How it works
Metamaze automates the classification and data extraction from your documents and emails. Get a detailed look on the underlying process.
1. Input documents in Metamaze
1. Input documents in Metamaze
Metamaze has several services (APIs) enabling you to programmatically ingest files. These API services are secured through different security mechanisms and can be configured in our platform. It is also possible to manually upload files through the user interface itself, SharePoint application based, through outlook or SFTP.
Current supported file formats are JPEG, PNG, PDF, Microsoft Word, OpenOffice, Plain Text TXT, TIFF, and RTF.
2. The Metamaze Process
2. The Metamaze Process
Once a document is uploaded, an entire process gets started automatically. This process can be configured entirely to the complexity and wishes of your organization. Get an overview of the underlying steps below.
-
Step 1
-
Pre-processing of the document
If the textual content of the inputted file is not a computer-readable format, such as a scanned file, image, or PDF, the document must first be converted to text. An OCR (Optical Character Recognition) AI-model is used to do so.
The pre-processing step is also responsible for optimizing a document in order to increase the quality of the output of the OCR model. This includes: deskewing of pages, optimising contract & brightness and its components, removing stains, text & contract optimization, …
-
Step 2
-
Page management and document classification
The document classification and page management process will split an uploaded file into separate pages. These pages are then merged back into the appropriate documents (page management model), hereby automatically detecting the document type and language (document classification). Metamaze supports 55 languages.
-
Step 3
-
Information extraction
In this step, information is extracted from each document. Each piece of extracted information is properly formatted, based on your format configurations.
-
Step 4
-
Object recognition
Object recognition makes it possible to recognize signatures or other objects that are not text.
-
Step 5
-
Validation of business rules
Business rules are used to validate the document information extracted from the document through conditions you can create. Metamaze provides all the necessary settings for creating different conditions that can be combined via boolean operators such as AND and OR. These conditions enable you can compare different elements with each other.
Furthermore, data enrichments allow you to embed custom code, custom logic and additional data sources into your processing pipeline.
Pre-processing of the document
If the textual content of the inputted file is not a computer-readable format, such as a scanned file, image, or PDF, the document must first be converted to text. An OCR (Optical Character Recognition) AI-model is used to do so.
The pre-processing step is also responsible for optimizing a document in order to increase the quality of the output of the OCR model. This includes: deskewing of pages, optimising contract & brightness and its components, removing stains, text & contract optimization, …
Page management and document classification
The document classification and page management process will split an uploaded file into separate pages. These pages are then merged back into the appropriate documents (page management model), hereby automatically detecting the document type and language (document classification). Metamaze supports 55 languages.
Information extraction
In this step, information is extracted from each document. Each piece of extracted information is properly formatted, based on your format configurations.
Object recognition
Object recognition makes it possible to recognize signatures or other objects that are not text.
Validation of business rules
Business rules are used to validate the document information extracted from the document through conditions you can create. Metamaze provides all the necessary settings for creating different conditions that can be combined via boolean operators such as AND and OR. These conditions enable you can compare different elements with each other.
Furthermore, data enrichments allow you to embed custom code, custom logic and additional data sources into your processing pipeline.
The feedback loop
Our feedback loop makes sure your underlying models keep on improving and learning through time, resulting in higher accuracy rates. This is done through human validation, threshold scores, enrichments, …
4. The Output
4. The Output
When all steps have been completed, the result is sent to your own service, application or data source. Using the project settings, you can select the desired configuration to get the information into your system. Output can be configured through REST API integrations. You can see an unlimited list of potential integrations in the visual here.
Metamaze is a no-code Intelligent Document Processing platform that uses AI to automate every document and email workflow.
Get Started
About
Metamaze is a no-code Intelligent Document Processing platform that uses AI to automate every document and email workflow.