Automated List Page Library Construction via Clustering

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for creating a list page library are complex and prone to errors, requiring manual operator intervention to identify and label list pages on websites, which reduces efficiency and reliability.

Innovation Solution

A method and device that acquire and cluster pages based on features, using page linking relationships to determine probabilities and select classes as list pages, eliminating the need for manual operator involvement by automating the process through model training and updating.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual operator intervention is used to identify and label list pages, then the list page library can be created, but the operations become complicated and error-prone, reducing efficiency and reliability

Engineering Contradiction:
Improvereliability of creating list page libraryVSAvoidcomplexity of operations
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system performs automatic page classification and list page identification through self-service mechanisms. The page processing system autonomously acquires pages, clusters them based on features, calculates probabilities using linking relationships, and selects list pages without requiring manual operator intervention, thereby eliminating operational complexity while maintaining high reliability

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual labeling process with an automated computational system. Instead of operators manually browsing and labeling pages, the system uses algorithmic processes including page clustering, probability calculation based on in-degree and out-degree metrics, and automated selection to identify list pages, substituting human mechanical operations with systematic computational methods

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If manual operator intervention is used to identify and label list pages, then the list page library can be created, but the efficiency is reduced due to time-consuming manual operations

Engineering Contradiction:
Improveefficiency of creating list page libraryVSAvoidtime for manual operations
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-calculating page features, clustering pages into categories, and pre-computing probability metrics based on linking relationships before final list page selection. This preliminary processing automates what would otherwise require time-consuming manual browsing and analysis, significantly improving efficiency while minimizing time loss

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The automated system performs all operations autonomously without human intervention, from page acquisition and clustering to probability calculation and list page selection. This self-service approach eliminates the time operators would spend manually identifying and labeling pages, dramatically improving productivity

Inventive Principle:
Principle #25Self-service

3Reliability

If manual operator intervention is used to identify and label list pages, then the list page library can be created, but mistakes are more likely to occur

Engineering Contradiction:
Improveaccuracy of list page identificationVSAvoidsimplicity of process
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The system incorporates feedback mechanisms through probability calculations based on in-degree and out-degree metrics. By continuously evaluating linking relationships and adjusting probability scores, the system provides feedback-driven refinement of list page selections, ensuring high accuracy through systematic verification rather than relying on manual judgment

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent replaces error-prone manual identification with automated computational processes that systematically evaluate page features and linking relationships. The algorithmic approach eliminates human mistakes by using consistent, objective criteria for list page selection, thereby improving accuracy while maintaining operational simplicity

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS10387545B2Processing page
Publication Date: 2019.08.20 ALIBABA GROUP HOLDING LTD
  • US10387545B2 patent drawing
  • US10387545B2 patent drawing
  • US10387545B2 patent drawing

AI summary

Example methods and devices for processing a page are described. One or more pages of a designated website are acquired. The one or more pages are clustered to obtain one or more classes in accordance with page features of the pages. At least one class is selected as a list page set according to a page linking relationship between the one or more classes. It is not necessary to require an operator to manually involve in the process of establishing the list page set. The present techniques have simple operations and high accuracy rate, thereby improving an efficiency and reliability of establishing a list page library.