US 10,945,033 B2Granted

System and method to generate a customized, parameter-based video

AssigneeIdomoo Ltd

InventorDanny Kalish

Life of this patent

Estimating the term…

Loading patent…

Abstract

The present invention provides a method for customizing video based on viewer behaviors, by performing the following steps: receiving/preparing plurality variations of customized video related to one video template, wherein each video variation has different features including at least one of: different scenario scene, different characters, different style, different objects displaying plurality of video variations to plurality of viewers; tracking viewer behavior while watching the video and after watching the video, wherein the viewers are identified by their profile in relation to real time context parameters; grading viewer behavior based on predefined viewers target (behavior) criteria; training a neural network to select video variants having specific features per each video presentation of a specific customizable video template in relation to viewer profile and context parameters, for maximizing viewer behavior grading in relation to said video variant. applying said neural network to a given viewer profile to determine for specific video template the video features for maximizing viewer behavior grading; streaming the determined a video based on determined video features.

Claims20

Dependent claims

A method for customizing video based on behaviors of a plurality of viewers, implemented by one or more processors operatively coupled to a non-transitory computer readable storage device, on which is stored instruction code that when executed cause the one or more processors to perform the following steps:

receiving/preparing plurality variations of customized video related to one customized video template, wherein each customized video variation has different features including at least one of:
different scenario scene, different characters, different style, different objects;
displaying a plurality of customized video variations to the plurality of viewers;
tracking behavior of the plurality of viewers while watching the plurality of customized video variations and after watching the customized video, wherein each of the plurality of viewers has a profile and the plurality of viewers are identified by their profile in relation to real time context parameters;
grading behavior of the plurality of viewers based on predefined viewers target (behavior) criteria;
training a neural network to select customized video variants having specific features per each customized video presentation of a specific customized video template in relation to a profile of one of the plurality of viewers and context parameters, for maximizing behavior grading of the one of the plurality of viewers in relation to one of said customized video variants;
applying said neural network to a profile of one of the plurality of viewers to determine for a specific customized video template the customized video features for maximizing behavior grading of the one of the plurality of viewers;
streaming the customized video based on the determined customized video features.

5 more elements

A system for customizing video based on behaviors of a plurality of viewers, said system comprising a non-transitory storage device and one or more processing devices operatively coupled to the storage device on which are stored engines of instruction code executable by the one or more processors:

customized video variation generation engine for receiving/preparing plurality variations of customized video relate to one customized video template from a customized video variation database, wherein each customized video variation has different features including at least one of:
different scenario, different characters, different style, different objects and displaying a plurality of customized video variation to the plurality of viewers;
behavior tracking engine for tracking behavior of the plurality of viewers while watching the customized video and after watching the customized video, wherein the plurality of viewers have profiles and the plurality of viewers are identified by parameters of their profile retrieved from a viewer profile/cluster groups database;
behavior analyzing engine for grading behavior of the plurality of viewers based on predefined viewers target (behavior) criteria;
neural network engine for training a neural network to select customized video variants having specific features per each customized video presentation of a specific customized video template in relation to a profile of one of the plurality of viewers and context parameters, for maximizing behavior grading of the one of the plurality of viewers in relation to one of said customized video variants and for applying said neural network to the profile of the one of the plurality of viewers to determine for a specific customized video template the customized video features for maximizing behavior grading of the one of the plurality of viewers;
customized video real-time engine for streaming the customized video based on the determined customized video features.

3 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/353,014Filed 14 Mar 2019 · us provisional application
Priority: 14 Mar 2018
Published: US 2019/0289362 A119 Sep 2019
Granted: 9 Mar 2021
Term ends: Not estimatedThe source records don’t support an estimate.

Classification12 codes

H04L 67/306
Profiles: user profiles
H04N 21/44218
Monitoring of end-user related data: detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the…
G06V 10/82
Using pattern recognition or machine learning: using neural networks
G06V 20/46
In video content: extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames