18156997. SYSTEMS USING HASH KEYS TO PRESERVE PRIVACY ACROSS MULTIPLE TASKS simplified abstract (Capital One Services, LLC)
Contents
SYSTEMS USING HASH KEYS TO PRESERVE PRIVACY ACROSS MULTIPLE TASKS
Organization Name
Inventor(s)
Omar Florez Choque of Oakland CA (US)
Erik Mueller of Chevy Chase MD (US)
SYSTEMS USING HASH KEYS TO PRESERVE PRIVACY ACROSS MULTIPLE TASKS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18156997 titled 'SYSTEMS USING HASH KEYS TO PRESERVE PRIVACY ACROSS MULTIPLE TASKS
Simplified Explanation
The abstract describes a system that uses hash keys to protect privacy across multiple tasks. Here is a simplified explanation of the abstract:
- The system receives training batches of input observations, each containing a customer request and a stored task.
- It assigns a hash key to each stored task.
- When a new batch of input observations with a new customer request and task is received, the system sends it to an encoder.
- The encoder generates a new hash key for the new customer request and checks if any existing hash key matches it.
- If a match is found, the system associates the new batch of input observations with the corresponding hash key and updates the hash key to provide access to the new batch.
- If no match is found, the system generates a new stored task and assigns the new hash key to it.
Potential applications of this technology:
- Privacy-preserving machine learning systems
- Secure data sharing across multiple tasks
- Collaborative learning environments
Problems solved by this technology:
- Protecting privacy by using hash keys to associate data without revealing sensitive information
- Efficiently managing and updating access to data across multiple tasks
Benefits of this technology:
- Enhanced privacy protection for sensitive data
- Improved efficiency in managing and accessing data across different tasks
- Facilitates secure collaboration and sharing of data in machine learning environments.
Original Abstract Submitted
A system for using hash keys to preserve privacy across multiple tasks is disclosed. The system may provide training batch(es) of input observations each having a customer request and stored task to an encoder, and assign a hash key(s) to each of the stored tasks. The system may provide a new batch of input observations with a new customer request and new task to the encoder. The encoder may generate a new hash key assigned to the new customer request and determine whether any existing hash key corresponds with the new hash key. If so, the system may associate the new batch of input observations with the corresponding hash key and update the corresponding hash key such that it is also configured to provide access to the new batch of input observations. If not, the system may generate a new stored task and assign the new hash key to it.
