Fix over-correlation: geocoding precision, thin path ambiguity, skip_reason propagation

- Geocoding: reject GEOMETRIC_CENTER/APPROXIMATE results — vague location strings
  (regions, city centroids) were resolving to node-area coords and creating false
  proximity matches that merged unrelated incidents
- Thin path: on dispatch channels with multiple active incidents, skip attachment
  rather than guessing — "10-4" with 3 active incidents is genuinely ambiguous
- Short transcripts (≤5 words) now write skip_reason="transcript_too_short" to
  the call doc, matching garbage transcript behavior
- upload.py no-scenes fallback now checks skip_reason before running correlation —
  flagged calls (garbage, too short) no longer attach via thin path
- Update Server README to reflect current project purpose, goals, and pipeline
This commit is contained in:
Logan
2026-05-31 23:51:46 -04:00
parent f774be12b8
commit b77d2cce36
4 changed files with 111 additions and 152 deletions
+17 -13
View File
@@ -241,20 +241,24 @@ async def _run_intelligence_pipeline(
# Correlator also runs for calls with no scenes (unclassified) to attempt
# talkgroup-based linking even when no transcript could be produced.
# Skip when extraction flagged the call — garbage or too-short transcripts
# carry no signal and would only attach spuriously via the thin path.
if not scenes:
incident_id = await incident_correlator.correlate_call(
call_id=call_id,
node_id=node_id,
system_id=system_id,
talkgroup_id=talkgroup_id,
talkgroup_name=talkgroup_name,
tags=[],
incident_type=None,
location=None,
location_coords=None,
)
if incident_id:
incident_ids.append(incident_id)
_call_doc = await fstore.doc_get("calls", call_id)
if not (_call_doc or {}).get("skip_reason"):
incident_id = await incident_correlator.correlate_call(
call_id=call_id,
node_id=node_id,
system_id=system_id,
talkgroup_id=talkgroup_id,
talkgroup_name=talkgroup_name,
tags=[],
incident_type=None,
location=None,
location_coords=None,
)
if incident_id:
incident_ids.append(incident_id)
if incident_ids:
await fstore.doc_set("calls", call_id, {"incident_ids": incident_ids})