18489617. SELECTIVE TRIGGERING OF NEURAL NETWORK FUNCTIONS FOR POSITIONING MEASUREMENT FEATURE PROCESSING AT A USER EQUIPMENT simplified abstract (QUALCOMM Incorporated)

SELECTIVE TRIGGERING OF NEURAL NETWORK FUNCTIONS FOR POSITIONING MEASUREMENT FEATURE PROCESSING AT A USER EQUIPMENT

Organization Name

QUALCOMM Incorporated

Inventor(s)

Jay Kumar Sundararajan of San Diego CA (US)

Krishna Kiran Mukkavilli of San Diego CA (US)

Taesang Yoo of San Diego CA (US)

Naga Bhushan of San Diego CA (US)

June Namgoong of San Diego CA (US)

Pavan Kumar Vitthaladevuni of San Diego CA (US)

Tingfang Ji of San Diego CA (US)

SELECTIVE TRIGGERING OF NEURAL NETWORK FUNCTIONS FOR POSITIONING MEASUREMENT FEATURE PROCESSING AT A USER EQUIPMENT - A simplified explanation of the abstract

This abstract first appeared for US patent application 18489617 titled 'SELECTIVE TRIGGERING OF NEURAL NETWORK FUNCTIONS FOR POSITIONING MEASUREMENT FEATURE PROCESSING AT A USER EQUIPMENT

Simplified Explanation

The abstract of this patent application describes a system where a user equipment (UE) obtains information associated with a set of triggering criteria for a set of neural network functions. These neural network functions are dynamically generated based on machine learning from historical measurement procedures. The UE also obtains positioning measurement data and processes it into positioning measurement features using the triggered neural network functions.

• The patent application describes a system where a UE obtains information associated with triggering criteria for neural network functions.
• The neural network functions are dynamically generated based on machine learning from historical measurement procedures.
• The UE obtains positioning measurement data and processes it into positioning measurement features using the triggered neural network functions.
• The neural network functions facilitate positioning measurement feature processing at the UE.
• The system allows for the efficient processing of positioning measurement data using machine learning and neural networks.

Potential applications of this technology:

• Location-based services: The system can be used to improve the accuracy and efficiency of location-based services on mobile devices.
• Autonomous vehicles: The technology can be applied to enhance the positioning capabilities of autonomous vehicles, improving their navigation and safety.
• Asset tracking: The system can be used to track the location of assets in real-time, enabling better inventory management and logistics.

Problems solved by this technology:

• Inefficient positioning measurement processing: The system addresses the problem of inefficient processing of positioning measurement data by dynamically generating neural network functions based on machine learning.
• Inaccurate location information: By using machine learning and neural networks, the system improves the accuracy of positioning measurement features, leading to more accurate location information.

Benefits of this technology:

• Improved accuracy: The use of machine learning and neural networks enhances the accuracy of positioning measurement features, resulting in more precise location information.
• Efficient processing: The dynamic generation of neural network functions based on machine learning allows for efficient processing of positioning measurement data.
• Enhanced user experience: The technology improves the performance of location-based services and other applications that rely on accurate positioning information, leading to a better user experience.

Original Abstract Submitted

In an aspect, a UE obtains information (e.g., UE-specific information) associated with a set of triggering criteria (e.g., from a server, a serving network, e.g., in conjunction with or separate from a set of neural network functions) for a set of neural network functions, the set of neural network functions configured to facilitate positioning measurement feature processing at the UE, the set of neural network functions being generated dynamically based on machine-learning associated with one or more historical measurement procedures. The UE obtains positioning measurement data associated with a location of the UE, and processes the positioning measurement data into a respective set of positioning measurement features based at least in part upon the positioning measurement data and at least one neural network function from the set of neural network functions that is triggered by at least one triggering criterion from the set of triggering criteria.