Embodiments disclose a system and method that distributes warning with a description the probability of the severity of the hazardous condition producing the warning and incorporating a policy engine for expressing rules for responding to the warning.
대표청구항▼
1. A system for distributing warnings regarding an event, the system comprising: a policy specification subsystem for generating one or more machine readable policies, each policy comprising at least one rule and at least one action associated with the at least one rule, wherein each rule includes a
1. A system for distributing warnings regarding an event, the system comprising: a policy specification subsystem for generating one or more machine readable policies, each policy comprising at least one rule and at least one action associated with the at least one rule, wherein each rule includes a plurality of event parameters and an associated plurality of predetermined event parameter probabilities;a change detection subsystem for receiving and monitoring data from a sensor system, the data including expected event parameter values and associated deviation metrics;a policy execution subsystem for executing the at least one rule and triggering the at least one action based on a comparison of the expected event parameter values and associated deviation metrics with the event parameters and the associated predetermined event parameter probabilities of the at least one rule, wherein the policy execution subsystem initiates processing of the at least one rule after receiving instructions from the change detection subsystem, wherein the change detection subsystem sends instructions to the policy execution subsystem upon detection of a predetermined change in at least one of the expected event parameter values; andan action processing subsystem for generating an output for performing the at least one action triggered by the policy execution subsystem. 2. The system of claim 1, further comprising a traceback subsystem that logs the operations of each subsystem to fixed media for evaluation following an event. 3. The system of claim 1, wherein the policy specification subsystem can accept input from an end user or third party or a combination of the end user and third party to generate the machine readable policy. 4. The system of claim 1, wherein the at least one rule comprises a Boolean predicate. 5. The system of claim 1, wherein the at least one rule comprises a fuzzy rule and the at least one action comprises a continuous action function. 6. The system of claim 4 wherein the at least one rule is expressed as a probability of exceeding a predetermined value of one of the plurality of event parameters. 7. The system of claim 6 wherein the probability of exceeding a predetermined value is computed based on a Gaussian distribution with a predetermined expected value and deviation. 8. The system of claim 1, wherein the policy execution subsystem executes the at least one rule in serial order and resolves conflicts and triggers actions based on the resolved rules. 9. The system of claim 1, wherein the action processing subsystem monitors the performance of triggered actions to verify that the actions have been executed to completion. 10. The system of claim 1, wherein the warning contains a parameterized summary of the event. 11. The system of claim 10 wherein the parameterized summary includes a probability distribution or information for the computation of a probability distribution. 12. The system of claim 1 wherein the output is produced periodically based upon detection of a predetermined change in at least one of the expected event parameter values. 13. The system of claim 1 wherein the policy comprises a predicate and an action or a continuous function of input parameters and a continuously varying control output. 14. The system of claim 1 wherein the policy specification subsystem receives information regarding the status of a device that receives the output of the action processing subsystem and modifies the policy based on the status of the device. 15. The system of claim 1 wherein the policy specification subsystem adjusts the rules based on past data. 16. The system of claim 1 wherein the rules are updated in real time. 17. The system of claim 1 wherein the policy specification subsystem comprises a plurality of user interfaces tailored to a user's level of expertise that allows the user to customize the rules. 18. The system of claim 11, wherein the probability distribution represents the severity of the event. 19. The system of any claim 1, wherein the output is sent to a speaker or a display to generate a warning message. 20. The system of claim 1, wherein the output energizes a relay or controls the operation of a motor, engine or turbine. 21. The system of claim 1 wherein the event is an earthquake and the event parameters include one or more of peak ground jerk, peak ground acceleration, peak ground velocity, peak ground displacement, modified Mercalli intensity, estimated time of arrival of hazardous shaking, and actual time of the arrival of S-waves. 22. The system of claim 1 wherein each policy is assigned a priority. 23. The system of claim 22 wherein the priority is specified through definition order, manually assigned by a user, or changed by the actions of a policy. 24. The system of claim 1 wherein the rules can reference action states and external system variables. 