Recently on April 29th, my colleague tomasz.janasz and I presented the topic Business Document Processing with SAP AI Business Services as part of the SAP Community call series.
This blog summarizes key highlights from this community call. You can watch the webinar recording of the same as well:
Many processes in enterprises still involve processing of business documents.
The main mission and value proposition of Business Document Processing is to transform unstructured documents to structured information with machine learning-based document processing and embed the information into your business processes for instant value.
Business Document Processing typically consists of three steps:
The value can be seen in increased automation rates, higher accuracies, increased processing speed and significant cost reductions by reducing human labor in these processes.
The portfolio for SAP AI Business Services related to Business Document Processing consists of three services.
Document Classification can classify business documents based on customer-specific machine learning models. These customer-specific classification models are trained based on a sub-set of already classified (labeled) documents.
Document Information Extraction extracts structured information from unstructured documents. The extracted information can be automatically enriched with your existing structured master data and transactional data.
Business Entity Recognition helps you to detect and highlight any given type of named entity in unstructured text and classify it in accordance with predefined categories.
Find more information about the services in our blog post Simplify Business Document Processing with SAP AI Business Services.
Accounts payable is the most time and labor intensive finance and administration function. In fact, processing costs per invoice typically range from 5-12 US dollars and ~60% of the costs come from manual processing.
Document Information Extraction can provide added value by automatically extracting and enriching unstructured data from an invoice.
The optimized process is shown in the following illustration:
An Accounts Payable clerk receives an invoice, the invoice is first split and data gets extracted automatically. The enrichment with supplier and employee data from the corresponding master data records takes place as well. The Invoice is then posted into the system of record and the clerk can proceed with the subsequent reconciliation process.
Applying Document Information Extraction to this process leads to higher accuracy, optimized employee productivity and better operational efficiency in terms of reduced costs and errors.
SAP customers frequently have to process business documents attached to emails from business partners. Usually the documents arrive in a central enterprise email inbox and classifying these attachments is often a manual and error-prone process which can cause damage to business critical processes.
Document Classification in conjunction with SAP Intelligent RPA can provide added value by automatically classifying and dispatching incoming documents. In this way the documents can be quickly pre-processed and dispatched to the corresponding business process by an intelligent bot.
The optimized process is shown in the following illustration:
First an intelligent bot screens incoming emails for attachments. The bot then sends all attachments to the Document Classification service for automatic classification. After this pre-processing the bot can finally initiate the subsequent business process.
Applying AI in this process helps to identify critical files within large volumes of documents.
It leads to reduction of repetitive tasks and much faster responses to customers.
SAP customers with shared service organizations which need to handle internal and/or external standard inquiries about various topics typically deal with high workloads of inquiries.
The combination of three SAP AI Business Services Business Entity Recognition and Document Information Extraction and Service Ticket Intelligence helps to automate and optimize the request handling process in shared service centers.
First incoming service requests are processed and classified by Service Ticket Intelligence. In a second step Business Entity Recognition identifies and extracts predefined entities from the service request itself. Document Information Extraction extracts structured information from attachments. The information extracted from Business Entity Recognition and Document Information Extraction (e.g. invoice or order numbers) is then used to either provide the service agents with assistance, or even directly answer the inquiries for them via a bot automatically.
By automating and optimizing the request handling process in shared service centers, new levels of operational excellence and reduction of responses rates can be achieved.
Everybody who visited trade fairs or conferences in the past, knows that one can collect many business cards at such events. Business cards collected at events or conferences need to be entered manually to capture leads. While business cards typically come in various languages and formats, manual lead capturing might lead to errors and an increase in the processing time.
Document Information Extraction and Business Entity Recognition help to extract and identify the contact-relevant information from the business cards with high accuracy. The contact-related information can then easily be used in further systems such as SAP Business ByDesign or SAP Cloud for Customer to create leads or contacts accordingly.
Overall, the process outlined above leads to a much easier and faster lead recognition with reduction of manual efforts.
To demo or try out the services for Business document processing, find an overview of the related tutorials here:
If you want to find out more about the SAP AI Business Services portfolio and its services, stay tuned for more webinars which will be announced on SAP Community Calls. You can also follow our tag SAP AI Business Services to find out about new community calls as we will publish an announcement blog post for the community calls under this tag, too.
Explore: SAP Community Page
Dive deeper: Open SAP Course
Get an overview: Blogpost part I | Blogpost part II
Exchange Knowledge:
Document Classification Questions | Document Information Extraction Questions
Business Entity Recognition Questions | Service Ticket Intelligence Questions
Data Attribute Recommendation Questions | Invoice Object Recommendation Questions
This blog summarizes key highlights from this community call. You can watch the webinar recording of the same as well:
Business document processing
Many processes in enterprises still involve processing of business documents.
The main mission and value proposition of Business Document Processing is to transform unstructured documents to structured information with machine learning-based document processing and embed the information into your business processes for instant value.
Business document processing
Business Document Processing typically consists of three steps:
- Classification: When a document arrives, you need to understand what type of document it is in order to know what to do with it.
- Extraction of business relevant information out of this document. Here we talk about the semantical information which is relevant for the business.
