Computer implemented method for the automated analysis or use of data
A computer implemented method comprise the steps of storing or accessing in a non-transitory storage medium a structured, machine-readable representation of data that conforms to a machine-readable language. The representation of data includes data relating to financial or accounting information. The structured representation of data that conforms to the language comprises semantic nodes and passages. Each node represents an entity and is represented by an identifier. Each passage is a node or a combination of nodes. At least some passages include combinations of nodes. Machine-readable meaning comes from choice of nodes and a way they are combined and ordered as passages. Nodes include executable computation units and the passages include executable reasoning passages which are structured representations of data that represent semantics of reasoning steps. The steps include automatically processing the structured representations to analyse the financial or accounting information and explain the analysis to a human user.
1. A computer implemented method for the automated analysis or use of data, comprising the steps of:
(a) storing or accessing in a non-transitory storage medium a structured, machine-readable representation of data that conforms to a machine-readable language; in which the machine-readable representation of data includes data relating to financial or accounting information, in which the structured, machine-readable representation of data that conforms to the machine-readable language comprises semantic nodes and passages; and in which each semantic node represents an entity and is itself represented by an identifier; and each passage is either (i) a semantic node or (ii) a combination of semantic nodes; in which at least some passages include combinations of semantic nodes; and where machine-readable meaning comes from choice of semantic nodes and a way they are combined and ordered as passages, wherein the semantic nodes include executable computation units, and wherein the passages include executable reasoning passages which are structured, machine-readable representations of data that represent semantics of reasoning steps and which are usable to explain how a conclusion has been reached;
(b) automatically processing the structured representations to analyse the financial or accounting information, and to use the executable reasoning passages which are usable to explain how a conclusion has been reached, to explain the analysis of the financial or accounting information to a human user.
2. The method of claim 1 in which the financial or accounting data for at least one business is processed, and at least some of the financial or accounting data is represented in a structured machine-readable format that encodes real-world meaning stored within one or more data stores.
3. The method of claim 2 in which the structured machine-readable format is comprised of combinations of identifiers where at least some of the identifiers represent real-world entities relevant to activities of the at least one business and where further meaning is encoded from choice of combinations of the identifiers.
4. The method of claim 3 in which answer to questions about the activities of the at least one business are automatically generated.
5. The method of claim 1 in which the structured representation of data further includes a representation of a spoken, written or GUI instruction provided by a human to a human/machine interface.
6. The method of claim 1 in which financial or accounting information is automatically translated into the machine readable language by a machine learning system that generates semantic nodes or passages that represent mapping data or location-based data.
7. The method of claim 1 including the step of automatically translating financial or accounting information expressed in a natural language into the machine-readable language, and in which structure of a sequence of words is compared with known machine-readable language structures in the non-transitory storage medium to identify similarities.
8. The method of claim 1 including the step of automatically translating the financial or accounting information into the machine-readable language by referencing a store of previously identified correct translations between a natural language and the machine-readable language.
9. The method of claim 1 including the step of automatically translating the financial or accounting information into the machine-readable language by utilising a pipeline of functions which transform a sequence of words into a series of intermediate forms.
10. The method of claim 6 in which the machine learning system is a neural network system.
11. The method of claim 6 in which the machine learning system has been trained on training data comprising natural language and a corresponding structured machine-readable representation.
12. The method of claim 1 in which the machine-readable language uses a single syntactical item to disambiguate the meaning of structured representations of data.
13. The method of claim 1 in which the machine-readable language uses a shared syntax across factual statements, queries and reasoning.
14. The method of claim 1 in which the machine-readable language uses nesting of nodes and passages, as an unambiguous syntax.
15. The method of claim 1 in which the machine-readable language comprises a plurality of identifiers or IDs which are selected from an address space that enables users to select a new identifier with no risk of selecting a previously allocated identifier.
16. The method of claim 1 in which the machine-readable language is scalable since there are no restrictions on which users can create a structured, machine-readable representation of data or related identifier.
17. The method of claim 1 in which the machine-readable language (i) uses a single syntactical item to disambiguate meaning of structured representations of data; and (ii) uses a syntax that is a single shared syntax that applies to passages that represent factual statements, query statements and reasoning statements; and (iii) uses a syntax that is an unambiguous syntax comprising nesting of structured representations of data; and (iv) uses an identifier selected from an address space that enables users to select a new identifier with no risk of selecting a previously allocated identifier; and (v) is scalable since there are no restrictions on which users can create a structured representations of data or related identifier.
