Implicit Reference Link Derivation via NLP

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Human analysis of web pages to identify implicit references and derive hyperlinks is time-consuming and costly, often resulting in missed references or imprecise results, as existing tools may ignore such references.

Innovation Solution

An automated system employing natural language processing and a hyperlink deriving classifier to identify and derive links from implicit references in web pages, using a syntactic model to generate structured or semi-structured hyperlinks accessible over a network.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated tools are used to identify implicit references, then productivity is improved, but measurement precision deteriorates

Engineering Contradiction:

Improvespeed of identifying implicit referencesVSAvoidaccuracy of identifying implicit references

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent replaces manual human analysis (mechanical system) with automated natural language processing and machine learning classifiers. The system uses computational algorithms to detect implicit references, extract entities, and generate hyperlinks automatically, thereby increasing productivity while maintaining acceptable precision through sophisticated NLP techniques.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Device complexity

If existing hyperlink tools are used, then device complexity is reduced, but loss of information increases

Engineering Contradiction:

Improvesimplicity of tool implementationVSAvoidmissed implicit references

Core Design Contradiction:

Device complexityVSLoss of information

Solution Approach 1:

The patent introduces an intermediary natural language processing layer between the raw web page content and the hyperlink generation process. This NLP intermediary analyzes the textual content, identifies implicit references that traditional tools miss, extracts relevant entities, and generates appropriate hyperlinks, thereby preventing information loss while adding necessary processing complexity.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If human analysts manually derive hyperlinks, then measurement precision is improved, but loss of time increases

Engineering Contradiction:

Improveaccuracy of hyperlink derivationVSAvoidtime required for analysis

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the mechanical process of human manual analysis with automated computational systems. Machine learning classifiers and natural language processing algorithms perform the analysis rapidly and consistently, achieving high precision in hyperlink derivation without the time costs associated with human analysts, thus resolving the time-precision tradeoff.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS10713329B2Deriving links to online resources based on implicit references

Publication Date: 2020.07.14 MICRO FOCUS IP DEV

AI summary

In some examples, a system performs language processing of text of an information page to determine whether the text refers to an online resource, and in response to determining that the text refers to the online resource, identify the text as an implicit reference to the online resource. The system derives a link to the online resource based on the implicit reference, the derived link useable in accessing the online resource.