Skip to content
/ imixs-ml Public

Machine Learning for Business Process Management

License

Notifications You must be signed in to change notification settings

imixs/imixs-ml

Repository files navigation

Imixs-ML

Imixs-ML is a machine learning framework for Imixs-Workflow. The project provides several microservices and APIs which integrate into an Imixs-Workflow environment. This project provides a generic machine learning API to adapt different ML frameworks like the spaCy API or Apache mxnet. In this way the Imixs-ML project combines the concepts of machine learning with the concepts of business process management. This is a powerful and very flexible solution to digitize business processes.

The core concept of Imixs-ML is based on Natural language processing (NLP) which is a subfield of machine learning. With the Named entity recognition (NER) a given stream of text can be analysed and text entities such as people, places or even invoice data such as dates and invoice totals can be extracted. Imixs-ML adapts this concept in its core API and provides classes to integrate NER into the processing life cycle of a Imixs-Workflow system.

The project consists of the following modules:

Imixs-ML Core

The module Imixs-ML Core defines the core interface to access a machine learning framework. It is providing java object classes and a client to access a ML framework.

Learn more in the section Imixs-ML Core.

Imixs-ML Workflow

The Imixs-ML Workflow defines Adapter Classes to be used in a Imixs BPMN workflow model.

Learn more in the section Imixs-ML API.

Imixs-ML spaCy

Imixs-ML-spaCy is a wrapper service to adapt the spaCy API for the Imixs-ML framework.

Learn more in the section Imixs-ML spaCy.

Imixs-ML Training

Imixs-ML-Training is separate training microserve to be use to train existing wokflow data.

Learn more in the section Imixs-ML spaCy.

Contribute

Imixs-ML is open source and your are sincerely invited to participate in it. If you want to contribute to this project please report any issues here. All source are available on Github.

License

Imixs-ML is free software, because we believe that an open exchange of experiences is fundamental for the development of valuable software. All results of this project are provided under the GNU General Public License.

Visual Code

https://k0nze.dev/posts/python-relative-imports-vscode/