{"id":41225,"date":"2022-11-10T09:12:15","date_gmt":"2023-01-18T00:00:16","guid":{"rendered":"https:\/\/www.silicloud.com\/zh\/blog\/%e7%94%a8ocr%e5%92%8celasticsearch%e5%88%9b%e5%bb%ba%e5%9b%be%e5%83%8f%e6%96%87%e4%bb%b6%e6%90%9c%e7%b4%a2%e5%bc%95%e6%93%8e%e3%80%82\/"},"modified":"2024-04-28T23:59:35","modified_gmt":"2024-04-28T15:59:35","slug":"%e7%94%a8ocr%e5%92%8celasticsearch%e5%88%9b%e5%bb%ba%e5%9b%be%e5%83%8f%e6%96%87%e4%bb%b6%e6%90%9c%e7%b4%a2%e5%bc%95%e6%93%8e%e3%80%82","status":"publish","type":"post","link":"https:\/\/www.silicloud.com\/zh\/blog\/%e7%94%a8ocr%e5%92%8celasticsearch%e5%88%9b%e5%bb%ba%e5%9b%be%e5%83%8f%e6%96%87%e4%bb%b6%e6%90%9c%e7%b4%a2%e5%bc%95%e6%93%8e%e3%80%82\/","title":{"rendered":"\u7528OCR\u548cElasticsearch\u521b\u5efa\u56fe\u50cf\u6587\u4ef6\u641c\u7d22\u5f15\u64ce"},"content":{"rendered":"<h2>\u9996\u5148<\/h2>\n<p>\u8fd9\u662fABEJA 2021\u5e74\u5723\u8bde\u8282\u65e5\u5386\u7684\u7b2c17\u5929\u7684\u6587\u7ae0\u3002<\/p>\n<p>\u672c\u6587\u4ecb\u7ecd\u4e86\u4f7f\u7528\u8c37\u6b4c\u7684Cloud Vision API\uff08OCR\uff09\u548c\u5168\u6587\u641c\u7d22\u5f15\u64ceElasticsearch\uff08\u4ee5\u4e0b\u7b80\u79f0ES\uff09\uff0c\u4f7f\u5f97\u53ef\u4ee5\u4ece\u56fe\u50cf\u6587\u4ef6\u7684\u6587\u672c\u5185\u5bb9\u4e2d\u8fdb\u884c\u5173\u952e\u8bcd\u641c\u7d22\u3002<\/p>\n<p>\u6211\u5011\u60f3\u8981\u5f9e\u5927\u91cf\u7684\u904e\u53bb\u6587\u4ef6\u548c\u8cc7\u6599\u4e2d\u627e\u5230\u7279\u5b9a\u7684\u6587\u4ef6\uff0c\u4f46\u4e00\u76f4\u627e\u4e0d\u5230&#8230;\u9019\u7bc7\u6587\u7ae0\u7684\u5167\u5bb9\u662f\u8981\u4ecb\u7d39\u5982\u4f55\u4f7f\u7528OCR\u548cES\u4f86\u5f9e\u6587\u4ef6\u5167\u5bb9\u4e2d\u66f4\u6709\u6548\u5730\u9032\u884c\u641c\u7d22\u3002<br \/>\n\u5982\u679c\u56e0\u70ba\u66f8\u9762\u6587\u4ef6\u592a\u591a\u800c\u653e\u68c4\u4e86\u6548\u7387\u5316\u7684\u8a71&#8230;\u4e5f\u53ef\u4ee5\u901a\u904e\u6383\u63cf\u6216\u4f7f\u7528\u76f8\u6a5f\u5c07\u6587\u4ef6\u5716\u50cf\u5316\u4f86\u9054\u5230\u540c\u6a23\u7684\u6548\u679c\u3002<\/p>\n<h2>\u76ee\u9304\u7d50\u69cb<\/h2>\n<p>\u6700\u7ec8\u7684\u76ee\u5f55\u7ed3\u6784\u3002<\/p>\n<pre class=\"post-pre\"><code>.\r\n\u251c\u2500\u2500 docker-compose.yml\r\n\u251c\u2500\u2500 docker\r\n\u2502   \u251c\u2500\u2500 python3\r\n\u2502   \u2502   \u2514\u2500\u2500 Dockerfile \r\n\u2502   \u2514\u2500\u2500 elasticsearch\r\n\u2502       \u2514\u2500\u2500 Dockerfile \r\n\u2514\u2500\u2500 src\r\n    \u251c\u2500\u2500 images\r\n    \u2502   \u2514\u2500\u2500 input\r\n    \u2502   \u2514\u2500\u2500 archive\r\n    \u2514\u2500\u2500 main.py\r\n<\/code><\/pre>\n<h2>\u51c6\u5907\u4f7f\u7528Cloud Vision API<\/h2>\n<p>\u4e3a\u4e86\u4f7f\u7528Cloud Vision API\uff0c\u9700\u8981\u6309\u7167\u4ee5\u4e0b\u6b65\u9aa4\u8fdb\u884c\u64cd\u4f5c\u3002<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Google Cloud Platform\u306e\u767b\u9332<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">Cloud Vision API\u3092\u6709\u52b9\u306b\u3059\u308b\u8a2d\u5b9a<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">API\u3092\u5b9f\u884c\u3059\u308b\u305f\u3081\u306e\u30b5\u30fc\u30d3\u30b9\u30a2\u30ab\u30a6\u30f3\u30c8\u306e\u4f5c\u6210<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u8a8d\u8a3c\u7528\u306eJSON\u30d5\u30a1\u30a4\u30eb\u3092\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u3057\u3001\u4efb\u610f\u306e\u30c7\u30a3\u30ec\u30af\u30c8\u30ea\u306b\u914d\u7f6e(\u4ee5\u964dcredential.json\u3068\u3057\u307e\u3059\u3002)<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\u8a8d\u8a3c\u7528\u306eJSON\u30d5\u30a1\u30a4\u30eb\u3078\u306epath\u3092\u901a\u3059<\/ul>\n<p>\u6211\u5df2\u53c2\u8003\u4e86\u8fd9\u7bc7\u6587\u7ae0\uff01<\/p>\n<h2>\u51c6\u5907\u6267\u884c\u73af\u5883<\/h2>\n<p>\u4f7f\u7528Docker\u521b\u5efaPython\u6267\u884c\u73af\u5883\u548cElasticsearch\u73af\u5883\u3002<\/p>\n<p>\u521b\u5efa\u4e00\u4e2aDockerfile\u6765\u8bbe\u7f6eDocker\/Python3\u7684\u73af\u5883\u3002\u5728\u8fd9\u4e2aDockerfile\u4e2d\uff0c\u8fdb\u884c\u4e86Python\u6267\u884c\u73af\u5883\u7684\u8bbe\u7f6e\u4ee5\u53ca\u5b89\u88c5\u6240\u9700\u7684google-cloud-vision\u5e93\u7528\u4e8e\u6267\u884cCloud