Document Display Assistance System for Automatic Keyword Highlighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing document display assistance technologies are cumbersome and inaccurate in highlighting significant or relevant words in a specific field, as they require manual input and subjective selection of keywords.
Innovation Solution
A document display assistance system that uses a learned word-selection model applied with machine learning to estimate the significance of words in a document, classifying them into selection-target, non-selection-target, or indeterminate words, and displays the selected words in a visually differentiated manner.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual input and subjective selection of keywords are used to highlight significant words, then the system can identify relevant information, but the process becomes cumbersome and time-consuming
Solution Approach 1:
The system performs automatic keyword selection through machine learning models that analyze document content and independently identify significant words without requiring manual user input. The word-selection model and field-determination model automatically determine which words to highlight based on their significance to the specific field, eliminating the need for users to manually enter keywords.
Solution Approach 2:
The manual mechanical process of selecting and inputting keywords is replaced by an automated information processing system using machine learning algorithms. The system substitutes human cognitive effort with computational analysis, where the word-selection model and field-determination model automatically process document text and identify significant keywords through pattern recognition and statistical analysis.
2Ease of operation
If users manually select keywords to search documents, then they can find relevant information, but the accuracy of identifying truly significant words is reduced due to subjective selection
Solution Approach 1:
The subjective human judgment process is replaced by objective machine learning models that analyze document content systematically. The word-selection model uses statistical methods and pattern recognition to objectively determine word significance, eliminating biases and inconsistencies inherent in manual keyword selection by users.
Solution Approach 2:
The system incorporates feedback mechanisms where the field-determination model first identifies the specific field of the document, then the word-selection model uses this field information to refine keyword selection. This multi-stage feedback process ensures that selected keywords are highly relevant to both the document content and the specific field, improving accuracy while maintaining ease of operation.
3Measurement precision
If the system processes and highlights multiple significant words automatically, then accuracy improves, but the system complexity increases
Solution Approach 1:
The complex automated processing system is divided into distinct functional modules: a field-determination model that identifies the document's specific field, a word-selection model that selects significant keywords based on field context, and a document display assistance system that presents results. This segmentation allows each module to specialize in a specific task, improving overall accuracy while making the system more manageable and maintainable.
Data Source
AI summary
The present invention provides a document display assistance system which estimates and highlights significant words in a document of a specific field. The system comprises: a database in which selection-target words and non-selection-target words are registered; a learned word-selection model having been applied with machine learning for estimating whether a word is a selection-target word; a text pre-processing unit which segments words from an accepted display-target document; a word classification unit which classifies, based on the database, the word into any of a selection-target word, a non-selection-target word, and an indeterminate word; a text post-processing unit which generates output data by imparting a predetermined attribute to a predetermined word in the display-target document; and an output unit which outputs the output data. If a label is estimated indicating that the indeterminate word classified by the word classification unit is a selection-target word, the word selection model classifies the indeterminate word into a selection-target word and the text post-processing unit imparts the predetermined attribute to the classified selection-target word.