Voice user interface authoring tool
First Claim
1. A method of generating a voice user interface implemented by a computing device, the method comprising:
- providing a response container for governing voice response processing for the voice user interface;
providing a plurality of nodes associated with the response container and defining acts to be performed;
providing a plurality of response classes defining types of voice input responses related to the plurality of nodes associated with the response container;
automatically generating a flow path for each of the plurality of response classes in the response container, each flow path spanning from a first node defining a first act to be performed to a second node defining a second act to be performed, wherein the generating the flow path for each of the plurality of response classes determines a callflow sequence of execution of acts of the plurality of nodes according to a response class associated with a voice input response;
receiving meanings of different possible answers expected in response to the plurality of nodes;
receiving sample inputs associated with each of the received meanings;
automatically generating control files to extract a meaning and to determine a response class associated with a received voice response based on the received meanings of different possible answers and the received sample inputs; and
automatically assigning a flow path to the received voice response based on an extracted meaning and a determined response class for establishing a callflow sequence in response to the received voice response.
2 Assignments
0 Petitions
Accused Products
Abstract
A voice user interface authoring tool is configured to use categorized example caller responses, from which callflow paths, automatic speech recognition, and natural language processing control files can be generated automatically within a single, integrated authoring user interface. A voice user interface (VUI) design component allows an author to create an application incorporating various types of action nodes, including Prompt/Response Processing (PRP) nodes. At runtime, the system uses the information from each PRP node to prompt a user to say something, and to process the user'"'"'s response in order to extract its meaning. An Automatic Speech Recognition/Natural Language Processing (ASR/NLP) Control Design component allows the author to associate sample inputs with each possible meaning, and automatically generates the necessary ASR and NLP runtime control files. The VUI design component allows the author to associate the appropriate ASR and NLP control files with each PRP node, and to associate an action node with each possible meaning, as indicated by the NLP control file.
26 Citations
15 Claims
-
1. A method of generating a voice user interface implemented by a computing device, the method comprising:
-
providing a response container for governing voice response processing for the voice user interface; providing a plurality of nodes associated with the response container and defining acts to be performed; providing a plurality of response classes defining types of voice input responses related to the plurality of nodes associated with the response container; automatically generating a flow path for each of the plurality of response classes in the response container, each flow path spanning from a first node defining a first act to be performed to a second node defining a second act to be performed, wherein the generating the flow path for each of the plurality of response classes determines a callflow sequence of execution of acts of the plurality of nodes according to a response class associated with a voice input response; receiving meanings of different possible answers expected in response to the plurality of nodes; receiving sample inputs associated with each of the received meanings; automatically generating control files to extract a meaning and to determine a response class associated with a received voice response based on the received meanings of different possible answers and the received sample inputs; and automatically assigning a flow path to the received voice response based on an extracted meaning and a determined response class for establishing a callflow sequence in response to the received voice response. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14)
-
-
15. A computer readable storage medium comprising instructions readable by a computing device, the instructions enabling the computing device to execute a voice user interface authoring tool, the instructions comprising:
-
an automatic speech recognition component; and a voice user interface design component implemented on a processor of the computing device to provide a response container for governing voice response processing for a voice user interface, to provide a plurality of nodes associated with the response container and defining acts to be performed, to provide a plurality of response classes defining types of voice input responses related to the plurality of nodes associated with the response container, to automatically generate a flow path for each of the plurality of response classes in the response container, each flow path spanning from a first node defining a first act to be performed to a second node defining a second act to be performed, wherein the generating the flow path for each of the plurality of response classes determines a callflow sequence of execution of acts of the plurality of nodes according to a response class associated with a voice input response, to receive meanings of different possible answers expected in response to the plurality of nodes, to receive sample inputs associated with each of the received meanings, to automatically generate control files to extract a meaning and to determine a response class associated with a received voice response based on the received meanings of different possible answers and the received sample inputs and to automatically assign a flow path to the received voice response based on an extracted meaning and a determined response class for establishing a callflow sequence in response to the received voice response.
-
Specification