User support apparatus and system using agents

• US 6,922,670 B2
• Filed: 03/30/2001
• Issued: 07/26/2005
• Est. Priority Date: 10/24/2000
• Status: Expired due to Fees

• Current Assignee: Sanyo Electric Company Limited (Panasonic Holdings Corporation)
• Original Assignee: Sanyo Electric Company Limited (Panasonic Holdings Corporation)
• Inventors: Maeda, Atsushi, Matsuoka, Tsugufumi, Yamada, Teruhiro
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US09/823,282
• Publication Number:
  US 20020049805A1
• Time in Patent Office: 1,579 Days
• Field of Search: 704/231, 704/246, 704/251, 704/270, 704/275, 704/270.1, 704 2- 9, 704/277, 379/88.01
• 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 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

A user support system employing agent technology is provided. The entrance server identifies the user command by matching it with a collection of anticipated user commands. An index search is performed to identify the contents of the user command. The identified user command is then used to determine which specialized server should respond to the user command. The specialized server contains a collection of action patterns for an agent to use in responding to a user command. An agent supports a user in searching for information and/or navigating to the desired information through friendly conversation with that user. The entrance server is configured as a portal site and a specialized server is provided for each specialized field.

Claims

1. A user support apparatus comprising:

an utterance identification block which has an electronic collection of user utterances, and identifies a content of a given user utterance, and

a response block which has an electronic collection of action patterns for a first agent for responding to user utterances, and enables the first agent to respond to the user utterances,

wherein the utterance identification block has an additional collection of anticipated utterances to which the first agent should react among utterances that a second agent makes to the user, and identifies a content of an utterance of the second agent if the utterance of the second agent exists in the additional utterance collection, and wherein the response block has an additional collection of action patterns for the first agent for reacting to the utterances of the second agent, and enables the first agent to occasionally react to the utterances of the second agent, and

wherein the additional utterance collection is incorporated into the user utterance collection, and the user utterance and the second agent utterance are matched with the integrated user utterance collection without any discrimination, when a process of the utterance identification block comes to at least a final stage.

2. A user support apparatus comprising:

an utterance identification block which has an electronic collection of user utterances, and identifies a content of a given user utterance; and

a response block which has an electronic collection of action patterns for a first agent for responding to user utterances, and enables the first agent to respond to the user utterances, wherein the utterance identification block has an additional collection of anticipated utterances to which the first agent should react among utterances that a second agent makes to the user, and identifies a content of an utterance of the second agent if the utterance of the second agent exists in the additional utterance collection, and wherein the response block has an additional collection of action patterns for the first agent for reacting to the utterances of the second agent, and enables the first agent to occasionally react to the utterances of the second agent, and

wherein both the first agent and the second agent are implemented on this apparatus, and the utterance identification block and the response block are symmetrically provided for the first agent and the second agent, and while the second agent mainly responds to the user instead of the first agent, the first agent occasionally reacts to the utterances of the second agent.

3. A user support system comprising a plurality of user support apparatus connected to a network as independent network nodes, wherein each of the apparatus is provided according to each specialized field, and the additional utterance collection, the agent action collection, and the additional action collection of each user support apparatus are generated according to each specialized field,

wherein each user support apparatus comprises:

an utterance identification block which has an electronic collection of user utterances, and identifies a content of a given user utterance; and

a response block which has an electronic collection of action patterns for a first agent for responding to user utterances and enables the first agent to respond to the user utterances,

wherein the utterance identification block has an additional collection of anticipated utterances to which the first agent should react among utterances that a second agent makes to the user, and identifies a content of an utterance of the second agent if the utterance of the second agent exists in the additional utterance collection, and wherein the response block has an additional collection of action patterns for the first agent for reacting to the utterances of the second agent, and enables the first agent to occasionally react to the utterances of the second agent.

4. The system of claim 3, wherein the plural user support apparatus include the respective response blocks therein and shares the utterance identification block at any one of the network nodes.

5. The system of claim 3, wherein each user support apparatus includes the first agent on the apparatus, and if the first agent appears on any other apparatus, the first agent acts as a second agent on said other apparatus.

6. The system of claim 3, wherein the utterance identification block includes:

an utterance search unit which searches the utterance of the user in the user utterance collection; and

a reporting unit which notifies a system administrator when the user utterance is not found in the user utterance collection.

7. The system of claim 6, wherein the utterance identification block further includes an index storing unit that stores an index of contents of the user utterance collection, and the search unit initially searches the given user utterance in the index storing unit.

8. The system of claim 3, further including a library providing unit which offers the user utterance library to a third party off line or on line.