Organization of signal segments supporting sensed features

• US 10,482,900 B2
• Filed: 02/17/2017
• Issued: 11/19/2019
• Est. Priority Date: 01/18/2017
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Mital, Vijay, Colle, Olivier, Abraham, Robin
• Primary Examiner(s): Tucker, Wesley J
• Application Number:
  US15/436,684
• Publication Number:
  US 20180204087A1
• Time in Patent Office: 1,005 Days
• CPC Class Codes: G06F 18/2414 Smoothing the distance, e.g. radial basis function networks [RBFN]
• CPC Class Codes: G06N 3/006 based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
• CPC Class Codes: G06N 5/045 Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence
• CPC Class Codes: G06V 10/764 using classification, e.g. of video objects
• CPC Class Codes: G06V 10/82 using neural networks
• CPC Class Codes: G10L 25/30 using neural networks
• CPC Class Codes: G10L 25/48 specially adapted for particular use

Abstract

The managing of sensed signals used to sense features of physical entities over time. A computer-navigable graph of sensed features is generated. For each sensed feature, a signal segment that was used to sense that feature is computer-associated with the sensed feature. Later, the graph of sensed features may be navigated to that features. The resulting signal segment(s) may then be access allowing for rendering of the signal evidence that resulted in the sensed feature. Accordingly, the principles described herein allow for sophisticated and organized navigation to sensed features of physical entities in the physical world, and allow for rapid rendering of the signals that evidence that sensed features.

Claims

1. A computing system for performing a method for managing sensed signals used to sense features of physical entities over time, the system comprising:

one or more processors;

one or more computer-readable media having thereon computer-executable instructions that, when executed by the one or more processors, cause the computing system to perform the method for managing sensed signals used to sense features of physical entities over time, the method comprising;

creating a computer-navigable graph of a plurality of sensed features of a plurality of sensed physical entities over a plurality of times, the sensed features determined from analysis of sensor signals observed of the plurality of sensed physical entities; and

for at least one of the sensed features of at least one of the sensed plurality of entities, associating within the computer-navigable graph a signal segment with the at least one sensed feature such that computer-navigation to the sensed feature also allows for computer-navigation to the signal segment, wherein the associated signal segment is a particular signal segment of the at least one sensed entity which had been analyzed to determine the at least one sensed feature.

2. The computing system in accordance with claim 1, the signal segment comprising an identification of a sensor that resulted in sensing of the sensed feature.

3. The computing system in accordance with claim 2, the signal segment excluding at least one or more signal segments from the identified sensor that were not used to sense the sensed feature.

4. The computing system in accordance with claim 1, the signal segment comprising a video signal, the signal segment comprising one or more frames of a video signal generated by a sensor.

5. The computing system in accordance with claim 4, wherein for at least one of the frames of the video signal, the signal segment includes just a portion of the frame.

6. The computing system in accordance with claim 1, the signal segment comprising an image signal captured by a sensor.

7. The computing system in accordance with claim 6, the signal segment including just a portion of the image captured by the sensor.

8. The computing system in accordance with claim 1, the sensed signal being an audio signal captured by a sensor.

9. The computing system in accordance with claim 1, the sensed signal being a filtered version of a signal captured by a sensor.

10. The computing system in accordance with claim 9, the filtered version being filtered by frequency.

11. The computing system in accordance with claim 1, the sensed signal being transformed.

12. The computing system in accordance with claim 1, the method further comprising:

navigating the navigable graph to a particular sensed feature of the plurality of features; and

navigating to the sensed signal computer-associated with the particular sensed feature using the computer-association between the particular sensed feature and the associated sensor signal.

13. The computing system in accordance with claim 12, the navigating the navigable graph to the particular sensed feature being performed in response to user input.

14. The computing system in accordance with claim 13, the navigating to the sensed signal occurring automatically upon performing the act of navigating to the particular sensed feature.

15. The computing system in accordance with claim 13, the navigating to the sensed signal occurring in response to user input received after the act of navigating the navigable graph to the particular sensed feature.

16. The computing system in accordance with claim 12, the navigating to the particular sensed feature being performed in response to a user query.

17. The computing system in accordance with claim 12, the method further comprising rendering the sensed signal.

18. A computer implemented method for managing sensed signals used to sense features of physical entities over time, the method comprising:

executing computer-executable instructions on one or more processors of a computing system, thereby causing the computing system to perform the method comprising;

creating a computer-navigable graph of a plurality of sensed features of a plurality of sensed physical entities over a plurality of times, the sensed features determined from analysis of sensor signals observed of the plurality of sensed physical entities; and

for at least one of the sensed features of at least one of the sensed plurality of entities, associating within the computer-navigable graph a signal segment with the at least one sensed feature such that computer-navigation to the sensed feature also allows for computer-navigation to the signal segment, wherein the associated signal segment is a particular signal segment of the at least one sensed entity which had been analyzed to determine the at least one sensed feature.

19. The method in accordance with claim 18, further comprising:

navigating the navigable graph to a particular sensed feature of the plurality of features; and

navigating to the sensed signal computer-associated with the particular sensed feature using the computer-association between the particular sensed feature and the associated sensor signal.

20. A computer program product for managing sensed signals used to sense features of physical entities over time, the computer program product comprising one or more computer-readable storage media having thereon computer-executable instructions that, when executed by one or more processors of a computing system, cause the computing system to perform a method for managing sensed signals used to sense features of physical entities over time, the method comprising:

creating a computer-navigable graph of a plurality of sensed features of a plurality of sensed physical entities over a plurality of times, the sensed features determined from analysis of sensor signals observed of the plurality of sensed physical entities; and

for at least one of the sensed features of at least one of the sensed plurality of entities, associating within the computer-navigable graph a signal segment with the at least one sensed feature such that computer-navigation to the sensed feature also allows for computer-navigation to the signal segment, wherein the associated signal segment is a particular signal segment of the at least one sensed entity which had been analyzed to determine the at least one sensed feature.