Text generation from correlated alerts

• US 9,946,711 B2
• Filed: 08/29/2013
• Issued: 04/17/2018
• Est. Priority Date: 08/29/2013
• Status: Active Grant

• Current Assignee: Arria Data2text Limited
• Original Assignee: Arria Data2text Limited
• Inventors: Reiter, Ehud B., Logan, Alasdair, Alvarez, Lucia Ortega, Apeh, Edward, Libman, Bracha, Bradshaw, William
• Primary Examiner(s): He, Jialong
• Application Number:
  US14/914,461
• Publication Number:
  US 20160217133A1
• Time in Patent Office: 1,692 Days
• CPC Class Codes: A61B 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/0816 Measuring devices for examining respiratory frequency measuring frequency of electric signals G01R23/00
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G08B 5/22 using electric transmission; using electromagnetic transmission

Abstract

Methods, apparatuses, and computer program products are described herein that are configured to generate an operator text in response to an alarm that is either received from an alarm or alert system or that is self-generated based on an analysis of one or more data feeds. The method of an example embodiment may include determining whether an operator text is to be generated in response to a received alert condition by performing data analysis operations comprising: analyzing, using a processor, a primary data feed and at least one confirmatory data feed to identify one or more features; and determining based on the detection of a feature in the primary data feed or the at least one confirmatory data feed satisfies at least one predetermined constraint. The method may further include generating an output text that is displayable in a user interface that describes at least a diagnosis for the feature that satisfied that at least one predetermined constraint.

Claims

1. A method for

determining whether an operator text is to be generated in response to a received alert condition by performing data analysis operations, the method comprising:

analyzing, using a processor, a primary data feed and at least one confirmatory data feed to identify one or more features related to the received alert condition;

determining whether the received alert condition in the primary data feed is confirmed by at least one confirmatory data feed, wherein the alert condition is validated in an instance in which a signal correlation between the primary data feed and the confirmatory data feed satisfies a correlation threshold;

determining whether the one or more features in the primary data feed are explainable by at least one diagnostic data feed; and

traversing, using the one or more features, a decision tree, wherein the decision tree is operable to determine that at least a portion of an operator text is to be generated in an instance in which a feature of the one or more features evaluates as true for at least one node of the decision tree; and

generating an output text that is displayable in a user interface that describes at least a diagnosis based on the at least one diagnostic data feed for the feature of the one or more features that evaluated as true.

2. The method of claim 1, the data analysis operations further comprising:

determining that the alert condition is present, wherein the alert condition is at least one of

received from an alert monitoring system over a data communication link;

or

determined based on a violation of a predetermined constraint by the one or more features in the primary data feed.

3. The method according to claim 1, wherein the one or more features is at least one of a trend, spike, oscillation or step in a data feed.

4. The method according to claim 1, the data analysis operations comprising validating the alert condition by performing validating operations further comprising:

determining whether an alert condition in the primary data feed is to be discarded based on at least one explanatory data feed, wherein the alert condition is discarded in an instance in which a signal correlation between the primary data feed and the explanatory data feed satisfies a discard threshold.

5. The method according to claim 1, wherein the at least one confirmatory data feed, an at least one explanatory data feed and an at least one diagnostic feed are identified as related to the primary data feed based on a loaded hierarchy.

6. The method according to claim 1, the data analysis operations further comprising:

determining a time until equipment failure based on the primary data feed; and

generating an output text that describes the time until equipment failure.

7. The method according to claim 1, further comprising:

determining an intended recipient of the operator text;

outputting the operator text in an instance in which the intended recipient is an operator; and

outputting a situational analysis text in an instance in which the intended recipient is not an operator.

8. The method according to claim 1, the data analysis operations further comprising:

analyzing the primary data feed and at least one of the confirmatory data feeds to determine whether the primary data feed and the at least one of the confirmatory data feeds is correlated for the one or more features by;

generating a signal correlation coefficient for each of the at least one of the confirmatory data feeds, the coefficient comparing the primary data feed with the at least confirmatory data feed; and

selecting the one or more of the at least one of the confirmatory data feeds in an instance in which a correlation threshold is satisfied; and

accessing a fault table, the fault table describing an associated fault for the feature of the primary data feed.

9. The method according to claim 1, wherein the message data structures comprise numerical data that describes at least one of the alert condition, a description of a stable period for the primary data feed, a description of a behavior of one or more related data feeds or a recommendation.

10. The method according to claim 1, data analysis operations further comprising:

determining an alert condition history over a predetermined time period for a machine that is monitored by the primary data feed; and

causing the operator text to comprise at least a portion of the alert condition history and an indication of the predetermined time period.

