Visual generation of an anomaly detection image

Patent metadata

Field	Value
Publication number	US-10325386-B2
Application number	US-201615087205-A
Country	US
Kind code	B2
Filing date	Mar 31, 2016
Priority date	Mar 31, 2016
Publication date	Jun 18, 2019
Grant date	Jun 18, 2019

Abstract

A method includes formatting for display, on a visual screen, an image comprising a coordinate system and a plurality of data points within the coordinate system, wherein the plurality of data points define historical performance data for a computer system. The method further includes receiving a user input defining a distinguishable area within the coordinate system and an action associated with the distinguishable area. The method additionally includes generating a formula representing the distinguishable area.

First claim

The invention claimed is:

1. A method comprising:
formatting for display, on a visual screen, an image comprising:
a coordinate system, and
a plurality of data points within the coordinate system, wherein the plurality of data points define historical performance data for a computer system;

receiving a plurality of user inputs within the displayed coordinate system defining:
a plurality of distinguishable areas within the coordinate system, and
an action associated with each of the distinguishable areas;

for each of the distinguishable areas input to the coordinate system by the user, determining a formula having potential solution values that correspond to a boundary for the distinguishable area, wherein the formula comprises a range of axis values corresponding to an area of the coordinate system, and wherein determining the formula comprises:
generating a raster image of the coordinate system and the distinguishable area within the coordinate system;
detecting a plurality of edges of the distinguishable area in the raster image; and
detecting a respective set of axis values corresponding to the plurality of edges of the distinguishable area in the raster image;

receiving a real-time data point corresponding to current performance of the computer system;
determining that a value of the real-time data point falls within one of the respective distinguishable areas based on the determined formulas; and
automatically invoking the action associated with the one of the respective distinguishable areas for the real-time data point.

2. The method of claim 1 , wherein the one of the respective distinguishable areas corresponds to one particular tolerance category of a plurality of tolerance categories, the particular tolerance category corresponding to an expected frequency of observing a data point.

3. The method of claim 2 , wherein one or more of the tolerance categories are associated with a respective response action.

4. The method of claim 2 , wherein the plurality of tolerance categories comprise an anomalous category, an acceptable category, or a normal category.

5. The method of claim 4 , wherein receiving the user input defining the action associated with each of the distinguishable areas comprises receiving an instruction to associate each of the distinguishable areas with the anomalous category.

6. The method of claim 1 , wherein the plurality of data points within the coordinate system represent a first variable and a second variable, the first variable being a load variable and the second variable being a performance variable.

7. The method of claim 1 , wherein one of the distinguishable areas within the coordinate system comprises a geometric shape.

8. The method of claim 1 , wherein the formula representing each of the distinguishable areas comprises a range of axis values corresponding to an area of the coordinate system associated with the distinguishable area.

9. The method of claim 8 , wherein generating the formula representing the distinguishable area comprises:
generating a vector image of the coordinate system and the distinguishable area within the coordinate system;
detecting a plurality of points on a vector line defining the distinguishable area; and
detecting a respective set of axis values corresponding to the plurality of points on the vector line defining the distinguishable area.

10. The method of claim 1 , wherein the coordinate system is three-dimensional.

11. The method of claim 1 , further comprising:
receiving a second user input defining:
a second distinguishable area within the coordinate system, and
a second action associated with the second distinguishable area; and
generating a second formula representing the second distinguishable area.

12. The method of claim 1 , further comprising:
receiving a new data point;
determining whether the new data point falls within a range of the coordinate system defined by one of the formulas; and
in response to determining that the new data point falls within the range of the coordinate system, initiating the action associated with the distinguishable area for the one of the formulas.

13. The method of claim 12 , wherein initiating the action associated with the distinguishable area for the one of the formulas comprises utilizing a processor to instruct an output device to generate a notification.

14. A non-transitory computer readable storage medium storing instructions that are executable to cause a system to perform operations comprising:
formatting for display, on a visual screen, an image comprising a coordinate system and a plurality of data points, defining historical performance data for a computer system, within the coordinate system;
receiving a plurality of user inputs within the displayed coordinate system defining:
a plurality of distinguishable areas within the coordinate system, wherein each of the distinguishable areas corresponds to a particular tolerance category of a plurality of tolerance categories, each tolerance category representing an expected frequency of observing a data point, and
an action associated with each of the distinguishable areas;

for each of the distinguishable areas input to the coordinate system by the user, determining a formula having potential solution values that correspond to a boundary for the distinguishable area, wherein the formula comprises a range of axis values corresponding to an area of the coordinate system, and wherein determining the formula comprises:
generating a vector image of the coordinate system and the distinguishable area within the coordinate system;
detecting a plurality of points on a vector line defining the distinguishable area; and
detecting a respective set of axis values corresponding to the plurality of points on the vector line defining the distinguishable area;

receiving a new data point corresponding to the performance of the computer system;
determining whether the new data point is associated with one or more of the distinguishable areas by determining whether the new data point falls within a range of the coordinate system defined by any of the formulas; and
in response to determining that the new data point falls within the range of the coordinate system, initiating the action associated with the one or more of the distinguishable areas.

15. The non-transitory computer readable storage medium of claim 14 , wherein receiving the user input defining the action associated with each of the distinguishable areas comprises receiving an instruction to associate each of the distinguishable areas with the anomalous category.

16. The non-transitory computer readable storage medium of claim 14 , wherein the formula representing each of the distinguishable areas comprises a range of axis values corresponding to an area of the coordinate system associated with the distinguishable area.

17. The non-transitory computer readable storage medium of claim 16 , wherein generating the formula representing the distinguishable area comprises:
generating a raster image of the coordinate system and the distinguishable area within the coordinate system;
detecting a plurality of edges of the distinguishable area in the raster image; and
detecting a respective set of axis values corresponding to the plurality of edges of the distinguishable area in the raster image.

18. The non-transitory computer readable storage medium of claim 16 , wherein the instructions are further executable to cause the system to perform:
removing the plurality of data points from the image; and
gene

Assignees

• Mankovskii Serguei
• Ca Inc

Inventors

• Mankovskii Serguei

Classifications

• G06T11/26 Primary

  Drawing of charts or graphs · CPC title

• G06T11/206 Primary

  Physics · mapped topic