Stochastic Page Rank Node Ranking Using Random Parameters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing page rank models rely on deterministic parameters, which fail to accurately represent the diverse browsing behaviors of individual users, leading to inaccurate ranking of web pages and neglecting valuable information from user behavior patterns.
Innovation Solution
Introducing random or stochastic parameters to induce a stochastic solution vector for ranking nodes in a graph, allowing for the incorporation of user behavior variability and providing additional metrics such as standard deviation and covariance, which can reveal patterns in user behavior and improve search result relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If deterministic parameters are used in page rank models, then the model is simple and computationally efficient, but it fails to accurately represent diverse browsing behaviors of individual users
Solution Approach 1:
The patent transforms the deterministic parameter α into a random variable with a probability distribution, changing the mathematical nature of the parameter from fixed to stochastic. This allows the model to capture user behavior variability while maintaining the same fundamental page rank computation framework.
Solution Approach 2:
The patent introduces dynamic behavior by allowing parameters to vary according to probability distributions rather than remaining static. The random variable α and its distribution enable the model to adapt to different user behaviors dynamically, improving measurement precision without completely overhauling the system.
2Loss of information
If deterministic parameters are used, then computational efficiency is maintained, but valuable information from user behavior patterns is neglected
Solution Approach 1:
The patent applies partial stochasticity by introducing random variables only where needed to capture user behavior patterns, rather than making the entire system stochastic. This selective application preserves computational efficiency while recovering valuable user behavior information that would be lost in a fully deterministic model.
Solution Approach 2:
The probability distribution acts as an intermediary between the deterministic page rank framework and the stochastic nature of user behavior. It mediates the transformation of fixed parameters into behavior-aware parameters without requiring a complete redesign of the computational system.
3Adaptability or versatility
If random parameters are introduced, then user behavior variability is captured, but the model becomes more complex
Solution Approach 1:
The patent changes the nature of parameters from deterministic values to random variables with distributions, enabling the model to represent user behavior variability. This parameter transformation increases adaptability while keeping the underlying computational structure relatively simple.
Data Source
AI summary
A ranking approach is used to determine rank-based relationships. In connection with various embodiments, the present invention is directed to a method for ranking nodes of a graph. A vector is provided as a function of a set of random parameters, and a probability matrix function is used, relative to nodes of the graph, to assess the statistics of the vector that solves a probability-based system. Certain embodiments are directed to determining a page rank for a web-based search.