Monitoring an activity and determining the type of actor performing the activity

• US 10,338,802 B2
• Filed: 02/08/2017
• Issued: 07/02/2019
• Est. Priority Date: 02/08/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bender, Michael, Hahn, Timothy J., Marin Junior, Leucir
• Primary Examiner(s): Islam, Mohammad K
• Application Number:
  US15/427,365
• Publication Number:
  US 20180224943A1
• Time in Patent Office: 874 Days
• CPC Class Codes: G06F 11/3003 Monitoring arrangements specially adapted to the computing system or computing system component being monitored
• CPC Class Codes: G06F 11/3409 for performance assessment
• CPC Class Codes: G06F 11/3452 Performance evaluation by statistical analysis
• CPC Class Codes: G06F 3/0488 using a touch-screen or digitiser, e.g. input of commands through traced gestures

Abstract

Determining a type of actor performing an activity includes monitoring the performance of the activity via at least one sensor to produce activity readings over a dimension. The activity readings are then compared to reference readings that are generated based on a machine performing same activity. The comparison of the reference readings to the activity readings is used to determine a variance between the activity readings and reference readings. Once the variance is determined, the variance is compared with a threshold value to determine the type of actor performing the activity.

Claims

1. A method of determining a type of actor performing an activity comprising:

monitoring a device receiving controls from the actor for performance of the activity, via a sensor, to produce activity readings over a dimension, wherein the device includes one of a vehicle and a computer system and the activity readings represent behavior of the device in response to control by the actor;

comparing the activity readings to reference readings generated based on a machine controlling the device for performing the activity to determine a variance between the activity readings and reference readings;

determining the type of actor controlling the device based on a comparison of the variance with a threshold;

adding randomized elements to the reference readings based on a probability distribution to produce simulated readings of the activity performed by an organism; and

utilizing the simulated readings to direct the machine to control the device to perform the activity in a manner simulating control of the device by the organism.

2. The method of claim 1, wherein the type of actor includes one of a machine and an organism.

3. The method of claim 1, wherein the activity includes one selected from a group of:

operating the vehicle to travel along a path, operating the computer system to access data, and operating an interface to access the device.

4. The method of claim 1, wherein determining the variance includes:

analyzing the activity and reference readings to define patterns.

5. The method of claim 4, further comprising:

producing a confidence level for the determined type of actor.

6. The method of claim 1, wherein the dimension includes one of time, a distance, and a path.

7. A processing system for determining a type of actor performing an activity comprising:

a processor configured to;

monitor a device receiving controls from the actor for performance of the activity, via a sensor, to produce activity readings over a dimension, wherein the device includes one of a vehicle and a computer system and the activity readings represent behavior of the device in response to control by the actor;

compare the activity readings to reference readings generated based on a machine controlling the device for performing the activity to determine a variance between the activity readings and reference readings;

determine the type of actor controlling the device based on a comparison of the variance with a threshold;

add randomized elements to the reference readings based on a probability distribution to produce simulated readings of the activity performed by an organism; and

utilize the simulated readings to direct the machine to control the device to perform the activity in a manner simulating control of the device by the organism.

8. The processing system of claim 7, wherein the type of actor includes one of a machine and an organism.

9. The processing system of claim 7, wherein the activity includes one selected from a group of:

operating the vehicle to travel along a path, operating the computer system to access data, and operating an interface to access the device.

10. The processing system of claim 7, wherein in determining the variance, the processor is further configured to:

analyze the activity and reference readings to define patterns.

11. The processing system of claim 10, wherein the processor is further configured to:

produce a confidence level for the determined type of actor.

12. The processing system of claim 7, wherein the dimension includes one of time, a distance, and a path.

13. A computer program product for determining a type of actor performing an activity, the computer program product comprising a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code executable by at least one processor to cause the at least one processor to:

monitor a device receiving controls from the actor for performance of the activity, via a sensor, to produce activity readings over a dimension, wherein the device includes one of a vehicle and a computer system and the activity readings represent behavior of the device in response to control by the actor;

compare the activity readings to reference readings generated based on a machine controlling the device for performing the activity to determine a variance between the activity readings and reference readings;

determine the type of actor controlling the device based on a comparison of the variance with a threshold;

add randomized elements to the reference readings based on a probability distribution to produce simulated readings of the activity performed by an organism; and

utilize the simulated readings to direct the machine to control the device to perform the activity in a manner simulating control of the device by the organism.

14. The computer program product of claim 13, wherein the type of actor includes one of a machine and an organism.

15. The computer program product of claim 13, wherein the activity includes one selected from a group of:

operating the vehicle to travel along a path, operating the computer system to access data, and operating an interface to access the device.

16. The computer program product of claim 13, wherein in determining the variance, the computer readable program code is further configured to cause the at least one processor to:

analyze the activity and reference readings to define patterns.

17. The computer program product of claim 16, wherein the computer readable program code is further configured to cause the at least one processor to:

produce a confidence level for the determined type of actor.