Vision API\u4ee5\u53ca\u5b89\u88c5\u6240\u9700\u7684\u5e93\u7528\u4e8e\u4f7f\u7528Elasticsearch\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"k\">FROM<\/span><span class=\"s\"> python:3.9<\/span>\r\n<span class=\"k\">USER<\/span><span class=\"s\"> root<\/span>\r\n\r\n<span class=\"k\">RUN <\/span>apt-get update\r\n<span class=\"k\">RUN <\/span>apt-get <span class=\"nt\">-y<\/span> <span class=\"nb\">install <\/span>locales <span class=\"o\">&amp;&amp;<\/span> <span class=\"se\">\\\r\n<\/span>    localedef <span class=\"nt\">-f<\/span> UTF-8 <span class=\"nt\">-i<\/span> ja_JP ja_JP.UTF-8\r\n<span class=\"k\">ENV<\/span><span class=\"s\"> LANG ja_JP.UTF-8<\/span>\r\n<span class=\"k\">ENV<\/span><span class=\"s\"> LANGUAGE ja_JP:ja<\/span>\r\n<span class=\"k\">ENV<\/span><span class=\"s\"> LC_ALL ja_JP.UTF-8<\/span>\r\n<span class=\"k\">ENV<\/span><span class=\"s\"> TZ JST-9<\/span>\r\n<span class=\"k\">ENV<\/span><span class=\"s\"> TERM xterm<\/span>\r\n\r\n<span class=\"k\">RUN <\/span><span class=\"nb\">mkdir<\/span> \/app\r\n\r\n<span class=\"k\">RUN <\/span>apt-get <span class=\"nb\">install<\/span> <span class=\"nt\">-y<\/span> vim\r\n<span class=\"k\">RUN <\/span>pip <span class=\"nb\">install<\/span> <span class=\"nt\">--upgrade<\/span> pip\r\n<span class=\"k\">RUN <\/span>pip <span class=\"nb\">install<\/span> <span class=\"nt\">--upgrade<\/span> setuptools\r\n\r\n<span class=\"k\">RUN <\/span>python <span class=\"nt\">-m<\/span> pip <span class=\"nb\">install <\/span>google-cloud-vision <span class=\"se\">\\\r\n<\/span>                          elasticsearch\r\n<\/code><\/pre>\n<p>\u521b\u5efa\u4e00\u4e2adocker\/elasticsearch\u7684Dockerfile\u3002\u6307\u5b9aElasticsearch\u955c\u50cf\u5e76\u5b89\u88c5analysis-kuromoji\u4ee5\u652f\u6301\u65e5\u8bed\u5168\u6587\u641c\u7d22\u529f\u80fd\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"k\">FROM<\/span><span class=\"s\"> docker.elastic.co\/elasticsearch\/elasticsearch:7.15.0<\/span>\r\n<span class=\"k\">RUN <\/span>elasticsearch-plugin <span class=\"nb\">install <\/span>analysis-kuromoji\r\n<\/code><\/pre>\n<p>\u521b\u5efadocker-compose.yml\u6587\u4ef6\u3002<br \/>\n\u672c\u6b21\u5c06\u53ea\u4f7f\u7528\u4e00\u4e2aElasticsearch\u5bb9\u5668\uff08\u8282\u70b9\uff09\uff0c\u4f46\u6839\u636e\u9700\u6c42\uff0c\u8bf7\u5728\u7f51\u7edc\u4e2d\u4f7f\u7528\u591a\u4e2a\u5bb9\u5668\uff08\u8282\u70b9\uff09\u3002<br \/>\n\u53e6\u5916\uff0c\u8bf7\u5c06environment\u7684GOOGLE_APPLICATION_CREDENTIALS\u6307\u5b9a\u4e3acredential.json\u7684\u8def\u5f84\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"na\">version<\/span><span class=\"pi\">:<\/span> <span class=\"s1\">'<\/span><span class=\"s\">3'<\/span>\r\n<span class=\"na\">services<\/span><span class=\"pi\">:<\/span>\r\n  <span class=\"na\">elasticsearch<\/span><span class=\"pi\">:<\/span>\r\n    <span class=\"na\">build<\/span><span class=\"pi\">:<\/span> <span class=\"s\">.\/docker\/elasticsearch<\/span>\r\n    <span class=\"na\">container_name<\/span><span class=\"pi\">:<\/span> <span class=\"s\">elasticsearch<\/span>\r\n    <span class=\"na\">environment<\/span><span class=\"pi\">:<\/span>\r\n      <span class=\"pi\">-<\/span> <span class=\"s\">discovery.type=single-node<\/span>\r\n      <span class=\"pi\">-<\/span> <span class=\"s\">cluster.name=es-docker-cluster<\/span>\r\n      <span class=\"pi\">-<\/span> <span class=\"s\">bootstrap.memory_lock=true<\/span>\r\n      <span class=\"pi\">-<\/span> <span class=\"s2\">\"<\/span><span class=\"s\">ES_JAVA_OPTS=-Xms512m<\/span> <span class=\"s\">-Xmx512m\"<\/span>\r\n    <span class=\"na\">ulimits<\/span><span class=\"pi\">:<\/span>\r\n      <span class=\"na\">memlock<\/span><span class=\"pi\">:<\/span>\r\n        <span class=\"na\">soft<\/span><span class=\"pi\">:<\/span> <span class=\"s\">-1<\/span>\r\n        <span class=\"na\">hard<\/span><span class=\"pi\">:<\/span> <span class=\"s\">-1<\/span>\r\n    <span class=\"na\">volumes<\/span><span class=\"pi\">:<\/span>\r\n      <span class=\"pi\">-<\/span> <span class=\"s\">.