Loic1
ServiceNow Employee
ServiceNow Employee

DI FAQ.png

 

Looking for the Quick Start Guide? Head this way.

Check out the AI & Intelligence forum to get the best content about ServiceNow's AI products!


As of the Utah release

Table of contents:

Getting Started
Document Intelligence and other solutions
AI and Training
Limitations

Implementation & Troubleshooting

 


Getting Started

 

What is Document Intelligence and how do I get started?

The Document Intelligence Quick Start Guide is available in the community.

 

How do I get Document Intelligence?

Document Intelligence can be installed via a Store Application; it is compatible with San Diego and later releases.

It requires a special license. It is available for Automation Engine PRO, CSM PRO and FSO PRO, APO (as of Vancouver) customers but reach out to your Account team to inquire how to get a license. It is tied to a quota of pages with the option to acquire additional pages via Document Intelligence via add-on bundles with the license.

 

How do I get Document Intelligence Admin?

Document Intelligence Admin is a separate plugin that can be installed via a Store Application; it is compatible with Tokyo and later releases.

 

What use cases does it cover?

The focus of the product is the extraction of data from documents to drive high-value workflows.

For example, a document is loaded, the information is extracted, and it drives actions, such as approvals, flows and integrations.

Check with the appropriate BU (Automation Engine, CSM, FSO, APO) for specific use cases.

An overview was also presented during the AI Academy: Get started with Document Intelligence

 

Document Intelligence and other solutions

 

What is the difference between Document Intelligence for Automation Engine and CSM/FSO/APO?

The Document Intelligence solution is pre-packaged and integrated with CSM, FSO and APO; this limits the configuration needed. For other use cases, the Automation/Creator tools (Flow, etc.) can be used with Document Intelligence to process documents and extract values in the Now Platform.

 

Is Document Intelligence the same as Robotic Process Automation (RPA)?

The AI in Document Intelligence and the human-in-the-loop design make it possible to address use cases for highly variable documents. RPA with Document Intelligence is a powerful combination for customers wanting to support complex cross-enterprise workflows spanning multiple teams and 3rd party systems.

 

AI and Training

 

What “models” is Document Intelligence trained on? What algorithms does it use?

It's a multi-faceted approach developed by ServiceNow that cannot be oversimplified as a computer vision and classification technique. Our approach aims to develop highly trusted models for various use cases using several techniques to deliver those results.

Additionally, Document Intelligence is fully integrated into the Now Platform to drive end-to-end workflows and limit the number of point solutions running their own algorithms.

 

When we say that Document Intelligence is “trained,” does that mean I can process the same document multiple times to train the AI model?

Not really; Document Intelligence uses human-in-the-loop, meaning that the training happens as agents process documents. That process should happen with documents that are reflective of your workflow. Forcing the training with a single or too few documents can skew (or overfit) the model.

 

Can I tell Document Intelligence where my field is on the document (instead of typing and selecting the recommendation)?

Yes, the Draw tool allows to select values from the document directly.

 

Where is the data trained? Is the Machine Learning process happening on my instance?

Training isn’t done directly in the ServiceNow instance; it is done on a secure server with specific hardware to perform Machine Learning in ServiceNow’s Data Center. The process is encrypted and doesn't cache or store data.

 

When we delete a trained task in Document Intelligence, does the training data related to that task get deleted?

No.

 

Limitations

 

What languages are supported? What file types are supported?

See the docs for the full list of limits.

 

Are there any limits to be aware of?

The following are not supported:

  • ‘Secured’, encrypted and password-protected PDFs
  • Handwritten documents
  • Free-form text
  • Synchronous processes

See the docs for the full list of limits.

 

Can the extracted data be validated by the submitter, for example on a portal?

Not at this time. The review is done by an agent (with a reviewer role) on the Document Intelligence Workspace.

 

Can I extract handwritten documents?

Although handwriting is not officially supported, the extraction can be accurate in cases where the text is legible. We strongly recommend additional validation for handwritten documents to assess the results.

 

Can I extract a whole paragraph or free-form text?

No, this is not currently supported.

 

Is it supported in Self-Hosted Environments?

Document Intelligence is now available for self-hosted customers, see this KB.

 

Is it supported in ServiceNow Regulated Environments?

Yes; refer to that KB article on Now Support.

 

Is it supported on my Personal Developer Instance (PDI)?

No.

 

If I upload a document with multi pages but only need the data on some of the pages, can Document Intelligence split the document or allow me to select which pages to process?

Yes, the page range filter demonstrated during the AI Academy "What's new in Washington DC for Document Intelligence", allows to limit the pages from which data extraction is executed.

