Data based truth maintenance
    2.
    发明授权

    公开(公告)号:US11568967B2

    公开(公告)日:2023-01-31

    申请号:US16507215

    申请日:2019-07-10

    申请人: KYNDRYL, INC.

    摘要: A truth maintenance method and system. The method includes receiving by a computer processor, health event data associated with heath care records for patients. The computer processor associates portions of the health event data with associated patients and related records in a truth maintenance system database. The computer processor derives first health related assumption data and retrieves previous health related assumption data derived from and associated with previous portions of previous health event data. The computer processor executes non monotonic logic with respect to the first health related assumption data and the previous health related assumption data. In response, the computer processor generates and stores updated first updated health related assumption data associated with the first health related assumption data and the previous health related assumption data.

    Multi-destination probabilistic data replication

    公开(公告)号:US11556562B1

    公开(公告)日:2023-01-17

    申请号:US17388593

    申请日:2021-07-29

    申请人: Kyndryl, Inc.

    摘要: Disclosed embodiments provide techniques for multi-destination probabilistic data replication. Data transfer occurs over multiple time intervals. A data image to be transferred is divided into chunks. A manifest is created that lists each chunk and specifies an order, such that the data image can be reconstructed at its destination. The manifest is sent to the destination. The chunks may be sent to the destination, or to an aggregator site that then forwards the chunks to the destination. The chunks are reassembled at the destination based on information in the manifest. A probabilistic function is used to select an aggregator site based on an efficacy. The efficacy is based on a reward function that is computed for destinations for each time interval. A data transfer policy is periodically updated with a new efficacy value which is used for adjustment of the probabilistic function.

    Cognitive systematic review (CSR) for smarter cognitive solutions

    公开(公告)号:US11526788B2

    公开(公告)日:2022-12-13

    申请号:US16004597

    申请日:2018-06-11

    申请人: Kyndryl, Inc.

    IPC分类号: G06N5/04 G06N7/08 G06N20/00

    摘要: An approach for determining a veracity of a reported event is provided. In an embodiment, a set of predictor variables is retrieved from a selected use case. Each of these predictor values is a condition that indicates the veracity of the reported event. In addition, a set of hidden predictor variables is generated from a set of unstructured documents related to the reported event using a hidden Markov model that is based on the predictor variables using a cognitive system. These hidden predictor variables are combined with the set of predictor variables to generate a set of updated predictor variables. These updated predictor variables are used by the cognitive system to return a determination of the veracity of the reported event.

    Computer system diagnostic log chain

    公开(公告)号:US11429574B2

    公开(公告)日:2022-08-30

    申请号:US16839261

    申请日:2020-04-03

    摘要: Disclosed embodiments provide a computer-implemented technique for creating a log chain from multiple software component logs. The log chain can include log information from multiple software components that interact with each other. In embodiments, a locality-sensitive hashing technique is used to create a signature of a log chain. Machine-learning systems are trained with log chains generated from test execution, and/or log chains from incidents with deployed software. In embodiments, logs are pre-processed by tokenizing and trimming. Logs from various components that interact with each other may be combined into a temporally sequential log chain. The signature of the log chain may be used to identify additional information about the error from a machine-learning process that was trained on previously generated log chains. In this way, the time required to identify a problem can be significantly reduced, resulting in increased reliability and availability of complex computer systems.

    Dynamic workflow with knowledge graphs

    公开(公告)号:US11314812B2

    公开(公告)日:2022-04-26

    申请号:US16702684

    申请日:2019-12-04

    摘要: Disclosed embodiments provide techniques for computerized technical support. A knowledge graph for a computer application is established. An input query from a user is processed to extract entities used as action identifiers. One or more nodes within the knowledge graph are identified, along with corresponding relationship edges leading to the nodes. When multiple candidate nodes are found that contain information relevant to the input query, a custom clarification statement is created based on the one or more identified relationship edges. The user provides answers to the clarification statement to narrow down which nodes contain the most relevant information. This process may continue, eliminating nodes based on user responses, until a single node remains, corresponding to an action identifier. The action identifier includes action description information that provides technical assistance to a user.

    System and method for health data management with wearable devices

    公开(公告)号:US11158414B2

    公开(公告)日:2021-10-26

    申请号:US16520724

    申请日:2019-07-24

    摘要: Disclosed embodiments provide techniques for identifying gaps in health management data, and combining an estimated data subset with the health management data to fill in gaps in the health management data. The health management data can be derived from a wearable electronic fitness tracking device such as a smart watch or pedometer. The estimated data subset can be derived based on historical data for the individual, average data for a demographic group, crowdsourced, or estimated based on user profile information, and/or portable electronic device information, such as from a smartphone belonging to a user. The estimated data subset is combined with the health management data to form a revised health parameter dataset. The estimated data subset may be sent to a wearable electronic fitness tracking device, which causes the wearable electronic fitness tracking device to initiate a fitness program adjustment based on the revised health parameter dataset.