Method, apparatus, and computer program product for user-directed reporting

• US 9,396,181 B1
• Filed: 09/16/2013
• Issued: 07/19/2016
• Est. Priority Date: 09/16/2013
• Status: Active Grant

• Current Assignee: Arria Data2text Limited
• Original Assignee: Arria Data2text Limited
• Inventors: Sripada, Gowri Somayajulu, de Paiva, Daniel da Silva, Dale, Robert, Feegrade, Mario
• Primary Examiner(s): McFadden, Susan
• Application Number:
  US14/027,684
• Time in Patent Office: 1,037 Days
• Field of Search: 704/9
• US Class Current: 1/1
• CPC Class Codes: G06F 16/31 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/3328 using graphical result space presentation or visualisation
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06F 40/134 Hyperlinking
• CPC Class Codes: G06F 40/169 Annotation, e.g. comment data or footnotes
• CPC Class Codes: G06F 40/56 Natural language generation

Abstract

A method, apparatus, and computer program product are recited herein for user-directed reporting. In the context of a method, context information is received, wherein the context information defines the data set from which a natural language text or a graph is to be derived. The method further includes generating a set of messages based on the context information. The method further includes generating, by a processor, a context-specific report based on the set of messages and the relationship between them, wherein the context-specific report is configured to linguistically or visually express at least of messages. A corresponding apparatus and computer program product are provided.

Claims

1. A method for processing a request that comprises context information received via a user interface to generate a context-specific report generated by a natural language generation system, the method comprising:

receiving context information as a result of a user interaction with the user interface, wherein the context information defines a feature set;

converting, by a processor, the received context information into a structured query language (SQL) query to retrieve relevant data from a data repository;

generating a reduced data set from the data repository, wherein the reduced data set corresponds to data received in response to the SQL query;

generating a set of messages that describe at least one or linguistically describable trend in the reduced data set, wherein the set of messages are instantiated based on an analysis of the reduced data set; and

generating, by a natural language generation system that is configured to execute on the processor, a context-specific report about the feature set based on the set of messages and a predefined relationship between them drawn from an ontology, wherein the context-specific report at least one of linguistically or visually expresses data in at least a portion of the messages.

2. The method according to claim 1, wherein the context-specific report includes at least one of natural language text and graphic displays.

3. The method according to claim 1, wherein the context information comprises at least one selected from the group consisting of:

a subject matter constraint, a time constraint, and a length constraint.

4. The method according to claim 1, wherein the context information comprises abstractions of one or more of the attributes of the data repository.

5. The method according to claim 1, wherein the context information is associated with more than one person.

6. The method according to claim 1, wherein the ontology specifies kinds of objects and concepts that exist in a domain in concrete or abstract form, properties predicated of said objects and concepts, relationships that hold between said objects and concepts, and representations of specific knowledge that is required to function in the domain.

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

displaying the context-specific report; and

generating additional messages based on the context information, wherein additional reporting data corresponding to the additional messages is viewable based on interaction with the displayed context-specific report.

8. The method according to claim 7, wherein the interaction with the displayed context-specific report comprises at least one selected from the group consisting of:

a mouse-over of an element of the context-specific report and selection of a hyperlinked portion of the context-specific report.

9. The method according to claim 7, wherein the additional reporting data comprises a pop-out annotation of graphical content, additional detail regarding a message in the context-specific report, preview information corresponding to a message in the context-specific report, and context-sensitive information generated based on a set of information previously presented with the context-specific report.

10. An 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:

receive context information as a result of a user interaction with the user interface, wherein the context information defines a feature set;

convert the received context information that defines a feature set into a structured query language (SQL) query to retrieve relevant data from a data repository;

generate a reduced data set from the data repository, wherein the reduced data set corresponds to data received in response to the SQL query;

generate a set of messages that describe at least one or linguistically describable trend in the reduced data set, wherein the set of messages are instantiated based on an analysis of the reduced data set;

generate a context-specific report about the feature set based on the set of messages and a predefined relationship between them drawn from an ontology, wherein the context-specific report at least one of linguistically or visually expresses data in at least a portion of the messages.

11. The apparatus according to claim 10, wherein the context-specific report includes at least one of natural language text and graphic displays.

12. The apparatus according to claim 10, wherein the context information comprises at least one selected from the group consisting of:

a subject matter constraint, a time constraint, and a length constraint.

13. The method according to claim 10, wherein the context information comprises abstractions of one or more of the attributes of the data repository.

14. The apparatus according to claim 10, wherein the context information is associated with more than one person.

15. The apparatus according to claim 10, wherein the ontology specifies kinds of objects and concepts that exist in a domain in concrete or abstract form, properties predicated of said objects and concepts, relationships that hold between said objects and concepts, and representations of specific knowledge that is required to function in the domain.

16. The apparatus according to claim 10, wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus to:

display the context-specific report; and

generate additional messages based on the context information, wherein additional reporting data corresponding to the additional messages is viewable based on interaction with the displayed context-specific report.

17. The apparatus according to claim 16, wherein the interaction with the displayed context-specific report comprises at least one selected from the group consisting of:

a mouse-over of an element of the context-specific report and selection of a hyperlinked portion of the context-specific report.

18. The apparatus according to claim 16, wherein the additional reporting data comprises a pop-out annotation of graphical content, additional detail regarding a message in the context-specific report, preview information corresponding to a message in the context-specific report, and context-sensitive information generated based on a set of information previously presented with the context-specific report.

19. A computer program product comprising at least one computer-readable non-transitory memory medium having program code instructions stored thereon, the program code instructions, when executed by an apparatus, causing the apparatus to:

receive context information as a result of a user interaction with the user interface, wherein the context information defines a feature set;

convert the received context information that defines a feature set into a structured query language (SQL) query to retrieve relevant data from a data repository;

generate a reduced data set from the data repository, wherein the reduced data set corresponds to data received in response to the SQL query;

generate a set of messages that describe at least one or linguistically describable trend in the reduced data set, wherein the set of messages are instantiated based on an analysis of the reduced data set;

generate a context-specific report about the feature set based on the set of messages and a predefined relationship between them drawn from an ontology, wherein the context-specific report at least one of linguistically or visually expresses data in at least a portion of the messages.

20. The computer program product according to claim 19, wherein the context-specific report includes at least one of natural language text and graphic displays.