公开(公告)号：US11941010B2

公开(公告)日：2024-03-26

申请号：US17130556

申请日：2020-12-22

Applicant: International Business Machines Corporation

Inventor： Soumitra Sarkar ,  Md Faisal Mahbub Chowdhury ,  Ruchi Mahindru ,  Gaetano Rossiello ,  Alfio Massimiliano Gliozzo ,  Nicolas Rodolfo Fauceglia

IPC: G06F17/00 ,  G06F7/00 ,  G06F16/2455 ,  G06F16/2457 ,  G06F16/248 ,  G06F16/28 ,  G06N20/00

CPC classification number: G06F16/24578 ,  G06F16/24556 ,  G06F16/248 ,  G06F16/285 ,  G06N20/00

Abstract: Embodiments of the present invention provide a computer system, a computer program product, and a method that comprises analyzing a performed query by identifying a plurality of indicative markers based on a pre-stored classification database associated with the performed query; generating a plurality of facets based on the analysis of the performed query; selecting at least two facets within the generated plurality of facets by determining a quantitative similarity value between each respective facet and the plurality of identified indicative markers associated with the performed query; dynamically ranking the selected facets by prioritizing the selected facets based on a calculated overall score associated with assigned weighted values for each selected facet in the generated plurality of facets using a supervised machine learning algorithm; and displaying the dynamically ranked facets within a user interface of a computing device associated with a user.

公开(公告)号：US11797611B2

公开(公告)日：2023-10-24

申请号：US17369040

申请日：2021-07-07

Applicant: International Business Machines Corporation ,  University of Notre Dame

Inventor： Wenhao Yu ,  Lingfei Wu ,  Yu Deng ,  Qingkai Zeng ,  Ruchi Mahindru ,  Sinem Guven Kaya ,  Meng Jiang

IPC: G06F16/00 ,  G06F16/9032 ,  G06N20/00 ,  G06V30/418 ,  G06F18/2431

CPC classification number: G06F16/90332 ,  G06F18/2431 ,  G06N20/00 ,  G06V30/418

Abstract: An approach for a non-factoid question answering framework across tasks and domains may be provided. The approach may include training a multi-task joint learning model in a general domain. The approach may also include initializing the multi-task joint learning model in a specific target domain. The approach may include tuning the joint learning model in the target domain. The approach may include determining which task of the multiple tasks is more difficult for the multi-task joint learning model to learn. The approach may also include dynamically adjusting the weights of the multi-task joint learning model, allowing the model to concentrate on learning the more difficult learning task.

公开(公告)号：US20220405315A1

公开(公告)日：2022-12-22

申请号：US17354136

申请日：2021-06-22

Applicant: International Business Machines Corporation

Inventor： Ruchi Mahindru ,  Daniela Rosu ,  David Konopnicki

IPC: G06F16/34 ,  G06F16/36 ,  G06N20/00

Abstract: An approach to ranking identified technical solutions summaries may be provided. The approach may include extracting data from technical tickets, subject matter expert reports, and online forum data. The approach may include receiving data relating to prior applications of one or more technical solutions. Steps associated with a technical solution may be included in the information from the prior application of the technical solutions and updated based on the information from prior applications of technical solutions. The approach may include generating a risk score and a cost score for the updated technical solution based on contextual factors associated with a user or machine. The approach may include enriching a static summary for the technical solution with the cost and risk score. The approach may include ranking the enriched summary against multiple potential technical solutions.

公开(公告)号：US11481404B2

公开(公告)日：2022-10-25

申请号：US17022204

申请日：2020-09-16

Applicant: International Business Machines Corporation

Inventor： Md Faisal Mahbub Chowdhury ,  Yu Deng ,  Alfio Massimiliano Gliozzo ,  Ruchi Mahindru ,  Nandana Mihindukulasooriya ,  Nicolas Rodolfo Fauceglia ,  Gaetano Rossiello

IPC: G06F16/2457 ,  G06F16/242

Abstract: A method, system, and computer program product for automated evaluation of information retrieval systems are provided. The method accesses a natural language query from a set of natural language queries. The natural language query is associated with a query difficulty level. The method generates one or more natural language responses to the natural language natural language query. Each natural language response is associated with at least one facet of the plurality of facets. The method generates a set of feedback cues. A set of search results for the natural language query are returned. The set of search results include a highest ranked natural language response of the one or more natural language responses. The method generates an evaluation result for the HCIR system for the query difficulty level based on the one or more natural language responses, the set of search results, and the set of feedback cues.

