Document Search Using Inferred Tags and Classification Codes

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing document search systems lack objectivity and efficiency, particularly in selecting search keywords and classification codes, making it difficult for users to find relevant information effectively.

Innovation Solution

A document search method that evaluates and classifies document data based on search queries, infers the importance of tags or words, and allows users to select these for targeted searches, using machine learning and feature vectors to enhance search efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a PageRank system like web search is used for document search, then the search can be conducted, but it lacks objectivity in searching for document contents

Engineering Contradiction:

Improveobjectivity of searchVSAvoidsearch effectiveness

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The patent introduces classification codes (CPC, IPC, FI, F-terms) as intermediary elements between the search query and document contents. Instead of directly searching document texts, the system translates queries into classification codes and searches documents based on these standardized categories, ensuring objectivity while maintaining search effectiveness

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent transforms the search parameter from direct text matching to classification code matching. By changing the search parameter from unstructured text to standardized classification codes, the system achieves both objectivity in search and effectiveness in retrieving relevant documents

Inventive Principle:

Principle #35Parameter changes

2Adaptability or versatility

If multiple expressions (hiragana, katakana, kanji, synonyms, broader terms, narrower terms) are used for one word, then language flexibility is improved, but it becomes difficult to select appropriate search keywords

Engineering Contradiction:

Improvelanguage flexibilityVSAvoidkeyword selection difficulty

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent makes classification codes universal across different language expressions. A single classification code represents multiple expressions (hiragana, katakana, kanji, synonyms, broader terms, narrower terms), allowing the system to handle language flexibility while simplifying keyword selection to just the classification code

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The classification code acts as an intermediary that connects multiple language expressions to a single standardized category. Instead of manually selecting among multiple expressions, users input the classification code which automatically maps to all relevant expressions, resolving the keyword selection difficulty

Inventive Principle:

Principle #24Intermediary (Mediator)

3Adaptability or versatility

If patent classification codes (CPC, IPC, FI, F-terms) are used for document classification, then classification comprehensiveness is improved, but it becomes difficult to appropriately select a classification code

Engineering Contradiction:

Improveclassification comprehensivenessVSAvoidclassification code selection difficulty

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent segments the complex classification code selection process into two simple steps: (1) user inputs a natural language search query, and (2) the system automatically translates the query into the appropriate classification code. This segmentation maintains comprehensive classification coverage while eliminating selection difficulty for users

Inventive Principle:

Principle #1Segmentation

4Ease of operation

If traditional keyword search is used, then search simplicity is maintained, but search accuracy and efficiency are reduced

Engineering Contradiction:

Improvesearch simplicityVSAvoidsearch accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent introduces classification codes as an intermediary layer between simple keyword input and accurate document retrieval. Users simply input keywords, the system translates them to classification codes, and performs accurate searches based on these codes, thereby maintaining simplicity while improving accuracy

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system dynamically changes the search parameter from simple keywords to classification codes during processing. This parameter transformation allows the system to maintain input simplicity while achieving measurement precision through standardized classification-based matching

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20250384091A1Document search method and document search system

Publication Date: 2025.12.18 SEMICON ENERGY LAB CO LTD

AI summary

To carry out a search for a document efficiently, a plurality of pieces of document data are received, a search query is received, each of the plurality of pieces of document data is evaluated on the basis of the search query, an evaluation result of at least part of the plurality of pieces of document data is output, classification of at least part of the plurality of pieces of document data is received, importance of a plurality of tags is inferred from the classification, the importance of at least part of the plurality of tags is output, at least one of the tags whose importance is output is received, and a search for a document is performed with use of the received tag.