VIDA.ai · MRNM SERVICE
Maintenance & Repair Notification
Management Service
As a ViDA.ai event hub, MRNM (Maintenance & Repair Notification Management) integrates device status, anomaly detection, and multi-channel notifications, turning scattered maintenance events into traceable, analyzable, and decision-ready management workflows.
Real-Time Equipment Monitoring Map
Monitors device online status, CPU, memory, and network status across Taiwan
- Communication Status: Abnormal
- CPU Usage: 100%
- Uptime: 120 min
- Recognition Records: 0 records
Device Statistics Overview
5
2
1
92.4%
System health monitoring uses icon colors to present maintenance status, allowing operators to identify faulty nodes at a glance.
Fault Repair Notification Management
When a device or service anomaly is detected, the system automatically creates a work order, significantly reducing the response time for maintenance personnel.
Automatically Dispatch Incident Tickets
After AI detects an anomaly, it immediately creates a repair incident and dispatches an engineer.
Complete Maintenance History Records
Fully preserves handler, time, and content records for auditing and performance tracking.
Multi-Channel Real-Time Notification
Supports SMS, Email, LINE, and API notifications.
Management Decision Basis
The system automatically calculates metrics such as fault type, mean time to repair (MTTR), and improvement rate, providing management with accurate data support.
MTTR Optimization
22% Average repair time shortened over the past 3 monthsPreventive Maintenance
15% Potential risks intercepted before occurrenceFault Type Distribution
- CPU
- Network
- Disk
Maintenance Processing Time Trend
Processing performance: maintained at A+ this month
Visualized Management
- Real-time dynamic map marking
- Color-coded warning status at a glance
- Centralized monitoring across regions
Automated Notification
- Automatic work-order assignment for anomalies
- LINE / Email multi-channel notifications
- Shorten by 60% response time
Digitalized Decision-Making
- In-depth fault type analysis
- Engineer handling performance statistics
- Accurate equipment lifecycle assessment