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 +1,33 @@
{
"source_file": "CRO-23089947.pdf",
"total_replacements": 12,
"regex_replacements": 5,
"ner_replacements": 4,
"sweep_replacements": 3,
"entities_found": [
{
"original": "Callot",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.924111008644104
},
{
"original": "ANDRIANAVALOMIONONA",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9755253195762634
},
{
"original": "DENIS",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.9081209301948547
},
{
"original": "BENAIM",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.9568770527839661
}
]
}

View File

@@ -0,0 +1,33 @@
{
"source_file": "CRO 23089947.pdf",
"total_replacements": 12,
"regex_replacements": 5,
"ner_replacements": 4,
"sweep_replacements": 3,
"entities_found": [
{
"original": "Callot",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.924111008644104
},
{
"original": "ANDRIANAVALOMIONONA",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9755253195762634
},
{
"original": "DENIS",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.9081209301948547
},
{
"original": "BENAIM",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.9568770527839661
}
]
}

View File

@@ -0,0 +1,177 @@
{
"source_file": "trackare-15001617-23089947_15001617_23089947.pdf",
"total_replacements": 135,
"regex_replacements": 75,
"ner_replacements": 11,
"sweep_replacements": 49,
"entities_found": [
{
"original": "15001617",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "15001617",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "15001617",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "15001617",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "15001617",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "15001617",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "15001617",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23089947",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089947",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089947",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089947",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089947",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089947",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23089947",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "ORAN",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "308 ROUTE DE BORDABERRI Ville de résidence: AICIRITS CAMOU SUHAST",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "DALIA Amaïa",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9900829792022705
},
{
"original": "DALIA Amaïa",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9779977798461914
},
{
"original": "Amaïa",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.969623327255249
},
{
"original": "Amaïa",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9767284393310547
},
{
"original": "Amaïa",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.942713737487793
},
{
"original": "Amaïa",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9716917872428894
},
{
"original": "Amaïa",
"replacement": "[SOIGNANT_4]",
"source": "ner",
"score": 0.9521362781524658
},
{
"original": "Goudarz TAGHVA PASS",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.9914166927337646
},
{
"original": "Goudarz TAGHVA PAS",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.9874054193496704
},
{
"original": "Goudarz",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.8597573637962341
},
{
"original": "Goudarz",
"replacement": "[SOIGNANT_3]",
"source": "ner",
"score": 0.9569267630577087
}
]
}