Andrey Epifancev 5dcfaf8fdd feat(ocr): эталоны нормализатора — предупреждения о пропущенных строках, формулировка ИНН (Срез 3a, #12)
aep_3 и aep_6: предупреждения «строк с нечисловым кодом пропущено: N» и «строк без кода с суммами пропущено: N» на таблицу;
aep_3: «ИНН распознан неуверенно» вместо «ИНН не распознан» (ИНН извлечён, confidence < 100). Документы (строки, суммы,
колонки) не изменились. В README — строка про ocr/expected_normalize/.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012vJkmBGKKqMoEMzvsXG3y2
2026-10-07 03:35:25 +04:00

1055 lines
32 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"documents": [
{
"columns": [
{
"column_index": 0,
"label": ""
},
{
"column_index": 1,
"label": ""
},
{
"column_index": 2,
"label": ""
}
],
"document_type": "BALANCE",
"header": {
"form_name": "Бухгалтерский баланс",
"inn": "3121200351",
"inn_confidence": 61.538464,
"organization_name": "><> ***** : во #У # ***ни > > 463 ■ из : <.... 20 1111Ы111 и \" - * * • 3' >> и 1 #:' ЗАК РЫТОВ АКЦИОНЕРНОЕ ОБЩЕСТВО Р'!А?Л:ЕЖ?С?Е|Е?В?С? ■ ... : ! : : - : - * : : ‘ : .... В : Россолькоставальнымажной • » ; о... ?.......- А.... .л глина ' ****** •. . **************************************** декамоддр». кообись пуждрматически пониках бирезовите 51828996ъ сум***********•******************************************* ЕВЦПУЮ * 245 61 - ,, {КИИ} И.ОЛ ОЧНОКО НСЕРВНЫЙ КОМВИНАТ\" ; ...предли 11»-1<1|1ч« 1114-4 •<««•< нам... бес * ******************************************************************* «ОР.РОЯ эластивентелиза зе раетьмы молоска.пача**************************************** 1Ш-Х I I 1 1 I ! I I I I 1 1 1 1 1 1 1 и 1 1 1 :€ и I I • ; 1 1 1 ; ; I I I х I. Л | | 4 1 = ’ 1- -1 » , ; (наименование органи ИИНН1 .",
"organization_name_confidence": 37.294117,
"report_date": "2024-12-31",
"report_date_text": "2|0|2|4|",
"units": "тыс. руб. год по ОКЕИ 13184"
},
"lines": [
{
"line_code": "1120",
"line_code_confidence": 50.0,
"line_name": "Результаты исследований и разработок",
"line_name_confidence": 50.0,
"values": [
{
"column_index": 0,
"confidence": 0.0,
"is_recognized": false,
"string_value": ":"
},
{
"column_index": 1,
"confidence": 0.0,
"is_recognized": false
},
{
"column_index": 2,
"confidence": 0.0,
"is_recognized": false,
"string_value": ":"
}
]
},
{
"line_code": "1150",
"line_code_confidence": 25.0,
"line_name": "Основные средства",
"line_name_confidence": 25.0,
"values": [
{
"amount": "2875532",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "2696440",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "2717959",
"column_index": 2,
"confidence": 42.857143,
"is_recognized": false
}
]
},
{
"line_code": "1160",
"line_code_confidence": 50.0,
"line_name": "Инвестиционная недвижимость",
"line_name_confidence": 50.0,
"values": [
{
"column_index": 0,
"confidence": 14.285715,
"is_recognized": false,
"string_value": "' : ’ :"
},
{
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"column_index": 2,
"confidence": 0.0,
"is_recognized": false,
"string_value": "+"
}
]
},
{
"line_code": "1170",
"line_code_confidence": 100.0,
"line_name": "Финансовые вложения",
"line_name_confidence": 100.0,
"values": [
{
"column_index": 0,
"confidence": 0.0,
"is_recognized": false,
"string_value": ":"
},
{
"amount": "200",
"column_index": 1,
"confidence": 80.0,
"is_recognized": false
},
{
"amount": "200",
"column_index": 2,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "1180",
"line_code_confidence": 100.0,
"line_name": "Отложенные налоговые активы",
"line_name_confidence": 100.0,
"values": [
{
"amount": "1",
"column_index": 0,
"confidence": 0.0,
"is_recognized": false
},
{
"amount": "28957",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "18121",
"column_index": 2,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "1210",
"line_code_confidence": 100.0,
"line_name": "Запасы",
"line_name_confidence": 100.0,
"values": [
{
"amount": "1108817",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "801643",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "720113",
"column_index": 2,
"confidence": 66.66667,
"is_recognized": false
}
]
},
{
"line_code": "1240",
"line_code_confidence": 50.0,
"line_name": "Финансовые вложения (за исключением денежных эквивалентов)",
"line_name_confidence": 50.0,
"values": [
{
"amount": "183600",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "192077",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "987440",
"column_index": 2,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "1250",
"line_code_confidence": 100.0,
"line_name": "Денежные средства и денежные эквиваленты",
