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 +1,63 @@
{
"source_file": "CRH 23096269.pdf",
"total_replacements": 187,
"regex_replacements": 168,
"ner_replacements": 7,
"sweep_replacements": 12,
"entities_found": [
{
"original": "10100402527",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "10100402527",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "VESICA",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8187446594238281
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9354087114334106
},
{
"original": "ALZUAGA Marie-josephe",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9945461750030518
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9149721264839172
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8203544020652771
},
{
"original": "ALZUAGA Marie-josephe",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9898970127105713
},
{
"original": "COUECOU",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9882931709289551
}
]
}

View File

@@ -0,0 +1,363 @@
{
"source_file": "trackare-07004859-23096269_07004859_23096269.pdf",
"total_replacements": 582,
"regex_replacements": 234,
"ner_replacements": 22,
"sweep_replacements": 326,
"entities_found": [
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "07004859",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23096269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "ST JEAN DE LUZ",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "MAISON OUHAIDEKO BORDA QR AMOTZ Ville de résidence: ST PEE SUR NIVELLE",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9914082288742065
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9866321086883545
},
{
"original": "BRAYER Céline",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9486510753631592
},
{
"original": "MAURY Elisa",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9919149279594421
},
{
"original": "Marie",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9067549705505371
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9925684928894043
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9888979196548462
},
{
"original": "BRAYER Céline",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9567642211914062
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9370718002319336
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.95831298828125
},
{
"original": "MAURY Elisa",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9920810461044312
},
{
"original": "Marie",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9111375212669373
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9963575601577759
},
{
"original": "Camille Marie",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9518718123435974
},
{
"original": "Camille Marie",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.8858247995376587
},
{
"original": "Habitus",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8969901204109192
},
{
"original": "Camille Marie",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9549326300621033
},
{
"original": "Camille Marie",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9341237545013428
},
{
"original": "LAGNAOUI",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8322418928146362
},
{
"original": "Habitus",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.869589626789093
},
{
"original": "Fille alzuaga sophie",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.962235152721405
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8138427734375
}
]
}