# US 2024/0252048 A1 · Ai assistance system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0252048 A1
- Document ID: US20240252048A1
- Status: Published application
- Kind: A1
- Application number: 18/620,946
- Filed: 2024-03-28
- Published: 2024-08-01
- Earliest claimed: 2019-02-26
- Inventors: Bao Tran
- Web page: https://patentgrep.com/patent/US20240252048A1

## CPC

- A61B 5/02055: {Simultaneously evaluating both cardiovascular condition and temperature}
- A61B 1/000096: {using artificial intelligence}
- A61B 1/00194: {adapted for three-dimensional imaging}
- A61B 1/045: Control thereof
- A61B 1/05: characterised by the image sensor, e.g. camera, being in the distal end portion
- A61B 1/227: for ears, i.e. otoscopes
- A61B 5/0022: {Monitoring a patient using a global network, e.g. telephone networks, internet}
- A61B 5/026: Measuring blood flow {(A61B3/1233, A61B3/1241 take precedence)}
- A61B 5/0537: Measuring body composition by impedance, e.g. tissue hydration or fat content
- A61B 5/0538: invasively, e.g. using a catheter
- A61B 5/1032: {Determining colour of tissue for diagnostic purposes}
- A61B 5/1117: {Fall detection}
- A61B 5/1118: {Determining activity level}
- A61B 5/12: Audiometering
- A61B 5/14546: {for measuring analytes not otherwise provided for, e.g. ions, cytochromes}
- A61B 5/165: {Evaluating the state of mind, e.g. depression, anxiety}
- A61B 5/33: specially adapted for cooperation with other devices
- A61B 5/378: Visual stimuli
- A61B 5/4803: {Speech analysis specially adapted for diagnostic purposes}
- A61B 5/6817: {Ear canal}
- A61B 5/6898: {Portable consumer electronic devices, e.g. music players, telephones, tablet computers}
- A61B 5/7267: {involving training the classification device}
- A61B 5/7465: {Arrangements for interactive communication between patient and care services, e.g. by using a telephone network (telemetry of measured physiological signal A61B5/0002)}
- G05B 13/027: {using neural networks only}
- G05B 13/042: {in which a parameter or coefficient is automatically adjusted to optimise the performance}
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- H04R 25/604: {of acoustic or vibrational transducers}
- H04R 25/652: {Ear tips; Ear moulds (hybrid ear moulds or post-processing thereof for their customisation H04R25/659)}
- H04R 25/659: {Post-processing of hybrid ear moulds for customisation, e.g. in-situ curing}
- A61B 5/02438: {with portable devices, e.g. worn by the patient}
- A61B 5/0816: {Measuring devices for examining respiratory frequency (measuring frequency of electric signals G01R23/00)}
- A61B 5/14532: {for measuring glucose, e.g. by tissue impedance measurement}
- A61B 5/369: Electroencephalography [EEG]
- A61B 5/486: {Biofeedback (using electroencephalography [EEG] A61B5/375)}
- A61B 2560/0247: for compensation or correction of the measured physiological value
- A61B 2562/0219: Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
- G06N 3/045: Combinations of networks
- G06N 5/02: Knowledge representation; Symbolic representation
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- H04R 25/356: {Amplitude, e.g. amplitude shift or compression}
- H04R 25/507: {implemented by neural network or fuzzy logic}
- H04R 2225/025: In the ear hearing aids [ITE] hearing aids
- H04R 2225/41: Detection or adaptation of hearing aid parameters or programs to listening situation, e.g. pub, forest
- H04R 2225/77: Design aspects, e.g. CAD, of hearing aid tips, moulds or housings
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04R: LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS (producing sounds with frequency not determined by supply frequency G10K)

## Abstract

Systems and methods for assisting user with an ear-worn/earable device and a learning machine language model to assist the user.

