{"id":35158,"date":"2025-08-10T14:09:50","date_gmt":"2025-08-10T06:09:50","guid":{"rendered":"https:\/\/www.kdjingpai.com\/?p=35158"},"modified":"2025-08-26T15:37:55","modified_gmt":"2025-08-26T07:37:55","slug":"dotsocr","status":"publish","type":"post","link":"https:\/\/www.kdjingpai.com\/de\/dotsocr\/","title":{"rendered":"dots.ocr\uff1a\u591a\u8bed\u8a00\u6587\u6863\u5e03\u5c40\u89e3\u6790\u7684\u7edf\u4e00\u89c6\u89c9-\u8bed\u8a00\u6a21\u578b"},"content":{"rendered":"<p>dots.ocr \u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u591a\u8bed\u8a00\u6587\u6863\u89e3\u6790\u5de5\u5177\uff0c\u57fa\u4e8e 1.7B \u53c2\u6570\u7684\u89c6\u89c9-\u8bed\u8a00\u6a21\u578b\uff08VLM\uff09\uff0c\u80fd\u591f\u540c\u65f6\u8fdb\u884c\u5e03\u5c40\u68c0\u6d4b\u548c\u5185\u5bb9\u8bc6\u522b\u3002\u5b83\u5728 OmniDocBench \u7b49\u57fa\u51c6\u6d4b\u8bd5\u4e2d\u5c55\u73b0\u4e86\u6700\u5148\u8fdb\u7684\u6027\u80fd\uff0c\u7279\u522b\u662f\u5728\u6587\u672c\u3001\u8868\u683c\u548c\u9605\u8bfb\u987a\u5e8f\u89e3\u6790\u65b9\u9762\u8868\u73b0\u51fa\u8272\u3002dots.ocr \u652f\u6301\u591a\u79cd\u8bed\u8a00\uff0c\u5305\u62ec\u4f4e\u8d44\u6e90\u8bed\u8a00\uff0c\u9002\u5408\u5904\u7406\u590d\u6742\u6587\u6863\u5982\u5b66\u672f\u8bba\u6587\u3001\u8d22\u52a1\u62a5\u544a\u7b49\u3002\u76f8\u6bd4\u4f20\u7edf\u591a\u6a21\u578b\u6d41\u6c34\u7ebf\uff0cdots.ocr \u4f7f\u7528\u5355\u4e00\u6a21\u578b\u67b6\u6784\uff0c\u901a\u8fc7\u7b80\u5355\u66f4\u6539\u8f93\u5165\u63d0\u793a\u5373\u53ef\u5207\u6362\u4efb\u52a1\uff0c\u63a8\u7406\u901f\u5ea6\u5feb\u4e14\u6548\u7387\u9ad8\u3002\u7528\u6237\u53ef\u4ee5\u901a\u8fc7 GitHub \u4e0a\u7684\u5f00\u6e90\u4ee3\u7801\u548c\u63d0\u4f9b\u7684 Docker \u955c\u50cf\u5feb\u901f\u90e8\u7f72\u548c\u4f7f\u7528\u3002<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-35159\" src=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/08\/5728315b944a0b6-scaled.png\" alt=\"\" width=\"2560\" height=\"1486\" srcset=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/08\/5728315b944a0b6-scaled.png 2560w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/08\/5728315b944a0b6-1536x891.png 1536w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/08\/5728315b944a0b6-2048x1189.png 2048w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/08\/5728315b944a0b6-18x10.png 18w\" sizes=\"auto, (max-width: 2560px) 100vw, 