Automated resolution of over and under-specification in a knowledge graph

    公开(公告)号:US11475318B2

    公开(公告)日:2022-10-18

    申请号:US16425102

    申请日:2019-05-29

    Applicant: KYNDRYL, INC.

    Abstract: Systems and methods for automated resolution of over-specification and under-specification in a knowledge graph are disclosed. In embodiments, a method includes: determining, by a computing device, that a size of an object cluster of a knowledge graph meets a threshold value indicating under-specification of a knowledge base of the knowledge graph; determining, by the computing device, sub-classes for objects of the knowledge graph; re-initializing, by the computing device, the knowledge graph based on the sub-classes to generate a refined knowledge graph, wherein the size of the object cluster is reduced in the refined knowledge graph; and generating, by the computing device, an output based on information determined from the refined knowledge graph.

    Machine learning multimedia conversion assignment

    公开(公告)号:US11301230B2

    公开(公告)日:2022-04-12

    申请号:US15952320

    申请日:2018-04-13

    Applicant: KYNDRYL, INC.

    Abstract: A method and system for improving a machine learning multimedia conversion process is provided. The method includes automatically connecting hardware devices to a server hardware device. Audio and/or video data from a meeting between individuals is recorded form a location and each individual is identified via sensor data. Attributes for each user are identified and the audio and/or video data is converted to text data. Portions of the text data are analyzed and associated with each individual. Action items in the text data are identified and assigned to the individuals based on the attributes. Self-learning software code for executing future multimedia conversion processes is generated based on the assigning and the self-learning software code is modified based on results of executing the future multimedia conversion processes.

    Machine-learned data management between devices

    公开(公告)号:US11449800B2

    公开(公告)日:2022-09-20

    申请号:US16798563

    申请日:2020-02-24

    Applicant: KYNDRYL, INC.

    Abstract: Management of machine-learned data between machine-learning devices is facilitated by a processor(s) obtaining a machine-learned data set of a first device, with the machine-learned data set of the first device being categorized machine-learned information. The processor(s) determines one or more device hardware requirements to use the machine-learned data set, and based on receiving a request to provide the machine-learned data set to a second device, determines whether the second device meets the one or more device hardware requirements to use the machine-learned data set of the first device. Based on determining that the second device meets the one or more device hardware requirements, the processor(s) provides the machine-learned data set of the first device to the second device to provide the categorized machine-learned information of the first device to the second device for use by the second device.

    Customizing content delivery through cognitive analysis

    公开(公告)号:US11314475B2

    公开(公告)日:2022-04-26

    申请号:US16197885

    申请日:2018-11-21

    Applicant: Kyndryl, Inc.

    Abstract: Approaches presented herein enable customization of content being consumed at a location. More specifically, a plurality of participants is identified as being located within an area. A data source corresponding to each of at least two participants is analyzed for preferences of the participants. Based on this analysis, a set of preferences for the participants is mapped, and this mapping includes linking related preferences of different participants. A sentiment of the plurality of participants is identified based on a real-time data feed that captures actions of the plurality of participants located within the area. A scored set of content is selected based on the mapped set of preferences and the identified sentiment of the plurality of participants.

    Data security across data residency restriction boundaries

    公开(公告)号:US11855995B2

    公开(公告)日:2023-12-26

    申请号:US18060839

    申请日:2022-12-01

    Applicant: KYNDRYL, INC.

    CPC classification number: H04L63/102 G06F21/6218

    Abstract: Data security across data residency restriction boundaries is provided by obtaining and profiling a dataset on which a desired analysis is to be performed, with some results of the desired analysis to be transferred from one location to another, the dataset subject to data residency restrictions that restrict transfer of the dataset across a boundary to the another location, and the profiling identifying a profile level for the dataset, then automatically generating a container image based on the profile level and the data residency restrictions that restrict the transfer of the dataset across the boundary, the container image configured for instantiation and execution to process the dataset into a reformatted dataset not restricted by the data residency restrictions for transfer across the boundary, and storing the container image to a container registry.

    Managing data and data usage in IoT network

    公开(公告)号:US11457032B2

    公开(公告)日:2022-09-27

    申请号:US16421156

    申请日:2019-05-23

    Applicant: KYNDRYL, INC.

    Abstract: In an approach, a processor receives from a network device a request. A processor obtains from a database a device profile for the network device. A processor determines whether the device profile of the network device has a data usage pattern related to data identified by a data identifier. In response to determining the device profile has a related data usage pattern, a processor receives the related data usage pattern from the database. In response to determining the device profile does not have a related data usage pattern, a processor obtains a device type profile from the database. A processor classifies the data usage request based on at least one of the device profile and the device type profile. A processor executes a security action based on the classification of the data usage request. A processor stores the data usage request and executed security action to the database.

Patent Agency Ranking