[[["容易理解","easyToUnderstand","thumb-up"],["確實解決了我的問題","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["難以理解","hardToUnderstand","thumb-down"],["資訊或程式碼範例有誤","incorrectInformationOrSampleCode","thumb-down"],["缺少我需要的資訊/範例","missingTheInformationSamplesINeed","thumb-down"],["翻譯問題","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["上次更新時間：2025-09-04 (世界標準時間)。"],[[["\u003cp\u003eDocument AI offers pretrained parsers designed to extract key-value pairs from various document types without requiring users to specify the extraction schema.\u003c/p\u003e\n"],["\u003cp\u003eParsers like Bank Statement, W2, US Passport, Utility, Pay Slip, US Driver License, Expense, and Invoice Parsers can extract generic entities from their respective document types, with the quantity of entities extracted varying between parsers.\u003c/p\u003e\n"],["\u003cp\u003eIdentity Document Proofing Parser can predict the validity of ID documents, identifying fraud signals like image manipulation, suspicious words, or online duplicates.\u003c/p\u003e\n"],["\u003cp\u003eMany parsers including bank statements, pay slip, expense, and invoice, support Enrichment and/or Normalization features for enhanced data processing.\u003c/p\u003e\n"],["\u003cp\u003eThe Summarizer feature within Document AI can create abstract or bullet point summaries for documents, with the option to adjust the length of the summary.\u003c/p\u003e\n"]]],[],null,["# Pretrained overview\n===================\n\nDocument AI offers multiple products to process documents for information\nfor different use cases.\n\nPretrained parsers\n------------------\n\nFor more information, go to [Explore pretrained processors](/document-ai/docs/processors-list#explore_pretrained_processors).\n\n### Bank statement parser\n\nBank statement parser extracts key-value pairs (KVP). It can extract up\nto 17 generic entities. Examples include: Account number, client name, bank name,\nand table items like deposits and withdrawals. You don't specify the fields\n(schema) you want to extract. Bank statement parser supports [Enrichment](/document-ai/docs/enrichment)\nand [Normalization](/document-ai/docs/normalization).\n\n### W2 parser\n\nW2 parser extracts from the IRS Form W2 as KVP. It can extract up\nto 12 generic entities, including employee name, Social Security Number,\nemployer, and wages. You don't specify the fields (schema) you want\nto extract. W2 parser supports [Enrichment](/document-ai/docs/enrichment).\n\n### US passport parser\n\nUS passport parser extracts KVP. It can extract up to seven generic entities. These include given names, family names, document ID, and\ndate of birth. You don't specify the fields (schema) you want to\nextract. US passport parser supports [Normalization](/document-ai/docs/normalization).\n\n### Utility parser\n\nUtility parser extracts KVP. It can extract up to 75 generic entities\nfrom utility bills. These include supplier name, previous paid amount, and line items like amount, description, and product code and quantity. You don't specify the fields (schema) you want to extract with the\nutility parser.\n\n### Identity document proofing parser\n\nIdentity document proofing parser predicts the validity of ID documents\nusing multiple signals.\n\n- `fraud_signals_is_identity_document` detection: Predicts whether an image contains a recognized identity document.\n- `fraud_signals_suspicious_words` detection: Predicts whether words are present that aren't typical on IDs.\n- `fraud_signals_image_manipulation` detection: Predicts whether the image was altered or tampered with an image editing tool.\n- `fraud_signals_online_duplicate` detection: Predicts whether the image can be found online (US only).\n\n### Pay slip parser\n\nPay slip parser extracts KVP. It can extract up to 26 generic entities from pay\nslips. These include employee name, bonus, commissions, overtime, and pay date.\nYou don't specify the fields (schema) you want to extract. Pay slip parser supports [Enrichment](/document-ai/docs/enrichment) and\n[Normalization](/document-ai/docs/normalization).\n\n### US driver license parser\n\nUS driver license parser extracts KVP. It can extract up to eight generic entities\nfrom a driver license. Examples include: Given name, family name, document ID, and\nexpiration date. You don't specify the fields (schema) you want to\nextract. US driver license parser supports [Normalization](/document-ai/docs/normalization).\n\n### Expense parser\n\nExpense parser extracts KVP. It can extract up to 17 generic entities from expense\nreports. Examples include: Expense date, supplier name, total amount, and currency.\nYou don't specify the fields (schema) you want to extract. Expense parser supports [Enrichment](/document-ai/docs/enrichment) and\n[Normalization](/document-ai/docs/normalization).\n\n### Invoice Parser\n\nInvoice Parser extracts KVP. It can extract up to 46 generic entities\nfrom invoices. These include invoice number, supplier name, invoice amount, tax\namount, invoice date, and due date. You don't specify the fields (schema) you want to extract. Invoice Parser supports [Enrichment](/document-ai/docs/enrichment)\nand [Normalization](/document-ai/docs/normalization).\n\nSummarizer\n----------\n\n[Summarizer](/document-ai/docs/custom-summarizer) gives abstract and bullet point\nsummaries for short and long documents. Summarizer also lets you specify the\noutput length of the summary as comprehensive, medium, or brief."]]
