Chat information service system

• US 20060155765A1
• Filed: 11/30/2005
• Published: 07/13/2006
• Est. Priority Date: 12/01/2004
• Status: Active Grant

• Current Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Takeuchi, Yohane, Hoshino, Atsushi
• Granted Patent: US 7,711,569 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

The present invention provides a chat information system having a voice recognition device for recognizing voices, a voice synthesizer, a humanoid robot, a microphone for receiving the voices and a speaker for pronouncing synthesized voices. The system comprises a headline sensor capturing news from the Internet, a news database for storing the captured news, and a conversation database including at least a general conversation database storing a set of inquiries and responses. The system also includes a chat engine configured to extract one or more keywords from a user'"'"'s speech that has been recognized by the voice recognition device, to search at least one of the news database and the conversation database with the extracted keywords and to output via the speaker the contents that have been hit by the search.

Claims

1. A chat information system having a voice recognition device for recognizing voices, a voice synthesizer, a humanoid robot, a microphone for receiving the voices and a speaker for pronouncing synthesized voices, comprising:

news capturing means for capturing news from the Internet;

a news database for storing the captured news;

a conversation database including at least a general conversation database storing a set of inquiries and responses; and

a chat engine configured to extract one or more keywords from a user'"'"'s speech that has been recognized by the voice recognition device, to search at least one of the news database and the conversation database with the extracted keywords and to output via the speaker the contents that have been hit by the search.

2. The system of claim 1, wherein said conversation database further includes a random chat database.

3. The system of claim 1, wherein the contents of the news database and the conversation database are assigned with priorities, and wherein the chat engine includes priority changing means for lowering the priority of the content that has been hit by the search and has been output as a response relative to the other contents.

4. The system of claim 2, wherein said conversation database includes a word conversion database.

5. The system as claimed in claim 3, wherein the chat engine searches at least one of said news database and the conversation database with a plurality of words included in a user'"'"'s speech, and when a plurality of contents are hit, selects and outputs one of the contents based on matching degree of the contents with the plurality of words and on said priorities assigned to the contents.

6. The system of claim 1, wherein said news capturing means includes a headline sensor capturing most recent news at a predetermined time interval, and wherein said news database updates its contents based on input from the headline sensor.

7. The system of claim 1, wherein the chat engine is configured to analyze the scripts of the content that is to be passed to said voice synthesizer, and to set a reserved chat flag when the script belongs to one of a plurality of predetermined chat patterns.

8. The system of claim 7, wherein, when said reserved chat flag is set, the chat engine outputs a response according to said chat pattern responsive to a user'"'"'s speech.