\/docker\/elasticsearch:\/usr\/share\/elasticsearch\/data<\/span>\r\n    <span class=\"na\">ports<\/span><span class=\"pi\">:<\/span>\r\n      <span class=\"pi\">-<\/span> <span class=\"s\">9200:9200<\/span>\r\n    <span class=\"na\">networks<\/span><span class=\"pi\">:<\/span>\r\n      <span class=\"pi\">-<\/span> <span class=\"s\">esnet<\/span>\r\n  <span class=\"na\">python3<\/span><span class=\"pi\">:<\/span>\r\n    <span class=\"na\">build<\/span><span class=\"pi\">:<\/span> <span class=\"s\">.\/docker\/python3<\/span>\r\n    <span class=\"na\">container_name<\/span><span class=\"pi\">:<\/span> <span class=\"s\">python3<\/span>\r\n    <span class=\"na\">working_dir<\/span><span class=\"pi\">:<\/span> <span class=\"s1\">'<\/span><span class=\"s\">\/app'<\/span>\r\n    <span class=\"na\">tty<\/span><span class=\"pi\">:<\/span> <span class=\"no\">true<\/span>\r\n    <span class=\"na\">environment<\/span><span class=\"pi\">:<\/span>\r\n      <span class=\"na\">GOOGLE_APPLICATION_CREDENTIALS<\/span><span class=\"pi\">:<\/span> <span class=\"s\">\/tmp\/keys\/credential.json<\/span>\r\n    <span class=\"na\">volumes<\/span><span class=\"pi\">:<\/span>\r\n      <span class=\"pi\">-<\/span> <span class=\"s\">.\/src:\/app<\/span>\r\n      <span class=\"pi\">-<\/span> <span class=\"s\">${GOOGLE_APPLICATION_CREDENTIALS}:\/tmp\/keys\/credential.json:ro<\/span>\r\n    <span class=\"na\">networks<\/span><span class=\"pi\">:<\/span>\r\n      <span class=\"pi\">-<\/span> <span class=\"s\">esnet<\/span>\r\n<span class=\"na\">networks<\/span><span class=\"pi\">:<\/span>\r\n  <span class=\"na\">esnet<\/span><span class=\"pi\">:<\/span>\r\n<\/code><\/pre>\n<p>\u5f53\u6587\u4ef6\u5168\u90e8\u653e\u597d\u540e\uff0c\u6267\u884c\u4ee5\u4e0b\u547d\u4ee4\uff0c\u5373\u53ef\u5b8c\u6210\u672c\u6b21\u4f7f\u7528\u73af\u5883\u7684\u521b\u5efa\u3002<\/p>\n<pre class=\"post-pre\"><code># \u8d77\u52d5\r\n&gt; docker-comopse up -d\r\n\r\n# \u78ba\u8a8d\r\n&gt; docker-compose ps   \r\n    Name                   Command               State                Ports              \r\n-----------------------------------------------------------------------------------------\r\nelasticsearch   \/bin\/tini -- \/usr\/local\/bi ...   Up      0.0.0.0:9200-&gt;9200\/tcp, 9300\/tcp\r\npython3         python3                          Up \r\n<\/code><\/pre>\n<h2>\u4f7f\u7528Cloud Vision API\u7684\u65b9\u6cd5<\/h2>\n<p>\u6211\u4eec\u6b63\u5728\u53c2\u8003\u8fd9\u4efd\u6587\u6863\u6765\u6267\u884c\u4ee3\u7801\u3002<br \/>\n\u4e3a\u4e86\u6d4b\u8bd5\uff0c\u6211\u4eec\u5c06\u6267\u884c\u4ee5\u4e0b\u4ee3\u7801\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"kn\">import<\/span> <span class=\"nn\">io<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">os<\/span>\r\n<span class=\"kn\">from<\/span> <span class=\"nn\">google.cloud<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">vision<\/span>\r\n\r\n\r\n<span class=\"k\">def<\/span> <span class=\"nf\">detect_document<\/span><span class=\"p\">(<\/span><span class=\"n\">file_path<\/span><span class=\"p\">):<\/span>\r\n    <span class=\"n\">client<\/span> <span class=\"o\">=<\/span> <span class=\"n\">vision<\/span><span class=\"p\">.<\/span><span class=\"n\">ImageAnnotatorClient<\/span><span class=\"p\">()<\/span>\r\n\r\n    <span class=\"n\">file_name<\/span> <span class=\"o\">=<\/span> <span class=\"n\">os<\/span><span class=\"p\">.<\/span><span class=\"n\">path<\/span><span class=\"p\">.<\/span><span class=\"n\">abspath<\/span><span class=\"p\">(<\/span><span class=\"n\">file_path<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"k\">with<\/span> <span class=\"n\">io<\/span><span class=\"p\">.<\/span><span class=\"nb\">open<\/span><span class=\"p\">(<\/span><span class=\"n\">file_name<\/span><span class=\"p\">,<\/span> <span class=\"s\">'rb'<\/span><span class=\"p\">)<\/span> <span class=\"k\">as<\/span> <span class=\"n\">image_file<\/span><span class=\"p\">:<\/span>\r\n        <span class=\"n\">content<\/span> <span class=\"o\">=<\/span> <span class=\"n\">image_file<\/span><span class=\"p\">.<\/span><span class=\"n\">read<\/span><span class=\"p\">()<\/span>\r\n\r\n    <span class=\"n\">image<\/span> <span class=\"o\">=<\/span> <span class=\"n\">vision<\/span><span class=\"p\">.