Information Output Using Behavior-Aware Policy Flow Graphs

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing flow graphs in policy planning, such as those used in medical care and administration, struggle to incorporate behavior selection into conditional branches, limiting the ability to predict the effects of policies that aim to change individual behaviors.

Innovation Solution

A server device incorporates a behavior selection model into the options of conditional branches in a flow graph, using algorithms like simple behavior models or attribute information use models to predict how individuals will select services, thereby predicting the flow of persons and the effects of policy changes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a flow graph of policy is used without behavior selection models, then the structure remains simple and easy to operate, but the ability to predict policy effects on individual behavior changes is insufficient

Engineering Contradiction:

Improveprediction accuracy of policy effectsVSAvoidcomplexity of flow graph structure

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The behavior selection model is nested within the conditional branches of the flow graph. Each conditional branch contains a behavior selection model that predicts individual behavior choices, allowing the system to maintain the overall simple flow graph structure while incorporating sophisticated prediction capabilities at specific decision points.

Inventive Principle:

Principle #7Nested doll (Nesting)

Solution Approach 2:

The behavior selection model acts as an intermediary between the policy flow graph and the prediction output. It translates policy conditions into predicted individual behavior choices, enabling accurate prediction of policy effects without requiring complex modifications to the overall flow graph structure.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Loss of information

If behavior selection models are incorporated into conditional branches, then the prediction capability of policy effects is improved, but the complexity of the system increases

Engineering Contradiction:

Improveinformation completeness on behavior predictionVSAvoidcomplexity of incorporating behavior models

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The system segments the flow graph into distinct conditional branches, each containing a behavior selection model. This segmentation allows behavior prediction to be applied only where needed in the policy flow, rather than throughout the entire system, reducing overall complexity while maintaining information completeness.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Behavior selection models are applied locally at specific conditional branches where behavior prediction is needed, rather than uniformly across the entire flow graph. This local application optimizes the balance between prediction capability and system complexity by concentrating computational resources only where behavior selection impacts policy outcomes.

Inventive Principle:

Principle #3Local quality

3Productivity

If traditional flow graphs are used without behavior prediction, then the system is easier to manufacture and implement, but the ability to evaluate policy impacts on service utilization is limited

Engineering Contradiction:

Improveefficiency of policy evaluationVSAvoidease of implementing flow graph system

Core Design Contradiction:

ProductivityVSEase of manufacture

Solution Approach 1:

The behavior selection models perform preliminary prediction of individual behavior choices before policy implementation. By predicting how individuals will respond to policy conditions in advance, the system enables more efficient policy evaluation and planning, allowing stakeholders to assess potential impacts on service utilization before committing resources.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250308679A1Computer-readable recording medium storing information output program, information output method, and information processing device

Publication Date: 2025.10.02 FUJITSU LTD

AI summary

An information output program for causing a computer to execute a process includes: identifying a flow of persons in a route that includes a plurality of options by using a behavior selection model that indicates which behavior a person selects for a policy; generating information that indicates a prediction result of the policy based on an identified flow of persons; and outputting generated information of a prediction result of policy to a display screen.