AI Keyword Filtering for Relevant Digital Content Delivery

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Digital content delivery systems face inefficiencies due to outdated negative keyword lists that prevent relevant content from being delivered, leading to increased processing power and network overhead.

Innovation Solution

An AI model is trained to generate summaries of digital content providers' strategies and audiences, recommending keyword additions or removals based on relevance, with user feedback integration for fine-tuning, resulting in filtered keyword lists that reduce processing load and improve content delivery accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If negative keyword lists are expanded to cover more keywords over time, then content filtering accuracy improves, but processing overhead and computational resources increase

Engineering Contradiction:

Improvecontent filtering accuracyVSAvoidprocessing overhead

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary actions by generating AI model recommendations to filter and remove outdated keywords from negative keyword lists before they are used in content delivery operations. This proactive maintenance reduces the size of keyword lists in advance, thereby decreasing processing overhead while maintaining filtering accuracy through selective retention of relevant keywords.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If negative keyword lists are expanded to cover more keywords over time, then content filtering accuracy improves, but network overhead increases

Engineering Contradiction:

Improvecontent filtering accuracyVSAvoidnetwork overhead

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The system performs preliminary filtering using AI model recommendations to remove unnecessary keywords from negative keyword lists before deployment. This reduces the amount of data that needs to be transmitted and processed across the network, thereby decreasing network overhead while maintaining filtering accuracy through intelligent keyword selection.

Inventive Principle:

Principle #10Preliminary action

3Reliability

If keyword lists are maintained manually in line with content delivery strategy changes, then keyword relevance improves, but operational complexity and time requirements increase

Engineering Contradiction:

Improvekeyword relevanceVSAvoidmaintenance time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system implements self-service by automatically generating keyword filtering recommendations using an AI model that analyzes content delivery strategies and audience changes. This automated approach eliminates the need for manual keyword list maintenance, reducing operational complexity and time requirements while ensuring keyword lists remain relevant to current content delivery objectives.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system incorporates feedback mechanisms where user interactions and content delivery performance data are continuously analyzed by the AI model to refine keyword recommendations. This feedback loop ensures keyword lists automatically adapt to strategy changes and audience preferences without manual intervention, maintaining high relevance while minimizing maintenance time.

Inventive Principle:

Principle #23Feedback

4Productivity

If AI model recommendations are implemented to filter keyword lists, then processing efficiency improves, but risk of removing relevant keywords increases

Engineering Contradiction:

Improveprocessing efficiencyVSAvoidkeyword accuracy

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system implements a feedback mechanism where user interactions and content delivery performance data are continuously analyzed to refine AI model recommendations. This allows the system to learn from actual outcomes and adjust keyword filtering decisions, maintaining high processing efficiency while minimizing the risk of removing relevant keywords through data-driven validation.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system applies partial filtering by implementing AI model recommendations selectively rather than universally. It processes keyword lists in batches and allows for gradual implementation, enabling verification of recommendation accuracy while maintaining processing efficiency. This approach reduces the risk of erroneous removals by allowing incremental validation of the AI model's filtering decisions.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20260050628A1Keyword Filtering For Digital Content Recommendation

Publication Date: 2026.02.19 GOOGLE LLC

AI summary

Methods, systems, and apparatus, including computer-readable storage media, for keyword list filtering as part of identifying digital content responsive or relevant to a search query or request for content. A user, such as a content provider, may generate a keyword list associated with digital content of the content provider. Keyword lists, however, may be built over the course of years and can grow to include millions of keywords. Further, these keyword lists are often not maintained in line with changes in a content provider's digital content delivery strategy or context. An artificial intelligence (AI) model may be trained to generate a summary of the digital content associated with the content provider. That summary, along with the keyword list of the content provider, is provided as input into the AI model, which is trained to provide, as output, a recommendation to keep or remove a keyword from the keyword list.