<\/span><span class=\"n\">Image<\/span><span class=\"p\">(<\/span><span class=\"n\">content<\/span><span class=\"o\">=<\/span><span class=\"n\">content<\/span><span class=\"p\">)<\/span>\r\n\r\n    <span class=\"n\">response<\/span> <span class=\"o\">=<\/span> <span class=\"n\">client<\/span><span class=\"p\">.<\/span><span class=\"n\">document_text_detection<\/span><span class=\"p\">(<\/span>\r\n        <span class=\"n\">image<\/span><span class=\"o\">=<\/span><span class=\"n\">image<\/span><span class=\"p\">,<\/span>\r\n        <span class=\"n\">image_context<\/span><span class=\"o\">=<\/span><span class=\"p\">{<\/span><span class=\"s\">'language_hints'<\/span><span class=\"p\">:<\/span> <span class=\"p\">[<\/span><span class=\"s\">'ja'<\/span><span class=\"p\">]}<\/span>\r\n    <span class=\"p\">)<\/span>\r\n\r\n    <span class=\"n\">text<\/span> <span class=\"o\">=<\/span> <span class=\"s\">''<\/span>\r\n    <span class=\"k\">for<\/span> <span class=\"n\">page<\/span> <span class=\"ow\">in<\/span> <span class=\"n\">response<\/span><span class=\"p\">.<\/span><span class=\"n\">full_text_annotation<\/span><span class=\"p\">.<\/span><span class=\"n\">pages<\/span><span class=\"p\">:<\/span>\r\n        <span class=\"k\">for<\/span> <span class=\"n\">block<\/span> <span class=\"ow\">in<\/span> <span class=\"n\">page<\/span><span class=\"p\">.<\/span><span class=\"n\">blocks<\/span><span class=\"p\">:<\/span>\r\n            <span class=\"k\">for<\/span> <span class=\"n\">paragraph<\/span> <span class=\"ow\">in<\/span> <span class=\"n\">block<\/span><span class=\"p\">.<\/span><span class=\"n\">paragraphs<\/span><span class=\"p\">:<\/span>\r\n                <span class=\"k\">for<\/span> <span class=\"n\">word<\/span> <span class=\"ow\">in<\/span> <span class=\"n\">paragraph<\/span><span class=\"p\">.<\/span><span class=\"n\">words<\/span><span class=\"p\">:<\/span>\r\n                    <span class=\"n\">text<\/span> <span class=\"o\">+=<\/span> <span class=\"s\">''<\/span><span class=\"p\">.<\/span><span class=\"n\">join<\/span><span class=\"p\">([<\/span>\r\n                        <span class=\"n\">symbol<\/span><span class=\"p\">.<\/span><span class=\"n\">text<\/span> <span class=\"k\">for<\/span> <span class=\"n\">symbol<\/span> <span class=\"ow\">in<\/span> <span class=\"n\">word<\/span><span class=\"p\">.<\/span><span class=\"n\">symbols<\/span>\r\n                    <span class=\"p\">])<\/span>\r\n                <span class=\"n\">text<\/span> <span class=\"o\">+=<\/span> <span class=\"s\">'<\/span><span class=\"se\">\\n<\/span><span class=\"s\">'<\/span>\r\n    <span class=\"k\">print<\/span><span class=\"p\">(<\/span><span class=\"n\">text<\/span><span class=\"p\">)<\/span>\r\n\r\n\r\n<span class=\"k\">if<\/span> <span class=\"n\">__name__<\/span> <span class=\"o\">==<\/span> <span class=\"s\">\"__main__\"<\/span><span class=\"p\">:<\/span>\r\n    <span class=\"n\">file_path<\/span> <span class=\"o\">=<\/span> <span class=\"s\">'images\/input\/wiki-ocr-short.png'<\/span>\r\n    <span class=\"n\">detect_document<\/span><span class=\"p\">(<\/span><span class=\"n\">file_path<\/span><span class=\"p\">)<\/span>\r\n<\/code><\/pre>\n<p>\u51c6\u5907\u4e00\u4e2a\u8fdb\u884c\u6587\u5b57\u8bc6\u522b\u7684\u56fe\u50cf\u6587\u4ef6\u3002\u7f51\u9875\u622a\u56fe\u3001\u626b\u63cf\u6587\u4ef6\u3001\u62cd\u6444\u624b\u5199\u6587\u5b57\u7eb8\u5f20\u7b49\u4efb\u4f55\u5305\u542b\u6587\u5b57\u7684\u56fe\u50cf\u90fd\u53ef\u4ee5\u3002<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d458837434c4406ca2cfb\/25-0.png\" alt=\"wiki_ocr_short.png\" \/><\/div>\n<p>\u5f53\u60a8\u6267\u884c\u547d\u4ee4\u65f6\uff0c\u6211\u8ba4\u4e3a\u4f1a\u8fd4\u56de\u6587\u5b57\u8bc6\u522b\u7684\u7ed3\u679c\u3002<\/p>\n<pre class=\"post-pre\"><code>&gt; docker-compose exec python3 python