KNOWLEDGE STORAGE AND RETRIEVAL SYSTEM AND METHOD

• US 20120036145A1
• Filed: 10/17/2011
• Published: 02/09/2012
• Est. Priority Date: 11/28/2000
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: True Knowledge Ltd (Amazon.com, Inc.)
• Inventors: Tunstall-Pedoe, William
• Granted Patent: US 8,219,599 B2
• Time in Patent Office: Days
• US Class Current: 707/760
• CPC Class Codes: G06F 16/24534 Query rewriting; Transformation
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 40/237 Lexical tools
• CPC Class Codes: Y10S 707/955 Object-oriented
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 707/99944 Object-oriented database structure
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing

Abstract

A system and method for representing, storing and retrieving real-world knowledge on a computer or network of computers is disclosed. Knowledge is broken down into permanent atomic “facts” which can be stored in a standard relational database and processed very efficiently. It also provides for the efficient querying of a knowledge base, efficient inference of new knowledge and translation into and out of natural language. Queries can also be processed with full natural language explanations of where the answers came from. The method can also be used in a distributed fashion enabling the system to be a large network of computers and the technology can be integrated into a web browser adding to the browser'"'"'s functionality.

Claims

1. A knowledge representation and retrieval system, comprising:

one or more data stores having a knowledge base stored therein comprising structured data representing first knowledge; and

one or more computing devices configured to;

convert a natural language question to an internal query that represents an interpretation of the natural language question and has an internal format compatible with the structured data;

compute one or more responses to the natural language question by processing the internal query with reference to the structured data, wherein the one or more responses include second knowledge derived from the first knowledge, the second knowledge not being stored in the knowledge base prior to receipt of the natural language question; and

generate a definitive natural language answer corresponding to at least one of the one or more responses.

2. The system of claim 1 wherein the one or more computing devices are further configured to generate a detailed presentation for the definitive natural language answer that includes additional information relating to one or more objects represented in the natural language answer.

3. The system of claim 1 wherein the one or more computing devices are further configured to generate one or more query interpretations corresponding to the natural language question, and to transmit representations of the one or more query interpretations for presentation on a user device.

4. The system of claim 1 wherein the one or more computing devices are configured to derive the second knowledge from the first knowledge by inference.

5. The system of claim 1 wherein the structured data represent the first knowledge using a plurality of objects and relationships between pairs of the objects.

6. The system of claim 1 wherein the structured data representing the first knowledge are stored in a relational database.

7. The system of claim 1 wherein the one or more computing devices are further configured to receive the natural language question from a user device in response to translation of spoken input by a voice recognition system operating on the user device.

8. The system of claim 1 wherein the one or more computing devices are configured to implement a web site configured to receive the natural language question using a first web page interface, and to present the definitive natural language answer using a second web page interface.

9. The system of claim 1 wherein the one or more computing devices are further configured to receive the natural language question from a remote client device via a network, and to transmit the definitive natural language answer to the remote client device via the network.

10. A computer-implemented method for providing access to a knowledge base, comprising:

converting a natural language question to an internal query that represents an interpretation of the natural language question and has an internal format compatible with structured data of the knowledge base, the structured data representing first knowledge;

computing one or more responses to the natural language question by processing the internal query with reference to the structured data, wherein the one or more responses include second knowledge derived from the first knowledge, the second knowledge not being stored in the knowledge base prior to receipt of the natural language question; and

generating a definitive natural language answer corresponding to at least one of the one or more responses.

11. The method of claim 10 further comprising generating a detailed presentation for the definitive natural language answer that includes additional information relating to one or more objects represented in the natural language answer.

12. The method of claim 10 further comprising generating one or more query interpretations corresponding to the natural language question, and transmitting representations of the one or more query interpretations for presentation on a user device.

13. The method of claim 10 wherein the second knowledge is derived from the first knowledge by inference.

14. The method of claim 10 wherein the structured data represent the first knowledge using a plurality of objects and relationships between pairs of the objects.

15. The method of claim 10 wherein the structured data representing the first knowledge are stored in a relational database.

16. The method of claim 10 further comprising receiving the natural language question from a user device in response to translation of spoken input by a voice recognition system operating on the user device.

17. The method of claim 10 further comprising implementing a web site configured to receive the natural language question using a first web page interface, and to present the definitive natural language answer using a second web page interface.

18. The method of claim 10 further comprising receiving the natural language question from a remote client device via a network, and transmitting the definitive natural language answer to the remote client device via the network.

19. A computer program product for providing access to a knowledge base, the computer program product comprising computer program instructions stored in one or more non-transitory computer-readable media, the computer program instructions being configured when executed to cause a computing device to:

receive a natural language question as input;

transmit the natural language question to the knowledge base for translation to an internal query that represents an interpretation of the natural language question and has an internal format compatible with structured data of the knowledge base, the structured data representing first knowledge; and

present a definitive natural language answer responsive to the natural language question received from the knowledge base and including second knowledge derived from the first knowledge, the second knowledge not having been stored in the knowledge base prior to transmission of the natural language question to the knowledge base.

20. The computer program product of claim 19 wherein the computer program instructions are further configured when executed to cause the computing device to present a detailed presentation for the definitive natural language answer that includes additional information relating to one or more objects represented in the natural language answer.

21. The computer program product of claim 19 wherein the computer program instructions are further configured when executed to cause the computing device to present representations of one or more query interpretations corresponding to the natural language question.

22. The computer program product of claim 19 wherein the computer program instructions are further configured when executed to cause the computing device to receive the natural language question from a voice recognition system operating on the computing device and configured to translate spoken input to the natural language question.

23. The computer program product of claim 19 wherein the natural language question is received and the definitive natural language answer is presented using first and second web page interfaces, respectively.

24. The computer program product of claim 19 wherein the computer program instructions are further configured when executed to cause the computing device to transmit the natural language question to the knowledge base via a network, and to receive the definitive natural language answer from the knowledge base via the network.

25. A computer-implemented method for providing access to a knowledge base, comprising:

receiving a natural language question as input;

transmitting the natural language question to the knowledge base for translation to an internal query that represents an interpretation of the natural language question and has an internal format compatible with structured data of the knowledge base, the structured data representing first knowledge; and

presenting a definitive natural language answer responsive to the natural language question received from the knowledge base and including second knowledge derived from the first knowledge, the second knowledge not having been stored in the knowledge base prior to transmission of the natural language question to the knowledge base.

26. The method of claim 25 further comprising presenting a detailed presentation for the definitive natural language answer that includes additional information relating to one or more objects represented in the natural language answer.

27. The method claim 25 further comprising presenting representations of one or more query interpretations corresponding to the natural language question.

28. The method of claim 25 further comprising receiving the natural language question from a voice recognition system configured to translate spoken input to the natural language question.

29. The method of claim 25 wherein the natural language question is received and the definitive natural language answer is presented using first and second web page interfaces, respectively.

30. The method of claim 25 further comprising transmitting the natural language question to the knowledge base via a network, and receiving the definitive natural language answer from the knowledge base via the network.