Semantic Data Language for Broad Medical Query Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing computer systems struggle to deeply understand and process the meaning of natural language due to the complexity and heterogeneity of data, leading to inefficiencies in applications requiring broad and diverse datasets, such as health management, nutrition tracking, and accounting, where structured data schemas become impractical and natural language processing lacks human-like understanding.
Innovation Solution
A machine-readable language, referred to as UL, is used to represent data in a structured and expressive format that allows for semantic nodes and links, enabling machines to process and understand a broad range of information, including user speech and text inputs, and facilitating faster and more accurate responses through simplified processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If structured data schemas are used to represent broad heterogeneous data, then data organization and processing become manageable, but the schema complexity and difficulty of building and maintaining the application grow impractically large
Solution Approach 1:
The patent segments the monolithic schema into modular knowledge graphs, where data is organized into discrete entities (patients, symptoms, tests, medications) with defined relationships. Each entity type can be independently managed and extended, allowing the system to handle broad heterogeneous data without requiring a single overwhelming schema structure.
Solution Approach 2:
The patent creates a universal data model that can represent multiple domains (healthcare, nutrition, accounting, recruitment) through a common framework of entities and relationships. This universal schema uses standardized entity types and relationship patterns that can be applied across different application domains, reducing the need for domain-specific schema complexity.
2Adaptability or versatility
If natural language processing techniques are used to process user input, then the system can handle diverse language inputs, but the system lacks deep semantic understanding and human-like interpretation
Solution Approach 1:
The patent introduces knowledge graphs as an intermediary layer between natural language input and system processing. User input is translated into queries against the structured knowledge graph, which provides semantic context and meaning. This intermediary enables the system to understand the intent and meaning behind natural language queries without requiring complex statistical NLP models.
Solution Approach 2:
The patent replaces statistical machine learning approaches with a rule-based semantic processing system. Instead of using probabilistic models to infer meaning, the system uses explicit semantic relationships defined in the knowledge graph to accurately interpret and process natural language queries, providing more reliable and explainable results.
3Adaptability or versatility
If comprehensive structured data is collected to cover all possible scenarios, then the application can handle any situation, but the data storage and processing requirements become unmanageably large
Solution Approach 1:
The patent pre-structures data into a knowledge graph framework with predefined entities, attributes, and relationships before actual data is collected. This preliminary schema framework allows the system to efficiently organize and store data as it arrives, avoiding the need to collect and process all possible data scenarios simultaneously. The framework guides data collection and ensures consistent organization.
Solution Approach 2:
The patent transforms flat tabular data into a multi-dimensional knowledge graph structure with entities, attributes, and hierarchical relationships. This dimensional transformation allows the system to represent complex scenarios using a compact graph structure rather than requiring extensive flat data tables, reducing storage requirements while maintaining comprehensive scenario coverage.
Data Source
AI summary
There is provided a computer implemented method for automated analysis or use of data, comprising the steps of: (a) storing in a memory store a structured, machine-readable representation of data that conforms to a machine-readable language; in which the data includes personal health or medical data; (b) automatically processing the structured representation of the data to analyse the personal health or medical data; in which the method includes the steps of (c) the machine-readable language representing a question in a memory in the structured, machine-readable representation of data; and (d) automatically generating a response to the question, using the following steps: (i) matching the question with the structured, machine-readable representations of data previously stored in the memory store; (ii) fetching and executing one or more computation units, wherein the computation units represent computational capabilities relevant to answering the question; (iii) fetching and execution of one or more reasoning passages.