main.py\r\n\r\n\u5149\u5b66\u6587\u5b57\u8a8d\u8b58\u51fa\u5178:\u30d5\u30ea\u30fc\u767e\u79d1\u4e8b\u5178\u300e\u30a6\u30a3\u30ad\u30da\u30c7\u30a3\u30a2(Wikipedia)\u300f\r\n\u5149\u5b66\u6587\u5b57\u8a8d\u8b58(\u3053\u3046\u304c\u304f\u3082\u3058\u306b\u3093\u3057\u304d\u3001\u82f1:Opticalcharacterrecognition)\u306f\u3001\u6d3b\u5b57\u3001\u624b\u66f8\u304d\u30c6\u30ad\u30b9\u30c8\u306e\u753b\u50cf\u3092\u6587\u5b57\u30b3\u30fc\u30c9\u306e\u5217\u306b\u5909\u63db\u3059\u308b\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3067\u3042\u308b\u3002\u753b\u50cf\u306f\u30a4\u30e1\u30fc\u30b8\u30b9\u30ad\u30e3\u30ca\u30fc\u3084\u5199\u771f\u3067\u53d6\u308a\u8fbc\u307e\u308c\u305f\u6587\u66f8\u3001\u98a8\u666f\u5199\u771f(\u98a8\u666f\u5185\u306e\u770b\u677f\u306e\u6587\u5b57\u306a\u3069)\u3001\u753b\u50cf\u5185\u306e\u5b57\u5e55(\u30c6\u30ec\u30d3\u653e\u9001\u753b\u50cf\u5185\u306a\u3069)\u304c\u4f7f\u308f\u308c\u308b[1]\u3002\u4e00\u822c\u306bOCR\u3068\u7565\u8a18\u3055\u308c\u308b\u3002\r\n\u30d1\u30b9\u30dd\u30fc\u30c8\u3001\u8acb\u6c42\u66f8\u3001\u9280\u884c\u53d6\u5f15\u660e\u7d30\u66f8\u3001\u30ec\u30b7\u30fc\u30c8\u3001\u540d\u523a\u3001\u30e1\u30fc\u30eb\u3001\u30c7\u30fc\u30bf\u3084\u6587\u66f8\u306e\u5370\u5237\u7269\u306a\u3069\u3001\u7d19\u306b\u8a18\u8f09\u3055\u308c\u305f\u30c7\u30fc\u30bf\u3092\u30c7\u30fc\u30bf\u5165\u529b\u3059\u308b\u624b\u6cd5\u3068\u3057\u3066\u5e83\u304f\u4f7f\u308f\u308c\u3001\u7d19\u306b\u5370\u5237\u3055\u308c\u305f\u6587\u66f8\u3092\u30c7\u30b8\u30bf\u30a4\u30ba\u3057\u3001\u3088\u308a\u30b3\u30f3\u30d1\u30af\u30c8\u306a\u5f62\u3067\u8a18\u9332\u3059\u308b\u306e\u306b\u5fc5\u8981\u3068\u3055\u308c\u308b\u3002\u3055\u3089\u306b\u3001\u6587\u5b57\u30b3\u30fc\u30c9\u306b\u5909\u63db\u3059\u308b\u3053\u3068\u3067\u30b3\u30b0\u30cb\u30c6\u30a3\u30d6\u30b3\u30f3\u30d4\u30e5\u30fc\u30c6\u30a3\u30f3\u30b0\u3001\u6a5f\u68b0\u7ffb\u8a33\u3084\u97f3\u58f0\u5408\u6210\u306e\u5165\u529b\u306b\u3082\u4f7f\u3048\u308b\u3088\u3046\u306b\u306a\u308a\u3001\u30c6\u30ad\u30b9\u30c8\u30de\u30a4\u30cb\u30f3\u30b0\u3082\u53ef\u80fd\u3068\u306a\u308b\u3002\u7814\u7a76\u5206\u91ce\u3068\u3057\u3066\u306f\u3001\u30d1\u30bf\u30fc\u30f3\u8a8d\u8b58\u3001\u4eba\u5de5\u77e5\u80fd\u3001\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30d3\u30b8\u30e7\u30f3\u304c\u5bfe\u5fdc\u3059\u308b\u3002\r\n\u521d\u671f\u306e\u30b7\u30b9\u30c6\u30e0\u306f\u7279\u5b9a\u306e\u66f8\u4f53\u3092\u8aad\u3080\u305f\u3081\u306e\u300c\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u300d\u304c\u5fc5\u8981\u3067\u3042\u3063\u305f(\u4e8b\u524d\u306b\u305d\u306e\u66f8\u4f53\u306e\u30b5\u30f3\u30d7\u30eb\u3092\u8aad\u307e\u305b\u308b\u3053\u3068\u3092\u610f\u5473\u3059\u308b)\u3002\u73fe\u5728\u3067\u306f\u3001\u307b\u3068\u3093\u3069\u306e\u66f8\u4f53\u3092\u9ad8\u3044\u8b58\u5b57\u7387\u3067\u5909\u63db\u3059\u308b\u3053\u3068\u304c\u53ef\u80fd\u3067\u3042\u308b\u3002\u3044\u304f\u3064\u304b\u306e\u30b7\u30b9\u30c6\u30e0\u3067\u306f\u8aad\u307f\u8fbc\u307e\u308c\u305f\u753b\u50cf\u304b\u3089\u305d\u308c\u3068\u307b\u307c\u540c\u3058\u306b\u306a\u308b\u3088\u3046\u30d5\u30a9\u30fc\u30de\u30c3\u30c8\u3055\u308c\u305f\u51fa\u529b(\u4f8b\u3048\u3070\u30ef\u30fc\u30c9\u30d7\u30ed\u30bb\u30c3\u30b5\u306e\u30d5\u30a1\u30a4\u30eb\u306e\u3088\u3046\u306a\u3082\u306e)\u3092\u751f\u6210\u3059\u308b\u3053\u3068\u304c\u53ef\u80fd\u3067\u3042\u308a\u3001\u4e2d\u306b\u306f\u753b\u50cf\u306a\u3069\u306e\u6587\u66f8\u4ee5\u5916\u306e\u90e8\u5206\u304c\u542b\u307e\u308c\u3066\u3044\u3066\u3082\u6b63\u3057\u304f\u8a8d\u8b58\u3059\u308b\u3082\u306e\u3082\u3042\u308b\u3002\r\n<\/code><\/pre>\n<p>\u4ee5\u8fd9\u79cd\u65b9\u5f0f\uff0c\u60a8\u51e0\u4e4e\u53ef\u4ee5\u5b8c\u7f8e\u5730\u9605\u8bfb\u5c4f\u5e55\u622a\u56fe\u56fe\u50cf\u7b49\u7f8e\u89c2\u7684\u6587\u5b57\uff01<\/p>\n<div><img decoding=\"async\" class=\"post-images\" title=\"\" src=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d458837434c4406ca2cfb\/29-0.png\" alt=\"gcp.png\" \/><\/div>\n<pre class=\"post-pre\"><code>&gt; docker-compose exec python3 python