# US 12,223,285 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 12,223,285 B2
- Document ID: US12223285B2
- Status: Granted
- Kind: B2
- Application number: 18/410,135
- Filed: 2024-01-11
- Published: 2024-05-02
- Granted: 2025-02-11
- 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/US12223285B2

## 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 structured, machine-readable representation of data includes tenets which define rules, the tenets including at least one non-changeable tenet;
(b) a computer system analysing a potential action to determine whether executing the potential action would result in compliance or non-compliance with one or more of the rules, and determining that executing the potential action would result in compliance or non-compliance with the one or more of the rules;
(c) the computer system generating a reasoned, natural language explanation of the compliance or non-compliance with the one or more of the rules.

### Claim 2 (depends on 1)

The method of claim 1, in which the rules include ethics rules.

### Claim 3 (depends on 1)

The method of claim 1, in which at least some of the rules define affirmative or allowed actions or content.

### Claim 4 (depends on 1)

The method of claim 1, in which at least some of the rules define goals, such as optimisable actions or states.

### Claim 5 (depends on 1)

The method of claim 1, in which the rules include web site or chatbot rules, such as abusive content rules.

### Claim 6 (depends on 1)

The method of claim 1, the tenets including at least one constraint tenet, in which the computer system generates a reasoned, natural language explanation that the potential action does comply or does not comply with the at least one constraint tenet.

### Claim 7 (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 8 (depends on 1)

The method of claim 1, in which the computer system does not change the tenets.

### Claim 9 (depends on 8)

The method of claim 8 in which the computer system not changing the tenets comprises the tenets including a tenet prohibiting actions which might result in changes to the tenets.

### Claim 10 (depends on 1)

The method of claim 1, in which the computer system independently checks each potential action against the tenets and discards the potential action if the independent check finds that the potential action is incompatible with the tenets.

### Claim 11 (depends on 1)

The method of claim 1 in which the potential action includes changing the state of a device linked to the computer system via a network.

### Claim 12 (depends on 1)

The method of claim 1 in which the potential action includes initiating a spoken interaction with a human being.

### Claim 13 (depends on 1)

The method of claim 1 in which the computer system learns from one or more of: (i) communication with at least one user and (ii) one external sensor connected to the computer system via a network.

### Claim 14 (depends on 1)

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.

### Claim 15 (depends on 1)

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 the 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.

### Claim 16 (depends on 15)

The method of claim 15 in which the events include communication from at least one user and where the actions include communication to at least one user.

### Claim 17 (depends on 15)

The method of claim 15 in which the computer system learns, and stores what it has learned to the long-term non-transitory computer-readable medium.

### Claim 18 (depends on 1)

The method of claim 1 in which the computer system comprises 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.

### Claim 19 (depends on 1)

The method of claim 1 in which the computer system actively excludes knowledge on itself from being used in determining actions.

### Claim 20 (depends on 1)

The method of claim 1 in which potential actions are autonomously generated by the computer system.

### Claim 21 (depends on 1)

The method of claim 1 in which potential actions are autonomously generated by the 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.

### Claim 22 (depends on 20)

The method of claim 20 in which the potential actions are automatically executed if they optimize or otherwise positively affect the achievement or realization of the tenets.

### Claim 23 (depends on 1)

The method of claim 1 in which reasoning with reference to the machine-readable representation produces further, new machine-readable representations.

### Claim 24 (depends on 1)

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.

### Claim 25 (depends on 1)

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.

### Claim 26 (depends on 1)

The method of claim 1 in which reasoning is where machine-readable language is generated from other machine-readable language using reasoning steps that are represented as machine representations, such as passages, which represent the semantics of the reasoning steps.

### Claim 27 (depends on 1)

The method of claim 1, in which new information is represented in the structured machine-readable representation, such as semantic nodes or passages, and is stored and used to improve reasoning steps.

### Claim 28 (depends on 1)

The method of claim 1, in which learning takes place from reasoning, in which machine representations that are generated from a chain of reasoning steps, are combined with reasoning passages, and are stored and utilised.

### Claim 29

Computer-based system configured to analyse data, the computer-based system configured to:
(a) store in a non-transitory memory 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 one or more tenets defining rules, the tenets including at least one non-changeable tenet;
(b) analyse a potential action to determine whether executing the potential action would result in compliance or non-compliance with one or more of the rules, and determining that executing the potential action would result in compliance or non-compliance with the one or more of the rules; and
(c) automatically generate a reasoned, natural language explanation of the compliance or non-compliance with the one or more of the rules.

### Claim 30 (depends on 29)

The system of claim 29, in which the computer system is configured to generate a reasoned, natural language explanation that the potential action does comply or does not comply with the at least one non-changeable tenet.