IP Library Granted Patent US 11,882,334
Granted Patent B2
US 11,882,334 · App. 17/028,830 · Granted Jan 23, 2024

Automated user-responsive video content

Inventors: Prudvi Raj Daniyala (Munnekolala Marthahalli, IN); Sandeep Rachoori (Mahadevpura, IN)
Assignee: DISH Network Technologies India Private Limited
H04N21/47202H04N21/44008H04N21/4667H04N21/47217
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,882,334
App. No.
17/028,830
Granted
Jan 23, 2024
Kind
B2
Abstract

Techniques are described for delivery and handling of automated user-responsive video sub-content. For example, a user is consuming video content associated with content-of-interest (COI) identifiers corresponding to certain sub-content relevant to the video content during certain playback time windows. During playback, embodiments use one or more sensors detect dynamic user input. At some time during playback of the video content, some of the COI identifiers are considered to be actively relevant, and detected dynamic user input is determined to invoke at least one of the actively relevant COI identifiers. A COI query can automatically be generated based on the invoked one or more COI identifiers, and a corresponding query response can be automatically generated and output to the user based on response data associated with the invoked one or more COI identifiers.

Claims (56)

1. A method for automated user-responsive video content delivery, the method comprising:

outputting video content to a user via a playback device, the video content temporally associated with content-of-interest (COI) identifiers, such that each COI identifier is defined as actively relevant during a respective playback time window of the video content, each COI identifier corresponding to respective sub-content that is displayed as part of the video content for a respective display duration, each COI associated with a respective stickiness, with a relevance window that includes the respective display duration and extends beyond the respective display duration by an amount of time based on the respective stickiness, and with respective response data;

detecting receipt of dynamic input from the user at a detection time by monitoring a sensor system during the outputting, the detected dynamic input comprising dynamic audio information detected by monitoring interaction by the user with an audio input sensor of the sensor system;

identifying a set of presently active COI identifiers as those of the COI identifiers having respective relevance windows that intersect with the detection time;

analyzing the dynamic input according to the set of presently active COI identifiers automatically to generate a COI query corresponding to at least one of the set of presently active COI identifiers based on determining that the dynamic audio information corresponds to interest by the user in content associated with the at least one of the set of presently active COI identifiers;

generating a query response automatically responsive to the COI query based on the respective response data of the at least one of the set of presently active COI identifiers; and

outputting the query response to the user via the playback device as responsive to the detecting.

2. The method of claim 1 , wherein the analyzing comprises:

generating a set of candidate COI keywords corresponding to the set of presently active COI identifiers;

parsing the dynamic input to identify at least one user trigger word relating to at least one of the set of candidate COI keywords; and

generating the COI query based on the at least one user trigger word, the at least one user trigger word corresponding to the at least one of the set of presently active COI identifiers.

3. The method of claim 1 , wherein the identifying is in response to the detecting.

4. The method of claim 1 , wherein the identifying comprises dynamically updating the set of presently active COI identifiers during the outputting by dynamically identifying those of the COI identifiers as actively relevant during respective playback time windows that intersect with a running playback time of the video content.

5. The method of claim 4 , wherein the detecting comprises monitoring the sensor system during the outputting to detect the receipt of the dynamic input from the user as invoking of at least one of the set of presently active COI identifiers dynamically updated at the running playback time corresponding to the detection time.

6. The method of claim 4 , wherein the outputting further comprises outputting, coincident with the video content, a visual indication of at least a portion of the set of presently active COI identifiers according to the running playback time.

7. The method of claim 1 , wherein the video content comprises the COI identifiers embedded therein.

8. The method of claim 1 , wherein:

the respective response data of the at least one of the set of presently active COI identifiers indicates a set of COI context hooks; and

the query response is generated further according to a set of user-contextual data identified based on the set of COI context hooks.

9. The method of claim 1 , wherein the dynamic input is analyzed according to natural language processing, machine learning, and/or a predefined command structure.

10. The method of claim 1 , further comprising:

analyzing the dynamic input according to the set of presently active COI identifiers to determine whether a valid COI query is generable,

wherein the analyzing the dynamic input to generate the COI query, the generating the query response, and the outputting the query response are performed only responsive to determining that a valid COI query is generable.

11. The method of claim 10 , further comprising:

outputting, responsive to determining that a valid COI query is not generable, an unsuccessful query indication to the user via the playback device.

