METHOD AND SYSTEM FOR MACHINE UNDERSTANDING, KNOWLEDGE, AND CONVERSATION

• US 20080140387A1
• Filed: 12/07/2007
• Published: 06/12/2008
• Est. Priority Date: 12/07/2006
• Status: Active Grant

• Current Assignee: Sheldon O. Linker
• Original Assignee: Sheldon O. Linker
• Inventors: Linker, Sheldon O.
• Granted Patent: US 8,117,022 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30

Abstract

A system for storing knowledge in a speakable, formal class of languages and allowing querying and retrieving of that knowledge is provided. The system further allows the users to input data, instructions, questions, and queries without structure or rules over and above the actual grammar of the class of languages. The system responds in words, phrases or complete sentences as applicable, and its output is bound by the rules of logic, rather than simple correlation or likely meaning.

Claims

1. A method of processing a language, comprising:

inputting data in a formal, speakable language;

parsing the input data into an internal format in such a way that a memory of an original grammar structure present in the input data is retained;

comparing the parsed input data with previously stored data in a data/knowledge base to prove, disprove or determine if the parsed data is plausible;

storing results of the evaluation in the data/knowledge base.

2. The method of claim 1, wherein the formal, speakable language is understood by speakers of a corresponding natural language.

3. The method of claim 1, wherein the input data is at least one word of text or speech.

4. The method of claim 1, wherein inputting the data in a formal, speakable language and parsing the input data into an internal format include,

receiving the input data in a formal, spoken or written language;

and

translating the data into an internal data structure.

5. The method of claim 1, wherein the formal, speakable language is at least one of a Loglan-compatible, Lojban-compatible language structure, or any other speakable formal language structure.

6. The method of claim 1, wherein the input data is one or more utterances including at least one or sounds, words, movement, symbols, or abstraction.

7. The method of claim 6, wherein the one or more utterances are verbal, written, signed, referenced, imagined or picked up by an electronic sensing apparatus.

8. The method of claim 6, further comprising comparing a first utterance to a second utterance, where the first utterance has a higher level of specificity than the second utterance, to determine if the second utterance is superfluous.

9. The method of claim 1, further comprising determining whether the input data is a command, a statement of fact, or a question.

10. The method of claim 1, further comprising:

discarding the input data if the input data is a statement known to be true or false.

11. The method of claim 10, wherein the statement is added based upon rules of possibility, conjunctions, implications, and disjunctions.

12. The method of claim 1, wherein the formal language includes a grammar structure defined by:

a first characteristic to form predications and statements;

a second characteristic to form questions and queries;

a third characteristic to apply modifiers to portions of the text; and

a fourth characteristic ability to apply a broad category of tenses to portions of the text.

13. The method of claim 1, further comprising retaining the input data if the input data is a statement which provides new information to the data/knowledge base and adding the statement to the data/knowledge base.

14. The method of claim 1, further comprising formulating an answer if the input data is a question or query.

15. The method of claim 1, further comprising:

retrieving selected data stored in the data/knowledge base in response to a question;

formatting the selected data into an original natural language for output.

16. The method of claim 15, wherein the selected data is formatted into a natural or artificial language for output in response to the question based on stored data in the data/knowledge base.

17. A device for processing a language selected by a user, comprising:

an input module for receiving input data in the form of utterances in a formal, speakable language;

a parsing module for parsing the input data from the input module into an internal format;

a prover module for receiving the formatted input data from the parse module and comparing the parsed input data with previously stored data in a data/knowledge base to prove, disprove or determine if the parsed data is plausible; and

storing results of the prover module in the data/knowledge base.

18. The device of claim 17, wherein the prover module is configured to prove the statements, disprove the statements or show that the statements are plausible and saves in the data/knowledge base.

19. The device of claim 17, wherein the data is formatted into at least one of a natural or artificial language for output in response to a question based on knowledge data found with the data/knowledge base.

20. A device for processing a language selected by a user, comprising:

means for receiving data in the form of utterances in a formal, speakable language;

means for parsing the data into an internal format;

means for comparing the parsed input data with previously stored data in a data/knowledge base to prove, disprove or determine if the parsed data is plausible; and

means for storing the results of the comparison in the data/knowledge base.