 

Implementation & Troubleshooting

 

I created the Extract Values Flow, but I noticed the values are not written in my target record after the extraction; what’s going on?

First, make sure the values are populated in the Field Values / Extracted Value table [(sys_)di_extracted_value]. Then, ensure the Extract Value Flow is running correctly and the Flow properties are set to run as System User; make sure you see the data in the Flow Execution logs. Finally, check the Table configuration:

  • Review ACLs on the Table
  • Application access on the Table
  • Check the cross-scope privileges
  • Make sure the target field type matches the type of data

For a live demo of these steps, refer to this AI Academy session.

 

How can I monitor ML Solutions to track the processing of a Document Intelligence task?

Type ml_solution.list in the navigation menu.

For a live demo of this step, refer to this AI Academy session.

 

Can I use a Key Group to extract values to a different table even though the data is not a table?

No, this is a bad idea, leading to lousy prediction performance and bad User Experience. The Key Groups are meant for extracting data displayed in a table or a list with a set of common fields or columns.

 

My PDFs are not being read/displayed by DocIntel, what’s going on?

There are a few reasons a PDF might not be processed properly:

  • The PDF is unaccessible – check that the PDF is not encrypted, secured or password-protected
  • The ACLs on the sys_attachment table prevent the creation of the processed record
  • The "glide.attachment.extensions" system property doesn’t have "jpeg" listed

 

My Document task shows “Failed to process the task” how can I troubleshoot?

Type ml_solution.list in the navigation menu and identify the failed solution, open it and open the “Show training progress” related link to find more information. The reason why a solution fails can be:

  • The instance doesn’t have access to the ML infrastructure, for example, a Personal Developer Instance (PDI) or a CloudLab instance
  • An issue with the system property [glide.shared_service_scheduler.url], which should be set to https://sncmlscheduler.service-now.com/
  • The “sharedservice.worker” user doesn’t exist or is not Active.

For a live demo of these steps, refer to this AI Academy session.

 

What's the best way to migrate and import/export task definition along with the trained models from one instance to another?

The easiest way is to open the use case on the Admin experience and select 'Add to update set'. This is available in Document Intelligence Admin v2, which requires Vancouver.

Picture1.png

 If you are using a previous version, follow the steps in this article.

 

I created Document tasks for my Use Case but they are never processed, what’s happening?

Make sure your Use Case record has a reference for each of the 4 ML Solution Definition fields. One common issue is Use Cases that were exported via Update Sets but the referenced ML Solution Definition records were missed.

For a live demo of this step, refer to this AI Academy session.

 

What are the changes in the table schema from v3 (Vancouver)?

In v3, the base tables have been migrated to a new table schema:

The 'Use cases' table is sys_di_task_definition (previously di_task_definition)

The 'Document tasks' table is sys_di_task (previously di_task)

The 'Field values' table is sys_di_extracted_value (previously di_extracted_value)

 

Note, that it can also mean they don't appear in some menus (like the Flow Designer "Table" selector), for this, you might need to update some system properties.

 

What are the changes in terminology from v2.3?

Picture2.png

 

How can I monitor usage and metrics for Document Intelligence?

To access the Document Intelligence Usage dashboard, navigate to All > Document Intelligence > Document Data Extraction Administration > Monitoring. Learn more in Product Docs .

 

docintel-monitoring-page.png

 

What are the stages of the processing for a Document Task [(sys_)di_task]?

Loic1_1-1698329425272.png

More info in Get Started with Document Intelligence [How-To].

 

Where are the Extracted Values/Field Values stored?

The extracted values are stored in the Field Value / Extracted Value table [(sys_)di_extracted_value]. To access them, navigate to Document Intelligence > Extracted Value and filter with the Task.

Picture5.png

More info in Get Started with Document Intelligence [How-To].

Comments
Vijay Talupula
Tera Guru
Tera Guru

@Loic1 Could you please clarify the below question? I am aware that SN DI is an AI based OCR solution but how it is different from the other OCR tools in the market.

 

What is the novel feature/wow factor in our ServiceNow document intelligence compared to the other AI based OCR tools in the market? OR why should we choose ServiceNow document intelligence compared to the OCR tools in the market?

 

Dan Y25
Tera Contributor

Hello @Loic1 and community, I have a couple questions:

 

1. How will DocIntel work if there are multiple documents of different types / use cases for a particular task?

 

2. Can you describe how document processing exceptions and errors could be managed?

 

Thank you!

 

Dan

Loic1
ServiceNow Employee
ServiceNow Employee

Hi @Dan Y25 ,

1. Document Tasks are really designed to receive one file containing the data to extract. If you need to identify specific document types from multiple files, the Document Classifier capability can be leveraged.

2. The Status field on the Document Task table provides relevant information to manage exceptions and errors.

Tanya D
Tera Contributor

Hi @Loic1 ,

 

I am having trouble with my Use Case. We recently updated our test instance where I had my use case trained. Now every time I upload a document I am getting a "DocIntel suggestions are not available yet." These documents are over a day old. 

 

Thanks!

Loic1
ServiceNow Employee
ServiceNow Employee

Hi @Tanya D,

Please create a Case on Support and we'll have somebody take a look.

 

Thanks

kiran kumar m1
Tera Contributor

HI @Loic1  I have created a use case in document intelligence and I have mapped few fields with my incident table . then I trained the model and set to autofill everything was working fine.

 

I changed a value for a particular field in my pdf and started uploading it as attachment but the recommendation score was not getting updated , so I deleted the field and created a new field with the same name and mapped to the same field , but now its not even showing the recommendation ,its not even able to find the value in the pdf and recommendation score is always 0 regardless how many times I train it.

 

what might be the problem is it due to the deletion of the field ?

 

or should I create a new use case.

Loic1
ServiceNow Employee
ServiceNow Employee

Hi @kiran kumar m1, I don't fully understand what you are trying to achieve and what steps you have taken.
Could you give more details? Or feel free to DM me.

Thanks

Aliakbar
Tera Explorer

Can information be extracted from Handwritten application form too with document intelligence? @Loic1 

Loic1
ServiceNow Employee
ServiceNow Employee

@Aliakbar Please see the question "Can I extract handwritten documents?" and its answer, that should answer your question.

Yaya1
Tera Explorer

Hi  Loic1 ,please i want to know if the document intelligence isn't yet used in PDI instance ?

Prashanth1607
Tera Contributor

Prashanth1607_0-1719926747325.png

Hi @Loic1 could you please help me in solving this error this is the error i found while trouble shooting from show training progress Thanks in advance.

Loic1
ServiceNow Employee
ServiceNow Employee
Dan_Tracey
Tera Contributor

I am unable to select the draw tool to help identify my table data any suggestions?

Dan_Tracey_0-1721859817285.png

 

HarikaM
Tera Explorer

Hi @Loic1 ,

 

As per the video on Washington Dc release for Docintel, we could select predefined pages in the document. Likewise, do we have any option to process selected documents attached to the record based on the naming convention of files attached.

 

For example, 

For an incident record, we have 2 attachments (File1: Testing.pdf and File2: Sample.pdf). I want my docintel  usecase to process the file with name has Test in it. So, I want only File1 to be processed in the Integration of process task.

 

Please suggest.

Loic1
ServiceNow Employee
ServiceNow Employee

@HarikaM 

Yes, it wasn't shown in the video you mentioned, but the attachment_filter can take a list of comma-separated SysIds. In your scenario, if you are able to identify the SysId of the attachments that you need, you can input them in the attachment_filter field of the document task.

 

More information on the format of attachment_filter:

It's a list of comma-separated strings following the convention sys_id_of_attachment{page_range}

HarikaM
Tera Explorer

Hi @Loic1,

I created a subflow, where I copied the DocIntel process flow Integration Actions. And I have given input to subflow as sys_id of a table record. And its working fine as same as Docintel OOO integration step(Process flow integration).

 

But, when I am trying to add file attachments string to input (trying to give selected attachments of a record as input to subflow instead of all the attached files of a record) , then the Action step is not taking those array.string of file attachments in type pill. Please find the screenshots below and guide me if anything needs to be added.

HarikaM_2-1729963549168.png

 

HarikaM_0-1729963458857.pngHarikaM_1-1729963499468.png

 

After saving of the sub flow, I am not able to see the file array.string data pill in Attachment IDs. And even test also failed as the Attachment IDs is not taking my input sys_ids of the attachments.

HarikaM_3-1729963650061.png

 

Please check and guide me.

 

lucaspaz
Tera Contributor

Hi @Loic1!

What happens to the flows and actions when we reach the daily process limit of 2000 calls? Do we receive an error message, or does it simply stop triggering?

RathanK
Kilo Guru

Hi @Loic1 ,
Hope you are good.

Here I have a question on the Doc Intel, we basically trained an Invoice and when ever we are trying to upload same type of Invoice it is not fetching the values, the same type of Invoice format also we are training separately, so is this something an issue within the Doc Intel or it is not that feasible to achieve our requirement.

If the type of the invoice is different we can train it but when it comes to same invoice that we 100% trained, the same format is not fetching, can you help me on this and provides me few insights, that helps a lot!


Thanks,

Rathan

Version history
Last update:
‎04-10-2025 09:31 AM
Updated by: