GENERATING ADAPTIVE MATCH KEYS BASED ON ESTIMATING COUNTS

    公开(公告)号:US20210124779A1

    公开(公告)日:2021-04-29

    申请号:US16661715

    申请日:2019-10-23

    Abstract: A system creates a graph of nodes connected by edges, the nodes including: i) a first node associated with a first value and a count of the first value, and ii) a second node associated with a second value and a count of the second value, the edges including an edge that connects the first and second nodes and is associated with a count of instances of the first value being stored with the second value. The system includes each node and each associated with clique count less than clique threshold in keys sets and deletes each node and each edge associated with clique count less than clique threshold. The system identifies triplet nodes connected by triplet edges. If estimated clique count for triplet values represented by triplet nodes is less than clique threshold, the system includes triplet values in keys set and identify triplet of nodes as analyzed.

    Dynamically balancing partitions within a distributed streaming storage platform

    公开(公告)号:US10992740B2

    公开(公告)日:2021-04-27

    申请号:US15979091

    申请日:2018-05-14

    Abstract: Described is a system that improves the performance of brokers that store partitions of data within a distributed data streaming platform by performing an efficient data redistribution process. The system may obtain data (e.g. metadata) describing the distribution storage partitions amongst storage brokers and determine the current (or initial) distribution may negatively impact the performance of the platform. Accordingly, the system may perform an efficient redistribution by performing a particular sequence of partition reassignments amongst brokers.

    SYSTEMS AND METHODS OF GENERATING PHOTOREALISTIC GARMENT TRANSFERENCE IN IMAGES

    公开(公告)号:US20210118149A1

    公开(公告)日:2021-04-22

    申请号:US16658206

    申请日:2019-10-21

    Abstract: Systems and methods are provided for determining a first semantic segmentation image of a first image, wherein the first image includes at least a portion of a person wearing a first fashion item. A plurality of keypoints of the person's body may be determined in the first image. Using the determined first semantic segmentation image, the determined keypoints, and a second image that includes a second fashion item, a second semantic segmentation image of the person in the first image with the second fashion item of the second image may be generated. The first image may be masked to occlude pixels of the first fashion item that is to be replaced with the second fashion item. Using the masked first image, the second semantic segmentation image, and the second image that includes the second fashion item, a third image may be generated that includes the person with the second fashion item.

    MULTI-LABEL PRODUCT CATEGORIZATION
    535.
    发明申请

    公开(公告)号:US20210118024A1

    公开(公告)日:2021-04-22

    申请号:US16658315

    申请日:2019-10-21

    Abstract: Systems, device and techniques are disclosed for multi-label product categorization. A catalog entry and a list of categories may be received. The catalog entry may be associated with an item. A textual description may be generated by comparing words in the catalog entry to existing vocabularies of words and applying part-of-speech tagging to the catalog entry. A feature vector may be generated from the textual description by applying any of token frequency feature creation, term frequency-inverse document frequency feature creation, and pre-trained word embeddings to the textual description. A set of probabilities may be determined by inputting the feature vector into a machine learning model. The set of probabilities may include a probability for each category in the list of categories.

    Customizing sequences of content objects

    公开(公告)号:US10984665B2

    公开(公告)日:2021-04-20

    申请号:US15479729

    申请日:2017-04-05

    Abstract: Disclosed are examples of systems, apparatus, methods, and computer program products customizing sequences of content objects in an educational content management system. In some implementations, educational content objects can be displayed. A first educational content object selection can be processed. A content object sequence can be generated or updated and the first educational content object can be added to the content object sequence. A second educational content object can be added to the content object sequence. The content object sequence can be shared with a user of an enterprise learning system.

    Predicting entities for search query results

    公开(公告)号:US10970336B2

    公开(公告)日:2021-04-06

    申请号:US16049559

    申请日:2018-07-30

    Abstract: For a database accessible by a plurality of separate organizations, a system is provided for predicting entities for database query results. The system includes a multi-layer neural network. The system is configured to receive a query encoding for one or more previous queries made into the database, a user entity view frequency encoding for a frequency of views by one or more users, and an organization encoding for one or more separate organizations accessing the database; and based on the query encoding, the user entity view frequency encoding, and the organization encoding, generate a neural model for predicting entities for results to a present query into the database. In some embodiments, the neural model is global across the separate organizations accessing the database.

Patent Agency Ranking