Discovery of occurrence-data

• US 9,261,383 B2
• Filed: 07/30/2004
• Issued: 02/16/2016
• Est. Priority Date: 07/30/2004
• Status: Active Grant

• Current Assignee: Alarm.com Inc. (Alarm.com Holdings, Inc.)
• Original Assignee: TriPlay Incorporated
• Inventors: Jung, Edward K. Y., Tegreene, Clarence T.
• Primary Examiner(s): SYED, FARHAN M
• Application Number:
  US10/909,200
• Publication Number:
  US 20060046711A1
• Time in Patent Office: 4,218 Days
• Field of Search: 707/6, 707/100, 707/101, 707/104.1
• US Class Current: 1/1
• CPC Class Codes: G01D 9/005 Solid-state data loggers
• CPC Class Codes: G06F 16/22 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/047 Pattern matching networks; Rete networks
• CPC Class Codes: G08B 29/186 Fuzzy logic; neural networks
• CPC Class Codes: G08B 29/188 Data fusion; cooperative systems, e.g. voting among different detectors
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: H04Q 2209/20 using a distributed architecture
• CPC Class Codes: H04Q 2209/40 using a wireless architecture
• CPC Class Codes: H04Q 9/00 Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom
• CPC Class Codes: H04W 4/38 for collecting sensor information
• CPC Class Codes: H04W 84/18 Self-organising networks, e.g. ad-hoc networks or sensor networks

Abstract

Methods, devices, and systems for discovery of electronic occurrence-data, including data protected by an information security measure. In an approach, an exemplary system includes data storage operable to store a plurality of instances of occurrence-data, each instance of the occurrence-data having a representative feature, a central computing device operable to communicate with the data storage, and instructions that cause a computing device to perform steps. The steps include receive from an input-selector an input selection corresponding to a target-occurrence having a representative feature, and select a pattern recognition criteria corresponding to the representative feature of the target-occurrence.

Claims

1. A computer-implemented method for processing sensor data, the method comprising:

electronically and automatically receiving, by at least one specially programmed computer processor, over a network, from a plurality of remotely located recording sensors, sensor data being captured by the plurality of remotely located recording sensors for a predetermined time period;

wherein the sensor data comprises one of;

1) visual scenery recording,

2) sound recording, and

3) the visual scenery recording and the sound recording;

analyzing, by the at least one specially programmed computer processor, a plurality of chronological progressions of the visual scenery, the sound recording, or both in the sensor data over the predetermined time period to identify parameters of a plurality of representative features within the sensor data, wherein the plurality of representative features are patterns of the visual scenery, the sound recording, or both;

storing, by the at least one specially programmed computer processor, data representative of the plurality of representative features in a database associated with the at least one specially programmed processor;

establishing, based on at least one pattern recognition criterion, by the at least one specially programmed computer processor, a correspondence between (i) at least one first representative feature from the plurality of representative features identified within the sensor data and (ii) at least one characteristic of at least one occurrence in the sensor data;

wherein the at least one characteristic is an attribute associated with the at least one occurrence;

associating, by the at least one specially programmed computer processor, at least one correlating tentative event identifier with data representative of the at least one first representative feature;

discovering, by the at least one specially programmed computer processor, at least one instance of the at least one occurrence within the sensor data based upon the correspondence between the at least one first representative feature within the sensor data to the at least one characteristic of the at least one occurrence;

electronically outputting, by the at least one specially programmed computer processor, an output indicative of the at least one instance of the at least one occurrences;

associating, by the specially programmed computer processor, at least one non-correlating tentative event identifier with data representative of at least one second representative feature of the plurality of representative features, wherein the at least one second representative feature does not correspond to the at least one instance of the at least one occurrence; and

electronically outputting, by the at least one specially programmed computer processor, a second output indicative of the at least one second representative feature based on the at least one non-correlating tentative event identifier.

2. The method of claim 1, wherein the at least one correlating tentative event identifier is represented using symbolic text.

3. The method of claim 1, wherein the output is a notification displayed on a monitor screen that alerts a user to the discovery of the at least one instance of the at least one occurrence within the sensor data.

4. The method of claim 1, further comprising at least one non-correlating tentative event identifier is represented using symbolic text.

5. The method of claim 1, wherein the at least one pattern recognition criterion is stored locally with the specially programmed processor.

6. The method of claim 1, wherein the at least one pattern recognition criterion is received by the specially programmed computer processor over a communication link of the network.

7. The method of claim 1, wherein the patterns of the plurality of representative features are determined using a second pattern recognition criterion.

8. An apparatus for processing sensor data, comprising:

at least one receiving communication port adapted to receive sensor data from a plurality of remotely located recording sensors for a predetermined time period, wherein the sensor data comprises one of;

1) visual scenery recording,

2) sound recording, and

3) the visual scenery recording and the sound recording;

a computer processor coupled to a non-transitory computer-readable memory, wherein the non-transitory computer-readable memory comprises computer instructions, when executed by the computer processor, cause the apparatus to;

analyze a plurality of chronological progressions of the visual scenery, the sound recording, or both in the sensor data over the predetermined time period to identify parameters of a plurality of representative features within the sensor data, wherein the plurality of representative features are patterns of the visual scenery, the sound recording, or both;

store data representatives of the plurality of representative features in a database associated with the at least one specially programmed processor;

establish, based on at least one pattern recognition criterion, a correspondence between (i) at least one first representative feature from the plurality of representative features identified within the sensor data and (ii) at least one characteristic of at least one occurrence in the sensor data, wherein the at least one characteristic is an attribute associated with the at least one occurrence;

associate at least one correlating tentative event identifier with data representative of the at least one first representative feature;

discover at least one instance of the at least one occurrence within the sensor data based upon the correspondence between the at least one first representative feature within the sensor data to the at least one characteristic of the at least one occurrence;

associate at least one non-correlating tentative event identifier with data representative of at least one second representative feature of the plurality of representative features, wherein the at least one second representative feature does not correspond to the at least one instance of the at least one occurrence; and

at least one transmitting communication port adapted to electrically output at least one of;

i) an notification indicative of the at least one instance of the at least one occurrence; and

ii) a second notification indicative of the at least one second representative feature based on the at least one non-correlating tentative event identifier.

9. The apparatus of claim 8, wherein the at least one correlating tentative event identifier is represented using symbolic text.

10. The apparatus of claim 8, wherein the notification is projected on a monitor screen that provides an alert to the discovery of the at least one instance of the at least one occurrence within the sensor data.

11. The apparatus of claim 8, wherein the at least one non-correlating tentative event identifier is represented using symbolic text.

12. The apparatus of claim 8, wherein the at least one pattern recognition criterion is stored locally within the non-transitory computer-readable media.

13. The apparatus of claim 8, wherein the at least one receiving communication port if further adapted to receive the at least one pattern recognition criterion over a communication link of a network.

14. The apparatus of claim 8, wherein the patterns of the plurality of representative features are determined using a second pattern recognition criterion.