Automated Data Summarization System for Visual and Text Datasets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data visualization systems fail to automatically interpret hidden features and patterns in data, requiring manual intervention and lacking the ability to summarize data based on reason and meaning, making it difficult for non-technical users to derive insights from datasets.
Innovation Solution
A method and system that classify datasets by type (text, numeric, visual) using predefined token and graphical models to generate summarized content, automatically determining usable tokens and graphical parameters for automated data summarization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual intervention is used to interpret and manage datasets, then accuracy of data interpretation can be maintained, but time consumption and human resource requirements increase significantly
Solution Approach 1:
The system performs self-service by automatically classifying datasets, determining usable tokens from text data, extracting graphical parameters from visual data, and generating summaries without requiring manual human intervention. The automated processing pipeline enables the system to serve itself in interpreting and managing diverse data types, thereby reducing time consumption while maintaining interpretation accuracy through systematic automated analysis
Solution Approach 2:
The patent replaces manual mechanical interpretation processes with automated computational systems. Machine learning models and algorithms substitute human analysts in performing data classification, token determination, parameter extraction, and summary generation, thereby eliminating the need for human time investment while preserving interpretation quality through programmed analytical methods
2Productivity
If automated processing is implemented for data summarization, then productivity and speed are improved, but the ability to interpret hidden features and patterns remains insufficient
Solution Approach 1:
The system introduces intermediary components including pre-trained language models and graphical models that act as mediators between raw data and final summaries. These intermediaries automatically determine usable tokens from text data and extract graphical parameters from visual data, enabling the system to detect hidden features and patterns while maintaining high processing speed through automated model-based analysis rather than manual interpretation
Solution Approach 2:
The patent transforms data into different parameter representations through automated processing. By converting diverse data types into standardized parameters (usable tokens, graphical parameters) that can be processed at high speed, the system enables both rapid productivity improvement and effective detection of hidden features through parameter transformation and standardized analysis frameworks
3Adaptability or versatility
If multiple data types are processed manually, then comprehensive analysis can be achieved, but device complexity and operational difficulty increase
Solution Approach 1:
The system segments the complex task of multi-type data processing into distinct modular components: a classification module that categorizes datasets by type, a text processing module that determines usable tokens, a visual data module that extracts graphical parameters, and a summary generation module. This segmentation reduces operational complexity by providing specialized handling for each data type while maintaining comprehensive analysis capabilities through the coordinated work of separate modules
Solution Approach 2:
The patent implements a universal processing framework that handles multiple data types (text, visual, structured) through a single integrated system. The classification module identifies data types, and appropriate processing pathways are automatically selected, enabling the system to perform comprehensive analysis across diverse data formats without requiring separate manual procedures for each type, thereby reducing operational complexity while maintaining versatility
Data Source
AI summary
A method and data summarization system for dynamically generating summarised content for visual and contextual text data, is disclosed. The method includes classifying plurality of dataset related to one or more domains based on datatype associated with each dataset. The datatype comprises text, numeric and visual data. Upon classification, one or more usable tokens are determined from the text data using a predefined token learning model. Further, one or more graphical parameters are determined from the visual data by using a pre-trained graphical model. Thereafter, based on the one or more usable tokens and the one or more graphical parameters, a summarized content is generated for the plurality of dataset.