Speech recognition interface for voice actuation of legacy systems

• US 7,606,712 B1
• Filed: 06/28/2001
• Issued: 10/20/2009
• Est. Priority Date: 06/28/2001
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Inventors: Smith, Steven G., Mills, Ralph J., Morton, Jr., Roland T., Davis, Mitchell E.
• Primary Examiner(s): Armstrong, Angela A
• Application Number:
  US09/892,664
• Time in Patent Office: 3,036 Days
• Field of Search: 704/270, 704/270.1, 704231-235, 704/9, 704/275, 705/35, 370/252, 379/88.13
• US Class Current: 704/270.1
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

Methods and apparatus are disclosed for a technician to access a systems interface to back-end legacy systems by voice input commands to a speech recognition module. Generally, a user logs a computer into a systems interface which permits access to back-end legacy systems. Preferably, the systems interface includes a first server with middleware for managing the protocol interface. Preferably, the systems interface includes a second server for receiving requests and generating legacy transactions. After the computer is logged-on, a request for voice input is made. A speech recognition module is launched or otherwise activated. The user inputs voice commands that are processed to convert them to commands and text that can be recognized by the client software. The client software formats the requests and forwards them to the systems interface in order to retrieve the requested information.

Claims

1. A system for permitting a user to remotely access data, comprising:

a systems interface to a plurality of legacy systems, the systems interface comprising a first server for managing protocol and a second server for generating legacy transactions, and a firewall that protects the first server and the second server, wherein the first server provides multiple operations that may be utilized for generating the legacy transactions;

a computer operable by the user to access data from the legacy systems through the systems interface, wherein the computer is programmed with a client application for accessing the systems interface, wherein the client application provides a graphical user interface that has a page for selecting one of the multiple operations provided by the protocol server for the client application, and has a page comprising a plurality of data fields for each of the multiple operations, wherein when an operation is selected, the corresponding page is displayed, and wherein the client application is adapted to format requests for information based on user input within one of the pages corresponding to one of the multiple operations;

a voice input device coupled to the computer for receiving spoken words as a voice input from a user;

a speech recognition application executing within the computer, the speech recognition application converting the voice input into data recognized by the client application; and

a voice module operating within the speech recognition application that accesses a stored separate vocabulary for each of the pages for selecting and performing the multiple operations utilized for generating the legacy transactions on the legacy systems,

wherein selecting the multiple operations comprises utilizing the voice input for navigating to a search page and selecting an operation for retrieving client account information,

wherein performing the multiple operations comprises inputting the client account information based on the spoken words as the voice input to complete at least one of the plurality of data fields comprises utilizing the voice input to navigate among the plurality of data fields.

2. The system of claim 1, wherein the computer logs into the first server over a wireless communications network.

3. The system of claim 1, wherein the computer logs into the first server over a wireline communications network.

4. A system for permitting a user to remotely access data, comprising:

means for providing an interface to a plurality of legacy systems, wherein the means for providing an interface includes at least one firewall that protects the means for providing an interface from the legacy systems, wherein the means for providing an interface provides multiple operations that may be utilized for generating transactions with the legacy systems;

a computer operable by the user to retrieve data from the legacy systems by sending user requests to the means for providing an interface, wherein the computer includes a voice input device;

a communications link coupling the computer and the means for providing an interface;

a client software application executing within the computer, the client software application providing a graphical user interface that includes a page for selecting one of the multiple operations provided by the means for providing an interface for the client application and has a page for each of the multiple operations, wherein when an operation is selected the corresponding page is displayed; and

a speech recognition software application for;

converting spoken words provided as a voice input into a user input, the speech recognition software application including a voice module that accesses a stored separate vocabulary for each of the pages for selecting the multiple operations utilized for generating the legacy transactions on the legacy systems, the stored vocabulary for each of the pages including a spoken Go To command and a spoken TAB command for navigating to a search page,

performing the multiple operations utilized for generating the legacy transactions on the legacy systems, wherein performing the multiple operations comprises inputting the client account information based on the spoken words provided as the voice input to complete at least one of a plurality of data fields, and

selecting an operation for retrieving client account information.

5. The system of claim 4, wherein the user requests are processed by the means for providing an interface in order to generate legacy transactions.

6. The system of claim 4, wherein the means for providing an interface comprises a protocol server and a transaction server.

7. The system of claim 4, wherein the protocol server receives the user requests and forwards the user requests to the transaction server, and wherein the transaction server generates legacy transactions based on the user requests, receives the requested information based on the legacy transactions, and forwards the requested information to the protocol server.

8. A system for remotely accessing legacy data from a plurality of legacy systems, comprising:

a voice input device;

a modem;

a systems interface in communication with the plurality of legacy systems wherein the systems interface is protected from the legacy systems by a firewall, and wherein the systems interface provides multiple operations that may be utilized for generating transactions with the legacy systems; and

a computer, wherein the computer includes at least one memory programmed with software for performing the following;

providing a graphical user interface that has a page for selecting one of the multiple operations provided by the systems interface for the client application and has a page for each of the multiple operations wherein when an operation is selected the corresponding page is displayed,

receiving a request to input by voice;

activating a speech recognition module in response to the request, the speech recognition module including a speech module that accesses a stored separate vocabulary for each of the pages for selecting and performing the multiple operations utilized for generating the legacy transactions on the legacy systems,

wherein selecting the multiple operations comprises utilizing a Go To command in a speech input for navigating to a search page and selecting an operation for retrieving client account information, and

wherein performing the multiple operations comprises inputting the client account information based on spoken words as a speech input to complete at least one of a plurality of data fields,

wherein inputting the client account information to complete at least one of the plurality of data fields comprises utilizing a TAB command in the speech input to navigate among the plurality of data fields;

converting spoken words that are the speech inputs into a user request for information by using the separate vocabulary corresponding to the page that is displayed;

sending the user request for information to the systems interface; and

receiving data responsive to the user request.

9. A method for allowing a user to access data, comprising:

logging onto a systems interface to legacy systems;

providing a graphical user interface that includes a page for selecting one of the multiple operations provided by the systems interface for the client application and includes a page for each of the multiple operations wherein when an operation is selected the corresponding page is displayed;

activating a speech recognition module in response to the request, the speech recognition module including a voice module that accesses a stored separate vocabulary for each of the pages for selecting and performing the multiple operations utilized for generating the legacy transactions on the legacy systems,

wherein selecting the multiple operations comprises utilizing a spoken Go To command in a speech input for navigating to a search page and selecting an operation for retrieving client account information, and

wherein performing the multiple operations comprises inputting the client account information based on spoken words as a voice input to complete at least one of a plurality of data fields, wherein inputting the client account information to complete at least one of the plurality of data fields comprises utilizing a TAB command in the voice input to navigate among the plurality of data fields;

receiving spoken words as the voice inputs from the user;

converting the voice inputs to a user request by using the separate vocabulary corresponding to the page that is displayed;

sending the user request to the systems interface; and

receiving data from the systems interface in response to the user request.

10. The method of claim 9, further comprising the steps of:

receiving a request for input by speech; and

activating the speech recognition module in response to the request for input by speech.

11. The method of claim 9, wherein the step of converting the voice inputs to a user request comprises converting the voice inputs to user inputs and converting the user inputs into the user request.

12. The method of claim 11, wherein the systems interface comprises a protocol server and a transaction server.