Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Anda dapat mengonversi invoice menjadi data terstruktur di Cloud Data Fusion menggunakan plugin Invoice Parser, yang didukung oleh Document AI. Data terstruktur disimpan di BigQuery.
Sebelum memulai
Untuk mengurai invoice, Anda memerlukan instance Cloud Data Fusion yang berjalan dalam
versi 6.4.1 atau yang lebih baru. Untuk mengetahui informasi selengkapnya, lihat
Mengupgrade instance Cloud Data Fusion.
Membuat pemroses
Di Google Cloud console, buka halaman Processors
Document AI.
Pastikan instance yang diinginkan telah diupgrade ke versi 6.4.1 atau yang lebih baru. Untuk versi sebelumnya, upgrade instance.
Klik Lihat instance.
UI Cloud Data Fusion akan terbuka.
Klik Hub.
Klik GCP, lalu deploy Plugin GCP.
Klik DocAI, lalu deploy Plugin Doc AI.
Klik Invoice Parser Quickstart>Create.
Sesuaikan pipeline Anda dengan memasukkan ID pemroses Invoice Parser,
jalur bucket Cloud Storage, dan detail tabel BigQuery.
Men-deploy dan menjalankan pipeline.
Invoice yang diuraikan disimpan dalam tabel output di BigQuery.
Metadata dari invoice disimpan di tabel Metadata dan mencakup status penguraian, jalur Cloud Storage, dan stempel waktu upload invoice mentah. Data dalam tabel output dan metadata dapat digabungkan dengan
kunci invoice_uuid.
[[["Mudah dipahami","easyToUnderstand","thumb-up"],["Memecahkan masalah saya","solvedMyProblem","thumb-up"],["Lainnya","otherUp","thumb-up"]],[["Sulit dipahami","hardToUnderstand","thumb-down"],["Informasi atau kode contoh salah","incorrectInformationOrSampleCode","thumb-down"],["Informasi/contoh yang saya butuhkan tidak ada","missingTheInformationSamplesINeed","thumb-down"],["Masalah terjemahan","translationIssue","thumb-down"],["Lainnya","otherDown","thumb-down"]],["Terakhir diperbarui pada 2025-09-04 UTC."],[[["\u003cp\u003eThe Invoice Parser plugin in Cloud Data Fusion, powered by Document AI, allows you to convert invoices into structured data.\u003c/p\u003e\n"],["\u003cp\u003eParsed data from invoices is stored in BigQuery, with invoice metadata stored in a separate table for additional information.\u003c/p\u003e\n"],["\u003cp\u003eTo use the Invoice Parser plugin, you must have a Cloud Data Fusion instance running version 6.4.1 or later and you need to have created an Invoice Parser processor in Document AI.\u003c/p\u003e\n"],["\u003cp\u003eThe pipeline is customizable, allowing you to specify the Invoice Parser processor ID, Cloud Storage bucket path, and BigQuery table details during configuration.\u003c/p\u003e\n"]]],[],null,["# Parse invoices\n\nYou can convert invoices into structured data in Cloud Data Fusion\nusing the Invoice Parser plugin, which is powered by Document AI. The\nstructured data gets stored in BigQuery.\n\nBefore you begin\n----------------\n\nTo parse invoices, you need a Cloud Data Fusion instance running in\nversion 6.4.1 or later. For more information, see\n[Upgrading Cloud Data Fusion instances](/data-fusion/docs/how-to/upgrading#upgrade-instances).\n\nCreate a processor\n------------------\n\n1. In the Google Cloud console, go to the Document AI **Processors**\n page.\n\n [Go to Processors](https://console.cloud.google.com/ai/document-ai/processors)\n2. [Create a processor](/document-ai/docs/create-processor). Select **Invoice\n parser** as the type of processor.\n\n | **Note:** When you create the processor, copy the processor ID for your plugin configurations.\n\nConfigure the invoice parser plugin\n-----------------------------------\n\n1. In the Google Cloud console, go to the Cloud Data Fusion **Instances**\n page.\n\n [Go to Instances](https://console.cloud.google.com/data-fusion/locations/-/instances)\n2. Ensure that the desired instance has been upgraded to version 6.4.1 or\n later. For earlier versions, [upgrade the instance](/data-fusion/docs/how-to/upgrading).\n\n3. Click **View instance**.\n The Cloud Data Fusion UI opens.\n\n4. Click **Hub**.\n\n5. Click **GCP** , and then deploy **GCP Plugins**.\n\n6. Click **DocAI** , and then deploy the **Doc AI Plugins**.\n\n7. Click the **Invoice Parser Quickstart** \\\u003e **Create**.\n\n8. Customize your pipeline by entering the Invoice Parser processor ID,\n Cloud Storage bucket path, and BigQuery table details.\n\n9. Deploy and run the pipeline.\n\nParsed invoices are stored in the output table in BigQuery.\nMetadata from the invoices is stored in the `Metadata` table and includes\nparsing status, Cloud Storage path, and upload timestamp of the raw\ninvoice. Records in the output and metadata tables can be joined with the\n`invoice_uuid` key."]]
