# US 12,223,286 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 12,223,286 B2
- Document ID: US12223286B2
- Status: Granted
- Kind: B2
- Application number: 18/517,720
- Filed: 2023-11-22
- Published: 2024-03-14
- 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/US12223286B2

## 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 30/0631: {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-based system configured to analyse data,
(a) the computer-based system configured to store 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 one or more tenets, statements or other rules, any of which we refer to as ‘tenets’, defining objectives or motives, also represented using the structured machine-readable representation of data, the one or more tenets including at least one constraint tenet that prohibits an action or actions;
(b) the computer-based system including a planning algorithm system, the planning algorithm system configured to generate candidate actions, and to analyse the candidate actions against the tenets including the at least one constraint tenet, to identify optimal actions from the generated candidate actions.

### Claim 2 (depends on 1)

The computer-based system of claim 1, in which the computer-based system is configured to analyse data, to process the data using the planning algorithm system, and to express the results of the analysis in the structured, machine-readable representation of data.

### Claim 3 (depends on 1)

The computer-based system of claim 1, in which the computer-based system is configured to think ahead in terms of actions and create plans of how it can meet its motives in the future, if it is not possible to achieve with one or more actions now.

### Claim 4 (depends on 3)

The computer-based system of claim 3, in which the computer-based system is configured to think ahead using the planning algorithm system.

### Claim 5 (depends on 1)

The computer-based system of claim 1, in which the planning algorithm system includes an understanding of what actions the computer-based system can perform in what circumstances, as well as the likely consequences of performing those actions.

### Claim 6 (depends on 1)

The computer-based system of claim 1, in which the planning algorithm system provides an understanding of what external effects might occur, in a given situation, to aid with planning.

### Claim 7 (depends on 1)

The computer-based system of claim 1, in which the planning algorithm system is configured to use a forward-chaining, breadth first search algorithm.

### Claim 8 (depends on 7)

The computer-based system of claim 7, in which inputs to the forward-chaining, breadth first search algorithm are: an initial state of the environment, encoded in the structured, machine-readable representation; a set of goals, encoded in the structured, machine-readable representation; a core structured, machine-readable representation store including reasoning passages and knowledge of actions, along with their requirements and consequences.

### Claim 9 (depends on 8)

The computer-based system of claim 8, in which the forward-chaining, breadth first search algorithm is configured to:
(a) First check if the goal passages can be met using the question processor, along with the information about the current environmental state; if they can, no action is required;
(b) Fetch possible complete actions that could be executed, based on the environmental state and the requirements of the actions, including looking at known partial actions and finding valid parameters for them;
(c) With an action selected, update the environmental context based on the known consequences of that action, giving a new environmental state;
(d) Check again if the goals are met using the new state; if they are, the current selected action is a valid plan;
(e) If not, the new state and selected action are recorded as a partial plan and added to a list of states to continue looking at;
(f) These states can be looped over, following the process of (a) to (e), to calculate the environmental state after multiple actions have been executed; after each new action is added, the state is used to see if it can help infer the goals, if so that series of actions is a valid plan.

### Claim 10 (depends on 9)

The computer-based system of claim 9, in which after a valid plan has been executed, the computer-based system can select the first action from the plan and execute it for real.

### Claim 11 (depends on 9)

The computer-based system of claim 9, in which if the full consequences of the actions are known, the computer-based system is configured to execute a plurality of actions from the plan in a row, until an uncertain action or required external effect is reached.

### Claim 12 (depends on 11)

The computer-based system of claim 11, in which when an uncertain action is reached, the computer-based system is configured to perform the uncertain action then wait to see how the real environment data changes based on the uncertain action; the computer-based system then re-plans to find the next action to execute.

### Claim 13 (depends on 1)

The computer-based system of claim 1, in which the planning algorithm system includes a sub-component responsible for generating candidate actions, by working out which available actions will optimise goal-like tenets.

### Claim 14 (depends on 13)

The computer-based system of claim 13, in which after the sub-component responsible for generating candidate actions generates a candidate action that is determined should be executed, the candidate action is sent to a component of the planning algorithm system to verify the candidate action, including testing that no constraint tenet is violated.

### Claim 15 (depends on 1)

The computer-based system of claim 1, in which if a constraint tenet is violated, a candidate action is not performed.

### Claim 16 (depends on 1)

The computer-based system of claim 1, in which a candidate action is to answer a question.

### Claim 17 (depends on 1)

The computer-based system of claim 1, in which the computer-based 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 18 (depends on 1)

The computer-based system of claim 1, in which the computer-based system is configured to utilise a process of automated curation to determine the value of passages stored in a passage store, to scalably maintain information represented in the structured representation of data without the need for human curation.

### Claim 19 (depends on 1)

The computer-based system of claim 1, in which the structured representation of data uses a shared syntax that applies to semantic nodes and passages that represent factual statements, query statements and reasoning statements.

### Claim 20 (depends on 1)

The computer-based system of claim 1, in which the machine-readable language is scalable since any natural language word, concept, or other thing can be represented by the structured, machine-readable representation of data.

### Claim 21 (depends on 1)

The computer-based system of claim 1, in which the computer-based system is configured to generate a reasoned, natural language explanation that a potential action does comply or does not comply with the at least one constraint tenet.

### Claim 22 (depends on 1)

The computer-based system 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 23 (depends on 1)

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

### Claim 24 (depends on 23)

The computer-based system of claim 23 in which the computer-based system not changing the tenets comprises the tenets including a tenet prohibiting actions which might result in changes to the tenets.

### Claim 25 (depends on 1)

The computer-based system 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 26 (depends on 1)

The computer-based system 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 27 (depends on 1)

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

### Claim 28 (depends on 1)

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

### Claim 29 (depends on 28)

The computer-based system of claim 28 in which the potential actions are automatically executed if they optimize or otherwise positively affect the achievement or realization of the tenets.

### Claim 30 (depends on 1)

The computer-based system of claim 1, the computer-based system configured to reason, in which 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.