Speech recognition interface for voice actuation of legacy systems
View Patent ↗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.
1. An apparatus comprising:
a processor; and
a computer-readable storage medium having instruction stored which, when executed by the processor, result in the processor performing operations comprising:
presenting a visual prompt to a user;
receiving, in response to the visual prompt, a multimodal request from the user to perform a transaction, wherein:
the multimodal request has a speech portion that is recognized by an input device using a separate vocabulary for each page linked to each operation;
the multimodal request has a second portion comprising a cursor input;
and
the multimodal request comprises input to:
navigate to a search page;
retrieve client account information; and
navigate among a plurality of data fields using a TAB command;
identifying a legacy system with which performing the transaction requires communication;
establishing a connection with the legacy system;
translating the multimodal request to a format compatible with the legacy system, to yield a translated multimedia request; and
submitting the translated multimodal request to the legacy system.
2. The apparatus of claim 1 , wherein the connection with the legacy system is over a wireless communications network.
3. The apparatus of claim 1 , wherein the connection with the legacy system is over a wireline communications network.
4. The apparatus of claim 1 , wherein the transaction comprises a plurality of operations in a plurality of pages associated with a graphical user interface.
5. The apparatus of claim 4 , wherein a plurality of vocabularies, each corresponding to the plurality of operations, comprises the separate vocabulary for each operation.
6. A method comprising:
presenting a visual prompt to a user;
in response to the visual prompt, receiving a multimodal request from the user to perform a transaction, wherein:
the multimodal request has a speech portion that is recognized by an input device using a separate vocabulary for each page linked to each operation;
the multimodal request has a second portion comprising a cursor input;
and
the multimodal request comprises input to:
navigate to a search page;
retrieve client account information; and
navigate among a plurality of data fields using a TAB command;
identifying, via a processor, a legacy system with which performing the transaction requires communication;
establishing a connection with the legacy system;
translating the multimodal request to a format compatible with the legacy system, to yield a translated multimedia request; and
submitting the translated multimodal request to the legacy system.
7. The method of claim 6 , wherein the connection with the legacy system is over a wireless communications network.
8. The method of claim 6 , wherein the connection with the legacy system is over a wireline communications network.
9. The method of claim 6 , wherein the transaction comprises a plurality of operations in a plurality of pages associated with a graphical user interface.
10. The method of claim 9 , wherein a plurality of vocabularies, each corresponding to the plurality of operations, comprises the separate vocabulary for each operation.
11. The method of claim 6 , wherein the TAB command is an audible command.
12. The method of claim 6 , wherein navigation among the plurality of data fields is further based on a Go To command.
13. The method of claim 12 , wherein the Go To command is another audible command.
14. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
presenting a visual prompt to a user;
in response to the visual prompt, receiving a multimodal request from the user to perform a transaction, wherein:
the multimodal request has a speech portion that is recognized by an input device using a separate vocabulary for each page linked to each operation;
the multimodal request has a second portion comprising a cursor input;
and
the multimodal request comprises multimodal input to:
navigate to a search page;
retrieve client account information; and
navigate among a plurality of data fields using a TAB command;
identifying a legacy system with which performing the transaction requires communication;
establishing a connection with the legacy system;
translating the multimodal request to a format compatible with the legacy system, to yield a translated multimedia request; and
submitting the translated multimodal request to the legacy system.
15. The computer-readable storage device of claim 14 , wherein the connection with the legacy system is over a wireless communications network.
16. The computer-readable storage device of claim 14 , wherein the connection with the legacy system is over a wireline communications network.
17. The computer-readable storage device of claim 14 , wherein the transaction comprises a plurality of operations in a plurality of pages associated with a graphical user interface.
18. The computer-readable storage device of claim 17 , wherein a plurality of vocabularies, each corresponding to the plurality of operations, comprises the separate vocabulary for each operation.