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 +1,75 @@
{
"source_file": "CRH 23083269.pdf",
"total_replacements": 259,
"regex_replacements": 242,
"ner_replacements": 8,
"sweep_replacements": 9,
"entities_found": [
{
"original": "10004401716",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "10004401716",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "10004401716",
"replacement": "[CODE_BARRE_1]",
"source": "regex",
"category": "code_barre"
},
{
"original": "Mademoiselle GUILHEM LAURIE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9629759788513184
},
{
"original": "GUILHEM Laurie",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9958993792533875
},
{
"original": "Mademoiselle GUILHEM LAURIE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9656683206558228
},
{
"original": "GUILHEM Laurie",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9943408370018005
},
{
"original": "Mademoiselle GUILHEM LAURIE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9781380891799927
},
{
"original": "DUTHEIL",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9940630793571472
},
{
"original": "GUILHEM Laurie",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9946999549865723
},
{
"original": "Ch",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8128128051757812
}
]
}

View File

@@ -0,0 +1,195 @@
{
"source_file": "trackare-16019953-23083269_16019953_23083269.pdf",
"total_replacements": 113,
"regex_replacements": 73,
"ner_replacements": 12,
"sweep_replacements": 28,
"entities_found": [
{
"original": "16019953",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "16019953",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "16019953",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "16019953",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "16019953",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "16019953",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "16019953",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "16019953",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23083269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23083269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23083269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23083269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23083269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23083269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23083269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23083269",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "BAYONNE",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "99 ROUTE DE LA MARQUEZE Ville de résidence: PEY",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "GUILLEMAUD GUILLEMAUD",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9925354719161987
},
{
"original": "Evelyne POCORENA",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.9988545179367065
},
{
"original": "Evelyne POCORENA S",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.9551607966423035
},
{
"original": "Evelyne POCORENA S",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.9563282132148743
},
{
"original": "DEMARSY Delphine S",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9169777035713196
},
{
"original": "Evelyne POCORENA",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.998930811882019
},
{
"original": "Evelyne POCORENA",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.998867928981781
},
{
"original": "Evelyne POCORENA",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.9986712336540222
},
{
"original": "DEMARSY Delphine Signé",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9498677849769592
},
{
"original": "Evelyne",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.9303488731384277
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[SOIGNANT_5]",
"source": "ner",
"score": 0.9957958459854126
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8093932271003723
}
]
}