Back to results
US 11,770,572 B1Granted
Content distribution platform for uploading and linking content to products and services
AssigneeAdrennial Inc.
InventorsSteven Plummer, Stylianos Kapetanakis, Panagiotis Paralakis, Nikolaos Baxevanis, Adam David Gwinnett
Life of this patent
Estimating the term…
Abstract
A content distribution platform is disclosed. The content distribution platform enables content creators to upload video based content onto the platform. Users can then view the videos or shortened versions of the videos. The videos may be classified/categorizes based on the contents of the video. Based on the categorization/classifications, specific product and service recommendations may be made to users. Recommendations can also be made based on tracking user behavior across the platform.
Claims20
A computer implemented method, comprising:
- analyzing, by one or more computing devices and using a first computer vision process, frames of a video uploaded to a content distribution platform to identify a first information from the video, wherein the first information comprises a type of activity being performed in the video;
- analyzing, by the one or more computing devices and using a second computer vision process, the frames of the video to identify a second information from the video, wherein the second information comprises a type of product displayed in the video;
- mapping, by the one or more computing devices and using one or more trained classifiers, one or more categories to the video based on the first information and the second information;
- generating, by the one or more computing devices, a video trailer of the video, wherein the video trailer is mapped to the one or more categories of the video;
- retrieving, by the one or more computing devices, the video trailer based on a search performed using keywords mapped to the one or more categories of the video trailer;
- transmitting, by the one or more computing devices, the video trailer to a client device for display on a graphical user interface (GUI) upon retrieval of the video trailer;
- wherein generating the video trailer is performed by:
- analyzing, by the one or more computing devices, an audio component of the video to determine one or more sound gaps indicating no human speech is taking place in the video;
- extracting, by the one or more computing devices, two-second video clips from the one or more sound gaps;
- and
- assembling, by the one or more computing devices, the two-second video clips to obtain the video trailer.
8 more elements
A non-transitory computer readable medium including instructions that when executed by a computing system, perform operations comprising:
- analyzing, by one or more computing devices and using a first computer vision process, frames of a video uploaded to a content distribution platform to identify a first information from the video, wherein the first information comprises a type of activity being performed in the video;
- analyzing, by the one or more computing devices and using a second computer vision process, frames of the video to identify a second information from the video, wherein the second information comprises a type of product displayed in the video;
- mapping, by the one or more computing devices and using one or more trained classifiers, one or more categories to the video based on the first information and the second information;
- generating, by the one or more computing devices, a video trailer of the video, wherein the video trailer is mapped to the one or more categories of the video;
- retrieving, by the one or more computing devices, the video trailer based on a search performed using keywords mapped to the one or more categories of the video trailer;
- transmitting, by the one or more computing devices, the video trailer to a client device for display on a graphical user interface (GUI) upon retrieval of the video trailer;
- wherein generating the video trailer is performed by:
- analyzing, by the one or more computing devices, an audio component of the video to determine one or more sound gaps indicating no human speech is taking place in the video;
- extracting, by the one or more computing devices, two-second video clips from the one or more sound gaps;
- and
- assembling, by the one or more computing devices, the two-second video clips to obtain the video trailer.
8 more elements
A computing system comprising:
- a memory storing instructions;
- and
- one or more processors, coupled to the memory and configured to process the stored instructions to:
- analyze, using a first computer vision process, frames of a video uploaded to a content distribution platform to identify a first information from the video, wherein the first information comprises a type of activity being performed in the video;
- analyze, using a second computer vision process, frames of the video to identify a second information from the video, wherein the second information comprises a type of product displayed in the video;
- map, using one or more trained classifiers, one or more categories to the video based on the first information and the second information;
- generate a video trailer of the video, wherein the video trailer is mapped to the one or more categories of the video;
- retrieve the video trailer based on a search performed using keywords mapped to the one or more categories of the video trailer;
- transmit the video trailer to a client device for display on a graphical user interface (GUI) upon retrieval of the video trailer;
- wherein generating the video trailer is performed by:
- analyzing an audio component of the video to determine one or more sound gaps indicating no human speech is taking place in the video;
- extracting two-second video clips from the one or more sound gaps;
- and
- assembling the two-second video clips to obtain the video trailer.
11 more elements
Dependencies are inferred from the claim text.