Edge AI › Smart Terminal AI Middleware

Smart Terminal AI Middleware

智能终端AI中间件

Edge AI tiered inference platform for IoT / industrial embedded scenarios

The Problem

IoT devices face a “last mile” problem after deployment: device state is opaque, O&M costs are high. Engineers need 30+ minutes per visit to connect debuggers, check logs, and build tools.

Smart Terminal AI fills the gap between “can’t run models on-device” and “pure cloud is unreliable” — letting every MCU device answer “what’s your current status?” in natural language.


Key Metrics

128KB Peak SRAM Usage
3,500+ Lines Full-Module Code
<100ms Local Inference Latency
240MHz RISC-V Clock

3-Tier Progressive Inference Architecture

Tier 3 · Cloud LLM Cloud LLM via WiFi · <3s · Complex semantic queries
Tier 2 · Rule NLP Local rule engine · <500ms · 19 intent types · Works offline
Tier 1 · Keyword Match Zero-dependency keyword library · <100ms · Stored in Flash · Only 128KB peak RAM

The inference scheduler automatically selects the optimal path based on query complexity + network state. Tier 3 failure auto-degrades to Tier 2, ensuring offline availability.


Four Core Components

🧠

AI Inference Engine Library

Portable to any RISC-V/ARM MCU + RTOS. Unified ai_engine_query() API with automatic 3-tier scheduling internally.

⌨️

Smart CLI Framework

Intent-aware CLI framework supporting mixed natural language and traditional commands. History + TAB completion. Zero dependency, fully portable.

📡

Device Monitoring SDK

Standardized CPU / memory / temperature / network / sensor collection interfaces, adapted to mainstream embedded platform drivers.

FPGA Acceleration Module

Lightweight inference acceleration IP for Anlogic EG4X20. Maps matrix multiply to FPGA lookup tables. Theoretical 50x speedup, compressing inference latency to under 200ms.


Live Demo

Plug in USB → Open serial terminal → Ask in natural language:

> ai is the device status normal?
→ CPU usage 12%, memory 21% (128KB/606KB), temperature 36.7°C normal,
  WiFi signal good (-58dBm), sensor data collection normal.
  Device is healthy.

> ai any anomalies in recent logs?
→ [AI Tier-3] Analyzing recent 47 log entries...
  Found 2 WARN level logs: ADC channel 2 signal is 0,
  possibly sensor disconnected. All other logs are INFO level,
  system operating normally.

Zero App install · Zero special tools · Serial direct connect · Second-level response

Back to Edge AI | Contact Sales

Quick Navigation
Contact & Cooperation

Dev board · IP licensing · Custom development

Contact Now

Technical Questions or Partnership Interest?

Contact our technical team for support

Contact Now