Method and apparatus for expressing time in an output text
US-2015324351-A1 · Nov 12, 2015 · US
US11561986B1 · US · B1
| Field | Value |
|---|---|
| Publication number | US-11561986-B1 |
| Application number | US-201816235594-A |
| Country | US |
| Kind code | B1 |
| Filing date | Dec 28, 2018 |
| Priority date | Jan 17, 2018 |
| Publication date | Jan 24, 2023 |
| Grant date | Jan 24, 2023 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Disclosed herein are example embodiments of an improved narrative generation system where an analysis service that executes data analysis logic that supports story generation is segregated from an authoring service that executes authoring logic for story generation through an interface. Accordingly, when the authoring service needs analysis from the analysis service, it can invoke the analysis service through the interface. By exposing the analysis service to the authoring service through the shared interface, the details of the logic underlying the analysis service are shielded from the authoring service (and vice versa where the details of the authoring service are shielded from the analysis service). Through parameterization of operating variables, the analysis service can thus be designed as a generalized data analysis service that can operate in a number of different content verticals with respect to a variety of different story types.
Opening claim text (preview).
What is claimed is: 1. A natural language generation (NLG) apparatus for applying artificial intelligence to generate a narrative story about structured data, the apparatus comprising: a processor and a memory that are operatively coupled with each other and comprise (1) an authoring service configured to execute authoring logic for story generation and (2) an analysis service configured to execute data analysis logic to support story generation; wherein the analysis service is segregated from and exposed to the authoring service through an interface so that (1) details of the data analysis logic are shielded from the authoring service and (2) details of the authoring logic are shielded from the analysis service; wherein the analysis service comprises a plurality of different analytics that are parameterizable via a plurality of operating variables so that the analysis service serves as a generalized analysis service that is operable in a plurality of different content verticals with respect to a plurality of different story types; wherein the authoring service is further configured to invoke the analysis service through the interface to obtain data analysis about the structured data from the analysis service, wherein the invocation of the analysis service through the interface includes a specification of a plurality of the operating variables for one or more of the analytics through the interface to configure the analysis service for analyzing the structured data; wherein the analysis service is further configured, in response to invocation by the authoring service through the interface, to (i) generate metadata about the structured data based on execution of the data analysis logic in accordance with the specified operating variables and (ii) communicate the metadata to the authoring service; and wherein the authoring service is further configured to (1) receive the communicated metadata and (2) process the structured data and the communicated metadata in accordance with a story configuration based on the authoring logic to (i) determine one or more insights about the structured data based on the communicated metadata and (ii) generate a narrative story that expresses the determined one or more insights as natural language text. 2. The apparatus of claim 1 wherein the authoring service is further configured to communicate a structured message to the analysis service through the interface to invoke the analysis service. 3. The apparatus of claim 2 wherein the analysis service is further configured, in response to invocation by the authoring service through the interface, to select a subset of the analytics for execution based on a parameter in the structured message. 4. The apparatus of claim 3 wherein the structured message parameter comprises a plurality of parameters in the structured message. 5. The apparatus of claim 3 wherein the structured message further comprises at least a portion of the structured data from which the narrative story is generated; and wherein the analysis service is further configured, in response to invocation by the authoring service through the interface, to select the subset of the analytics for execution based on (1) the structured message parameter and (2) structured data within the structured message. 6. The apparatus of claim 3 wherein the analysis service is further configured to (1) resolve an analytics configuration based on the structured message, wherein the resolved analytics configuration enables the selected subset of the analytics, (2) instantiate an analytics application based on the analytics configuration, (3) execute the instantiated analytics application to selectively invoke the selected subset of the analytics, and (4) receive and serialize a plurality of results from the selectively invoked subset of the analytics. 7. The apparatus of claim 6 wherein the analytics configuration specifies an order of precedence for the selectively invoked subset of the analytics. 8. The apparatus of claim 6 wherein the analytics configuration specifies a parameter value for use in controlling at least one of the selectively invoked subset of the analytics. 9. The apparatus of claim 8 wherein the parameter value comprises a threshold value. 10. The apparatus of claim 8 wherein the structured message includes the parameter value. 11. The apparatus of claim 1 wherein the structured data comprises visualization data. 12. The apparatus of claim 11 wherein the visualization data comprises at least one of line chart data, bar chart data, histogram data, pie chart data, and/or scatterplot data. 13. The apparatus of claim 1 wherein the analysis service is configured as a web service. 14. The apparatus of claim 1 wherein the processor and memory comprise a plurality of processors and memories. 15. The apparatus of claim 14 wherein the processors and memories are arranged as a distributed computing architecture. 16. The apparatus of claim 1 wherein the structured data comprises a plurality of values for a plurality of fields of the structured data, wherein a plurality of the analytics are parameterizable for execution to analyze values within the structured data to generate metadata about the structured data that is indicative of an insight about the structured data. 17. The apparatus of claim 16 wherein a plurality of the analytics are organized into a plurality of different analysis libraries; wherein the analysis service further comprises a plurality of different analysis applications, wherein each of a plurality of the analysis applications is configured to bundle different subsets of the analytics via links to the analysis libraries; wherein the authoring service is further configured to communicate a structured message to the analysis service through the interface to invoke the analysis service; wherein the analysis service is further configured, in response to invocation by the authoring service through the interface, to (1) select an analysis application based on the structured message, (2) invoke a subset of the analytics within one or more of the analysis libraries for execution via the selected analysis application, and (3) parameterize and execute the invoked subset of the analytics using the structured data to generate metadata about the structured data. 18. The apparatus of claim 17 wherein the interface comprises a first interface, and wherein the analysis applications are segregated from the analysis libraries and the analytics through a second interface, and wherein the analysis applications are configured to invoke the subset of the analytics via one or more of the analysis libraries at runtime through the second interface, and wherein the metadata generated by the subset of the analytics are communicated to the selected analysis application via the second interface. 19. The apparatus of claim 17 wherein the different analysis applications are associated with different story types, wherein the structured message is indicative of a story type for the narrative story, and wherein the analysis service is further configured, in response to invocation by the authoring service through the interface, to select the analysis application that is associated with the story type indicated by the structured message. 20. The apparatus of claim 17 wherein the structured data comprises chart data, wherein the structured message identifies a chart type for the chart data, wherein the analysis applications include a plurality of different analysis applications associated with dif
Presentation of query results · CPC title
using data annotations, e.g. user-defined metadata · CPC title
using ranking · CPC title
Natural language analysis (semantic analysis of natural language G06F40/30) · CPC title
Visual data mining; Browsing structured data · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.