Resource allocation based on a contextual scenario

    公开(公告)号:GB2604973A

    公开(公告)日:2022-09-21

    申请号:GB202116549

    申请日:2021-11-17

    Applicant: IBM

    Abstract: A processor may analyze, using an AI system, an application, where the application includes one or more application modules. The processor may determine, using the AI system, that an application module is critical based on a contextual scenario. The AI system may be trained utilizing data regarding heat generation of hardware on which the application module is operating. The processor may identify, using the AI system, required resources of the hardware for the application module to function during the contextual scenario. The processor may allocate an availability of the required resources for the application module.

    Bioprinted living tissue with therapy capability

    公开(公告)号:GB2611437A

    公开(公告)日:2023-04-05

    申请号:GB202218055

    申请日:2021-04-30

    Applicant: IBM

    Abstract: An artificial tongue is provided. The artificial tongue includes tongue tissue formed by a bioprinting process, an antenna embedded within the tongue tissue and configured to wirelessly receive power from an external device, a processor embedded within the tongue tissue and operatively coupled to the antenna, and a piezoelectric element embedded within the tongue tissue and operatively coupled to the processor. The piezoelectric element is configured to deform in response to an applied electric bias, and the processor is configured to cause the electric bias to be applied to the piezoelectric element based on the power received by the antenna.

    Electronic cloth for generating power

    公开(公告)号:GB2602380A

    公开(公告)日:2022-06-29

    申请号:GB202115057

    申请日:2021-10-21

    Applicant: IBM

    Abstract: A method, a computer program product, and a computer system for supplying power to a device that includes generating power from movement of one or more metal coils relative to one or more pieces of cloth containing one or more electronic threads and transferring the generated power to a device. The one or more coils may be copper coils or may be tattoos applied to a user’s skin. The cloth may comprise an article of clothing, a bed sheet, a bed cover or a curtain. The coils and pieces of cloth may be waterproof, and the coils may be located around a washing drum of a washing machine.

    Image encryption
    5.
    发明专利

    公开(公告)号:GB2630253B

    公开(公告)日:2025-04-30

    申请号:GB202413401

    申请日:2023-03-21

    Applicant: IBM

    Abstract: Image data encryption by receiving first image data corresponding to a first image having a first image size, compressing the first image data, yielding second image data corresponding to a second image having a second image size, augmenting the second image data yielding third image data corresponding to a third image having the first image size, determining coordinates of a location of the second image within the third image, encrypting the third image data according to the coordinates, providing the encrypted third image data to a decoder by a first communications channel, and providing the coordinates of the second image within the third image to the decoder by a second communications channel.

    Self-learning artificial intelligence voice response based on user behavior during injection

    公开(公告)号:GB2603249A

    公开(公告)日:2022-08-03

    申请号:GB202115855

    申请日:2021-11-04

    Applicant: IBM

    Abstract: A system is provided for recommending guidance instructions to a user. The system includes a memory 312 having computer readable instructions and a processor 302 for executing the computer readable instructions. The computer readable instructions control the processor to perform operations of monitoring an ongoing task comprising at least one act performed by a user, generating a user image 434,485 depicting the user performing the ongoing task, and displaying the image of the ongoing task. The system analyses the ongoing task and generates an augmented image 500 depicting how to correctly perform the act. The augmented image is overlaid on the user image so that the augmented image is displayed simultaneously with the ongoing task to direct the user to progress the ongoing task. The augmented image may be generated and overlaid on the user image in response to the system detecting an incorrectly performed act.

    Time controlled medication
    9.
    发明专利

    公开(公告)号:GB2602717A

    公开(公告)日:2022-07-13

    申请号:GB202116124

    申请日:2021-11-10

    Applicant: IBM

    Abstract: A method, a computer program product, and a computer system provide medications to a patient with a time gap including determining a dissolving pattern for the patient. The dissolving pattern includes a medication dissolving rate for a first medication prescribed to the patient and a filler dissolving rate for a filler selected so that the time gap is elapsed prior to a second medication being provided after the first medication. The medication dissolving rate and the filler dissolving rate are specific to the patient. The method includes determining dimensions of the first medication to correspond to a dosage of the prescribed first medication and dimensions of the filler to correspond to the time gap. The method includes providing a pill including at least the first medication and the filler, the first medication surrounding the filler such that the first medication is dissolved prior to the filler being dissolved. The pill may include multiple medications. The pill may be a signal pill comprising an edible electronic circuit configured to provide an alert.

    Optimization of lip syncing in natural language translated video

    公开(公告)号:GB2625696A

    公开(公告)日:2024-06-26

    申请号:GB202405450

    申请日:2022-09-22

    Applicant: IBM

    Abstract: An approach for generating an optimized video of a speaker, translated from a source language into a target language with the speaker's lips synchronized to the translated speech, while balancing optimization of the translation into a target language. A source video may be fed into a neural machine translation model. The model may synthesize a plurality of potential translations.The translations may be received by a generative adversarial network which generates video for each translation and classifies the translations as in-sync or out of sync. A lip-syncing score may be for each of the generated videos that are classified as in-sync.

Patent Agency Ranking