# US 12,008,327 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 12,008,327 B2 - Document ID: US12008327B2 - Status: Granted - Kind: B2 - Application number: 18/088,595 - Filed: 2022-12-25 - Published: 2023-04-27 - Granted: 2024-06-11 - 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/US12008327B2 ## 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 16/951: 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 A computer implemented method for the automated analysis or use of data is implemented by a voice assistant. The method comprises the steps of: (a) storing in a memory a structured, machine-readable representation of data that conforms to a machine-readable language (‘machine representation’); the machine representation including representations of user speech or text input to a human/machine interface; and (b) automatically processing the machine representations to analyse the user speech or text input. ## Claims ### Claim 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 data relates to user speech or text information input to a human/machine interface; (b) automatically processing the structured machine-readable representation to analyse the user speech or text information; (c) identifying a first wake word in the analysed user speech or text information, and initiating processing in response to identifying the first wake word, and entering a privacy-preserving state after the initiating processing; and (d) after entering the privacy-preserving state, identifying a second wake word in the analysed user speech or text information, and continuing processing in response to identifying the second wake word, wherein the second wake word is sufficiently long or unusual that a false recognition of the second wake word is significantly more improbable than a false recognition of the first wake word; in which a neural architecture is used to generate the machine-readable language and the neural architecture utilises recurrent neural networks or long short-term memories (LSTMs) or attention mechanisms or transformers. ### Claim 2 (depends on 1) 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 the choice of semantic nodes and the way they are combined and ordered as passages. ### Claim 3 (depends on 2) The method of claim 2 in which user speech or text input information is automatically translated into the machine readable language by a machine learning system that generates the semantic nodes or passages that represent the user speech or text input information. ### Claim 4 (depends on 3) The method of claim 3 in which the machine learning system has been trained on training data comprising natural language and a corresponding structured machine-readable representation, such as a machine-readable language comprising semantic nodes and passages. ### Claim 5 (depends on 1) The method of claim 1 in which output of a plurality of different voice assistants is provided to a plurality of users using at least one non-transitory data store embodied on a computer-readable medium containing personality information which determines the personality of at least some of the plurality of different voice assistants. ### Claim 6 (depends on 5) The method of claim 5 in which the personality information includes information about the voice assistant's gender or name or voice or moods or emotional reactions or level of formality or position on the extrovert-introvert scale or position on any Myers Briggs scale or a Myers Briggs categorisation or categorisation in a personality test or visual appearance. ### Claim 7 (depends on 5) The method of claim 5 in which the personality information includes at least one set of machine-readable tenets that represent goals and rules to guide at least some of the plurality of voice assistants, in which actions are performed that conform with the tenets by referencing the tenets; in which the at least one set of machine-readable tenets is a plurality of sets of machine-readable tenets, the method including mapping selected ones of the plurality of different voice assistants to selected ones of the plurality of sets of machine-readable tenets wherein different voice assistants are driven by different tenets. ### Claim 8 (depends on 5) The method of claim 5 in which private user data is accessible only by selected ones of the plurality of different voice assistants. ### Claim 9 (depends on 1) The method of claim 1 including the step of automatically translating user speech or text input information expressed in a natural language into the machine-readable language, and in which the 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 10 (depends on 1) The method of claim 1 including the step of automatically translating the user speech or text input information into the machine-readable language by referencing a non-transitory store embodied on a computer-readable medium of previously identified correct translations between the natural language and the machine-readable language. ### Claim 11 (depends on 1) The method of claim 1 including the step of automatically translating the user speech or text input information into the machine-readable language by utilising a pipeline of functions which transform the word or sequence of words into a series of intermediate forms. ### Claim 12 (depends on 1) The method of claim 1 in which the neural architecture utilises a switch transformer feed forward neural network system. ### Claim 13 (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 14 (depends on 2) The method of claim 2 in which the neural architecture includes an encoder and decoder and beam searching is used during decoding of the semantic representations from the decoder to remove invalid semantic representations. ### Claim 15 (depends on 1) The method of claim 1 in which the machine-readable language uses a single syntactical item, such as parentheses or brackets, to disambiguate the meaning of structured representations of data. ### Claim 16 (depends on 1) The method of claim 1 in which the machine-readable language uses a shared syntax across factual statements, queries and reasoning. ### Claim 17 (depends on 1) The method of claim 1 in which the machine-readable language uses nesting of nodes and passages, as a substantially unambiguous syntax. ### Claim 18 (depends on 1) 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, such as Universally Unique Identifier (UUID) or Unicode, that is sufficiently large to enable users to select a new identifier with negligible risk of selecting a previously allocated identifier. ### Claim 19 (depends on 1) 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. ### Claim 20 (depends on 1) The method of claim 1 in which the machine-readable language (i) uses a single syntactical item to disambiguate the 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 a substantially unambiguous syntax comprising nesting of structured representations of data; and (iv) uses an identifier selected from an address space that is sufficiently large to enable users to select a new identifier with negligible risk of selecting a previously allocated identifier; and (v) is scalable since there are no restrictions on which users can create structured representations of data or related identifier. ### Claim 21 (depends on 1) The method of claim 1 which includes the step of (a) representing a question in a non-transitory computer-readable medium as a structured, machine-readable representation of data, in the machine-readable language; and the method further includes the step of (b) automatically generating a response to the question, using one or more of the following steps: (i) matching the question with structured, machine-readable representations of data previously stored in the non-transitory computer-readable medium store; (ii) fetching and executing one or more computation units, where computation units represent computational capabilities relevant to answering the question; (iii) fetching and executing one or more reasoning passages, which are structured, machine-readable representations of data that represent semantics of potentially applicable reasoning steps relevant to answering the question; and in which the representation of the question, the structured, machine-readable representations of data previously stored in the non-transitory computer-readable medium store, the computation units and the reasoning passages are all represented in substantially the same machine-readable language. ### Claim 22 (depends on 1) The method of claim 1 which includes the step of learning new information and representing the new information in a structured, machine-readable representation of data that conforms to the machine-readable language. ### Claim 23 (depends on 1) The method of claim 1 which includes the step of (i) receiving a word or sequence of words in a natural language; and (ii) automatically translating that word or sequence of words into the machine-readable language by identifying or generating structured machine-readable representations that semantically represent the meaning of the word or sequence of words in the machine-readable language. ### Claim 24 (depends on 1) 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, which is a shared identifier for the entity. ### Claim 25 (depends on 1) The method of claim 1 in which the method enables translating between a first natural language and a second natural language, by: (a) storing in a memory 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 (i) identifying a structured, machine-readable representation of data that represents the semantics of the word or sequence of words in the first natural language and (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. ### Claim 26 (depends on 1) 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. ### Claim 27 (depends on 1) The method of claim 1 including 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; 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 the actions optimize or otherwise positively affect the achievement or realization of those tenets, statements or other rules. ### Claim 28 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 data includes input data relating to user speech or text information input to a human/machine interface, and in which the structured representation of data includes one or more tenets, statements or other rules defining objectives or motives; (b) automatically processing the structured machine-readable representation to analyse the user speech or text information; (c) automatically selecting, deciding on or executing actions; 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 the actions optimize or otherwise positively affect the achievement or realization of those tenets, statements or other rules; in which a neural architecture is used to generate the machine-readable language and the neural architecture utilises recurrent neural networks or long short-term memories (LSTMs) or attention mechanisms or transformers.