Irregular event detection in push notifications

• US 9,536,308 B2
• Filed: 12/09/2013
• Issued: 01/03/2017
• Est. Priority Date: 12/10/2012
• Status: Active Grant

• Current Assignee: Cognyte Technologies Israel Ltd. (Cognyte Software Ltd.)
• Original Assignee: Verint Systems Limited (Verint Systems Incorporated)
• Inventors: Ostrovsky-Berman, Yaron, Gur, Ran, Naor, Nir, Wronsky, Ran, Milman, Michael
• Primary Examiner(s): Liew, Alex
• Application Number:
  US14/100,895
• Publication Number:
  US 20140161315A1
• Time in Patent Office: 1,121 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 40/103 Formatting, i.e. changing of presentation of documents automatic justification G06F40/189; automatic line break hyphenation G06F40/191
• CPC Class Codes: G06F 40/186 Templates
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06V 20/41 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 Class Codes: G06V 20/44 Event detection
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69

Abstract

Systems and methods of detecting irregular events include the extraction of values for measure in each of a plurality of notifications. The extracted values are stored in a measures database and a distribution is calculated for the values of each of the measures. The extracted values are compared to the calculated distributions to determine if an irregular event has occurred. An irregularity alert is produced if an irregular event has occurred.

Claims

1. A method of detecting irregular events from acquired data, the method comprising:

acquiring data from a data acquisition system, said data comprising video data;

identifying, on a frame-by-frame basis, objects in the video data;

automatedly producing, with the acquisition system, analytics data from the identified objects;

formatting the analytics data into a report notification pursuant to a report template;

extracting values of report measures from the report notification;

transmitting the extracted values across a communications interface to a measures database;

transmitting metadata regarding classes of report measures across a user interface to the measures database;

storing the extracted values and the metadata in the measures database;

calculating a distribution for the values of each of the report measures in accordance with the metadata for the class associated with each report measure;

comparing extracted values to the calculated distributions;

determining if an irregular event has occurred based upon the comparison of the extracted values to the calculated distributions; and

producing an irregularity alert if an irregular event is determined.

2. The method of claim 1, wherein the irregularity alert is a pushed notification comprising a time scale set forth in an underlying report template.

3. The method of claim 1, wherein the irregularity alert is visually presented in a graphical user interface.

4. The method of claim 1, further comprising:

receiving at least one user preference;

using the at least one user preference to determine if an irregular event has occurred.

5. The method of claim 4, wherein the at least one user preference is an irregularity threshold.

6. The method of claim 1, wherein the notifications are analytics reports and the measures are report measures conveying analytics data.

7. The method of claim 6, further comprising:

receiving analytics data;

automatedly generating the analytics reports from the received analytics data; and

pushing the automatedly generated analytics reports to at least one recipient.

8. The method of claim 7, wherein the analytics reports are automatedly generated by applying the received analytics data to at least one report template, and the at least one report template defines the report measures in each of the analytics reports.

9. The method of claim 8, wherein the at least one report template defines the report measures and further comprising calculating the values of the report measures from the analytics data.

10. The method of claim 7, further comprising scheduling the automated generation of the analytics reports, the calculation of the distribution for the values of the report measures, and the determination of irregular events to periodically recur.

21. The method of claim 1, said data further comprising audio data.

22. The method of claim 1, said video data further comprising a time stamp transmitted via said communications interface on a frame-by-frame basis with said report measures to said measures database.

23. The method of claim 22, further comprising calculating and storing in said measures database dwell times for a location from said objects and said time stamps.

24. The method of claim 1, wherein producing the analyzing data and producing the irregularity alert occur on a real time or near real time basis.

25. The method of claim 1, further comprising automatically detecting and acquiring the video.

11. A method of detecting irregular events in pushed analytics reports, the method comprising:

automatedly generating a plurality of pushed analytics reports comprising formatting templates that are conditional upon user input, each analytics report comprising values and time stamps for a plurality of report measures;

extracting the values and time stamps for report measures from each of the plurality of pushed analytics reports according to the user input from a user interface;

storing the extracted values in a measures database;

storing metadata regarding classes of report measures by transmitting the metadata across a user interface to the measures database;

calculating a distribution of values for each of the report measures;

storing a distribution sensitivity in accordance with said meta data;

comparing extracted values to the calculated distributions pursuant to said distribution sensitivity;

determining if an irregular event has occurred based upon the comparison of the extracted values to the calculated distributions; and

producing an irregularity alert if an irregular event is determined.

12. The method of claim 11, further comprising:

receiving at least one irregularity threshold; and

using the at least one irregularity threshold to determine if an irregular event has occurred.

13. The method of claim 11, further comprising calculating a plurality of distribution of values for each of the report measures for different temporal durations.

14. The method of claim 11, further comprising:

automatedly generating a current analytics report comprising current values for the plurality of report measures;

extracting the current values from the current analytics report;

comparing the current values to the calculated distributions; and

determining if an irregular event occurred from the comparison of the current values to the calculated distributions.

15. A system for detection of irregular events, the system comprising:

a measures extractor that is configured to receive a plurality of pushed report notifications and extract a plurality of values for report measures from the plurality of pushed report notifications;

a measures database operating on a computer readable medium, the measures database receives and stores the plurality of values from the measures extractor;

a distribution analyzer that calculates at least one distribution for each of the report measures from the plurality of values for each of the report measures;

an irregularity analyzer that is configured to utilize a feedback loop to the measures database to receive values for report measures and compare the received values to the calculated at least one distribution for each of the report measures to determine if an irregular event occurs and for values determined to be normal, flagging the values in the measures database for use by the distribution analyzer;

an alerter that produces an irregularity alert when a determination is made that an irregular event has occurred.

16. The system of claim 15, further comprising a graphical display configured to present a graphical user interface that visually presents the irregularity alert.

17. The system of claim 15, wherein the graphical user interface further visually presents the values of the report measures.

18. The system of claim 15, further comprising a reporter module that receives analytics data and applies the analytics data to at least one report template to automatedly generate pushed report notifications that comprise the plurality of values for report measures.

19. The system of claim 18, further comprising an analytics engine that is configured to receive video data and analyze the video data on a frame by frame basis to produce analytics data, the analytics engine is further configured to provide the analytics data to the reporter module.

20. The system of claim 18, further comprising a scheduler communicatively connected to the reporter module, distribution analyzer, and the irregularity analyzer, the scheduler controls the reporter module, distribution analyzer, and the irregularity analyzer to operate at predetermined intervals.