Classifying static leaf nodes in a motion detection system

• US 10,498,467 B1
• Filed: 01/24/2019
• Issued: 12/03/2019
• Est. Priority Date: 01/24/2019
• Status: Active Grant

• Current Assignee: Cognitive Systems Corp.
• Original Assignee: Cognitive Systems Corp.
• Inventors: Ravkine, Mikhail
• Primary Examiner(s): Moore, Ian N
• Assistant Examiner(s): Le, Brian T
• Application Number:
  US16/256,377
• Time in Patent Office: 313 Days
• CPC Class Codes: G08B 13/187 by interference of a radiation field
• CPC Class Codes: G08B 13/2491 Intrusion detection systems, i.e. where the body of an intruder causes the interference with the electromagnetic field
• CPC Class Codes: H04B 17/11 for calibration
• CPC Class Codes: H04B 17/318 Received signal strength
• CPC Class Codes: H04W 24/04 Arrangements for maintaining operational condition
• CPC Class Codes: H04W 52/0238 where the received signal is an unwanted signal, e.g. interference or idle signal
• CPC Class Codes: H04W 52/0254 detecting a user operation or a tactile contact or a motion of the device
• CPC Class Codes: H04W 76/34 Selective release of ongoing connections

Abstract

In a general aspect, a motion detection system manages leaf nodes used for sounding by one or more access points. For example, an access point identifies one or more static leaf nodes based on presence activity of each leaf node in a calibration window. A health score is determined for each AP-leaf node link for each calibration window based on AP-leaf node link quality information. One or more of the static leaf nodes are selected to be used for sounding in the motion detection system based on the health scores for each of the AP-leaf node links. The motion detection system is then updated to use the selected one or more static leaf nodes for motion detection.

Claims

1. A method for managing nodes in a motion detection system, comprising:

identifying, by an access point (AP) of the motion detection system, one or more static leaf nodes based on presence activity of each static leaf node of the one or more static leaf nodes in a calibration window, the calibration window comprising a number of calibration periods;

determining a health score for each AP-leaf node link for the calibration window based on AP-leaf node link quality information, each AP-leaf node link defined between the AP and one of the static leaf nodes of the one or more static leaf nodes,

wherein determining a health score for each AP-leaf node link for the calibration window comprises;

assigning each AP-leaf node link a classification based on quality information for the AP-leaf node link, wherein the classification indicates a link quality is passing, noisy, or sleeping,

wherein the link quality of the AP-leaf node link is passing when a success rate of sounding operations during the calibration window is above a first threshold, and a failure rate of sounding operations during the calibration period is below a second threshold,

wherein the link quality of the AP-leaf node link is noisy when the success rate of sounding operations during the calibration period is below a third threshold, and the failure rate of sounding operations during the calibration period is above a fourth threshold;

assigning a value to each AP-leaf node link corresponding to the classification assigned to the AP-leaf node link; and

deriving the health score for each AP-leaf node link based on the assigned values in each of the number of calibration periods in the calibration window;

selecting one or more of the static leaf nodes to use for sounding in the motion detection system based on the health scores for each of the AP-leaf node links; and

updating the motion detection system to use the selected one or more static leaf nodes for motion detection.

2. The method of claim 1, wherein the AP-leaf node link quality information comprises one or more of:

a success rate of sounding operations during a calibration period;

a failure rate of sounding operations during a calibration period;

an average link received signal strength indicator (RSSI); and

a motion detection failure rate.

3. The method of claim 1, wherein selecting one or more of the static leaf nodes to use in the motion detection system based on the health scores for each of the AP-leaf node link comprises:

when an AP-leaf node link health score is negative, disabling the AP-leaf node link;

when an AP-leaf node link health score is positive, prioritizing the AP-leaf node link with other AP-leaf node links having positive health scores; and

selecting the leaf node with the highest AP-leaf node link health score to use with the motion detection system.

4. The method of claim 1, wherein updating the motion detection system to use at least one of the one or more static leaf nodes for motion detection, comprises:

determining the motion detection system allows adding a new leaf node;

transmitting, to a user device, a zone creation event to for the selected static leaf node;

marking the selected leaf node as a unique local zone.

5. The method of claim 1, comprising:

obtaining, by the AP, presence and link quality information for a plurality of AP-leaf node links for the number of calibration periods; and

initiating a calibration event for the calibration window.

6. The method of claim 5, wherein the AP operates as a hub for the motion detection system, and the AP obtains reports from one or more other APs in the motion detection system containing presence and link quality information for each of the other AP-leaf node links.

