chineseclass/Raw/Xiezuo/OCR/写作Chapter5.json
StillHammer 4ebc31dd5f Initial commit - Chinese learning project setup
Complete course materials, notes, and learning tools for Jiaotong Daxue intensive Chinese program.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-10-27 15:56:36 +08:00

519 lines
9.8 KiB
JSON
Raw Permalink 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.

{
"source_pdf": "Raw/Xiezuo/PDF/写作Chapter5.pdf",
"processed_at": "2025-10-13T19:52:31.440591",
"ai_correction_enabled": true,
"pages": [
{
"page": 1,
"text": "在哪儿:\n2.把关键词归类。\n\n为什么\n\n怎么做\n谁\n国\n做什么\n怎么样",
"text_corrected": "在哪儿:\n2.把关键词归类。\n\n为什么\n\n怎么做\n谁\n国家\n做什么\n怎么样",
"details": [
{
"text": "在哪儿:",
"confidence": 0.9176860451698303,
"bbox": [
[
1135,
1876
],
[
1337,
1881
],
[
1335,
1954
],
[
1133,
1949
]
]
},
{
"text": "2.把关键词归类。",
"confidence": 0.9921038746833801,
"bbox": [
[
203,
1949
],
[
657,
1954
],
[
656,
2018
],
[
203,
2014
]
]
},
{
"text": "",
"confidence": 0.0,
"bbox": [
[
1936,
2139
],
[
2466,
2316
],
[
2262,
2931
],
[
1732,
2755
]
]
},
{
"text": "为什么:",
"confidence": 0.9706306457519531,
"bbox": [
[
309,
2191
],
[
510,
2195
],
[
509,
2271
],
[
308,
2267
]
]
},
{
"text": "",
"confidence": 0.0,
"bbox": [
[
901,
2295
],
[
1135,
2403
],
[
1031,
2631
],
[
797,
2524
]
]
},
{
"text": "怎么做:",
"confidence": 0.978158712387085,
"bbox": [
[
1431,
2354
],
[
1637,
2354
],
[
1637,
2429
],
[
1431,
2429
]
]
},
{
"text": "谁:",
"confidence": 0.9779330492019653,
"bbox": [
[
555,
2713
],
[
657,
2713
],
[
657,
2792
],
[
555,
2792
]
]
},
{
"text": "国",
"confidence": 0.13306954503059387,
"bbox": [
[
1714,
2865
],
[
2263,
2865
],
[
2263,
3403
],
[
1714,
3403
]
]
},
{
"text": "做什么:",
"confidence": 0.979296088218689,
"bbox": [
[
1329,
2957
],
[
1533,
2955
],
[
1534,
3029
],
[
1330,
3032
]
]
},
{
"text": "怎么样:",
"confidence": 0.9686256647109985,
"bbox": [
[
408,
3174
],
[
610,
3174
],
[
610,
3242
],
[
408,
3242
]
]
}
]
},
{
"page": 2,
"text": "32",
"text_corrected": "Il n'y a pas de texte à corriger. Veuillez fournir le texte de la page 2 du manuel de chinois pour que je puisse corriger les erreurs OCR.",
"details": [
{
"text": "32",
"confidence": 0.9998297691345215,
"bbox": [
[
1222,
3314
],
[
1284,
3314
],
[
1284,
3366
],
[
1222,
3366
]
]
}
]
},
{
"page": 3,
"text": "1\n在哪儿\n2.把关键词归类。\n\n为什么\n怎么做\n谁\n做什么\n怎么样\n33",
"text_corrected": "1 \n在哪儿 \n2.把关键词归类。 \n\n为什么 \n怎么做 \n谁 \n做什么 \n怎么样 \n33 ",
"details": [
{
"text": "1",
"confidence": 0.08752845972776413,
"bbox": [
[
1821,
1634
],
[
2466,
1662
],
[
2444,
2189
],
[
1798,
2161
]
]
},
{
"text": "在哪儿:",
"confidence": 0.8921666145324707,
"bbox": [
[
1128,
1744
],
[
1333,
1751
],
[
1331,
1822
],
[
1126,
1816
]
]
},
{
"text": "2.把关键词归类。",
"confidence": 0.9963535666465759,
"bbox": [
[
218,
1842
],
[
658,
1842
],
[
658,
1906
],
[
218,
1906
]
]
},
{
"text": "",
"confidence": 0.0,
"bbox": [
[
1906,
1865
],
[
2480,
2079
],
[
2229,
3196
],
[
1554,
2983
]
]
},
{
"text": "为什么:",
"confidence": 0.96550053358078,
"bbox": [
[
302,
1976
],
[
503,
1978
],
[
502,
2050
],
[
301,
2048
]
]
},
{
"text": "怎么做:",
"confidence": 0.9728918075561523,
"bbox": [
[
1423,
2153
],
[
1628,
2153
],
[
1628,
2231
],
[
1423,
2231
]
]
},
{
"text": "谁:",
"confidence": 0.9834979176521301,
"bbox": [
[
573,
2362
],
[
674,
2362
],
[
674,
2441
],
[
573,
2441
]
]
},
{
"text": "做什么:",
"confidence": 0.9812941551208496,
"bbox": [
[
1326,
2566
],
[
1528,
2562
],
[
1530,
2633
],
[
1327,
2636
]
]
},
{
"text": "怎么样:",
"confidence": 0.9264674186706543,
"bbox": [
[
378,
2752
],
[
588,
2747
],
[
590,
2826
],
[
380,
2831
]
]
},
{
"text": "33",
"confidence": 0.9998812675476074,
"bbox": [
[
1158,
3368
],
[
1220,
3364
],
[
1224,
3414
],
[
1162,
3419
]
]
}
]
},
{
"page": 4,
"text": "34",
"text_corrected": "Il n'y a pas de texte à corriger. Veuillez fournir le texte de la page 4 du manuel de chinois pour que je puisse effectuer les corrections nécessaires.",
"details": [
{
"text": "34",
"confidence": 0.9998695254325867,
"bbox": [
[
1228,
3307
],
[
1290,
3307
],
[
1290,
3358
],
[
1228,
3358
]
]
}
]
}
]
}