Cognitive Computing Service for Dynamic Spam Call Screening

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current spam call screening technologies rely on static blacklists and do not adapt to changing circumstances, such as phone number changes or emergency situations, failing to effectively differentiate between legitimate and unwanted calls.

Innovation Solution

A cognitive computing platform that analyzes caller details, user preferences, and past behavior to determine whether to accept or reject incoming calls, using machine learning, natural language processing, and voice signature recognition to provide personalized call screening decisions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If static blacklists are used for spam call screening, then implementation simplicity is improved, but adaptability to changing circumstances deteriorates

Engineering Contradiction:

Improveimplementation simplicityVSAvoidadaptability to changing circumstances

Core Design Contradiction:

Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The system transitions from static blacklists to dynamic cognitive computing platforms that continuously learn from user behavior patterns. The cognitive computing service analyzes caller details, call logs, and user interactions to dynamically update screening decisions, enabling the system to adapt to changing circumstances such as phone number changes and emergency situations while maintaining automated operation.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback loops where user interactions with calls are analyzed by the cognitive computing service to refine future screening decisions. The system learns from user behavior patterns and adjusts its call acceptance/rejection algorithms accordingly, improving adaptability while maintaining automated operation through continuous iterative improvement.

Inventive Principle:

Principle #23Feedback

2Measurement precision

If cognitive computing platforms analyze caller details and user behavior, then call acceptance and rejection accuracy is improved, but system complexity increases

Engineering Contradiction:

Improvecall acceptance and rejection accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The cognitive computing service acts as an intermediary layer between the telecommunication infrastructure and the user's call screening decisions. It receives caller details from the telecommunication system, processes them through machine learning models and natural language processing, and returns screening recommendations, thereby achieving high accuracy without requiring complex direct user intervention.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system replaces manual user judgment and simple blacklist mechanisms with automated cognitive computing processes. Machine learning algorithms and natural language processing models substitute for human decision-making in call screening, achieving higher accuracy while managing complexity through intelligent automation rather than straightforward mechanical rules.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Reliability

If the system learns from user interactions and adapts to changing circumstances, then spam call filtering effectiveness is improved, but processing time increases

Engineering Contradiction:

Improvespam call filtering effectivenessVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The cognitive computing service performs preliminary analysis of caller details and compares them against pre-processed call log information and user behavior patterns before final screening decisions are made. This preliminary processing of historical data enables faster real-time decisions while maintaining high filtering effectiveness through pre-computed patterns and models.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS10057419B2Intelligent call screening

Publication Date: 2018.08.21 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A computer receives an incoming call by a cognitive computing service. The computer determines, by the cognitive computing service (CCS), caller details that the incoming call is not within intended recipient preferences, based on comparing the caller details to call log information database and call information database, wherein the call log information database and call information database comprises previous caller details. The computer references, by the CCS, additional caller details from the call log information database and call information database relating to the caller details. The computer determines whether an intended recipient of the incoming call would reject the incoming call and based on the computer determination that the intended recipient of the incoming call would reject the incoming call the computer rejects the incoming call.