Extract data from key information documents

Koncile's AI OCR extracts and structures data from key information documents (DIC) to automate your checks, analyses, and treatments at scale.

50 free credits

No credit card

100% secured

Key information documentsKey information documents

The best teams work with Koncile

logo Kuhn
logo Sightness
logo demathieu bard
logo SpendHQ
logo Giesper
logo Beal
logo Cosma
logo skyrm

The tool that extracts key information

Koncile’s OCR automatically analyzes Key Information Documents (KIDs), identifies essential sections such as risk profile, fees, performance scenarios, or holding duration, and converts them into structured data (JSON, Excel, etc.).

Perfect for automating checks, feeding a database, or enabling large-scale analysis.

Extraction template for key information documents

Koncile automates the intelligent extraction of contractual data. Despite the complexity of our clients’ contracts, the tool ensures quality and speed, saving us valuable time.

Fields extracted by the tool

Designed for compliance, finance, or product teams, the tool allows you to centralize KIDs into a structured table: product name, objective, risk level, fees, performance scenarios, recommended holding period, and practical information.

Ideal for automating checks and building a reliable data repository with intelligent document processing.

Name

Type

Example

Guideline

Validité

Text

Oui

Vérifie que le RIB est bien constitué des éléments suivants :
- Code banque (5 chiffres)
- Code guichet (5 chiffres)
- Numéro de compte (11 caractères alphanumériques)
- Clé RIB (2 chiffres)
Si les RIB est bien constitué de ces éléments, choisis la valeur "Oui". Sinon choisis la valeur "Non".

Product name

Text VALOREM DYNAMIQUE 2032 Extract the trade name of the product, often at the top or in the title of the document.

Product type

Text Formula investment contract Identify the category (funds, structured contracts, life insurance, etc.).

Manufacturer

Text Finvaria Capital Full name of the issuing entity (completely fictitious name).

Regulatory authority

Text European Financial Supervision Commission Extract the organization that oversees the product.

Date of publication

Date 28/03/2024 Mark the date to check if the KID is up to date.

Recommended investment period

Text 7 years Identify the recommended investment horizon.

Risk scale

Number 5 Extract the grade from 1 to 7 (SRRI grid).

Main risks

Text Market risk, non-liquidity risk Identify the specific risks mentioned in the document.

Entry costs

Price 120 € Extract the initial fees paid at the time of subscription.

Recurring costs

Number 1,15 % Identify the annual management fees expressed as a percentage or fixed amount.
Flèche courbée vers le haut.

Add any extraction field

Flèche courbée vers le haut.

Edit AI instructions

Why choose Koncile OCR for your AMF regulatory documents?

No items found.
Logo de Koncile.

Try next-generation data extraction

Start with a ready-to-use model, test on a document and scale

Créez vos modèles d’extraction, testez sur un premier document et passez à l’échelle !

A unique extraction solution for your regulatory documents

Automatic collection by OCR and AI

Combination of two technologies to recognize key information, despite the variability of AMF documents

Document flow management

Accelerate your document flow management thanks to automatic field detection.

Optimized document workflow

Koncile's OCR API uses AI algorithms and LLMs to ensure the best reliability in extraction.

Mass documentary check

Build a database based on the information extracted. Perform checks on large volumes.

DIC control and analysis base

Does the DIC contain all the required regulatory information? Is the risk level reported correctly? Are the performance scenarios complete and up to date? Are all the fees well detailed (entry, management, exit)? Is the recommended length of detention specified and consistent? Is the practical information present and accurate? Automate the reading, verification, and structuring of DICs with Koncile's AI OCR.

