US2013275121A1PendingUtilityA1

Knowledge repository

53
Assignee: EVI TECHNOLOGIES LTDPriority: Aug 1, 2005Filed: May 16, 2013Published: Oct 17, 2013
Est. expiryAug 1, 2025(expired)· nominal 20-yr term from priority
G06F 40/279G06F 16/3329G06F 16/532G06N 5/00G06F 40/40G06F 17/28
53
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

A knowledge storage system is described. A specific embodiment is a computer system comprising a knowledge base of general knowledge in structured form which can be added to and queried by untrained users. Various embodiments include the facility for remote computers to access the knowledge stored in the system, natural language questions to be answered, profile screens giving general knowledge about an object in the system, and methods for distinguishing between reliable and unreliable facts.

Claims

exact text as granted — not AI-modified
What is claimed is: 
     
         1 . A computer-implemented method, comprising:
 receiving a natural language question, wherein the natural language question was entered as input on a client device;   generating a query for use with a knowledge base using the natural language question;   generating a natural language answer to the natural language question by processing the query with reference to the knowledge base;   obtaining search results by providing one or more keywords derived from the natural language question to a search engine; and   transmitting the natural language answer and the search results for presentation on the client device.   
     
     
         2 . The method of  claim 1 , further comprising deriving the one or more keywords from the natural language question by identifying one or more objects represented in the natural language question that are also represented in the knowledge base. 
     
     
         3 . The method of  claim 1 , wherein the one or more keywords derived from the natural language question comprise the natural language question. 
     
     
         4 . The method of  claim 1 , wherein the one or more keywords derived from the natural language question comprise at least one word included in the natural language question. 
     
     
         5 . The method of  claim 1 , wherein the transmitting of the search results only occurs after the natural language answer has been presented on the client device and a request for the search results has been received from the client device. 
     
     
         6 . The method of  claim 1 , further comprising:
 identifying an object represented by the natural language question and represented in the knowledge base;   generating profile information describing the object from the knowledge base; and   transmitting the profile information to the client device for presentation on the client device.   
     
     
         7 . A computing system for responding to natural language input, comprising:
 one or more data stores having a knowledge base stored therein; and   one or more computing devices configured to:
 receive a natural language question, wherein the natural language question was entered as input on a client device; 
 generate a query for use with a knowledge base using the natural language question; 
 generate a natural language answer by processing the query with reference to the knowledge base; 
 obtain search results by providing one or more keywords derived from the natural language question to a search engine; and 
 transmit the natural language answer and the search results for presentation on the client device. 
   
     
     
         8 . The computing system of  claim 7 , wherein the one or more computing devices are further configured to derive the one or more keywords from the natural language question by identifying one or more objects represented in the natural language question that are also represented in the knowledge base. 
     
     
         9 . The computing system of  claim 7 , wherein the one or more computing devices are further configured to derive the one or more keywords from the natural language question by providing the natural language question to the search engine. 
     
     
         10 . The computing system of  claim 7 , wherein the one or more computing devices are further configured to derive the one or more keywords from the natural language question by removing one or more words included in the natural language question. 
     
     
         11 . The computing system of  claim 7 , wherein the one or more computing devices are further configured to transmit the search results only after the natural language answer has been presented on the client device and a request for the search results has been received from the client device. 
     
     
         12 . The computing system of  claim 7 , wherein the one or more computing devices are further configured to:
 identify an object represented by the natural language question and represented in the knowledge base;   generate profile information describing the object from the knowledge base; and   transmit the profile information to the client device for presentation on the client device.   
     
     
         13 . A computer-implemented method, comprising:
 receiving a natural language question entered as input on a client device;   generating a query for use with a knowledge base using the natural language question;   attempting to respond to the natural language question by processing the query with reference to the knowledge base;   where processing the query fails to generate a response, obtaining search results by providing one or more keywords derived from the natural language question to a search engine; and   transmitting the search results for presentation on the client device.   
     
     
         14 . The method of  claim 13 , further comprising deriving the one or more keywords from the natural language question by identifying one or more objects represented in the natural language question that are also represented in the knowledge base. 
     
     
         15 . The method of  claim 13 , further comprising deriving the one or more keywords from the natural language question by providing the natural language question to the search engine. 
     
     
         16 . The method of  claim 13 , further comprising deriving the one or more keywords from the natural language question by removing one or more words included in the natural language question. 
     
     
         17 . The method of  claim 13 , further comprising:
 identifying an object represented by the natural language question and represented in the knowledge base;   generating profile information describing the object from the knowledge base; and   transmitting the profile information for presentation on the client device.   
     
     
         18 . A computing system for responding to natural language input, comprising:
 one or more data stores having a knowledge base stored therein; and   one or more computing devices configured to:
 receive a natural language question entered as input on a client device; 
 generate a query for use with the knowledge base using the natural language question; 
 attempt to respond to the natural language question by processing the query with reference to the knowledge base; 
 where processing the query fails to generate a response, obtain search results by providing one or more keywords derived from the natural language question to a search engine; and 
 transmit the search results for presentation on the client device. 
   
     
     
         19 . The computing system of  claim 18 , wherein the one or more computing devices are further configured to derive the one or more keywords from the natural language question by identifying one or more objects represented in the natural language question that are also represented in the knowledge base. 
     
     
         20 . The computing system of  claim 18 , wherein the one or more computing devices are further configured to derive the one or more keywords from the natural language question by providing the natural language question to the search engine. 
     
     
         21 . The computing system of  claim 18 , wherein the one or more computing devices are further configured to derive the one or more keywords from the natural language question by removing one or more words included in the natural language question. 
     
     
         22 . The computing system of  claim 18 , wherein the one or more computing devices are further configured to:
 identify an object represented by the natural language question and represented in the knowledge base;   generate profile information describing the object from the knowledge base; and   transmit the profile information for presentation on the client device.

Cited by (0)

No later patents cite this yet.

References (0)

No backward citations on record.