Personalized Visually Isolated Text via ML Annotation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing natural language processing systems fail to effectively personalize and highlight relevant information in text documents based on user profiles, leading to inefficient information retrieval and presentation, particularly in healthcare and enterprise content management.

Innovation Solution

A method and system that automatically generates visually isolated text fragments by annotating and categorizing input text using machine-learning annotators, incorporating user profile characteristics to prioritize and highlight relevant information, leveraging semantic and linguistic inferences to predict correct textual context and present concise summaries.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If existing natural language processing systems are used to process text documents, then text processing can be performed, but the systems fail to effectively personalize and highlight relevant information based on user profiles

Engineering Contradiction:

Improvepersonalization capabilityVSAvoidrelevance of information

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The system performs preliminary actions by creating and storing user profiles with characteristics, preferences, and roles before text processing occurs. These pre-established profiles enable subsequent personalization of information retrieval and highlighting without requiring real-time adaptation during text processing.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system applies local quality by selectively highlighting only the relevant portions of text based on user profile characteristics, rather than treating the entire document uniformly. This allows different parts of the text to receive different levels of emphasis according to their relevance to specific user needs.

Inventive Principle:

Principle #3Local quality

2Loss of information

If all text fragments are processed and presented equally, then complete information is provided, but information retrieval efficiency decreases

Engineering Contradiction:

Improvecompleteness of informationVSAvoidinformation retrieval efficiency

Core Design Contradiction:

Loss of informationVSProductivity

Solution Approach 1:

The system extracts and isolates only the most relevant text fragments from the complete document based on user profile matching. By taking out and presenting only the essential information fragments, the system maintains information completeness for the user's needs while dramatically improving retrieval efficiency by eliminating irrelevant content.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system applies partial action by processing and presenting only a subset of text fragments that are most relevant to the user profile, rather than processing the entire document equally. This selective approach provides sufficient information for the user's specific needs without the overhead of complete document processing.

Inventive Principle:

Principle #16Partial or excessive action

3Measurement precision

If manual annotation and categorization of text is performed, then high accuracy is achieved, but time consumption increases

Engineering Contradiction:

Improveannotation accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs self-service by automatically annotating and categorizing text fragments using machine learning algorithms and user profile data, eliminating the need for manual annotation. The system serves itself by generating annotations and categorizations autonomously based on learned patterns and user characteristics.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system replaces the mechanical process of manual annotation with automated computational processes. Machine learning models and algorithms substitute for human annotators, performing categorization and annotation tasks automatically while maintaining high accuracy through pattern recognition and profile-based matching.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Loss of information

If comprehensive text analysis is performed without personalization, then all concepts are identified, but user-specific relevance is lost

Engineering Contradiction:

Improvecompleteness of concept identificationVSAvoiduser-specific relevance

Core Design Contradiction:

Loss of informationVSAdaptability or versatility

Solution Approach 1:

The system changes the parameter of relevance by incorporating user profile characteristics as an additional dimension in text analysis. Instead of analyzing text in isolation, the system adjusts the relevance parameters based on user-specific attributes such as role, preferences, and historical behavior, transforming generic concept identification into personalized information retrieval.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS10565291B2Automatic generation of personalized visually isolated text

Publication Date: 2020.02.18 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

Input text containing a plurality of patient information can be annotated for annotations and extracted. One or more annotations are parsed for relevant contextual information. The one or more annotations are assigned a semantic type. The one or more annotations are visually isolated, personalized to a user profile job, and outputted. The one or more extracted annotations are subjected to natural language processing operations.