Computerized assistance using artificial intelligence knowledge base

1. One or more hardware storage machines comprising computer executable instructions embodied thereon, that when executed by a computing device, cause the computing device to perform actions comprising:

receiving a user input through a natural language user interface;

outputting a computer-readable representation of the user input;

associating the user input with a particular user;

updating a user-centric artificial intelligence knowledge base associated with the particular user to include a new or updated user-centric fact based on the computer-readable representation of the user input, wherein the user-centric artificial intelligence knowledge base is updated via an update protocol useable by a plurality of different computer services, the update protocol constraining a storage format of the new or updated user-centric fact to an application-agnostic data format,

wherein the application-agnostic data format is associated with a node record format that supports a facet pointer to auxiliary application-specific data associated with application-specific facts of application-specific contexts where users interact with the plurality of different computer services.

2. The one or more hardware storage machines of claim 1 , the method further comprising outputting an enrichment based on the computer-readable representation of the user input, and wherein the new or updated user-centric fact includes the enrichment.

3. The one or more hardware storage machines of claim 1 , wherein the user-centric artificial intelligence knowledge base includes one or more encrypted user-centric facts, wherein access to the one or more encrypted user-centric facts is constrained by a credential associated with the particular user.

4. The one or more hardware storage machines of claim 1 , the method further comprising querying the user-centric artificial intelligence knowledge base associated with the particular user; and

outputting a response based on a subset of user-centric facts in the user-centric artificial intelligence knowledge base satisfying one or more constraints defined by a computer-readable representation of a query.

5. The one or more hardware storage machines 4 , wherein the user-centric artificial intelligence knowledge base is queried via a query protocol useable by a plurality of different computer services.

6. The one or more hardware storage machines of claim 4 , wherein the method further comprises:

receiving a user query through the natural language user interface; and

outputting the computer-readable representation of the query based on the user query.

7. The one or more hardware storage machines claim 6 , wherein the method further comprises outputting a recognized user intent based on the user query, and wherein the one or more constraints defined by the computer-readable representation of the query include a constraint based on the recognized user intent.

8. The one or more hardware storage machines of claim 4 , wherein the query is a user context query to determine a current context of the user, and wherein the subset of user-centric facts includes one or more user-centric facts relating to the current context.

9. The one or more hardware storage machines of claim 4 , wherein:

the one or more constraints defined by the computer-readable representation of the query include an answer type constraint; and

the subset of user-centric facts includes only user-centric facts that satisfy the answer type constraint.

10. The one or more hardware storage machines of claim 4 , wherein:

the one or more constraints defined by the computer-readable representation of the query include a graph context constraint; and

the subset of user-centric facts includes only user-centric facts that are related to a contextualizing user-centric fact in the user-centric artificial intelligence knowledge base that satisfies the graph context constraint.

11. The one or more hardware storage machines of claim 4 , wherein the response includes computer-readable instructions configured to cause a cooperating computer service to perform an action to assist the user based on the subset of user-centric facts in the user-centric artificial intelligence knowledge base satisfying the one or more constraints defined by the computer-readable representation of the query.

12. The one or more hardware storage machines of claim 11 , wherein the action to assist the user includes changing a preference setting of the cooperating computer service based on the subset of user-centric facts in the user-centric artificial intelligence knowledge base satisfying the one or more constraints defined by the computer-readable representation of the query.

13. The one or more hardware storage machines of claim 11 , wherein the action to assist the user includes visually presenting a depiction of state data of the cooperating computer service, the state data related to the subset of user-centric facts in the user-centric artificial intelligence knowledge base satisfying the one or more constraints defined by the computer-readable representation of the query.

14. One or more hardware storage machines comprising computer executable instructions embodied thereon, that when executed by a computing device, cause the computing device to perform actions comprising:

receiving a user query through a natural language user interface;

associating the user query with a particular user;

outputting a computer-readable representation of the user query;

querying a user-centric artificial intelligence knowledge base associated with the particular user; and

outputting a response to the user query based on a subset of user-centric facts in the user-centric artificial intelligence knowledge base satisfying one or more constraints defined by the computer-readable representation of the user query, wherein the user-centric artificial intelligence knowledge base is updateable to include a new or updated user-centric fact via an update protocol useable by a plurality of different computer services, the update protocol constraining a storage format of the new or updated user-centric fact to an application-agnostic data format,

wherein the application-agnostic data format is associated with a node record format that supports a facet pointer to auxiliary application-specific data associated with application-specific facts of application-specific contexts where users interact with the plurality of different computer services.

15. A method for automatically responding to queries, comprising:

recognizing a computer-readable representation of a query associated with a particular user of a computer service;

querying a user-centric artificial intelligence knowledge base associated with the particular user via a query protocol useable by a plurality of different computer services; and

outputting a response based on a subset of user-centric facts in the user-centric artificial intelligence knowledge base satisfying one or more constraints defined by the computer-readable representation of the query, wherein the user-centric artificial intelligence knowledge base is updateable to include a new or updated user-centric fact via an update protocol useable by a plurality of different computer services, the update protocol constraining a storage format of the new or updated user-centric fact to an application-agnostic data format,

wherein the application-agnostic data format is associated with a node record format that supports a facet pointer to auxiliary application-specific data associated with application-specific facts of application-specific contexts where users interact with the plurality of different computer services.

16. The method of claim 15 , wherein a facet pointer supports multiple file types for storing different kinds of auxiliary application-specific data associated with auxiliary application-specific facts of application-specific contexts.

17. The method of claim 15 , wherein the query is a user context query to determine a current context of the user, and wherein the subset of user-centric facts includes one or more user-centric facts relating to the current context.

18. The method of claim 17 , wherein the query indicates a state of the computer service and wherein the one or more user-centric facts relating to the current context include a user-centric fact relating to the state of the computer service.

19. The method of claim 18 , further comprising recognizing a computer-readable representation of a natural language feature defined by the state of the computer service, and wherein the one or more constraints include a constraint based on the natural language feature.

20. The method of claim 15 , further comprising causing the computer service to perform an action to assist the user based on the subset of user-centric facts in the user-centric artificial intelligence knowledge base satisfying the one or more constraints defined by the computer-readable representation of the query.