Glossary

Unstructured Data

What is Unstructured Data?

Unstructured data follow no fixed table schema: emails, contracts, manuals, web pages, presentations, images or audio recordings. They make up a large share of organisational knowledge but were long difficult to analyse automatically. Language models can read and search such content and turn it into structured information, for example extracting deadlines and amounts from a contract into a table.

How KI.ordo helps

In KI.ordo, text, PDFs with a text layer, Word files and web pages can be added as knowledge, which agents then use with source references.

Learn more →

Topics

Data
Documents
Knowledge

Try KI.ordo

Agents, flows and templates in one workspace – free 24-hour demo.

Start demo

← All terms

Related terms

Structured data

Structured data follows a fixed schema with clearly named fields, such as tables, databases or JSON objects containing details like name, price and date. Machines can read, filter and process it reliably – unlike free text or images. On websites, schema.org markup describes products, events or FAQs, for example, so that search engines and AI systems understand the content unambiguously. AI can also extract structured data from unstructured text.

data
JSON
+1

Intelligent Document Processing (IDP)

Intelligent document processing (IDP) automatically reads documents such as invoices, contracts or forms, identifies their type and turns the relevant details into structured data. It combines text recognition for scans, natural language processing and validation rules. Organisations save manual data entry and speed up processes such as handling incoming invoices or post. Uncertain fields should be checked by people.

Documents
Data extraction
+1

Template

Data mining

Data mining is the systematic search of large data sets for patterns, relationships and anomalies. It draws on statistical techniques and machine learning methods such as clustering, classification or association analysis. A classic example is market basket analysis in retail, which shows which products are often bought together – a basis for product range, placement and recommendations.

data analysis
pattern recognition
+1