Refine canonical meeting knowledge architecture

- establish Canonical Meeting Knowledge as the semantic source of truth
- introduce Output View Rendering architecture
- define Working Protocol, Distribution Protocol and Knowledge Objects as parallel renderers
- document renderer responsibilities and terminology
- clarify future Knowledge Object architecture
- document long-term reuse for enterprise knowledge systems
This commit is contained in:
2026-07-30 16:59:58 +02:00
parent f7ad9ba51f
commit 5c03ed7efd
5 changed files with 335 additions and 34 deletions
+27 -3
View File
@@ -43,7 +43,9 @@ Extraktion
↓
Konsolidierung
↓
Protokoll
Canonical Meeting Knowledge
↓
Arbeitsprotokoll / Verteilerprotokoll / Knowledge Objects
```
Jeder Verarbeitungsschritt löst genau eine klar definierte Aufgabe.
@@ -89,18 +91,40 @@ chunk_transcript.py
↓
Extraktoren
↓
Protokoll
Canonical Meeting Knowledge
↓
Output-Ansichten
```
Die Themensegmentierung bildet den nächsten großen Entwicklungsschritt.
Das Meeting Lab behandelt "das Protokoll" nicht mehr als ein einzelnes
Endprodukt. Das konsolidierte Meeting-Wissen ist die **Canonical Meeting
Knowledge**, also die kanonische semantische Repräsentation eines Meetings und
die Single Source of Truth für alle nachgelagerten Ausgaben.
Aus dieser Canonical Meeting Knowledge entstehen drei unabhängige
Output-Ansichten:
- Working Protocol (`working_protocol.md`, Arbeitsprotokoll): relativ vollständig, mit Kontext,
Begründungen, Entscheidungen, Aufgaben und offenen Fragen.
- Distribution Protocol (`distribution_protocol.md`, Verteilerprotokoll): deutlich kürzer,
ergebnisorientiert und für Kolleginnen, Management oder Stakeholder geeignet.
- Knowledge Objects, dargestellt zum Beispiel als Knowledge-base Entry
(`knowledge_entry.md`) oder später strukturiert gespeichert, zum Beispiel als
`knowledge_entry.json` (Wissensdatenbankeintrag).
Diese Ausgaben sind parallele Renderings desselben semantischen Modells. Das
Arbeitsprotokoll ist nicht die Quelle des Verteilerprotokolls, und das
Verteilerprotokoll ist nicht die Quelle der Knowledge Objects.
---
## Projektstatus
Aktuell liegt der Schwerpunkt auf der Entwicklung eines modularen Diskussionsanalyzers.
Die eigentliche Protokollerstellung ist bewusst der letzte Verarbeitungsschritt.
Die eigentliche Ausgabeerzeugung ist bewusst der letzte Verarbeitungsschritt.
---
+27 -5
View File
@@ -100,9 +100,11 @@ Specialized Extraction
↓
Consolidation
↓
Structured Meeting Data
Canonical Meeting Knowledge
↓
Protocol Generation
Output View Rendering
↓
Working Protocol / Distribution Protocol / Knowledge Objects
```
Each stage solves one clearly defined problem.
@@ -185,11 +187,25 @@ Typical responsibilities:
## protocol/
Generates human-readable output from structured meeting data.
Generates output views from Canonical Meeting Knowledge.
Protocol generation never invents information.
Output generation never invents information.
It only reformulates the analysis results.
It only reformulates the analysis results for a specific audience and purpose.
Depending on the output and maturity of the implementation, a renderer may be
deterministic, template-based or LLM-assisted.
The planned output products are:
- Working Protocol (`working_protocol.md`, Arbeitsprotokoll)
- Distribution Protocol (`distribution_protocol.md`,
Verteilerprotokoll)
- Knowledge Objects, which may be rendered as a Knowledge-base Entry
(`knowledge_entry.md`) and later stored in a structured format such as
`knowledge_entry.json` (Wissensdatenbankeintrag)
These are parallel renderings of the same canonical semantic model, not
documents derived from one another.
---
@@ -214,6 +230,7 @@ Examples:
- segmentation.md
- prompts.md
- experiments.md
- output-views.md
The architecture document only describes the overall system.
@@ -231,6 +248,11 @@ The current extraction step still performs multiple tasks simultaneously.
This was sufficient as a proof of concept but does not reflect the intended long-term architecture.
