GEOTAGGING STRUCTURED DATA
    9.
    发明公开

    公开(公告)号:US20240102820A1

    公开(公告)日:2024-03-28

    申请号:US18531220

    申请日:2023-12-06

    IPC分类号: G01C21/36 G06F16/29 G06F16/50

    摘要: A method comprises receiving a query via a graphical user interface (GUI); running the query against a gazetteer system to obtain one or more geographical coordinates; causing a presentation in the GUI of a digital map including a set of regions corresponding to a set of geographical coordinates from the one or more geographical coordinates; receiving a selection of a region of the set of regions; causing a presentation in the GUI a geotag dialog for an object corresponding to the region, the object being of an object type in an ontology model and having a plurality of properties; receiving via the geotag dialog a selection of a property of the plurality of properties; associating a geotag with the property, the geotag including a geographical coordinate of the one or more geographical coordinates corresponding to the region, wherein the method is performed by one or more processors.

    Automatic personalized image-based search

    公开(公告)号:US11941044B2

    公开(公告)日:2024-03-26

    申请号:US16259822

    申请日:2019-01-28

    摘要: A method including training a recurrent neural network model to create a trained model based at least in part on: (a) first images associated with first items on a website, (b) first search terms used by users of the website to search for the first items on the website, and (c) personal features of the users. The method also can include receiving an input image that was uploaded by a current user. The method additionally can include obtaining a user encoded representation vector for the current user based on a set of personal features of the current user. The method further can include generating an image encoded representation vector for the input image. The method additionally can include deriving search terms that are personalized to the current user for the one or more items depicted in the input image, using the trained model and based on the user encoded representation vector for the current user and the image encoded representation vector for the input image. Other embodiments are disclosed.