Neural Network Search Ranking with Page Site Supersite Weights
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional search engines face limitations in efficiently ranking and weighting web resources, leading to suboptimal search results as the scope of search increases, with existing systems struggling to remove redundancy, spam, and low-quality content effectively.
Innovation Solution
A neural network supercomputer optimizes internet search by uniquely ranking and weighting resources using Page Rank, Site Rank, and Supersite Rank, employing Big Data Indexing and fuzzy logic to filter out irrelevant content and identify the highest quality results, mimicking human decision-making processes to provide interactive and personalized search outcomes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If conventional search engines increase the scope of search to cover more web resources, then the quantity of search results increases, but the quality of results deteriorates due to redundancy, spam, and low-quality content
Solution Approach 1:
The patent applies parameter changes by introducing multiple ranking parameters (Page Rank, Site Rank, Supersite Rank) instead of a single ranking metric. These parameters dynamically adjust the weighting and filtering of search results based on quality thresholds, enabling the system to maintain high reliability while expanding search scope. The fuzzy logic component continuously adjusts these parameters to optimize the balance between quantity and quality.
Solution Approach 2:
The patent extracts and removes low-quality content through quality threshold filtering. By establishing minimum quality standards for pages, sites, and supersites, the system extracts only the highest-quality results from the search environment, eliminating redundancy, spam, and low-quality content even as the overall search scope expands.
2Adaptability or versatility
If conventional search engines expand the search environment to include more web pages, then the coverage increases, but the complexity of processing and ranking increases
Solution Approach 1:
The patent segments the search environment into hierarchical levels: pages, sites, and supersites. Each level has its own ranking parameters and quality thresholds. This segmentation allows the system to process and manage large volumes of web resources by breaking them into manageable units with specific ranking criteria, reducing overall processing complexity while maintaining comprehensive coverage.
Solution Approach 2:
The patent introduces dynamic adjustment mechanisms where ranking parameters and quality thresholds are not fixed but adapt based on search patterns, user feedback, and environmental changes. This dynamic approach allows the system to handle expanding search environments efficiently by adjusting processing complexity in real-time rather than requiring static, overly complex structures.
3Reliability
If conventional search engines process more web resources, then the comprehensiveness of results improves, but the time required for processing increases
Solution Approach 1:
The patent implements preliminary action by pre-calculating and storing ranking parameters (Page Rank, Site Rank, Supersite Rank) and quality thresholds for web resources before actual search queries. This pre-processing allows the system to quickly retrieve and filter results during search operations without performing complex calculations in real-time, maintaining comprehensive evaluation while reducing processing time.
Solution Approach 2:
The patent employs feedback mechanisms where search results and user interactions continuously refine ranking parameters and quality thresholds. This feedback loop allows the system to learn from past searches and improve processing efficiency over time, maintaining comprehensive result evaluation while progressively reducing the time required for processing through optimized parameter sets.
Data Source
AI summary
An evolving system of computers linked into a neural network continuously scans and gathers information from, understands, and interacts with, an environment; and a client computer program interactively executes software instructions using a subject matter data warehouse to transform input into a search pattern. The evolving system server supercomputer program executes multivariant big data indexing to cherry pick the optimal input and output using page, site and supersite probabilities. The client computer program analyzes the optimal output given a search pattern in order to interact and engage scripted communication with the end user.