main.py\r\n\r\nGoogleCloudPlatform\r\nGCP\u3068\u306f\u3001Google\u304c\u63d0\u4f9b\u3057\u3066\u3044\u308b\u30af\u30e9\u30a6\u30c9\u30b3\u30f3\u30d4\u30e5\u30fc\u30c6\u30a3\u30f3\u30b0\u30b5\u30fc\u30d3\u30b9\u3067\u3042\u308b\u3002\r\n<\/code><\/pre>\n<p>\u6211\u53ef\u4ee5\u89e3\u8b80\/\u95b1\u8b80\u5b83\u4e86\uff01<\/p>\n<p>\u8fd9\u6b21\u80fd\u591f\u5f88\u597d\u5730\u8bc6\u522b\u51fa\u8fd9\u4e24\u4e2a\u56fe\u7247\uff0c\u4f46\u5bf9\u4e8e\u4ee5\u4e0b\u7c7b\u4f3c\u7684\u6587\u5b57\u6216\u56fe\u50cf\u60c5\u51b5\u53ef\u80fd\u4f1a\u964d\u4f4e\u8bc6\u522b\u7684\u51c6\u786e\u5ea6\u3002<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u30b9\u30ad\u30e3\u30f3\u3057\u305f\u969b\u306b\u591a\u304f\u306e\u30ce\u30a4\u30ba\u304c\u5165\u3063\u3066\u3057\u307e\u3063\u3066\u3044\u308b\u753b\u50cf<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u6975\u7aef\u306b\u660e\u308b\u304b\u3063\u305f\u308a\u3001\u6697\u304b\u3063\u305f\u308a\u3059\u308b\u5199\u771f\u306a\u3069\u306e\u753b\u50cf<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">\n<li style=\"list-style-type: none;\">\n<ul class=\"post-ul\">\u6587\u5b57\u306e\u80cc\u666f\u306b\u67c4\u304c\u5165\u3063\u3066\u3044\u308b\u5834\u5408<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<ul class=\"post-ul\">etc<\/ul>\n<p>\u53e6\u5916\uff0c\u5982\u679c\u4e0d\u4ed4\u7ec6\u5730\u4e66\u5199\u624b\u5199\u6587\u5b57\uff0c\u8981\u5b8c\u7f8e\u5730\u8bfb\u53d6\u662f\u5f88\u56f0\u96be\u7684\u3002\u5f53\u65e0\u6cd5\u6709\u6548\u5730\u8bc6\u522b\u5b57\u7b26\u65f6\uff0c\u901a\u8fc7\u8fdb\u884c\u56fe\u50cf\u9884\u5904\u7406\uff0c\u5982\u53bb\u9664\u566a\u97f3\u3001\u8c03\u6574\u4eae\u5ea6\u7b49\uff0c\u53ef\u4ee5\u63d0\u9ad8\u51c6\u786e\u6027\u3002<\/p>\n<h2>\u5c06\u4fe1\u606f\u6ce8\u518c\u5230Elasticsearch\u4e2d\u3002<\/h2>\n<p>\u521b\u5efa\u4e00\u4e2a\u7528\u4e8e\u5c06\u6570\u636e\u6ce8\u518c\u5230ES\u7684\u7d22\u5f15\u3002\u7c7b\u4f3c\u4e8e\u5173\u7cfb\u6570\u636e\u5e93\u4e2d\u7684\u6570\u636e\u5e93\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"c\"># \u30a4\u30f3\u30c7\u30c3\u30af\u30b9\u767b\u9332<\/span>\r\n<span class=\"o\">&gt;<\/span> curl <span class=\"nt\">-XPUT<\/span> <span class=\"s1\">'http:\/\/localhost:9200\/document?pretty'<\/span>\r\n\r\n<span class=\"c\"># \u30a4\u30f3\u30c7\u30c3\u30af\u30b9\u4e00\u89a7\u8868\u793a<\/span>\r\n<span class=\"o\">&gt;<\/span> curl <span class=\"s1\">'http:\/\/localhost:9200\/_cat\/indices?v'<\/span>     \r\nhealth status index            uuid                   pri rep docs.count docs.deleted store.size pri.store.size\r\ngreen  open   .geoip_databases FR2MULeESTOjuvrjO56-0g   1   0         42            0     41.2mb         41.2mb\r\nyellow open   document         xApyPIshRMe9kNk4tvnu0g   1   1          0            0       208b           208b\r\n<\/code><\/pre>\n<p>\u8fd9\u6bb5\u4ee3\u7801\u4f7f\u7528Python\u5411Elasticsearch\u6ce8\u518c\u6570\u636e\u3002<br \/>\n\u6307\u5b9a\u4e86Elasticsearch\u7684\u5bb9\u5668\u540d\u79f0\u548c\u7aef\u53e3\u53f7\u4e3aelasticsearch:9200\u3002<\/p>\n<pre class=\"post-pre\"><code>es = Elasticsearch('elasticsearch:9200')\r\nes.index(index='document', document=doc)\r\n<\/code><\/pre>\n<p>\u53d6\u5f97\u76ee\u5f55\u4e0b\u7684\u6240\u6709\u56fe\u50cf\u6587\u4ef6\uff0c\u5e76\u9010\u4e00\u8fdb\u884cOCR\u5904\u7406\u540e\uff0c\u5c06\u5176\u6ce8\u518c\u5230ES\u4e2d\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"kn\">import<\/span> <span class=\"nn\">io<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">os<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">glob<\/span>\r\n<span class=\"kn\">import<\/span> <span class=\"nn\">shutil<\/span>\r\n\r\n<span class=\"kn\">from<\/span> <span class=\"nn\">elasticsearch<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">Elasticsearch<\/span>\r\n<span class=\"kn\">from<\/span> <span class=\"nn\">google.cloud<\/span> <span class=\"kn\">import<\/span> <span class=\"n\">vision<\/span>\r\n\r\n\r\n<span class=\"k\">def<\/span> <span class=\"nf\">detect_document<\/span><span class=\"p\">(<\/span><span class=\"n\">file_path<\/span><span class=\"p\">):<\/span>\r\n    <span class=\"c1\"># \u7701\u7565\r\n<\/span>\r\n\r\n<span class=\"k\">def<\/span> <span class=\"nf\">es_create<\/span><span class=\"p\">(<\/span><span class=\"n\">doc<\/span><span class=\"p\">):<\/span>\r\n    <span class=\"n\">es<\/span> <span class=\"o\">=<\/span> <span class=\"n\">Elasticsearch<\/span><span class=\"p\">(<\/span><span class=\"s\">'elasticsearch:9200'<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"k\">return<\/span> <span class=\"n\">es<\/span><span class=\"p\">.