OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Data & Analytics

Units Of Measure Harmonization Intelligence Platform

A public Apache-2.0 KNIME machine-learning workflow for detecting, validating and harmonizing unit-of-measure errors in structured data.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Units Of Measure Harmonization Intelligence Platform — OpenViST project profile in AI Data & Analytics.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when structured manufacturing, procurement or supply-chain data contains unit fields that need automated screening and review before analysis or operational use.

Who it is for

  • Manufacturing data teams
  • Procurement and supply-chain analysts
  • Teams cleaning inventory, SKU, bill-of-materials or supplier data
  • KNIME users building data-quality workflows

Documented uses

  • Detect unit mismatches, decimal errors, formatting problems and missing UOM fields
  • Validate quantities with conversion rules
  • Review suspected inconsistencies through a visual dashboard
  • Prepare corrected unit-of-measure data for downstream systems or analytics
Before you choose

Requirements & limits

The repository is public and identified with an Apache-2.0 license. The documented workflow requires KNIME Analytics Platform 4.5 or later.

  • It is built as a KNIME workflow rather than a standalone hosted application.
  • The documented pipeline accepts CSV, Excel, tab-separated and pipe-delimited inputs.
  • Its architecture combines XGBoost classification, conversion-rule validation, Q-learning automation and an interactive dashboard.
  • The repository identifies PowerShell as its primary language and Windows as a platform.
  • Published performance figures are project claims and should be evaluated against the reader's own data and workflow requirements.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Import and run the sample UOM validation workflow

Set up the repository in KNIME and execute the documented sample-data workflow.

Before you start

  • A clone of the public repository
  • KNIME Analytics Platform 4.5 or later
  • The repository's workflow folder
  • The sample file data-sample/sample_10k.csv

Steps

  1. Clone the repository and change into its directory.

  2. In KNIME, use File -> Import KNIME Workflow and select the workflow folder.

  3. Right-click the imported workflow and choose Execute.

  4. Select data-sample/sample_10k.csv when prompted, then review the results in the dashboard.

Expected outcome

A KNIME run produces unit-of-measure detection and correction results for the supplied sample data, with dashboard views described by the repository.

Guide limitations

  • This recipe covers the repository's sample-data workflow only; it does not establish compatibility with a particular external data system.
  • The repository's reported processing time, accuracy and automation figures are claims in the project documentation, not independent execution results.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
4 October 2026
Original website title
JulietMirambo/Units_of_Measure_Harmonization-intelligence-platform · Official homepage title · retained in its source language
How we review sourcesSuggest a correction