The Invoice JP document skill is an AI extraction model designed to capture key data points from Japanese invoices (both in English and Japanese). The Invoice JP skill is a preview skill. It has been trained on a small document set and is intended to be used by citizen developers as a quick-start basis when automating invoice processing within the accounts payable process. The model can be further trained to achieve the desired straight-through-processing rates.

The AI extraction model for invoices is built with efficiency in mind, significantly reducing the time and effort required for invoice processing. By automating repetitive tasks and eliminating manual data entry, your team can focus on more strategic initiatives, driving productivity and freeing up valuable resources.

• Pre-trained model that automatically detects key fields on the invoice and extracts relevant data (invoice date and number, vendor, PO, amounts, sales taxes, line items, etc.). For a full list of extracted fields, please see the skill documentation.
• This preview extraction model, trained on a smaller document set, automatically detects key fields on the invoice and extracts relevant data (invoice date and number, vendor, PO, amounts, sales taxes, line items, etc.). For a full list of extracted fields, please see the skill documentation.
• Receives and processes invoices in a variety of input formats - scanned images, PDFs, etc. Provides exceptional accuracy of OCR conversion and data extraction.
• Detects Business Unit, Vendor and Purchase Order automatically, or allows to match against an existing data catalog for optimal accuracy.
• Includes tax schemes and business rules specific to the individual regions. Performs automatic validations such as required fields, tax amount calculation etc. Further business rules can be added as individually required.
• Can be augmented by human-in-the-loop review and verification based on accuracy thresholds, missing or incorrect information. The system learns from human interaction and constantly improves the model over time.
• Preview document skills provide a quick-start basis for conducting proof of concept and automating document-centric processes, without wasting time to train a new skill from the ground up. In most preview skills the main data fields have been labeled and the skill has been trained on a small document set to provide a starting point for further training on customer side. Preview skills generally come at no additional cost, but consume page volume from the base Vantage Core Skills volume.
• Can be combined with the Document Splitter Skill for Invoices to handle files including multiple invoices.