Submitted by admin on Wed, 08/10/2022 - 22:59

Maximising non-aeronautical revenue

Sequence Number 5 Industry Airports & Airlines Banner Maximising non-aeronautical revenue How 5G enabled

Ability to generate insights on consumer behavior, historical spending and provide a personalised retail & shopping experience.

Data Flows
Title Devices Icon Devices Description
  • Cameras at all critical locations to capture images
  • Collect other data types: stock/shelf levels; sales levels; etc.
Title Connectivity Icon Connectivity Description
  • Images transmitted to edge and enterprise storage
  • Timeseries/Asset data
Title Edge Compute Icon Edge Compute Description
  • AI (MV and ML models) to be developed
  • AI (MV and ML models) to be developed; ML mainly non-critical
Title Cloud Compute & Storage Icon Cloud Compute & Storage Description
  • All data is stored in enterprise data storage, where data ownership belongs to the company
Title Applications & Services Icon Applications & Services Description
  • Non-critical MV / ML models execution, e.g forecasting models
  • Automated processes by default
Title Inform Decision Makers Icon Inform Decision Makers Description
  • Exploit XR to show passenger analytics
Title Support Decision Making Icon Support Decision Making Description
  • End of process
Application Logic
Description
  • Personal data privacy and protection is to be considered when collecting, analysing and viewing data.
  • Collect images from different angles as they will have a different purpose.
  • Ensure all relevant data is sent to the Enterprise data store to be provided selectively to different AI models.
Description
  • All AI (ML and MV) models will be developed through a joint effort of SME and data scientists.
  • Development of these models will be iterative (will require time) to achieve an appropriate quality level.
  • There will be multiple MV models as passengers will be tracked for various reasons.
  • Both MV and ML models developed will be operating to provide visibility e.g. people flow, system flow, sales transactions, etc.
Description
  • MV and ML models can be developed to provide insights such as stock vs shelf levels vs sales levels, could include environmental information such as time of day/year, weather, seasonal celebrations, etc.
  • Most of the time series data will most likely not be time-critical, therefore the data will be are cloud-based.
Expected benefits Key value created