{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T06:30:54Z","timestamp":1765866654980,"version":"3.48.0"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T00:00:00Z","timestamp":1765843200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Due to the complexity of hotel operation processes, abnormal situations are inevitable, making proactive anomaly prediction essential for ensuring operational stability. Although current deep learning methods can encode control and data flows to predict anomalies in attributes like activity and time, they often fail to adequately represent the behavioral relationships between activities and lack specific mechanisms to model the interaction between control and data flows. To address these challenges, this paper proposes a business process anomaly prediction method based on a Multi-perspective Graph Transformer and Auto Encoder (MLGTAE). The proposed method first constructs multi-perspective trace graphs by combining Petri nets\u2014which capture process behaviors\u2014with data attributes such as time and resources. It then leverages an attention mechanism to achieve deep semantic interaction between process behavior and data, followed by a decoder that performs reconstruction to detect anomalies. Validated on multiple real-world datasets, the results demonstrate that MLGTAE outperforms existing state-of-the-art methods, showing superior accuracy in predicting anomalies at both the activity and data attribute levels.<\/jats:p>","DOI":"10.3389\/frai.2025.1682701","type":"journal-article","created":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T06:26:39Z","timestamp":1765866399000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-perspective hotel operation process anomaly prediction method based on graph transformer and autoencoder"],"prefix":"10.3389","volume":"8","author":[{"given":"Yidan","family":"Ma","sequence":"first","affiliation":[]},{"given":"Yue","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Xinsheng","family":"Fang","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,12,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.is.2012.04.004","article-title":"Algorithms for anomaly detection of traces in logs of process aware information systems","volume":"38","author":"Bezerra","year":"2013","journal-title":"Inf. Syst."},{"key":"B2","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/978-3-319-65000-5_5","article-title":"\u201cMulti instance anomaly detection in business process executions,\u201d","volume-title":"Business Process Management","author":"B\u00f6hmer","year":"2017"},{"key":"B3","doi-asserted-by":"publisher","first-page":"101438","DOI":"10.1016\/j.is.2019.101438","article-title":"Mining association rules for anomaly detection in dynamic process runtime behavior and explaining the root cause to users","volume":"90","author":"B\u00f6hmer","year":"2020","journal-title":"Inf. Syst."},{"key":"B4","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1007\/s10115-019-01365-y","article-title":"Anomaly detection of event sequences using multiple temporal resolutions and Markov chains","volume":"62","author":"Boldt","year":"2020","journal-title":"Knowl. Inf. Syst."},{"key":"B5","doi-asserted-by":"publisher","first-page":"3279","DOI":"10.1109\/TKDE.2021.3126456","article-title":"A general survey on attention mechanisms in deep learning","volume":"35","author":"Brauwers","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"B6","doi-asserted-by":"publisher","first-page":"7464","DOI":"10.1609\/aaai.v34i05.6243","article-title":"Graph transformer for graph-to-sequence learning","volume":"34","author":"Cai","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"B7","volume-title":"Sepsis Survival Minimal Clinical Records","author":"Chicco","year":"2020"},{"key":"B8","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/s40537-023-00708-5","article-title":"Deep reinforcement learning for data-efficient weakly supervised business process anomaly detection","volume":"10","author":"Elaziz","year":"2023","journal-title":"J. Big Data"},{"key":"B9","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/s10844-018-0501-z","article-title":"Discovering anomalous frequent patterns from partially ordered event logs","volume":"51","author":"Genga","year":"2018","journal-title":"J. Intell. Inf. Syst."},{"key":"B10","doi-asserted-by":"publisher","first-page":"e0152173","DOI":"10.1371\/journal.pone.0152173","article-title":"A comparative evaluation of unsupervised anomaly detection algorithms for multivariate data","volume":"11","author":"Goldstein","year":"2016","journal-title":"PLoS ONE"},{"key":"B11","author":"Guan","year":"","journal-title":"GAMA: A Multi-Graph-Based Anomaly Detection Framework for Business Processes Via Graph Neural Networks"},{"key":"B12","doi-asserted-by":"publisher","first-page":"3412","DOI":"10.1109\/TSC.2023.3262405","article-title":"GRASPED: a GRU-AE network based multi-perspective business process anomaly detection model","volume":"16","author":"Guan","year":"","journal-title":"IEEE Trans. Serv. Comput."},{"key":"B13","first-page":"4475","article-title":"\u201cImproving transformer optimization through better initialization,\u201d","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML'20), Vol. 119","author":"Huang","year":"2020"},{"key":"B14","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1007\/978-3-030-85469-0_26","article-title":"\u201cGraph autoencoders for business process anomaly detection,\u201d","volume-title":"Business Process Management","author":"Huo","year":"2021"},{"key":"B15","doi-asserted-by":"publisher","first-page":"4039","DOI":"10.1609\/aaai.v33i01.33014039","article-title":"Precision-recall versus accuracy and the role of large data sets","volume":"33","author":"Juba","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"B16","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1109\/ICPM49681.2020.00032","article-title":"\u201cAnomaly detection on event logs with a scarcity of labels,\u201d","volume-title":"2020 2nd International Conference on Process Mining (ICPM)","author":"Junior","year":"2020"},{"key":"B17","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.ins.2020.11.017","article-title":"Detecting anomalies in business process event logs using statistical leverage","volume":"549","author":"Ko","year":"2021","journal-title":"Inf. Sci."