Intelligent Recognition of Counterfeit Goods Text Based on BERT and Multimodal Feature Fusion

Intelligent Recognition of Counterfeit Goods Text Based on BERT and Multimodal Feature Fusion | 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 Article Intelligent Recognition of Counterfeit Goods Text Based on BERT and Multimodal Feature Fusion Tinghao Wang, Yuheng Li, Lijuan Zhou, Ning Luo This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7267617/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 27 Nov, 2025 Read the published version in Scientific Reports → Version 1 posted 15 You are reading this latest preprint version Abstract Counterfeit goods are often imitated through the similarity of pronunciation or character shape of the trade name, for example, '蓝月亮' is altered to'蓝月壳', and this text-level imitation means brings great trouble to consumer identification. However, there is a scarcity of research on intelligent recognition techniques for this phenomenon. Although the Chinese Spelling Correction (CSC) technique provides some ideas for solving this problem, it still faces the challenges of scarce datasets, significant interference of erroneous characters with the contextual semantics, and high confusion between erroneous characters and correct characters in terms of pronunciation or glyphs in practical applications. In view of the above problems, this paper proposed a Corrector-Detector Auxiliary Network named CDANet. Specifically, (i) A lightweight Transformer Block is used to assist in locating erroneous characters to reduce their interference with contextual semantics;(ii) The multimodal information of erroneous characters is deeply exploited by integrating glyph, pinyin, and semantic features to enhance the correction accuracy; (iii) A counterfeit goods text dataset (CGT-Dataset) containing 289,851 samples was constructed to alleviate the problem of data scarcity.The experimental results show that CDANet achieves the current optimal performance on the self-built CGT-Dataset and exhibits excellent generalization ability on three public benchmark datasets, providing an efficient solution for counterfeit goods text recognition. Physical sciences/Mathematics and computing Social science/Science technology and society Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 27 Nov, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 23 Sep, 2025 Reviews received at journal 19 Sep, 2025 Reviewers agreed at journal 11 Sep, 2025 Reviewers agreed at journal 10 Sep, 2025 Reviews received at journal 07 Sep, 2025 Reviewers agreed at journal 07 Sep, 2025 Reviews received at journal 07 Sep, 2025 Reviewers agreed at journal 07 Sep, 2025 Reviewers agreed at journal 07 Sep, 2025 Reviewers agreed at journal 05 Sep, 2025 Reviewers invited by journal 05 Sep, 2025 Editor assigned by journal 05 Sep, 2025 Editor invited by journal 20 Aug, 2025 Submission checks completed at journal 07 Aug, 2025 First submitted to journal 07 Aug, 2025 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-7267617","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":513050954,"identity":"1804543a-e9f0-4b1a-b373-4f368708df08","order_by":0,"name":"Tinghao Wang","email":"","orcid":"","institution":"Hainan University","correspondingAuthor":false,"prefix":"","firstName":"Tinghao","middleName":"","lastName":"Wang","suffix":""},{"id":513050955,"identity":"3248ddd1-3933-4ee0-9347-503ec8e52c7e","order_by":1,"name":"Yuheng Li","email":"","orcid":"","institution":"Hainan University","correspondingAuthor":false,"prefix":"","firstName":"Yuheng","middleName":"","lastName":"Li","suffix":""},{"id":513050956,"identity":"45a72525-c072-4e15-8927-776adc0080b4","order_by":2,"name":"Lijuan Zhou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBElEQVRIiWNgGAWjYDACCSB+YMAGJJmPMTAYQEV5CGlJAGthSyNFC0SZGUIUnxb52c3HJBIK+BL7Z/d8e/Cj4I68uUQC44O3bQzy5ji0MM45liYBdFjijDtntxv2GDwz3DkjgdlwbhuD4c4G7FqYJXLMwFoabuRuk+AxOMy44UYCmzRvG9CDB7BrYYNpmX8j55nkH4PD9kAt7L/xaeGBadlwI4dNGmhLIsgWZnxaJCTSki2AWow33kgzk5YxOJy84czDZsk55yQMN+DQIj8j+eCND3+Oyc67kfxM8s2fw7Ybjicf/PCmzEYely1QcAyZw9jAAIkvvKCGkIJRMApGwSgYyQAAJYBaajii3WQAAAAASUVORK5CYII=","orcid":"","institution":"Hainan University","correspondingAuthor":true,"prefix":"","firstName":"Lijuan","middleName":"","lastName":"Zhou","suffix":""},{"id":513050957,"identity":"3cf7fb42-d28a-4ffc-82b1-efb524357f0f","order_by":3,"name":"Ning Luo","email":"","orcid":"","institution":"Hainan University","correspondingAuthor":false,"prefix":"","firstName":"Ning","middleName":"","lastName":"Luo","suffix":""}],"badges":[],"createdAt":"2025-08-01 05:38:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7267617/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7267617/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-29693-w","type":"published","date":"2025-11-27T15:58:21+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":97178532,"identity":"a95ded7b-a055-47ba-a09b-b2a8ce76e85c","added_by":"auto","created_at":"2025-12-01 16:10:46","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":493091,"visible":true,"origin":"","legend":"","description":"","filename":"IntelligentRecognitionofCounterfeitGoodsTextBasedonBERTandMultimodalFeatureFusionRevised.