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 +1,21 @@
{
"source_file": "LETTRE DE SORTIE 23113695.pdf",
"total_replacements": 10,
"regex_replacements": 6,
"ner_replacements": 2,
"sweep_replacements": 2,
"entities_found": [
{
"original": "Monsieur IRIBARNE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9818539619445801
},
{
"original": "IRIBARNE",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9765933156013489
}
]
}

View File

@@ -0,0 +1,393 @@
{
"source_file": "trackare--23113695__23113695.pdf",
"total_replacements": 473,
"regex_replacements": 200,
"ner_replacements": 43,
"sweep_replacements": 230,
"entities_found": [
{
"original": "23113695",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23113695",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23113695",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23113695",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23113695",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23113695",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23113695",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23113695",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23113695",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23113695",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23113695",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23113695",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23113695",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23113695",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23113695",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23113695",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23113695",
"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": "CHIRURGIE UROLOGIE - CHIRURGIE UROLOGIE\nDossier Patient\nDétails des patients",
"replacement": "[PATIENT_2]",
"source": "regex",
"category": "patient"
},
{
"original": "MAISON XORTAENIA 135 chemin d'oxobia Ville de résidence: IRISSARRY",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "CURUTCHET",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9703191518783569
},
{
"original": "Juliette Glyc",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9721087217330933
},
{
"original": "Juliette Glyc",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9948718547821045
},
{
"original": "Juliette Glyc",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9950029253959656
},
{
"original": "Juliette Glyc",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.8224825263023376
},
{
"original": "Jean Signé",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9471039175987244
},
{
"original": "Jean Signé",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9933045506477356
},
{
"original": "Jean S",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.8872615098953247
},
{
"original": "Jean Signé",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.8709748387336731
},
{
"original": "Jean S",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9963275194168091
},
{
"original": "Jean Signé",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9469223022460938
},
{
"original": "Jean S",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9929468631744385
},
{
"original": "MASCLE Laurent",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9342138767242432
},
{
"original": "Juliette Glyc",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9902276396751404
},
{
"original": "Juliette Glyc",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9925429821014404
},
{
"original": "Juliette Glyc",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9953696131706238
},
{
"original": "Juliette Glyc",
"replacement": "[MEDECIN_3]",
"source": "ner",
"score": 0.9943369626998901
},
{
"original": "Aurélie PATIENT",
"replacement": "[PATIENT_2]",
"source": "ner",
"score": 0.884096622467041
},
{
"original": "Jean Signé",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9721887707710266
},
{
"original": "Jean Signé",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9903861880302429
},
{
"original": "MATERNOWSKI Paul Jean",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.992494523525238
},
{
"original": "Jean Signé",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9322002530097961
},
{
"original": "Jean",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.8930354714393616
},
{
"original": "Jean Signé",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9921853542327881
},
{
"original": "Aurélie Signé",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.8494909405708313
},
{
"original": "Aurélie",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9203699827194214
},
{
"original": "Aurélie Signé",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9248508810997009
},
{
"original": "Aurélie",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.8167300820350647
},
{
"original": "Aurélie S",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9146349430084229
},
{
"original": "Aurélie Signé",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.9372491836547852
},
{
"original": "Aurélie Signé",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.8139567971229553
},
{
"original": "Aurélie",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.8845905065536499
},
{
"original": "Aurélie",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.8810440301895142
},
{
"original": "Aurélie S",
"replacement": "[SOIGNANT_17]",
"source": "ner",
"score": 0.8536562323570251
},
{
"original": "Clément KLEIN",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9971322417259216
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_18]",
"source": "ner",
"score": 0.9976404905319214
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_18]",
"source": "ner",
"score": 0.9919688701629639
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_18]",
"source": "ner",
"score": 0.9947693943977356
},
{
"original": "Marion PUJOS",
"replacement": "[SOIGNANT_18]",
"source": "ner",
"score": 0.9943573474884033
},
{
"original": "LM",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9922340512275696
},
{
"original": "LM",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9800857305526733
},
{
"original": "LM",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8362404108047485
},
{
"original": "LM",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9002178311347961
}
]
}