11. An apparatus for determining whether an operator text is to be generated in response to a received alert condition, the apparatus comprising:

at least one processor; and

at least one memory including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to at least;

analyze a primary data feed and at least one confirmatory data feed to identify one or more features related to the received alert condition;

determine whether the received alert condition in the primary data feed is confirmed by at least one confirmatory data feed, wherein the alert condition is validated in an instance in which a signal correlation between the primary data feed and the confirmatory data feed satisfies a correlation threshold;

determine whether the one or more features in the primary data feed are explainable by at least one diagnostic data feed; and

traverse, using the one or more features, a decision tree, wherein the decision tree is operable to determine that at least a portion of an operator text is to be generated in an instance in which a feature of the one or more features evaluates as true for at least one node of the decision tree; and

generate an output text that is displayable in a user interface that describes at least a diagnosis based on the at least one diagnostic data feed for the feature of the one or more features that evaluated as true.

12. The apparatus of claim 11, wherein the at least one memory including the computer program code is further configured to, with the at least one processor, cause the apparatus to:

determine that the alert condition is present, wherein the alert condition is at least one of

received from an alert monitoring system over a data communication link;

or

determined based on a violation of a predetermined constraint by the one or more features of the primary data feed.

13. The apparatus according to claim 11, wherein the one or more features is at least one of a trend, spike, oscillation or step in a data feed.

14. The apparatus according to claim 11, wherein the at least one memory including the computer program code is further configured to, with the at least one processor, cause the apparatus to:

determine whether an alert condition in the primary data feed is to be discarded based on at least one explanatory data feed, wherein the alert condition is discarded in an instance in which a signal correlation between the primary data feed and the explanatory data feed satisfies a discard threshold.

15. The apparatus according to claim 11, wherein the at least one confirmatory data feed, an at least one explanatory data feed and an at least one diagnostic feed are identified as related to the primary data feed based on a loaded hierarchy.

16. The apparatus according to claim 11, wherein the at least one memory including the computer program code is further configured to, with the at least one processor, cause the apparatus to:

determine a time until equipment failure based on the primary data feed; and

generate an output text that describes the time until equipment failure.

17. The apparatus according to claim 11, wherein the at least one memory including the computer program code is further configured to, with the at least one processor, cause the apparatus to:

determine an intended recipient of the operator text;

output the operator text in an instance in which the intended recipient is an operator; and

output a situational analysis text in an instance in which the intended recipient is not an operator.

18. The apparatus according to claim 11, wherein the at least one memory including the computer program code is further configured to, with the at least one processor, cause the apparatus to:

analyze the primary data feed and at least one of the confirmatory data feeds to determine whether the primary data feed and the at least one of the confirmatory data feeds is correlated for the one or more features by;

generating a signal correlation coefficient for each of the at least one of the confirmatory data feeds, the coefficient comparing the primary data feed with the at least confirmatory data feed; and

selecting the one or more of the at least one of the confirmatory data feeds in an instance in which a correlation threshold is satisfied; and

accessing a fault table, the fault table describing an associated fault for the one or more features of the primary data feed.

19. The apparatus according to claim 11, wherein the message data structures comprise numerical data that describes at least one of the alert condition, a description of a stable period for the primary data feed, a description of a behavior of one or more related data feeds or a recommendation.

20. The apparatus according to claim 11, wherein the at least one memory including the computer program code is further configured to, with the at least one processor, cause the apparatus to:

determine an alert condition history over a predetermined time period for a machine that is monitored by the primary data feed; and

cause the operator text to comprise at least a portion of the alert condition history and an indication of the predetermined time period.

21. A computer program product for determining whether an operator text is to be generated in response to a received alert condition, the computer program product comprising at least one computer readable non-transitory memory medium having program code instructions stored thereon, the program code instructions which when executed by an apparatus cause the apparatus at least to:

analyze a primary data feed and at least one confirmatory data feed to identify one or more features related to the received alert condition;

determine whether the received alert condition in the primary data feed is confirmed by at least one confirmatory data feed, wherein the alert condition is validated in an instance in which a signal correlation between the primary data feed and the confirmatory data feed satisfies a correlation threshold;

determine whether the one or more features in the primary data feed is explainable by at least one diagnostic data feed; and

traverse, using the one or more features, a decision tree, wherein the decision tree is operable to determine that at least a portion of an operator text is to be generated in an instance in which a feature of the one or more features evaluates as true for at least one node of the decision tree; and

generate an output text that is displayable in a user interface that describes at least a diagnosis based on the at least one diagnostic data feed for the feature of the one or more features that evaluated as true.