中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

17 records (took 0.018 seconds)

    Automated Knowledge Graph Based Regression Scope Identification
    3.
    发明公开
    Automated Knowledge Graph Based Regression Scope Identification 审中-公开

    公开(公告)号：US20230305815A1

    公开(公告)日：2023-09-28

    申请号：US17700905

    申请日：2022-03-22

    Applicant: International Business Machines Corporation

    Inventor： Yuan Li ,  Chao Yu ,  Shen Qi ,  Tao Liu ,  Qiang He ,  Nuo Xu

    IPC: G06F8/30

    CPC classification number: G06F8/30

    Abstract: Mechanisms are provided to automatically identify a regression scope of a requirements specification for at least one functionality of a software product. A first knowledge graph, having function entities, is generated of the requirements specification specifying functional requirements for a software product and a first vector representation is generated for the function entities. Code entities for existing code for the software product are generated that comprise features associated with portions of the existing code, and a second vector representation is generated for these code entities. Code entities are linked to function entities based on a vector similarity analysis between the first vector representation and the second vector representation. A regression scope knowledge graph output is generated, based on the linked code entities and function entities, that depicts relationships between function entities corresponding to the functional requirements with code entities corresponding to portions of existing code for the software product.

    Predictively provisioning cloud computing resources for virtual machines
    4.
    发明授权
    Predictively provisioning cloud computing resources for virtual machines 有权

    公开(公告)号：US11099877B2

    公开(公告)日：2021-08-24

    申请号：US16456063

    申请日：2019-06-28

    Applicant: International Business Machines Corporation

    Inventor： Zhong Qi Feng ,  Jiang Tao Li ,  Yi Bin Wang ,  Chao Yu ,  Qing Feng Zhang

    IPC: G06F9/455 ,  G06F9/48 ,  G06F9/50 ,  G06N5/00 ,  G06N20/00 ,  H04L29/08 ,  H04L29/06 ,  G06F11/34 ,  G06F11/30 ,  G06F11/00

    Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: predictively provisioning, by one or more processor, cloud computing resources of a cloud computing environment for at least one virtual machine; and initializing, by the one or more processor, the at least one virtual machine with the provisioned cloud computing resources of the cloud computing environment. In one embodiment, the predictively provisioning may include: receiving historical utilization information of multiple virtual machines of the cloud computing environment, the multiple virtual machines having similar characteristics to the at least one virtual machine; and determining the cloud computing resources for the at least one virtual machine using the historical utilization information of the multiple virtual machines. In another embodiment, the predictively may include updating a provisioning database with the historical utilization information of the multiple virtual machines of the cloud computing environment.

    ADAPTIVELY COMPRESSING A DEEP LEARNING MODEL
    5.
    发明申请
    ADAPTIVELY COMPRESSING A DEEP LEARNING MODEL 有权

    公开(公告)号：US20230103149A1

    公开(公告)日：2023-03-30

    申请号：US17449652

    申请日：2021-09-30

    Applicant: International Business Machines Corporation

    Inventor： Chao Yu ,  Kun Yan Yin ,  Ming Jin Chen ,  Teng Sun ,  Guang Qing Zhong

    IPC: G06N3/04

    Abstract: An approach is provided for adaptively compressing a deep learning model. An original deep learning model for different Internet of Things (IoT) devices is determined. Device information is collected from the IoT devices. Based on the device information, multiple recommendation engines are selected from a set of recommendation engines. Compression factor combinations are determined by using the multiple recommendation engines. Compression ratios and model accuracies for the compression factor combinations are determined. Based on the compression ratios and the model accuracies, an optimal compression factor combination is selected from the compression factor combinations. A compressed deep learning model is generated by compressing the original deep learning model by using the optimal compression factor. The compressed deep learning model is deployed to the IoT devices.

