Skip to main content
blog.backLink
ยท7 minintelligenceproductivityNLP

Automatic Insight Extraction: Decisions, Tasks, and Deadlines

After a one-hour meeting, you have thousands of words. But what actually matters? The three decisions made, five action items assigned, and the deadline mentioned in passing. dijin extracts these automatically.

5 categories
Insight Types
99 supported
Languages
6
Pipeline Stages
100% on-device
Processing

What Gets Extracted

Insight TypeExampleWhat Gets Captured
Decisions"We decided to go with Option B"Participants, context, timestamp
Action Items"Ayse will prepare the report by Friday"Assignee, deadline, task description
Calendar Events"Let's meet next Tuesday at 3pm"Date/time parsed across 99 languages
Key TopicsImportant subjects discussedWeighted by frequency and context
People MentionedNames and referencesLinked to the knowledge graph

The 6-Stage FrameCompiler Pipeline

1

Signal Detection

Scans for temporal markers, imperative verbs, and decision language in the transcript text.

2

Entity Extraction

Identifies people, organizations, dates, and locations mentioned in the conversation.

3

Relationship Mapping

Links entities together โ€” who assigned what to whom, who committed to which deadline.

4

Classification

Categorizes each insight as decision, action item, calendar event, or topic.

5

Confidence Scoring

Low-confidence items go to a quarantine queue for human review before being committed.

6

Structured Output

Clean, typed data written to your local database โ€” ready for search and retrieval.

Calendar Detection Across 99 Languages

๐Ÿ’ก
The CalendarDetectionService supports 99 languages with a 7-stage parsing pipeline. "Yarin saat 10'da" (Turkish), "ๆ˜Žๆ—ฅใฎ10ๆ™‚ใซ" (Japanese), and "tomorrow at 10am" (English) all resolve to the same absolute datetime.
Calendar Detection Pipeline
Raw Text: "Let's meet tomorrow at 10am"
Language Detection โ”€โ”€โ–ถ English
Temporal Signal โ”€โ”€โ–ถ "tomorrow" = relative
Time Extraction โ”€โ”€โ–ถ "10am" = 10:00
Absolute Resolution โ”€โ”€โ–ถ 2026-03-23T10:00:00
Validation โ”€โ”€โ–ถ โœ” Valid future datetime```

Everything On-Device

๐Ÿ”’
The entire pipeline runs locally using on-device language model. Your insights are generated and stored on your device. The cloud never sees your meeting content.

blog.tryCta

blog.ctaDescription

blog.ctaButton
Automatic Insight Extraction: Decisions, Tasks, and Deadlines