"line_name_confidence": 100.0,
"values": [
{
"amount": "4447",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "538696",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "239614",
"column_index": 2,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "1260",
"line_code_confidence": 100.0,
"line_name": "Прочие оборотные активы",
"line_name_confidence": 100.0,
"values": [
{
"amount": "30524",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "10989",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "8753",
"column_index": 2,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "1200",
"line_code_confidence": 100.0,
"line_name": "Итого по разделу II",
"line_name_confidence": 100.0,
"values": [
{
"amount": "2618567",
"column_index": 0,
"confidence": 71.42857,
"is_recognized": false
},
{
"amount": "2684969",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "3179205",
"column_index": 2,
"confidence": 57.14286,
"is_recognized": false
}
]
},
{
"line_code": "1320",
"line_code_confidence": 50.0,
"line_name": "Собственные акции, выкупленные у акционеров",
"line_name_confidence": 50.0,
"values": [
{
"column_index": 0,
"confidence": 66.66667,
"is_recognized": false,
"string_value": "I"
},
{
"column_index": 1,
"confidence": 57.14286,
"is_recognized": false,
"string_value": "(-) + {"
},
{
"column_index": 2,
"confidence": 66.66667,
"is_recognized": false,
"string_value": "(-)"
}
]
},
{
"line_code": "1340",
"line_code_confidence": 50.0,
"line_name": "Переоценка внеоборотных активов",
"line_name_confidence": 50.0,
"values": [
{
"amount": "146927",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "122477",
"column_index": 1,
"confidence": 70.0,
"is_recognized": false
},
{
"amount": "121946",
"column_index": 2,
"confidence": 68.75,
"is_recognized": false
}
]
},
{
"line_code": "1350",
"line_code_confidence": 100.0,
"line_name": "Добавочный капитал (без переоценки)",
"line_name_confidence": 100.0,
"values": [
{
"amount": "24",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "24",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "24",
"column_index": 2,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "1360",
"line_code_confidence": 50.0,
"line_name": "Резервный капитал",
"line_name_confidence": 50.0,
"values": [
{
"amount": "2416",
"column_index": 0,
"confidence": 25.0,
"is_recognized": false
},
{
"amount": "2416",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "2416",
"column_index": 2,
"confidence": 25.0,
"is_recognized": false
}
]
},
{
"line_code": "1370",
"line_code_confidence": 50.0,
"line_name": "Нераспределенная прибыль (непокрытый убыток)",
"line_name_confidence": 50.0,
"values": [
{
"amount": "3248875",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "2856983",
"column_index": 1,
"confidence": 73.333336,
"is_recognized": false
},
{
"amount": "2288967",
"column_index": 2,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "1300",
"line_code_confidence": 50.0,
"line_name": "Итого по разделу III",
"line_name_confidence": 50.0,
"values": [
{
"amount": "3446569",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "3030227",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "2401680",
"column_index": 2,
"confidence": 71.42857,
"is_recognized": false
}
]
},
{
"line_code": "1310",
"line_code_confidence": 100.0,
"line_name": "Уставный капитал",
"line_name_confidence": 100.0,
"values": [
{
"amount": "1",
"column_index": 0,
"confidence": 33.333336,
"is_recognized": false
},
{
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"column_index": 2,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "1410",
"line_code_confidence": 100.0,
"line_name": "Заемные средства",
"line_name_confidence": 100.0,
"values": [
{
"amount": "628256",
"column_index": 0,
"confidence": 87.5,
"is_recognized": false
},
{
"amount": "1561454",
"column_index": 1,
"confidence": 42.857143,
"is_recognized": false
},
{
"amount": "1938454",
"column_index": 2,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "420",
"line_code_confidence": 99.0,
"line_name": "Отложенные налоговые обязательства",
"line_name_confidence": 100.0,
"values": [
{
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "43094",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "30700",
"column_index": 2,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "1430",
"line_code_confidence": 50.0,
"line_name": "Оценочные обязательства",
"line_name_confidence": 50.0,
"values": [
{
"column_index": 0,
"confidence": 100.0,
"is_recognized": true,
"string_value": "."
},
{
"column_index": 1,
"confidence": 20.0,
"is_recognized": false,
"string_value": "! : г ’ ."
