Invoking tapered prompts in a multimodal application
First Claim
1. A computer-implemented method for invoking a tapered prompt comprising a plurality of prompt elements, each prompt element comprising a voice component and a non-voice component, the method comprising acts of:
- selecting a first voice style for the voice component of a first prompt element in the plurality of prompt elements of the tapered prompt, wherein the voice component of the first prompt element solicits requested information from a user;
selecting, in conjunction with selecting the first voice style, a first non-voice style for the non-voice component of the first prompt element, wherein the non-voice component of the first prompt element solicits the same requested information as the voice component of the first prompt element;
receiving voice input provided by the user in response to the first prompt element;
using at least one processor to process the voice input to determine whether the user provided the requested information; and
in response to determining that at least some of the requested information was not provided by the user, selecting a second voice style for the voice component of a second prompt element of the tapered prompt, and selecting, in conjunction with selecting the second voice style, a second non-voice style for the non-voice component of the second prompt element, wherein;
both the voice component and non-voice component of the second prompt element further solicit the at least some of the requested information from the user,the second voice style is different from the first voice style, andthe second non-voice style is different from the first non-voice style.
4 Assignments
0 Petitions
Accused Products
Abstract
Methods, apparatus, and computer program products are described for invoking tapered prompts in a multimodal application implemented with a multimodal browser and a multimodal application operating on a multimodal device supporting multiple modes of user interaction with the multimodal application, the modes of user interaction including a voice mode and one or more non-voice modes. Embodiments include identifying, by a multimodal browser, a prompt element in a multimodal application; identifying, by the multimodal browser, one or more attributes associated with the prompt element; and playing a speech prompt according to the one or more attributes associated with the prompt element.
164 Citations
18 Claims
-
1. A computer-implemented method for invoking a tapered prompt comprising a plurality of prompt elements, each prompt element comprising a voice component and a non-voice component, the method comprising acts of:
-
selecting a first voice style for the voice component of a first prompt element in the plurality of prompt elements of the tapered prompt, wherein the voice component of the first prompt element solicits requested information from a user; selecting, in conjunction with selecting the first voice style, a first non-voice style for the non-voice component of the first prompt element, wherein the non-voice component of the first prompt element solicits the same requested information as the voice component of the first prompt element; receiving voice input provided by the user in response to the first prompt element; using at least one processor to process the voice input to determine whether the user provided the requested information; and in response to determining that at least some of the requested information was not provided by the user, selecting a second voice style for the voice component of a second prompt element of the tapered prompt, and selecting, in conjunction with selecting the second voice style, a second non-voice style for the non-voice component of the second prompt element, wherein; both the voice component and non-voice component of the second prompt element further solicit the at least some of the requested information from the user, the second voice style is different from the first voice style, and the second non-voice style is different from the first non-voice style. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. At least one computer readable storage device having encoded thereon instructions that, when executed by at least one processor, perform a method for invoking a tapered prompt comprising a plurality of prompt elements, each prompt element comprising a voice component and a non-voice component, the method comprising acts of:
-
selecting a first voice style for the voice component of a first prompt element in the plurality of prompt elements of the tapered prompt, wherein the voice component of the first prompt element solicits requested information from a user; selecting, in conjunction with selecting the first voice style, a first non-voice style for the non-voice component of the first prompt element, wherein the non-voice component of the first prompt element solicits the same requested information as the voice component of the first prompt element; receiving voice input provided by the user in response to the first prompt element; processing the voice input to determine whether the user provided the requested information; and in response to determining that at least some of the requested information was not provided by the user, selecting a second voice style for the voice component of a second prompt element of the tapered prompt, and selecting, in conjunction with selecting the second voice style, a second non-voice style for the non-voice component of the second prompt element, wherein; both the voice component and non-voice component of the second prompt element further solicit the at least some of the requested information from the user, the second voice style is different from the first voice style, and the second non-voice style is different from the first non-voice style. - View Dependent Claims (8, 9, 10, 11, 12)
-
-
13. A system for invoking a tapered prompt comprising a plurality of prompt elements, each prompt element comprising a voice component and a non-voice component, the system comprising at least one processor programmed to:
-
select a first voice style for the voice component of a first prompt element in the plurality of prompt elements of the tapered prompt, wherein the voice component of the first prompt element solicits requested information from a user; select, in conjunction with selecting the first voice style, a first non-voice style for the non-voice component of the first prompt element, wherein the non-voice component of the first prompt element solicits the same requested information as the voice component of the first prompt element; receive voice input provided by the user in response to the first prompt element; process the voice input to determine whether the user provided the requested information; and in response to determining that at least some of the requested information was not provided by the user, select a second voice style for the voice component of a second prompt element of the tapered prompt, and select, in conjunction with selecting the second voice style, a second non-voice style for the non-voice component of the second prompt element, wherein; both the voice component and non-voice component of the second prompt element further solicit the at least some of the requested information from the user, the second voice style is different from the first voice style, and the second non-voice style is different from the first non-voice style. - View Dependent Claims (14, 15, 16, 17, 18)
-
Specification