Forced Web Traffic Detection and Filtering System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods fail to effectively identify and filter non-intentional or forced network traffic data from streaming network data, which contaminates user behavior analysis and targeting models in advertising campaigns, particularly unable to detect new network locations with high forced access rates and those monetizing forced traffic.
Innovation Solution
A processor-readable medium with code to filter data associated with entities accessing preselected network locations with forced web traffic patterns, using predefined time periods and behavior models to differentiate between intentional and non-intentional traffic, thereby modifying filtering rules based on access patterns and traffic analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If known methods are used to monitor network locations with high forced access rates, then existing forced traffic can be detected, but new network locations with high forced access rates cannot be identified
Solution Approach 1:
The system dynamically updates the set of preselected network locations based on continuously analyzed access patterns. Rather than using a static list of known forced traffic locations, the system adapts to identify new network locations exhibiting forced access patterns by monitoring behavioral characteristics such as multiple accesses within predefined time periods, enabling detection of both existing and emerging forced traffic sources
Solution Approach 2:
The system implements feedback loops where access data is continuously collected, analyzed for forced traffic patterns, and used to update filtering rules and expand the set of preselected network locations. This feedback mechanism allows the system to learn from new forced traffic sources and automatically adjust its detection capabilities without manual intervention
2Measurement precision
If streaming network data is analyzed in real time to filter forced traffic, then user behavior analysis accuracy improves, but processing complexity and computational resources increase
Solution Approach 1:
The system preselects network locations that are likely to generate forced traffic based on initial analysis or known patterns, creating a predefined set of monitoring targets. By focusing computational resources on these preidentified locations rather than analyzing all network traffic equally, the system reduces processing complexity while maintaining high detection accuracy for forced traffic patterns
Solution Approach 2:
The system applies filtering rules selectively to data associated with entities accessing preselected network locations, rather than uniformly processing all network data. This partial action approach concentrates computational effort where forced traffic is most likely to occur, improving efficiency while maintaining comprehensive monitoring capability
3Object-affected harmful factors
If filtering rules are applied to all network data, then forced traffic is removed, but legitimate user data is also lost
Solution Approach 1:
The system applies filtering rules locally and selectively only to data associated with entities that have accessed preselected network locations known or suspected to generate forced traffic. Legitimate user data from other network locations or from users without suspicious access patterns is preserved without filtering, maintaining data quality while eliminating forced traffic contamination
4Reliability
If multiple accesses by an entity to preselected network locations are monitored, then forced traffic patterns are detected, but false positives from legitimate users may occur
Solution Approach 1:
The system dynamically adjusts filtering decisions based on the temporal patterns and frequency of accesses to preselected network locations. By analyzing whether multiple accesses occur within predefined time periods and comparing against behavioral baselines, the system can distinguish between forced traffic patterns (which typically show repetitive, unnatural access patterns) and legitimate user behavior (which shows more varied and purposeful access patterns), reducing false positives while maintaining detection reliability
Data Source
AI summary
A non-transitory processor-readable medium is provided that stores code representing instructions to be executed by a processor to filter data associated with an entity for a first predefined time period in response to an access by the entity at a first time to a preselected network location from a plurality of preselected network locations. The plurality of preselected network locations are associated with forced web traffic patterns. The processor is also caused to filter data associated with the entity for a second predefined time period in response to an access by the entity at a second time to a preselected network location from the plurality of preselected network locations during the first predefined time period. The second time is after the first time.