• Skip to main content

Polydocs

Automate Data Capture for Infor ERP

  • Products
        • DOC²
            • Inbox automation
            • Autonomous capturing
            • Master data validation
            • Portfolio of integrations
        • Insight²
  • Use Cases
      • 1200px-Infor_logo.svgAccounting Automation
        • Invoice processing for Infor LN
        • Invoice processing for Infor M3
      • Document approval
        • Approval of invoices
  • Resources
    • Blog
    • Watch & Learn
    • Documentation
    • Glossary
  • Company
    • Contact
    • Career
    • Partner
    • Services
  • English
    • Deutsch
  • Try it free
  • Get a Demo

documents

Sep 28 2022

How you can work with other companies to automate your document processing

28. September 2022 from Ines Brandao

How you can work with other companies to automate your document processing


This might seem contradictory at first sight but it is really possible to optimize your processes by working in a community with other companies and even your competitors. This can be simply achieved by introducing swarmintelligence. So what does this term exactly mean?

Swarm intelligence is a branch of AI that uses the collective work of people to train the specific AI model. Let’s take document processing as an example. The amount of different document structures and layouts that suppliers use is unlimited, which makes it sometimes a difficult task for document capturing softwares to automatically classify and extract the documents. The solution here is the introduction of swarm intelligence. The biggest advantage is that nobody does the work alone, since the training is shared between many companies and their users.

processing

With DOC² we have integrated swarm intelligence to our AI-based repository to easily automate document processing. This means that our customers share the same Cloud-based repository where they can create, delete and manage the classification and extraction rules for their document processing. If company A processes all their supplier documents and trains the software with a simple click, company B, C, D & E can profit from already-trained document types and layouts. It’s a win-win situation for everybody!

Companies can forget about configuring and programming supplier-based templates and can already profit from a self-learning system with DOC².

processing

Image credit: Header & post image from canva.com

Written by Ines Brandao · Categorized: artificial intelligence, automation, Blog, DOC², English, Machine Learning · Tagged: AI, Artificial Intelligence, automate invoices, documents

Mar 29 2022

When are documents ready for automation?

When are documents ready for automation?

One of the most important benefits of document automation is the ability to read and process documents without human intervention. By automating routine tasks, companies can thus save time and money. However, in order for a document to be processed automatically, it must first be trained properly. This blog post discusses when a document is suitable for automation and how you can train your documents.

In Doc², you can see directly via the AI indicator how well the document is trained. The AI indicator is a measure of how well the OCR engine has been trained to recognise the document. The higher the score, the less likely it is that a human will need to intervene to ensure the document is processed correctly.

After each successful export, the AI indicator automatically increases. If someone intervenes in the document and changes the rules for the document, the AI indicator will be negatively affected.

For automatic document capture, the documents should be processed at least 4-5 times without any changes and the AI indicator should be at least 50%.

In the example we train a new invoice and export it 5 times with different values.

The first time the document is read in, the AI indicator is at the minimum level:

Let’s train the document and export it for the first time:

This way, the fields are read automatically when they are exported again and we get a recognition score that shows the read quality for the current document:

Furthermore, for each successful export, the AI indicator is influenced so that it will gradually move from the red to the green area in the graph.

Documentation: AI Indicators

Written by Daniel Jordan · Categorized: DOC², English · Tagged: automation, documents

Mar 07 2022

Swarm Intelligence

Swarm Intelligence
7. March 2022 von Stephanie Propstmeier

Swarm Intelligence


Swarm intelligence (SI) is the collective behavior of decentralized, self-organized systems, natural or artificial. The concept is employed in work on artificial intelligence.

Our products Fellow2KV and Doc² works with Machine Models and archive now almost 100% to detect the fields.

What happens if something is not recognized correctly?

Here our Swarm intelligence is taking in place. Most user will never see or notice it because it so simple.

By changing anything this process will run in the background:

Flow

Here our Swarm Intelligence come into place.

When you do any change in Ephesoft Capture or in Doc² we create a Rule of the TF-IDF document layout.

Our internal business flow will automatic provide the best result for the export.

Doc² Demo

Test our System

Test our System

When we explain the benefit of Swarm intelligence we oft get ask from customer do we share any supplier information. The quick answer is NO

What we share are TF-IDF models and rules to extract data. How a document layout is setup – for example coordinates where to find information in an invoice. But we are not sharing any business information.

TF-IDF (term frequency-inverse document frequency) is a statistical measure that evaluates how relevant a word is to a document in a collection of documents.

This is done by multiplying two metrics: how many times a word appears in a document, and the inverse document frequency of the word across a set of documents. To find out more about TF-IDF the next page

Swarm intelligence

Written by Stephanie Propstmeier · Categorized: data, DOC², English · Tagged: AI, data, documents, optimize, Swarmintelligence, Workflow

Mar 07 2022

Why data matters when improving workflows

improving workflows
7. March 2022 von Stephanie Propstmeier

Why data matters when improving workflows


To optimize your workflows and streamline your entire operation, you need accurate and relevant data. 🤓⚙️

Compiling internal and external data is a time-consuming, labor-intensive, and financially taxing task if you’re doing it manually.🤔
 
In fact, collecting and collating vast amounts of industry data is next to impossible considering the volumes of information circulating in the online and offline realms.
 
That’s why it’s important to employ AI systems to automate big data analytics and generate actionable reports quickly.💪
 
👉Companies are increasingly using big data and AI to collect and organize valuable data quickly and automatically, which leads to better predictions and forecasting. 
 
👉While using AI to automate workflows, one challenge companies are facing is a forest and trees problem: If an organization is automating one-off tasks, it is not improving processes or driving the kind ROI that organizational leaders likely expect.
 
👉Companies should keep in mind that while there’s a role for AI to play, it’s crucial that they are automating the right things for the right reasons and using the right tool for the right job.
 
Have you used AI to improve your workflows?🤔

https://doc2landing.cloudintegration.eu/

Written by Stephanie Propstmeier · Categorized: data, DOC², English, Workflow² · Tagged: AI, data, documents, optimize, Workflow

Mar 07 2022

Invoice processing & digital transformation

7. March 2022 von Stephanie Propstmeier

Invoice processing & digital transformation


Why you should automate manual processes?

For a long time, companies and small businesses have relied on manual invoicing to maintain accounts and process payments. 

Organizations suffered from dissatisfied and stressed employees, lost or misplaced invoices, reduced productivity, inefficient operations, increased cost and human error, and unreliability due to delayed or missed payments.

Approximately 3.6% of invoices entered manually include a data entry error. 
However, through digital transformation, the invoicing process can be done more effectively and accurately. 🚀

Anyone who thinks handwritten data only exists on fixed, standardized forms has never really dug into a government process or

👉Automated invoicing creates a smarter, more effective, and accurate workflow. Using deep learning and AI enables machines to perform efficiently or even better than humans.

Plus, automation eliminates many of the manual processing pitfalls by utilizing advanced computing techniques.💪

What about the invoicing process at your company? Did you automate it already?

https://doc2landing.cloudintegration.eu/

Written by Stephanie Propstmeier · Categorized: data, DOC², English · Tagged: AI, Artificial Intelligence, Blockchain, data, digitalization, documents, Produktivität, Workflow

  • Go to page 1
  • Go to page 2
  • Go to page 3
  • Go to Next Page »
  • Contact
  • Privacy Policy
  • Imprint
  • Master Service Agreement
  • Status

Copyright © 2023 · Polydocs Gmbh · Log in