Caregiver Task Inference Using Location and Stay-Time Data

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for collecting task data in caregiving require human observation, which is burdensome and inefficient, and there is a need for a more convenient and efficient way to gather such data.

Innovation Solution

An information processing system that estimates caregiving-related tasks based on location and time data collected by sensors, using a task category estimation model trained with machine learning to categorize tasks into multiple levels.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If task data is collected using an apparatus to record time and motion study data, then task data can be collected, but an observer must accompany the subject to identify task categories and collect data, which increases device complexity and operational burden

Engineering Contradiction:
Improvetask data collection efficiencyVSAvoidobserver requirement
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system enables self-service data collection by equipping the caregiver with a wearable device that automatically collects location and time information without requiring an external observer. The caregiver's own device serves the function of data collection, eliminating the need for additional personnel.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical system of human observation with an automated electronic system. Sensors and processors automatically track location, time, and task category information, substituting the human observer's manual recording function with automated technological means.

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

2Measurement precision

If an observer accompanies the subject to collect task data, then task categories can be identified accurately, but the process becomes burdensome and inefficient

Engineering Contradiction:
Improvetask category identification accuracyVSAvoiddata collection burden
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system replaces the mechanical process of human observation and manual categorization with an automated electronic system that uses sensors to track location and time, and a processor to automatically determine task categories based on pre-stored location-category relationships.

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

Solution Approach 2:

The system performs preliminary action by pre-storing the relationships between locations and task categories in the device. This advance preparation allows the system to automatically determine task categories without requiring real-time human judgment, thereby reducing operational burden while maintaining accuracy.

Inventive Principle:
Principle #10Preliminary action

3Loss of information

If manual observation methods are used to collect caregiving task data, then comprehensive task information can be gathered, but the process is time-consuming and reduces productivity

Engineering Contradiction:
Improvetask data completenessVSAvoiddata collection speed
Core Design Contradiction:
Loss of informationVSProductivity

Solution Approach 1:

The system replaces manual observation with automated sensing and processing. Location sensors continuously track the caregiver's position, and the processor automatically determines task categories based on location-time relationships, enabling comprehensive data collection without the time constraints of manual methods.

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

Solution Approach 2:

The system enables continuous data collection through automated sensing and processing. The wearable device continuously monitors location and time without interruption, and the processor continuously determines task categories, eliminating the gaps and inefficiencies inherent in manual observation methods.

Inventive Principle:
Principle #20Continuity of useful action

Data Source

PatentEP4704024A1Work division inference method, work division inference program, and information processing device
Publication Date: 2026.03.04 NATIONAL INSTITUTE OF ADVANCED INDUSTRIAL SCIENCE & TECHNOLOGY
  • EP4704024A1 patent drawingFigure 1
  • EP4704024A1 patent drawingFigure 2
  • EP4704024A1 patent drawingFigure 3

AI summary

A task category estimation method of estimating the category of a task performed by a caregiver at a caregiving site includes acquiring location information regarding a plurality of locations to which the caregiver moved at the caregiving site and time information regarding a time that the caregiver stayed at each of the plurality of locations to which the caregiver moved, estimating a category of a task performed by the caregiver at at least one location among the plurality of locations, based on the location information and the time information, and outputting an estimated result of the category of the task performed by the caregiver.