SELF-IMPROVING CLASSIFICATION

• US 20180225355A1
• Filed: 02/07/2017
• Published: 08/09/2018
• Est. Priority Date: 02/07/2017
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Greco, Nancy A., Ko, Bong Jun, Touma, Maroun, Verma, Dinesh C., Wood, David A.
• Application Number:
  US15/426,465
• Publication Number:
  US 20180225355A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/23 Updating
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06F 18/2431 Multiple classes
• CPC Class Codes: G06F 2218/12 Classification; Matching

Abstract

An approach for self-improving classification. The approach receives sensor data of a machine, wherein the sensor data is collected during operation of the machine. The approach defines one or more categories, wherein each category of the one or more categories is associated with one or more parameters. The approach determines whether the sensor data matches one or more parameters of a first category of the one or more categories. Responsive to a determination that the sensor data matches the one or more parameters of the first category, the approach classifies the sensor data into the first category. The approach applies a first category label to the sensor data, wherein the first category label is associated with the first category.

Claims

1. A method for self-improving classification, the method comprising:

receiving, by one or more computer processors, sensor data of a machine, wherein the sensor data is collected during operation of the machine;

defining, by the one or more computer processors, one or more categories, wherein each category of the one or more categories is associated with one or more parameters;

determining, by the one or more computer processors, whether the sensor data matches one or more parameters of a first category of the one or more categories;

responsive to a determination that the sensor data matches the one or more parameters of the first category, classifying, by the one or more computer processors, the sensor data into the first category; and

applying, by the one or more computer processors, a first category label to the sensor data, wherein the first category label is associated with the first category.

2. The method of claim 1, further comprising:

responsive to a determination that the sensor data does not match the one or more parameters of the first category, requesting, by the one or more computer processors, maintenance of the machine, wherein requesting maintenance includes at least one of;

transmitting, by the one or more computer processors, a notification to a user,

illuminating, by the one or more computer processors, a warning light,

sounding, by the one or more computer processors, an audio warning, and

submitting, by the one or more computer processors, a request via a support system.

3. The method of claim 2, further comprising:

receiving, by the one or more computer processors, user input from the user, wherein the user input includes the maintenance of the machine;

determining, by the one or more computer processors, whether to reclassify the sensor data based on the user input, wherein determining includes determining whether the first category label applied to the sensor data matches the user input;

responsive to a determination that the first category label does not match the user input, determining, by the one or more computer processors, to reclassify the sensor data;

responsive to a determination to reclassify the sensor data, determining, by the one or more computer processors, whether the user input matches a second category of the one or more categories; and

responsive to a determination that the user input matches the second category, reclassifying, by the one or more computer processors, the sensor data into the second category, wherein reclassifying includes removing the first category label associated with the first category and applying a second category label associated with the second category.

4. The method of claim 3, further comprising:

responsive to a determination that the user input does not match the second category, defining, by the one or more computer processors, a third category of the one or more categories, wherein defining the third category includes;

determining one or more category parameters associated with the third category based on the sensor data, and

determining the third category label associated with the third category based on the user input.

5. The method of claim 4, wherein determining the third category label, comprises at least one of:

determining the third category label based on the user input;

determining the third category label based on an ontology; and

determining the third category label based on natural language processing of the user input.

6. The method of claim 1, further comprising:

receiving, by the one or more computer processors, input from a user; and

updating, by the one or more computer processors, the one or more category parameters based on the input from the user.

7. The method of claim 1, wherein the sensor data, comprises at least one of:

sound, light, infrared, radio, pressure, humidity, and temperature measurements.

8. A computer program product for self-improving classification, the computer program product comprising:

one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the stored program instructions comprising;

program instructions to receive sensor data of a machine, wherein the sensor data is collected during operation of the machine;

program instructions to define one or more categories, wherein each category of the one or more categories is associated with one or more parameters;

program instructions to determine whether the sensor data matches one or more parameters of a first category of the one or more categories;

responsive to a determination that the sensor data matches the one or more parameters of the first category, program instructions to classify the sensor data into the first category; and

program instructions to apply a first category label to the sensor data, wherein the first category label is associated with the first category.

