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 +1,27 @@
{
"source_file": "CRO 23108560.pdf",
"total_replacements": 10,
"regex_replacements": 7,
"ner_replacements": 3,
"sweep_replacements": 0,
"entities_found": [
{
"original": "Dufour",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9145491123199463
},
{
"original": "ALAIN",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.9586260318756104
},
{
"original": "DUCASSOU",
"replacement": "[ADRESSE_1]",
"source": "ner",
"score": 0.9851601719856262
}
]
}

View File

@@ -0,0 +1,21 @@
{
"source_file": "LETTRE DE SORTIE 23108560.pdf",
"total_replacements": 10,
"regex_replacements": 7,
"ner_replacements": 2,
"sweep_replacements": 1,
"entities_found": [
{
"original": "ALAIN",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.962059736251831
},
{
"original": "DUCASSOU",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9934127330780029
}
]
}

View File

@@ -0,0 +1,8 @@
{
"source_file": "anapath 171_23108560.pdf",
"total_replacements": 0,
"regex_replacements": 0,
"ner_replacements": 0,
"sweep_replacements": 0,
"entities_found": []
}

View File

@@ -0,0 +1,315 @@
{
"source_file": "trackare-98200358-23108560_98200358_23108560.pdf",
"total_replacements": 272,
"regex_replacements": 161,
"ner_replacements": 19,
"sweep_replacements": 92,
"entities_found": [
{
"original": "98200358",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98200358",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98200358",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98200358",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98200358",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98200358",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98200358",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98200358",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98200358",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98200358",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98200358",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98200358",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98200358",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "98200358",
"replacement": "[IPP_1]",
"source": "regex",
"category": "ipp"
},
{
"original": "23108560",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23108560",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23108560",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23108560",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23108560",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23108560",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23108560",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23108560",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23108560",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23108560",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23108560",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23108560",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23108560",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "23108560",
"replacement": "[EPISODE_1]",
"source": "regex",
"category": "episode"
},
{
"original": "640000162",
"replacement": "[FINESS]",
"source": "regex",
"category": "finess"
},
{
"original": "MOUGUERRE",
"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": "JAUBERRIA",
"replacement": "[ADRESSE_1]",
"source": "regex",
"category": "adresse"
},
{
"original": "HENRIOT Jeremy",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9871063232421875
},
{
"original": "David MALABAT",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9930360317230225
},
{
"original": "David MALABAT",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.995150625705719
},
{
"original": "David MALABAT",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9934267401695251
},
{
"original": "HENRIOT Jeremy",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9939147233963013
},
{
"original": "HENRIOT Jeremy Signé",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.8687640428543091
},
{
"original": "HENRIOT Jeremy",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9960166811943054
},
{
"original": "David MALABAT",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9963513612747192
},
{
"original": "David MALABAT",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9972975254058838
},
{
"original": "David MALABAT",
"replacement": "[SOIGNANT_14]",
"source": "ner",
"score": 0.9964207410812378
},
{
"original": "HENRIOT Jeremy",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9937800168991089
},
{
"original": "HENRIOT Jeremy",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9900762438774109
},
{
"original": "HENRIOT Jeremy",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9932613372802734
},
{
"original": "HENRIOT Jeremy",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9931471943855286
},
{
"original": "HENRIOT",
"replacement": "[SOIGNANT_9]",
"source": "ner",
"score": 0.9953426718711853
},
{
"original": "Léo SCHURDI-LEVRAUD",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9979493618011475
},
{
"original": "LEVRAUD",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.8535398840904236
},
{
"original": "Léo SCHURDI",
"replacement": "[PERSONNE_1]",
"source": "ner",
"score": 0.9940086603164673
},
{
"original": "Ducassou Suzy",
"replacement": "[PATIENT_1]",
"source": "ner",
"score": 0.9730498790740967
}
]
}