Site Data Meaning Estimation in Manufacturing Process Modeling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing technologies struggle to create a process model that defines the data structure of site data generated in manufacturing processes when the meaning of data items is unknown, as they require prior knowledge of data item meanings.

Innovation Solution

An information processing system estimates the meaning of data items in site data by selecting start-to-completion achievement data, estimating feature amounts, and comparing them to identify candidate data items indicating predetermined meanings, thereby creating a process model.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If prior knowledge of data item meanings is required to create a process model, then the process model creation is simpler and more direct, but it becomes impossible to handle site data with unknown data item meanings

Engineering Contradiction:

Improveprocess model creation simplicityVSAvoidcapability to handle unknown data meanings

Core Design Contradiction:

Ease of manufactureVSAdaptability or versatility

Solution Approach 1:

The system enables self-service by automatically estimating data item meanings through comparison processing between site data and process model data, eliminating the need for manual annotation or prior knowledge of data meanings while creating process models autonomously

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical process of data annotation and meaning assignment with an automated information processing system that uses comparison processing and estimation algorithms to determine data item meanings automatically

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If site data from multiple departments is collected and analyzed separately, then each department can optimize its own task efficiency, but information sharing and cooperation among departments deteriorates

Engineering Contradiction:

Improvedepartmental task efficiencyVSAvoidinformation sharing among departments

Core Design Contradiction:

ProductivityVSLoss of information

Solution Approach 1:

The system merges site data from multiple departments into a unified process model that preserves both department-specific task information and cross-departmental process relationships, enabling simultaneous local optimization and global coordination

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The process model serves multiple functions: it enables departmental task analysis, facilitates information sharing across departments, and supports overall manufacturing process optimization, making the system universally applicable to various analytical needs

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentEP4651048A1Information processing system and information processing method

Publication Date: 2025.11.19 HITACHI LTD

Figure 1
Figure 2A
Figure 2B

AI summary

An information processing system holds: start-to-completion achievement data which is selected from site data relating to a process including tasks and in which a data item indicating a predetermined meaning is specified; and meaning estimation target data selected from the site data; estimates a candidate of a data item indicating the predetermined meaning from the data items of the meaning estimation target data based on a feature amount of the data item of the start-to-completion achievement data indicating the predetermined meaning and a feature amount of each data item included in the meaning estimation target data; and estimate a data item indicating the predetermined meaning from the candidates based on a result of the comparing the start-to-completion achievement data and the meaning estimation target data in a case in which the candidate is the data item indicating the predetermined meaning.