Wireless AP Selection via Predictive Scoring and User Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless network access technologies face challenges in efficiently selecting appropriate access points (APs) due to limitations in existing discovery and selection methods, including lack of support for advanced features like GAS/ANQP, non-transparent user preferences, and insufficient coverage by service provider policies, leading to user frustration and security risks.
Innovation Solution
A method and system that determine a recommended access point by collecting and analyzing access point feature values and user feature values, using predictive scoring based on weighting factors and models derived from collaborative filtering, to connect to the most suitable wireless network.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual AP selection is performed by users, then users can choose APs based on their needs, but the process is time-consuming and tedious
Solution Approach 1:
The system enables automatic AP selection where the wireless device autonomously evaluates multiple APs based on feature values and predicted scores, eliminating the need for manual user intervention in the selection process while still meeting user preferences
Solution Approach 2:
The patent replaces manual mechanical selection processes with an automated electronic evaluation system that uses predictive scoring models to automatically determine the optimal AP based on multiple criteria including user preferences and network conditions
2Reliability
If users manually enter credentials and payment information, then access can be obtained, but security risks increase and the process becomes vulnerable to threats
Solution Approach 1:
The system performs preliminary evaluation of AP security features and user credential requirements before the actual connection process, allowing the device to pre-determine safe APs and prepare appropriate authentication methods, thereby preventing exposure to security threats
Solution Approach 2:
The patent introduces an intermediary evaluation layer that assesses AP security characteristics and mediates the authentication process, preventing direct exposure of user credentials to potentially malicious APs by filtering and verifying AP trustworthiness first
3Measurement precision
If comprehensive AP evaluation is performed with multiple features, then selection accuracy improves, but system complexity increases
Solution Approach 1:
The patent segments the complex evaluation process into distinct feature value collection modules, each handling specific AP characteristics, and combines them through a predictive scoring system that systematically integrates multiple criteria without overwhelming system complexity
4Adaptability or versatility
If service provider policies are enforced for AP selection, then network management is improved, but coverage and adaptability are insufficient
Solution Approach 1:
The patent creates a universal AP evaluation framework that can accommodate multiple types of APs (service provider, public, private, enterprise) and various selection criteria simultaneously, making the system adaptable to diverse network environments while maintaining policy enforcement capabilities
Data Source
AI summary
A method, wireless device and computer program product determine a recommended access point (AP) for the wireless device to access a wireless network. AP feature values associated with each one of a plurality of APs within an access range of the wireless device and user feature values associated with identified user features of a user of the wireless device are obtained via a wireless interface. A predicted score for each AP is determined based on the feature values and a recommended AP is determined based on the predicted scores. The wireless device connects to the wireless network based at least in part on the recommended AP. AP feature values include AP characteristic, scheduling and payment values. User features include wireless device location and velocity, services-in-use, time of day and day of week. Optionally, circumstantial feature values may be obtained and used to determine the predicted scores.