Optimal alignment of business process models based on log probability distribution

Optimal alignment of business process models based on log probability distribution | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Optimal alignment of business process models based on log probability distribution Xinjian Fang, Duoqin Li, Ke Lu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3852504/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Relying only on the cost function to calculate the optimal alignment between the model and the log may cause the alignment results to fail to accurately reflect the deviation between the actual process and the modeled process. In order to solve this problem, an optimal alignment selection strategy combining conformance log probability distribution and the cost function is proposed. Firstly, a log probability automata is constructed based on the conformance event log. Then, all possible execution sequences of the model are obtained and pre-aligned with the non-conformance log based on the cost function. Finally, all asynchronous moving left and right associative event pairs in pre-alignment are determined, and the average confidence value of the direct following dependency relationship of these event pairs is obtained according to the log probability automata. The concept of credibility value is proposed by combining the average confidence value with the pre-aligned cost value, and the alignment with the highest credibility value is considered as the optimal alignment. In the evaluation section, a large number of alignment results are evaluated, and the results show that compared with the existing two alignment methods that only based on cost function, the average alignment accuracy of the proposed method is improved by 5.55% and 10.97% respectively under various noises, and the alignment accuracy is the most stable. log probability distribution directly follow dependency cost function optimal alignment process mining Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-3852504","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":267009060,"identity":"1d2a2e50-5b16-4a58-aa08-cae32372ccc2","order_by":0,"name":"Xinjian Fang","email":"","orcid":"","institution":"Anhui University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Xinjian","middleName":"","lastName":"Fang","suffix":""},{"id":267009061,"identity":"9d5266f9-3736-44fe-ade2-02f24cfa0171","order_by":1,"name":"Duoqin Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAu0lEQVRIiWNgGAWjYDCCA0CcwMAgw8be2PjgAylaeNh4DjcbziBaCxDwMEikt0lzEKOD70bywRsPdzDw8Ek+bJBmYLCT020goEXyRlqyReIZoMOkExuMCxiSjc0OENBicCPHTCKxDaIleQbDgcRtxGuRPNhwmIc0LRKMjc1EaZE88wzoF5AWnsRmxhkGRPiF73jywZs/2xjk5NuPP//xocJOjqAWEJBgYPgPcycRyqFaRsEoGAWjYBTgAQDhSD6jPIh7MwAAAABJRU5ErkJggg==","orcid":"","institution":"Anhui University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Duoqin","middleName":"","lastName":"Li","suffix":""},{"id":267009062,"identity":"9b8b10fa-18fc-4bf5-b58b-099e367cc433","order_by":2,"name":"Ke Lu","email":"","orcid":"","institution":"Anhui University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Ke","middleName":"","lastName":"Lu","suffix":""}],"badges":[],"createdAt":"2024-01-11 06:14:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3852504/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3852504/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":51276791,"identity":"171054b0-7baf-4287-8e4b-2a15a46159f2","added_by":"auto","created_at":"2024-02-18 03:24:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":432407,"visible":true,"origin":"","legend":"","description":"","filename":"Optimalalignmentofbusinessprocessmodelsbasedonlogprobabilitydistribution.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3852504/v1_covered_cfff4733-ec47-4eb5-ab7c-885c8ec65621.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Optimal alignment of business process models based on log probability distribution","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"log probability distribution, directly follow dependency, cost function, optimal alignment, process mining","lastPublishedDoi":"10.21203/rs.3.rs-3852504/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3852504/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eRelying only on the cost function to calculate the optimal alignment between the model and the log may cause the alignment results to fail to accurately reflect the deviation between the actual process and the modeled process. In order to solve this problem, an optimal alignment selection strategy combining conformance log probability distribution and the cost function is proposed. Firstly, a log probability automata is constructed based on the conformance event log. Then, all possible execution sequences of the model are obtained and pre-aligned with the non-conformance log based on the cost function. Finally, all asynchronous moving left and right associative event pairs in pre-alignment are determined, and the average confidence value of the direct following dependency relationship of these event pairs is obtained according to the log probability automata. The concept of credibility value is proposed by combining the average confidence value with the pre-aligned cost value, and the alignment with the highest credibility value is considered as the optimal alignment. In the evaluation section, a large number of alignment results are evaluated, and the results show that compared with the existing two alignment methods that only based on cost function, the average alignment accuracy of the proposed method is improved by 5.55% and 10.97% respectively under various noises, and the alignment accuracy is the most stable.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e","manuscriptTitle":"Optimal alignment of business process models based on log probability distribution","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-16 03:38:30","doi":"10.21203/rs.3.rs-3852504/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"53f515d8-b581-4d4d-be82-0cedde3be142","owner":[],"postedDate":"January 16th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-02-18T03:16:05+00:00","versionOfRecord":[],"versionCreatedAt":"2024-01-16 03:38:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3852504","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3852504","identity":"rs-3852504","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}