applicant: KYNDRYL, INC.

    Abstract: A machine learning model repeatedly scans data exhaust for workstations (for which there are retention requirements regarding data exhaust) over a period of time. The machine learning model analyzes the respective data exhaust and the retention requirements to determine respective data exhaust logging parameters for each workstation. The machine learning model monitors respective data exhaust activity for each workstation over a subsequent period of time. An instance is identified in which logging activity of data exhaust for an identified workstation fails the retention requirements. An ameliorative action designed to satisfy the respective retention requirements for the identified workstation is executed.

    Autonomous vehicle management
    57.
    发明授权

    公开(公告)号:US11608074B2

    公开(公告)日:2023-03-21

    申请号:US16176258

    申请日:2018-10-31

    Applicant: Kyndryl, Inc.

    Abstract: A computer-implemented method for controlling a vehicle. The method monitors one or more characteristics of one or more users within the vehicle, and compares the one or more characteristics of the one or more users with one or more corresponding baseline characteristics of the one or more users. The method further determines, based on the comparison, that a difference between the one or more characteristics and the one or more corresponding baseline characteristics of the one or more users exceeds a threshold value, and performs a controlling action associated with the vehicle, wherein the controlling action may be taking a higher level of autonomous control over the vehicle; varying speed and handling of the vehicle; and overriding the one or more characteristics of the one or more users in order to avoid an accident.

    Facilitating client ergonomic support via machine learning

    公开(公告)号:US11580443B2

    公开(公告)日:2023-02-14

    申请号:US16442300

    申请日:2019-06-14

    Applicant: Kyndryl, Inc.

    Abstract: Techniques are described with respect to facilitating client ergonomic support. An associated method includes receiving a plurality of posture datapoints associated with multiple clients and constructing a machine learning knowledge model based upon the plurality of posture datapoints in order to identify a plurality of predefined ergonomic support design elements. The method further includes receiving client-specific posture datapoints associated with a first client and analyzing, via the machine learning knowledge model, the client-specific posture datapoints in view of the plurality of posture datapoints in order to select an initial ergonomic support design element among the plurality of predefined ergonomic support design elements. The method further includes facilitate printing of the initial ergonomic support design element for a seat component associated with the first client. In an embodiment, the method further includes providing at least one ergonomic refinement to the first client based upon ergonomic sensor data.

    Identifying electrical power ports utilizing IoT information and augmented reality

    公开(公告)号:US11573626B2

    公开(公告)日:2023-02-07

    申请号:US16445313

    申请日:2019-06-19

    Applicant: KYNDRYL, INC.

    Abstract: A method for locating an identifying an electrical power port. The method includes one or more computer processors determining that a battery of a first mobile device of a user is less than fully charged. The method further includes identifying one or more Internet-of-Things (IoT)-enabled electrical power ports within a proximity of the first mobile device. The method further includes receiving metadata respectively associated with the one or more IoT-enabled electrical power ports. The method further includes generating one or more augmented reality (AR) elements respectively associated with the one or more IoT-enabled electrical power ports based on the received metadata respectively associated with the one or more IoT-enabled electrical power ports.

    Dynamically creating a composition reference video to support a user activity

    公开(公告)号:US11562568B2

    公开(公告)日:2023-01-24

    申请号:US17303395

    申请日:2021-05-27

    Applicant: KYNDRYL, INC.

    Abstract: A computer-implemented method, a computer program product, and a computer system for dynamically creating a composition reference video to support a user activity. In response to that a user selects a reference video for performing an activity, the computer system identifies a search query of a reference video. The computer system identifies personalized parameters of the user, based on a knowledge corpus user preferences of performing activities, and the search query. The computer system identifies appropriate videos and video transcripts in an online video repository and identifies textual contents through document and text search, based on a prediction about how the user is to perform the activity. The computer system draws series of images based on the textual contents. The computer system normalizes contents from the appropriate videos and the series of images and normalizes voices in the contents from the appropriate videos.

Patent Agency Ranking