Hallucination Detection
US-2024394600-A1 · Nov 28, 2024 · US
US9606985B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9606985-B2 |
| Application number | US-201414304289-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jun 13, 2014 |
| Priority date | Jun 13, 2014 |
| Publication date | Mar 28, 2017 |
| Grant date | Mar 28, 2017 |
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.
In accordance with aspects of the disclosure, a computing device may identify a prompt associated with an automated dialog application. An application expectation of the automated dialog application may be identified. The application expectation may comprise a structured natural language representation for a natural language response to the prompt. The computing device may receive natural language input responsive to the prompt, populate one or more data fields of the structured natural language representation with at least a portion of the natural language input, and may respond to the application expectation using the one or more data fields of the structured natural language representation.
Opening claim text (preview).
What is claimed is: 1. A computer-assisted method, comprising: identifying, by at least one processor of a computing device, a prompt associated with an automated dialog application; identifying, by the at least one processor, an application expectation of the automated dialog application that comprises a structured natural language representation for a natural language response to the prompt; receiving natural language input uttered by a user responsive to the prompt; transforming, by the at least one processor, one or more portions of the natural language input to one or more values responsive to the application expectation; populating, by the at least one processor, one or more data fields of the structured natural language representation with the one or more values responsive to the application expectation; and responding, by the at least one processor, to the application expectation using the one or more data fields of the structured natural language representation, wherein the structured natural language representation for the natural language input comprises a list structured natural language representation comprising a plurality of structured natural language representations of a common type, wherein the at least a portion of the natural language input comprises a first portion of natural language input corresponding to the common type and a second portion of natural language input corresponding to the common type, and wherein populating the one or more data fields of the structured natural language representation comprises populating one or more fields of a first structured natural language representation of the plurality of structured natural language representations of the common type with one of the one or more values transformed from the first portion of natural language input, and populating one or more fields of a second structured natural language representation of the plurality of structured natural language representation of the common type with one of the one or more values transformed from the second portion of natural language input. 2. The computer-assisted method of claim 1 , wherein the one or more data fields of the structured natural language representation comprise at least one data field configured for a text string, wherein the transforming the one or more portions of the natural language input comprises converting at least one portion of the natural language input to an input text string, and wherein the at least one data field configured for the text string is populated with the input text string. 3. The computer-assisted method of claim 1 , wherein the one or more data fields of the structured natural language representation comprise at least one data field configured for a numerical value, wherein the transforming the one or more portions of the natural language input comprises converting at least one portion of the natural language input to an input numerical value, and wherein the at least one data field configured for the numerical value is populated with the input numerical value. 4. The computer-assisted method of claim 1 , wherein the one or more fields of the first structured natural language representation are configured for a text string, wherein the one or more fields of the second structured natural language representation are configured for a text string, wherein the transforming the one or more portions of the natural language input comprises converting the first portion of the natural language input to a first input text string and the second portion of the natural language input to a second input text string, and wherein at least one of the fields of the first structured natural language representation is populated with the first input text string and at least one of the fields of the second structured natural language representation is populated with the second input text string. 5. The computer-assisted method of claim 1 , wherein the one or more fields of the first structured natural language representation are configured for a numerical value, wherein the one or more fields of the second structured natural language representation are configured for a numerical value, wherein the transforming the one or more portions of the natural language input comprises converting the first portion of the natural language input to a first input numerical value and converting the second portion of the natural language input to a second input numerical value, and wherein at least one of the fields of the first structured natural language representation is populated with the first input numerical value and at least one of the fields of the second structured natural language representation is populated with the second input numerical value. 6. The computer-assisted method of claim 1 , wherein the structured natural language representation for the natural language input comprises a hierarchical structured natural language representation comprising a plurality of different structured natural language representations and one or more attributes that interrelate the plurality of different structured natural language representations. 7. The computer-assisted method of claim 6 , wherein at least one of the one or more attributes indicates that a first of the plurality of different structured natural language representations is a subtype of a second of the plurality of different structured natural language representations. 8. The computer-assisted method of claim 7 , wherein the structured natural language representation for the natural language input comprises the second of the plurality of different structured natural language representations, and wherein populating the one or more data fields of the structured natural language representation comprises populating one or more data fields of the first of the plurality of different structured natural language representations. 9. The computer-assisted method of claim 8 , wherein the one or more data fields of the first of the plurality of different structured natural language representations are configured for a text string, wherein the transforming the one or more portions of the natural language input comprises converting at least one portion of the natural language input to an input text string, and wherein at least one of the data fields of the first of the plurality of different structured natural language representations is populated with the input text string. 10. The computer-assisted method of claim 8 , wherein the one or more data fields of the first of the plurality of different structured natural language representations are configured for a numerical value, and wherein the transforming the one or more portions of the natural language input comprises converting at least one portion of the natural language input to an input numerical value, and wherein at least one of the data fields of the first of the plurality of different structured natural language representations is populated with the input numerical value. 11. The computer-assisted method of claim 6 , wherein at least one of the one or more attributes indicates that a first of the plurality of different structured natural language representations comprises a second of the plurality of different structured natural language representations. 12. The computer-assisted method of claim 11 , wherein the structured natural language representation for the natural language input comprises the first of the plurality of different structured natural language representations, and wherein populating the one or more data fields of the structured natural language representation comprises populating one or more data fields of the second of the plurality of different st
Form filling; Merging · CPC title
Discourse or dialogue representation · CPC title
Execution procedure of a spoken command · CPC title
Natural language query formulation · CPC title
Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.