Trained User Behavior Model for Secure Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data analysis and machine learning systems face challenges in providing secure services to users by protecting personal user data from unauthorized access, especially when user actions are analyzed remotely.
Innovation Solution
The system provides a trained model of user behavior to a computing device, which is used to identify the user without transmitting actual personal data. This model is updated and transmitted to the service, allowing for personalized content generation while maintaining data security.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If personal user data is transmitted to external services for analysis and identification, then user identification accuracy and personalized service quality improve, but information security and data protection deteriorate
Solution Approach 1:
The patent extracts only the essential behavioral patterns from user data to create behavior models, leaving the actual personal data on the user's device. The behavior model contains sufficient information for identification purposes while excluding sensitive personal information, thus achieving identification accuracy without compromising data security
Solution Approach 2:
The behavior model serves as an intermediary between user data and external services. Instead of transmitting raw personal data, the system transmits the behavior model which mediates the identification process, allowing services to analyze user behavior without direct access to personal information
2Adaptability or versatility
If user behavior data is sent to remote computing devices for analysis, then service personalization improves, but data vulnerability to unauthorized access increases
Solution Approach 1:
The system creates a copy of user behavior patterns in the form of a behavior model that can be transmitted to remote services. This copy enables personalized service delivery while the original personal data remains securely stored on the user's device, reducing vulnerability to unauthorized access
Solution Approach 2:
The patent transforms user behavior data from its original form into a behavior model with different parameters and structure. This transformation maintains the essential characteristics needed for personalization while changing the data format to reduce security risks associated with transmitting sensitive information
3Object-affected harmful factors
If trained models are used to process user data locally, then information security improves, but the ability to provide personalized services may be limited
Solution Approach 1:
The system segments the data processing functionality into two parts: local behavior model training on the user's device for security, and remote behavior model analysis for personalized service delivery. This segmentation allows both data protection and personalized services to coexist by dividing responsibilities between local and remote components
Data Source
AI summary
Disclosed herein are systems and methods for providing a trained model to a computing device of a user. In one aspect, an exemplary method comprises, receiving, by a model transmitter, registration information from the computing device of the user comprising a trained model of the user's behavior, wherein the model is constructed using software provided by a service, storing, by the model transmitter, the received registration information in a database of behavior models, and during a repeat visit, by the user, to the service, updating the trained model of the user's behavior and transmitting the updated trained model to the service, wherein the updated trained model differs from a previously sent model of the user's behavior by no more than is allowed for unambiguous identification of the user on the service.