Systems and methods for intelligent alert filters

Patent metadata

Field	Value
Publication number	US-2016307100-A1
Application number	US-201514691235-A
Country	US
Kind code	A1
Filing date	Apr 20, 2015
Priority date	Apr 20, 2015
Publication date	Oct 20, 2016
Grant date	—

Abstract

A system and method of generating intelligent alerts based on updatable rules, filters, or algorithms, the method includes receiving one or more device status messages from sensors monitoring devices of a monitored system, determining an alert priority for each of the one or more device status messages, storing the alert priority, the respective device status message, and associated metadata in a data store, providing an alert message to an interactive user interface, the alert message indicating the alert priority, monitoring a user's interaction with the alert message, classifying the user's interaction with the alert message, storing the user's interaction correlated with the corresponding alert message in a data store, analyzing the user's interaction to develop correlations between a cause of respective device status message, its associated data, and the user's interaction, and updating a data store with the correlation. A system and non-transitory computer readable medium are also disclosed.

First claim

1 . A method of generating intelligent alerts, the method comprising:
receiving one or more device status messages from sensors monitoring devices of a system; determining an alert priority for each of the one or more device status messages; storing the alert priority, the respective device status message, and associated metadata in a data store; providing an alert message to an interactive user interface, the alert message indicating the alert priority; monitoring a user's interaction with the alert message; classifying the user's interaction with the alert message; storing the user's interaction correlated with the corresponding alert message in a data store; analyzing the user's interaction to develop correlations between a cause of respective device status message, its associated data, and the user's interaction; and updating a data store with the correlation.

2 . The method of claim 1 , the determining step including applying rules, filters, or algorithms associated with the monitored device.

3 . The method of claim 2 , including updating the rules, filters, or algorithms based on respective ones of the correlations

4 . The method of claim 3 , including applying the updated rules, filters, or algorithms to respective ones of the device status messages.

5 . The method of claim 1 , the analyzing step including analyzing the classification of the user's interaction.

6 . The method of claim 1 , including automatically acting on a device status message prior to providing the alert message to the interactive user interface.

7 . A non-transitory computer-readable medium having stored thereon instructions which when executed by a processor cause the processor to perform a method of generating intelligent alerts, the method comprising:
receiving one or more device status messages from sensors monitoring devices of a system; determining an alert priority for each of the one or more device status messages; storing the alert priority, the respective device status message, and associated metadata in a data store; providing an alert message to an interactive user interface, the alert message indicating the alert priority; monitoring a user's interaction with the alert message; classifying the user's interaction with the alert message; storing the user's interaction correlated with the corresponding alert message in a data store; analyzing the user's interaction to develop correlations between a cause of respective device status message, its associated data, and the user's interaction; and updating a data store with the correlation.

8 . The non-transitory computer-readable medium of claim 7 , including instructions to cause the processor to perform the determining step by including applying rules, filters, or algorithms associated with the monitored device.

9 . The non-transitory computer-readable medium of claim 8 , including instructions to cause the processor to perform updating the rules, filters, or algorithms based on respective ones of the correlations

10 . The non-transitory computer-readable medium of claim 9 , including instructions to cause the processor to perform applying the updated rules, filters, or algorithms to respective ones of the device status messages.

11 . The non-transitory computer-readable medium of claim 7 , including instructions to cause the processor to perform the analyzing step by including analyzing the classification of the user's interaction.

12 . The non-transitory computer-readable medium of claim 7 , including instructions to cause the processor to perform the step of automatically acting on a device status message prior to providing the alert message to the interactive user interface.

13 . A system for generating intelligent alert filters, the system comprising:
an alert generating unit configured to receive one or more device status messages from sensors monitoring devices of a monitored system; a control processor configured to determine an alert priority for each of the one or more device status messages; a data store configured to store the alert priority from the alert generating unit, the respective device status message, and associated metadata; an interactive user interface configured to provide a user with an alert message indicating the alert priority; a monitoring unit configured to monitor and capture a user's interaction with the alert message at the interactive user interface; a classification unit configured to classify the user's interaction with the alert message; a heuristic/artificial intelligence/machine learning (HAIML) unit configured to store the user's interaction correlated with the corresponding alert message in a data store; the HAIML unit configured to analyze the user's interaction and develop correlations between a cause of respective device status message, its associated data, and the user's interaction; and the HAIML unit configured to update the data store with the correlation.

14 . The system of claim 13 , further including the alert generating unit configured to apply rules, filters, or algorithms associated with the monitored device.

15 . The system of claim 14 , including the HAIML unit configured to update the rules, filters, or algorithms based on respective ones of the correlations

16 . The system of claim 15 , including the alert generating unit configured to apply the updated rules, filters, or algorithms to respective ones of the device status messages.

17 . The system of claim 13 , including the HAIML unit configured to analyze the classification of the user's interaction.

18 . The system of claim 13 , including the alert generating unit configured to automatically act on a device status message prior to providing the alert message to the interactive user interface.

Assignees

• Gen Electric

Inventors

• Cooper Jennifer Ruth
• Sykes Benjamin James

Classifications

• B64D2045/0085

  Devices for aircraft health monitoring, e.g. monitoring flutter or vibration · CPC title

• G06F3/0484 Primary

  for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range · CPC title

• B64D45/00

  Aircraft indicators or protectors not otherwise provided for · CPC title

• G06N5/025 Primary

  Extracting rules from data · CPC title

• G05B23/027 Primary

  Alarm generation, e.g. communication protocol; Forms of alarm · CPC title