Dive into Business Document Processing with AI
Step by Step
Public
Disclaimer
The information in this presentation is confidential and proprietary to SAP and may not be disclosed without the permission of SAP.
Except for your obligation to protect confidential information, this presentation is not subject to your license agreement or any other service
or subscription agreement with SAP. SAP has no obligation to pursue any course of business outlined in this presentation or any related
document, or to develop or release any functionality mentioned therein.
This presentation, or any related document and SAP's strategy and possible future developments, products and or platforms directions and
functionality are all subject to change and may be changed by SAP at any time for any reason without notice. The information in this
presentation is not a commitment, promise or legal obligation to deliver any material, code or functionality. This presentation is provided
without a warranty of any kind, either express or implied, including but not limited to, the implied warranties of merchantability, fitness for a
particular purpose, or non-infringement. This presentation is for informational purposes and may not be incorporated into a contract. SAP
assumes no responsibility for errors or omissions in this presentation, except if such damages were caused by SAP’s intentional or gross
negligence.
All forward-looking statements are subject to various risks and uncertainties that could cause actual results to differ materially from
expectations. Readers are cautioned not to place undue reliance on these forward-looking statements, which speak only as of their dates,
and they should not be relied upon in making purchasing decisions.
Public 2
Welcome and let’s get started!
Presenters
▪ Tobias Weller, Area Product Owner
▪ Maha Feghali-Vartanians, Enterprise Architect
▪ Maximilian Streifeneder, Solution Expert
Objective
Learn how to use Document Information Extraction
Agenda
▪ Document Information Extraction Primer – 20 min
▪ Workshop – 90 min
▪ Summary – 10 min
Public 3
Welcome and let’s get started!
Presenters
▪ Dr. Tomasz Janasz, Area Product Manager
Objective
Learn how to use Document Information Extraction
Agenda
▪ Document Information Extraction Primer – 20 min
▪ Workshop – 90 min
▪ Summary – 10 min
Public 4
Bild anpassen
Document Information Extraction
Primer
Document Information Extraction Presenter: Maha
Intelligent document processing with SAP
8 h/week Document Information
time employees spend
managing documents Extraction SAP captured and converted new
- PWC
invoices we supplied for the demo much
Extract information with pre- more accurately than others, indicating
trained models for various superior expertise.
$10.89 document types and languages
average cost per invoice - IDC
- Ardent Partners Enrich the extracted information
with your master data through
automated matching Helps to save 350 hours per month:
Typically it takes 10-15 minutes per
80-90% Extend the existing models with invoice. Now you can do 10-15 minutes
of enterprise data is locked your own templates to process review of all the document you have got
within unstructured formats additional document types in. So, it is a lot more straightforward.
- Everest Group - Aspen Pumps | Jon Curlis
Transform unstructured documents into structured information for instant value.
Accuracy Achieve Automation Increase Cost Reduce processing
more accurate results than efficiency and enable teams costs and leverage advantages
classical systems to focus on strategic tasks in follow-up processes
Public 6
Presenter:
Document Information Extraction
Tobias
Product overview & roadmap
Find also on
SAP Discovery
Center
Product Capabilities
SAP-managed Use Cases Features & Extensions
Supplier Payment User Business
Master Data
Invoice Advice Interface OCR
Enrichment
Purchase Business Cards Template
Order (only via API) Schema definition creation & management
Globalization SAP-managed Extractors Consumption
Official languages Business OCR Data Centers: Extracted Extracted DOX API DOX User Interface Standard
(per document Languages EU10, EU11, Header Fields Line Items Reference Application Integrations
type) JP10, US10,
AP10
Roadmap Outlook (2023)
Training of Custom Business Rule Scene Text New generation of Extended file type Enhanced schema
Models Framework Recognition SAP-managed models support configuration options
Public 7
Document Information Extraction Presenter: Maha
Selected use cases that are natively
integrated into SAP standard products.
Business use cases
Extract supplier invoice information Finance
Intelligent order processing Sales
Proof of purchase Post Sales
HR Admission & Onboarding Process People Management
Document
Information Data Governance
Automated Vendor Master Data Reconciliation
Extraction
Enterprise email inbox handling Document Management
Critical document filtering Legal
Lead creation from business cards Lead to Cash
Automated request handling Service Management
Public 8
Presenter:
Document Information Extraction
Tobias
Integration Architecture
Firewall
INTERNET
SAP and non-SAP SAP Business Technology Platform
applications
Cloud Foundry Environment
Document Information
HTTPS 1 trust Extraction
User provides
credentials OAuth 2.0
and more …
2 REST REST API
Authenticated inference Call
End User
3 optional
Secure tunnel
Cloud Data push Connectivity
Connector Service
Web
Application
Authenticated inference Call
4
Web Browser
Public 9
SAP
Workshop Github
Repo
Document information extraction
Start today
Ready to Use Natively Available
▪ Available under Free Tier option on SAP BTP The service is integrated into variety of SAP standard
products that you use already today:
▪ Commercially available via Cloud Platform SAP Concur Invoice Capture
Enterprise Agreement, on SAP Store or as Pay-as- SAP Central Invoice Management for SAP S/4HANA Cloud
you-go model SAP CashApplication
SAP Business ByDesign
▪ Available as Test Demo & Development for Partners
SAP S/4HANA Cloud
▪ Available on following Data Centers: EU10, EU11, SAP Process Automation
JP10, US10, AP10 …and many mode (see consumption options).
SAP HELP SAP DISOVERY SAP CONSUMPTION
PORTAL CENTER COMMUNITY OPTIONS
Public 11
Sala Jairzinho 26/04
Por favor, responda a pesquisa abaixo sobre a sessão:
11h – Dive into Business Document Processing with AI Step by Step
Thank you.
Tobias Weller Maha Feghali-Vartanians Maximilian Streifeneder
Area Product Owner Enterprise Architect Solution Expert
SAP Product Engineering SAP Customer Success SAP Technology & Innovation
https://people.sap.com/tobias.weller
Thank you.
Dr. Tomasz Janasz
Area Product Manager
SAP Product Engineering
https://people.sap.com/tomasz.janasz
