System, method and computer readable medium for determining an event generator type
Human interaction with a webpage may be determined by processing an event stream generated by the client device during the webpage interaction. A classification server receives the event stream and compares components of the event stream, including components of an event header message, with prerecorded datasets. The datasets include prerecorded event streams having a known interaction type. Training clients may be provided for generating the prerecorded datasets.
1. A method, comprising:
receiving first training data from a simulation device, the first training data including a first event stream that includes a first event header message and one or more first event messages, the first event header message including one or more parameters corresponding to hardware components of the simulation device, wherein the one or more parameters comprise an identification of a type of operating system, and each message of the one or more first event messages corresponding to a webpage interaction, wherein each of the one or more first event messages are associated with a first event type;
defining, by an analysis server, an event generator type for the one or more first event messages, the event generator type corresponding to the first event type, wherein the event generator type indicates a type of webpage interaction between a client and a webpage server;
generating, by the analysis server, a first event instance that includes the first event header message, at least one of the one or more first event messages, and an identifier of the event generator type of the one or more first event messages;
storing the first event instance in a repository of event instances;
receiving second training data from the simulation device, the second training data including a second event stream that includes a second event header message and one or more second event messages, the second event header message including the one or more parameters corresponding to the hardware components of the simulation device, and each message of the one or more second event messages corresponding to a webpage interaction, wherein a second event message of the one or more second event messages is associated with a second event type, the second event type being different from the event generator type;
defining a new event generator type for the one or more second event messages, the new event generator type corresponding to the second event type;
generating, by the analysis server, a second event instance that includes the second event header message, at least one of the one or more second event messages, and an identifier of the new event generator type of the one or more second event messages;
storing the second event instance in the repository of event instances;
training a machine-learning model using the one or more first event messages and the one or more second event messages;
receiving a third event stream that includes a third event header message and one or more third event messages, each of the one or more third event messages having been generated based on a webpage interaction;
generating a third event instance that includes the third event header message comprising one or more third event parameters corresponding to third event-hardware components facilitating the webpage interaction and at least one of the one or more third event messages;
comparing, using the machine-learning model, the third event instance comprising the one or more third event parameters corresponding to the third event hardware components to individual event instances stored in the repository of event instances;
determining, using the machine-learning model and based on comparing the third event instance to event instances of the repository of event instances, that the third event instance matches a particular event instance of the repository of event instances with a degree of confidence exceeding a threshold value;
categorizing, using the machine-learning model, the third event stream, wherein categorizing the third event stream includes assigning an event generator type of the particular event instance to the third event stream;
storing the event generator type of the third event stream;
receiving a fourth event stream that includes a fourth event header message and one or more fourth event messages, each of the one or more fourth event messages having been generated based on an additional webpage interaction;
generating a fourth event instance that includes the fourth event header message comprising one or more fourth event parameters corresponding to fourth event hardware components facilitating the additional webpage interaction and at least one of the one or more fourth event messages;
comparing, using the machine-learning model, the fourth event instance comprising the one or more fourth event parameters corresponding to the fourth event hardware components to the individual event instances stored in the repository of event instances; and
determining, using the machine-learning model and based on comparing the fourth event instance to the event instances of the repository of event instances, that the fourth event instance does not match an additional particular event instance of the repository of event instances with the degree of confidence exceeding the threshold value.
2. The method of claim 1 , wherein the first event type is included in the first event header message, the first event type comprising at least one of: a human interaction, a computer assisted human interaction, a computer-based interaction, a robot interaction, a natural action interaction, a simulated input device interaction, and a fluctuating input device interaction.
3. The method of claim 1 , further comprising:
receiving simulation device data from an event message of the one or more first event messages, the simulation device data including one or more of: the type of operating system, a type of browser, a type of client device, and a screen size.
4. The method of claim 1 , further comprising:
receiving a plurality of the one or more fourth event messages from a plurality of different devices, each of the plurality of the one or more fourth event messages having been generated based on a webpage interaction, wherein each of the plurality of the one or more fourth event messages include device data corresponding to a device of the plurality of different devices that sent the fourth event message, and wherein the device data includes one or more of: the type of operating system, a type of browser, and a type of event generator including human and computer initiated event generation.