## Claims

### Claim 1

A method for assisting a user, comprising:
receiving a verbal request from the user with a device coupled to an ear, wherein the device includes biometric sensors coupled to the ear;
selecting a learning machine language model or an intelligent agent based on the user request, the selected model or agent applying user environmental information including positioning information or nearby images in responding to the requested information or decision; and
providing a response to the verbal request.

### Claim 2 (depends on 1)

The method of claim 1, comprising applying a learning machine to identify an aural environment and adjust the amplifiers for optimum hearing or to adjust amplifier parameters for a particular environment with a predetermined noise pattern.

### Claim 3 (depends on 1)

The method of claim 1, comprising capturing vital signs with the in-ear device.

### Claim 4 (depends on 1)

The method of claim 1, comprising capturing a user environment with a camera facing away from the ear, and providing the user environmental information to the learning machine language model or intelligent agent for use with the response.

### Claim 5 (depends on 1)

The method of claim 1, comprising deploying one or more intelligent agents to provide the requested information, wherein each agent has a fixed lifetime or fixed cost structure, wherein the agent is specific to skills, expertise, languages, or locations.

### Claim 6 (depends on 1)

The method of claim 1, wherein agent types are defined based on a predefined taxonomy or ontology, allowing for the selection of relevant agent types based on the user request.

### Claim 7 (depends on 1)

The method of claim 1, wherein the fixed lifetime of the agent is determined based on an expected duration of the user request or available computational resources.

### Claim 8 (depends on 1)

The method of claim 1, wherein the cost limit for the agent is determined based on the complexity of the information being collected or the computational resources required to process the collected data.

### Claim 9 (depends on 1)

The method of claim 1, wherein the one or more intelligent agents operate autonomously by using local search algorithms, distributed decision-making, or other decentralized coordination mechanisms to efficiently gather and aggregate information.

### Claim 10 (depends on 1)

The method of claim 1, wherein the recommendation or decision is further refined or validated by consulting external knowledge sources or expert systems.

### Claim 11 (depends on 1)

The method of claim 1, comprising maintaining a history of previous agent swarm deployments to optimize the selection and configuration of agent types for future requests.

### Claim 12 (depends on 1)

The method of claim 1, wherein the user device provides a user interface for monitoring the progress of the agent swarm and adjusting the parameters of the deployment as needed.

### Claim 13 (depends on 1)

The method of claim 1, wherein the agent swarm deployment is integrated with other services or applications on the user device, such as personal assistants, task management tools, or decision support systems.

### Claim 14 (depends on 1)

The method of claim 1, comprising providing super app functionality for the user with a large langue model (LLM) and a plurality of software or apps.

### Claim 15 (depends on 14)

The method of claim 14, further comprising:
identifying a plurality of apps installed on a user's device;
determining features or capabilities of the identified apps and one or more commands to access the features or capabilities;
extracting and storing the features or capabilities of the apps in a knowledge base;
applying the LLM to identify a user need;
identifying one or more selected apps that address the user need; and
sending one or more commands to the selected app for the user.

### Claim 16 (depends on 15)

The method of claim 15, further comprising monitoring user interactions with the apps over time; analyzing user preferences, habits, or common tasks performed using the apps; and
updating a database with the user's behavioral patterns and preferences.

### Claim 17 (depends on 1)

The method of claim 1, further comprising identifying the user's current context, including location, time, and ongoing activities and selecting the one or more mobile apps based on the user's context and preferences.

### Claim 18 (depends on 1)

The method of claim 1, comprising a large langue model (LLM) configured to understand requests from the user and to translate the request into actions to control and interact with hardware or with software apps.

### Claim 19 (depends on 18)

The method of claim 18, wherein the LLM generates content as text, images, and code for software apps and wherein the LLM enables multimodal interaction, allowing the user to interact with a “super app” using different input and output methods.

### Claim 20 (depends on 7)

The method of claim 7, further comprising deploying the LLM system on the user's device, enabling offline functionality and reducing reliance on network connectivity.
