chore: mise à jour output pipeline (anonymized + structured)

Résultats de re-traitement pipeline v2 sur 261 dossiers.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
dom
2026-03-07 23:14:42 +01:00
parent c73515ac89
commit 13fe9fa666
734 changed files with 157158 additions and 304963 deletions

View File

@@ -0,0 +1,51 @@
{
"source_file": "CRH 23048705.pdf",
"total_replacements": 30,
"regex_replacements": 20,
"ner_replacements": 7,
"sweep_replacements": 3,
"entities_found": [
{
"original": "FRANCIS",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.8766564130783081
},
{
"original": "BOUDJEMA",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9406740069389343
},
{
"original": "BOUDJEMA",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9612061381340027
},
{
"original": "BOUDJEMA Francis",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9887377619743347
},
{
"original": "Francis BOUDJEMA",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9965651035308838
},
{
"original": "FRANCIS",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9016990065574646
},
{
"original": "BOUDJEMA",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9898114204406738
}
]
}

View File

@@ -0,0 +1,27 @@
{
"source_file": "CRO 23048705.pdf",
"total_replacements": 12,
"regex_replacements": 7,
"ner_replacements": 3,
"sweep_replacements": 2,
"entities_found": [
{
"original": "Justin ANDRIAMIANDRASOA",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9986991882324219
},
{
"original": "FRANCIS",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9388927221298218
},
{
"original": "BOUDJEMA",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9931316375732422
}
]
}