5. The method of claim 1 , wherein the one or more parameters comprise an indication of a screen size.
6. A system, comprising:
one or more processors;
a non-transitory machine-readable storage medium containing instructions, which when executed on the one or more processors, cause the one or more processors to perform operations including:
receiving first training data from a simulation device, the first training data including a first event stream that includes a first event header message and one or more first event messages, the first event header message including one or more parameters corresponding to hardware components of the simulation device, wherein the one or more parameters comprise an identification of a type of operating system, and each message of the one or more first event messages corresponding to a webpage interaction, wherein each of the one or more first event messages are associated with a first event type;
defining an event generator type for the one or more first event messages, the event generator type corresponding to the first event type, wherein the event generator type indicates a type of webpage interaction between a client and a webpage server;
generating a first event instance that includes the first event header message, at least one of the one or more first event messages, and an identifier of the event generator type of the one or more first event messages;
storing the first event instance in a repository of event instances;
receiving second training data from the simulation device, the second training data including a second event stream that includes a second event header message and one or more second event messages, the second event header message including the one or more parameters corresponding to the hardware components of the simulation device, and each message of the one or more second event messages corresponding to a webpage interaction, wherein a second event message of the one or more second event messages is associated with a second event type, the second event type being different from the event generator type;
defining a new event generator type for the one or more second event messages, the new event generator type corresponding to the second event type;
generating a second event instance that includes the second event header message, at least one of the one or more second event messages, and an identifier of the new event generator type of the one or more second event messages;
storing the second event instance in the repository of event instances;
training a machine-learning model using the one or more first event messages and the one or more second event messages;
receiving a third event stream that includes a third event header message and one or more third event messages, each of the one or more third event messages having been generated based on a webpage interaction;
generating a third event instance that includes the third event header message comprising one or more third event parameters corresponding to third event hardware components facilitating the webpage interaction and at least one of the one or more third event messages;
comparing, using the machine-learning model, the third event instance comprising the one or more third event parameters corresponding to the third event hardware components to individual event instances stored in the repository of event instances;
determining, using the machine-learning model and based on comparing the third event instance to event instances of the repository of event instances, that the third event instance matches a particular event instance of the repository of event instances with a degree of confidence exceeding a threshold value;
categorizing, using the machine-learning model, the third event stream, wherein categorizing the third event stream includes assigning an event generator type of the particular event instance to the third event stream;
storing the event generator type of the third event stream;
receiving a fourth event stream that includes a fourth event header message and one or more fourth event messages, each of the one or more fourth event messages having been generated based on an additional webpage interaction;
generating a fourth event instance that includes the fourth event header message comprising one or more fourth event parameters corresponding to fourth event hardware components facilitating the additional webpage interaction and at least one of the one or more fourth event messages;
comparing, using the machine-learning model, the fourth event instance comprising the one or more fourth event parameters corresponding to the fourth event hardware components to the individual event instances stored in the repository of event instances; and
determining, using the machine-learning model and based on comparing the fourth event instance to the event instances of the repository of event instances, that the fourth event instance does not match an additional particular event instance of the repository of event instances with the degree of confidence exceeding the threshold value.
7. The system of claim 6 , wherein the first event type is included in the first event header message, the first event type comprising at least one of a human interaction, a computer assisted human interaction, a computer-based interaction, a robot interaction, a natural action interaction, a simulated input device interaction, and a fluctuating input device interaction.
8. The system of claim 6 , further comprising:
receiving simulation device data from an event message of the one or more first event messages, the simulation device data including one or more of: the type of operating system, a type of browser, a type of client device, and a screen size.
9. The system of claim 6 , further comprising:
receiving a plurality of the one or more fourth event messages from a plurality of different devices, each of the plurality of the one or more fourth event messages having been generated based on a webpage interaction, wherein each of the plurality of the one or more fourth event messages includes device data corresponding to a device of the plurality of different devices that sent the fourth event message, and wherein the device data includes one or more of: the type of operating system, a type of browser, and a type of event generator including human and computer initiated event generation.
