Altering behavior of a multimodal application based on location

• US 9,208,783 B2
• Filed: 02/27/2007
• Issued: 12/08/2015
• Est. Priority Date: 02/27/2007
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Ativanichayaphong, Soonthorn, Cross, Charles W. Jr., Jablokov, Igor R., McCobb, Gerald M.
• Primary Examiner(s): ROBERTS, SHAUN A
• Application Number:
  US11/679,301
• Publication Number:
  US 20080208593A1
• Time in Patent Office: 3,206 Days
• Field of Search: 704/270, 704/275, 4554141-4144
• US Class Current: 1/1
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/24 Speech recognition using non-acoustical features

Abstract

Methods, apparatus, and products are disclosed for altering behavior of a multimodal application based on location. The multimodal application operates on a multimodal device supporting multiple modes of user interaction with the multimodal application, including a voice mode and one or more non-voice modes. The voice mode of user interaction with the multimodal application is supported by a voice interpreter. Altering behavior of a multimodal application based on location includes: receiving a location change notification in the voice interpreter from a device location manager, the device location manager operatively coupled to a position detection component of the multimodal device, the location change notification specifying a current location of the multimodal device; updating, by the voice interpreter, location-based environment parameters for the voice interpreter in dependence upon the current location of the multimodal device; and interpreting, by the voice interpreter, the multimodal application in dependence upon the location-based environment parameters.

Claims

1. A method for altering behavior of a multimodal application, executing on a first multimodal device, using semantically recognized voice commands that indicate a location of the first multimodal device, wherein the multimodal application comprises a plurality of markup documents, the method comprising:

storing, in a device location repository, location semantics for each of a plurality of multimodal devices including the first multimodal device and a second multimodal device, wherein first location semantics for the first multimodal device include a semantic representation of a first location and geographic coordinates for the first location, and wherein second location semantics for the second multimodal device are stored separately in the device location repository from the first location semantics for the first multimodal device;

determining, by a device location manager, that the first multimodal device is currently located at the first location based, at least in part, on geographic coordinates received from a position detection component of the first multimodal device and the geographic coordinates for the first location stored in the device location repository;

receiving, by a voice interpreter, a location change notification indicating the first multimodal device is currently located at the first location, wherein the location change notification includes the semantic representation of the first location;

responsive to receiving the location change notification, obtaining, by the voice interpreter, values for location-based environment parameters for the multimodal application executing on the first multimodal device from a configuration repository using the semantic representation of the first location received in the location change notification, wherein the values for the location-based environment parameters specify how to interpret at least some markup elements of the plurality of markup documents for the multimodal application; and

altering the behavior of the multimodal application based, at least in part, on the obtained values for the location-based parameters, wherein the voice interpreter uses the values for the location-based environment parameters to control the behavior of the multimodal application.

2. The method of claim 1, further comprising:

receiving, by the first multimodal device, an utterance comprising a location definition that associates the semantic representation of the first location with the geographic coordinates of the first location; and

providing the location definition to the location device manager.

3. The method of claim 2 further comprising recognizing the utterance using a speech engine.

4. The method of claim 1, wherein receiving the location change notification further comprises receiving the location change notification from the device location manager.

5. The method of claim 1, wherein altering the behavior of the multimodal application further comprises configuring the multimodal application to specify a location specific output modality for user interaction.

6. The method of claim 1, wherein altering the behavior of the multimodal application further comprises configuring the multimodal application to use a natural language for user interaction.

7. A multimodal device configured to customize a multimodal application using semantically recognized voice commands that indicate a location of the multimodal device, wherein the multimodal application comprises a plurality of markup documents, the multimodal device comprising:

a device location manager executing on the multimodal device configured to;

store, in a device location repository, location semantics for the multimodal device, wherein the location semantics for the multimodal device include a semantic representation of a location and geographic coordinates for the first location;

a voice interpreter executing on the multimodal device configured to;

receive a location change notification indicating the multimodal device is currently located at the first location, wherein the location change notification includes the semantic representation of the location;

obtain values for location-based environment parameters for the multimodal application executing on the multimodal device from a configuration repository using the semantic representation of the location received in the location received in the location change notification, wherein the values for the location-based environment parameters specify how to interpret at least some markup elements of the plurality of markup documents for the multimodal application; and

alter a behavior of the multimodal application based, at least in part, on the obtained values for the location-based environment parameters, wherein the voice interpreter uses the values for the location-based environment parameters to control the behavior of the multimodal application.

8. The multimodal device of claim 7, wherein the voice interpreter receives the location change notification from the device location manager.