<\/span><span class=\"n\">index<\/span><span class=\"p\">(<\/span><span class=\"n\">index<\/span><span class=\"o\">=<\/span><span class=\"s\">'document'<\/span><span class=\"p\">,<\/span> <span class=\"n\">document<\/span><span class=\"o\">=<\/span><span class=\"n\">doc<\/span><span class=\"p\">)<\/span>\r\n\r\n\r\n<span class=\"k\">def<\/span> <span class=\"nf\">handler<\/span><span class=\"p\">():<\/span>\r\n    <span class=\"n\">images<\/span> <span class=\"o\">=<\/span> <span class=\"n\">glob<\/span><span class=\"p\">.<\/span><span class=\"n\">glob<\/span><span class=\"p\">(<\/span><span class=\"s\">\".\/images\/input\/*\"<\/span><span class=\"p\">)<\/span>\r\n    <span class=\"k\">for<\/span> <span class=\"n\">file_path<\/span> <span class=\"ow\">in<\/span> <span class=\"n\">images<\/span><span class=\"p\">:<\/span>\r\n        <span class=\"n\">text<\/span> <span class=\"o\">=<\/span> <span class=\"n\">detect_document<\/span><span class=\"p\">(<\/span><span class=\"n\">file_path<\/span><span class=\"p\">)<\/span>\r\n\r\n        <span class=\"n\">doc<\/span> <span class=\"o\">=<\/span> <span class=\"p\">{<\/span>\r\n            <span class=\"s\">'file_name'<\/span><span class=\"p\">:<\/span> <span class=\"n\">os<\/span><span class=\"p\">.<\/span><span class=\"n\">path<\/span><span class=\"p\">.<\/span><span class=\"n\">basename<\/span><span class=\"p\">(<\/span><span class=\"n\">file_path<\/span><span class=\"p\">),<\/span>\r\n            <span class=\"s\">'text'<\/span><span class=\"p\">:<\/span> <span class=\"n\">text<\/span>\r\n        <span class=\"p\">}<\/span>\r\n\r\n        <span class=\"n\">result<\/span> <span class=\"o\">=<\/span> <span class=\"n\">es_create<\/span><span class=\"p\">(<\/span><span class=\"n\">doc<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"k\">print<\/span><span class=\"p\">(<\/span><span class=\"n\">result<\/span><span class=\"p\">)<\/span>\r\n        <span class=\"n\">shutil<\/span><span class=\"p\">.<\/span><span class=\"n\">move<\/span><span class=\"p\">(<\/span><span class=\"n\">file_path<\/span><span class=\"p\">,<\/span> <span class=\"s\">\"images\/archive\/\"<\/span><span class=\"p\">)<\/span>\r\n\r\n\r\n<span class=\"k\">if<\/span> <span class=\"n\">__name__<\/span> <span class=\"o\">==<\/span> <span class=\"s\">\"__main__\"<\/span><span class=\"p\">:<\/span>\r\n    <span class=\"n\">handler<\/span><span class=\"p\">()<\/span>\r\n\r\n<\/code><\/pre>\n<p>\u5b8c\u6210\u6ce8\u518c\u6d41\u7a0b\u540e\uff0c\u5c06\u8981\u6ce8\u518c\u5230ES\u7684\u56fe\u7247\u6587\u4ef6\u653e\u7f6e\u5728src\/images\/input\uff0c\u5e76\u6267\u884c\u4ee5\u4e0b\u547d\u4ee4\u3002<br \/>\n\u672c\u6b21\u5df2\u6ce8\u518c\u4e8610\u5f20wikipedia\u9875\u9762\u7684\u622a\u56fe\u3002<br \/>\n\u5df2\u6ce8\u518c\u7684\u9875\u9762\u5305\u62ecDocker\u3001Python\u3001\u5149\u5b66\u6587\u5b57\u8bc6\u522b\u3001\u5723\u8bde\u65e5\u5386\u3001\u4eba\u5de5\u667a\u80fd\u3001\u86cb\u7cd5\u3001Elasticsearch\u3001\u5723\u8bde\u8282\u3001GCP\u3001\u5723\u8bde\u8001\u4eba\uff01<\/p>\n<p>\u5f53\u6587\u4ef6\u914d\u7f6e\u5b8c\u6210\u540e\uff0c\u8ba9\u6211\u4eec\u518d\u6b21\u6267\u884c\u4e00\u6b21\u8bd5\u8bd5\u770b\u3002<\/p>\n<pre class=\"post-pre\"><code>docker-compose <span class=\"nb\">exec <\/span>python3 python main.py\r\n<span class=\"c\"># \u3053\u306e\u3088\u3046\u306b\u51fa\u529b\u3055\u308c\u3066\u3044\u305f\u3089\u6210\u529f\u3067\u3059<\/span>\r\n<span class=\"o\">{<\/span><span class=\"s1\">'_index'<\/span>: <span class=\"s1\">'document'<\/span>, <span class=\"s1\">'_type'<\/span>: <span class=\"s1\">'_doc'<\/span>, <span class=\"s1\">'_id'<\/span>: <span class=\"s1\">'NaHhyX0BxArSaCGZYWO_'<\/span>, <span class=\"s1\">'_version'<\/span>: 1, <span class=\"s1\">'result'<\/span>: <span class=\"s1\">'created'<\/span>, <span class=\"s1\">'_shards'<\/span>: <span class=\"o\">{<\/span><span class=\"s1\">'total'<\/span>: 2, <span class=\"s1\">'successful'<\/span>: 