10. The system of claim 6 , wherein the one or more parameters comprise an indication of a screen size.
11. A non-transitory computer readable storage medium configured to store instructions that, when executed by a processor, cause the processor to perform operations including:
receiving first training data from a simulation device, the first training data including a first event stream that includes a first event header message and one or more first event messages, the first event header message including one or more parameters corresponding to hardware components of the simulation device, wherein the one or more parameters comprise an identification of a type of operating system, and each message of the one or more first event messages corresponding to a webpage interaction, wherein each of the one or more first event messages are associated with a first event type;
defining, by an analysis server, an event generator type for the one or more first event messages, the event generator type corresponding to the first event type, wherein the event generator type indicates a type of webpage interaction between a client and a webpage server;
generating, by the analysis server, a first event instance that includes the first event header message, at least one of the one or more first event messages, and the event generator type of the one or more first event messages, wherein the first event instance is stored in a repository of event instances;
storing the first event instance in a repository of event instances;
receiving second training data from the simulation device, the second training data including a second event stream that includes a second event header message and one or more second event messages, the second event header message including the one or more parameters corresponding to the hardware components of the simulation device, and each message of the one or more second event messages corresponding to a webpage interaction, wherein a second event message of the one or more second event messages is associated with a second event type, the second event type being different from the event generator type;
defining a new event generator type for the one or more second event messages, the new event generator type corresponding to the second event type;
generating a second event instance that includes the second event header message, at least one of the one or more second event messages, and the new event generator type of the one or more second event messages wherein the second event instance is stored in the repository of event instances;
storing the second event instance in the repository of event instances;
training a machine-learning model using the one or more first event messages and the one or more second event messages;
receiving a third event stream that includes a third event header message and one or more third event messages, each of the one or more third event messages having been generated based on a webpage interaction;
generating a third event instance that includes the third event header message comprising one or more third event parameters corresponding to third event hardware components facilitating the webpage interaction and at least one of the one or more third event messages;
comparing, using the machine-learning model, the third event instance comprising the one or more third event parameters corresponding to the third event hardware components to individual event instances stored in the repository of event instances;
determining, using the machine-learning model and based on comparing the third event instance to event instances of the repository of event instances, that the third event instance matches a particular event instance of the repository of event instances with a degree of confidence exceeding a threshold value;
categorizing, using the machine-learning model, the third event stream, wherein categorizing the third event stream includes assigning an event generator type of the particular event instance to the third event stream;
storing the event generator type of the third event stream;
receiving a fourth event stream that includes a fourth event header message and one or more fourth event messages, each of the one or more fourth event messages having been generated based on an additional webpage interaction;
generating a fourth event instance that includes the fourth event header message comprising one or more fourth event parameters corresponding to fourth event hardware components facilitating the additional webpage interaction and at least one of the one or more fourth event messages;
comparing, using the machine-learning model, the fourth event instance comprising the one or more fourth event parameters corresponding to the fourth event hardware components to the individual event instances stored in the repository of event instances; and
determining, using the machine-learning model and based on comparing the fourth event instance to the event instances of the repository of event instances, that the fourth event instance does not match an additional particular event instance of the repository of event instances with the degree of confidence exceeding the threshold value.
12. The non-transitory computer readable storage medium of claim 11 , wherein the first event type is included in the first event header message, the first event type comprising at least one of a human interaction, a computer assisted human interaction, a computer-based interaction, a robot interaction, a natural action interaction, a simulated input device interaction, and a fluctuating input device interaction.
13. The non-transitory computer readable storage medium of claim 11 , wherein the processor is further configured to perform operations including:
receiving simulation device data from an event message of the one or more first event messages, the simulation device data including one or more of: the type of operating system, a type of browser, a type of client device, and a screen size.
14. The non-transitory computer readable storage medium of claim 11 , wherein the processor is further configured to perform operations including:
receiving a plurality of the one or more fourth event messages from a plurality of different devices, each of the plurality of the one or more fourth event messages having been generated based on a webpage interaction, wherein each of the plurality of the one or more fourth event messages include device data corresponding to a device of the plurality of different devices that sent the fourth event message, and wherein the device data includes one or more of: the type of operating system, a type of browser, and a type of event generator including human and computer initiated event generation.