9. The computer program product of claim 8, further comprising:

responsive to a determination that the sensor data does not match the one or more parameters of the first category, program instructions to request maintenance of the machine, wherein the program instructions to request maintenance include at least one of;

program instructions to transmit a notification to a user,

program instructions to illuminate a warning light,

program instructions to sound an audio warning, and

program instructions to submit a request via a support system.

10. The computer program product of claim 9, further comprising:

program instructions to receive user input from the user, wherein the user input includes the maintenance of the machine;

program instructions to determine whether to reclassify the sensor data based on the user input, wherein the program instructions to determine include program instructions to determine whether the first category label applied to the sensor data matches the user input;

responsive to a determination that the first category label does not match the user input, program instructions to determine to reclassify the sensor data;

responsive to a determination to reclassify the sensor data, program instructions to determine whether the user input matches a second category of the one or more categories; and

responsive to a determination that the user input matches the second category, program instructions to reclassify the sensor data into the second category, wherein the program instructions to reclassify include program instructions to remove the first category label associated with the first category and program instructions to apply a second category label associated with the second category.

11. The computer program product of claim 10, further comprising:

responsive to a determination that the user input does not match the second category, program instructions to define a third category of the one or more categories, wherein the program instructions to define the third category include;

program instructions to determine one or more category parameters associated with the third category based on the sensor data, and

program instructions to determine the third category label associated with the third category based on the user input.

12. The computer program product of claim 11, wherein the program instructions to determine the third category label, comprise at least one of:

program instructions to determine the third category label based on the user input;

program instructions to determine the third category label based on an ontology; and

program instructions to determine the third category label based on natural language processing of the user input.

13. The computer program product of claim 8, further comprising:

program instructions to receive input from a user; and

program instructions to update the one or more category parameters based on the input from the user.

14. The computer program product of claim 8, wherein the sensor data, comprises at least one of:

sound, light, infrared, radio, pressure, humidity, and temperature measurements.

15. A computer system for self-improving classification, the computer system comprising:

one or more computer processors;

one or more computer readable storage media;

and program instructions stored on the one or more computer readable storage media, the stored program instructions comprising;

program instructions to receive sensor data of a machine, wherein the sensor data is collected during operation of the machine;

program instructions to define one or more categories, wherein each category of the one or more categories is associated with one or more parameters;

program instructions to determine whether the sensor data matches one or more parameters of a first category of the one or more categories;

responsive to a determination that the sensor data matches the one or more parameters of the first category, program instructions to classify the sensor data into the first category; and

program instructions to apply a first category label to the sensor data, wherein the first category label is associated with the first category.

16. The computer system of claim 15, further comprising:

responsive to a determination that the sensor data does not match the one or more parameters of the first category, program instructions to request maintenance of the machine, wherein the program instructions to request maintenance include at least one of;

program instructions to transmit a notification to a user,

program instructions to illuminate a warning light,

program instructions to sound an audio warning, and

program instructions to submit a request via a support system.

17. The computer system of claim 16, further comprising:

program instructions to receive user input from the user, wherein the user input includes the maintenance of the machine;

program instructions to determine whether to reclassify the sensor data based on the user input, wherein the program instructions to determine include program instructions to determine whether the first category label applied to the sensor data matches the user input;

responsive to a determination that the first category label does not match the user input, program instructions to determine to reclassify the sensor data;

responsive to a determination to reclassify the sensor data, program instructions to determine whether the user input matches a second category of the one or more categories; and

responsive to a determination that the user input matches the second category, program instructions to reclassify the sensor data into the second category, wherein the program instructions to reclassify include program instructions to remove the first category label associated with the first category and program instructions to apply a second category label associated with the second category.

18. The computer system of claim 17, further comprising:

responsive to a determination that the user input does not match the second category, program instructions to define a third category of the one or more categories, wherein the program instructions to define the third category include;

program instructions to determine one or more category parameters associated with the third category based on the sensor data, and

program instructions to determine the third category label associated with the third category based on the user input.

19. The computer system of claim 15, further comprising:

program instructions to receive input from a user; and

program instructions to update the one or more category parameters based on the input from the user.

20. The computer system of claim 15, wherein the sensor data, comprises at least one of:

sound, light, infrared, radio, pressure, humidity, and temperature measurements.