Self-updating user interface/entertainment device that simulates personal interaction

• US 6,728,679 B1
• Filed: 10/30/2000
• Issued: 04/27/2004
• Est. Priority Date: 10/30/2000
• Status: Expired due to Fees

• Current Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Gutta, Srinivas, Pelletier, Daniel, Eshelman, Larry J., Strubbe, Hugo J., Milanski, John
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): Lerner, Martin
• Application Number:
  US09/699,578
• Time in Patent Office: 1,275 Days
• Field of Search: 707/3, 707/4, 707/5, 707/10, 704/270, 704/275, 704/270.1
• US Class Current: 704/270.1
• CPC Class Codes: G06F 3/011 Arrangements for interaction with the human body, e.g. for user immersion in virtual reality blind teaching G09B21/00

Abstract

An interaction simulator has the ability to dynamically update response templates and response data by retrieving current information from a data source. The interaction simulator may interact verbally or by other means such as gesture, typed text, or other means to generate a “dialogue. ” The interaction simulator, by dynamically updating its responses, is able to be more interesting and useful to users and also more personally relevant than prior art, so-called chatterbots. The device also reduces the required number of rules and library of response data that must be retained compared to prior art conversation simulators. The criteria used to create new response data can come from fixed specifications, for example, the current weather, or from the content of previous conversations (for example, the system creating a new template about a topic indicated by the user to be of interest to him/her).

Claims

1. A conversation simulator for simulating conversational interaction with a user, comprising:

a controller programmed to receive first, second, and third user inputs, each chronologically separated by at least one reply from said controller;

said first user input including a natural language declaration as distinguished from a query or a command;

an output device connected to said controller to output said corresponding replies;

an input device connected to apply said first, second, and third user inputs to said controller;

said controller being connected to a first external data source;

said controller being connected to a first data store containing reply data, said controller being programmed to generate said at least one reply corresponding to said first user input responsively to said first user input and said reply data;

said controller being connected also to a second external data source to retrieve live data periodically from said second external data source;

said controller being further programmed to generate said at least one reply corresponding to said second user input responsively to said live data.

2. A conversation simulator as in claim 1, wherein said live data is responsive to said first user input.

3. A conversation simulator as in claim 1, wherein said live data is retrieved responsive solely to a predefined schedule.

4. A conversation simulator as in claim 1, wherein said second external data source includes a network and said live data includes natural language text.

5. A conversation simulator as in claim 2, wherein said at least one reply corresponding to each of said first, second, and third user inputs includes natural language speech or text.

6. A conversation simulator as in claim 2, wherein said at least one reply corresponding to said first user input is not responsive to data retrieved from said first external data source.

7. A conversation simulator as in claim 2, wherein said second external data source include a network and said live data includes one of weather and current news.

8. A conversation simulator as in claim 7, wherein said at least one reply corresponding to each of said first, second, and third user inputs includes natural language speech or text.

9. A conversation simulator as in claim 1, wherein said second external data source include a network and said live data includes one of weather and current news.

10. A conversation simulator as in claim 1, wherein said at least one reply corresponding to each of said first, second, and third user inputs includes natural language speech or text.

11. A conversation simulator as in claim 1, wherein said at least one reply corresponding to said first user input is not responsive to data retrieved from said first external data source.

12. A conversation simulator as in claim 1, wherein said first, second, and third user inputs include audible speech and said input device includes an audio transducer.

13. A device for simulating personal interaction with a user, comprising:

a controller programmed to receive first, second, and third user inputs, each chronologically separated by at least one reply from said controller;

said first user input including a natural language declaration as distinguished from a query or a command;

an output device connected to said controller to output said corresponding replies;

an input device connected to apply said first, second, and third user inputs to said controller;

said controller being connected to a first external data source;

said controller being connected to a first data store containing reply data, said controller being programmed to generate said at least one reply corresponding to said first user input responsively to said first user input and said reply data;

said controller being connected also to a second external data source to retrieve live data responsive to said first user input;

said controller being further programmed to generate said at least one reply corresponding to said second user input responsively to said live data.

14. A device as in claim 13, wherein said second external data source includes a network and said live data includes natural language text.

15. A device as in claim 14, wherein said at least one reply corresponding to each of said first, second, and third user inputs includes natural language speech or text.

16. A device as in claim 14, wherein said at least one reply corresponding to said first user input is not responsive to data retrieved from said first external data source.

17. A device as in claim 14, wherein said second external data source include a network and said live data includes one of weather and current news.

18. A device as in claim 17, wherein said at least one reply corresponding to each of said first, second, and third user inputs includes natural language speech or text.

19. A device as in claim 13, wherein said second external data source include a network and said live data includes one of weather and current news.

20. A device as in claim 13, wherein said at least one reply corresponding to each of said first, second, and third user inputs includes natural language speech or text.

21. A device as in claim 13, wherein said at least one reply corresponding to said first user input is not responsive to data retrieved from said first external data source.

22. A device as in claim 13, wherein said first, second, and third user inputs include audible speech and said input device includes an audio transducer.

23. A method for simulating interaction, including verbal dialogue, between a user and a device, comprising the steps of:

storing on said device, first reply data corresponding to said verbal dialogue;

retrieving periodically second reply data from an external data source and storing said second reply data to add to said first reply data;

receiving, on said device, dialogue input from said user;

generating replies to said dialogue input responsively to said first reply data and said second reply data.

24. A method as in claim 23, wherein said step of receiving includes receiving natural language speech data.

25. A method as in claim 23, wherein said step of retrieving includes accessing text data from through an internet.

26. A method as in claim 23, wherein said step of generating includes generating audible speech.

27. A method as in claim 26, wherein said step of generating includes generating an animation synchronized with said speech.