AI Platform

Demand, load, price, equipment health and user behaviour fuse in real time inside one intelligence layer. Each capability plugs in alone or works with the others.

HQZN Neural Core

Predict. Optimise.Act autonomously.

Models train on DGX Spark, infer on Jetson Thor and are validated in Omniverse.

Built for enterprise operations

  • OCPP
  • Jetson
  • Omniverse
  • OpenUSD
  • RK3568
Energy AIEdge AIDigital twin platformEdge interactionCharging-scene AIIntelligent operationsHQZNAI

02 / Core capabilities

Not a general chatbot, but a set of specialised models trained, deployed and continuously tuned for charging operations.

01

Energy AI

Know demand before the peak.

Site-level demand forecasting from historical load, tariffs and weather, feeding dispatch and pricing decisions.

  • Intelligent dispatch
  • Demand forecasting
  • Dynamic pricing
02

Edge AI

Millisecond recognition, on site.

Jetson Thor and RK3568 run vision inference locally for millisecond recognition, safety detection and anomaly alerts.

  • Jetson Thor
  • RK3568
  • Millisecond recognition
  • Safety detection
  • Anomaly alerts
03

Digital twin platform

Simulate in the twin, then execute on site.

NVIDIA Omniverse-based station twins with 3D visualisation, scenario simulation and remote operations.

  • Omniverse
  • 3D visualisation
  • Simulation
04

Edge interaction

Terminals that listen and see.

RK3568-powered on-site terminals with voice interaction, gesture recognition and guided flows that lower the barrier for drivers.

  • RK3568
  • Voice interaction
  • Gesture recognition
  • Smart guidance
05

Charging-scene AI

From plate to battery, end to end.

Plate recognition, charging-behaviour analysis and battery health diagnosis make every session measurable and optimisable.

  • Plate recognition
  • Behaviour analysis
  • Battery health
06

Intelligent operations

Fix failures before downtime.

Multi-source time-series anomaly detection and predictive maintenance that open work orders early and cut O&M cost by 40% or more.

  • Predictive maintenance
  • Work-order automation
  • 40%+ lower O&M cost

The data-to-decision loop

01

Collect

Charger telemetry, vision and tariff data

02

Predict

Demand, failure and battery-health models

03

Decide

Dispatch, pricing and maintenance recommendations

04

Act

Execute within authorised limits and report back

Technology matrix

The hardware and software products used across training, edge inference, simulation and data interoperability.

COMPUTE01

DGX Spark

Desktop AI supercomputer

Train and fine-tune charging models on site without sending operating data off campus.

EDGE02

Jetson Thor

Real-time edge inference

Run vision and time-series models at the station with millisecond response to safety events.

SIMULATE03

Omniverse

Physically based simulation

Build interactive station twins and rehearse dispatch strategies virtually.

INTEROP04

OpenUSD

Open scene description

Let equipment, BIM and simulation data flow in one format.

HQZN / AI charging operating system

Bring your own station data and see forecasting, dynamic pricing and the digital twin at work.

Book a platform demo