Task Process Analysis Using Neural Network Sequence Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for improving or automating task processes are limited as they focus on specific tasks rather than entire task processes, failing to consider the correlation between tasks, which hinders the prediction of subsequent tasks and automation of the entire process.
Innovation Solution
A method involving an electronic device that collects work history data, including log and image data, to create sequence data for a task prediction module using neural networks, enabling the prediction of subsequent tasks by analyzing the entire task process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If existing methods focus on specific tasks for analysis, then analysis complexity is reduced, but the ability to predict subsequent tasks and automate entire processes is limited
Solution Approach 1:
The patent segments the task analysis process into distinct components: work history collection module that gathers raw data, preprocessing module that structures data into sequences, and task prediction module that generates predictions. This segmentation allows the system to handle entire task processes systematically while maintaining manageable complexity at each stage.
Solution Approach 2:
The patent transitions from analyzing isolated specific tasks to analyzing entire task processes by adding the dimension of temporal sequencing. The preprocessing module creates sequence data that captures the chronological order and relationships between multiple tasks, enabling predictions about subsequent tasks based on historical task patterns.
2Measurement precision
If the analysis target is expanded to entire task processes, then task prediction capability is improved, but data collection and processing complexity increases
Solution Approach 1:
The preprocessing module performs preliminary actions by collecting and structuring work history data into standardized sequence formats before prediction analysis. This preprocessing step organizes raw work history data into a consistent structure that the task prediction module can efficiently process, reducing the complexity of the overall system.
Solution Approach 2:
The preprocessing module acts as an intermediary between work history collection and task prediction. It transforms raw, unstructured work history data into structured sequence data that bridges the gap between data collection and prediction analysis, simplifying the interfaces between system components.
3Reliability
If work history data including log and image data is collected for entire task process analysis, then prediction reliability is improved, but data storage requirements increase
Solution Approach 1:
The system extracts only the essential features and patterns from comprehensive work history data that are necessary for task prediction. The preprocessing module identifies and extracts relevant sequential patterns from log and image data, discarding redundant information while maintaining prediction reliability.
Solution Approach 2:
The system collects comprehensive work history data including both log and image data (excessive action) to ensure sufficient information for accurate prediction, but the preprocessing module processes only the portions necessary for creating sequence data (partial action), balancing data collection thoroughness with processing efficiency.
Data Source
AI summary
According to an embodiment of the present disclosure, there may be provided a task process analysis method, the method of collecting work history data of an individual or a group to predict a next task that should be performed after a certain task when the individual or the group performs the certain task, and obtaining prediction data about the next task by inputting the collected work history data into a natural language processing model.