Deep Learning Policy Plan for Communicable Disease Management

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

During chaotic events such as pandemics, businesses face difficulties in making informed decisions due to the complexity and rarity of such events, leading to inadequate planning and ineffective policies, which can have cumulative negative effects on the public.

Innovation Solution

A computer-implemented method using deep machine learning to generate communicable disease policy plans by collecting and analyzing employment data, including sick leave data, to identify correlations and predict effective workplace policies for businesses, thereby creating tailored policy plans.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional manual methods are used to analyze employment data and design workplace policies, then businesses can make informed decisions, but the process becomes tedious, difficult, and time-consuming

Engineering Contradiction:
Improvepolicy design efficiencyVSAvoidtime required for policy analysis
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical analysis of employment data with an automated machine learning system. The ML model automatically processes employment data, identifies patterns, and generates policy recommendations, substituting human analytical efforts with computational algorithms that operate faster and without fatigue.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables businesses to independently generate policy recommendations through automated data processing. The machine learning model self-adjusts and self-optimizes by continuously learning from employment data patterns, allowing businesses to obtain policy insights without external consulting services.

Inventive Principle:
Principle #25Self-service

2Reliability

If comprehensive employment data is collected from multiple sources to make well-informed policy decisions, then policy effectiveness improves, but data collection and analysis complexity increases

Engineering Contradiction:
Improvepolicy decision accuracyVSAvoiddata collection system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The machine learning system serves multiple functions: it collects data from various employment sources, processes and cleans the data, identifies patterns, generates policy recommendations, and evaluates policy effectiveness. This multi-functional approach consolidates what would otherwise require separate systems into a single unified platform.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent introduces an intermediary layer of data processing and feature engineering between raw employment data and policy recommendations. This intermediary layer standardizes and structures diverse data sources, making them compatible for analysis while simplifying the overall system architecture.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Speed

If businesses independently make decisions during chaotic events like pandemics, then each business can respond quickly, but cumulative negative effects on the public worsen due to lack of coordination

Engineering Contradiction:
Improveresponse speed to chaotic eventsVSAvoidcumulative public impact
Core Design Contradiction:
SpeedVSObject-affected harmful factors

Solution Approach 1:

The system incorporates feedback mechanisms that allow businesses to share policy outcomes and employment data patterns. The machine learning model learns from aggregated data across multiple businesses, enabling each business to benefit from collective insights while maintaining independent decision-making capability and fast response times.

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS11403578B2Multi-task deep learning of health care outcomes
Publication Date: 2022.08.02 ADP INC
  • US11403578B2 patent drawing
  • US11403578B2 patent drawing
  • US11403578B2 patent drawing

AI summary

A method for generating a communicable disease policy plan by using machine learning. The process identifies a number of workplace policies for a number of business entities. The workplace policies comprise a number of dimensions of data collected from a number of sources. The process collects employment data for each of the business entities. The employment data includes sick leave data about employees of the plurality of business entities. The process determines metrics for the sick leave data during a given time interval; simultaneously models the workplace policies and the metrics for the sick leave data to identify correlations among the number of dimensions of data and generalize rules for predicting effective workplace policies; predicts a number of effective workplace policies for a particular business entity; and generates a communicable disease policy plan for the particular business entity based on the number of effective workplace policies.