Automated Call Filtering via Sensor Telemetry and Scoring

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for blocking unwanted telephone calls are inadequate, as they often restrict desired calls while allowing junk calls to pass through, and manual management of whitelists and blacklists is cumbersome and ineffective.

Innovation Solution

A network-oriented, automated system that scores incoming calls based on predetermined criteria, including sensor data and user-defined modes, to classify and reject unwanted calls, using a processor to compare scores to a threshold and selectively block or allow calls, with the option to add callers to whitelists or blacklists.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual whitelists and blacklists are used to filter calls, then some unwanted calls can be blocked, but the system becomes cumbersome and inaccurate due to manual management requirements

Engineering Contradiction:

Improvecall filtering accuracyVSAvoidmanual management complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system automatically manages call filtering by self-learning from user interactions and call patterns, eliminating the need for manual whitelist/blacklist management. The machine learning model continuously improves filtering accuracy autonomously based on user feedback and call behavior analysis.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical list management with an automated machine learning system that uses algorithms to analyze call patterns, predict unwanted calls, and dynamically adjust filtering criteria without human intervention.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Object-affected harmful factors

If blacklists are used to block unwanted calls, then known spam numbers can be rejected, but too many legitimate calls are also blocked due to incomplete blacklist coverage

Engineering Contradiction:

Improveunwanted call blockingVSAvoidlegitimate call delivery

Core Design Contradiction:

Object-affected harmful factorsVSReliability

Solution Approach 1:

The system performs preliminary analysis of call patterns and caller behavior before the call reaches the user. By predicting unwanted calls in advance using machine learning models that analyze calling patterns, timing, and recipient behavior, the system can prevent unwanted calls while preserving legitimate communications.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system continuously learns from user interactions with filtered calls, adjusting its predictions based on feedback. When users interact with filtered calls, the system uses this feedback to refine its machine learning models, improving accuracy over time and reducing false positives.

Inventive Principle:

Principle #23Feedback

3Reliability

If whitelists are used to allow only known acceptable callers, then desired calls are ensured to reach users, but the system becomes too restrictive and blocks legitimate calls from new or unknown sources

Engineering Contradiction:

Improvedesired call deliveryVSAvoidcall source flexibility

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system dynamically adjusts filtering thresholds and criteria based on changing call patterns and user behavior. Rather than static whitelists, the machine learning model continuously adapts to new legitimate callers and evolving communication patterns, maintaining flexibility while ensuring reliability.

Inventive Principle:

Principle #15Dynamics

4Measurement precision

If automated scoring systems are implemented, then call filtering accuracy is improved, but the system complexity increases

Engineering Contradiction:

Improvecall desirability assessmentVSAvoidautomation system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The machine learning system performs self-training and automatic optimization based on call data and user interactions. The system self-adjusts its scoring criteria and prediction models without requiring complex manual configuration or external intervention, reducing operational complexity while maintaining high measurement precision.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS9560198B2Identifying and filtering incoming telephone calls to enhance privacy

Publication Date: 2017.01.31 OOMA INC

AI summary

A computer-implemented method for filtering a telephone call is provided. The method may comprise: receiving from a caller the telephone call directed to a communication device associated with an intended call recipient, the Internet being disposed between a computer implementing the method and the communication device, the intended call recipient being in a structure; determining a state of the intended call recipient using telemetry received from at least one of a sensor and an appliance disposed in the structure; scoring the telephone call based on predetermined scoring criteria to create a score indicative of a desirability of the telephone call, the predetermined scoring criteria being provided by the intended call recipient, the predetermined scoring criteria including the state of the intended call recipient; comparing the score to a predetermined threshold score; classifying the telephone call as an unwanted telephone call using the comparison; and selectively rejecting the unwanted telephone call.