},
{
"column_index": 2,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "1450",
"line_code_confidence": 50.0,
"line_name": "Прочие обязательства",
"line_name_confidence": 50.0,
"values": [
{
"column_index": 0,
"confidence": 33.333336,
"is_recognized": false,
"string_value": "# -"
},
{
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"column_index": 2,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "1400",
"line_code_confidence": 50.0,
"line_name": "Итого по разделу IV",
"line_name_confidence": 50.0,
"values": [
{
"amount": "67135",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "1592154",
"column_index": 1,
"confidence": 71.42857,
"is_recognized": false
},
{
"amount": "1953529",
"column_index": 2,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "1510",
"line_code_confidence": 100.0,
"line_name": "Заемные средства",
"line_name_confidence": 100.0,
"values": [
{
"amount": "570663",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "198822",
"column_index": 1,
"confidence": 66.66667,
"is_recognized": false
},
{
"amount": "641960",
"column_index": 2,
"confidence": 66.66667,
"is_recognized": false
}
]
},
{
"line_code": "1520",
"line_code_confidence": 100.0,
"line_name": "Кредиторская задолженность",
"line_name_confidence": 100.0,
"values": [
{
"amount": "817769",
"column_index": 0,
"confidence": 66.66667,
"is_recognized": false
},
{
"amount": "536304",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "828554",
"column_index": 2,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "1530",
"line_code_confidence": 50.0,
"line_name": "Доходы будущих периодов",
"line_name_confidence": 50.0,
"values": [
{
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"column_index": 2,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "1540",
"line_code_confidence": 50.0,
"line_name": "Оценочные обязательства",
"line_name_confidence": 50.0,
"values": [
{
"amount": "47001",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"column_index": 1,
"confidence": 0.0,
"is_recognized": false,
"string_value": "<"
},
{
"amount": "42192",
"column_index": 2,
"confidence": 40.0,
"is_recognized": false
}
]
},
{
"line_code": "1550",
"line_code_confidence": 50.0,
"line_name": "Прочие обязательства",
"line_name_confidence": 50.0,
"values": [
{
"amount": "31",
"column_index": 0,
"confidence": 0.0,
"is_recognized": false
},
{
"amount": "31",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "29",
"column_index": 2,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "1700",
"line_code_confidence": 100.0,
"line_name": "БАЛАНС",
"line_name_confidence": 100.0,
"values": [
{
"amount": "1",
"column_index": 0,
"confidence": 0.0,
"is_recognized": false
},
{
"amount": "5399730",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "5920582",
"column_index": 2,
"confidence": 85.71429,
"is_recognized": false
}
]
}
],
"locator": "file:3f1c2b7a-0000-4000-8000-000000000001.json;table:0"
},
{
"columns": [
{
"column_index": 0,
"label": ""
},
{
"column_index": 1,
"label": ""
}
],
"document_type": "INCOME",
"header": {
"form_name": "Отчет о финансовых результатах",
"inn": "3121200351",
"inn_confidence": 61.538464,
"organization_name": "><> ***** : во #У # ***ни > > 463 ■ из : <.... 20 1111Ы111 и \" - * * • 3' >> и 1 #:' ЗАК РЫТОВ АКЦИОНЕРНОЕ ОБЩЕСТВО Р'!А?Л:ЕЖ?С?Е|Е?В?С? ■ ... : ! : : - : - * : : ‘ : .... В : Россолькоставальнымажной • » ; о... ?.......- А.... .л глина ' ****** •. . **************************************** декамоддр». кообись пуждрматически пониках бирезовите 51828996ъ сум***********•******************************************* ЕВЦПУЮ * 245 61 - ,, {КИИ} И.ОЛ ОЧНОКО НСЕРВНЫЙ КОМВИНАТ\" ; ...предли 11»-1<1|1ч« 1114-4 •<««•< нам... бес * ******************************************************************* «ОР.РОЯ эластивентелиза зе раетьмы молоска.пача**************************************** 1Ш-Х I I 1 1 I ! I I I I 1 1 1 1 1 1 1 и 1 1 1 :€ и I I • ; 1 1 1 ; ; I I I х I. Л | | 4 1 = ’ 1- -1 » , ; (наименование органи ИИНН1 .",
"organization_name_confidence": 37.294117,
"report_date": "2024-12-31",
"report_date_text": "2|0|2|4|",
"units": "тыс. руб. год по ОКЕИ 13184"
},
"lines": [
{
"line_code": "2120",
"line_code_confidence": 100.0,
"line_name": "Себестоимость продаж",
"line_name_confidence": 100.0,
"values": [
{
"amount": "7744536",
"column_index": 0,
"confidence": 88.88889,
"is_recognized": false
},
{
"amount": "-6032409",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "2210",
"line_code_confidence": 100.0,
"line_name": "Коммерческие расходы",
"line_name_confidence": 100.0,
"values": [
{