The OCR API to automate your PDF data capture

status

string

Document status, which can be DONE, DUPLICATE, or IN PROGRESS.

document_id

integar

Unique number assigned to each invoice

general_fields

objects

General fields that appear only once in each extracted document. Returned in the format: {field name: extracted value}

line_fields

objects

Repeated fields extracted in bulk for each line or table. Returned in the format: {field name: extracted value}

status

string

Statut du document qui peut être DONE, DUPLICATE, IN PROGRESS.

document_id

integer

Numéro unique attribué pour chaque document

general_fields

objects

Champs généraux apparaissant une seule fois dans chaque document extrait. Retour au format : {nom du champ: valeur extraite}

line_fields

objects

Champs répétés extraits en bloc pour chaque ligne ou chaque tableau. Retour au format : {nom du champ: valeur extraite}

Request

curl api.koncile.ai/tasks/{task_id}/ \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY"
response = requests.get(f"{api_url}/tasks/{task_id}/",
headers={"accept": "application/json", "Authorization":{"Bearer{api_key}"})

Response

{
"status": DONE | DUPLICATE | IN PROGRESS | FAILED,
"document_id": ID,
"document_name": "name",
"status_message": "",
	"General_fields":
		{
		"Date" : {"value": "05/08/2022", "confidence_score": 0.99},
		"Price" : {"value": "$23", "confidence_score": 0.98}
		}
	,
	"Line_fields":
		{
		"Date" : [{"value": "05/08", "confidence_score": 0.97}, {"value" : "05/08", "confidence_score": 0.98}, ],
		"Price" : [{"value": "$23", "confidence_score": 0.98}, {"value": "$12", "confidence_score": 0.97}],
		}
}

An AI-powered OCR designed for security

No training on your data

Fully encrypted software

Secure storage of extracted data

RGPD compliant

Cadenas noir entouré d'étoiles noires.

Discover all the documents to be automated

SEE ALL TEMPLATES
Confirmation of payment

Accounting

Amount paid, date, payee, bank reference, currency

Transaction confirmation

Accounting

Transaction type, ISIN, amounts, fees

Scan PDF to text automatically extracting information from an energy bill, such as customer name, billing address, energy consumption, total amount due, issue date, due date, due date, and contract number.

Accounting

Customer name, billing address, energy consumption, total amount due, date of issue...

Scan PDF in text automatically extracting information from a Bank check, such as the amount, check number, name of the holder, bank...

Accounting

Amount, check number, name of the holder, bank...

Any question?

Contact us at contact@koncile.ai, check out our documentation, or book a demo.

How does OCR extract information from a key information document?

Koncile OCR automatically detects the essential sections of a DIC, such as the characteristics of the financial product, associated risks, and possible fees. It thus facilitates the analysis and management of regulatory documents.

Can I extract specific information from a key information document?

Yes! You can configure Koncile OCR to retrieve only certain fields such as historical performance, transaction costs, or regulatory warnings according to your needs.

In what format should I import a key information document for OCR analysis?

You can upload your key information document in PDF, PNG, or JPEG. These formats are fully compatible with our OCR technology and guarantee reliable extraction of the data contained. Consult the documentation for more details on the import process.

Can OCR process a printed or handwritten key information document?

Yes, Koncile OCR is capable of processing printed and handwritten documents. If the text is handwritten, it uses advanced character recognition to improve the accuracy of the extracted data.

How does Koncile integrate with my existing tools and software?

Koncile is accessible via an API, with complete documentation available here. Additionally, you can import your documents directly into the application and download the extracted data in XLSX, XLS, CSV, or JSON formats for seamless integration into your workflows.

I need further assistance.

Check our API documentation, contact us at contact@koncile.ai. You can also create a demo account or book a demonstration with our team.

What are Koncile's prices?

Koncile offers 3 plans, including enterprise options for handling large volumes of data. You can check our pricing on the dedicated page in our documentation.

What are general fields and repeated fields?

In each extraction template, you will find:

  • General fields: These are pieces of information that appear only once in each document (e.g., the invoice number or the invoice date).
  • Repeated fields: These are pieces of information that appear multiple times in a document, such as item descriptions or prices in each line of a quote. Use repeated fields for extracting tables and charts from your documents.