15. The non-transitory computer readable storage medium of claim 11 , wherein the one or more parameters comprise an indication of a screen size.
16. A method, comprising:
receiving first training data from a simulation device, the first training data including a first event stream that includes a first event header message and one or more first event messages, the first event header message including one or more parameters corresponding to hardware components of the simulation device, wherein the one or more parameters comprise an indication of a type of browser, and each message of the one or more first event messages corresponding to a webpage interaction, wherein each of the one or more first event messages are associated with a first event type;
defining, by an analysis server, an event generator type for the one or more first event messages, the event generator type corresponding to the first event type, wherein the event generator type indicates a type of webpage interaction between a client and a webpage server;
generating, by the analysis server, a first event instance that includes the first event header message, at least one of the one or more first event messages, and an identifier of the event generator type of the one or more first event messages;
storing the first event instance in a repository of event instances;
receiving second training data from the simulation device, the second training data including a second event stream that includes a second event header message and one or more second event messages, the second event header message including the one or more parameters corresponding to the hardware components of the simulation device, and each message of the one or more second event messages corresponding to a webpage interaction, wherein a second event message of the one or more second event messages is associated with a second event type, the second event type being different from the event generator type;
defining a new event generator type for the one or more second event messages, the new event generator type corresponding to the second event type;
generating, by the analysis server, a second event instance that includes the second event header message, at least one of the one or more second event messages, and an identifier of the new event generator type of the one or more second event messages;
storing the second event instance in the repository of event instances;
training a machine-learning model using the one or more first event messages and the one or more second event messages;
receiving a third event stream that includes a third event header message and one or more third event messages, each of the one or more third event messages having been generated based on a webpage interaction;
generating a third event instance that includes the third event header message comprising one or more third event parameters corresponding to third event-hardware components facilitating the webpage interaction and at least one of the one or more third event messages;
comparing, using the machine-learning model, the third event instance comprising the one or more third event parameters corresponding to the third event hardware components to individual event instances stored in the repository of event instances;
determining, using the machine-learning model and based on comparing the third event instance to event instances of the repository of event instances, that the third event instance matches a particular event instance of the repository of event instances with a degree of confidence exceeding a threshold value;
categorizing, using the machine-learning model, the third event stream, wherein categorizing the third event stream includes assigning an event generator type of the particular event instance to the third event stream;
storing the event generator type of the third event stream;
receiving a fourth event stream that includes a fourth event header message and one or more fourth event messages, each of the one or more fourth event messages having been generated based on an additional webpage interaction;
generating a fourth event instance that includes the fourth event header message comprising one or more fourth event parameters corresponding to fourth event hardware components facilitating the additional webpage interaction and at least one of the one or more fourth event messages;
comparing, using the machine-learning model, the fourth event instance comprising the one or more fourth event parameters corresponding to the fourth event hardware components to the individual event instances stored in the repository of event instances; and
determining, using the machine-learning model and based on comparing the fourth event instance to the event instances of the repository of event instances, that the fourth event instance does not match an additional particular event instance of the repository of event instances with the degree of confidence exceeding the threshold value.
17. The method of claim 16 , wherein the one or more parameters comprise an indication of a screen size.
18. The method of claim 16 , wherein the first event type is included in the first event header message, the first event type comprising at least one of: a human interaction, a computer assisted human interaction, a computer-based interaction, a robot interaction, a natural action interaction, a simulated input device interaction, and a fluctuating input device interaction.
19. The method of claim 16 , further comprising:
receiving simulation device data from an event message of the one or more first event messages, the simulation device data including one or more of: a type of operating system, the type of browser, a type of client device, and a screen size.
20. The method of claim 16 , further comprising:
receiving a plurality of the one or more fourth event messages from a plurality of different devices, each of the plurality of the one or more fourth event messages having been generated based on a webpage interaction, wherein each of the plurality of the one or more fourth event messages include device data corresponding to a device of the plurality of different devices that sent the fourth event message, and wherein the device data includes one or more of: a type of operating system, the type of browser, and a type of event generator including human and computer initiated event generation.
