IP Library Granted Patent US 12,666,121
Granted Patent B1
US 12,666,121 · App. 18/504,110 · Granted Jun 23, 2026

Event broadcast natural language interface

Inventors: Ziv Rader (Tel Aviv, IL); Bar Segev (Petah Tikva, IL); Yossi Biton (Rosh Haayin, IL); Avi Avraham Ben-Cohen (Holon, IL); Matan Karklinsky (Zur Hadassa, IL)
Assignee: Amazon Technologies, Inc.
H04N21/8549H04N21/4312H04N21/47217
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 12,666,121
App. No.
18/504,110
Filed
Nov 7, 2023
Granted
Jun 23, 2026
Kind
B1
Art Unit
2425
USPC
725/38
Abstract

The application describes systems and methods for accepting a request in a natural language command to retrieve and presentation information regarding an event broadcast. The natural language command can be processed by a natural language processor to identify moment metadata, such as a moment type from the event broadcast. The system can utilize the moment type to retrieve data compiled by components of the system to create a media representation. The media representation can be created to satisfy a requested presentation type identified by the natural language command and interpreted by the natural language processor. The media representation can then be presented to the user.

Claims (45)

1 . A method comprising:

receiving data of an event broadcast over a network, wherein the data is stored in data storage accessible by a natural language processor;

prior to receiving a natural language command, normalizing the data of the event broadcast, wherein normalizing the data adjusts audio characteristics and video characteristics of the data as compared to the data as received;

identifying event broadcast metadata associated with the event broadcast from the normalized data;

receiving a user request from a user, wherein the user request includes the natural language command related to the event broadcast, and wherein the natural language command comprises a first condition and a second condition;

providing the natural language command as an input to the natural language processor, wherein providing the natural language command as the input to the natural language processor causes the natural language processor to generate a response to the natural language command by:

identifying moment metadata of the event broadcast metadata requested by the natural language command that satisfies the first condition and the second condition, and

determining a presentation type defined by the natural language command;

retrieving, from the data storage, a subset of the data of the event broadcast, wherein the subset of the data of the event broadcast corresponds to the identified moment metadata;

creating a media representation of the subset of the data, wherein the media representation is created according to the presentation type defined by the natural language command; and

causing a user device to present the media representation of the subset of the data.

2 . The method of claim 1 , wherein the subset of the data of the event broadcast includes one or more moment clips from the event broadcast.

3 . The method of claim 2 , wherein creating the media representation includes combining the one or more moment clips into a moment reel to be presented to the user.

4 . The method of claim 1 , wherein causing a user device to present the media representation further comprises causing the user device to present a graphical overlay on the event broadcast as the event broadcast is being presented for the user.

5 . The method of claim 1 , wherein the user request is a text or a speech request.

6 . The method of claim 1 , wherein the subset of the data can include closed captioning data interpreted from the event broadcast by the natural language processor.

7 . A non-transitory computer-readable medium storing instructions that, when executed by a computing system within a cloud provider network, cause the computing system to perform operations comprising:

prior to receiving a natural language command, adjusting audio characteristics and video characteristics of data of an event broadcast as compared to the data as received;

identifying event broadcast metadata associated with the event broadcast from the normalized data;

receiving a request, wherein the request includes the natural language command related to the event broadcast of an event;

providing the natural language command as an input to a natural language processor, wherein providing the natural language command as the input to the natural language processor causes the natural language processor to generate a response to the natural language command by identifying a characteristic of the event broadcast metadata requested by the natural language command, and wherein the natural language command comprises a first condition and a second condition;

retrieving a subset of a set of data of the event broadcast, wherein the subset of the set of the data corresponds to the characteristic;

creating a media representation of the subset of the set of data of the event that satisfies the request; and

causing a user device to present the media representation of the subset of the set of data.

8 . The non-transitory computer-readable medium of claim 7 , wherein the characteristic is associated with moment metadata.

9 . The non-transitory computer-readable medium of claim 7 , wherein the natural language command further identifies a presentation type defined by the natural language command.

10 . The non-transitory computer-readable medium of claim 9 , wherein the media representation is created according to the presentation type.

11 . The non-transitory computer-readable medium of claim 7 , wherein the subset of the set of data of the event broadcast includes one or more moment clips from the event broadcast.

12 . The non-transitory computer-readable medium of claim 11 , wherein the instructions, when executed, further cause the computing system to perform operations comprising combining the one or more moment clips into a moment reel to be presented at a presentation device.

