Currently set to Index
Currently set to Follow

Artificial Intelligence

Prepare any document for processing using artificial intelligence

We have been experiencing an exponential increase in the amount of data as a natural consequence of shifting our reality to the virtual world. It is impossible to process enormous volumes of information efficiently using only classic ERP or ECM software, which requires employee control. Here, AI-based contextual software comes in handy.

The Artificial Intelligence module will support you in preparing any document for processing. It will recognize, among others, document type, validate the data, export the data to appropriate form fields in ECM or ERP system, prevent duplicates and alert you about unusual and dangerous operations.

Moduł AI do procesowania dokumentów

How it works?

The purchase invoice automatically goes to the accounting department, CV to the HR department, and the offer to the company’s front desk.

After manual document upload to the system or auto-download from an email inbox, the OCR process starts automatically. An app adds a text layer to the file and converts it into PDF format. For example, the software can recognize the type of document and automatically forward it to the appropriate department or employee. Moreover, it could suggest the right team while showing the percentage of the recommendation correctness.

The next steps of the document processing may vary depending on the service usage scenario. Recognized invoice data can be automatically imported into the ERP system form, received CVs can be sorted by vacancy and duplicates removed, offers are summarized, and keywords extracted to simplify their selection.

Key components of the AI module

OCR

A service that adds a text layer to image files (*.jpeg, *.png, or non-searchable *.pdf). Any file from a scanner or a document picture converts into a searchable file in a *.pdf format.

TEXT CLASSIFICATION

A service that recognizes document class from historical data. It enables routine and repetitive tasks automation, such as document type recognition of a file sent to a corporate email and forwarding it to the appropriate department.

DATA CAPTURE

A service that enables data extraction from a document to a system form. Algorithms that check the returned data correctness allow validation of the extracted information, such as Tax ID or bank account number. We can define a document template or use ready-made services that do not require the user’s work, i.e. for invoices, business cards, tables, and “key-value” pairs.

ANOMALY DETECTION

A service that detects abnormalities and unusual situations. It may be used, for example, to verify whether the invoice amount from a particular supplier does not differ from the predicted value or to monitor unusual user activity in the system (uploading too many documents or downloading a huge number of files).

TEXT SIMILARITY DETECTION & ANALYSIS

A service that provides intelligent text analysis, including word meaning (tokens) and its location in a sentence and the entire text. Text analysis enables both similar content and duplicate fragment recognition. Based on the identified similarities, a service generates key phrases and document content summaries.

OCR
speed

OCR
effectiveness

TEXT CLASSIFICATION
speed

TEXT CLASSIFICATION
effectiveness

DATA CAPTURE
speed

DATA CAPTURE
effectiveness

Benefits

The Artificial Intelligence module is a set of services, allowing you to automate your office work to ensure its total capacity. Discover the most important benefits of our software.

AI module usage scenarios

OCR na własnym serwerze

Server-based OCR

Converting an image into a searchable PDF file becomes the standard. However, this process is often fragmented (scanner-based OCR, the need for using additional applications, etc.). Within our model, the OCR service operates at the server-side, is efficient because of its container architecture (docker), and ensures that each document will be in a searchable form.

Contextual search within OCR-ed documents

Documents in text format and information entered on the form (metadata) can be searched contextually (as in Google) using specialized tools: Elastic search, Full-text search, etc.

Wyszukiwanie kontekstowe z-OCR-owanych dokumentów
Gotowe do użycia modele przechwytywania danych

Ready-to-use data capture models

General data capture models are ready to use without additional training. Most customers use the model for sales documents (invoices), but we are working on others (business cards, CVs, etc.).

Create your own data capture models

You can either train general models or create your own from scratch. While model training (e.g., for invoices), we adjust the existing field settings or add recognition of new ones. You can save settings for a specific contractor. You can also design models for new document classes.

Tworzenie własnych modeli przechwytywania danych
Rozpoznawanie typów dokumentów

Document type recognition

The primary use of text classification is to identify the document type. Based on the document content, the system evaluates whether it is an invoice, a letter, a contract, etc. The trained type classifier is individual for each environment.

Form field recommendations

Another use of the text classifier is to estimate values for a particular field. The system recommends, for example, a document holder, accounts, or a cost center based on its analysis of historical documents.

Rekomendacje dla pól formularza

Pricing

Interested in learning more about the AI module's capabilities?





    The form is the best way to contact us. Your message will be forwarded to one of our sales leaders, who will respond to your inquiry at lightning speed. Of course, you can also call us or choose to talk via social media: Facebook and Linkedin.

    Tomasz Czapran

    Sales Leader - DACH Region

    Mateusz Illg

    Sales Leader - Poland
    Menu