    Automatic image annotations
    6.
    发明授权
    Automatic image annotations 有权

    公开(公告)号：US11615618B2

    公开(公告)日：2023-03-28

    申请号：US17225165

    申请日：2021-04-08

    Applicant: International Business Machines Corporation

    Inventor： Kun Yan Yin ,  Chao Yu ,  Ming Jin Chen ,  Teng Sun ,  Hong Bing Zhang

    IPC: G06K9/62 ,  G06V20/20 ,  G06V10/46

    Abstract: A computer-implemented method for annotating images is disclosed. The computer-implemented method includes generating a saliency map corresponding to an input image, wherein the input image is an image that requires annotation, generating a behavior saliency map, wherein the behavior saliency map is a saliency map formed from an average of a plurality of objects contained within respective bounding boxes of a plurality of sample images, generating a historical saliency map, wherein the historical saliency map is a saliency map formed from an average of a plurality of tagged objects in the plurality of sample images, fusing the saliency map corresponding to the input image, the behavior saliency map, and the historical saliency map to form a fused saliency map, and generating, based on the fused saliency map, a bounding box around an object in the input image.

    AUTOMATIC IMAGE ANNOTATIONS
    7.
    发明申请
    AUTOMATIC IMAGE ANNOTATIONS 有权

    公开(公告)号：US20220327312A1

    公开(公告)日：2022-10-13

    申请号：US17225165

    申请日：2021-04-08

    Applicant: International Business Machines Corporation

    Inventor： Kun Yan Yin ,  Chao Yu ,  Ming Jin Chen ,  Teng Sun ,  Hong Bing Zhang

    IPC: G06K9/00 ,  G06K9/46 ,  G06K9/62

    Abstract: A computer-implemented method for annotating images is disclosed. The computer-implemented method includes generating a saliency map corresponding to an input image, wherein the input image is an image that requires annotation, generating a behavior saliency map, wherein the behavior saliency map is a saliency map formed from an average of a plurality of objects contained within respective bounding boxes of a plurality of sample images, generating a historical saliency map, wherein the historical saliency map is a saliency map formed from an average of a plurality of tagged objects in the plurality of sample images, fusing the saliency map corresponding to the input image, the behavior saliency map, and the historical saliency map to form a fused saliency map, and generating, based on the fused saliency map, a bounding box around an object in the input image.

    MIGRATION OF APPLICATIONS TO A COMPUTING ENVIRONMENT
    8.
    发明申请
    MIGRATION OF APPLICATIONS TO A COMPUTING ENVIRONMENT 审中-公开

    公开(公告)号：US20190149617A1

    公开(公告)日：2019-05-16

    申请号：US15812347

    申请日：2017-11-14

    Applicant: International Business Machines Corporation

    Inventor： Xue Feng Gao ,  Chao Yu ,  Qing Feng Zhang ,  Jin Rong Zhao

    IPC: H04L29/08 ,  G06F9/445

    Abstract: A method of migrating an application to a computing environment including: obtaining a service topology and a deployment sequence from an existing application; choosing a deployment preference, each deployment preference containing factors and a weight of each of the factors; outputting the service topology and the deployment preference; reading service records for the chosen service topology and deployment preference from a repository, the service records containing a value score and weight mapping information of each factor of each service record; performing a mock conversion of migrating the application to the computing environment; adjusting the value score and weight mapping of the service records according to the results of the mock conversion; responsive to a user choosing one service record representing a solution for migrating the application to the computing environment, generating files for the solution; and deploying the solution into the computing environment using the files.

    DEPLOYING PARALLELIZABLE DEEP LEARNING MODELS BY ADAPTING TO THE COMPUTING DEVICES
    10.
    发明申请
    DEPLOYING PARALLELIZABLE DEEP LEARNING MODELS BY ADAPTING TO THE COMPUTING DEVICES 有权

    公开(公告)号：US20220351020A1

    公开(公告)日：2022-11-03

    申请号：US17245541

    申请日：2021-04-30

    Applicant: International Business Machines Corporation

    Inventor： Kun Yan Yin ,  Chao Yu ,  Ming Jin Chen ,  Teng Sun ,  Xiao Ye Li

    IPC: G06N3/04

    Abstract: In an approach to deploying parallelizable deep learning models by adapting to the computing devices, a deep learning model is split into a plurality of slices, where each slice can exchange data with related slices. Virtual models are created from the plurality of slices, where the virtual models are based on capabilities of a plurality of devices on which the one or more virtual models are to be deployed, and further where each virtual model contains each slice of the plurality of slices. The one or more virtual models are stored in a cache. Responsive to determining that the deep learning model is to be deployed on one or more devices, a candidate model is selected from the virtual models in the cache, where the selection is based on information from a device monitor about the devices.

Patent Agency Ranking