Trust Score Call Processing Using Messaging Patterns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Despite advancements in filtering techniques, unwanted messages such as spam continue to increase, and existing methods require complex keyword and character string specifications, making them inefficient against constantly evolving spammer tactics.
Innovation Solution
A method and system that utilize 'trust scores' based on messaging patterns to filter incoming communications, allowing users to control call processing by assigning a numerical or categorical score to messages, determining their legitimacy and relevance, and automatically taking actions such as blocking or forwarding based on pre-defined thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If rules-based filtering with keywords and character strings is used, then filtering capability is provided, but the system becomes complex and ineffective against evolving spam tactics
Solution Approach 1:
The patent changes the filtering parameter from static keywords and character strings to dynamic trust scores that are continuously updated based on messaging patterns. This allows the system to adapt to evolving spam tactics without increasing complexity, as the trust score mechanism automatically adjusts to new patterns through behavioral analysis rather than requiring manual rule updates
Solution Approach 2:
The filtering system performs self-service by automatically calculating trust scores based on observed messaging patterns without requiring manual configuration of filtering rules. The system learns and adapts autonomously by monitoring communication behaviors and adjusting trust scores accordingly, eliminating the need for complex manual rule maintenance
2Adaptability or versatility
If manual specification of filtering rules is required, then filtering can be customized, but user burden increases and operation becomes complex
Solution Approach 1:
The system provides automatic customization by computing trust scores based on messaging patterns without requiring users to manually specify filtering rules. Users simply set a threshold trust score, and the system automatically adapts the filtering behavior based on observed communication patterns, making the system both versatile and easy to operate
Solution Approach 2:
The system changes from requiring multiple specific filtering parameters (keywords, character strings, email addresses) to a single threshold trust score parameter. This simplifies user operation while maintaining adaptability, as the trust score mechanism internally handles the complexity of pattern recognition and filtering decision-making
Data Source
AI summary
Messaging patterns for a plurality of subscribers are obtained and analyzed to determine a “trust score” that is an indication of the likelihood that a given message for a particular subscriber is of interest, as opposed to unwanted, e.g., spam or telemarketing phone calls. Subscribers establish or set trust score thresholds and call processing actions to take based on the thresholds and the trust score for a given incoming communication. For example, if a subscriber establishes a processing action of “block call” for calls with a “low” threshold trust score, and an incoming message (email, SMS, instant message, or phone call) has a trust score of “low” or “very low”, the message is blocked. Conversely, if the trust score for the message is “high” and the user has specified to pass through “high” trust score messages, the message is passed through. Various algorithms can be used compute trust scores based on messaging patterns.