Computer implemented method for the automated analysis or use of data
There is provided a computer implemented method for the automated analysis or use of data, comprising the steps of: (a) storing in a non-transitory computer-readable medium a structured, machine-readable representation of data that conforms to a machine-readable language; in which the structured, machine-readable representation of data includes a plurality of tenets defining rules, the plurality of tenets including at least one constraint tenet, the at least one constraint tenet preventing a bad action; wherein the plurality of tenets comprise different sets of tenets; (b) using the different sets of tenets in different contexts, e.g. for different types of chatbots, or for different end-users.
1. A computer implemented method for the automated analysis or use of data, comprising the steps of:
(a) storing in a non-transitory computer-readable medium a structured, machine-readable representation of data that conforms to a machine-readable language; in which the structured, machine-readable representation of data includes a plurality of tenets defining rules, the plurality of tenets including at least one constraint tenet, the at least one constraint tenet preventing a bad action; wherein the plurality of tenets comprise different sets of tenets;
(b) using the different sets of tenets in different contexts, e.g. for different types of chatbots, or for different end-users.
2. The method of claim 1 , including using the different sets of tenets for different types of chatbots.
3. The method of claim 2 , the method enabling more extensive and faster scaling of the chatbots' capabilities.
4. The method of claim 2 , wherein a question is received by a chatbot of the chatbots, wherein semantic nodes include representations of user speech input to a human/machine interface and include representations of the human/machine interface itself.
5. The method of claim 1 , including using the different sets of tenets for different end-users.
6. The method of claim 1 , including checking that actions conform to the tenets prior to doing the actions.
7. The method of claim 1 , including using the tenets to help select or generate an action.
8. The method of claim 1 , including responding differently to different personalities.
9. The method of claim 1 , including responding differently to different language styles.
10. The method of claim 1 , including providing a useful vertical application where the useful vertical application requires data which is heterogeneous and extremely broad in scope, the data comprising at least one data store containing a machine-readable representation of the data that encodes meaning.
11. The method of claim 1 , including generating a reasoned, natural language explanation that a potential action does comply or does not comply with the at least one constraint tenet.
12. The method of claim 1 in which the structured, machine-readable representation of data that conforms to the machine-readable language comprises semantic nodes and passages; and in which a semantic node represents an entity and is itself represented by an identifier; and a passage is either (i) a semantic node or (ii) a combination of semantic nodes; and where machine-readable meaning comes from choice of semantic nodes and a way they are combined and ordered as passages.
13. The method of claim 1 , including not changing the tenets.
14. The method of claim 13 in which not changing the tenets comprises the tenets including a tenet prohibiting actions which might result in changes to the tenets.
15. The method of claim 1 , including independently checking each potential action against the tenets and discarding a potential action if the independent check finds that the potential action is incompatible with the tenets.
16. The method of claim 15 in which a potential action includes changing a state of a device linked to a computer system via a network.
17. The method of claim 15 in which a potential action includes initiating a spoken interaction with a human being.
18. The method of claim 1 , including learning from one or more of: (i) communication with at least one user and (ii) one external sensor connected to a computer system via a network.
19. The method of claim 1 in which the tenets are at least partially represented by combinations of identifiers and where at least some of the identifiers represent concepts corresponding to real-world things.
20. The method of claim 1 in which the non-transitory computer-readable medium comprises a long-term non-transitory computer-readable medium; and in which a computer system comprises a short-term memory; the long-term non-transitory computer-readable medium including a tenet-store containing machine-readable tenets representing rules to guide the computer system and in which the computer system receives events and utilises the events, the contents of the long-term non-transitory computer-readable medium, the contents of the short-term memory and the tenets to do actions that conform with the tenets.
21. The method of claim 20 in which the events include communication from at least one user and where the actions include communication to at least one user.
22. The method of claim 20 in which the computer system learns, and stores what it has learned to the long-term non-transitory computer-readable medium.
23. The method of claim 1 in which the method is carried out by a computer system comprising a component which generates candidate actions; a component that decides whether to execute the candidate actions with reference to the tenets and a component which executes actions.
24. The method of claim 1 in which the method is carried out by a computer system which actively excludes knowledge on itself from being used in determining actions.
25. The method of claim 1 in which the method is carried out by a computer system such that potential actions are autonomously generated by the computer system.
26. The method of claim 1 in which potential actions are autonomously generated by a computer system according to one or more of the following: as outputs from processing inputs, such as audio or text; as a process that operates substantially continuously; as outputs without any external trigger event to initiate processing or user instruction or action to initiate processing.
27. The method of claim 25 in which the potential actions are automatically executed if they optimize or otherwise positively affect achievement or realization of the tenets.
28. The method of claim 1 in which reasoning with reference to the machine-readable representation produces further, new machine-readable representations.
29. The method of claim 1 in which generating responses to queries comprises three operations, namely matching with machine-readable representations, such as passages, in a store, fetching and execution of computation units and fetching reasoning passages.
30. The method of claim 1 in which a question is represented in a memory as a machine representation, and the representation of the question, the machine representations previously stored in the non-transitory memory computer-readable medium, computation units and reasoning passages are all represented in substantially the same machine readable language.