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 +1,27 @@
{
"source_file": "LETTRE DE SORTIE 23077016.pdf",
"total_replacements": 9,
"regex_replacements": 5,
"ner_replacements": 3,
"sweep_replacements": 1,
"entities_found": [
{
"original": "Marisa CARVALHO DA SILVA ALUAI",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9980971813201904
},
{
"original": "MARISA CARVALHO DA SILVA",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9982215166091919
},
{
"original": "CARVALHO DA SILVA ALUAI",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9930835962295532
}
]
}

View File

@@ -0,0 +1,573 @@
{
"source_file": "trackare-05006025-23077016_05006025_23077016.pdf",
"total_replacements": 296,
"regex_replacements": 166,
"ner_replacements": 46,
"sweep_replacements": 84,
"entities_found": [
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "05006025",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23077016",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "278059913921066",
"replacement": "[NIR_1]",
"source": "regex",
"category": "nir"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "99139",
"replacement": "[LIEU_NAISS_2]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "Nationalité: PORTUGAL Code Postal: 64100",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "CARVALHO DA SILVA",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "DOUARD Antoine",
"replacement": "[MEDECIN_1]",
"source": "regex",
"category": "patient"
},
{
"original": "CHIRURGIE UROLOGIE - CHIRURGIE UROLOGIE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "OLIVEIRA",
"replacement": "[CONTACT_2]",
"source": "regex",
"category": "contact"
},
{
"original": "CARVALHO DA SILVA ALUAI",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "MARISA",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "MARISA",
"replacement": "[PATIENT_1]",
"source": "regex",
"category": "patient"
},
{
"original": "7 AVENUE DE JOUANDIN BAT 7 8eme etage Ville de résidence: BAYONNE",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "BURTIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9926689267158508
},
{
"original": "GILBERT Clara",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9272481203079224
},
{
"original": "KARAM Lydia",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9800959825515747
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9983878135681152
},
{
"original": "Clara ARGANO",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9988400936126709
},
{
"original": "Clara ARGANO",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9988911747932434
},
{
"original": "Clara ARGANO",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9969693422317505
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9971696734428406
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9965109825134277
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9942179322242737
},
{
"original": "SCHURDI-LEVRAUD",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8557348251342773
},
{
"original": "LANSOPRAZOLE",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9175722002983093
},
{
"original": "SOL DOUARD Antoine",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.8552507162094116
},
{
"original": "KARAM Lydia",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.9906021952629089
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9976065754890442
},
{
"original": "Clara ARGANO",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9980559945106506
},
{
"original": "Clara ARGANO",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.998266339302063
},
{
"original": "Clara ARGANO",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9981390237808228
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9974718689918518
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9970868229866028
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9950857758522034
},
{
"original": "SCHURDI-LEVRAUD",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9161380529403687
},
{
"original": "KARAM Lydia",
"replacement": "[MEDECIN_5]",
"source": "ner",
"score": 0.8443399667739868
},
{
"original": "SCHURDI-LEVRAUD",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8160402774810791
},
{
"original": "SCHURDI-LEVRAUD",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9905277490615845
},
{
"original": "SCHURDI-LEVRAUD",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9793316125869751
},
{
"original": "SOL DOUARD Antoine",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.8724178075790405
},
{
"original": "Myriam TOILETTE",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9526510834693909
},
{
"original": "Clara SOMMEIL",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9467781782150269
},
{
"original": "Myriam S",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.8076021671295166
},
{
"original": "Myriam LEVER",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.8362615704536438
},
{
"original": "Myriam",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.8469980955123901
},
{
"original": "Léo SCHURDI-LEVRAUD",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9989754557609558
},
{
"original": "Léo SCHURDI-LEVRAUD",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9989690780639648
},
{
"original": "Léo SCHURDI-LEVRAUD",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9989358186721802
},
{
"original": "Léo SCHURDI",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9777721166610718
},
{
"original": "LEVRAUD",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9160251021385193
},
{
"original": "Léo SCHURDI",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.993896484375
},
{
"original": "LEVRAUD",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9355131983757019
},
{
"original": "Léo SCHURDI",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9965866804122925
},
{
"original": "Quincke",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.917259156703949
},
{
"original": "A.DOUARD",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9736952781677246
},
{
"original": "A.Douard",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9365774393081665
},
{
"original": "A.Douard",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.9758402109146118
},
{
"original": "U.Duranteau",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9936211705207825
},
{
"original": "U.Duranteau",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9627269506454468
}
]
}