Keyword Generation Using Machine Learning for Content Relevance

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing keyword selection and optimization methods for content providers rely heavily on user search queries, which may not provide optimal results for content providers looking to improve their search engine optimization and reach their targeted audience effectively.

Innovation Solution

A computing system utilizing machine-learned techniques to generate keywords by processing data from third-party content providers, calculating similarity scores, and suggesting keywords that are more relevant to the content provider's products or services.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If keyword selection is based on user search queries, then keyword coverage is improved, but keyword relevance to content provider's products or services deteriorates

Engineering Contradiction:

Improvekeyword coverageVSAvoidkeyword relevance

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

Instead of deriving keywords from user search queries (traditional approach), the system inverts the approach by generating keywords from the content provider's own content data and product information. This ensures keywords are inherently relevant to the content provider's offerings while still capturing search intent through machine learning analysis of successful third-party keywords.

Inventive Principle:

Principle #13The other way round (Inversion)

Solution Approach 2:

The system introduces machine learning models as an intermediary between content provider data and keyword generation. The ML models analyze both the content provider's content and third-party successful keywords to generate optimized keywords that balance relevance and coverage, resolving the contradiction between these two opposing requirements.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If manual keyword selection is used, then keyword relevance is improved, but time consumption and operational complexity deteriorates

Engineering Contradiction:

Improvekeyword relevanceVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system enables automated keyword generation that serves itself by using the content provider's existing content data as input. The machine learning model automatically processes this data, analyzes patterns, and generates optimized keywords without requiring manual intervention, thus maintaining high relevance while eliminating time consumption and operational complexity.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system replaces the manual mechanical process of keyword selection with an automated machine learning-based system. This substitution maintains or improves keyword relevance through intelligent analysis while dramatically reducing the time and effort required, as the ML model processes data and generates keywords automatically without human intervention.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If automated keyword generation is used, then productivity is improved, but keyword quality and precision deteriorates

Engineering Contradiction:

Improvekeyword generation efficiencyVSAvoidkeyword quality

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system performs preliminary analysis of the content provider's content data and product information before generating keywords. The machine learning model pre-processes and understands the content semantics, ensuring that the subsequently generated keywords are both efficient to produce and high in quality and precision, rather than being randomly generated.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system incorporates feedback mechanisms where the ML model analyzes the performance and effectiveness of generated keywords, using this feedback to continuously improve future keyword generation. This ensures that automated generation maintains high productivity while progressively improving keyword quality and precision based on real-world performance data.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20250110978A1Automated Content Presentation Based on a Determined Keyword

Publication Date: 2025.04.03 GOOGLE LLC

AI summary

Methods, computing systems, and technology for using machine-learned techniques for determining a keyword for a web resource, and automating content presentation for the web resource. The system can receive, from a user device of a first content provider, a request associated with a web resource having a plurality of assets. Additionally, the system can determine, based on the plurality of assets, a first keyword associated with the web resource. Moreover, the system can determine, based on a first keyword cluster associated with the first keyword, the first keyword being associated with a first query cluster having a query performance metric. Furthermore, the system can process, using a machine-learned forecasting model, the first keyword and the first query cluster to generate a keyword performance metric for the first keyword. Subsequently, the system can perform an action based on the keyword performance metric associated with the first keyword.