25. A computer implemented method for distributing warnings regarding an event, the method comprising: generating one or more machine readable policies, each policy comprising at least one rule and at least one action associated with the at least one rule, wherein each rule includes a plurality of event parameters and an associated plurality of predetermined event parameter probabilities;receiving and monitoring data from a sensor system, the data including expected event parameter values and associated deviation metrics;initiating processing of the at least one rule upon detection of predetermined change in at least one of the expected event parameter values;executing the at least one rule and triggering the at least one action based on a comparison of the expected event parameter values and associated deviation metrics with the event parameters and the associated predetermined event parameter probabilities of the at least one rule; andgenerating an output for performing the at least one action triggered by the policy execution subsystem. 26. The method of claim 25, further comprising logging the operations of each subsystem to fixed media for evaluation following an event. 27. The method of claim 25, further comprising accepting input from an end user or third party or a combination of the end user and third party to generate the machine readable policy. 28. The method of claim 25, wherein the at least one rule comprises a Boolean predicate. 29. The method of claim 25, wherein the at least one rule comprises a fuzzy rule and the at least one action comprises a continuous action function. 30. The method of claim 28 wherein the at least one rule is expressed as a probability of exceeding a predetermined value of one of the plurality of event parameters. 31. The method of claim 30 wherein the probability of exceeding a predetermined value is computed based on a Gaussian distribution with a predetermined expected value and deviation. 32. The method of claim 25, further comprising executing the at least one rule in serial order and resolving conflicts and triggers actions based on the resolved rules. 33. The method of claim 25, further comprising monitoring the performance of triggered actions to verify that the actions have been executed to completion. 34. The method of claim 25, wherein the warning contains a parameterized summary of the event. 35. The method of claim 34 wherein the parameterized summary includes a probability distribution or information for the computation of a probability distribution. 36. The method of claim 25 wherein the output is produced periodically based upon detection of a predetermined change in at least one of the expected event parameter values. 37. The method of claim 25 wherein the policy comprises a predicate and an action or a continuous function of input parameters and a continuously varying control output. 38. The method of claim 25 further comprising receiving information regarding the status of a device that receives the output of the action processing subsystem and modifies the policy based on the status of the device. 39. method of any claim 25 further comprising adjusting the rules based on past data. 40. The method of claim 25 further comprising updating the rules in real time. 41. The method of claim 25 further comprising customizing the rules using a plurality of user interfaces tailored to a user's level of expertise. 42. The method of claim 25, wherein the probability distribution represents the severity of the event. 43. The method of claim 25, further comprising sending the output to a speaker or a display to generate a warning message. 44. The method of claim 25, further comprising sending the output to energize a relay or control the operation of a motor, engine or turbine. 45. The method of claim 25 wherein the event is an earthquake and the event parameters include one or more of peak ground jerk, peak ground acceleration, peak ground velocity, peak ground displacement, modified Mercalli intensity, estimated time of arrival of hazardous shaking, and actual time of the arrival of S-waves. 46. The method of claim 25 further comprising assigning a priority to each policy. 47. The method of claim 46 wherein the priority is specified through definition order, manually assigned by a user, or changed by the actions of a policy. 48. The method of claim 25 wherein the rules can reference action states and external system variables. 49. A device for distributing warnings regarding an event, the device comprising: a processor and memory for storing instructions which when executed by the processor causes the processor to:generate one or more machine readable policies, each policy comprising at least one rule and at least one action associated with the at least one rule, wherein each rule includes a plurality of event parameters and an associated plurality of predetermined event parameter probabilities;receive and monitor data from a sensor system, the data including expected event parameter values and associated deviation metrics;initiate processing of the at least one rule upon detection of a predetermined change in at least one of the expected event parameter values;execute the at least one rule and triggering the at least one action based on a comparison of the expected event parameter values and associated deviation metrics with the event parameters and the associated predetermined event parameter probabilities of the at least one rule; andgenerate an output for performing the at least one action triggered by the policy execution subsystem.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (8)
Zimmers, Steven L.; Davis, Daniel W., Alert notification system.
Agre Jonathan R. ; Clare Loren P. ; Marcy ; 5th Henry O. ; Twarowski Allen J. ; Kaiser William ; Mickelson Wilmer A. ; Yakos Michael D. ; Loeffelholz Christian J. ; Engdahl Jonathan R., Wireless integrated sensor network using multiple relayed communications.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.