SYSTEMS AND METHODS FOR SYNTHETIC DATA GENERATION

    公开(公告)号:US20200012933A1

    公开(公告)日:2020-01-09

    申请号:US16151407

    申请日:2018-10-04

    IPC分类号: G06N3/08 G06F21/62

    摘要: A cloud computing system can be configured to generate data models. A model optimizer of the cloud computing system can provision computing resources of the cloud computing system with a data model. A dataset generator of the cloud computing system can generate a synthetic dataset for training the data model. The computing resources can train the data model using the synthetic dataset. The model optimizer can store the data model and metadata of the data model in a model storage. The cloud computing system can receive production data from a data source by a production instance of the cloud computing system using a common file system. The production data can be processed using the data model by the production instance. The computing resources, the dataset generator, and the model optimizer can be hosted by separate virtual computing instances of the cloud computing system.

    SYSTEM AND TECHNIQUES FOR DIGITAL DATA LINEAGE VERIFICATION

    公开(公告)号:US20230050601A1

    公开(公告)日:2023-02-16

    申请号:US17979257

    申请日:2022-11-02

    摘要: Disclosed are examples for providing functions to receive a media file to be stored in a media repository. In the examples, a location in the media repository may be assigned to the media file. A media file address in a blockchain platform may be assigned to the media file. Metadata including the assigned location in the media repository and the assigned media file address in the blockchain platform may be added to the media file. A media file hash value may be generated by applying a hash function to the media file including the metadata. The media file hash value may be included in a message and uploaded to the assigned media file address in the blockchain platform as a transaction in the blockchain. An indication that the media file is uploaded to the media repository may be delivered to a subscriber device from which the media file was received.

    GENERATING SYNTHETIC IMAGES AS TRAINING DATASET FOR A MACHINE LEARNING NETWORK

    公开(公告)号:US20210183069A1

    公开(公告)日:2021-06-17

    申请号:US17249378

    申请日:2021-03-01

    摘要: A method may include identifying a first image for training a deep learning network, wherein the first image includes at least one target object associated with at least one location in the first image, and wherein the first image is associated with a mask image; determining a set of deformations to create a training set of deformed images, wherein the training set is to be used to train the deep learning network; generating the training set of deformed images by applying the set of deformations to the first image; and generating a set of deformed mask images by applying the set of deformations to the mask image, wherein each deformed image of the training set of deformed images is associated with a respective mask image to identify the location of the at least one target object in each deformed image.

    REAL-TIME SYNTHETICALLY GENERATED VIDEO FROM STILL FRAMES

    公开(公告)号:US20210120285A9

    公开(公告)日:2021-04-22

    申请号:US16457670

    申请日:2019-06-28

    摘要: Systems and methods for generating synthetic video are disclosed. For example, a system may include a memory unit and a processor configured to execute the instructions to perform operations. The operations may include receiving video data, normalizing image frames, generating difference images, and generating an image sequence generator model. The operations may include training an autoencoder model using difference images, the autoencoder comprising an encoder model and a decoder model. The operations may include identifying a seed image frame and generating a seed difference image from the seed image frame. The operations may include generating, by the image sequence generator model, synthetic difference images based on the seed difference image. In some aspects, the operations may include using the decoder model to synthetic normalized image frames from the synthetic difference images. The operations may include generating synthetic video by adding background to the synthetic normalized image frames.

    SYSTEM AND TECHNIQUES FOR DIGITAL DATA LINEAGE VERIFICATION

    公开(公告)号:US20210037270A1

    公开(公告)日:2021-02-04

    申请号:US17063843

    申请日:2020-10-06

    摘要: Disclosed are examples for providing functions to receive a media file to be stored in a media repository. In the examples, a location in the media repository may be assigned to the media file. A media file address in a blockchain platform may be assigned to the media file. Metadata including the assigned location in the media repository and the assigned media file address in the blockchain platform may be added to the media file. A media file hash value may be generated by applying a hash function to the media file including the metadata. The media file hash value may be included in a message and uploaded to the assigned media file address in the blockchain platform as a transaction in the blockchain. An indication that the media file is uploaded to the media repository may be delivered to a subscriber device from which the media file was received.

    RELATION-BASED SYSTEMS AND METHODS FOR FRAUD DETECTION AND EVALUATION

    公开(公告)号:US20210012346A1

    公开(公告)日:2021-01-14

    申请号:US16507147

    申请日:2019-07-10

    IPC分类号: G06Q20/40 G06F16/901

    摘要: A method for detecting fraud is provided in which a graph database of transaction relationships is constructed using transaction information for a plurality of transactions. Using the graph database, a plurality of account holder identifiers are associated into an account holder group. When transaction information for a new transaction associated with a transaction account holder identifier is received, a determination is made as to whether the transaction account holder identifier is in the account holder group. Responsive to a determination that the transaction account holder identifier is included in the account holder group, the new transaction information is compared to the transaction information for the account holder group and a fraud factor is determined for the new transaction. The fraud factor is indicative of a degree of similarity to the transaction information of the account holder group.