18. The method of claim 1 which includes the step of (a) the machine-readable language representing a question in a memory as a structured, machine-readable representation of data; and the method further includes the step of (b) automatically generating a response to the question, using all of the following steps: (i) matching the question with structured, machine-readable representations of data previously stored in a memory store; (ii) fetching and executing one or more computation units, where computation units represent computational capabilities relevant to answering the question; (iii) fetching and execution of one or more reasoning passages; and in which the representation of the question, the structured, machine-readable representations of data previously stored in the memory store, the computation units and the reasoning passages are all represented in the same machine-readable language.
19. The method of claim 1 which includes the step of learning new information and representing the new information in the structured, machine-readable representation of data that conforms to the machine-readable language.
20. The method of claim 1 which includes the step of (i) receiving a sequence of words in a natural language; and (ii) automatically translating that sequence of words into the machine-readable language by identifying or generating structured machine-readable representations that semantically represent meaning of the sequence of words in the machine-readable language.
21. The method of claim 1 which includes the step of providing a service operable to receive a description of an entity and return one or more identifiers for structured, machine-readable representations of data corresponding to the entity, so that a user is able to use a shared identifier for the entity.
22. The method of claim 1 in which the method enables translating between a first natural language and a second natural language, by: (a) receiving a sequence of words in the first natural language to be translated into the second natural language; (b) automatically translating that sequence of words expressed in the first natural language into the second natural language by (i) identifying a structured, machine-readable representation of data that represents semantics of the sequence of words in the first natural language and (ii) retrieving a sequence of words in the second natural language that corresponds in meaning to the identified structured, machine-readable representation of data.
23. The method of claim 1 which includes the step of automatically and autonomously processing detected audio or text into the structured representation of data whenever audio or text is detected or received.
24. The method of claim 1 which enables automatically selecting, deciding on or executing actions, and in which the structured representation of data includes one or more tenets, statements or other rules defining objectives or motives, also represented using the structured representation of data; and the method further includes the steps of (i) analysing a potential action to determine whether executing the action would optimize or otherwise affect achievement or realization of those tenets, statements or other rules; (ii) automatically selecting, deciding on or executing actions only if they optimize or otherwise positively affect achievement or realization of those tenets, statements or other rules.
25. The method of claim 1 in which representations of financial or accounting information have been automatically translated into the machine readable language.
26. A computer-based system configured to analyse data, the system being configured to:
(a) store or access in a non-transitory storage medium a structured, machine-readable representation of data that conforms to a machine-readable language; in which the machine-readable representation of data includes data relating to financial or accounting information, in which the structured, machine-readable representation of data that conforms to the machine-readable language comprises semantic nodes and passages; and in which each semantic node represents an entity and is itself represented by an identifier; and each passage is either (i) a semantic node or (ii) a combination of semantic nodes; in which at least some passages include combinations of semantic nodes; and where machine-readable meaning comes from choice of semantic nodes and a way they are combined and ordered as passages, wherein the semantic nodes include executable computation units, and wherein the passages include executable reasoning passages which are structured, machine-readable representations of data that represent semantics of reasoning steps and which are usable to explain how a conclusion has been reached; and;
(b) automatically process the structured representations to analyse the financial or accounting information, and to use the executable reasoning passages which are usable to explain how a conclusion has been reached, to explain the analysis of the financial or accounting information to a human user.
27. The method of claim 10 in which the neural network system is a deep learning system.
28. The method of claim 11 in which the training data comprising natural language and a corresponding structured machine-readable representation is a machine-readable language comprising semantic nodes and passages.
29. The method of claim 15 in which the address space is Universal Unique Identifier (UUID) or Unicode.
30. The method of claim 1 , including the step of learning using natural language, including translating all or parts of document sources of natural language into semantic nodes or passages.
31. The method of claim 1 , wherein the explanation of the analysis of the financial or accounting information to a human user is performed using text.
32. The method of claim 1 , wherein the explanation of the analysis of the financial or accounting information to a human user is performed using speech.