Systems and methods for reduced resource utilization for event modeling

Patent metadata

Field	Value
Publication number	US-12249146-B2
Application number	US-202217673292-A
Country	US
Kind code	B2
Filing date	Feb 16, 2022
Priority date	Feb 16, 2022
Publication date	Mar 11, 2025
Grant date	Mar 11, 2025

Abstract

A system described herein may provide a technique for using modeling techniques to identify events, trends, etc. in a set of data, such as streaming video or audio content. The system may perform lightweight pre-processing operations on a different set of data, such as object position data, to identify timeframes at which an event may potentially have occurred, and the modeling techniques may be performed at portions of the streaming content that correspond to such timeframes. The system may forgo performing such modeling techniques at other portions of the streaming content, thus conserving processing resources.

First claim

What is claimed is:

1. A device, comprising:
one or more processors configured to:
monitor a first set of data to identify whether a particular set of criteria are met with respect to the first set of data, wherein the first set of data is associated with a first timeframe;
identify, based on the monitoring, a second timeframe during which the particular set of criteria are met with respect to the first set of data, wherein the second timeframe is a subset of the first timeframe;
provide an indication, to a content provider that maintains a second set of data, of the identified second timeframe,
wherein the content provider identifies a subset of the second set of data, wherein the subset of the second set of data is associated with the identified second timeframe, and
wherein the content provider outputs, based on the indication, the identified subset of the second set of data;

receive the subset of the second set of data that is outputted by the content provider;
perform one or more modeling techniques on the subset of the second set of data, associated with the identified particular timeframe, to identify an occurrence of a particular event during the second timeframe;
identify, based on performing the one or more modeling techniques on the second set of data, the occurrence of the particular event during the second timeframe; and
output an indication of the identified particular event occurring during the second timeframe.

2. The device of claim 1 , wherein the second set of data includes data that is not included in the first set of data.

3. The device of claim 2 , wherein the first set of data includes monitored position information of one or more objects in a field, and wherein the second set of data includes captured video data depicting at least one of the one or more objects in the field.

4. The device of claim 3 , wherein the position information is based on position information provided by one or more positional sensors.

5. The device of claim 1 , wherein the one or more processors are further configured to:
forgo performing the one or more modeling techniques on portions of the second set of data, that is associated with times other than the subset of the second set of data that is associated with the identified second timeframe.

6. The device of claim 1 , wherein the second set of data includes captured content, wherein the content provider forgoes outputting captured content, associated with times other than the second timeframe, to the device.

7. The device of claim 1 , wherein monitoring the first set of data consumes fewer processing resources than performing the one or more modeling techniques on the second set of data.

8. A non-transitory computer-readable medium, storing a plurality of processor-executable instructions to:
monitor a first set of data to identify whether a particular set of criteria are met with respect to the first set of data, wherein the first set of data is associated with a first timeframe;
identify, based on the monitoring, a second timeframe during which the particular set of criteria are met with respect to the first set of data, wherein the second timeframe is a subset of the first timeframe;
provide an indication, to a content provider that maintains a second set of data, of the identified second timeframe,
wherein the content provider identifies a subset of the second set of data, wherein the subset of the second set of data is associated with the identified second timeframe, and
wherein the content provider outputs, based on the indication, the identified subset of the second set of data;

receive the subset of the second set of data that is outputted by the content provider;
perform one or more modeling techniques on the subset of the second set of data, associated with the identified particular timeframe, to identify an occurrence of a particular event during the second timeframe;
identify, based on performing the one or more modeling techniques on the second set of data, the occurrence of the particular event during the second timeframe; and
output an indication of the identified particular event occurring during the second timeframe.

9. The non-transitory computer-readable medium of claim 8 , wherein the second set of data includes data that is not included in the first set of data.

10. The non-transitory computer-readable medium of claim 9 , wherein the first set of data includes monitored position information of one or more objects in a field, and wherein the second set of data includes captured video data depicting at least one of the one or more objects in the field.

11. The non-transitory computer-readable medium of claim 10 , wherein the position information is based on position information provided by one or more positional sensors.

12. The non-transitory computer-readable medium of claim 8 , wherein the plurality of processor-executable instructions further include processor-executable instructions to:
forgo performing the one or more modeling techniques on portions of the second set of data, that is associated with times other than the subset of the second set of data that is associated with the identified second timeframe.

13. The non-transitory computer-readable medium of claim 8 , wherein the second set of data includes captured content, wherein the content provider forgoes outputting captured content, associated with times other than the second timeframe.

14. The non-transitory computer-readable medium of claim 8 , wherein monitoring the first set of data consumes fewer processing resources than performing the one or more modeling techniques on the second set of data.

15. A method, comprising:
monitoring a first set of data to identify whether a particular set of criteria are met with respect to the first set of data, wherein the first set of data is associated with a first timeframe;
identifying, based on the monitoring, a second timeframe during which the particular set of criteria are met with respect to the first set of data, wherein the second timeframe is a subset of the first timeframe;
providing an indication, to a content provider that maintains a second set of data, of the identified second timeframe,
wherein the content provider identifies a subset of the second set of data, wherein the subset of the second set of data is associated with the identified second timeframe, and
wherein the content provider outputs, based on the indication, the identified subset of the second set of data;

receiving the subset of the second set of data that is outputted by the content provider;
performing one or more modeling techniques on the subset of the second set of data, associated with the identified particular timeframe, to identify an occurrence of a particular event during the second timeframe;
identifying, based on performing the one or more modeling techniques on the second set of data, the occurrence of the particular event during the second timeframe; and
outputting an indication of the identified particular event occurring during the second timeframe.

16. The method of claim 15 , wherein the first set of data includes monitored position information of one or more objects in a field, and wherein the second set of data includes captured video data depicting at least one of the one or more objects in the field.

17. The method of claim 16 , wherein the position information is based on position information provided by one or more positional sensors.

18. The method of claim 15 , further comprising:
forgoing performing the one or more modeling techniques on

Assignees

• Verizon Patent & Licensing Inc

Inventors

• Su Le
• Tang Lin
• Iyer Krishna Pichumani
• Wan Yu
• Chen Yiming
• Lu Wenyuan

Classifications

• G06V20/41

  Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49) · CPC title

• G06V20/46

  Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames · CPC title

• G06V10/755

  Deformable models or variational models, e.g. snakes or active contours · CPC title

• G06V20/44 Primary

  Event detection · CPC title

• G06V20/42 Primary

  of sport video content · CPC title