Implement WP-15c enhancements across graph and retrieval modules, including full metadata support for Super-Edge aggregation and Note-Level Diversity Pooling. Update scoring logic to reflect new edge handling and improve retrieval accuracy. Version updates to reflect these changes.
This commit is contained in:
1 parent
cd5056d4c9
commit
d35bdc64b9
5 files changed
+202
-91
No files matched your search
@@ -1,11 +1,10 @@
|
||||
"""
|
||||
FILE: app/core/retrieval/retriever_scoring.py
|
||||
DESCRIPTION: Mathematische Kern-Logik für das WP-22 Scoring.
|
||||
DESCRIPTION: Mathematische Kern-Logik für das WP-22/WP-15c Scoring.
|
||||
Berechnet Relevanz-Scores basierend auf Semantik, Graph-Intelligence und Content Lifecycle.
|
||||
MODULARISIERUNG: Verschoben in das retrieval-Paket für WP-14.
|
||||
VERSION: 1.0.2
|
||||
FIX v1.0.3: Optimierte Interaktion zwischen Typ-Boost und Status-Dämpfung.
|
||||
VERSION: 1.0.3
|
||||
STATUS: Active
|
||||
DEPENDENCIES: app.config, typing
|
||||
"""
|
||||
import os
|
||||
import logging
|
||||
@@ -23,10 +22,6 @@ logger = logging.getLogger(__name__)
|
||||
def get_weights() -> Tuple[float, float, float]:
|
||||
"""
|
||||
Liefert die Basis-Gewichtung (semantic, edge, centrality) aus der Konfiguration.
|
||||
Priorität:
|
||||
1. config/retriever.yaml (Scoring-Sektion)
|
||||
2. Umgebungsvariablen (RETRIEVER_W_*)
|
||||
3. System-Defaults (1.0, 0.0, 0.0)
|
||||
"""
|
||||
from app.config import get_settings
|
||||
settings = get_settings()
|
||||
@@ -58,7 +53,7 @@ def get_status_multiplier(payload: Dict[str, Any]) -> float:
|
||||
|
||||
- stable: 1.2 (Belohnung für verifiziertes Wissen)
|
||||
- active: 1.0 (Standard-Gewichtung)
|
||||
- draft: 0.5 (Bestrafung für unfertige Fragmente)
|
||||
- draft: 0.5 (Dämpfung für unfertige Fragmente)
|
||||
"""
|
||||
status = str(payload.get("status", "active")).lower().strip()
|
||||
if status == "stable":
|
||||
@@ -75,35 +70,42 @@ def compute_wp22_score(
|
||||
dynamic_edge_boosts: Optional[Dict[str, float]] = None
|
||||
) -> Dict[str, Any]:
|
||||
"""
|
||||
Die zentrale mathematische Scoring-Formel der Mindnet Intelligence.
|
||||
Implementiert das WP-22 Hybrid-Scoring (Semantic * Lifecycle * Graph).
|
||||
Die zentrale mathematische Scoring-Formel (WP-15c optimiert).
|
||||
Implementiert das Hybrid-Scoring (Semantic * Lifecycle * Graph).
|
||||
|
||||
FORMEL:
|
||||
Score = (Similarity * StatusMult) * (1 + (TypeWeight - 1) + ((EdgeW * EB + CentW * CB) * IntentBoost))
|
||||
LOGIK:
|
||||
1. Base = Similarity * StatusMult (Lifecycle-Filter).
|
||||
2. Boosts = (TypeBoost - 1) + (GraphBoni * IntentFactor).
|
||||
3. Final = Base * (1 + Boosts).
|
||||
|
||||
Returns:
|
||||
Dict mit dem finalen 'total' Score und allen mathematischen Zwischenwerten für den Explanation Layer.
|
||||
Der edge_bonus_raw enthält bereits die Super-Edge-Aggregation (WP-15c).
|
||||
"""
|
||||
sem_w, edge_w_cfg, cent_w_cfg = get_weights()
|
||||
status_mult = get_status_multiplier(payload)
|
||||
|
||||
# Retriever Weight (Type Boost aus types.yaml, z.B. 1.1 für Decisions)
|
||||
# Retriever Weight (Typ-Boost aus types.yaml, z.B. 1.1 für Decisions)
|
||||
node_weight = float(payload.get("retriever_weight", 1.0))
|
||||
|
||||
# 1. Berechnung des Base Scores (Semantik gewichtet durch Lifecycle-Status)
|
||||
# WICHTIG: Der Status wirkt hier als Multiplikator auf die Basis-Relevanz.
|
||||
base_val = float(semantic_score) * status_mult
|
||||
|
||||
# 2. Graph Boost Factor (Teil C: Intent-spezifische Verstärkung)
|
||||
# 2. Graph Boost Factor (Intent-spezifische Verstärkung aus decision_engine.yaml)
|
||||
# Erhöht das Gewicht des gesamten Graphen um 50%, wenn ein spezifischer Intent vorliegt.
|
||||
graph_boost_factor = 1.5 if dynamic_edge_boosts and (edge_bonus_raw > 0 or cent_bonus_raw > 0) else 1.0
|
||||
|
||||
# 3. Einzelne Graph-Komponenten berechnen
|
||||
# WP-15c Hinweis: edge_bonus_raw ist durch den retriever.py bereits gedämpft/aggregiert.
|
||||
edge_impact_final = (edge_w_cfg * edge_bonus_raw) * graph_boost_factor
|
||||
cent_impact_final = (cent_w_cfg * cent_bonus_raw) * graph_boost_factor
|
||||
|
||||
# 4. Finales Zusammenführen (Merging)
|
||||
# (node_weight - 1.0) sorgt dafür, dass ein Gewicht von 1.0 keinen Einfluss hat (neutral).
|
||||
total = base_val * (1.0 + (node_weight - 1.0) + edge_impact_final + cent_impact_final)
|
||||
# (node_weight - 1.0) wandelt das Gewicht in einen relativen Bonus um (z.B. 1.2 -> +0.2).
|
||||
# Alle Boni werden addiert und wirken dann auf den base_val.
|
||||
type_impact = node_weight - 1.0
|
||||
total_boost = 1.0 + type_impact + edge_impact_final + cent_impact_final
|
||||
|
||||
total = base_val * total_boost
|
||||
|
||||
# Sicherstellen, dass der Score niemals 0 oder negativ ist (Floor)
|
||||
final_score = max(0.0001, float(total))
|
||||
@@ -114,7 +116,7 @@ def compute_wp22_score(
|
||||
"cent_bonus": float(cent_bonus_raw),
|
||||
"status_multiplier": status_mult,
|
||||
"graph_boost_factor": graph_boost_factor,
|
||||
"type_impact": node_weight - 1.0,
|
||||
"type_impact": type_impact,
|
||||
"base_val": base_val,
|
||||
"edge_impact_final": edge_impact_final,
|
||||
"cent_impact_final": cent_impact_final
|
||||
|
||||
Reference in new issue
Block a user