Smart Glasses Chat Architecture Using Mobile and Cloud AI

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing smart glasses have limited functionality and low intelligence, lacking advanced interaction capabilities beyond basic music listening and calling functions.

Innovation Solution

Integration of Generative Artificial Intelligence Large Language Models (GAILLMs) into smart glasses, enabling chat functions through a processor, microphone, speaker, and memory, with a system that includes a smart mobile terminal and a model server for processing user queries and generating responses.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If Generative AI Large Language Models are integrated into smart glasses, then the intelligence and interactivity are improved, but the device complexity and cost increase

Engineering Contradiction:
ImproveintelligenceVSAvoiddevice complexity
Core Design Contradiction:
Extent of automationVSDevice complexity

Solution Approach 1:

The system is divided into multiple components: the smart glasses handle audio input and output, the mobile terminal manages speech-to-text conversion and model coordination, and the cloud server provides the GAILLMs processing power. This segmentation allows the complex AI functionality to be distributed across devices, reducing the complexity burden on the smart glasses themselves while still achieving high intelligence.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The mobile terminal acts as an intermediary between the smart glasses and the cloud-based GAILLMs model server. It coordinates the interaction by receiving audio data from the glasses, managing the speech-to-text conversion, and facilitating communication with the model server, thereby simplifying the overall system architecture.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If Generative AI Large Language Models are integrated into smart glasses, then the functionality and interactivity are enhanced, but the manufacturing cost increases

Engineering Contradiction:
ImprovefunctionalityVSAvoidmanufacturing cost
Core Design Contradiction:
Adaptability or versatilityVSEase of manufacture

Solution Approach 1:

The system leverages the mobile terminal and cloud server, which are existing universal platforms, to provide the complex AI processing capabilities. The smart glasses themselves remain relatively simple devices that can be manufactured using conventional processes, while the enhanced functionality is achieved through the multi-functional mobile terminal and cloud infrastructure that can serve multiple applications.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

Instead of embedding expensive AI hardware directly in the smart glasses, the system uses the mobile terminal and cloud server to provide the intelligence. This allows the smart glasses to be manufactured at lower costs while still accessing advanced AI capabilities through software and network connections.

Inventive Principle:
Principle #26Copying

3Ease of operation

If complex chat functions with GAILLMs are implemented, then the interactivity is improved, but the processing time and energy consumption increase

Engineering Contradiction:
ImproveinteractivityVSAvoidprocessing time
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The system moves the complex processing from the local device (smart glasses) to the cloud dimension (model server). By transitioning from local edge computing to cloud-based processing, the system can handle complex GAILLMs operations without being constrained by the limited processing power and battery capacity of the smart glasses, thereby reducing local energy consumption while maintaining interactivity.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS20240386893A1Smart glasses, system and control method based on generative artificial intelligence large language models
Publication Date: 2024.11.21 SOLOS TECH SHENZHEN LTD
  • US20240386893A1 patent drawing
  • US20240386893A1 patent drawing
  • US20240386893A1 patent drawing

AI summary

Smart glasses, control method and system based on generative artificial intelligence large language models are provided. The smart glasses include a front frame, a temple, a microphone, a speaker, a processor and a memory, one or more computer programs executable on the processor are stored in the memory, the one or more computer programs include instructions for: activating a chat function of the smart glasses in response to a first control instruction; obtaining a first speech of a user through the microphone, wherein the first speech includes a question asked by the user; obtaining a second speech including a reply corresponding to the question through generative artificial intelligence large language models, and playing the second speech through the speaker. The application improves the intelligence and interactivity of the smart glasses.