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 23119008.pdf",
"total_replacements": 174,
"regex_replacements": 159,
"ner_replacements": 7,
"sweep_replacements": 8,
"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": "KWIKPEN Junior",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9720983505249023
},
{
"original": "KWIKPEN Junior",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9831259250640869
},
{
"original": "REVENEAU Serge",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9700112342834473
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9496606588363647
},
{
"original": "KWIKPEN Junior",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9851958751678467
},
{
"original": "KWIKPEN Junior",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9858477711677551
},
{
"original": "REVENEAU Serge",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9697928428649902
}
]
}

View File

@@ -0,0 +1,561 @@
{
"source_file": "trackare-12020723-23119008_12020723_23119008.pdf",
"total_replacements": 356,
"regex_replacements": 167,
"ner_replacements": 58,
"sweep_replacements": 131,
"entities_found": [
{
"original": "12020723",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12020723",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12020723",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12020723",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12020723",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12020723",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12020723",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12020723",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12020723",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12020723",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12020723",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12020723",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12020723",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12020723",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "12020723",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23119008",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119008",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119008",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119008",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119008",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119008",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119008",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119008",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119008",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119008",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119008",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119008",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119008",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119008",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23119008",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "VALENCIENNES",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "Concubine Rothe Coline FRANCE",
"replacement": "[CONTACT_1]",
"source": "regex",
"category": "contact"
},
{
"original": "7 IMPASSE POYDENOT Ville de résidence: BAYONNE",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "BURTIN BURTIN",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9971469044685364
},
{
"original": "MAJCHRZAK Camille",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9907227158546448
},
{
"original": "KWIKPEN Junior",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9251273274421692
},
{
"original": "MAJCHRZAK Camille",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9927493929862976
},
{
"original": "KWIKPEN Junior",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9497787356376648
},
{
"original": "MAJCHRZAK Camille",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9916108250617981
},
{
"original": "KWIKPEN Junior",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9434484839439392
},
{
"original": "BARGAIN Beatrice",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.8086560964584351
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9920848608016968
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9931483864784241
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9908513426780701
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9974392652511597
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9953908324241638
},
{
"original": "MAURY Elisa",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9789789319038391
},
{
"original": "MAJCHRZAK Camille GELULE",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9430648684501648
},
{
"original": "MAJCHRZAK Camille GELULE",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9988347291946411
},
{
"original": "Marie ORALE",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9395096898078918
},
{
"original": "MAJCHRZAK Camille GELULE",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9985052347183228
},
{
"original": "MAJCHRZAK Camille",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9644875526428223
},
{
"original": "KWIKPEN Junior",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9071839451789856
},
{
"original": "MAJCHRZAK Camille",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9937517046928406
},
{
"original": "KWIKPEN Junior",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9771153926849365
},
{
"original": "MAJCHRZAK Camille",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9878664612770081
},
{
"original": "KWIKPEN Junior",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9758450984954834
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9980661869049072
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9971195459365845
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9980360269546509
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9970771074295044
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9976925849914551
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9974943399429321
},
{
"original": "MAURY Elisa",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9479776620864868
},
{
"original": "TRESIBA FLESTOUCH",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9273208379745483
},
{
"original": "Marie ORALE",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9979271292686462
},
{
"original": "MAJCHRZAK Camille GELULE",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9983386993408203
},
{
"original": "Marie ORALE",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9972643852233887
},
{
"original": "MAJCHRZAK Camille GELULE",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9980244636535645
},
{
"original": "Marie ORALE",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9844522476196289
},
{
"original": "MG MAJCHRZAK Camille GELULE",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.953220784664154
},
{
"original": "Marie ORALE",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9838399887084961
},
{
"original": "MG MAJCHRZAK Camille GELULE",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9464771747589111
},
{
"original": "Beatrice",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9207473397254944
},
{
"original": "Beatrice",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.8554028868675232
},
{
"original": "Beatrice",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.8272924423217773
},
{
"original": "Beatrice",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.872344970703125
},
{
"original": "Beatrice",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.904251217842102
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.991797149181366
},
{
"original": "Camille Marie",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9109447002410889
},
{
"original": "Camille Marie",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9554448127746582
},
{
"original": "MAURY",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.8434082865715027
},
{
"original": "MAJCHRZAK LANSOPRAZOLE",
"replacement": "[SOIGNANT_6]",
"source": "ner",
"score": 0.9668657779693604
},
{
"original": "Camille Marie",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.894985556602478
},
{
"original": "Maider",
"replacement": "[MEDECIN_10]",
"source": "ner",
"score": 0.8683978915214539
},
{
"original": "Marie MAILHOS",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9605945348739624
},
{
"original": "Mathieu B",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.9610006213188171
},
{
"original": "Camille Marie",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9643537402153015
},
{
"original": "Marie Pierre",
"replacement": "[MEDECIN_6]",
"source": "ner",
"score": 0.9622669219970703
},
{
"original": "Camille Marie",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9591531753540039
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_4]",
"source": "ner",
"score": 0.8403472900390625
}
]
}