2560px\" \/><\/p>\n<p>&nbsp;<\/p>\n<h2>\u529f\u80fd\u5217\u8868<\/h2>\n<ul>\n<li><strong>\u5e03\u5c40\u68c0\u6d4b<\/strong>\uff1a\u8bc6\u522b\u6587\u6863\u4e2d\u7684\u5143\u7d20\uff08\u5982\u6587\u672c\u3001\u8868\u683c\u3001\u516c\u5f0f\u3001\u56fe\u7247\u7b49\uff09\u5e76\u63d0\u4f9b\u7cbe\u786e\u7684\u8fb9\u754c\u6846\uff08bbox\uff09\u5750\u6807\u3002<\/li>\n<li><strong>\u5185\u5bb9\u8bc6\u522b<\/strong>\uff1a\u63d0\u53d6\u6587\u6863\u4e2d\u7684\u6587\u672c\u3001\u8868\u683c\uff08\u4ee5 HTML \u683c\u5f0f\u8f93\u51fa\uff09\u3001\u516c\u5f0f\uff08\u4ee5 LaTeX \u683c\u5f0f\u8f93\u51fa\uff09\u7b49\u5185\u5bb9\u3002<\/li>\n<li><strong>\u591a\u8bed\u8a00\u652f\u6301<\/strong>\uff1a\u652f\u6301 100 \u79cd\u8bed\u8a00\u7684\u6587\u6863\u89e3\u6790\uff0c\u7279\u522b\u5728\u4f4e\u8d44\u6e90\u8bed\u8a00\u4e0a\u8868\u73b0\u4f18\u5f02\u3002<\/li>\n<li><strong>\u9605\u8bfb\u987a\u5e8f\u4f18\u5316<\/strong>\uff1a\u6309\u7167\u4eba\u7c7b\u9605\u8bfb\u4e60\u60ef\u6392\u5e8f\u6587\u6863\u5143\u7d20\uff0c\u786e\u4fdd\u8f93\u51fa\u7684\u903b\u8f91\u6027\u3002<\/li>\n<li><strong>\u5feb\u901f\u63a8\u7406<\/strong>\uff1a\u57fa\u4e8e 1.7B \u53c2\u6570\u7684\u7d27\u51d1\u6a21\u578b\uff0c\u63a8\u7406\u901f\u5ea6\u4f18\u4e8e\u8bb8\u591a\u5927\u578b\u6a21\u578b\u3002<\/li>\n<li><strong>\u7075\u6d3b\u63d0\u793a\u5207\u6362<\/strong>\uff1a\u901a\u8fc7\u4e0d\u540c\u63d0\u793a\uff08\u5982\u00a0<code>prompt_layout_only_en<\/code>\u3001<code>prompt_ocr<\/code>\uff09\u5b9e\u73b0\u7279\u5b9a\u4efb\u52a1\u7684\u89e3\u6790\u3002<\/li>\n<li><strong>\u8f93\u51fa\u591a\u6837\u5316<\/strong>\uff1a\u751f\u6210 JSON \u683c\u5f0f\u7684\u7ed3\u6784\u5316\u5e03\u5c40\u6570\u636e\u3001Markdown \u6587\u4ef6\u4ee5\u53ca\u5e26\u8fb9\u754c\u6846\u7684\u53ef\u89c6\u5316\u56fe\u50cf\u3002<\/li>\n<\/ul>\n<h2>\u4f7f\u7528\u5e2e\u52a9<\/h2>\n<h3>\u5b89\u88c5\u6d41\u7a0b<\/h3>\n<p>\u8981\u4f7f\u7528 dots.ocr\uff0c\u9996\u5148\u9700\u8981\u5b89\u88c5\u5fc5\u8981\u7684\u73af\u5883\u548c\u6a21\u578b\u6743\u91cd\u3002\u4ee5\u4e0b\u662f\u8be6\u7ec6\u7684\u5b89\u88c5\u6b65\u9aa4\uff1a<\/p>\n<ol>\n<li><strong>\u521b\u5efa\u865a\u62df\u73af\u5883<\/strong>\uff1a\n<pre><code>conda create -n dots_ocr python=3.12\r\nconda activate dots_ocr\r\n<\/code><\/pre>\n<\/li>\n<\/ol>\n<pre><code>\r\n<\/code><\/pre>\n<ol start=\"2\">\n<li><strong>\u514b\u9686\u4ee3\u7801\u4ed3\u5e93<\/strong>\uff1a\n<pre><code>git clone https:\/\/github.com\/rednote-hilab\/dots.ocr.git\r\ncd dots.ocr\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u5b89\u88c5 PyTorch \u548c\u4f9d\u8d56<\/strong>\uff1a<br \/>\n\u6839\u636e\u4f60\u7684 CUDA \u7248\u672c\uff0c\u5b89\u88c5\u5bf9\u5e94\u7248\u672c\u7684 PyTorch\u3002\u4f8b\u5982\uff1a<\/p>\n<pre><code>pip install torch==2.7.0 torchvision==0.22.0 torchaudio==2.7.0 --index-url https:\/\/download.pytorch.org\/whl\/cu128\r\npip install -e .