- Überblick
- Erstellen von Modellen
- Verbrauchen von Modellen
- Automatisierungen in Document Understanding™
- Aktivitäten
- API-Aufrufe
- Generative Funktionen
- ML-Pakete
- 1040 – ML-Paket
- 1040 Anlage C – ML-Paket
- 1040 Anlage D – ML-Paket
- 1040 Anlage E – ML-Paket
- 1040x – ML-Paket
- 3949a – ML-Paket
- 4506T – ML-Paket
- 709 – ML-Paket
- 9465 – ML-Paket
- ACORD125 – ML-Paket
- ACORD126 – ML-Paket
- ACORD131 – ML-Paket
- ACORD140 – ML-Paket
- ACORD25 – ML-Paket
- Bank Statements – ML-Paket
- BillsOfLading – ML-Paket
- Certificate of Incorporation – ML-Paket
- Certificates of Origin – ML-Paket
- Checks – ML-Paket
- Children Product Certificate – ML-Paket
- CMS1500 – ML-Paket
- EU Declaration of Conformity – ML-Paket
- Financial Statements – ML-Paket
- FM1003 – ML-Paket
- I9 – ML-Paket
- ID Cards – ML-Paket
- Invoices – ML-Paket
- InvoicesAustralia – ML-Paket
- InvoicesChina – ML-Paket
- Rechnungen Hebräisch – ML-Paket
- InvoicesIndia – ML-Paket
- InvoicesJapan – ML-Paket
- Invoices Shipping – ML-Paket
- Packing Lists – ML-Paket
- Gehaltsabrechnungen (Pay slips) – ML-Paket
- Passports – ML-Paket
- Purchase Orders – ML-Paket
- Receipts – ML-Paket
- RemittanceAdvices – ML-Paket
- UB04 – ML-Paket
- Utility Bills – ML-Paket
- Vehicle Titles – ML-Paket
- W2 – ML-Paket
- W9 – ML-Paket
- Öffentliche Endpunkte
- Unterstützte Sprachen
- Daten und Sicherheit
- Lizenzierungs- und Gebührenlogik
- Anleitungen zu …
Generative Funktionen
Diese Funktion ist derzeit Teil eines Prüfungsprozesses und gilt erst nach Abschluss der Überprüfung als Teil der FedRAMP-Autorisierung. Hier finden Sie die vollständige Liste der Funktionen, die derzeit überprüft werden.
Generative KI ist eine Form der KI-Technologie, die Machine-Learning-Modelle (ML) nutzt, um neue Inhalte, Daten oder Informationen zu erstellen und zu generieren.
Ausschlaggebend für die meisten generativen KI-Aufgaben sind Large Language Models (LLMs). Dabei handelt es sich um ML-Modelle, die mit einer großen Menge von Textdaten trainiert werden, um Text zu generieren, der klingt, als wäre er von einem Menschen verfasst worden. LLMs können auch Eingabeaufforderungen verstehen und darauf reagieren, indem sie Sätze oder Absätze auf eine menschliche Art vervollständigen.
Primarily applied during the automatic annotation process of documents in the Build step, these generative models accelerate taxonomy design and help in training models efficiently.
Pre-annotation in Document Understanding is done using a combination of generative and specialized models, based on the document type's schema. The schema clearly defines the fields you want to extract from a particular document type.
To get a deeper understanding of how Generative Annotation works and how you can use it efficiently in your projects, check the Annotate documents page.
Generative extraction is a crucial feature within Document UnderstandingTM that uses the power of generative AI models. These models are configured using activities and are primarily used at runtime for data extraction.
Generative extraction is capable of deciphering and extracting specific information from unstructured or semi-structured documents. For instance, it can scan through an invoice and accurately retrieve details such as the date, billed amount, and company name. This enables fast, efficient, and highly accurate information gathering from various types of documents.
- Document Understanding activities package:
- Extract Document Data, Prompt parameter after choosing the Generative extractor.
- Document Understanding ML activities package:
- IntelligentOCR activities package:
- Data Extraction Scope, ApplyAutoValidation parameter.
You can also use Document Understanding APIs to leverage generative extraction features.
Generative classification uses AI models to automatically classify documents immediately after they are uploaded.
This automatic classification process leverages ML models to 'read' the content of a document, understand its context, and consequently classify it into predefined categories. This way, the system can handle and organize multiple types of documents efficiently.
By accurately classifying unstructured or semi-structured documents, Generative Classification improves the document processing workflow, saves time, and enhances the overall document management.
- Document Understanding activities package:
- Document Understanding ML activities package:
You can also use Document Understanding APIs to leverage generative classification features.
Generative validation is a distinctive feature in Document Understanding that plays an important role during the validation process. This feature is primarily used after the extraction step to validate the confidence score for the extraction made using specialized models.
When a ML model's confidence score for a document extraction is low, generative validation is used to cross-check the output. This validation process involves both the specialized and generative ML models working together to ensure accuracy.
If both models yield the same output, human validation can be bypassed, leading to a significant enhancement in the time efficiency of validation. This process not only saves valuable time in the document validation step but also improves the performance of your models by employing a secondary generative model to cross-verify the output, ensuring a higher level of accuracy.
- Document Understanding activities package:
- Extract Document Data, Auto-validation parameter
- IntelligentOCR activities package:
- Data Extraction Scope, ApplyAutoValidation and AutoValidationConfidenceThreshold parameters
You can also use Document Understanding APIs to leverage generative validation features.
