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 +1,81 @@
{
"source_file": "CRH 23099448.pdf",
"total_replacements": 398,
"regex_replacements": 364,
"ner_replacements": 9,
"sweep_replacements": 25,
"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": "J. LOEB",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9114052653312683
},
{
"original": "GIMENEZ Taoh",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9943520426750183
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9114052653312683
},
{
"original": "GIMENEZ Taoh",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9935986399650574
},
{
"original": "COUECOU",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9939371347427368
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9114052653312683
},
{
"original": "GIMENEZ Taoh",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9935986399650574
},
{
"original": "GIMENEZ TAOH",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9970524907112122
},
{
"original": "COUECOU",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9950222969055176
}
]
}

View File

@@ -0,0 +1,417 @@
{
"source_file": "trackare-23002370-23099448_23002370_23099448.pdf",
"total_replacements": 267,
"regex_replacements": 147,
"ner_replacements": 37,
"sweep_replacements": 83,
"entities_found": [
{
"original": "23002370",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23002370",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23002370",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23002370",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23002370",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23002370",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23002370",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23002370",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23002370",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23002370",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23002370",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23002370",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23002370",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23002370",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23099448",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23099448",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23099448",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23099448",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23099448",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23099448",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23099448",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23099448",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23099448",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23099448",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23099448",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23099448",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23099448",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23099448",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "DAX",
"replacement": "[LIEU_NAISS_1]",
"source": "regex",
"category": "lieu_naissance"
},
{
"original": "1 ALLEE DES OYATS Ville de résidence: VIEUX BOUCAU LES BAINS",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "T BRAYER Céline",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.9657481908798218
},
{
"original": "T BRAYER Céline",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.9795312881469727
},
{
"original": "MAJCHRZAK Camille GELULE",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.8813554048538208
},
{
"original": "Marie ORALE",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9975466728210449
},
{
"original": "MAJCHRZAK Camille GELULE",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9963634610176086
},
{
"original": "Marie ORALE",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9971691966056824
},
{
"original": "MAJCHRZAK Camille GELULE",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9962520599365234
},
{
"original": "MAJCHRZAK Camille GELULE",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.8131133317947388
},
{
"original": "Laurence",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.8196704387664795
},
{
"original": "RITZ-QUILLACQ",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9964309334754944
},
{
"original": "BRAYER Céline",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.8904731273651123
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9210235476493835
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9924564957618713
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.987855851650238
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.992040753364563
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.987057089805603
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.992902398109436
},
{
"original": "GLYCEMIE CAPILLAIRE",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9880914688110352
},
{
"original": "Marie ORALE",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9928398132324219
},
{
"original": "AJCHRZAK Camille",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.8567579388618469
},
{
"original": "Marie ORALE",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.991990864276886
},
{
"original": "MAJCHRZAK Camille",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9952861070632935
},
{
"original": "MAJCHRZAK Camille GELULE",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.8733892440795898
},
{
"original": "MAJCHRZAK Camille",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9103072285652161
},
{
"original": "RITZ-QUILLACQ",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9966469407081604
},
{
"original": "RITZ-QUILLACQ S",
"replacement": "[MEDECIN_1]",
"source": "ner",
"score": 0.9293441772460938
},
{
"original": "BRAYER Céline",
"replacement": "[SOIGNANT_2]",
"source": "ner",
"score": 0.9022835493087769
},
{
"original": "MAJCHRZAK NASALE",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9244511127471924
},
{
"original": "BAQSIMI Camille RE",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.9172675013542175
},
{
"original": "GLUCAGON",
"replacement": "[PERSONNE_2]",
"source": "ner",
"score": 0.9842612743377686
},
{
"original": "Marie",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9378681778907776
},
{
"original": "Camille Marie MAJCHRZAK",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9711960554122925
},
{
"original": "MAJCHRZAK",
"replacement": "[SOIGNANT_7]",
"source": "ner",
"score": 0.8475980162620544
},
{
"original": "Camille Marie",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.8920328617095947
},
{
"original": "Camille Marie",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.8052644729614258
},
{
"original": "Camille Marie",
"replacement": "[MEDECIN_9]",
"source": "ner",
"score": 0.9479092955589294
},
{
"original": "J. LOEB",
"replacement": "[PERSONNE_3]",
"source": "ner",
"score": 0.8309068083763123
}
]
}