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": "CONSULTATION ANESTHESISTE 23056022.pdf",
"total_replacements": 23,
"regex_replacements": 19,
"ner_replacements": 0,
"sweep_replacements": 4,
"entities_found": [
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "65 LOTISSEMENT HITTA GOTEIN-LI N° Tél : [TEL_1]",
"replacement": "[ADRESSE_2]",
"source": "regex",
"category": "adresse"
},
{
"original": "65 LOTISSEMENT HITTA GOTEIN-LI N° Tél : [TEL_1]",
"replacement": "[ADRESSE_2]",
"source": "regex",
"category": "adresse"
}
]
}

View File

@@ -0,0 +1,33 @@
{
"source_file": "CRO 23056022.pdf",
"total_replacements": 15,
"regex_replacements": 8,
"ner_replacements": 4,
"sweep_replacements": 3,
"entities_found": [
{
"original": "Hémolock",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9408332705497742
},
{
"original": "Dufour",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8179958462715149
},
{
"original": "JOSEPH",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.8311591148376465
},
{
"original": "URRUTY",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.9263807535171509
}
]
}

View File

@@ -0,0 +1,267 @@
{
"source_file": "trackare--23056022__23056022.pdf",
"total_replacements": 359,
"regex_replacements": 168,
"ner_replacements": 23,
"sweep_replacements": 168,
"entities_found": [
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23056022",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "GOTEIN LIBARRENX",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "CHIRURGIE UROLOGIE - CHIRURGIE UROLOGIE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "65 LOTISSEMENT HITTA GOTEIN-LIBARRENX Ville de résidence: GOTEIN-LIBARRENX",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "GUILLEMAUD",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9894537329673767
},
{
"original": "KASPARIAN Samuel",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9960604906082153
},
{
"original": "KASPARIAN Samuel S",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9789056777954102
},
{
"original": "Admin",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.8085595965385437
},
{
"original": "KASPARIAN Samuel",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9484346508979797
},
{
"original": "KASPARIAN Samuel",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9475103616714478
},
{
"original": "KASPARIAN Samuel",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9917181730270386
},
{
"original": "KASPARIAN Samuel",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9887701869010925
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_19]",
"source": "ner",
"score": 0.9832062721252441
},
{
"original": "Myriam MAIA",
"replacement": "[SOIGNANT_19]",
"source": "ner",
"score": 0.889935314655304
},
{
"original": "KASPARIAN Samuel",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.991866946220398
},
{
"original": "KASPARIAN Samuel",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9819073677062988
},
{
"original": "KASPARIAN Samuel",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9837175607681274
},
{
"original": "KASPARIAN Samuel Signé",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8373237252235413
},
{
"original": "Celine",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.8264954090118408
},
{
"original": "Celine",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.8168286085128784
},
{
"original": "KASPARIAN",
"replacement": "[SOIGNANT_13]",
"source": "ner",
"score": 0.9810078740119934
},
{
"original": "Clément KLEIN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9974716305732727
},
{
"original": "Clément KLEIN",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9966729879379272
},
{
"original": "Dufour",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8656144142150879
},
{
"original": "Marie Noelle",
"replacement": "[PERSONNE_5]",
"source": "ner",
"score": 0.9791045188903809
},
{
"original": "Agnes SAINT",
"replacement": "[PERSONNE_6]",
"source": "ner",
"score": 0.8532719612121582
},
{
"original": "Clément",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.839396059513092
}
]
}