# US 12,217,009 B2 · Computer implemented method for the automated analysis or use of data > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,217,009 B2 - Document ID: US12217009B2 - Status: Granted - Kind: B2 - Application number: 18/088,580 - Filed: 2022-12-25 - Published: 2023-04-27 - Granted: 2025-02-04 - Earliest claimed: 2020-08-24 - Assignees: Unlikely Artificial Intelligence Limited - Applicants: Unlikely Artificial Intelligence Limited - Inventors: William Tunstall-Pedoe; Finlay Curran; Harry Roscoe; Robert Heywood - Web page: https://patentgrep.com/patent/US12217009B2 ## CPC - G06F 40/35: Discourse or dialogue representation - G06F 16/243: {Natural language query formulation} - G06F 16/322: {Trees} - G06F 16/3329: Natural language query formulation - G06F 16/36: Creation of semantic tools, e.g. ontology or thesauri - G06F 16/951: Indexing; Web crawling techniques - G06F 40/123: Storage facilities - G06F 40/126: Character encoding - G06F 40/20: Natural language analysis (semantic analysis of natural language G06F40/30) - G06F 40/205: Parsing - G06F 40/211: Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars - G06F 40/226: Validation - G06F 40/242: Dictionaries - G06F 40/279: Recognition of textual entities - G06F 40/30: Semantic analysis - G06F 40/45: Example-based machine translation; Alignment - G06F 40/47: Machine-assisted translation, e.g. using translation memory - G06F 40/58: Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06N 3/0499: Feedforward networks - G06N 3/08: Learning methods - G06N 5/02: Knowledge representation; Symbolic representation - G06Q 10/1053: Employment or hiring - G06Q 30/0255: {based on user history} - G06Q 30/0257: {User requested} - G06Q 30/0631: {Recommending goods or services} - G10L 15/16: using artificial neural networks - G10L 15/1815: {Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning} - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - G10L 25/63: for estimating an emotional state - G16H 10/60: for patient-specific data, e.g. for electronic patient records - H04L 51/02: using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages - G06N 3/091: Active learning - G10L 2015/088: {Word spotting} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract There is provided a computer implemented method for translating between a first natural language and a second natural language, 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; (b) receiving a word or sequence of words in the first natural language to be translated into the second natural language; (c) automatically translating that word or sequence of words expressed in the first natural language into the second natural language by first translating that word or sequence of words expressed in the first natural language into the machine readable language, and then translating from the machine readable language into the second natural language. ## Claims ### Claim 1 A computer implemented method for translating between a first natural language and a second natural language, 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; (b) receiving a word or sequence of words in the first natural language to be translated into the second natural language; (c) automatically translating that word or sequence of words expressed in the first natural language into the second natural language by first translating that word or sequence of words expressed in the first natural language into the machine readable language, and then translating from the machine readable language into the second natural language, wherein the machine readable language is one in which: (I) syntax for the machine-readable language is a substantially unambiguous syntax comprising nesting of structured representations of data; (II) each structured representation of data includes an identifier selected from an address space that is sufficiently large to select a new identifier with negligible risk of selecting a previously allocated identifier; 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 a semantic node or a combination of semantic nodes; and at least some of the 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; the method including: (i) identifying a structured, machine-readable representation of data comprising semantic nodes and/or passages that conform to the machine-readable language, which represents semantics of the word or sequence of words in the first natural language; (ii) retrieving a word or sequence of words in the second natural language that corresponds in meaning to the identified structured, machine-readable representation of data; and (iii) outputting the retrieved word or sequence of words in the second natural language that corresponds in meaning to the identified structured, machine-readable representation of data. ### Claim 2 (depends on 1) The method of claim 1 in which a machine learning system is used to generate the semantic nodes or the passages, wherein the semantic nodes or the passages correspond to words or sequence of words in a natural language. ### Claim 3 (depends on 2) The method of claim 2 in which the machine learning system is a neural network system. ### Claim 4 (depends on 3) The method of claim 3 in which the neural network system utilises recurrent neural networks or long short-term memories (LSTMs) or attention mechanisms or transformers. ### Claim 5 (depends on 3) The method of claim 3 in which the neural network system is a switch transformer feed forward neural network system. ### Claim 6 (depends on 3) The method of claim 3 in which the neural network system comprises an encoder and decoder and beam searching is used during decoding of the semantic representations from the decoder to remove invalid semantic representations. ### Claim 7 (depends on 3) The method of claim 3 in which the machine learning system is a deep learning system. ### Claim 8 (depends on 2) The method of claim 2 in which the machine learning system has been trained on training data comprising natural language and a corresponding structured machine-readable representation, wherein the corresponding structured machine-readable representation comprises semantic nodes and passages that conform to the machine-readable language. ### Claim 9 (depends on 2) The method of claim 2 in which the semantic nodes or the passages that correspond to the words or sequence of words provide a machine-readable representation of meaning of the words or sequence of words. ### Claim 10 (depends on 2) The method of claim 2 in which the semantic nodes or the passages that correspond to the words or sequence of words are processed by a computer-based