Remote access system and method and intelligent agent therefor

Abstract

The invention relates to remote access systems and methods using automatic speech recognition to access a computer system. The invention also relates to an intelligent agent resident on the computer system for facilitating remote access to, and receipt of, information on the computer system through speech recognition or text-to-speech read-back. The remote access systems and methods can be used by a user of the computer system while traveling. The user can dial into a server system which is configured to interact with the user by automatic speech recognition and text-to-speech conversion. The server system establishes a connection to an intelligent agent running on the user's remotely located computer system by packet communication over a public network. The intelligent agent sources information on the user's computer system or a network accessible to the computer system, processes the information and transmits it to the server system over the public network. The server system converts the information into speech signals and transmits the speech signals to a telephone operated by the user.

1 . A method of providing access to a computer system over a network, the method comprising the steps of:
 receiving at the server system a first speech command from a user;   determining a type of command for the first speech command;   loading a set of indexed possible utterances associated with the type of command;   receiving at the server system a second speech command associated with the first speech command;   interpreting the second speech command using the set of indexed possible utterances;   at the server, generating first packet data based on the first and second speech command;   transmitting the first packet data over the network from the server to an agent;   at the server system, receiving second packet data from the agent in response to the first packet data, wherein the agent is operable to generate at least a portion of the second packet data from a dynamic set of sources; and   generating and transmitting a speech signal to the user based on the second packet data.   
     
     
         2 . The method of  claim 1  further comprising
 receiving user identification information; 
 authenticating the user at the server system based on the user identification information; and 
 prior to transmitting the first packet data, sending an initialization packet comprising the user identification information to the agent, wherein the identification information is for use by the agent to validate the user by comparing the identification information contained in the initialization packet to corresponding information stored at the agent. 
 
     
     
         3 . The method of  claim 1 , wherein each utterance of the set of indexed possible utterances is ranked based on a probability of usage. 
     
     
         4 . The method of  claim 1 , wherein the second packet data corresponds to an object accessible to the computer system. 
     
     
         5 . The method of  claim 4 , wherein the second packet data comprises a summarized form of the object, and wherein the summarized form is generated by the agent based on the object. 
     
     
         6 . The method of  claim 1 , further comprising the steps of establishing an encrypted connection between the server system and the agent resident on the computer system. 
     
     
         7 . The method of  claim 1  wherein the speech command received from the user is selected from the group consisting of: retrieving, creating, and modifying data accessible to the agent. 
     
     
         8 . The method of  claim 1  further comprising receiving a username and password from the user in order to generate identification information. 
     
     
         9 . The method of  claim 1  wherein the first packet data and the second packet data are generated based on a communication protocol that provides a mechanism for a variety of speech requests and payload replies to be handled by the server system, wherein the protocol specifies that the first packet data and the second packet data comprise a name of a service type to be accessed or delivered, an action to be performed, and parameters. 
     
     
         10 . A system for providing access to information over a network, the system comprising a server system, the server system having computer program code accessible thereto which, when executed by the server system, causes the server system to:
 receive a voice call from a user;   receive a first speech command from the user;   determine a type of command for the first speech command;   load a set of indexed possible utterances associated with the type of command;   receive at the server system a second speech command associated with the first speech command;   interpret the second speech command using the set of indexed possible utterances;   establish a connection with an agent;   generate first packet data based on the first and second speech commands;   transmit the first packet data over the network to the agent;   receive second packet data from the agent, wherein the agent is operable to generate at least a portion of the second packet data from a dynamic set of sources accessible by the agent; and   generate and transmit speech signals to the user based on the second packet data.   
     
     
         11 . The system of  claim 10 , wherein the computer program code executed by the server system, causes the server system:
 receive user identification information;   authenticate the user at the server system based on the user identification information; and   prior to transmitting the first packet data, send an initialization packet comprising the user identification information to the agent, wherein the identification information is for use by the agent to validate the user by comparing the identification information contained in the initialization packet to corresponding information stored at the agent.   
     
     
         12 . The system of  claim 10 , wherein the computer program code executed by the server system, causes the server system to configure a security manager to manage a security policy for authenticating the user. 
     
     
         13 . The system of  claim 10 , wherein the computer program code executed by the server system, causes the server system to configure a security manager to manage a secure connection to the agent on the computer system. 
     
     
         14 . The system of  claim 10 , wherein the agent has access to a remote server and the user is associated with a user account for the remote server. 
     
     
         15 . The system of  claim 10 , wherein the computer program code executed by the server system, causes the server system to configure a speech server for communicating with the user using automated speech recognition for received speech commands and automatic text-to-speech conversion for to generate speech signals for transmission to the user. 
     
     
         16 . The system of  claim 15 , further comprising a voice relay server in communication with the speech server and in communication with the agent for receiving data from the agent and for transmitting command request data to the agent corresponding to the speech commands received from the user at the speech server. 
     
     
         17 . The system of  claim 16 , wherein the computer program code executed by the server system causes the server system to maintain a user information datastore; and wherein the voice relay server compares user authentication information received from the user at the speech server to the user information data store to authenticate the user for access to the agent. 
     
     
         18 . The system of  claim 17 , wherein the user authentication information is determined by the speech server based on an identification utterance received from the user over the public telephone network. 
     
     
         19 . The system of  claim 14 , wherein the remote server hosts a plurality of user accounts and the agent facilitates remote access to each of the user accounts via the server system. 
     
     
         20 . The system of  claim 10  wherein the server system comprises a voice relay server configured to index the speech commands received by the user by maintaining a profile of speech commands for the user, wherein each speech command in the profile of speech commands is associated with a probability based on the frequency of usage by the user; the profile of speech commands for facilitating automated speech recognition of speech commands received from the user. 
     
     
         21 . The system of  claim 10  wherein the first packet data and the second packet data are generated based on a communication protocol that provides a mechanism for a variety of speech requests and payload replies to be handled by the server system, wherein the protocol specifies that the first packet data and the second packet data comprise a name of a service type to be accessed or delivered, an action to be performed, and parameters.