21. A system, comprising:
one or more processors;
a non-transitory machine-readable storage medium containing instructions, which when executed on the one or more processors, cause the one or more processors to perform operations including:
receiving first training data from a simulation device, the first training data including a first event stream that includes a first event header message and one or more first event messages, the first event header message including one or more parameters corresponding to hardware components of the simulation device, wherein the one or more parameters comprise an indication of a type of browser, and the first event header message including each message of the one or more first event messages corresponding to a webpage interaction, wherein each of the one or more first event messages are associated with a first event type;
defining, by an analysis server, an event generator type for the one or more first event messages, the event generator type corresponding to the first event type, wherein the event generator type indicates a type of webpage interaction between a client and a webpage server;
generating a first event instance that includes the first event header message, at least one of the one or more first event messages, and an identifier of the event generator type of the one or more first event messages;
storing the first event instance in a repository of event instances;
receiving second training data from the simulation device, the second training data including a second event stream that includes a second event header message and one or more second event messages, the second event header message including the one or more parameters corresponding to the hardware components of the simulation device, and each message of the one or more second event messages corresponding to a webpage interaction, wherein a second event message of the one or more second event messages is associated with a second event type, the second event type being different from the event generator type;
defining a new event generator type for the one or more second event messages, the new event generator type corresponding to the second event type;
generating a second event instance that includes the second event header message, at least one of the one or more second event messages, and an identifier of the new event generator type of the one or more second event messages;
storing the second event instance in the repository of event instances;
training a machine-learning model using the one or more first event messages and the one or more second event messages;
receiving a third event stream that includes a third event header message and one or more third event messages, each of the one or more third event messages having been generated based on a webpage interaction;
generating a third event instance that includes the third event header message comprising one or more third event parameters corresponding to third event hardware components facilitating the webpage interaction and at least one of the one or more third event messages;
comparing, using the machine-learning model, the third event instance comprising the one or more third event parameters corresponding to the third event hardware components to individual event instances stored in the repository of event instances;
determining, using the machine-learning model and based on comparing the third event instance to event instances of the repository of event instances, that the third event instance matches a particular event instance of the repository of event instances with a degree of confidence exceeding a threshold value;
categorizing, using the machine-learning model, the third event stream, wherein categorizing the third event stream includes assigning an event generator type of the particular event instance to the third event stream;
storing the event generator type of the third event stream;
receiving a fourth event stream that includes a fourth event header message and one or more fourth event messages, each of the one or more fourth event messages having been generated based on an additional webpage interaction;
generating a fourth event instance that includes the fourth event header message comprising one or more fourth event parameters corresponding to fourth event hardware components facilitating the additional webpage interaction and at least one of the one or more fourth event messages;
comparing, using the machine-learning model, the fourth event instance comprising the one or more fourth event parameters corresponding to the fourth event hardware components to the individual event instances stored in the repository of event instances; and
determining, using the machine-learning model and based on comparing the fourth event instance to the event instances of the repository of event instances, that the fourth event instance does not match an additional particular event instance of the repository of event instances with the degree of confidence exceeding the threshold value.
22. The system of claim 21 , wherein the first event type is included in the first event header message, the first event type comprising at least one of a human interaction, a computer assisted human interaction, a computer-based interaction, a robot interaction, a natural action interaction, a simulated input device interaction, and a fluctuating input device interaction.
23. The system of claim 21 , further comprising:
receiving simulation device data from an event message of the one or more first event messages, the simulation device data including one or more of: a type of operating system, the type of browser, a type of client device, and a screen size.
24. The system of claim 21 , further comprising:
receiving a plurality of the one or more fourth event messages from a plurality of different devices, each of the plurality of the one or more fourth event messages having been generated based on a webpage interaction, wherein each of the plurality of the one or more fourth event messages include device data corresponding to a device of the plurality of different devices that sent the fourth event message, and wherein the device data includes one or more of: a type of operating system, the type of browser, and a type of event generator including human and computer initiated event generation.
