Mobile Neural Network Recognition for Low-Latency Product Scanning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional online product purchase systems are cumbersome and inconvenient for offline product searches, with delayed response times and reduced recognition rates due to high data transmission and computational demands, especially when recognizing new products or products with real-time updates.
Innovation Solution
A mobile artificial neural network device equipped with a camera and AI recognition model for real-time product information recognition, utilizing a lightweight AI model and augmented reality to display product information simultaneously, with the ability to update models and receive real-time additional information from a server.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high-definition video is transmitted to the Internet server in real time for product recognition, then product information can be recognized, but the amount of data transmission increases significantly and response speed is delayed
Solution Approach 1:
The patent extracts the AI recognition model from the server environment and embeds it directly into the mobile terminal. This allows the terminal to perform local real-time recognition without transmitting video data to the server, thereby eliminating transmission delays while maintaining recognition accuracy.
Solution Approach 2:
The system segments the recognition functionality from the communication infrastructure. By placing the AI model locally in the terminal rather than relying on server-based processing, the patent separates the recognition task from network-dependent operations, enabling independent real-time processing.
2Speed
If an AI recognition model is stored in the mobile terminal for local processing, then response speed improves, but the device complexity and power consumption increase
Solution Approach 1:
The patent transforms the AI model into a lightweight format suitable for mobile deployment by converting it to TensorFlow Lite format and applying quantization techniques. This reduces the model's computational requirements and storage needs while maintaining recognition performance, thereby reducing device complexity.
Solution Approach 2:
The system uses a simplified, optimized version of the AI model tailored for mobile devices rather than the full-featured server-based model. This lightweight model consumes fewer resources and is specifically designed for the constrained environment of mobile terminals.
3Measurement precision
If the AI recognition model is updated frequently to recognize new products, then recognition rate for new products improves, but the computational amount and power consumption for learning increase
Solution Approach 1:
The patent implements a pre-training mechanism where the AI model is trained on a comprehensive dataset of products before being deployed to mobile terminals. This preliminary training allows the model to recognize new products with reasonable accuracy without requiring extensive on-device learning, thereby reducing power consumption.
Solution Approach 2:
The system enables the AI model to adapt to new products through lightweight fine-tuning using minimal data collected from actual usage. Rather than requiring full retraining, the model performs self-adjustment with small datasets, significantly reducing the computational burden and power consumption associated with updates.
Data Source
AI summary
A mobile artificial neural network device is provided. The mobile artificial neural network device includes a camera configured to output a video of a product at a first frame rate, an AI recognition model configured to recognize a product information by receiving the product video, an artificial neural network processor configured to drive the AI recognition model at a second frame rate, and a display module configured to display the video of the product at the first frame rate and display the product information at the second frame rate.