You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
GovInsight-AI 是一个基于大语言模型 (LLM) 的政务诉求工单办理质量智能检测系统。该项目专门针对政务服务热线(如12345)中"群众诉求"与"办理答复"的一致性问题进行自动化检测。系统通过集成阿里云Qwen-Plus模型,像资深质检员一样自动比对群众原始诉求与职能部门办理回复,精准识别答非所问、逻辑不通、解决不彻底、态度生硬等问题,并提供智能化的修正建议。项目已重构为Cloudflare Pages全栈Serverless架构,支持本地开发和云端部署。Intelligent Quality Inspection System for Government Service Hotlines (12345) powered by LLM.
An AQL-based Quality Assurance extension for ERPNext’s Quality Inspection module, with the objective of consolidating and replacing the existing standalone quality management system.
AI-powered industrial surface defect detection system using YOLOv8 for automated steel quality inspection. Detects and classifies six defect types with deep learning and computer vision.
An end-to-end Computer Vision project implementing automated surface crack detection using Convolutional Neural Networks (CNNs) with TensorFlow and Keras, featuring dataset preprocessing, augmentation, model training, evaluation, and single-image inference.
Resources for checking Chinese suppliers and factories before ordering: company registry lookups, customs and trade data, third-party inspection firms, factory-vs-trader checks, and payment safety — an awesome list for overseas buyers and importers.
Computer-vision pipeline for automated surface-defect detection and classification in Friction Stir Welding (FSW): illumination flattening, ROI extraction, and defect segmentation.
AI-powered manufacturing quality inspection system using TensorFlow, MobileNetV2 Transfer Learning, OpenCV, and Flask. Classifies industrial products as Good or Defective in real time with a modern web interface.
This repository describes AI-based approaches using Deep Learning (DL), making a benchmark of multiple Convolutional Neural Network (CNN) models and performance comparison specifically for inspection. Feel free to contribute.