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 +1,39 @@
{
"source_file": "LETTRE DE SORTIE 23074376.pdf",
"total_replacements": 15,
"regex_replacements": 6,
"ner_replacements": 5,
"sweep_replacements": 4,
"entities_found": [
{
"original": "Monsieur Baptiste GARAY",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9595668911933899
},
{
"original": "Monsieur Baptiste GARAY",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9094526171684265
},
{
"original": "Docteu HEBERT",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.9928783178329468
},
{
"original": "Do HEBERT",
"replacement": "[MEDECIN_2]",
"source": "ner",
"score": 0.8603065609931946
},
{
"original": "BAPTISTE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.8035805225372314
}
]
}

View File

@@ -0,0 +1,387 @@
{
"source_file": "trackare-05000272-23074376_05000272_23074376.pdf",
"total_replacements": 281,
"regex_replacements": 172,
"ner_replacements": 25,
"sweep_replacements": 84,
"entities_found": [
{
"original": "05000272",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05000272",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05000272",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05000272",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05000272",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05000272",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05000272",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05000272",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05000272",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05000272",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05000272",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05000272",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05000272",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05000272",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05000272",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23074376",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23074376",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23074376",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23074376",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23074376",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23074376",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23074376",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23074376",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23074376",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23074376",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23074376",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23074376",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23074376",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23074376",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23074376",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "99999",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "Nationalité: FRANCE Code Postal: 40440",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "GARAY",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "GARAY",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "BAPTISTE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "BAPTISTE",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "559 AV DU 8 MAI 1945 Ville de résidence: ONDRES",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "GUILLEMAUD GUILLEMAUD",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9979950189590454
},
{
"original": "Willis",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8246563673019409
},
{
"original": "Willis",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.802290678024292
},
{
"original": "Willis",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8591846823692322
},
{
"original": "LACAZEDIEU Laure",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9427973628044128
},
{
"original": "LACAZEDIEU Laure",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9403047561645508
},
{
"original": "LACAZEDIEU Laure Signé",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9161123633384705
},
{
"original": "LACAZEDIEU Laure Signé",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.8772880434989929
},
{
"original": "Antoine S",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.8338096141815186
},
{
"original": "Laure TOILETTE",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9722241163253784
},
{
"original": "Laure SOMMEIL",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.951752781867981
},
{
"original": "Laure REPAS",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9538171291351318
},
{
"original": "Laure S",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9889230728149414
},
{
"original": "Laure",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9339106678962708
},
{
"original": "Laure",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.8447633981704712
},
{
"original": "Baptiste SAUDE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.99173504114151
},
{
"original": "Baptiste SAUDE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9975992441177368
},
{
"original": "Baptiste SAUDE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.996890664100647
},
{
"original": "Baptiste SAUDE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9957278966903687
},
{
"original": "Baptiste SAUDE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9898887276649475
},
{
"original": "Baptiste SAUDE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9858978390693665
},
{
"original": "Willis",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8502018451690674
},
{
"original": "BAUNY DE RECY",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9388448596000671
},
{
"original": "Sylvie CHALVET",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9858371019363403
},
{
"original": "Baptiste SAUDE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9675445556640625
}
]
}