"amount": "-693052",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "-546441",
"column_index": 1,
"confidence": 62.5,
"is_recognized": false
}
]
},
{
"line_code": "2220",
"line_code_confidence": 100.0,
"line_name": "Управленческие расходы",
"line_name_confidence": 100.0,
"values": [
{
"amount": "-278598",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "-872980",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "2200",
"line_code_confidence": 100.0,
"line_name": "Прибыль (убыток) от продаж",
"line_name_confidence": 100.0,
"values": [
{
"amount": "532514",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "644908",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "2320",
"line_code_confidence": 100.0,
"line_name": "Проценты к получению",
"line_name_confidence": 100.0,
"values": [
{
"amount": "9825",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "34466",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "2330",
"line_code_confidence": 100.0,
"line_name": "Проценты к уплате",
"line_name_confidence": 100.0,
"values": [
{
"amount": "38378",
"column_index": 0,
"confidence": 71.42857,
"is_recognized": false
},
{
"amount": "-47771",
"column_index": 1,
"confidence": 85.71429,
"is_recognized": false
}
]
},
{
"line_code": "2340",
"line_code_confidence": 100.0,
"line_name": "Прочие доходы",
"line_name_confidence": 100.0,
"values": [
{
"amount": "22266",
"column_index": 0,
"confidence": 80.0,
"is_recognized": false
},
{
"amount": "420962",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "2350",
"line_code_confidence": 100.0,
"line_name": "Прочие расходы",
"line_name_confidence": 100.0,
"values": [
{
"amount": "-241654",
"column_index": 0,
"confidence": 75.0,
"is_recognized": false
},
{
"amount": "-339029",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "2300",
"line_code_confidence": 100.0,
"line_name": "Прибыль (убыток) до налогообложения",
"line_name_confidence": 100.0,
"values": [
{
"amount": "500028",
"column_index": 0,
"confidence": 100.0,
"is_recognized": true
},
{
"amount": "713536",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "2410",
"line_code_confidence": 50.0,
"line_name": "Налог на прибыль",
"line_name_confidence": 50.0,
"values": [
{
"amount": "-108450",
"column_index": 0,
"confidence": 87.5,
"is_recognized": false
},
{
"amount": "-148179",
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "2460",
"line_code_confidence": 100.0,
"line_name": "Прочее",
"line_name_confidence": 100.0,
"values": [
{
"column_index": 0,
"confidence": 23.529411,
"is_recognized": false,
"string_value": "в ом нашкаманы. -"
},
{
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "2900",
"line_code_confidence": 100.0,
"line_name": "Базовая прибыль (убыток) на акцию",
"line_name_confidence": 100.0,
"values": [
{
"column_index": 0,
"confidence": 57.14286,
"is_recognized": false,
"string_value": "..... ."
},
{
"column_index": 1,
"confidence": 100.0,
"is_recognized": true
}
]
},
{
"line_code": "2930",
"line_code_confidence": 99.0,
"line_name": "Разводненная прибыль (убыток) на акцию",
"line_name_confidence": 100.0,
"values": [
{
"column_index": 0,
"confidence": 28.57143,
"is_recognized": false,
"string_value": ", - : :"
},
{
"column_index": 1,
"confidence": 0.0,
"is_recognized": false,
"string_value": "*"
}
]
}
],
"locator": "file:3f1c2b7a-0000-4000-8000-000000000001.json;table:1"
}
],
"error": null,
"metrics": {
"rows": 41
},
"status": "needs_check",
"warnings": [
"3f1c2b7a-0000-4000-8000-000000000001.json: ИНН распознан неуверенно",
"3f1c2b7a-0000-4000-8000-000000000001.json: table:0: шапка синтезирована: колонки без дат",
"3f1c2b7a-0000-4000-8000-000000000001.json: table:0: строк с нечисловым кодом пропущено: 8",
"3f1c2b7a-0000-4000-8000-000000000001.json: table:0: строк без кода с суммами пропущено: 2",
"3f1c2b7a-0000-4000-8000-000000000001.json: table:0: код 1320 повторяется: оставлена первая строка",
"3f1c2b7a-0000-4000-8000-000000000001.json: table:0: код 1350 повторяется: оставлена первая строка",
"3f1c2b7a-0000-4000-8000-000000000001.json: table:0: код 1360 повторяется: оставлена первая строка",
"3f1c2b7a-0000-4000-8000-000000000001.json: table:0: код 1370 повторяется: оставлена первая строка",
"3f1c2b7a-0000-4000-8000-000000000001.json: table:1: шапка синтезирована: колонки без дат",
"3f1c2b7a-0000-4000-8000-000000000001.json: table:1: строк с нечисловым кодом пропущено: 2",
"3f1c2b7a-0000-4000-8000-000000000001.json: table:1: строк без кода с суммами пропущено: 2",
"3f1c2b7a-0000-4000-8000-000000000001_ofr.json: INVALID_DOCUMENT: Не удалось определить тип документа."
]
}