Gestational Eligibility Machine Learning Model

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for making decisions during gestation are often uninformed and inconsistent, lacking compatibility assessments for products and activities based on the user's gestational phase.

Innovation Solution

A system and method using a computing device to calculate the gestational phase, receive user inquiries, generate a machine-learning model that utilizes gestational phase labels and biological data to determine eligibility, and provide compatibility labels for products and activities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If decisions are made during gestation without physiological information, then the decision-making process is simple and quick, but the accuracy and safety of the decisions are poor

Engineering Contradiction:

Improvedecision accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary calculation of gestational phase and generation of machine-learning models before making product compatibility decisions. By pre-processing physiological data and establishing predictive models in advance, the system enables accurate, informed decisions without adding complexity to the actual decision-making moment.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary machine-learning model that acts as a bridge between raw physiological data and product compatibility assessments. This intermediary layer processes complex physiological information and translates it into actionable compatibility guidance, resolving the contradiction between decision accuracy and system complexity.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If a machine-learning model is generated to determine gestational eligibility, then product compatibility accuracy is improved, but computational complexity and processing time increase

Engineering Contradiction:

Improvecompatibility assessment reliabilityVSAvoidmodel generation complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system segments the compatibility assessment process into distinct phases: gestational phase calculation, biological data extraction, machine-learning model generation, and eligibility determination. This segmentation allows each component to be optimized independently, improving overall reliability while managing complexity through modular architecture.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system generates gestational phase labels and biological extractions as partial inputs to the machine-learning model, rather than requiring complete physiological profiles. This partial action approach enables reliable compatibility assessments with reduced data requirements, lowering computational complexity while maintaining assessment reliability.

Inventive Principle:

Principle #16Partial or excessive action

3Loss of information

If gestational phase calculation and biological data extraction are performed, then informed decision-making is enabled, but data processing requirements and system resources increase

Engineering Contradiction:

Improvephysiological information completenessVSAvoidcomputational resource consumption

Core Design Contradiction:

Loss of informationVSUse of energy by moving object

Solution Approach 1:

The system extracts only the essential biological data features required for gestational phase determination and product compatibility assessment, rather than processing complete physiological datasets. This selective extraction maintains information completeness for decision-making while significantly reducing computational resource consumption.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system transforms raw biological data into standardized gestational phase labels and eligibility parameters through the machine-learning model. This parameter transformation condenses complex physiological information into manageable categories, enabling informed decisions with reduced computational overhead.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11829895B2Methods and systems for physiologically informed gestational inquiries

Publication Date: 2023.11.28 KPN INNOVATIONS LLC

AI summary

A system for physiologically informed gestational inquiries. The system includes a computing device configured to calculate a gestational phase, wherein the gestational phase is calculated by receiving a gestational datum, classifying the gestational datum to a gestational phase, and generating a gestational phase label. The computing device is further configured to receive from a remote device a gestational inquiry. The computing device is further configured to classify a gestational inquiry to an inquiry category. The computing device is further configured to select a gestational machine-learning model. The computing device is further configured to generate a gestational machine-learning model wherein the gestational machine-learning model utilizes a user biological extraction as an input and outputs gestational eligibility. The computing device is further configured to determine the gestational eligibility of a gestational inquiry.