METHOD AND ARRANGEMENT FOR MANAGING GRAMMAR OPTIONS IN A GRAPHICAL CALLFLOW BUILDER

• US 20120209613A1
• Filed: 01/05/2012
• Published: 08/16/2012
• Est. Priority Date: 12/02/2003
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Agapi, Ciprian, Gomez, Felipe, Lewis, James R., Michelini, Vanessa V.
• Granted Patent: US 8,355,918 B2
• Time in Patent Office: Days
• US Class Current: 704/270.1
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/193 Formal grammars, e.g. finite state automata, context free grammars or word networks
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 2203/355 Interactive dialogue design tools, features or methods
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

A method (10) in a speech recognition application callflow can include the steps of assigning (11) an individual option and a pre-built grammar to a same prompt, treating (15) the individual option as a valid output of the pre-built grammar if the individual option is a potential valid match to a recognition phrase (12) or an annotation (13) in the pre-built grammar, and treating (14) the individual option as an independent grammar from the pre-built grammar if the individual option fails to be a potential valid match to the recognition phrase or the annotation in the pre-built grammar.

Claims

1. A method for generating a speech recognition application call flow from a call flow representation of the speech recognition application call flow specified by a designer using a user interface provided by a call flow design application executing on a computer, the call flow design application configured to allow the designer to create the call flow representation by allowing the user to specify elements of the call flow via the user interface, the method comprising:

adding a representation of a first prompt to the call flow representation in response to at least one designer instruction, received via the user interface provided by the call flow design application executing on the computer, to add the first prompt, the first prompt being defined to solicit a response from a user of the speech recognition application call flow;

adding a representation of at least one grammar, selected by the designer from a list of existing grammars, to the call flow representation in response to at least one designer instruction, received via the user interface provided by the call flow design application executing on the computer, to add the at least one grammar in association with the first prompt, the at least one grammar defining valid responses to the first prompt;

adding a representation of a response option to the call flow representation in response to at least one designer instruction, received via the user interface provided by the call flow design application executing on the computer, to add the response option in association with the first prompt, the response option defining a valid response to the first prompt;

adding a representation of a second prompt to the call flow representation in response to at least one designer instruction, received via the user interface provided by the call flow design application executing on the computer, to add the second prompt, the second prompt to be provided to the user should the user respond to the first prompt with one of the valid responses defined in the at least one grammar;

adding a representation of a third prompt to the call flow representation in response to at least one designer instruction, received via the user interface provided by the call flow design application executing on the computer, to add the third prompt, the third prompt to be provided to the user should the user respond to the first prompt with the response option; and

automatically checking whether the response option is defined as a valid response in the at least one grammar; and

automatically generating the speech recognition application call flow from the call flow representation such that if the response option is defined as a valid response in the at least one grammar, the third prompt is presented to the user instead of the second prompt when the user responds to the first prompt with the response option.

2. At least one non-transitory computer readable medium encoded with instruction that, when executed on at least one computer, perform a method for generating a speech recognition application call flow from a call flow representation of the speech recognition application call flow specified by a designer using a user interface configured to allow the designer to create the call flow representation, the method comprising:

adding a representation of a first prompt to the call flow representation in response to at least one designer instruction, received via the user interface, to add the first prompt, the first prompt being defined to solicit a response from a user of the speech recognition application call flow;

adding a representation of at least one grammar, selected by the designer from a list of existing grammars, to the call flow representation in response to at least one designer instruction, received via the user interface, to add the at least one grammar in association with the first prompt, the at least one grammar defining valid responses to the first prompt;

adding a representation of a response option to the call flow representation in response to at least one designer instruction, received via the user interface, to add the response option in association with the first prompt, the response option defining a valid response to the first prompt;

adding a representation of a second prompt to the call flow representation in response to at least one designer instruction, received via the user interface, to add the second prompt, the second prompt to be provided to the user should the user respond to the first prompt with one of the valid responses defined in the at least one grammar;

adding a representation of a third prompt to the call flow representation in response to at least one designer instruction, received via the user interface, to add the third prompt, the third prompt to be provided to the user should the user respond to the first prompt with the response option; and

automatically checking whether the response option is defined as a valid response in the at least one grammar; and

automatically generating the speech recognition application call flow from the call flow representation such that if the response option is defined as a valid response in the at least one grammar, the third prompt is presented to the user instead of the second prompt when the user responds to the first prompt with the response option.