[Paper Review] OCEL (Object-Centric Event Log) 2.0 Specification

Alessandro Berti, István Koren+11 more|arXiv (Cornell University)|Mar 4, 2024

Scientific Computing and Data Management8 citations

TL;DR

OCEL 2.0 specifies an enhanced object-centric event log standard with support for object relationships, dynamic object attributes, qualifiers, and three exchange formats (relational SQLite, XML, JSON) to advance object-centric process mining.

ABSTRACT

Object-Centric Event Logs (OCELs) form the basis for Object-Centric Process Mining (OCPM). OCEL 1.0 was first released in 2020 and triggered the development of a range of OCPM techniques. OCEL 2.0 forms the new, more expressive standard, allowing for more extensive process analyses while remaining in an easily exchangeable format. In contrast to the first OCEL standard, it can depict changes in objects, provide information on object relationships, and qualify these relationships to other objects or specific events. Compared to XES, it is more expressive, less complicated, and better readable. OCEL 2.0 offers three exchange formats: a relational database (SQLite), XML, and JSON format. This OCEL 2.0 specification document provides an introduction to the standard, its metamodel, and its exchange formats, aimed at practitioners and researchers alike.

Motivation & Objective

• Motivate and describe the need for object-centric event data in process mining beyond traditional case-centric logs.
• Present a formally defined metamodel for OCEL 2.0 that supports object-to-object (O2O) relationships and dynamic attribute values.
• Define three practical exchange formats (relational SQLite, XML, JSON) that faithfully implement the OCEL 2.0 metamodel.
• Show how OCEL 2.0 extends OCEL 1.0 to enable more expressive and scalable analyses while remaining exchangeable.
• Provide guidance for practitioners and researchers to implement conformant process mining tools and resources.

Proposed method

• Introduce OCEL 2.0 as a metamodel and formal definitions for object-centric event logs.
• Extend OCEL 1.0 by adding Object-to-Object (O2O) relationships, dynamic object attribute values, and relationship qualifiers.
• Present a dense-relational (SQLite) implementation with per-type tables and E2O/O2O mappings.
• Describe XML and JSON formats with enhanced schemas to capture event/object attributes and evolving relationships.
• Provide concrete running example to illustrate the metamodel and relational/XML/JSON mappings.

Figure 1 : OCEL 2.0 metamodel

Experimental results

Research questions

• RQ1 How does OCEL 2.0 address limitations of OCEL 1.0 and XES for object-centric data?
• RQ2 What are the formal definitions and universes that underpin OCEL 2.0?
• RQ3 How can OCEL 2.0 be implemented in relational, XML, and JSON formats while preserving semantics?
• RQ4 What capabilities do O2O relationships and attribute dynamics enable for object-centric process mining analyses?

Key findings

• OCEL 2.0 introduces Object-to-Object (O2O) relationships and qualifiers for E2O and O2O relationships.
• Object attributes can have dynamic values over time, enabling evolving object state tracking.
• Event-to-Object (E2O) relationships are qualified to describe object roles in events, and O2O relationships can be qualified as well.
• The standard uses dense relational tables to improve storage efficiency and scalability for multiple event/object types.
• XML and JSON specifications are enhanced to represent complex data, including object evolution and inter-object relations.
• A relational SQLite implementation is provided with per-type tables and explicit E2O/O2O mappings, alongside corresponding XML/JSON schemas.

Figure 2 : Linking the OCEL 2.0 metamodel to the formalization in Definition 2 .