7. A device for managing nodes in a motion detection system, comprising:

one or more processors; and

memory comprising instructions which when executed by the one or more processors cause the device to perform operations comprising;

identifying, by an access point (AP) of the motion detection system, one or more static leaf nodes based on presence activity of each static leaf node of the one or more static leaf nodes in a calibration window, the calibration window comprising a number of calibration periods;

determining a health score for each AP-leaf node link for the calibration window based on AP-leaf node link quality information, each AP-leaf node link defined between the AP and one of the static leaf nodes of the one or more static leaf nodes,

wherein determining a health score for each AP-leaf node link for the calibration window comprises;

assigning each AP-leaf node link a classification based on quality information for the AP-leaf node link, wherein the classification indicates a link quality is passing, noisy, or sleeping,

wherein the link quality of the AP-leaf node link is passing when a success rate of sounding operations during the calibration window is above a first threshold, and a failure rate of sounding operations during the calibration period is below a second threshold,

wherein the link quality of the AP-leaf node link is noisy when the success rate of sounding operations during the calibration period is below a third threshold, and the failure rate of sounding operations during the calibration period is above a fourth threshold;

assigning a value to each AP-leaf node link corresponding to the classification assigned to the AP-leaf node link; and

deriving the health score for each AP-leaf node link based on the assigned values in each of the number of calibration periods in the calibration window;

selecting one or more of the static leaf nodes to use for sounding in the motion detection system based on the health scores for each of the AP-leaf node links; and

updating the motion detection system to use the selected one or more static leaf nodes for motion detection.

8. The device of claim 7, wherein the AP-leaf node link quality information comprises one or more of:

a success rate of sounding operations during a calibration period;

a failure rate of sounding operations during a calibration period;

an average link received signal strength indicator (RSSI); and

a motion detection failure rate.

9. The device of claim 7, wherein selecting one or more of the static leaf nodes to use in the motion detection system based on the health scores for each of the AP-leaf node link comprises:

when an AP-leaf node link health score is negative, disabling the AP-leaf node link;

when an AP-leaf node link health score is positive, prioritizing the AP-leaf node link with other AP-leaf node links having positive health scores; and

selecting the leaf node with the highest AP-leaf node link health score to use with the motion detection system.

10. The device of claim 7, wherein updating the motion detection system to use at least one of the one or more static leaf nodes for motion detection, comprises:

determining the motion detection system allows adding a new leaf node;

transmitting, to a user device, a zone creation event to for the selected static leaf node;

marking the selected leaf node as a unique local zone.

11. The device of claim 7, the operations comprising:

obtaining, by the AP, presence and link quality information for a plurality of AP-leaf node links for the number of calibration periods; and

initiating a calibration event for the calibration window.

12. The device of claim 11, wherein the AP is configured to operate as a hub for the motion detection system, and the AP is configured to obtain reports from one or more other APs in the motion detection system containing presence and link quality information for each of the other AP-leaf node links.

13. A non-transitory computer readable medium comprising instructions which when executed by data processing apparatus cause the data processing apparatus to perform operations comprising:

identifying, by an access point (AP) of the motion detection system, one or more static leaf nodes based on presence activity of each static leaf node of the one or more static leaf nodes in a calibration window, the calibration window comprising a number of calibration periods;

determining a health score for each AP-leaf node link for the calibration window based on AP-leaf node link quality information, each AP-leaf node link defined between the AP and one of the static leaf nodes of the one or more static leaf nodes,

wherein determining a health score for each AP-leaf node link for the calibration window comprises;

assigning each AP-leaf node link a classification based on quality information for the AP-leaf node link, wherein the classification indicates a link quality is passing, noisy, or sleeping,

wherein the link quality of the AP-leaf node link is passing when a success rate of sounding operations during the calibration window is above a first threshold, and a failure rate of sounding operations during the calibration period is below a second threshold,

wherein the link quality of the AP-leaf node link is noisy when the success rate of sounding operations during the calibration period is below a third threshold, and the failure rate of sounding operations during the calibration period is above a fourth threshold;

assigning a value to each AP-leaf node link corresponding to the classification assigned to the AP-leaf node link; and

deriving the health score for each AP-leaf node link based on the assigned values in each of the number of calibration periods in the calibration window;

selecting one or more of the static leaf nodes to use for sounding in the motion detection system based on the health scores for each of the AP-leaf node links; and

updating the motion detection system to use the selected one or more static leaf nodes for motion detection.

14. The non-transitory computer readable medium of claim 13, wherein the AP-leaf node link quality information comprises one or more of:

a success rate of sounding operations during a calibration period;

a failure rate of sounding operations during a calibration period;

an average link received signal strength indicator (RSSI); and

a motion detection failure rate.

15. The non-transitory computer readable medium of claim 13, wherein selecting one or more of the static leaf nodes to use in the motion detection system based on the health scores for each of the AP-leaf node link comprises:

when an AP-leaf node link health score is negative, disabling the AP-leaf node link;

when an AP-leaf node link health score is positive, prioritizing the AP-leaf node link with other AP-leaf node links having positive health scores; and

selecting the leaf node with the highest AP-leaf node link health score to use with the motion detection system.

16. The non-transitory computer readable medium of claim 13, wherein updating the motion detection system to use at least one of the one or more static leaf nodes for motion detection, comprises:

determining the motion detection system allows adding a new leaf node;

transmitting, to a user device, a zone creation event to for the selected static leaf node;

marking the selected leaf node as a unique local zone.

17. The non-transitory computer readable medium of claim 13, the operations comprising:

obtaining, by the AP, presence and link quality information for a plurality of AP-leaf node links for the number of calibration periods; and

initiating a calibration event for the calibration window.

18. The non-transitory computer readable medium of claim 13, wherein the AP operates as a hub for the motion detection system, and the AP obtains reports from one or more other APs in the motion detection system containing presence and link quality information for each of the other AP-leaf node links.