Nec corporation (20240184807). INFORMATION SYSTEM FOR GENERATION OF NEW MOLECULE BY USING GRAPH REPRESENTING MOLECULE simplified abstract
Contents
INFORMATION SYSTEM FOR GENERATION OF NEW MOLECULE BY USING GRAPH REPRESENTING MOLECULE
Organization Name
Inventor(s)
Francesco Alesiani of Heidelberg (DE)
Markus Zopf of Heidelberg (DE)
INFORMATION SYSTEM FOR GENERATION OF NEW MOLECULE BY USING GRAPH REPRESENTING MOLECULE - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240184807 titled 'INFORMATION SYSTEM FOR GENERATION OF NEW MOLECULE BY USING GRAPH REPRESENTING MOLECULE
The patent application describes a machine learning method for learning and applying a rule set from relational data, such as medical data, to optimize machine learning tasks and support decision-making processes.
- Receiving a graph representing relational data, where nodes represent elements and edges represent relationships.
- Generating an intermediate vector representation of the graph by mapping features of nodes and edges.
- Learning optimized logical rules for nodes and edges based on the intermediate vector representation.
- Defining a maximum satisfiability (max-sat) problem for the graph.
- Estimating a gradient around a solution of the max-sat problem to produce optimized logical rules.
- Applying the learned rules to a new graph for tasks like disease prediction using medical data.
- Potential Applications:**
- Disease prediction using medical data. - Optimization of machine learning tasks. - Decision-making support systems.
- Problems Solved:**
- Efficient learning and application of rule sets from relational data. - Optimization of machine learning tasks. - Enhanced decision-making processes.
- Benefits:**
- Improved accuracy in disease prediction. - Streamlined machine learning processes. - Enhanced decision-making capabilities.
- Commercial Applications:**
Title: "Enhanced Disease Prediction System Using Machine Learning" This technology can be utilized in healthcare industries for developing advanced disease prediction systems, optimizing medical research processes, and improving patient care outcomes.
- Prior Art:**
There are existing machine learning methods for analyzing relational data, but this patent application focuses on optimizing logical rules based on an intermediate vector representation, which is a novel approach.
- Frequently Updated Research:**
Stay updated on advancements in machine learning algorithms for relational data analysis and optimization techniques for rule sets in medical data prediction systems.
- Questions about Machine Learning for Disease Prediction:**
1. How does this method improve the accuracy of disease prediction compared to traditional machine learning approaches? 2. What are the potential challenges in implementing this technology in real-world healthcare settings?
Original Abstract Submitted
a machine learning method for learning and applying a rule set from relational data includes receiving a graph representing relational data, wherein nodes represent elements of the graph, and edges represent relationships between nodes, and generating an intermediate representation of the graph by mapping features of the nodes and edges of the graph to an intermediate vector representation. optimized logical rules that define the nodes and edges of the graph based on the intermediate vector representation are learned by: defining a maximum satisfiability (max-sat) problem for the graph; and estimating a gradient around a solution of the max-sat problem to produce the optimized logical rules, which are applied to a new graph. the data can be medical data and the graph can be used in a machine-learning task, such as using the medical data for disease prediction, for optimization of the machine-learning task and/or to support decision-making.