The current protocol builder is also an interim implementation. It concatenates
extraction results into `meeting_protocol.md` for technical validation. The
planned architecture separates Canonical Meeting Knowledge from the final Output
Views documented in `output-views.md`.
---
# Next Milestone
+42 -5
View File
@@ -238,23 +238,60 @@ After extraction, every topic contains the collected information.
}
```
This object represents the main output of the analysis pipeline.
This object feeds the Canonical Meeting Knowledge representation.
---
# Meeting Result
# Canonical Meeting Knowledge
The complete structured meeting.
The canonical semantic representation of one meeting.
This representation is the single source of truth for all downstream outputs.
```json
{
"meeting_id": "meeting_001",
"topics": []
"metadata": {},
"topics": [],
"facts": [],
"decisions": [],
"todos": [],
"questions": [],
"positions": [],
"technical_details": [],
"rationale": [],
"uncertainty": [],
"source_references": []
}
```
Protocol generation operates exclusively on this structure.
This is the common intermediate representation for all final Output Views.
The exact schema is not final and should be refined during future
implementation work.
---
# Output Views
The final outputs are independent renderings of the Canonical Meeting Knowledge.
```text
Canonical Meeting Knowledge
├── Working Protocol
├── Distribution Protocol
└── Knowledge Objects
```
The Working Protocol, Distribution Protocol and Knowledge Objects are not
derived from one another. Each renderer reads the same canonical semantic
model and selects the level of detail appropriate for its purpose.
Knowledge Objects represent durable organizational knowledge such as processes,
definitions, responsibilities, rules, accepted practices and long-term
decisions. They are independent of the original meeting wording. Markdown is one
possible presentation, but JSON or another structured format is expected to
become the canonical storage format later.
---
+185
View File
@@ -0,0 +1,185 @@
# Output Views
The Meeting Lab does not treat "the protocol" as one single final output.
Canonical Meeting Knowledge is the canonical semantic representation of one
meeting. It is the single source of truth for all downstream outputs.
The three output products are independent renderings of this shared semantic
model:
```text
Meeting transcript
->
chunk extraction
->
Canonical Meeting Knowledge
├── Working Protocol
├── Distribution Protocol
└── Knowledge Objects
```
The Working Protocol is not the source of the Distribution Protocol. The
Distribution Protocol is not the source of the Knowledge-base Entry or future
Knowledge Objects.
## Common Intermediate Representation
The common intermediate representation is Canonical Meeting Knowledge.
It should conceptually include:
- meeting metadata
- topics
- facts
- decisions
- action items
- open questions
- positions
- technical information
- rationale and discussion context
- contradictions or uncertainty
- source references and evidence
The detailed schema is future implementation work. The current implementation
still uses simple extraction JSON files and a basic Markdown protocol builder for
technical validation.
## Renderers
Each Output View is produced by a renderer.
Depending on the implementation, rendering may be:
- deterministic
- template-based
- LLM-assisted
The architecture does not assume that every renderer must always use an LLM.
## Working Protocol
Suggested filename: `working_protocol.md`
German working term: Arbeitsprotokoll
Purpose:
- recap the meeting later
- preserve reasoning and context
- support participants and follow-up work
- remain understandable to a neutral reader with limited background
Characteristics:
- relatively complete
- retains relevant background and rationale
- shows how conclusions were reached
- includes decisions, tasks, open questions and important discussion context
- may include rejected alternatives when they help explain the result
- removes obvious noise, duplicates and irrelevant technical interruptions
- is not a verbatim transcript
Completeness goal: optimize for recall and traceability.
## Concise Distribution Protocol
Suggested filename: `distribution_protocol.md`
German working term: Verteilerprotokoll
Terminology decision: use "distribution protocol" rather than "management
protocol" as the default English term because the audience includes colleagues,
management and stakeholders. The document should be suitable for circulation,
not only for management.
Purpose:
- distribute meeting results to colleagues, management or stakeholders
- enable rapid understanding
- communicate only what matters operationally
Characteristics:
- significantly more condensed than the working protocol
- organized around core topics and outcomes
- focuses on purpose, key conclusions, decisions, agreed next steps and
responsibilities
- omits most discussion history and exploratory reasoning
- reads like a polished meeting summary or management memo
Completeness goal: optimize for relevance and brevity.