13 . The non-transitory computer-readable medium of claim 7 , wherein the instructions, when executed, further cause the computing system to perform operations comprising presenting a graphical overlay on the event broadcast as the event broadcast is being presented at a presentation device.

14 . The non-transitory computer-readable medium of claim 7 , wherein the request is a text or a speech request.

15 . The non-transitory computer-readable medium of claim 7 , wherein the subset of the set of data can include closed captioning data interpreted from the event broadcast by the natural language processor.

16 . An interactive broadcast system comprising:

a memory, wherein the memory is configured to store computer-executable instructions; and

one or more processors in communication with the memory, wherein the computer-executable instructions, when executed by the one or more processors, configure the one or more processors to perform operations including:

prior to receiving a natural language command, adjusting audio characteristics and video characteristics of data of an event broadcast as compared to the data as received;

identifying event broadcast metadata associated with the event broadcast from the normalized data;

receiving a user request, wherein the user request includes the natural language command related to the event broadcast;

providing the natural language command as an input to a natural language processor, wherein providing the natural language command as the input to the natural language processor causes the natural language processor to generate a response to the natural language command by identifying a characteristic of the event broadcast metadata requested by the natural language command, and wherein the natural language command comprises a first condition and a second condition;

creating a media representation that presents the response and satisfies the first condition and the second condition; and

causing a user device to present the media representation.

17 . The interactive broadcast system of claim 16 , wherein the natural language processor identifies a characteristic requested by the natural language command.

18 . The interactive broadcast system of claim 17 , wherein the characteristic is associated with moment metadata.

19 . The interactive broadcast system of claim 16 , wherein the natural language command further identifies a presentation type defined by the natural language command.

20 . The interactive broadcast system of claim 19 , wherein the media representation is created according to the presentation type.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 10, 2023
From: RADER, ZIV; SEGEV, BAR; BITON, YOSSI; BEN-COHEN, AVI AVRAHAM; KARKLINSKY, MATAN
To: AMAZON TECHNOLOGIES, INC.
Reel/Frame 065530/0350 →
References Cited (32)
US 9715901B1 · Singh · 2017 [cited by examiner]
US 10182271B1 · Sanchez · 2019 [cited by examiner]
US 10433030B2 · Packard et al. · 2019 [cited by applicant]
US 10714145B2 · Kulkarni et al. · 2020 [cited by applicant]
US 11122341B1 · Decrop et al. · 2021 [cited by applicant]
US 11425469B2 · Trollope et al. · 2022 [cited by applicant]
US 11664053B2 · Raju et al. · 2023 [cited by applicant]
US 11670085B2 · Verma et al. · 2023 [cited by applicant]
US 11705161B2 · Ebong · 2023 [cited by applicant]
US 11830241B2 · Merler et al. · 2023 [cited by applicant]
US 11956516B2 · Shichman et al. · 2024 [cited by applicant]
US 11962833B2 · Kraegeloh et al. · 2024 [cited by applicant]
US 11962838B2 · Yelton et al. · 2024 [cited by applicant]
US 12167108B1 · Dubey · 2024 [cited by examiner]
US 12283291B1 · Sarfati · 2025 [cited by examiner]
US 12301960B1 · Ben-Cohen et al. · 2025 [cited by applicant]
US 20060059120A1 · Xiong et al. · 2006 [cited by applicant]
US 20150110468A1 · Abecassis et al. · 2015 [cited by applicant]
US 20160105708A1 · Packard et al. · 2016 [cited by applicant]
US 20160217329A1 · Kang · 2016 [cited by examiner]
US 20180199102A1 · Gross · 2018 [cited by applicant]
US 20190356951A1 · Selim · 2019 [cited by examiner]
US 20190356952A1 · Leung · 2019 [cited by examiner]
US 20210149955A1 · Cannon · 2021 [cited by examiner]
US 20230230378A1 · Rfenacht et al. · 2023 [cited by applicant]
US 20230236442A1 · Shtukater · 2023 [cited by examiner]
US 20230283878A1 · Huang et al. · 2023 [cited by applicant]
US 20240155197A1 · Engin · 2024 [cited by examiner]
US 20240163532A1 · Lythcott-Haims · 2024 [cited by examiner]
US 20240314396A1 · Streater · 2024 [cited by applicant]
US 20250008201A1 · Xu · 2025 [cited by examiner]
US 20250150690A1 · Packard et al. · 2025 [cited by applicant]