},{"key":"B18","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1007\/s12599-023-00794-y","article-title":"A systematic review of anomaly detection for business process event logs","volume":"65","author":"Ko","year":"2023","journal-title":"Bus. Inf. Syst. Eng."},{"key":"B19","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.procs.2021.08.005","article-title":"Semi-supervised anomaly detection in business process event data using self-attention based classification","volume":"192","author":"Krajsic","year":"2021","journal-title":"Procedia Comput. Sci."},{"key":"B20","doi-asserted-by":"publisher","first-page":"178536","DOI":"10.1109\/ACCESS.2024.3502361","article-title":"Optimized ensemble methods for classifying imbalanced water quality index data","volume":"12","author":"Lawal","year":"2024","journal-title":"IEEE Access"},{"key":"B21","doi-asserted-by":"publisher","first-page":"103498","DOI":"10.1016\/j.compind.2021.103498","article-title":"A survey on anomaly detection for technical systems using LSTM networks","volume":"131","author":"Lindemann","year":"2021","journal-title":"Comput. Ind."},{"key":"B22","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1007\/978-3-319-42887-1_11","article-title":"\u201cDetecting deviating behaviors without models,\u201d","volume-title":"Business Process Management Workshops","author":"Lu","year":"2016"},{"key":"B23","doi-asserted-by":"publisher","first-page":"109713","DOI":"10.1016\/j.automatica.2021.109713","article-title":"Marking diagnosability verification in labeled Petri nets","volume":"131","author":"Ma","year":"2021","journal-title":"Automatica"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1145\/3487553.3524258","article-title":"Universal graph transformer self-attention networks","author":"Nguyen","year":"2022","journal-title":"arXiv"},{"key":"B25","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.eswa.2019.04.052","article-title":"Autoencoders for improving quality of process event logs","volume":"131","author":"Nguyen","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"B26","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1007\/s10994-018-5702-8","article-title":"Analyzing business process anomalies using autoencoders","volume":"107","author":"Nolle","year":"2018","journal-title":"Mach. Learn."},{"key":"B27","doi-asserted-by":"publisher","first-page":"101458","DOI":"10.1016\/j.is.2019.101458","article-title":"BINet: multi-perspective business process anomaly classification","volume":"103","author":"Nolle","year":"2022","journal-title":"Inf. Syst."},{"key":"B28","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1145\/3297280.3297326","article-title":"\u201cAn anomaly detection technique for business processes based on extended dynamic bayesian networks,\u201d","volume-title":"Proceedings of the 34th ACM\/SIGAPP Symposium on Applied Computing","author":"Pauwels","year":"2019"},{"key":"B29","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-031-46846-9_22","article-title":"\u201cBAnDIT: business process anomaly detection in transactions,\u201d","volume":"14353","author":"Rudolf","year":"2024","journal-title":"Switzerland)"},{"key":"B30","first-page":"1","article-title":"\u201cControl-flow based anomaly detection in the bug-fixing process of open-source projects,\u201d","volume-title":"Proceedings of the 13th Innovations in Software Engineering Conference (formerly known as India Software Engineering Conference)","author":"Saini","year":"2020"},{"key":"B31","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1186\/s40537-019-0277-1","article-title":"Anomaly detection in business processes using process mining and fuzzy association rule learning","volume":"7","author":"Sarno","year":"2020","journal-title":"J. Big Data"},{"key":"B32","volume-title":"BPI Challenge 2013, Open Problems","author":"Steeman","year":"2013"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.2298\/CSIS220110005T","article-title":"Matching business process behavior with encoding techniques via meta-learning: an anomaly detection study","volume":"20","author":"Tavares","year":"2023","journal-title":"Comput. Sci. Inf. Syst."},{"key":"B34","doi-asserted-by":"publisher","first-page":"106557","DOI":"10.1016\/j.knosys.2020.106557","article-title":"Business process variant analysis: survey and classification","volume":"211","author":"Taymouri","year":"2021","journal-title":"Knowl. Based Syst."},{"key":"B35","doi-asserted-by":"publisher","first-page":"101824","DOI":"10.1016\/j.is.2021.101824","article-title":"Natural language-based detection of semantic execution anomalies in event logs","volume":"102","author":"Van der Aa","year":"2021","journal-title":"Inf. Syst."},{"key":"B36","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1007\/978-3-642-31131-4_9","article-title":"\u201cOn profiles and footprints \u2013 relational semantics for Petri nets,\u201d","volume-title":"Application and Theory of Petri Nets","author":"Weidlich","year":"2012"},{"key":"B37","first-page":"11983","article-title":"\u201cGraph transformer networks,\u201d","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems","author":"Yun","year":"2019"},{"key":"B38","doi-asserted-by":"publisher","first-page":"2645","DOI":"10.1007\/s11063-020-10404-7","article-title":"Semi-supervised classification of graph convolutional networks with laplacian rank constraints","volume":"54","author":"Zhang","year":"2022","journal-title":"Neural Process. Lett."},{"key":"B39","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1109\/TASE.2020.3027532","article-title":"Heuristic scheduling of batch production processes based on Petri nets and iterated greedy algorithms","volume":"19","author":"Zhao","year":"2022","journal-title":"IEEE Trans. Autom. Sci. Eng."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1682701\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T06:26:46Z","timestamp":1765866406000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1682701\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,16]]},"references-count":39,"alternative-id":["10.3389\/frai.2025.1682701"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1682701","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,16]]},"article-number":"1682701"}}