Keyword Graph Clustering for Search Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems fail to accurately classify keywords and keyword sequences, leading to incorrect categorization, which affects the performance of search algorithms, machine learning models, and search engine marketing, resulting in unpredictable ad behavior and irrelevant results.
Innovation Solution
A system that determines interaction metrics between keywords, constructs a graph with nodes representing keywords, identifies clusters, optimizes these clusters, and uses them to alter the graphical user interface, ensuring more accurate keyword classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If keywords are classified based on search engine results, then classification can be performed using available data, but classification accuracy deteriorates leading to incorrect categorization
Solution Approach 1:
The patent introduces an intermediary classification system that uses co-occurrence analysis and graph-based clustering as a mediator between raw search data and final keyword classification. This intermediary process analyzes multiple keywords together and their relationships, rather than classifying individual keywords based solely on search results, thereby improving accuracy while maintaining ease of classification
Solution Approach 2:
The system implements feedback mechanisms where classification results are continuously refined through iterative optimization. The graph-based approach allows the system to feedback on cluster quality and adjust classifications accordingly, improving accuracy over time while maintaining an automated classification process
2Device complexity
If traditional keyword classification is used, then processing is simpler, but downstream performance deteriorates in search algorithms and machine learning models
Solution Approach 1:
The patent segments the keyword classification problem into distinct components: co-occurrence analysis, graph construction, cluster identification, and optimization. This segmentation allows each component to be processed independently with appropriate algorithms, improving downstream performance while managing complexity through modular processing steps
Solution Approach 2:
The system transitions from traditional single-dimension keyword classification to a multi-dimensional approach by constructing graphs that capture relationships between keywords. This dimensional change from scalar classification to graph-based clustering enables more accurate representations that improve search algorithms and machine learning model performance
3Measurement precision
If accurate keyword classification is implemented through graph clustering, then classification precision is improved, but computational complexity increases
Solution Approach 1:
The patent applies preliminary actions by pre-processing keywords to identify co-occurrences and construct the graph structure before performing clustering. This preliminary organization of data into meaningful relationships reduces the computational complexity of the actual clustering operation while maintaining high classification precision
Solution Approach 2:
The system changes parameters by adjusting graph construction thresholds, clustering algorithms, and optimization criteria to balance precision and computational complexity. By tuning these parameters, the system achieves accurate classification while managing computational resources effectively
Data Source
AI summary
Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform determining a respective interaction metric between at least two respective keywords of a plurality of keywords; constructing, using each respective interaction metric, as determined, a graph comprising a plurality of nodes connected by at least one edge; identifying one or more clusters of nodes using the graph; optimizing each cluster of nodes of the one or more clusters of nodes; and facilitating altering a graphical user interface (GUI) of an electronic device based upon a cluster of nodes of the one or more clusters of nodes, as identified and optimized. Other embodiments are disclosed herein.