Natural language querying of process execution data - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Information Systems Année : 2023

Natural language querying of process execution data

Résumé

Process-oriented data analysis techniques allow organizations to understand how their processes operate, where modifications are needed and where enhancements are possible. A recurrent task in any process analysis technique is querying. Process data querying allows analysts to easily explore the data with the intent of getting insights about the execution of business processes. The current generation of process query languages targets data scientists. However, there is a need to a query language to support domain analysts who may be inexperienced with database technologies. This paper addresses this challenge by proposing a natural language interface that assists the end-users in querying the stored event data. The interface takes a natural language query from the user, automatically constructs a corresponding structured query to be executed over the stored event data. We use graph based storage techniques, namely labeled property graphs, which allow to explicitly model event data relationships. As an executable query language, we use the Cypher language which is widely used for querying property graphs. The approach has been implemented and evaluated using two publicly available event logs.
Fichier non déposé

Dates et versions

hal-04376914 , version 1 (07-01-2024)

Identifiants

Citer

Meriana Kobeissi, Nour Assy, Walid Gaaloul, Bruno Defude, Boualem Benatallah, et al.. Natural language querying of process execution data. Information Systems, 2023, 116, pp.102227:1-102227:16. ⟨10.1016/J.IS.2023.102227⟩. ⟨hal-04376914⟩
25 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More