\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u4e0b\u8f7d\u6a21\u578b\u6743\u91cd<\/strong>\uff1a<br \/>\n\u4f7f\u7528\u63d0\u4f9b\u7684\u811a\u672c\u4e0b\u8f7d\u6a21\u578b\u6743\u91cd\u3002\u6ce8\u610f\uff0c\u6a21\u578b\u4fdd\u5b58\u8def\u5f84\u7684\u6587\u4ef6\u5939\u540d\u4e0d\u80fd\u5305\u542b\u53e5\u70b9\uff0c\u5efa\u8bae\u4f7f\u7528\u00a0<code>DotsOCR<\/code>\uff1a<\/p>\n<pre><code>python3 tools\/download_model.py\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u4f7f\u7528 Docker \u955c\u50cf\uff08\u53ef\u9009\uff09<\/strong>\uff1a<br \/>\n\u5982\u679c\u9047\u5230\u5b89\u88c5\u95ee\u9898\uff0c\u53ef\u4ee5\u4f7f\u7528\u5b98\u65b9\u63d0\u4f9b\u7684 Docker \u955c\u50cf\uff1a<\/p>\n<pre><code>git clone https:\/\/github.com\/rednote-hilab\/dots.ocr.git\r\ncd dots.ocr\r\npip install -e .\r\n<\/code><\/pre>\n<\/li>\n<\/ol>\n<h3>\u90e8\u7f72\u65b9\u5f0f<\/h3>\n<p>dots.ocr \u63a8\u8350\u4f7f\u7528 <a href=\"https:\/\/www.kdjingpai.com\/vllm\/\">vLLM<\/a> \u8fdb\u884c\u90e8\u7f72\uff0c\u4ee5\u83b7\u5f97\u6700\u4f73\u63a8\u7406\u6027\u80fd\u3002\u4ee5\u4e0b\u662f\u57fa\u4e8e vLLM \u7684\u90e8\u7f72\u6b65\u9aa4\uff1a<\/p>\n<ol>\n<li><strong>\u6ce8\u518c\u6a21\u578b\u5230 vLLM<\/strong>\uff1a\n<pre><code>python3 tools\/download_model.py\r\nexport hf_model_path=.\/weights\/DotsOCR\r\nexport PYTHONPATH=$(dirname \"$hf_model_path\"):$PYTHONPATH\r\nsed -i '\/^from vllm\\.entrypoints\\.cli\\.main import main$\/a\\\r\nfrom DotsOCR import modeling_dots_ocr_vllm' `which vllm`\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u542f\u52a8 vLLM \u670d\u52a1<\/strong>\uff1a\n<pre><code>CUDA_VISIBLE_DEVICES=0 vllm serve ${hf_model_path} --tensor-parallel-size 1 --gpu-memory-utilization 0.95 --chat-template-content-format string --served-model-name model --trust-remote-code\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u8fd0\u884c vLLM API \u793a\u4f8b<\/strong>\uff1a\n<pre><code>python3 .\/demo\/demo_vllm.py --prompt_mode prompt_layout_all_en\r\n<\/code><\/pre>\n<\/li>\n<\/ol>\n<p>\u6216\u8005\uff0c\u4f7f\u7528 HuggingFace \u8fdb\u884c\u63a8\u7406\uff1a<\/p>\n<pre><code>python3 demo\/demo_hf.py\r\n<\/code><\/pre>\n<h3>\u6587\u6863\u89e3\u6790\u64cd\u4f5c<\/h3>\n<p>\u5728 vLLM \u670d\u52a1\u542f\u52a8\u540e\uff0c\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u547d\u4ee4\u89e3\u6790\u56fe\u50cf\u6216 PDF \u6587\u4ef6\uff1a<\/p>\n<ol>\n<li><strong>\u89e3\u6790\u5355\u5f20\u56fe\u50cf<\/strong>\uff1a\n<pre><code>python3 dots_ocr\/parser.py demo\/demo_image1.jpg\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u89e3\u6790 PDF \u6587\u4ef6<\/strong>\uff1a<br \/>\n\u5bf9\u4e8e\u591a\u9875 PDF\uff0c\u5efa\u8bae\u8bbe\u7f6e\u8f83\u5927\u7684\u7ebf\u7a0b\u6570\uff1a<\/p>\n<pre><code>python3 dots_ocr\/parser.py demo\/demo_pdf1.pdf --num_threads 64\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u4ec5\u8fdb\u884c\u5e03\u5c40\u68c0\u6d4b<\/strong>\uff1a\n<pre><code>python3 dots_ocr\/parser.py demo\/demo_image1.jpg --prompt prompt_layout_only_en\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u4ec5\u63d0\u53d6\u6587\u672c\uff08\u6392\u9664\u9875\u7709\u9875\u811a\uff09<\/strong>\uff1a\n<pre><code>python3 dots_ocr\/parser.py demo\/demo_image1.jpg --prompt prompt_ocr\r\n<\/code><\/pre>\n<\/li>\n<li><strong>\u57fa\u4e8e\u8fb9\u754c\u6846\u7684\u89e3\u6790<\/strong>\uff1a\n<pre><code>python3 dots_ocr\/parser.py demo\/demo_image1.jpg --prompt prompt_grounding_ocr --bbox 163 241 1536 705\r\n<\/code><\/pre>\n<\/li>\n<\/ol>\n<h3>\u8f93\u51fa\u7ed3\u679c<\/h3>\n<p>\u89e3\u6790\u5b8c\u6210\u540e\uff0cdots.ocr \u4f1a\u751f\u6210\u4ee5\u4e0b\u6587\u4ef6\uff1a<\/p>\n<ul>\n<li><strong>JSON \u6587\u4ef6<\/strong>\uff08\u5982\u00a0<code>demo_image1.json<\/code>\uff09\uff1a\u5305\u542b\u5e03\u5c40\u5143\u7d20\u7684\u8fb9\u754c\u6846\u3001\u7c7b\u522b\u548c\u6587\u672c\u5185\u5bb9\u3002<\/li>\n<li><strong>Markdown \u6587\u4ef6<\/strong>\uff08\u5982\u00a0<code>demo_image1.md<\/code>\uff09\uff1a\u5c06\u6240\u6709\u68c0\u6d4b\u5230\u7684\u6587\u672c\u5185\u5bb9\u5408\u5e76\u4e3a Markdown \u683c\u5f0f\uff0c\u53e6\u6709\u00a0<code>demo_image1_nohf.md<\/code>\u00a0\u7248\u672c\u6392\u9664\u9875\u7709\u9875\u811a\u3002<\/li>\n<li><strong>\u53ef\u89c6\u5316\u56fe\u50cf<\/strong>\uff08\u5982\u00a0<code>demo_image1.jpg<\/code>\uff09\uff1a\u5728\u539f\u59cb\u56fe\u50cf\u4e0a\u7ed8\u5236\u68c0\u6d4b\u5230\u7684\u8fb9\u754c\u6846\u3002<\/li>\n<\/ul>\n<h3>\u8fd0\u884c\u6f14\u793a<\/h3>\n<p>\u53ef\u4ee5\u901a\u8fc7\u4ee5\u4e0b\u547d\u4ee4\u542f\u52a8\u4ea4\u4e92\u5f0f\u6f14\u793a\u754c\u9762\uff1a<\/p>\n<pre><code>python demo\/demo_gradio.py\r\n<\/code><\/pre>\n<p>\u6216\u8fd0\u884c\u57fa\u4e8e\u8fb9\u754c\u6846\u7684 OCR \u6f14\u793a\uff1a<\/p>\n<pre><code>python