Behavioral Analysis Engine for Wireless Subscriber Profiling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current web usage tracking technologies fail to provide detailed, individual-level insights into subscriber behavior, primarily focusing on aggregate reporting at the website or product level, which limits understanding and differentiation of wireless subscribers.
Innovation Solution
A behavioral engine that collects, categorizes, and analyzes subscriber data from various sources, including mobile web requests and content purchases, using a common set of categories to create detailed subscriber profiles, enabling precise tracking and application of business rules for marketing, customer service, and product development.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If aggregate reporting at website or product level is used, then reporting simplicity is improved, but subscriber differentiation capability deteriorates
Solution Approach 1:
The patent segments subscriber behavior data into multiple dimensions including website category, content type, service type, and temporal patterns. Each behavior record is divided into discrete categorical attributes that can be independently analyzed and recombined, enabling both simple aggregate reporting and detailed individual subscriber profiling simultaneously.
Solution Approach 2:
The patent adds multiple categorical dimensions to the reporting framework, transforming one-dimensional aggregate reports into multi-dimensional behavioral profiles. By categorizing behaviors across website categories, content types, services, and time patterns, the system enables precise subscriber differentiation while maintaining reporting simplicity through standardized categorical frameworks.
2Loss of information
If detailed individual-level behavioral tracking is implemented, then subscriber understanding is improved, but data processing complexity deteriorates
Solution Approach 1:
The patent transforms continuous behavioral data into discrete categorical parameters. By converting raw behavior records into standardized categories (website category, content type, service type, temporal patterns), the system reduces data complexity while preserving essential behavioral information, making detailed subscriber understanding achievable without proportionally increasing processing complexity.
Solution Approach 2:
The patent introduces categorical frameworks as intermediary layers between raw behavior data and analysis applications. These categories act as mediators that structure and organize detailed behavioral information, reducing the complexity of processing individual-level data while maintaining comprehensive subscriber understanding.
3Adaptability or versatility
If multiple behavior record types are categorized using a common framework, then system versatility is improved, but categorization complexity deteriorates
Solution Approach 1:
The patent creates a universal categorical framework that handles multiple types of behavior records (website visits, content purchases, service usage) through a unified classification system. The same category structures and processing logic apply across all behavior types, enabling the system to accommodate diverse data sources and future extensions without proportionally increasing categorization complexity.
Data Source
AI summary
A method and system are disclosed for behavioral analysis for profiling wireless subscribers. The method includes loading carrier reference data comprising a set of common categories and loading a plurality of behavior records of at least two types, wherein each behavior record is generated by a mobile device activity of a subscriber. The method proceeds by associating each behavior record with one or more of the categories, thereby generating categorized data records. Finally each category associated with a behavior record is added to a subscriber profile for the subscriber whose activity generated the behavior record.