Keyword Category Segmentation for Relevance Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In computer networked environments, content providers face challenges in accurately selecting relevant keywords for content items due to the overwhelming number of complexly related keywords generated using semantic relationship graphs, leading to inaccurate or irrelevant selections and increased processing power consumption.
Innovation Solution
A data processing system uses a semantic relationship graph to classify keywords into categories based on semantic distance and affinity scores, selecting keywords with scores above a threshold and indicating others as irrelevant, while adjusting scores based on frequency, placement, and normalization factors, and resolving semantic conflicts between categories.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If semantic relationship graphs are used to generate keywords, then keyword relevance is improved, but processing power consumption increases
Solution Approach 1:
The patent segments the keyword generation process by dividing keywords into different categories (e.g., navigational, transactional, informational) and applying different processing strategies to each category. This segmentation allows the system to focus computational resources on categories that require higher precision while using simpler methods for other categories, thereby reducing overall processing power consumption while maintaining keyword relevance accuracy.
Solution Approach 2:
The patent applies local quality by treating different keyword categories with different levels of processing intensity. High-value keywords that directly impact conversion receive more rigorous analysis and filtering, while less critical keywords undergo lighter processing. This localized approach to quality control optimizes the balance between measurement precision and energy consumption by concentrating computational resources where they provide the most value.
2Measurement precision
If comprehensive keyword analysis is performed, then keyword selection accuracy is improved, but processing time increases
Solution Approach 1:
The patent implements preliminary action by pre-processing and categorizing keywords before the main selection process. Keywords are预先 classified into categories and pre-filtered based on basic criteria, which reduces the computational burden during the actual keyword selection phase. This preliminary organization enables faster processing while maintaining comprehensive analysis quality for the final keyword selection.
Solution Approach 2:
The patent applies partial action by performing comprehensive analysis only on keywords that meet certain criteria or belong to specific categories, while applying simplified analysis to other keywords. This selective approach ensures that the most important keywords receive thorough analysis for high accuracy, while less critical keywords are processed more quickly, thereby reducing overall processing time without significantly compromising keyword selection accuracy for high-priority terms.
Data Source
AI summary
A server can receive a seed keyword to generate additional keywords relevant to the seed keyword. The server can identify, using a semantic relationship graph, keyword categories. Each keyword can have a semantic distance from the seed keyword less than a threshold. The server can generate, for each keyword of the keyword categories, a keyword-seed affinity score based on a frequency of the keyword occurring with the seed keyword on an information resource. The server can determine, for each keyword category, a category-seed affinity score based on the keyword-seed affinity scores for each of keyword in the keyword category. The server can compare each category-seed affinity score a threshold. The server can transmit, for display, the keywords. One keyword category can be indicated as selected and another keyword category can be indicated as unselected based on the comparison.