Machine Learning Engine for Predicting Content Exposure at EV Charging Stations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies lack the ability to accurately predict content exposure at locations without installed electronic content displays, making it difficult to select optimal sites for new installations, as conventional auditing methods only provide insights after installation, not before.
Innovation Solution
Training a machine learning engine with data from existing installation locations to predict content exposure at candidate locations using location features and exposure metrics, enabling informed site selection for new installations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If content exposure auditing is performed at existing installation locations, then the amount of content exposure can be ascertained, but it is not helpful for selecting installation sites for new panels
Solution Approach 1:
The system performs preliminary action by training a machine learning model on existing installation location data before new site selection decisions are made. The model predicts content exposure metrics for candidate locations in advance, enabling informed site selection before any physical installation or auditing occurs. This transforms post-installation auditing into pre-installation prediction capability.
Solution Approach 2:
The system creates a virtual copy of the auditing function by using machine learning to simulate what content exposure metrics would be at candidate locations. Instead of physically installing panels and conducting audits at every potential site, the system copies the essential predictive information from existing locations through the trained model, providing exposure estimates for candidate sites without physical presence.
2Ease of manufacture
If panels are installed at locations with insufficient content exposure, then installation costs are incurred, but the investment does not yield sufficient returns
Solution Approach 1:
The system performs preliminary evaluation of candidate locations using the trained machine learning model to predict content exposure metrics before installation decisions are made. This preliminary action identifies locations likely to yield sufficient returns, filtering out poor candidates before any installation investment is committed, thereby protecting investment reliability.
Solution Approach 2:
The system uses feedback from actual content exposure data at existing installation locations to continuously improve site selection. The machine learning model learns from real-world performance data, creating a feedback loop that refines predictions for candidate locations, making installation decisions increasingly reliable over time based on proven performance patterns.
Data Source
AI summary
Techniques are described herein for predicting content exposure that will result from installing a panel at a location at which no panel is currently installed. The location may include at least one electric vehicle charging station (EVCS) that includes an integrated or external panel for displaying content. The techniques involve training a machine learning engine based on information obtained about locations at which panels are already installed. The information used to train the machine learning engine includes, for each existing installation location: (a) features of the location, and (b) exposure data that has been generated for the location. When the machine learning engine has been trained, the trained machine learning engine predicts the content exposure for a location at which no panel has been installed based on the features of that location.