Keyword Extraction Server Using Relative Importance and User Weights

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing keyword analysis methods rely on subjective selection of keywords, leading to potential misidentification of important keywords in documents.

Innovation Solution

A method that calculates the relative importance of words in documents and applies user-defined keyword weights to determine important keywords, using a server that receives documents and user-defined keywords, calculates relative importance values, and transmits identified important keywords to the user terminal.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If keyword analysis uses subjectively selected words by an analyzer, then the analysis process is simple, but the accuracy of identifying important keywords deteriorates

Engineering Contradiction:

Improvesimplicity of keyword analysis processVSAvoidaccuracy of important keyword identification

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent replaces the manual, subjective mechanical process of keyword selection by an analyzer with an automated computational system. The server calculates relative importance values using objective algorithms that process document frequency, term frequency, and user-defined keyword weights, eliminating subjective bias while maintaining operational simplicity through automated processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces quantitative parameters (relative importance values, document frequency, term frequency, and user-defined weights) to transform the subjective keyword selection process into an objective calculation. By changing from qualitative subjective judgment to quantitative computational parameters, the system achieves both operational simplicity and improved accuracy in identifying important keywords.

Inventive Principle:

Principle #35Parameter changes

2Use of energy by moving object

If keyword analysis relies on subjective experience of an analyzer, then the process requires minimal computational resources, but the reliability of keyword identification deteriorates

Engineering Contradiction:

Improvecomputational resource consumptionVSAvoidreliability of keyword identification

Core Design Contradiction:

Use of energy by moving objectVSReliability

Solution Approach 1:

The patent replaces the unreliable human subjective judgment mechanism with a reliable automated computational system. The server consistently applies mathematical formulas to calculate relative importance values based on document frequency, term frequency, and user-defined weights, ensuring reliable and reproducible keyword identification without requiring excessive computational resources.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service keyword identification by automatically processing documents and calculating important keywords without requiring human analyzers. The server independently performs document frequency analysis, term frequency calculation, and relative importance computation, providing reliable results through autonomous operation with minimal computational overhead.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS10055408B2Method of extracting an important keyword and server performing the same

Publication Date: 2018.08.21 LG CNS CO LTD

AI summary

A method of extracting an important keyword by an important keyword extracting server, the method includes receiving a set of one or more documents from a network, receiving one or more user defined keywords from a user terminal, calculating, by the server, a relative importance value for each of words detected in the set of documents, determining, by the server, a weight for each of the words based on the one or more user defined keywords, applying, by the server, the weight for each of the words to the relative importance value for each of the words, determining, by the server, at least one of the words to be the important keyword based on the relative importance value to which the weight is applied and transmitting, by the server, the important keyword to the user terminal. Therefore, the method may effectively detect a user defined keyword from at least one document.