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7267617/v1_covered_d7766469-723f-46f0-b07c-6d6caf8c1a5d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Intelligent Recognition of Counterfeit Goods Text Based on BERT and Multimodal Feature Fusion","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7267617/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7267617/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Counterfeit goods are often imitated through the similarity of pronunciation or character shape of the trade name, for example, '蓝月亮' is altered to'蓝月壳', and this text-level imitation means brings great trouble to consumer identification. However, there is a scarcity of research on intelligent recognition techniques for this phenomenon. Although the Chinese Spelling Correction (CSC) technique provides some ideas for solving this problem, it still faces the challenges of scarce datasets, significant interference of erroneous characters with the contextual semantics, and high confusion between erroneous characters and correct characters in terms of pronunciation or glyphs in practical applications. In view of the above problems, this paper proposed a Corrector-Detector Auxiliary Network named CDANet. Specifically, (i) A lightweight Transformer Block is used to assist in locating erroneous characters to reduce their interference with contextual semantics;(ii) The multimodal information of erroneous characters is deeply exploited by integrating glyph, pinyin, and semantic features to enhance the correction accuracy; (iii) A counterfeit goods text dataset (CGT-Dataset) containing 289,851 samples was constructed to alleviate the problem of data scarcity.The experimental results show that CDANet achieves the current optimal performance on the self-built CGT-Dataset and exhibits excellent generalization ability on three public benchmark datasets, providing an efficient solution for counterfeit goods text recognition.","manuscriptTitle":"Intelligent Recognition of Counterfeit Goods Text Based on BERT and Multimodal Feature Fusion","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-11 09:37:36","doi":"10.21203/rs.3.rs-7267617/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-23T04:07:37+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-19T07:59:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"161299430132216044769074878978352441406","date":"2025-09-11T06:12:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"200106423160662705920700454102358997976","date":"2025-09-10T10:58:30+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-08T02:33:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"305766987312724715183608778301964910435","date":"2025-09-08T01:50:26+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-08T00:05:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"277183015622166916705870396862297365919","date":"2025-09-07T23:17:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"303199974690967521380901464104209558675","date":"2025-09-07T06:01:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"82773302105099096939906270457663697336","date":"2025-09-05T14:52:20+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-05T09:45:21+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-05T09:41:02+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-08-20T13:24:44+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-07T11:00:11+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-08-07T10:58:45+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"c8ad8fd4-cf2e-4f0f-b187-c6ebf48dbf8b","owner":[],"postedDate":"September 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":54500643,"name":"Physical sciences/Mathematics and computing"},{"id":54500644,"name":"Social science/Science technology and society"}],"tags":[],"updatedAt":"2025-12-01T16:03:53+00:00","versionOfRecord":{"articleIdentity":"rs-7267617","link":"https://doi.org/10.1038/s41598-025-29693-w","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-11-27 15:58:21","publishedOnDateReadable":"November 27th, 2025"},"versionCreatedAt":"2025-09-11 09:37:36","video":"","vorDoi":"10.1038/s41598-025-29693-w","vorDoiUrl":"https://doi.org/10.1038/s41598-025-29693-w","workflowStages":[]},"version":"v1","identity":"rs-7267617","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7267617","identity":"rs-7267617","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}