公开(公告)号：US20210365306A1

公开(公告)日：2021-11-25

申请号：US16880556

申请日：2020-05-21

Applicant: International Business Machines Corporation

Inventor： Rajarshi Haldar ,  Yu Deng ,  Lingfei Wu ,  Ruchi Mahindru ,  Shu Tao

IPC: G06F9/54 ,  G06F40/205 ,  G06F16/38 ,  G06F16/35 ,  G06F16/901 ,  G06N3/08 ,  G06N20/00

Abstract: Computer-implemented techniques for unsupervised event extraction are provided. In one instance, a computer implemented method can include parsing, by a system operatively coupled to a processor, unstructured text comprising event information to identify candidate event components. The computer implemented method can further include employing, by the system, one or more unsupervised machine learning techniques to generate structured event information defining events represented in the unstructured text based on the candidate event components.

公开(公告)号：US11153164B2

公开(公告)日：2021-10-19

申请号：US15398329

申请日：2017-01-04

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： John A. Bivens ,  Min Li ,  Ruchi Mahindru ,  HariGovind V. Ramasamy ,  Yaoping Ruan ,  Valentina Salapura ,  Eugen Schenfeld

IPC: G06F13/00 ,  H04L12/24 ,  H04L29/08 ,  G06F11/07 ,  H04L12/26

Abstract: Various embodiments for performing hardware upgrades in a disaggregated computing environment. A workload is run on a disaggregated computing system while providing a new component to at least one of a plurality of component pools used by the disaggregated computing system. Point-to-point circuit wire level switching is used to switch the disaggregated system from an assigned component residing in a first of the plurality of component pools to the new component residing in a second of the plurality of component pools without interrupting the running workload.

公开(公告)号：US11012423B2

公开(公告)日：2021-05-18

申请号：US16141851

申请日：2018-09-25

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Min Li ,  John A. Bivens ,  Ruchi Mahindru ,  Valentina Salapura ,  Eugen Schenfeld

IPC: H04L29/06 ,  H04L9/14 ,  H04L9/08 ,  G06F13/40

Abstract: Embodiments are provided herein for maximizing resource utilization in a disaggregated computing system. A general purpose link is established between a first sub-plurality of computing elements and a second sub-plurality of computing elements. The first sub-plurality belongs to a first plurality of computing components of a first type and the second sub-plurality belongs to a second plurality of computing components of a second type in the disaggregated computing system. A determination is made that the first and second sub-pluralities of computing elements are assigned to a first tenant having first data communications. The general purpose link is secured to the first tenant while allowing second data communications of a second tenant to pass through the general purpose link concurrent with the first data communications of the first tenant.

公开(公告)号：US11003523B2

公开(公告)日：2021-05-11

申请号：US16431728

申请日：2019-06-04

Applicant: International Business Machines Corporation

Inventor： Long Wang ,  Ruchi Mahindru ,  Soumitra Sarkar ,  Yu Deng

IPC: G06F11/00 ,  G06F11/07 ,  G06F16/23

Abstract: An example operation may include one or more of receiving, by a disaster recovery orchestrator, configuration changes independent from a disaster recovery test schedule, from one or more monitoring agents at each of an information technology system, analyzing incremental configuration changes since a previous disaster recovery test for potential to limit a need for unnecessary disaster recovery retest, determining component level changes at each information technology system that impact disaster recovery test readiness, initiating a partial disaster recovery retest without regard to periodic disaster recovery test schedules, in response to incremental configuration changes that are at the information technology system component-level, and invoking a blockchain service to generate blockchain transactions, the blockchain transactions committing configuration changes, disaster recovery testing actions, and disaster recovery testing results to a shared ledger of a blockchain network.

公开(公告)号：US20210019615A1

公开(公告)日：2021-01-21

申请号：US16516009

申请日：2019-07-18

Applicant: International Business Machines Corporation

Inventor： Tarek Sakakini ,  Yu Deng ,  Anup Kalia ,  Ruchi Mahindru ,  Daniela Rosu ,  Shu Tao

IPC: G06N3/08 ,  G06N3/04

Abstract: Systems, computer-implemented methods, and computer program products that can facilitate extraction of entities having defined lengths of text spans are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a configuration component that defines different hyperparameters of multiple artificial intelligence models, and determines target hyperparameters of an artificial intelligence model based on performance of the multiple artificial intelligence models. The computer executable components can further comprise an application component that employs the artificial intelligence model to extract one or more entities from a data source based on the target hyperparameters.

公开(公告)号：US10893096B2

公开(公告)日：2021-01-12

申请号：US15982589

申请日：2018-05-17

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： John A. Bivens ,  Ruchi Mahindru ,  Eugen Schenfeld ,  Min Li ,  Valentina Salapura

IPC: G06F15/173 ,  H04L29/08

Abstract: Embodiments for optimizing dynamic resource allocations in a disaggregated computing environment. A data heat map associated with a data access pattern of data elements associated with a workload is maintained. The workload is classified into one of a plurality of classes, each class characterized by the data access pattern associated with the workload. The workload is then assigned to a dynamically constructed disaggregated system optimized with resources according to the one of the plurality of classes the workload is classified into to increase efficiency during a performance of the workload.