Artificially intelligent natural language computational interface system for interfacing a human to a data processor having human-like responses

• US 5,855,002 A
• Filed: 06/11/1996
• Issued: 12/29/1998
• Est. Priority Date: 06/11/1996
• Status: Expired due to Fees

• Current Assignee: Pegasus Micro-Technologies, Inc.
• Original Assignee: Pegasus Micro-Technologies, Inc.
• Inventors: Armstrong, Alan A.
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US08/661,433
• Time in Patent Office: 931 Days
• Field of Search: 395/2.79, 395/2.84, 395/2.86, 364/419.07, 379/88, 704/270, 704/275, 704/277
• US Class Current: 704/270
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 2015/226 using non-speech characteristics

Abstract

A system for interfacing a human user to a data processor which receives inputs from the user and includes associated storage resource information. The data processor generates outputs to the user and associated output devices. The interface system includes structure for receiving a statement generated by the human user in natural language on a word-by-word basis. The system analyzes the statement to identify a subject and object and searches the stored resource information for data related to the identified subject. Output devices are provided for generating to the user the data from the stored resource information related to the identified subject.

Claims

1. A system for interfacing a human user to a data processor, the data processor receiving inputs from the user and includes associated stored resource information, and which generates outputs to the user and associated output devices, the system comprising:

means for receiving a statement generated by the human user in natural language on a word-by-word basis;

means for analyzing the statement to identify a subject;

means for searching the stored resource information for data related to said identified subject;

means for providing to the users data from the stored resource information related to the identified subject;

means for determining a mood of a user from the statements generated by the user and for creating a human-like response; and

means for providing an output to the user, the output being responsive to the user based upon an analysis of the data from the stored resource information to provide an answer to the user, thereby providing new data to the user which is not directly stored in the resource information.

2. The system of claim 1 wherein said analyzing means reformats statements presented in the form of questions into statements in the form of a sentence.

3. The system of claim 1 wherein said analyzing means identifies key words based on pre-stored words in the stored resource information.

4. The system of claim 1 wherein said searching means includes:

a first storage area for storing resources associated with the user;

a second storage area for storing resources associated with the system; and

a third storage area for storing resources external to the system.

5. A method for interfacing a human user to a data processor, the data processor receiving inputs from the user and includes associated stored resource information, and which generates outputs to the user and associated output devices, the method comprising the steps of:

receiving a statement generated by the human user in natural language on a word-by-word basis;

analyzing the statement to identify a subject;

searching the stored resource information for data related to the identified subject;

providing to the user, data from the stored resource information related to the identified subject;

means for determining a mood of a user from the statements generated by the user and for creating a human-like response; and

generating an output to the user, the output being responsive to the user based upon an analysis of the data from the stored resource information to provide an answer to the user, thereby providing new data to the user which is not directly stored in the resource information.

6. The method of claim 5 wherein the step of searching includes:

searching a first storage area for storing resources associated with the user;

searching a second storage area for storing resources associated with the system; and

searching a third storage area for storing resources external to the system.

7. The method of claim 6 wherein the step of analyzing includes reformatting statements presented in the form of questions into statements in the form of a sentence.

8. The method of claim 6 wherein the step of analyzing includes identifying key words based on pre-stored words in the stored resource information.