25. The system of claim 21 , wherein the one or more parameters comprise an indication of a screen size.
26. A non-transitory computer readable storage medium configured to store instructions that, when executed by a processor, cause the processor to perform operations including:
receiving first training data from a simulation device, the first training data including a first event stream that includes a first event header message and one or more first event messages, the first event header message including one or more parameters corresponding to hardware components of the simulation device, wherein the one or more parameters comprise an indication of a type of browser, and each message of the one or more first event messages corresponding to a webpage interaction, wherein each of the one or more first event messages are associated with a first event type;
defining, by an analysis server, an event generator type for the one or more first event messages, the event generator type corresponding to the first event type, wherein the event generator type indicates a type of webpage interaction between a client and a webpage server;
generating, by the analysis server, a first event instance that includes the first event header message, at least one of the one or more first event messages, and an identifier of the event generator type of the one or more first event messages;
storing the first event instance in a repository of event instances;
receiving second training data from the simulation device, the second training data including a second event stream that includes a second event header message and one or more second event messages, the second event header message including the one or more parameters corresponding to the hardware components of the simulation device, and each message of the one or more second event messages corresponding to a webpage interaction, wherein a second event message of the one or more second event messages is associated with a second event type, the second event type being different from the event generator type;
defining a new event generator type for the one or more second event messages, the new event generator type corresponding to the second event type;
generating, by the analysis server, a second event instance that includes the second event header message, at least one of the one or more second event messages, and an identifier of the new event generator type of the one or more second event messages;
storing the second event instance in the repository of event instances;
training a machine-learning model using the one or more first event messages and the one or more second event messages;
receiving a third event stream that includes a third event header message and one or more third event messages, each of the one or more third event messages having been generated based on a webpage interaction;
generating a third event instance that includes the third event header message comprising one or more third event parameters corresponding to third event-hardware components facilitating the webpage interaction and at least one of the one or more third event messages;
comparing, using the machine-learning model, the third event instance comprising the one or more third event parameters corresponding to the third event hardware components to individual event instances stored in the repository of event instances;
determining, using the machine-learning model and based on comparing the third event instance to event instances of the repository of event instances, that the third event instance matches a particular event instance of the repository of event instances with a degree of confidence exceeding a threshold value;
categorizing, using the machine-learning model, the third event stream, wherein categorizing the third event stream includes assigning an event generator type of the particular event instance to the third event stream;
storing the event generator type of the third event stream;
receiving a fourth event stream that includes a fourth event header message and one or more fourth event messages, each of the one or more fourth event messages having been generated based on an additional webpage interaction;
generating a fourth event instance that includes the fourth event header message comprising one or more fourth event parameters corresponding to fourth event hardware components facilitating the additional webpage interaction and at least one of the one or more fourth event messages;
comparing, using the machine-learning model, the fourth event instance comprising the one or more fourth event parameters corresponding to the fourth event hardware components to the individual event instances stored in the repository of event instances; and
determining, using the machine-learning model and based on comparing the fourth event instance to the event instances of the repository of event instances, that the fourth event instance does not match an additional particular event instance of the repository of event instances with the degree of confidence exceeding the threshold value.
27. The non-transitory computer readable storage medium of claim 26 , wherein the first event type is included in the first event header message, the first event type comprising at least one of a human interaction, a computer assisted human interaction, a computer-based interaction, a robot interaction, a natural action interaction, a simulated input device interaction, and a fluctuating input device interaction.
28. The non-transitory computer readable storage medium of claim 26 , wherein the processor is further configured to perform operations including:
receiving simulation device data from an event message of the one or more first event messages, the simulation device data including one or more of: a type of operating system, the type of browser, a client device type, and a screen size.
29. The non-transitory computer readable storage medium of claim 26 , wherein the processor is further configured to perform operations including:
receiving a plurality of the one or more fourth event messages from a plurality of different devices, each of the plurality of the one or more fourth event messages having been generated based on a webpage interaction, wherein each of the plurality of the one or more fourth event messages include device data corresponding to a device of the plurality of different devices that sent the fourth event message, and wherein the device data includes one or more of: a type of operating system, the type of browser, and an event generator type including human and computer initiated event generation.
30. The non-transitory computer readable storage medium of claim 26 , wherein the one or more parameters comprise an indication of a screen size.