Reasoning engine services
A reasoning engine is disclosed. Contemplated reasoning engines acquire data relating to one or more aspects of various environments. Inference engines within the reasoning engines review the acquire data, historical or current, to generate one or more hypotheses about how the aspects of the environments might be correlated, if at all. The reasoning engine can attempt to validate the hypotheses through controlling acquisition of the environment data.
1. A computer-based multi-layered reasoning engine system comprising:
at least one non-transitory computer-readable memory storing software instructions relating to multiple layers of inference engines; and
at least one processor coupled with the at least one non-transitory computer-readable memory and that performs, upon execution of the software instructions, the operations of:
receiving an inquiry related to at least one aspect of an environment;
selecting, from the at least one non-transitory computer-readable memory, at least one reasoning rule set as a function of environmental data that are associated with the at least one aspect of the environment, wherein the at least one reasoning rule set is selected based on mapping the environmental data to extrapolation paths comprising pointers to types of reasoning;
generating, via a first inference engine in a first layer of a reasoning engine, at least one first hypothesis relating to the inquiry and the at least one aspect of the environment, the at least one first hypothesis being generated according to the selected at least one reasoning rule set;
sending the at least one first hypothesis to a second inference engine in a second layer of the reasoning engine;
generating, via the second inference engine in the second layer of the reasoning engine, at least one second hypothesis relating to the at least one first hypothesis and the at least one aspect of the environment; and
presenting to a user, via a user interface, a response relating to the inquiry and the at least one aspect of the environment derived in part from the at least one second hypothesis.
2. The system of claim 1 , wherein the first inference engine or the second inference engine comprises a computer-based agent.
3. The system of claim 1 , wherein the inquiry comprises at least one of the following types of digital data: text data, image data, video data, and sensor data.
4. The system of claim 1 , wherein the second inference engine comprises at least one validation module.
5. The system of claim 4 , wherein the at least one second hypothesis comprises a validity score.
6. The system of claim 5 , wherein the validity score comprises a single value score.
7. The system of claim 5 , wherein the validity score comprises a multi-valued score.
8. The system of claim 1 , wherein the operations further include generating a validation plan that validates the at least one first hypothesis.
9. The system of claim 1 , wherein the operations further include injecting data back into the environment via at least one data interface.
10. The system of claim 9 , wherein the at least one second hypothesis is derived at least in part based on observed changes to the environment from the injected data.
11. The system of claim 1 , wherein the system further comprises a cloud-based server operating as at least one of the first inference engine or the second inference engine.
12. The system of claim 1 , wherein the at least one of the first hypothesis or second hypothesis comprises an assertion.
13. The system of claim 1 , wherein the first inference engine or the second inference engine comprises a personalized inference engine.
14. The system of claim 1 , wherein the first inference engine or the second inference engine comprises at least one reasoning rule sets.
15. The system of claim 14 , wherein the reasoning rules sets include at least one of the following types of reasoning rules: forward chaining rules, backward chaining rules, abductive reasoning rules, deductive resulting rules, indicative reasoning rules, and fuzzy logic rules.
16. The system of claim 14 , wherein the operations further include presenting reasoning step taken to generate the at least one first hypothesis or second hypothesis.
17. The system of claim 1 , wherein the at least one first hypothesis or second hypothesis comprises a suspected correlation between the at least one aspect of the environment and another aspect of the environment.
18. The system of claim 1 , wherein the inquiry is associated with a game.
19. The system of claim 1 , wherein the inquiry comprises a medical inquiry.
20. The system of claim 1 , wherein the inquiry relates to education.
21. A non-transitory computer-readable memory (CRM) storing software instructions relating to multiple layers of inference engines that, when executed by at least one processor, cause the at least one processor to:
receive an inquiry related to at least one aspect of an environment;
select at least one reasoning rule set as a function of environmental data that are associated with the at least one aspect of the environment, wherein the at least one reasoning rule set is selected based on mapping the environmental data to extrapolation paths comprising pointers to types of reasoning;
generate, via a first inference engine in a first layer of a reasoning engine, at least one first hypothesis relating to the inquiry and the at least one aspect of the environment, the at least one first hypothesis being generated according to the selected at least one reasoning rule set;
send the at least one first hypothesis to a second inference engine in a second layer of the reasoning engine;
generate, via the second inference engine in the second layer of the reasoning engine, at least one second hypothesis relating to the at least one first hypothesis and the at least one aspect of the environment; and
present to a user, via a user interface, a response relating to the inquiry and the at least one aspect of the environment derived in part from the at least one second hypothesis.
22. A method comprising:
receiving an inquiry related to at least one aspect of an environment;
selecting at least one reasoning rule set as a function of environmental data that are associated with the at least one aspect of the environment, wherein the at least one reasoning rule set is selected based on mapping the environmental data to extrapolation paths comprising pointers to types of reasoning;
generating, via a first inference engine in a first layer of a reasoning engine, at least one first hypothesis relating to the inquiry and the at least one aspect of the environment;
sending the at least one first hypothesis to a second inference engine in a second layer of the reasoning engine;
generating, via the second inference engine in the second layer of the reasoning engine, at least one second hypothesis relating to the at least one first hypothesis and the at least one aspect of the environment, the at least one first hypothesis being generated according to the selected at least one reasoning rule set; and
presenting to a user, via a user interface, a response relating to the inquiry and the at least one aspect of the environment derived in part from the at least one second hypothesis.