Problem manipulators for language-independent computerized reasoning

1. An artificial intelligent agent comprising:

a processor;

a problem solving and reasoning engine configured to perform acts comprising:

receiving a query from a user;

decomposing the query into two or more sub-queries arranged according to a tree structure;

determining an answer to at least one of the two or more sub-queries in a knowledge base;

further decomposing one of the two or more sub-queries when the results of one of the two or more sub-queries return with no answer;

repeating the further decomposing of one of the two or more sub-queries until an answer is found in the knowledge base;

receiving results of the sub-queries;

assembling the results of the sub-queries into a query response; and

transmitting the query response to the user.

2. The artificial intelligent agent of claim 1 , wherein the query received from the user is in an input language selected from at least one of a natural language query, logic or formal syntax and visual language.

3. The artificial intelligent agent of claim 2 , wherein the problem solving and reasoning engine is further configured to perform an act comprising:

receiving a corpus of natural language into a memory of the artificial intelligent agent; and

encoding the natural language query into a digitized query for the act of decomposing the query into two or more sub-queries.

4. The artificial intelligent agent of claim 2 , wherein the query response is transmitted to the user as a natural language response.

5. The artificial intelligent agent of claim 1 , wherein the act of decomposing the query into two or more sub-queries is independent of a language of the query from the user.

6. The artificial intelligent agent of claim 1 , wherein the tree structure is arranged as a disjunction of conjunctions of sub-queries.

7. The artificial intelligent agent of claim 1 , wherein the problem solving and reasoning engine is further configured to perform an act comprising applying forward reasoning and backward reasoning to create the tree structure.

8. The artificial intelligent agent of claim 1 , wherein the problem solving and reasoning engine is further configured to perform an act comprising learning a rule based on at least a portion of the tree structure.

9. A computer implemented method comprising:

receiving a query from a user;

decomposing the query into two or more sub-queries arranged according to a tree structure;

executing an answer to at least one of the two or more sub-queries in a knowledge base;

receiving results of the two or more sub-queries;

further decomposing one of the two or more sub-queries when the results of the two or more sub-queries return with no answer;

repeating the further decomposing one of the two or more sub-queries until an answer is found in the knowledge base;

assembling the results of the sub-queries into a query response; and

transmitting the query response to the user, wherein the decomposing the query into the sub-queries, executing the sub-queries in the knowledge base, receiving results of the executed sub-queries, and composing the results of the executed one or more sub-queries are independent of a language of the query from the user.

10. The method of claim 9 , wherein the query received from the user is in an input language selected from at least one of a natural language query, logic or formal syntax and visual language.

11. The method of claim 9 , further comprising

receiving a corpus of natural language into a memory; and

encoding the natural language query into a digitized query for the act of decomposing the query into two or more sub-queries.

12. The method of claim 11 , further comprising further decomposing a second of the two or more sub-queries when the results of the executed one of the two or more sub-queries returns with no answer.

13. The method of claim 9 , further comprising applying forward reasoning and backward reasoning to create the tree structure.

14. The method of claim 9 , further comprising learning a rule based on at least a portion of the tree structure.

15. A non-transitory computer readable storage medium tangibly embodying a computer readable program code having computer readable instructions that, when executed, causes a computer device to carry out a method of improving computing efficiency of a computing device for problem solving and reasoning, the method comprising:

receiving a query from a user;

decomposing the query into two or more sub-queries arranged according to a tree structure;

determining an answer to at least one of the two or more sub-queries in a knowledge base;

receiving results of the two or more sub-queries;

further decomposing one of the two or more sub-queries when the results of the executed one of the two or more sub-queries returns with no answer;

repeating the further decomposing of one of the two or more sub-queries until an answer is found in the knowledge base;

assembling the results of the two or more sub-queries into a query response; and

transmitting the query response to the user, wherein decomposing the query into one or more sub-queries, executing the one or more sub-queries in the knowledge base, receiving results of the executed one or more sub-queries and composing the results of the executed one or more sub-queries are independent of a language of the query from the user.

16. The non-transitory computer readable storage medium of claim 15 , wherein the execution of the code by the processor further configures the computing device to perform an act comprising applying forward reasoning and backward reasoning to create the tree structure.

17. The non-transitory computer readable storage medium of claim 15 , wherein the execution of the code by the processor further configures the computing device to perform an act comprising learning a rule based on at least a portion of the tree structure.