Automatic detection of human and non-human activity

• US 10,594,836 B2
• Filed: 06/30/2017
• Issued: 03/17/2020
• Est. Priority Date: 06/30/2017
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Walker, Toby, Nagpal, Sarvesh, Kohavi, Ron, Frasca, Brian
• Primary Examiner(s): Vostal, Ondrej C
• Application Number:
  US15/639,938
• Publication Number:
  US 20190007523A1
• Time in Patent Office: 991 Days
• Field of Search: 709202
• CPC Class Codes: G06F 21/316 by observing the pattern of computer usage, e.g. typical user behaviour
• CPC Class Codes: G06F 2221/2133 Verifying human interaction, e.g., Captcha
• CPC Class Codes: G06F 2221/2139 Recurrent verification
• CPC Class Codes: H04L 41/5022 by giving priorities, e.g. assigning classes of service
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34
• CPC Class Codes: H04L 67/56 Provisioning of proxy services store-and-forward switching systems in data switching networks H04L12/54
• CPC Class Codes: H04L 67/63 Routing a service request depending on the request content or context

Abstract

Systems, methods, and computer-readable storage media are provided for determining whether a user is a human agent or a non-human agent. A user is initially classified as a human or non-human agent based on user request properties. Sensor data is received from the user device and used to determine whether the user is to be reclassified as a human agent or non-human agent. Based on the sensor data, the user is then reclassified as a human agent or non-human agent. A service is adapted based on the classification.

Claims

1. A system comprising:

one or more processors; and

computer storage memory having computer-executable instructions stored thereon which, when executed by the one or more processors, are configured to implement a method for determining whether a user is a human agent or a non-human agent, the method comprising;

classifying the user as the human agent or the non-human agent based on received user request properties;

receiving sensor data from a user device of the user;

modifying the classification of the user based on the sensor data;

based on classifying the user as the human agent, preventing modification of the user as the non-human agent for a predetermined interval; and

performing an action based on the classification.

2. The system of claim 1, wherein the user request properties are used to provide an initial classification of the user as the human agent or the non-human agent.

3. The system of claim 2, wherein the sensor data is used to modify the initial classification of the user.

4. The system of claim 1, wherein the sensor data comprises data indicative of whether one or more keys of a keyboard are pressed.

5. The system of claim 1, wherein the sensor data is continuously received from the user device.

6. The system of claim 1, wherein the method further comprises calculating a score for the user from the sensor data and reclassifying the user as the human agent when the score exceeds a threshold.

7. A computer-performed method for determining whether a user is a human agent or a non-human agent, the method comprising:

initially classifying the user as the non-human agent based on one or more user request properties;

receiving sensor data from a user device of the user indicative of the human agent;

reclassifying the user as the human agent based on the sensor data; and

preventing modification of the user as the non-human agent for a predetermined interval and maintaining a tier of service to the user based on the reclassification.

8. The method of claim 7, wherein the sensor data is continuously received, and wherein the method further comprises reclassifying the user and updating the tier of service based on the continuously received sensor data.

9. The method of claim 7, wherein the user request properties comprise at least one of an internet protocol (IP) address, a type and version of a browser, or a location of the user device.

10. The method of claim 7, wherein the sensor data comprises one or more of pointer and keyboard interaction data, content displayed to the user, and scrolling data.

11. The method of claim 7, wherein the tier of service that is maintained based on the reclassification of the user as the human agent is higher than a tier of service that is provided based on classification as the non-human agent.

13. The method of claim 11, wherein the higher tier corresponds to a higher quality of service.

12. A system comprising:

one or more processors; and

computer storage memory having computer-executable instructions stored thereon which, when executed by the one or more processors, are configured to implement a method comprising;

classifying a user as a human agent or a non-human agent based on received user request properties,

receiving sensor data from a user device of the user;

modifying the classification of the user based on the sensor data;

based on classifying the user as the human agent, preventing modification of the user as the non-human agent for a predetermined interval; and

performing an action based on the classification.

14. The system of claim 12, wherein the user request properties comprise at least one of an internet protocol (IP) address, a browser identifier, or a location of the user device.

15. The system of claim 12, wherein the user request properties comprise one or more previous classifications of the user as the human agent or the non-human agent.

16. The system of claim 12, wherein the method further comprises receiving at least one of historical data of the user or data from multiple users.

17. The system of claim 12, wherein the sensor data comprises data indicative of whether one or more keys of a keyboard are pressed or whether a pointer is moved and clicked.

18. The system of claim 12, wherein the sensor data comprises camera data.

19. The system of claim 12, wherein classifying the user as the human agent or the non-human agent comprises calculating a score based on the user request properties and sensor data and reclassifying the user as the human agent when the score exceeds a threshold.

20. The system of claim 12, wherein the method further comprises reclassifying the user as the human agent upon receiving sensor data indicative of the human agent.