Keyword Priority Scoring via Popularity-Relevance Multiplication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing on-line social network systems face challenges in effectively prioritizing keywords for job search results, as current methods rely solely on the number of job postings containing a keyword, which can lead to over-utilized keywords like 'assistant' being prioritized unnecessarily, affecting the relevance of search results.
Innovation Solution
Implementing a search engine optimization (SEO) system that calculates priority scores for keywords by multiplying their popularity scores by relevance scores, using a probabilistic model that considers how likely a keyword is to be included in a search query and produce relevant results, and incorporating user engagement signals and profile data to refine these scores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If keyword prioritization is based solely on the number of job postings containing the keyword, then the implementation is simple and straightforward, but the relevance of search results deteriorates due to over-utilized keywords being prioritized unnecessarily
Solution Approach 1:
The patent changes the parameter for keyword prioritization from a single metric (number of job postings) to a composite metric combining multiple parameters: popularity score (frequency in search queries), relevance score (quality of matching job postings), and user engagement signals. This multi-parameter approach resolves the contradiction by maintaining implementation feasibility while significantly improving search result relevance through the formula: priority score = popularity score × relevance score
Solution Approach 2:
The patent creates a composite scoring system that combines multiple independent scoring components (popularity, relevance, user engagement) into a unified priority score for keywords. This composite approach allows the system to capture multiple dimensions of keyword value simultaneously, improving measurement precision without excessive complexity increase
2Device complexity
If the system prioritizes keywords with high frequency in job postings, then the system complexity remains low, but the quality of job search results deteriorates due to irrelevant keywords being over-prioritized
Solution Approach 1:
The patent segments the keyword scoring process into distinct independent components: popularity score calculation (based on search query frequency), relevance score calculation (based on job posting matching quality), and user engagement signal integration. Each component can be computed and optimized separately, then combined through multiplication to produce the final priority score, maintaining manageable system complexity while improving result quality
Solution Approach 2:
The patent incorporates user engagement signals (clicks, time spent, conversions) as feedback to continuously refine and update keyword priority scores. This feedback mechanism allows the system to adapt to actual user behavior patterns, improving the reliability of job search results over time while maintaining a relatively simple update process through periodic recalibration
Data Source
AI summary
A search engine optimization system is provided with an on-line social network system. The on-line social network system includes or is in communication with a search engine optimization (SEO) system that is configured to prioritize keywords (potential search terms) based on their respective predicted contribution to the ranking of JSERPs. The value of a job-related keyword is expressed as a priority score assigned to that keyword. The SEO system generates priority scores for different keywords, using a probabilistic model that takes into account a value expressing how likely the keyword is to be included in a search query as a search term and/or a value expressing how likely is a search that includes the keyword as a search term is to produce relevant results.