17388942. MACHINE LEARNING BASED DYNAMIC DEMODULATOR SELECTION simplified abstract (QUALCOMM Incorporated)
MACHINE LEARNING BASED DYNAMIC DEMODULATOR SELECTION
Organization Name
Inventor(s)
Shay Landis of Hod Hasharon (IL)
Shlomit Shaked of Rosh Haayin (IL)
MACHINE LEARNING BASED DYNAMIC DEMODULATOR SELECTION - A simplified explanation of the abstract
This abstract first appeared for US patent application 17388942 titled 'MACHINE LEARNING BASED DYNAMIC DEMODULATOR SELECTION
Simplified Explanation
The abstract describes a patent application for a system that allows a user's device to select the best demodulator based on machine learning model coefficients trained by a base station. Here is a simplified explanation of the abstract:
- User equipment can select the most suitable demodulator using machine learning model coefficients trained by a base station.
- The user equipment sends a dynamic demodulator indication to the base station.
- The user equipment also transmits channel information to the base station.
- In response to the dynamic demodulator indication, the user equipment receives updated coefficient information from the base station based on the channel information.
- The user equipment then selects a demodulator based on the updated coefficient information.
- Finally, the user equipment communicates with the base station using the selected demodulator.
Potential Applications
This technology can have various applications, including:
- Wireless communication systems: The system can be used in wireless networks to improve the selection of demodulators, leading to better communication performance.
- Internet of Things (IoT): IoT devices can benefit from this technology by optimizing their demodulator selection, resulting in improved connectivity and reliability.
- Mobile devices: Smartphones and tablets can utilize this system to enhance their wireless communication capabilities, leading to better network performance and user experience.
Problems Solved
This technology addresses the following problems:
- Suboptimal demodulator selection: Traditional systems may not always select the most suitable demodulator, leading to reduced communication performance.
- Channel variations: Wireless channels can experience fluctuations in quality, and this system helps adapt the demodulator selection based on updated coefficient information to mitigate the impact of channel variations.
- Limited resources: By utilizing machine learning and dynamic demodulator selection, this system optimizes the use of available resources, improving overall efficiency.
Benefits
The benefits of this technology include:
- Improved communication performance: By selecting the most suitable demodulator, the system enhances the quality and reliability of wireless communication.
- Adaptability to channel conditions: The system can dynamically adjust the demodulator selection based on updated coefficient information, ensuring optimal performance even in varying channel conditions.
- Resource optimization: By utilizing machine learning and dynamic selection, the system optimizes the use of available resources, leading to improved efficiency and reduced waste.
Original Abstract Submitted
A user equipment may be configured to perform demodulator selection based on ML model coefficients trained by a base station. In some aspects, the user equipment may transmit a dynamic demodulator indication to a base station, transmit channel information to the base station, and receive, in response to the dynamic demodulator indication, updated coefficient information based on the channel information. Further, the user equipment may select a demodulator based on the updated coefficient information, and communicate with the base station via the demodulator in response to the selection of the demodulator.
