Web Page Navigation Ordering via Machine Learning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users face difficulties in navigating multiple open web pages, leading to frustration and inefficiencies due to the challenge of quickly finding and returning to desired pages.

Innovation Solution

A computer-implemented method using machine learning and user operation behavior analysis to determine the probability of each web page being visited, ordering and managing open web pages based on this analysis, and providing hints and tips for high-probability pages while hiding or closing low-visit frequency pages.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple web pages are kept open for user access, then user accessibility to various web pages is improved, but user navigation efficiency and time to find desired pages deteriorates

Engineering Contradiction:
Improveuser accessibility to web pagesVSAvoidnavigation time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of user browsing behavior and page features before navigation occurs. It pre-calculates visit probabilities and pre-arranges the ordering of web pages based on predicted user intent, so that when users need to navigate, the desired page is already positioned for quick access without requiring manual searching through multiple open tabs.

Inventive Principle:
Principle #10Preliminary action

2Productivity

If machine learning analysis is applied to determine page visit probability, then navigation efficiency is improved, but system complexity increases

Engineering Contradiction:
Improvenavigation efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The machine learning system operates autonomously by automatically collecting user behavior data, analyzing page features, calculating visit probabilities, and ordering web pages without requiring user intervention. The system serves itself by continuously learning from user interactions and automatically adjusting the page ordering, eliminating the need for manual configuration or complex user setup procedures.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS20220284319A1Intelligent guidance using machine learning for user navigation of multiple web pages
Publication Date: 2022.09.08 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US20220284319A1 patent drawing
  • US20220284319A1 patent drawing
  • US20220284319A1 patent drawing

AI summary

Facilitating web page selection by a user navigating multiple web pages on a computer can include determining, using a computer, a probability of each of a plurality of web pages being visited by a user. The probability can be determined using machine learning and user operational behavior analysis based on an analysis of web page features. Using a cognitive analysis, the open web pages can be ordered based on the probability of each of the web pages being visited by the user. The ordering can include ranking web pages based on a highest probability of a web page being visited. The open web pages can be managed based on the ordering of the open web pages where the managing includes prompting the user to visit a web page of the open web pages in response to the ranking of an open web page in the order.