Abnormal video filtering
    31.
    发明授权

    公开(公告)号:US10922550B2

    公开(公告)日:2021-02-16

    申请号:US16408616

    申请日:2019-05-10

    Abstract: Methods, systems and computer program products for flagging abnormal videos are provided. Aspects include training an image recognition model based on a plurality of images that depict one or more of a plurality of subjects. Aspects also include generating a normal subject relationship graph representing normal relationships between the plurality of subjects by applying the image recognition model to a plurality of training videos and a test subject relationship graph representing test relationships between subjects depicted in a test video by applying the image recognition model to the test video. Each normal relationship is associated with a strength value. Responsive to determining that a difference between a strength value associated with a first normal relationship and a strength value associated with a corresponding first test relationship exceeds a predetermined threshold, aspects include flagging the test video as being abnormal.

    SELF-ADAPTIVE WEB CRAWLING AND TEXT EXTRACTION

    公开(公告)号:US20190303501A1

    公开(公告)日:2019-10-03

    申请号:US15936666

    申请日:2018-03-27

    Abstract: A method, computer system, and a computer program product for crawling and extracting main content from a web page is provided. The present invention may include retrieving a HTML document associated with a web page. The present invention may then include identifying at least one entry point located in the retrieved HTML document by utilizing a self-adaptive entry point locator. The present invention may also include extracting a main content article associated with the retrieved HTML document based on the identified at least one entry point. The present invention may further include presenting the extracted main content associated with the retrieved HTML document to the user.

    Data migration for applications on a mobile device

    公开(公告)号:US10353617B2

    公开(公告)日:2019-07-16

    申请号:US15668056

    申请日:2017-08-03

    Abstract: In various embodiments, a computer-implemented method includes identifying data files in external storage, where the data files correspond to a computer software application (application) on a mobile device and where the data files were previously stored on the mobile device. The method may also include sorting the data files into different access levels, where the access levels designate a hierarchy for the data files. The method may also include predicting the sorted data files that will be accessed on the mobile device using a prediction engine. The method may also include locating, in response to the predicting, the predicted data files in the external storage. The method may also include migrating the predicted data files from the external storage to the mobile device, where the migrating is done in order of the access levels.

    Data migration for applications on a mobile device

    公开(公告)号:US10248355B2

    公开(公告)日:2019-04-02

    申请号:US15438994

    申请日:2017-02-22

    Abstract: In various embodiments, a computer-implemented method includes identifying computer software applications (applications) on a mobile device. The method may also include generating migration profiles for the applications, where each application corresponds (corresponding application) to a migration profile and where the migration profile includes data files about the corresponding application. The method may also include monitoring storage space of the applications on the mobile device, where the monitoring includes identifying data files of the applications. The method may also include calculating an amount of storage space to determine whether there is a shortage of storage space for the data files. The method may also include, in response to calculating that there is a shortage of storage space, determining when the data files will be migrated. The method may also include, in response to determining when the data files will be migrated, migrating the data files to external storage.

Patent Agency Ranking