12. A content delivery appliance comprising:

a network interface configured to receive video content from a content network, the video content temporally associated with content-of-interest (COI) identifiers, such that each COI identifier is defined as actively relevant during a respective playback time window of the video content, each COI identifier corresponding to respective sub-content that is displayed as part of the video content for a respective display duration, each COI associated with a respective stickiness, with a relevance window that includes the respective display duration and extends beyond the respective display duration by an amount of time based on the respective stickiness, and with respective response data;

a playback subsystem including a playback interface configured to couple with a playback device, the playback subsystem to output the video content to a user via the playback device;

a sensor interface configured to couple with one or more sensors and to monitor the one or more sensors during outputting of the video content by the playback subsystem;

an automated responder subsystem coupled with the sensor interface to detect receipt of dynamic input from the user via the one or more sensors at a detection time, the detected dynamic input comprising dynamic audio information detected by monitoring interaction by the user with an audio input sensor of the sensor system, the automated responder subsystem configured to:

identify a set of presently active COI identifiers as those of the COI identifiers having respective relevance windows that intersect with the detection time;

analyze the dynamic input according to the set of presently active COI identifiers automatically to generate a COI query corresponding to at least one of the set of presently active COI identifiers based on determining that the dynamic audio information corresponds to interest by the user in content associated with the at least one of the set of presently active COI identifiers;

generate a query response automatically responsive to the COI query based on the respective response data of the at least one of the set of presently active COI identifiers; and

direct the playback subsystem to output the query response to the user via the playback device as a response to the detecting.

13. The content delivery appliance of claim 12 , further comprising: a data store to store the COI identifiers in association with the video content,

wherein the automated responder subsystem is to identify the set of presently active COI identifiers by querying the data store.

14. The content delivery appliance of claim 12 , wherein the automated responder subsystem is to analyze the dynamic input by:

generating a set of candidate COI keywords corresponding to the set of presently active COI identifiers;

parsing the dynamic input to identify at least one user trigger word relating to at least one of the set of candidate COI keywords; and

generating the COI query based on the at least one user trigger word, the at least one user trigger word corresponding to the at least one of the set of presently active COI identifiers.

15. The content delivery appliance of claim 12 , wherein the automated responder subsystem is to identify the set of presently active COI identifiers by dynamically updating the set of presently active COI identifiers during outputting by the playback subsystem by dynamically identifying those of the COI identifiers as actively relevant during respective playback time windows that intersect with a running playback time of the video content.

16. The content delivery appliance of claim 15 , wherein the automated responder subsystem is to detect receipt of the dynamic input by monitoring the one or more sensors during outputting by the playback subsystem to detect the dynamic input from the user as invoking of at least one of the set of presently active COI identifiers dynamically updated at the running playback time corresponding to the detection time.

17. A system for automated user-responsive video content delivery, the system comprising:

a set of processors;

a processor-readable medium having instructions stored thereon, which, when executed, cause the set of processors to perform steps comprising:

outputting video content to a user via a playback device, the video content temporally associated with content-of-interest (COI) identifiers, such that each COI identifier is defined as actively relevant during a respective playback time window of the video content, each COI identifier corresponding to respective sub-content that is displayed as part of the video content for a respective display duration, each COI associated with a respective stickiness, with a relevance window that includes the respective display duration and extends beyond the respective display duration by an amount of time based on the respective stickiness, and with respective response data;

detecting receipt of dynamic input from the user at a detection time by monitoring a sensor system during the outputting, the detected dynamic input comprising dynamic audio information detected by monitoring interaction by the user with an audio input sensor of the sensor system;

identifying a set of presently active COI identifiers as those of the COI identifiers having respective relevance windows that intersect with the detection time;

analyzing the dynamic input according to the set of presently active COI identifiers automatically to generate a COI query corresponding to at least one of the set of presently active COI identifiers based on determining that the dynamic audio information corresponds to interest by the user in content associated with the at least one of the set of presently active COI identifiers;

generating a query response automatically responsive to the COI query based on the respective response data of the at least one of the set of presently active COI identifiers; and

outputting the query response to the user via the playback device as responsive to the detecting.

18. The system of claim 17 , wherein the instructions, when executed, cause the set of processors to perform the analyzing by:

generating a set of candidate COI keywords corresponding to the set of presently active COI identifiers;

parsing the dynamic input to identify at least one user trigger word relating to at least one of the set of candidate COI keywords; and

generating the COI query based on the at least one user trigger word, the at least one user trigger word corresponding to the at least one of the set of presently active COI identifiers.

19. The system of claim 17 , wherein the instructions, when executed, cause the set of processors to perform the identifying by dynamically updating the set of presently active COI identifiers during the outputting by dynamically identifying those of the COI identifiers as actively relevant during respective playback time windows that intersect with a running playback time of the video content.

Assignments (2)
CHANGE OF NAME Recorded Jul 27, 2022
From: SLING MEDIA PRIVATE LIMITED
To: DISH NETWORK TECHNOLOGIES INDIA PRIVATE LIMITED
Reel/Frame 060647/0281 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 17, 2021
From: DANIYALA, PRUDVI RAJ; RACHOORI, SANDEEP
To: SLING MEDIA PVT. LTD.
Reel/Frame 055294/0666 →
Priority Claims (1)
IN 202041031734 · Jul 24, 2020 · national
Continuity (1)
Related Publication 20220030316A1 · Jan 27, 2022