View source for 20240054322. Targeted Energy Usage Device Presence Detection Using Multiple Trained Machine Learning Models simplified abstract (Oracle International Corporation)

=Targeted Energy Usage Device Presence Detection Using Multiple Trained Machine Learning Models=


==Organization Name==

[[:Category:Oracle International Corporation|Oracle International Corporation]]


[[Category:Oracle International Corporation]]

==Inventor(s)==

[[:Category:Jessica Lin of Virginia Beach VA (US)|Jessica Lin of Virginia Beach VA (US)]][[Category:Jessica Lin of Virginia Beach VA (US)]]

[[:Category:Anastasiia Pirus of Kharkiv (UA)|Anastasiia Pirus of Kharkiv (UA)]][[Category:Anastasiia Pirus of Kharkiv (UA)]]

[[:Category:Serhii Kravchenko of Velikyi Dalnik (UA)|Serhii Kravchenko of Velikyi Dalnik (UA)]][[Category:Serhii Kravchenko of Velikyi Dalnik (UA)]]

[[:Category:Andrii Zagoruiko of Vrsovice (CZ)|Andrii Zagoruiko of Vrsovice (CZ)]][[Category:Andrii Zagoruiko of Vrsovice (CZ)]]

[[:Category:Dmytro Ielkin of Odesa (UA)|Dmytro Ielkin of Odesa (UA)]][[Category:Dmytro Ielkin of Odesa (UA)]]

[[:Category:Oleksandr Bielov of Odesa (UA)|Oleksandr Bielov of Odesa (UA)]][[Category:Oleksandr Bielov of Odesa (UA)]]

[[:Category:Oleksandr Annenkov of Zaporizhzhya (UA)|Oleksandr Annenkov of Zaporizhzhya (UA)]][[Category:Oleksandr Annenkov of Zaporizhzhya (UA)]]

[[:Category:Serhii Derevianko of Odesa (UA)|Serhii Derevianko of Odesa (UA)]][[Category:Serhii Derevianko of Odesa (UA)]]

[[:Category:Saak Akopov of Kyiv (UA)|Saak Akopov of Kyiv (UA)]][[Category:Saak Akopov of Kyiv (UA)]]

==Targeted Energy Usage Device Presence Detection Using Multiple Trained Machine Learning Models - A simplified explanation of the abstract==


This abstract first appeared for US patent application 20240054322 titled 'Targeted Energy Usage Device Presence Detection Using Multiple Trained Machine Learning Models

==Simplified Explanation==

The patent application describes a method for generating machine learning predictions to discover targeted device energy usage in households.

* Embodiments train a first machine learning model to predict the presence of a first device in households.
* The training data used for the first machine learning model is not sufficient for a second device, so embodiments train a second machine learning model to predict the presence of the second device.
* Input data of household energy use and weather data is received, and the trained models are used to predict the presence of the first and second devices in each household.
* By subtracting the households predicted to have the second device from those predicted to have the first device, a prediction of households that have the first device is generated.

---

### Potential Applications
* Energy management systems for households
* Targeted marketing for energy-efficient devices
* Demand forecasting for energy consumption

### Problems Solved
* Identifying specific devices contributing to energy usage in households
* Improving accuracy of predictions for different types of devices
* Optimizing energy efficiency strategies based on device presence

### Benefits
* Enhanced energy monitoring and management
* Tailored recommendations for energy-saving measures
* Increased understanding of household energy consumption patterns


==Original Abstract Submitted==

embodiments generate machine learning predictions to discover targeted device energy usage. embodiments train a first machine learning model to predict a presence of a first device, where a training data used to train the first machine is deficient for a second device. embodiments train a second machine learning model to predict a presence of a second device. embodiments receive input data of household energy use and weather data and, based on the input data, use the trained first machine learning model to predict the presence of the first device per household. based on the input data, embodiments use the trained second machine learning model to predict the presence of the second device per household. embodiments then subtract the households predicted to have the second device from the households predicted to have the first device to generate a prediction of households that have the first device.



[[Category:G06N3/04]]
[[Category:G06N3/08]]