Method and apparatus for situational analysis text generation

• US 9,323,743 B2
• Filed: 06/23/2014
• Issued: 04/26/2016
• Est. Priority Date: 08/30/2012
• Status: Active Grant

• Current Assignee: Arria Data2text Limited
• Original Assignee: Arria Data2text Limited
• Inventors: Reiter, Ehud B.
• Primary Examiner(s): Nguyen, Timothy
• Application Number:
  US14/311,998
• Publication Number:
  US 20140372104A1
• Time in Patent Office: 673 Days
• Field of Search: 704/9
• US Class Current: 1/1
• CPC Class Codes: G06F 40/154 Tree transformation for tree-structured or markup documents, e.g. XSLT, XSL-FO or stylesheets
• CPC Class Codes: G06F 40/169 Annotation, e.g. comment data or footnotes
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G08B 21/18 Status alarms G08B21/02 takes precedence

Abstract

Methods, apparatuses, and computer program products are described herein that are configured to generate a situational analysis text. In some example embodiments, a method is provided that comprises generating a set of messages based on one or more key events in a primary data channel and one or more significant events in one or more related data channels in response to an alert condition. The method of this embodiment may also include generating a situational analysis text based on the set of messages and the relationships between them. In some example embodiments, the situational analysis text is configured to linguistically express the one or more key events, the one or more significant events, and the relationships between the one or more key events and the one or more significant events.

Claims

1. A method for generating a situational analysis text by transforming data that is expressed in a non-linguistic format into a format that can be expressed linguistically in a situational analysis text, the method comprising:

assigning, at least one data channel on which an alert condition was identified, as a primary data channel;

determining whether one or more data channels that are identified as related to the primary data channel are to be assigned as one or more related data channels, wherein the one or more related data channels are a subset of one or more monitored data channels;

generating, using a natural language generation system that is configured to execute on a processor, a graph based at least on the data in the primary data channel, wherein at least a portion of data in the primary data channel comprises numerical data; and

generating, using the natural language generation system that is configured to execute on the processor, the situational analysis text for display with the graph, the situational analysis text generated based at least on the data in the primary data channel, wherein the situational analysis text is configured to linguistically express contextual information related to the alert condition and the graph is configured to display numerical data in the primary data as a function of time, wherein at least a portion of the graph and at least a portion of the situational analysis text are generated in response to the identification of the alert condition.

2. The method according to claim 1, wherein the situational analysis text is further configured to express at least one of a proximate cause of the alert condition or an explanation of a diagnosis of the alert condition.

3. The method according to claim 1, wherein the situational analysis text is further generated based on data in the one or more related data channels in an instance in which one or more data channels are determined to be related to the primary data channel.

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

determining one or more causes of the alert condition; and

causing one or more related data channels to be selected that correspond to the one or more causes of the alert condition, wherein the situational analysis text is further configured to linguistically express the one or more causes of the alert condition.

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

determining that a relationship exists between the primary data channel and the one or more related data channels in an instance in which one or more data channels are determined to be related to the primary data channel;

determining an expression that linguistically describes the relationship between the primary data channel and the one or more related data channels; and

causing the expression to be expressed linguistically in the situational analysis text.

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

accessing at least one of historical data or event data for the primary data channel and the one or more related data channels; and

causing the at least one of the historical data or the event data to be expressed linguistically in the situational analysis text.

7. The method according to claim 6, wherein the historical data further comprises at least one of a previous event, contextual information, background information, or actions taken during a previous instance of the alert condition.

8. The method according to claim 6, wherein the historical data is related to a historical alert condition other than the alert condition.

9. The method according to claim 1, wherein the situational analysis text is further configured to comprise at least one of coherent text describing the alert condition, one or more events, or a history of the alert condition or related alert conditions.

10. The method according to claim 1, wherein a scale for the graph is determined based on one or more events in at least one of the primary data channel or the one or more related data channels.

11. The method according to claim 1, wherein the graph further comprises one or more textual annotations.

12. The method according to claim 1, wherein the graph is further generated based on data in the one or more related data channels in an instance in which one or more data channels are determined to be related to the primary data channel.

13. An apparatus for generating a situational analysis text that is configured to transform underlying data that is expressed in a non-linguistic format into a format that can be expressed linguistically in a situational analysis text, the apparatus comprising:

a data analyzer that is stored in a memory and configured, when executed on a processor, to access input raw data from one or more monitored data channels over a network and to identify at least one data channel of the one or more monitored data channels as the primary data channel based on the detection of an alert condition, wherein the data analyzer is further configured to determine whether one or more data channels that are to be assigned as one or more related data channels, wherein the one or more related data channels are a subset of one or more monitored data channels;

a data interpreter that is stored in the memory and configured, when executed on the processor, to generate, from the input raw data, language independent data structures that collect underlying data in the primary data channel and the more or more related data channels such that the underlying data is linguistically expressible, wherein at least a portion of the underlying data in the primary data channel comprises numerical data; and

a natural language generation system that is stored in the memory and configured, when executed on the processor, to input the one or more generated language independent data structures to determine a scale of a graph and the content of the situational analysis text, wherein the situational analysis text generated based at least on the data in the primary data channel, wherein the situational analysis text is configured to linguistically express contextual information related to the alert condition and wherein the graph is displayable with the situational analysis text and is generated based at least on the data in the primary data channel within the determined scale and the graph is further configured to display numerical data in the primary data channel as a function of time, wherein at least a portion of the graph and at least a portion of the situational analysis text are generated in response to the identification of the alert condition.

14. The apparatus according to claim 13, wherein the situational analysis text is further configured to express at least one of a proximate cause of the alert condition or an explanation of a diagnosis of the alert condition.

15. The apparatus according to claim 13, wherein the situational analysis text is further generated based on data in the one or more related data channels in an instance in which one or more data channels are determined to be related to the primary data channel.

16. The apparatus according to claim 13, wherein the data interpreter is further configured to generate language independent data structures based on at least one of historical data or event data for the primary data channel and the one or more related data channels, wherein the language independent data structures are configurable to cause the at least one of the historical data or the event data to be expressed linguistically in the situational analysis text.

17. The apparatus according to claim 16, wherein the historical data is related to a historical alert condition other than the alert condition.

18. The apparatus according to claim 13, wherein the situational analysis text is further configured to comprise at least one of coherent text describing the alert condition, one or more events, or a history of the alert condition or related alert conditions.

19. The apparatus according to claim 13, wherein a scale for the graph is determined based on the one or more related data channels and wherein the graph is further generated based on data in the one or more related data channels in an instance in which one or more data channels are determined to be related to the primary data channel.

20. The apparatus according to claim 13, wherein the graph further comprises one or more textual annotations.