Natural Language Search Sentence Generation for Intent Precision

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing search systems struggle to accurately reflect the true intention and nuance of natural language inputted search queries, often excluding negative meanings and requiring users to create complex search expressions.

Innovation Solution

A search sentence generation system that analyzes natural language input, decomposes sentences into words, determines operators and target words, and generates appropriate search sentences based on these elements, ensuring the true intention and nuance are reflected.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a search expression is created automatically based on a natural sentence using a search word dictionary, then the ease of operation is improved, but the measurement precision of the search intention deteriorates

Engineering Contradiction:
Improveease of creating search expressionVSAvoidprecision of search intention
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent introduces an analysis unit as an intermediary between the natural sentence input and the search expression generation. This unit performs detailed linguistic analysis including identifying operators (AND, OR, NOT), target words, and their hierarchical relationships, thereby preserving search intention precision while maintaining automatic generation capability

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent segments the natural sentence into distinct components: operators, target words, and their relationships. By dividing the analysis into these granular elements and establishing hierarchical structures between them, the system accurately captures search intention while automating the process

Inventive Principle:
Principle #1Segmentation

2Productivity

If keywords are rewritten by adding keywords or changing operators to increase the number of answers, then the productivity is improved, but the measurement precision of the search intention deteriorates

Engineering Contradiction:
Improvenumber of search answersVSAvoidprecision of search intention
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent creates a dynamic search expression generation process where the structure and content of search expressions are adaptively determined based on the analyzed natural sentence. The system dynamically adjusts operator selection, keyword combination, and hierarchical relationships to balance result quantity with intention precision

Inventive Principle:
Principle #15Dynamics

3Ease of operation

If negative meaning of search words is excluded during automatic search expression creation, then the ease of operation is improved, but the measurement precision of the search intention deteriorates

Engineering Contradiction:
Improveease of inputting search queryVSAvoidprecision of negative meaning
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent implements feedback mechanisms where the analysis unit continuously monitors and identifies negative meaning indicators in the natural sentence, such as 'not' or negation patterns. This feedback ensures that negative constraints are properly translated into the search expression while maintaining system simplicity

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS12373426B2Search sentence generation system and search sentence generation method
Publication Date: 2025.07.29 UNIVERSAL ENTERTAINMENT CORP
  • US12373426B2 patent drawing
  • US12373426B2 patent drawing
  • US12373426B2 patent drawing

AI summary

To provide a search sentence generation system capable of generating an appropriate search sentence automatically based on a natural sentence inputted by a user. A search sentence generation server 300 determines a word corresponding to an operator and a target word adjacent to the word by analyzing a received input sentence and generates a search sentence corresponding to the input sentence based on the determined words in this manner.