system for one or more of the following: to derive facts or relationships, to reason, to learn, to answer questions, to process natural language content, to enable man-machine interaction, to represent and to police rules or tenets, to enable one or more vertical applications. ### Claim 11 (depends on 2) The method of claim 2 in which the semantic nodes or the passages that correspond to the words or sequence of words are processed by a computer-based system to generate an output that is human-readable. ### Claim 12 (depends on 11) The method of claim 11 in which the human readable output includes one or more of the following: an answer to a question expressed in the first natural language; a reasoning statement that explains how the computer-based system has reached a conclusion; a learning statement that explains what the computer-based system has learnt; a response in a man/machine interaction. ### Claim 13 (depends on 11) The method of claim 11 in which the computer-based system is further operable to automatically translate from the structured-machine readable representation to the second natural language in real time. ### Claim 14 (depends on 11) The method of claim 11 in which when translating from the structured-machine readable representation to the second natural language the computer-based system varies the generated translations between alternatives that are substantially semantically equivalent to create varied responses for the benefit of human users. ### Claim 15 (depends on 1) The method of claim 1 in which a passage of natural language is passed through a sequence-to-sequence neural architecture trained on training data comprising natural language and a corresponding structured representation that encodes meaning. ### Claim 16 (depends on 1) The method of claim 1 in which the word or sequence of words in the first natural language is a question and the question is answered with reference to a semantic representation. ### Claim 17 (depends on 1) The method of claim 1 in which the word or sequence of words in the first natural language is one or more documents and a semantic representation of the one or more documents is used to answer a question. ### Claim 18 (depends on 1) The method of claim 1 in which reasoning with reference to a semantic representation produces further, new representations. ### Claim 19 (depends on 1) The method of claim 1 in which when automatically translating a sequence of words expressed in the first natural language into the machine-readable language, a structure of the sequence of words is compared with known machine-readable language structures in the non-transitory computer-readable medium to identify similarities. ### Claim 20 (depends on 1) The method of claim 1 in which automatically translating the word or sequence of words into the machine-readable language is achieved by referencing a store of previously identified correct translations between the first natural language and the machine-readable language. ### Claim 21 (depends on 1) The method of claim 1 in which automatically translating the word or sequence of words into the machine-readable language is achieved by utilising a pipeline of functions which transform the word or sequence of words into a series of intermediate forms. ### Claim 22 (depends on 1) The method of claim 1 in which semantic impact of changes to the word or sequence of words in the first natural language is automatically assessed to determine whether known or ground truth examples of semantic nodes or passages can be used. ### Claim 23 (depends on 1) The method of claim 1 in which the word or sequence of words in the second language that correspond to the identified semantic nodes or passages are automatically varied to provide for varied translations. ### Claim 24 (depends on 1) The method of claim 1 in which automatically translating the word or sequence of words into the machine-readable language is achieved by referencing a context of information relevant to generating a correct translation. ### Claim 25 A computer-based system configured to translate between a first natural language and a second natural language, the system being configured to: (a) store in a non-transitory computer-readable medium a structured, machine-readable representation of data that conforms to a machine-readable language; (b) receive a word or sequence of words in the first natural language to be translated into the second natural language; (c) automatically translate that word or sequence of words expressed in the first natural language into the second natural language by first translating that word or sequence of words expressed in the first natural language into the machine readable language, and then translating from the machine readable language into the second natural language, wherein the machine readable language is one in which: (I) syntax for the machine-readable language is a substantially unambiguous syntax comprising nesting of structured representations of data; (II) each structured representation of data includes an identifier selected from an address space that is sufficiently large to select a new identifier with negligible risk of selecting a previously allocated identifier; 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 a semantic node or a combination of semantic nodes; and at least some of the 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 system is configured to (i) identify a structured, machine-readable representation of data comprising semantic nodes and/or passages that conform to the machine-readable language, which represents semantics of the word or sequence of words in the first natural language; (ii) retrieve a word or sequence of words in the second language that corresponds in meaning to the identified structured, machine-readable representation of data, and (iii) output the retrieved word or sequence of words in the second natural language that corresponds in meaning to the identified structured, machine-readable representation of data. ### Claim 26 (depends on 25) The computer-based system of claim 25, the computer-based system including a machine-learning system, in which the machine learning system is configured to generate the semantic nodes or the passages, wherein the semantic nodes or the passages correspond to words or sequence of words in a natural language. ### Claim 27 (depends on 26) The computer-based system of claim 26 in which the machine learning system is a neural network system. ### Claim 28 (depends on 27) The computer-based system of claim 27 in which the machine learning system is a deep learning system.