KNOWLEDGE REPOSITORY
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.
1 . A computer-implemented method, comprising:
receiving a natural language question;
determining that the natural language question relates to a first fictional context of a plurality of fictional contexts represented in the knowledge base;
generating a query compatible with structured knowledge of a knowledge base using the natural language question;
generating a result by processing the query with reference to the knowledge base and the first fictional context; and
generating a response to the natural language question using the result.
2 . The method of claim 1 , wherein determining that the natural language question relates to the first fictional context comprises:
determining that the natural language question refers to an object; and
determining that the object is associated with the first fictional context in the knowledge base.
3 . The method of claim 1 , wherein determining that the natural language question relates to the first fictional context comprises identifying a reference to the first fictional context in the natural language question.
4 . The method of claim 1 , wherein the natural language question is received from a user of the knowledge base, and wherein determining that the natural language question relates to the first fictional context comprises determining that the first fictional context is associated with the user in the knowledge base.
5 . The method of claim 4 , further comprising associating the first fictional context with the user in response to input from the user identifying the first fictional context.
6 . The method of claim 1 , wherein the knowledge base includes a plurality of facts, and wherein a first fact of the plurality of the facts includes a label corresponding to the first fictional context.
7 . The method of claim 1 , wherein the knowledge base includes a fact that is valid in the first fictional context and invalid in a second fictional context of the plurality of fictional contexts.
8 . A computing system for responding to natural language input, comprising:
one or more data stores having a knowledge base stored therein comprising structured knowledge; and
one or more computing devices configured to:
receive a natural language question;
determining that the natural language question relates to a first fictional context of a plurality of fictional contexts represented in the knowledge base;
generate a query compatible with the structured knowledge of the knowledge base using the natural language question;
generate a result by processing the query with reference the knowledge base and the first fictional context; and
generate a response to the natural language question using the result.
9 . The computing system of claim 8 , wherein the one or more computing devices are configured to determine that the natural language question relates to the first fictional context by:
determining that the natural language question refers to an object; and
determining that the object is associated with the first fictional context in the knowledge base.
10 . The computing system of claim 8 , wherein the one or more computing devices are configured to determine that the natural language question relates to the first fictional context by identifying a reference to the first fictional context in the natural language question.
11 . The computing system of claim 8 , wherein the natural language question is received from a user of the knowledge base, and wherein the one or more computing devices are configured to determine that the natural language question relates to the first fictional context by determining that the first fictional context is associated with the user in the knowledge base.
12 . The computing system of claim 11 , wherein the one or more computing devices are further configured to associate the first fictional context with the user in response to input from the user identifying the first fictional context.
13 . The computing system of claim 8 , wherein the knowledge base includes a plurality of facts, and wherein a first fact of the plurality of the facts includes a label corresponding to the first fictional context.
14 . The computing system of claim 8 , wherein the knowledge base includes a fact that is valid in the first fictional context and invalid in a second fictional context of the plurality of fictional contexts.
15 . A computer program product for responding to natural language input, comprising one or more non-transitory computer-readable media having computer program instructions stored therein, the computer program instructions being configured such that, when executed, the computer program instructions cause one or more computing devices to:
receive a natural language question;
determine that the natural language question relates to a first fictional context of a plurality of fictional contexts represented in the knowledge base;
generate a query compatible with structured knowledge of a knowledge base using the natural language question;
generate a result by processing the query with reference to the knowledge base and the first fictional context; and
generate a response to the natural language question using the result.
16 . The computer program product of claim 15 , wherein the computer program instructions are configured such that, when executed, the computer program instructions cause the one or more computing devices to determine that the natural language question relates to the first fictional context by:
determining that the natural language question refers to an object; and
determining that the object is associated with the first fictional context in the knowledge base.
17 . The computer program product of claim 15 , wherein the computer program instructions are configured such that, when executed, the computer program instructions cause the one or more computing devices to determine that the natural language question relates to the first fictional context by identifying a reference to the first fictional context in the natural language question.
18 . The computer program product of claim 15 , wherein the natural language question is received from a user of the knowledge base, and wherein the computer program instructions are configured such that, when executed, the computer program instructions cause the one or more computing devices to determine that the natural language question relates to the first fictional context by determining that the first fictional context is associated with the user in the knowledge base.
19 . The computer program product of claim 18 , wherein the computer program instructions are further configured such that, when executed, the computer program instructions cause the one or more computing devices to associate the first fictional context with the user in response to input from the user identifying the first fictional context.
20 . The computer program product of claim 15 , wherein the knowledge base includes a plurality of facts, and wherein a first fact of the plurality of the facts includes a label corresponding to the first fictional context.
21 . The computer program product of claim 15 , wherein the knowledge base includes a fact that is valid in the first fictional context and invalid in a second fictional context of the plurality of fictional contexts.