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 +1,381 @@
{
"source_file": "trackare-22030445-23052612_22030445_23052612.pdf",
"total_replacements": 191,
"regex_replacements": 118,
"ner_replacements": 27,
"sweep_replacements": 46,
"entities_found": [
{
"original": "22030445",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22030445",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22030445",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22030445",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22030445",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22030445",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22030445",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22030445",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22030445",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22030445",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22030445",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22030445",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "22030445",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23052612",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23052612",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23052612",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23052612",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23052612",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23052612",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23052612",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23052612",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23052612",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23052612",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23052612",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23052612",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23052612",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "264086410202830",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "64102",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "BAYONNE",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "CONDOM",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "GROCQ",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "MARIE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "MARIE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "7 CLOS CANTE LOUSSE Ville de résidence: BIZANOS",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "BURTIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9603862166404724
},
{
"original": "T BRAYER Céline",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9877320528030396
},
{
"original": "T BRAYER Céline",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9778780937194824
},
{
"original": "Gonzague Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9987064599990845
},
{
"original": "Gonzague Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9986165165901184
},
{
"original": "Gonzague Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9984229803085327
},
{
"original": "Gonzague Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9944714307785034
},
{
"original": "Gonzague Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9985146522521973
},
{
"original": "MARTIN LECAMP Gonzague Signé",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9932006001472473
},
{
"original": "T BRAYER Céline",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9876630902290344
},
{
"original": "T BRAYER Céline",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9779804944992065
},
{
"original": "Gonzague Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.996349036693573
},
{
"original": "Gonzague Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9732286334037781
},
{
"original": "Gonzague Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9984866976737976
},
{
"original": "Gonzague Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9948990941047668
},
{
"original": "Gonzague Signé",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9985092282295227
},
{
"original": "MARTIN LECAMP Gonzague Signé",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9932416081428528
},
{
"original": "Céline",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9690679907798767
},
{
"original": "Céline ENVIRONNEMENT",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9608566164970398
},
{
"original": "Gonzague MARTIN LECAMP",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.970598578453064
},
{
"original": "Gonzague MARTIN LECAMP",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9183041453361511
},
{
"original": "Gonzague BACTRIM",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9942266345024109
},
{
"original": "Gonzague SPASFON",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.98794025182724
},
{
"original": "CONDOM",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.954666793346405
},
{
"original": "thierry FRANCE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.8715682625770569
},
{
"original": "LOUIS ARAGON",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9120356440544128
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8153306245803833
}
]
}