feat(iace): narrative vocabulary overlap filter replaces blacklist

Replace machine-specific term blacklist with generic vocabulary overlap:
- Extract significant words (>=5 chars, not generic safety terms) from
  pattern zone/scenario
- If pattern has specific words but NONE appear in narrative → filter
- genericSafetyTerms whitelist with ~50 terms that appear in all assessments
- Truly generic approach: works for any machine type without maintenance

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

ai-compliance-sdk/internal/api/handlers/iace_handler_init_helpers.go

@@ -199,53 +199,65 @@ func containsSubstring(haystack, needle string) bool {
 	)
 }
 
-// machineSpecificTerms are words in a pattern's zone/scenario that indicate
-// the pattern is specific to a particular machine type. If a pattern contains
-// such a term but the machine narrative does NOT, the pattern is irrelevant.
-var machineSpecificTerms = []string{
-	"extruder", "spinnmaschine", "spielplatz", "aufzug", "elevator",
-	"kran", "crane", "bagger", "excavator", "traktor", "tractor",
-	"harvester", "druckmaschine", "printing", "webstuhl", "weaving",
-	"ofen", "furnace", "kessel", "boiler", "walzwerk", "rolling",
-	"zentrifuge", "centrifuge", "autoklav", "autoclave", "saege",
-	"kreissaege", "circular_saw", "hobel", "fraese", "drehmaschine",
-	"lathe", "schleifmaschine", "grinder", "stanze", "stanzpresse",
-	"infusion", "beatmung", "ventilator", "patient",
-	"lebensmittel", "food", "pharma", "verpackung", "packaging",
-	"seilnetz", "kletterseil", "schaukel", "rutsche",
-	"gabelstapler", "forklift", "flurfoerder",
+// genericSafetyTerms are words that appear in almost all risk assessments
+// and should NOT be used to determine machine-specificity.
+var genericSafetyTerms = map[string]bool{
+	"maschine": true, "anlage": true, "bereich": true, "gesamte": true,
+	"arbeitsplatz": true, "gefahrbereich": true, "gefahrstelle": true,
+	"gefahrenstelle": true, "person": true, "werker": true, "bediener": true,
+	"steuerung": true, "schutzeinrichtung": true, "sicherheit": true,
+	"betrieb": true, "wartung": true, "instandhaltung": true, "reinigung": true,
+	"bewegung": true, "beweglich": true, "feststehend": true, "teil": true,
+	"teile": true, "oeffnung": true, "zugang": true, "gefahr": true,
+	"verletzung": true, "quetsch": true, "scher": true, "schneid": true,
+	"stoss": true, "schlag": true, "einzug": true, "brand": true,
+	"motor": true, "antrieb": true, "achse": true, "achsen": true,
+	"kabel": true, "leitung": true, "schaltschrank": true, "spannung": true,
+	"schutz": true, "gehaeuse": true, "oberflaeche": true, "boden": true,
+	"leitfaehig": true, "elektrisch": true, "mechanisch": true,
+	"bedienfeld": true, "display": true, "anzeige": true,
+	"energie": true, "druck": true, "temperatur": true,
 }
 
 // isPatternRelevant checks whether a pattern match is relevant to the actual
-// machine described in the narrative. A pattern is considered irrelevant if its
-// zone or scenario contains machine-specific terms that don't appear in the
-// narrative or component list.
+// machine described in the narrative. Uses narrative vocabulary overlap:
+// if the pattern's zone/scenario contains machine-specific words (not generic
+// safety terms) and NONE of them appear in the narrative → irrelevant.
 func isPatternRelevant(mp iace.PatternMatch, narrative string, compNames []string) bool {
-	patternText := iace.NormalizeDEPublic(mp.ZoneDE + " " + mp.ScenarioDE + " " + mp.PatternName)
+	patternText := iace.NormalizeDEPublic(mp.ZoneDE + " " + mp.ScenarioDE)
 	narrativeNorm := iace.NormalizeDEPublic(narrative)
 
-	// Check if pattern mentions machine-specific terms absent from narrative
-	for _, term := range machineSpecificTerms {
-		if !strings.Contains(patternText, term) {
+	// Extract machine-specific words from pattern (not generic safety terms)
+	patternWords := strings.Fields(patternText)
+	var specificWords []string
+	for _, w := range patternWords {
+		// Clean punctuation
+		w = strings.Trim(w, ".,;:!?()/-")
+		if len(w) < 5 || genericSafetyTerms[w] {
 			continue
 		}
-		// Pattern mentions this machine-specific term — check if machine has it
-		if strings.Contains(narrativeNorm, term) {
-			continue // Machine has this term, pattern is relevant
+		specificWords = append(specificWords, w)
+	}
+
+	// If pattern has no specific words, it's generic → always relevant
+	if len(specificWords) == 0 {
+		return true
+	}
+
+	// Check if at least one specific word appears in the narrative or components
+	for _, sw := range specificWords {
+		if strings.Contains(narrativeNorm, sw) {
+			return true
 		}
-		// Also check component names
-		found := false
 		for _, cn := range compNames {
-			if strings.Contains(cn, term) {
-				found = true
-				break
+			if strings.Contains(cn, sw) {
+				return true
 			}
 		}
-		if !found {
-			return false // Pattern mentions a machine type we don't have
-		}
 	}
-	return true
+
+	// No specific word found in narrative → pattern is for a different machine
+	return false
 }
 
 // normalizeZoneKey reduces a zone string to its core components for better dedup.