## Knowledge-Base Entry
Suggested filename: `knowledge_entry.md`
Alternative planned structured format: `knowledge_entry.json`
German working term: Wissensdatenbankeintrag
Purpose:
- preserve durable organizational knowledge
- provide reusable input for a future Knowledge Assistant or RAG system
- detach stable knowledge from the meeting event itself
Characteristics:
- is not written as a meeting recap
- removes conversational framing
- removes temporary discussion details
- focuses on accepted processes, definitions, responsibilities, rules,
decisions with continuing validity and unresolved knowledge gaps
- distinguishes stable knowledge from temporary meeting-specific actions
- may retain source meeting metadata for traceability, but not in the main prose
Completeness goal: optimize for durability and reuse.
Long-term target: Knowledge Objects.
Knowledge Objects may represent durable organizational knowledge such as:
- processes
- definitions
- responsibilities
- rules
- accepted practices
- long-term decisions
Knowledge Objects are independent of the original meeting wording. Markdown is
only one possible presentation. JSON or another structured format is expected to
become the canonical storage format later.
## Future Reuse
Canonical Meeting Knowledge and future Knowledge Objects are intended to become
reusable building blocks for systems such as:
- Meeting Assistant
- Production Knowledge Assistant
- future enterprise knowledge retrieval
- RAG systems
This section is conceptual. It does not define a storage engine, retrieval
architecture or embedding strategy.
## Comparison
Working Protocol:
- preserves context
- useful for later recollection
- relatively complete
Distribution protocol:
- concise
- outcome-oriented
- suitable for circulation
Knowledge-base Entry / Knowledge Objects:
- event-independent
- durable
- structured for future retrieval and reuse
+50 -17
View File
@@ -36,10 +36,14 @@ Specialized Extraction
Consolidation
│
▼
Structured Meeting
Canonical Meeting Knowledge
│
▼
Protocol Generation
Output View Rendering
│
├── Working Protocol
├── Distribution Protocol
└── Knowledge Objects
```
Each stage receives a well-defined input and produces a well-defined output.
@@ -299,13 +303,13 @@ Planned
---
# Stage 7 – Structured Meeting
# Stage 7 – Canonical Meeting Knowledge
## Purpose
Produce a complete machine-readable representation of the meeting.
Produce the canonical semantic representation of one meeting.
This is the primary output of the analysis pipeline.
This representation is the single source of truth for all downstream outputs.
Example:
@@ -326,29 +330,58 @@ Example:
The exact schema will evolve during development.
Conceptually, the Canonical Meeting Knowledge should include:
- meeting metadata
- topics
- facts
- decisions
- action items
- open questions
- positions
- technical information
- rationale and discussion context
- contradictions or uncertainty
- source references and evidence
The detailed schema remains future implementation work.
## Current Status
Planned
---
# Stage 8 – Protocol Generation
# Stage 8 – Output View Rendering
## Purpose
Generate human-readable documents from structured meeting data.
Render purpose-specific outputs from Canonical Meeting Knowledge.
Possible outputs include:
The planned output products are:
- Full protocol
- Executive summary
- Action list
- Decision log
- Technical report
- Working Protocol (`working_protocol.md`, Arbeitsprotokoll)
- Distribution Protocol (`distribution_protocol.md`, Verteilerprotokoll)
- Knowledge Objects, rendered as a Knowledge-base Entry (`knowledge_entry.md`)
and later stored in a structured format such as `knowledge_entry.json`
(Wissensdatenbankeintrag)
Protocol generation never performs additional analysis.
Output rendering never performs additional analysis.
It only transforms existing structured information into readable text.
It only transforms existing structured information into the required view.
The outputs are rendered in parallel from the canonical representation. The
Distribution Protocol is not derived from the Working Protocol, and Knowledge
Objects are not derived from either protocol.
Rendering may be deterministic, template-based or LLM-assisted depending on the
output and implementation maturity.
Completeness differs by output:
- The Working Protocol optimizes for recall and traceability.
- The Distribution Protocol optimizes for relevance and brevity.
- Knowledge Objects optimize for durability and reuse.
## Processing Type
@@ -420,9 +453,9 @@ A processing stage may be replaced by another implementation as long as it prese
⬜ Consolidation
⬜ Structured Meeting
⬜ Canonical Meeting Knowledge
⬜ Protocol Generation
⬜ Output View Rendering
```
The immediate development focus is **Topic Segmentation**, as it provides the semantic structure on which all subsequent processing stages depend.