- Enriching the information with additional master data and posting it back to the system of record for further processing.
The value can be seen in increased automation rates, higher accuracies, increased processing speed and significant cost reductions by reducing human labor in these processes.
Services for Business document processing
The portfolio for SAP AI Business Services related to Business Document Processing consists of three services.
Document Classification can classify business documents based on customer-specific machine learning models. These customer-specific classification models are trained based on a sub-set of already classified (labeled) documents.
Document Information Extraction extracts structured information from unstructured documents. The extracted information can be automatically enriched with your existing structured master data and transactional data.
Business Entity Recognition helps you to detect and highlight any given type of named entity in unstructured text and classify it in accordance with predefined categories.
Services for Business document processing
Find more information about the services in our blog post Simplify Business Document Processing with SAP AI Business Services.
Selected use cases
| The use cases described below are only a selection of the use cases around business document processing. |
Accounts payable invoice extraction
Accounts payable is the most time and labor intensive finance and administration function. In fact, processing costs per invoice typically range from 5-12 US dollars and ~60% of the costs come from manual processing.
Document Information Extraction can provide added value by automatically extracting and enriching unstructured data from an invoice.
The optimized process is shown in the following illustration:
Accounts payable invoice extraction
An Accounts Payable clerk receives an invoice, the invoice is first split and data gets extracted automatically. The enrichment with supplier and employee data from the corresponding master data records takes place as well. The Invoice is then posted into the system of record and the clerk can proceed with the subsequent reconciliation process.
Applying Document Information Extraction to this process leads to higher accuracy, optimized employee productivity and better operational efficiency in terms of reduced costs and errors.
Enterprise email inbox handling
SAP customers frequently have to process business documents attached to emails from business partners. Usually the documents arrive in a central enterprise email inbox and classifying these attachments is often a manual and error-prone process which can cause damage to business critical processes.
Document Classification in conjunction with SAP Intelligent RPA can provide added value by automatically classifying and dispatching incoming documents. In this way the documents can be quickly pre-processed and dispatched to the corresponding business process by an intelligent bot.
The optimized process is shown in the following illustration:
Enterprise email inbox handling
First an intelligent bot screens incoming emails for attachments. The bot then sends all attachments to the Document Classification service for automatic classification. After this pre-processing the bot can finally initiate the subsequent business process.
Applying AI in this process helps to identify critical files within large volumes of documents.
It leads to reduction of repetitive tasks and much faster responses to customers.
Request Handling in Shared Service Centers
SAP customers with shared service organizations which need to handle internal and/or external standard inquiries about various topics typically deal with high workloads of inquiries.
The combination of three SAP AI Business Services Business Entity Recognition and Document Information Extraction and Service Ticket Intelligence helps to automate and optimize the request handling process in shared service centers.
Request Handling in Shared Service Centers
First incoming service requests are processed and classified by Service Ticket Intelligence. In a second step Business Entity Recognition identifies and extracts predefined entities from the service request itself. Document Information Extraction extracts structured information from attachments. The information extracted from Business Entity Recognition and Document Information Extraction (e.g. invoice or order numbers) is then used to either provide the service agents with assistance, or even directly answer the inquiries for them via a bot automatically.
By automating and optimizing the request handling process in shared service centers, new levels of operational excellence and reduction of responses rates can be achieved.
Intelligent lead capturing from business cards
Everybody who visited trade fairs or conferences in the past, knows that one can collect many business cards at such events. Business cards collected at events or conferences need to be entered manually to capture leads. While business cards typically come in various languages and formats, manual lead capturing might lead to errors and an increase in the processing time.
Intelligent lead capturing from business cards
Document Information Extraction and Business Entity Recognition help to extract and identify the contact-relevant information from the business cards with high accuracy. The contact-related information can then easily be used in further systems such as SAP Business ByDesign or SAP Cloud for Customer to create leads or contacts accordingly.
Overall, the process outlined above leads to a much easier and faster lead recognition with reduction of manual efforts.
Resources
To demo or try out the services for Business document processing, find an overview of the related tutorials here:
- Document Information Extraction
- Use Machine Learning to Extract Information from Business Documents and Enrich Data
- Set Up and Use User Interface Application
- Document Classification
- Use Machine Learning to Classify Documents with a Pretrained Model (Trial)
- Use Machine Learning to Classify Documents with Custom Models (Enterprise Account)
- Business Entity Recognition
- Use Pretrained Machine Learning Models to Process Unstructured Text
- Use Custom Machine Learning Models to Process Unstructured Text
What's Next?
If you want to find out more about the SAP AI Business Services portfolio and its services, stay tuned for more webinars which will be announced on SAP Community Calls. You can also follow our tag SAP AI Business Services to find out about new community calls as we will publish an announcement blog post for the community calls under this tag, too.
For more information on SAP AI Business Services:
Explore: SAP Community Page
Dive deeper: Open SAP Course
Get an overview: Blogpost part I | Blogpost part II
Exchange Knowledge:
Document Classification Questions | Document Information Extraction Questions
Business Entity Recognition Questions | Service Ticket Intelligence Questions
Data Attribute Recommendation Questions | Invoice Object Recommendation Questions
- SAP Managed Tags:
