• Required

• Type

• Additional Settings

• Key name

In this article, we will discuss how mandatory fields work, the different data types available, and the importance of the key name. The additional settings for each data type will be covered in a separate article, including a detailed step-by-step guide and examples. The link to these articles can be found under the heading for each data type.

Required entities & error messages:

If an entity is marked as required, it must have a value in the Output Window to be processed. If this is not the case, the user will receive an error message and the document will not be able to be processed. Below you can see how to mark an entity as required. This can also be identified by the red dot that appears on the left side.

In addition to what has been discussed previously, it is possible that the extracted value from a document does not match the correct Data Type (which will be discussed later in this article) or does not comply with the Additional Settings. In all of these cases, the user will see an error notification and the document is not able to be processed without manual adjustment.

Data types

Coming soon:

• Address

• Currency

• Timespan

Type: Any

The data type "any" refers to a type that can be any value. This is useful when the value of a field is unknown or may vary, as it allows the type checker to accept any value without raising an error.

For example, if a field may contain both text and numerical values, it may be necessary to use the data type "any" to allow for both types of values.

Type: Calculated

The data type "calculated" refers to a type that is calculated based on the values of other fields. This allows users to automatically calculate values based on other data, such as totals or averages.

When using the data type "calculated", it is important to carefully define the calculation that will be used to determine the value of the field. This may involve using mathematical operators or functions, such as addition, subtraction, multiplication, or division.

When the data type of an entity is calculated, make sure that the fields involved are indicated as "numbers"

Read this article for a thorough explanation.

Type: Date

The data type "date" refers to a type that represents a calendar date. This data type is used to store and manipulate dates in a standardized format, such as "YYYY-MM-DD".

Auto-Pilot has an in-house date parser that converts unstructured dates to a single, standardized format.

For example, this parser can convert 24th of January '23 to 24.04.2023

Read this article if you are solely interested in our date parser API.

Type: Date range

The data type "date range" refers to a type that represents a range of dates, such as a start date and an end date. This data type is used to store and manipulate date ranges in a standardized format, such as "YYYY-MM-DD to YYYY-MM-DD".

Like our Date parser mentioned in the previous section, we also have an in-house date range parser available.

For example, this parser can convert: 'END/JAN - 1H FEB' to '21.01.2023 - 10.02.2023'

The conversion rules can be tailored to meet specific customer requirements.

Type: Lookup API

The data type "Lookup API" refers to a type that retrieves data from an external API (Application Programming Interface) using a specific key or reference. This allows businesses to automatically retrieve and integrate data from other systems or databases into their own processes.

Here are some examples of when you might need the lookup API:

• Look up if an extracted value exists in an external database, such as client name, product name or related fees.

• "Standardize different input forms that refer to the same concept or data point. For example, 'RTM', 'RDM', 'RDAM', and 'R'dam' all refer to 'Rotterdam', but the endpoint only allows the format 'Rotterdam'. This is also common in medical jargon."

Type: Number

The data type "number" refers to a type that represents a numerical value. This data type is used to store and manipulate numerical data, such as prices, quantities, or measurements.

When using this entity to calculate the value of another entity, make sure to set the data type of this entity to "number".

Type: Regular Expression

The data type "regular expression" refers to a type that uses a specific pattern or syntax to match and extract data from a string. This data type is commonly used to extract specific pieces of data from unstructured text, such as names, addresses, or phone numbers.

When using the data type "regular expression", it is important to specify the pattern or syntax that will be used to match the data. It is also important to consider the range of data that may be matched and ensure that the regular expression is flexible enough to handle variations in the data.

See a couple of specific examples in this article.

Type: String

The data type "string" refers to a type that represents a sequence of characters, such as words or sentences. This data type is used to store and manipulate text data, such as names, addresses, or descriptions.

Wanneer gebruik je dit?

Key name

This is the name that is used in the JSON file that is generated as output when a document is processed.

Default mode

The Output Window is located on the right and displays all extracted labels in a list format by default like in the picture.

Step 1: Go Navigate to Output Window settings

Project settings > Export > Output template

Step 2: Select the positions on the grid to display the labels

To select a range of boxes, click and hold on the first box, then drag to the last box and release. If you want to group data, please read this article.

Once your done, wait until the top right box displays "saved"

Step 3: Check the result

To view the results, navigate back to the inbox and click on a document.

Find out how to cross-check and validate the raw extracted data in our type-checking module

Type checking involves parsing raw extracted data into the correct format to improve accuracy and reliability, and ensure data is in a consistent and standardized format for easy integration with other systems and processes.

For more information read this article.

Once the data has been extracted from a document, it is important to type check the raw extracted data to ensure that it is accurate and in the correct format. This process involves parsing the data into the appropriate format, such as parsing dates into a standardized date format or parsing addresses into a specific format. Type checking the extracted data is important because it helps to improve the accuracy and reliability of the data. It also ensures that the data can be easily integrated with other systems and processes, as it ensures that the data is in a consistent and standardized format. To type check the extracted data, it is necessary to use specialized software or tools that are designed to parse and format the data. By carefully type checking the extracted data, businesses can improve the quality and value of their data, as well as streamline their processes and improve efficiency.

Business Processes that would benefit from a Passport & ID Card extractor

There are a variety of business processes that could benefit from using a passport and ID card extractor engine. For example, many financial institutions use a process called "Know Your Customer" (KYC) to verify the identity of their clients and assess their potential risks for money laundering or financing terrorism. In this process, it is often necessary to verify the authenticity of passports and ID cards presented by clients and to ensure that they match the information provided. A passport and ID card extractor engine could be used to quickly and accurately extract this information, making the KYC process more efficient and effective. Other business processes that could benefit from using a passport and ID card extractor engine include employment verification, international travel, financial transactions, renting a property, and obtaining a driver's license. By automating the data extraction process, businesses can save time and improve the accuracy of their data.

What fields can we extract from Dutch Passports & ID cards

• Full name

• Nationality

• Date of birth

• Place of birth

• Gender

• Issue date

• Issuing country

• Expiry date

• Document number

• Social security number (BSN)

• Photo on passport

• Machine readable zone (MRZ)

Get the JSON output from the API

{
"document_number": "SPECI2014",
"surname": "De Bruijn",
"given_name": "Willeke Liselotte",
"nationality": "NLD",
"date_of_birth": "100365",
"place_of_birth": "Stad en Dorp",
"gender": "F",
"height": "175",
"date_of_issue": "150114",
"date_of_expiry": "150124",
"personal_number": "999999990",
"photo_on_passport": "https://example.com/passport_photo.jpg",
"issuing_country": "Netherlands"
}

Get in touch!

If you have any questions about our passport and ID card extractor engine, or if you would like to learn more about how it can benefit your business, don't hesitate to reach out to us.

In this article, we’ll explore this concept and why it matters for companies who are in the midst of a digital transformation.

What is Intelligent Document Processing?

Intelligent document processing (IDP) solutions transform unstructured and semi-structured data into structured usable data. For example, the process of taking a document (in whatever format), extracting the relevant information, and passing that through into your business system is an example of intelligent documentation processing. This translation helps to connect the myriad of inputs you receive as a business with the internal systems and processes that keeps the cogs turning.

The roots of IDP can be traced back to optical character recognition (OCR) tools which would convert images of text into machine-usable text, but things have progressed significantly since then. Advancements in machine learning and natural language processing have taken Document Processing beyond mere character recognition, and into a world where the algorithms can also read the context, tone, and other indirect features that make that information usable.

These cutting-edge IDP tools are self-learning, and the more they are used, the more precise they become. Leveraging feedback loops involving your staff members, they can quickly become an incredibly valuable component of your operational efficiency.

Why Does It Matter?

80% of all enterprise data is unstructured and it takes a lot of time and resources to process that information in a way that can be utilized by your company. Many companies rely on their staff to fulfill this role – working through documents manually and extracting the key information that must then be captured into another system. However, this route is expensive, slow, and prone to human error. In addition, these tasks are incredibly tedious and they can really suck all the joy out of work for the people who do this processing.

Intelligent document processing tools circumvent all of this and provide highly efficient, accurate, and quick turnarounds for your data processing needs – freeing up your human resources to work on higher-level tasks. This contributes to a better experience for your employees but also for your customers who will feel the improved internal efficiency that these tools create.

But it goes further than that. When you have a means of achieving high-quality structured data at scale, it also opens up opportunities for other data science projects. The success of those projects relies on a clean and structured dataset – so anything you can do to improve that will have compounding positive effects. Intelligent document processing is the first step on that journey and the more effective you can be here, the more value you’ll get out of your data goldmine.

It's Time to Put Your Documents on Auto-Pilot

Here at Auto-Pilot, we’ve built the single best intelligent document processing offering on the market, providing highly sophisticated natural language processing for a wide variety of different document formats. By leveraging our platform you can achieve more intelligent automation that pushes your company forward and frees your staff of the tedious tasks.

To explore whether this might be a fit for your organization, take our free quiz here, or contact our team directly. We can’t wait to hear from you!

What is the Accounts Payable Process?

A company’s accounts payable refers to the amount the money that a business owes to its suppliers and vendors, but has not paid yet. So, the accounts payable process lays out all the steps that it takes from placing the order, to the final payment of the invoice. These short-term payment obligations can grow in complexity quickly, and so having a well-defined and well-understood process helps to maintain high standards and ensure that all payments are being made on time, and in line with strategic objectives.

Which Documents Are Typically Encountered in Accounts Payable?

There are three major types of documents that play vital roles in the accounts payable process:

• Purchase Orders (PO). A purchase order is a formal document that lays out the exact goods and services that are being ordered from the vendor. This is typically the last stage of the negotiation process and it commits both parties to the type of engagement, the price, and all the other details that the vendor might need to fulfill the order.

• Order Confirmations. An order confirmation is a document from the vendor that confirms the order has been received and that the process has started to fulfill the order. This is tied to the corresponding purchase order and it binds the vendor to deliver on whatever was agreed upon in the purchase order.

• Invoices. An invoice is a document sent to the buyer after delivery in order to collect payment. It details the goods and services delivered, the price, payment terms, and any other relevant information that is needed to settle payment for the order.

Each of these documents plays an important role along the process and your systems need to be set up to handle them at scale if you want to maintain a robust and efficient workflow.

Common Challenges in the Accounts Payable Process

Having an efficient accounts payable process is crucial for cash flow and general operations but there are a number of common challenges that CFOs and finance managers face as they try to build the right workflows in their organization. Some of these include the following:

• Slow Processing. As with any paperwork, slow processing can cause backlogs and bottlenecks that get in the way of the business moving forward – and when they happen it can be very difficult to cut through the noise and get back on track. Sometimes this is due to limited staff or just to an over-burdensome administrative process.

• Matching Errors. The invoice needs to match the purchase order (two-way) and often the order confirmation (three-way) to ensure that all vendor invoices are paid correctly. Companies can experience incongruencies through data entry errors and incorrect billing information that take time and effort to rectify.

• Unauthorized Purchases. The accounts payable department is set up to regulate and standardize purchasing behavior – but there can still be unauthorized purchases that slip through if you’re not careful.

• Early and Late Payments. If payments are made early, you could get into trouble because the money is gone before goods have been delivered. What happens if they aren’t delivered or if you’re not happy with the quality? Good luck getting that money back. On the other hand, if you pay late you could find yourself liable for penalties and extra fees. A robust accounts payable process can help you avoid both extremes.

• Lost Paperwork. Accounts payable rely on documentation so when paperwork gets lost or misplaced it can cause chaos in the accounts payable cycle and during month-end closing – resulting in friction with vendors and delayed operations.

• Double Payments. Typos, or forgetting to mark an invoice as paid could cause you to unknowingly process duplicate payments that then need to be reversed – causing headaches and additional administrative efforts.

These are just some of the challenges within accounts payable that many companies face – and if you can take steps to streamline your process and automate where possible, it will reduce accounts payable discrepancies, shorten cycle times, and boost overall satisfaction across the process.

How to Streamline the Accounts Payable Process

Here are some key considerations for streamlining your accounts payable process:

• Centralize all accounts payable documentation. If you can get all of your documents in one place, that makes it easier to reconcile, manage, and process them through your systems.

• Reduce paperwork where possible. Putting aside the crucial environmental concerns, reducing the volume of paperwork that you’re dealing with, can also minimize errors and speed up processing overall.

• Streamline your workflows. Work through your processes carefully and cut out any friction that you can – reducing the number of touches that processing these documents requires.

• Integrate with your ERP system. When your accounts payable process is well integrated with your ERP it means that everything stays in alignment and team members aren’t duplicating efforts.

• Use three-way matching principles. Enforcing a strict three-way matching process helps to eliminate matching errors and achieve more consistency. Moreover, this decreases the chance of paying fraudulent invoices.

• Automate information extraction. By automating the extraction of data from your documents, you can get away from human capturing errors and speed up your processing by orders of magnitude.

• Build in warnings and alerts. Having proactive warnings and alerts means that you can spot problems earlier and fix them before they cause issues in the workflow.

• Create periodic reports. Regular monitoring and reporting on your accounts payable puts you in a much better position to understand spending patterns and prepare for audits.

By implementing any of these actions, you’ll find that your accounts payable can see drastic improvements which, in turn, has positive effects across vital parts of the organization.

Accounts Payable Automation with Auto-Pilot

We have many enterprise clients who use Auto-Pilot to boost their accounts payable automation and to build an end-to-end workflow that prioritizes efficiency and accuracy. This reduces the manual workload and minimizes the chance of costly errors from your staff.

Our platform can receive documents from a myriad of different sources (emails, scans, PDFs, and more) and extract the key data to be fed into the rest of your business systems. This is done through machine learning models that can deliver accuracy scores of 98-99% which far outperforms general invoice parsers/tools which are not trained on your specific data. Auto-Pilot is a dedicated solution rather than a one-size-fits-some solution.

The data extraction can be done at very specific levels of detail – which is crucial for certain sectors that work with complex documentation. And this data can then be integrated with ERP and other accounting tools through an API. For the companies that are stuck with legacy systems – we can also work with your RPA team (or a consultant of our own) to establish the necessary connection between Auto-Pilot and what you currently use.

Custom cross-checks and other validation (including three-way matching) come standard – with key warnings about when a user is about to process a high amount, there is missing information or other things like that. Everything is taken care of to produce a highly efficient and functional accounts payable process.