17949331. SYSTEMS AND METHODS FOR PREDICTING OCCUPANCY FOR ONE BUILDING USING A MODEL TRAINED AT ANOTHER BUILDING simplified abstract (HONEYWELL INTERNATIONAL INC.)

SYSTEMS AND METHODS FOR PREDICTING OCCUPANCY FOR ONE BUILDING USING A MODEL TRAINED AT ANOTHER BUILDING

Organization Name

HONEYWELL INTERNATIONAL INC.

Inventor(s)

Rohil Pal of Lal Bangla Kanpur (IN)

Navneet Kumar of Gurgaon (IN)

Deepika Sandeep of Bangalore (IN)

Prabhat Ranjan of Bangalore (IN)

Bhavesh Gupta of Niantic CT (US)

SYSTEMS AND METHODS FOR PREDICTING OCCUPANCY FOR ONE BUILDING USING A MODEL TRAINED AT ANOTHER BUILDING - A simplified explanation of the abstract

This abstract first appeared for US patent application 17949331 titled 'SYSTEMS AND METHODS FOR PREDICTING OCCUPANCY FOR ONE BUILDING USING A MODEL TRAINED AT ANOTHER BUILDING

Simplified Explanation

The abstract describes a patent application for a Building Management System (BMS) that can be controlled based on predicted occupancy using a trained model. The model is trained using environmental data and corresponding occupancy data from a training building, and then used to predict occupancy in a use building based on environmental data alone.

• Trained model predicts occupancy based on environmental data and occupancy data from a training building.
• Use building's BMS is controlled based on predicted occupancy value from the trained model.

Potential Applications

This technology could be applied in various industries such as commercial real estate, hospitality, and healthcare to optimize building management systems based on predicted occupancy.

Problems Solved

This technology helps in efficiently managing building systems by predicting occupancy without the need for occupancy data in the use building, reducing the reliance on manual adjustments.

Benefits

The benefits of this technology include improved energy efficiency, enhanced comfort for occupants, and streamlined building management processes.

Potential Commercial Applications

One potential commercial application of this technology could be in smart buildings and IoT systems for predictive building management based on occupancy predictions.

Possible Prior Art

Prior art in this field may include research on predictive modeling for building management systems and occupancy prediction algorithms.

How does the trained model handle variations in occupancy patterns between the training building and the use building?

The trained model may need to be fine-tuned or adjusted to account for differences in occupancy patterns between buildings.

What are the potential limitations of using environmental data alone to predict occupancy in a building?

Using only environmental data may not capture all factors influencing occupancy, such as special events or unexpected changes in occupancy patterns.

Original Abstract Submitted

A Building Management System (BMS) may be controlled in accordance with predicted occupancy using a trained model. A model is trained by providing the model with time stamped environmental data and corresponding time stamped occupancy data pertaining to a training building, wherein the time stamped environmental data is derived from one or more environmental sensors of the training building and the corresponding time stamped occupancy data is derived from one or more occupancy sensors of the training building. Once trained, the trained model is provided with time stamped environmental data for a use building that is derived from one or more environmental sensors of the use building. Occupancy data for the use building is not required. The trained model outputs a predicted occupancy value that represents a predicted occupancy count in the use building, and the BMS of the use building is controlled based at least in part on the predicted occupancy value.