Delivery of audio driving directions via a telephone interface

• US 7,522,711 B1
• Filed: 09/18/2002
• Issued: 04/21/2009
• Est. Priority Date: 10/19/2001
• Status: Expired due to Fees

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Stein, Adam, Denney, Justin, Day, Chester, Coleman, Keith, Randall, Graham
• Primary Examiner(s): Nguyen; Quynh H
• Application Number:
  US10/247,074
• Time in Patent Office: 2,407 Days
• Field of Search: 379/88.04, 701/200, 701/201, 701/202, 701/208, 701/211, 701/212, 701/213, 701/1, 701/207
• US Class Current: 379/88.04
• CPC Class Codes: G01C 21/3608 using speech input, e.g. using speech recognition
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: H04M 2201/39 using speech synthesis speech synthesis per se G10L13/00
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2242/15 Information service where the information is dependent on the location of the subscriber
• CPC Class Codes: H04M 2242/30 Determination of the location of a subscriber
• CPC Class Codes: H04M 3/42365 Presence services providing information on the willingness to communicate or the ability to communicate in terms of media capability or network connectivity

Abstract

Methods for improving the delivery of audio driving directions from a voice portal to a caller via a telephone interface are described. These methods provide accurate and clear audio driving directions in a manner that is easy to use. Moreover, caller-provided inputs are responded to quickly.

Claims

1. A method of capturing an address from a caller via a telephone interface, said method comprising:

setting a grammar;

audibly prompting said caller to provide an utterance representing said address;

receiving said utterance via said telephone interface;

verifying said utterance using said grammar; and

if said utterance matches multiple entries of said grammar, identifying said utterance from said multiple entries using a relative size threshold, wherein said identifying comprises;

determining a relative size of each street name entry matching said utterance;

determining whether said relative size threshold is exceeded by relative size of any of street name entries; and

if said relative size threshold is exceeded by relative size of a particular street name entry, selecting said particular street name entry.

2. The method as recited in claim 1 wherein said grammar is set to one of city names, street names, and street numbers.

3. The method as recited in claim 1 wherein said verifying comprises:

if verification of said utterance is unsuccessful, playing an audio error message to said caller via said telephone interface.

4. The method as recited in claim 1 further comprising:

sending said address to a raw driving directions generator;

verifying said address with said raw driving directions generator;

if said verification of said address is unsuccessful, receiving an error message from said raw driving directions generator;

determining a helpful error message to provide to said caller via said telephone interface based on said error message; and

playing said helpful error message to said caller via said telephone interface.

5. A method of delivering audio driving directions via a telephone interface, said method comprising:

capturing an origin address and a destination address inputted by a caller via said telephone interface;

generating raw driving directions based on said origin and destination addresses;

generating formatted driving directions from identifying a maneuver in said raw driving directions;

wherein the maneuver comprises at least one of a merge-type, turn-type, and exit-ramp type;

wherein said generating formatted driving directions comprises;

removing one or more redundant steps from said raw driving directions;

replacing one or more first steps from said raw driving directions;

consolidating one or more second steps from said raw driving directions; and

renumbering said steps of said raw driving directions to form said formatted driving directions;

generating said audio driving directions based on said formatted driving directions; and

playing to said caller said audio driving directions in response to a command provided by said caller.

6. A voice portal comprising:

a processor;

a memory for storing therein instructions which when executed perform a method of capturing an address from a caller via a telephone interface, said method comprising;

setting a grammar;

audibly prompting said caller to provide an utterance representing said address;

receiving said utterance via said telephone interface;

verifying said utterance using said grammar; and

if said utterance matches multiple entries of said grammar, identifying said utterance from said multiple entries using a relative size threshold, wherein said identifying comprises;

determining a relative size of each street name entry matching said utterance;

determining whether said relative size threshold is exceeded by relative size of any of street name entries; and

if said relative size threshold is exceeded by relative size of a particular street name entry, selecting said particular street name entry.

7. The voice portal as recited in claim 6 wherein said grammar is set to one of city names, street names, and street numbers.

8. The voice portal as recited in claim 6 wherein said verifying comprises:

if verification of said utterance is unsuccessful, playing an audio error message to said caller via said telephone interface.

9. The voice portal as recited in claim 6 wherein said method further comprises:

sending said address to a raw driving directions generator;

verifying said address with said raw driving directions generator;

if said verification of said address is unsuccessful, receiving an error message from said raw driving directions generator;

determining a helpful error message to provide to said caller via said telephone interface based on said error message; and

playing said helpful error message to said caller via said telephone interface.