Autonomous systems and network management using speech

• US 8,150,697 B2
• Filed: 09/30/2003
• Issued: 04/03/2012
• Est. Priority Date: 09/30/2003
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Mandalia, Baiju D., Mansey, Pradeep P.
• Primary Examiner(s): Smits, Talivaldis Ivars
• Assistant Examiner(s): PULLIAS, JESSE SCOTT
• Application Number:
  US10/677,891
• Publication Number:
  US 20050071164A1
• Time in Patent Office: 3,108 Days
• Field of Search: 704/270.1
• US Class Current: 704/275
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00

Abstract

A method of managing systems in a managed network can include storing configuration information corresponding to at least one managed system and automatically generating a grammar and a speech dialog for each managed system using the configuration information. User speech selecting a managed system can be received over a telephone call. The user speech can be recognized to identify the selected managed system. A grammar and speech dialog for the selected managed system can be loaded. Accordingly, the user can interact with one or more managed systems using the speech dialog. The user speech can be processed using the grammar.

Claims

1. A method of administering a plurality of managed systems in a managed network using a voice interface, the method comprising:

storing a configuration data store comprising a system speech profile corresponding to at least one managed system of the plurality of managed systems, wherein the system speech profile specifies which capabilities of the at least one managed system are available on the managed network and which capabilities are to be voice-enabled and made accessible via a telephony interface; and

automatically generating a grammar and a speech dialog for the at least one managed system using the system speech profile, wherein;

the speech dialog for the at least one managed system includes at least one generated audio prompt that is played via a telephone in response to accessing, via the telephony interface, at least one of the capabilities of the at least one managed system that are specified in the system speech profile to be voice-enabled, and wherein the at least one of the voice enabled capabilities comprises at least one administrative function to administer the at least one managed system,

the grammar is used to process speech input received from a user in response to the at least one generated audio prompt,

the speech dialog allows the user to administer the at least one managed system by accessing the at least one administrative function via at least one voice command, and

the at least one generated audio prompt comprises information extracted from a response from the at least one managed system responsive to the at least one voice command as dictated by the configuration data store.

2. The method of claim 1, further comprising:

adding a new managed system to the managed network by;

connecting the new managed system to the managed network;

detecting the new managed system; and

loading a system speech profile for the detected managed system.

3. The method of claim 1, wherein each system speech profile is generated based on specific capabilities of its corresponding managed system.

4. The method of claim 1, further comprising an act of:

providing an interface that enables a system administrator to manually edit the automatically generated speech dialog.

5. At least one computer readable storage device encoded with computer-executable instructions that, when executed on a computer system, perform a method of administering a plurality of managed systems in a managed network using a voice interface, the method comprising:

storing a configuration data store comprising a system speech profile corresponding to each managed system, wherein each system speech profile specifies which capabilities of its corresponding managed system that are available on the managed network and which capabilities are to be voice-enabled and made accessible via a telephony interface; and

automatically generating a grammar and a speech dialog for each managed system using its corresponding system speech profile, wherein;

the speech dialog for each managed system includes at least one generated audio prompt that is played via a telephone in response to accessing, via the telephony interface, at least one of the capabilities of its corresponding managed system that are specified in the corresponding system speech profile to be voice-enabled, wherein the at least one of the voice enabled capabilities comprises at least one administrative function to administer the corresponding managed system,

the grammar is used to process speech input received from a user in response to the at least one generated audio prompt,

the speech dialog allows the user to administer the corresponding managed system by accessing the at least one administrative function via at least one voice command, and

the at least one generated audio prompt comprises information extracted from a response from the corresponding managed system responsive to the at least one voice command as dictated by the configuration data store.

6. A computer system for administering a plurality of managed systems in a managed network, the computer system comprising:

a telephony interface to the managed network;

at least one controller, coupled to the telephony interface, that;

stores a configuration data store comprising a system speech profile corresponding to each managed system, wherein each system speech profile specifies which capabilities of its corresponding managed system are available on the managed network and which capabilities are to be voice-enabled and made accessible via a telephony interface; and

automatically generates a grammar and a speech dialog for each managed system using its corresponding system speech profile, wherein;

the speech dialog for each managed system includes at least one generated audio prompt that is played via a telephone in response to accessing, via the telephony interface, at least one of the capabilities of its corresponding managed system that are specified in the corresponding system speech profile to be voice-enabled, wherein the at least one of the voice enabled capabilities comprises at least one administrative function to administer the corresponding managed system,

the grammar is used to process speech input received from a user in response to the at least one generated audio prompt,

the speech dialog allows the user to administer the corresponding managed system by accessing the at least one administrative function via at least one voice command, and

the at least one generated audio prompt comprises information extracted from a response from the corresponding managed system responsive to the at least one voice command as dictated by the configuration data store.