demo\/demo_gradio_annotion.py\r\n<\/code><\/pre>\n<h3>\u6ce8\u610f\u4e8b\u9879<\/h3>\n<ul>\n<li><strong>\u6a21\u578b\u4fdd\u5b58\u8def\u5f84<\/strong>\uff1a\u786e\u4fdd\u6a21\u578b\u4fdd\u5b58\u8def\u5f84\u4e0d\u5305\u542b\u53e5\u70b9\uff08\u5982\u00a0<code>DotsOCR<\/code>\uff09\uff0c\u5426\u5219\u53ef\u80fd\u5bfc\u81f4\u6a21\u5757\u52a0\u8f7d\u9519\u8bef\u3002<\/li>\n<li><strong>\u56fe\u50cf\u5206\u8fa8\u7387<\/strong>\uff1a\u5efa\u8bae\u56fe\u50cf\u5206\u8fa8\u7387\u4e0d\u8d85\u8fc7 11289600 \u50cf\u7d20\uff0cPDF \u89e3\u6790\u65f6 DPI \u8bbe\u7f6e\u4e3a 200\u3002<\/li>\n<li><strong>\u7279\u6b8a\u5b57\u7b26\u5904\u7406<\/strong>\uff1a\u8fde\u7eed\u7684\u7279\u6b8a\u5b57\u7b26\uff08\u5982\u00a0<code>...<\/code>\u00a0\u6216\u00a0<code>_<\/code>\uff09\u53ef\u80fd\u5bfc\u81f4\u8f93\u51fa\u5f02\u5e38\uff0c\u5efa\u8bae\u4f7f\u7528\u00a0<code>prompt_layout_only_en<\/code>\u00a0\u6216\u00a0<code>prompt_ocr<\/code>\u00a0\u63d0\u793a\u3002<\/li>\n<\/ul>\n<h2>\u5e94\u7528\u573a\u666f<\/h2>\n<ol>\n<li><strong>\u5b66\u672f\u8bba\u6587\u89e3\u6790<\/strong><br \/>\ndots.ocr \u53ef\u4ee5\u9ad8\u6548\u89e3\u6790\u5b66\u672f\u8bba\u6587\u4e2d\u7684\u6587\u672c\u3001\u516c\u5f0f\u548c\u8868\u683c\uff0c\u751f\u6210\u7ed3\u6784\u5316\u7684 JSON \u6570\u636e\u548c Markdown \u6587\u6863\uff0c\u9002\u5408\u7814\u7a76\u4eba\u5458\u6574\u7406\u6587\u732e\u5185\u5bb9\u3002<\/li>\n<li><strong>\u8d22\u52a1\u62a5\u544a\u5904\u7406<\/strong><br \/>\n\u5bf9\u4e8e\u8d22\u52a1\u62a5\u544a\uff0cdots.ocr \u80fd\u51c6\u786e\u63d0\u53d6\u8868\u683c\u548c\u6587\u672c\u5185\u5bb9\uff0c\u751f\u6210 HTML \u683c\u5f0f\u7684\u8868\u683c\uff0c\u4fbf\u4e8e\u6570\u636e\u5206\u6790\u548c\u5b58\u6863\u3002<\/li>\n<li><strong>\u591a\u8bed\u8a00\u6587\u6863\u6574\u7406<\/strong><br \/>\n\u652f\u6301 100 \u79cd\u8bed\u8a00\u7684\u89e3\u6790\uff0c\u9002\u5408\u5904\u7406\u591a\u8bed\u8a00\u5408\u540c\u3001\u6cd5\u5f8b\u6587\u4ef6\u7b49\uff0c\u786e\u4fdd\u5185\u5bb9\u548c\u5e03\u5c40\u51c6\u786e\u63d0\u53d6\u3002<\/li>\n<li><strong>\u6559\u80b2\u8d44\u6599\u6574\u7406<\/strong><br \/>\n\u89e3\u6790\u6559\u79d1\u4e66\u3001\u8bd5\u5377\u7b49\u6559\u80b2\u6750\u6599\uff0c\u63d0\u53d6\u516c\u5f0f\uff08\u4ee5 LaTeX \u683c\u5f0f\uff09\u548c\u6587\u672c\uff0c\u65b9\u4fbf\u6559\u5e08\u548c\u5b66\u751f\u6574\u7406\u5b66\u4e60\u8d44\u6e90\u3002<\/li>\n<\/ol>\n<h2>QA<\/h2>\n<ol>\n<li><strong>dots.ocr \u652f\u6301\u54ea\u4e9b\u8bed\u8a00\uff1f<\/strong><br \/>\ndots.ocr \u652f\u6301 100 \u79cd\u8bed\u8a00\uff0c\u5305\u62ec\u82f1\u8bed\u3001\u4e2d\u6587\u3001\u897f\u85cf\u8bed\u3001\u4fc4\u8bed\u7b49\uff0c\u5c24\u5176\u5728\u4f4e\u8d44\u6e90\u8bed\u8a00\u4e0a\u8868\u73b0\u4f18\u5f02\u3002<\/li>\n<li><strong>\u5982\u4f55\u5904\u7406\u5927\u578b PDF \u6587\u4ef6\uff1f<\/strong><br \/>\n\u4f7f\u7528\u00a0<code>parser.py<\/code>\u00a0\u811a\u672c\u5e76\u8bbe\u7f6e\u00a0<code>--num_threads<\/code>\u00a0\u53c2\u6570\uff08\u5982 64\uff09\uff0c\u4ee5\u52a0\u901f\u591a\u9875 PDF \u7684\u89e3\u6790\u3002<\/li>\n<li><strong>\u89e3\u6790\u7ed3\u679c\u5982\u4f55\u8f93\u51fa\uff1f<\/strong><br \/>\n\u7ed3\u679c\u5305\u62ec JSON \u6587\u4ef6\uff08\u7ed3\u6784\u5316\u6570\u636e\uff09\u3001Markdown \u6587\u4ef6\uff08\u6587\u672c\u5185\u5bb9\uff09\u548c\u53ef\u89c6\u5316\u56fe\u50cf\uff08\u5e26\u8fb9\u754c\u6846\uff09\u3002<\/li>\n<li><strong>\u5982\u4f55\u89e3\u51b3\u6a21\u578b\u52a0\u8f7d\u9519\u8bef\uff1f<\/strong><br \/>\n\u786e\u4fdd\u6a21\u578b\u4fdd\u5b58\u8def\u5f84\u4e0d\u542b\u53e5\u70b9\uff08\u5982\u4f7f\u7528\u00a0<code>DotsOCR<\/code>\uff09\uff0c\u5e76\u68c0\u67e5 vLLM \u6ce8\u518c\u811a\u672c\u662f\u5426\u6b63\u786e\u6267\u884c\u3002<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"<p>dots.ocr \u662f\u4e00\u4e2a\u5f3a\u5927\u7684\u591a\u8bed\u8a00\u6587\u6863\u89e3\u6790\u5de5\u5177\uff0c\u57fa\u4e8e 1.7B \u53c2\u6570\u7684\u89c6\u89c9-\u8bed\u8a00\u6a21\u578b\uff08VLM\uff09\uff0c\u80fd\u591f\u540c\u65f6\u8fdb\u884c\u5e03\u5c40\u68c0\u6d4b\u548c\u5185\u5bb9\u8bc6\u522b\u3002\u5b83\u5728 OmniDocBench \u7b49\u57fa\u51c6\u6d4b\u8bd5\u4e2d\u5c55\u73b0\u4e86\u6700\u5148\u8fdb\u7684\u6027\u80fd\uff0c\u7279\u522b\u662f\u5728\u6587\u672c\u3001\u8868\u683c\u548c\u9605\u8bfb\u987a\u5e8f\u89e3\u6790\u65b9\u9762\u8868\u73b0\u51fa\u8272\u3002&#8230;<\/p>\n","protected":false},"author":1,"featured_media":32782,"comment_status":"open","ping_status":"closed","sticky":true,"template":"","format":"standard","meta":{"footnotes":""},"categories":[425,20,502],"tags":[230,248],"class_list":["post-35158","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-professional","category-tool","category-text-recognition","tag-aikaiyuanxiangmu","tag-ocr"],"_links":{"self":[{"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/posts\/35158","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/comments?post=35158"}],"version-history":[{"count":0,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/posts\/35158\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/media\/32782"}],"wp:attachment":[{"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/media?parent=35158"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/categories?post=35158"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/tags?post=35158"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}