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": "CRO 23110276.pdf",
"total_replacements": 14,
"regex_replacements": 6,
"ner_replacements": 5,
"sweep_replacements": 3,
"entities_found": [
{
"original": "Jackson Pratt",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9895081520080566
},
{
"original": "MAITENA-JEANNINE ETCHEBER",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9890620708465576
},
{
"original": "PARRIEUS",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.8870981335639954
},
{
"original": "Pfannenstiel",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9201762676239014
},
{
"original": "MAITENA-JEANNINE ETCHEBER",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9873958230018616
}
]
}

View File

@@ -0,0 +1,351 @@
{
"source_file": "trackare-13001603-23110276_13001603_23110276.pdf",
"total_replacements": 593,
"regex_replacements": 267,
"ner_replacements": 13,
"sweep_replacements": 313,
"entities_found": [
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "13001603",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23110276",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "MAULEON LICHARRE",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "CHIRURGIE VISCERALE - CHIRURGIE VISCERALE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_3]",
"source": "regex",
"category": "patient"
},
{
"original": "14 RUE PAUL JEAN TOULET Ville de résidence: CARRESSE CASSABER",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "REY Juliette",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9077056050300598
},
{
"original": "REY Juliette",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9467732310295105
},
{
"original": "HIRIGARAY Mirentxu",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.8931079506874084
},
{
"original": "SOL REY Juliette",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9826032519340515
},
{
"original": "ONDANSETRON AGT",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9894355535507202
},
{
"original": "SOL REY Juliette",
"replacement": "[MEDECIN_4]",
"source": "ner",
"score": 0.9547348022460938
},
{
"original": "ONDANSETRON AGT",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.913563072681427
},
{
"original": "Goudarz",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.8030011057853699
},
{
"original": "Goudarz TAGHVA PASSAND",
"replacement": "[SOIGNANT_8]",
"source": "ner",
"score": 0.9522589445114136
},
{
"original": "Goudarz",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.8097088932991028
},
{
"original": "Dr.DURANTEAU",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.994686484336853
},
{
"original": "Jackson",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8055833578109741
},
{
"original": "Parrieus Jean Daniel",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9689241647720337
}
]
}