1, <span class=\"s1\">'failed'<\/span>: 0<span class=\"o\">}<\/span>, <span class=\"s1\">'_seq_no'<\/span>: 0, <span class=\"s1\">'_primary_term'<\/span>: 1<span class=\"o\">}<\/span>\r\n<span class=\"o\">{<\/span><span class=\"s1\">'_index'<\/span>: <span class=\"s1\">'document'<\/span>, <span class=\"s1\">'_type'<\/span>: <span class=\"s1\">'_doc'<\/span>, <span class=\"s1\">'_id'<\/span>: <span class=\"s1\">'NqHhyX0BxArSaCGZi2Nv'<\/span>, <span class=\"s1\">'_version'<\/span>: 1, <span class=\"s1\">'result'<\/span>: <span class=\"s1\">'created'<\/span>, <span class=\"s1\">'_shards'<\/span>: <span class=\"o\">{<\/span><span class=\"s1\">'total'<\/span>: 2, <span class=\"s1\">'successful'<\/span>: 1, <span class=\"s1\">'failed'<\/span>: 0<span class=\"o\">}<\/span>, <span class=\"s1\">'_seq_no'<\/span>: 1, <span class=\"s1\">'_primary_term'<\/span>: 1<span class=\"o\">}<\/span>\r\n<span class=\"o\">{<\/span><span class=\"s1\">'_index'<\/span>: <span class=\"s1\">'document'<\/span>, <span class=\"s1\">'_type'<\/span>: <span class=\"s1\">'_doc'<\/span>, <span class=\"s1\">'_id'<\/span>: <span class=\"s1\">'N6HhyX0BxArSaCGZvWN5'<\/span>, <span class=\"s1\">'_version'<\/span>: 1, <span class=\"s1\">'result'<\/span>: <span class=\"s1\">'created'<\/span>, <span class=\"s1\">'_shards'<\/span>: <span class=\"o\">{<\/span><span class=\"s1\">'total'<\/span>: 2, <span class=\"s1\">'successful'<\/span>: 1, <span class=\"s1\">'failed'<\/span>: 0<span class=\"o\">}<\/span>, <span class=\"s1\">'_seq_no'<\/span>: 2, <span class=\"s1\">'_primary_term'<\/span>: 1<span class=\"o\">}<\/span>\r\n<span class=\"o\">{<\/span><span class=\"s1\">'_index'<\/span>: <span class=\"s1\">'document'<\/span>, <span class=\"s1\">'_type'<\/span>: <span class=\"s1\">'_doc'<\/span>, <span class=\"s1\">'_id'<\/span>: <span class=\"s1\">'OKHhyX0BxArSaCGZ6mM7'<\/span>, <span class=\"s1\">'_version'<\/span>: 1, <span class=\"s1\">'result'<\/span>: <span class=\"s1\">'created'<\/span>, <span class=\"s1\">'_shards'<\/span>: <span class=\"o\">{<\/span><span class=\"s1\">'total'<\/span>: 2, <span class=\"s1\">'successful'<\/span>: 1, <span class=\"s1\">'failed'<\/span>: 0<span class=\"o\">}<\/span>, <span class=\"s1\">'_seq_no'<\/span>: 3, <span class=\"s1\">'_primary_term'<\/span>: 1<span class=\"o\">}<\/span>\r\n<span class=\"o\">{<\/span><span class=\"s1\">'_index'<\/span>: <span class=\"s1\">'document'<\/span>, <span class=\"s1\">'_type'<\/span>: <span class=\"s1\">'_doc'<\/span>, <span class=\"s1\">'_id'<\/span>: <span class=\"s1\">'OaHiyX0BxArSaCGZHmMH'<\/span>, <span class=\"s1\">'_version'<\/span>: 1, <span class=\"s1\">'result'<\/span>: <span class=\"s1\">'created'<\/span>, <span class=\"s1\">'_shards'<\/span>: <span class=\"o\">{<\/span><span class=\"s1\">'total'<\/span>: 2, <span class=\"s1\">'successful'<\/span>: 1, <span class=\"s1\">'failed'<\/span>: 0<span class=\"o\">}<\/span>, <span class=\"s1\">'_seq_no'<\/span>: 4, <span class=\"s1\">'_primary_term'<\/span>: 1<span class=\"o\">}<\/span>\r\n<span class=\"o\">{<\/span><span class=\"s1\">'_index'<\/span>: <span class=\"s1\">'document'<\/span>, <span class=\"s1\">'_type'<\/span>: <span class=\"s1\">'_doc'<\/span>, <span class=\"s1\">'_id'<\/span>: <span class=\"s1\">'OqHiyX0BxArSaCGZK2Mm'<\/span>, <span class=\"s1\">'_version'<\/span>: 1, <span class=\"s1\">'result'<\/span>: <span class=\"s1\">'created'<\/span>, <span class=\"s1\">'_shards'<\/span>: <span class=\"o\">{<\/span><span class=\"s1\">'total'<\/span>: 2, <span class=\"s1\">'successful'<\/span>: 1, <span class=\"s1\">'failed'<\/span>: 0<span class=\"o\">}<\/span>, <span class=\"s1\">'_seq_no'<\/span>: 5, <span class=\"s1\">'_primary_term'<\/span>: 1<span class=\"o\">}<\/span>\r\n<span class=\"o\">{<\/span><span class=\"s1\">'_index'<\/span>: <span class=\"s1\">'document'<\/span>, <span class=\"s1\">'_type'<\/span>: <span class=\"s1\">'_doc'<\/span>, <span class=\"s1\">'_id'<\/span>: <span class=\"s1\">'O6HiyX0BxArSaCGZWGNL'<\/span>, <span class=\"s1\">'_version'<\/span>: 1, <span class=\"s1\">'result'<\/span>: <span class=\"s1\">'created'<\/span>, <span class=\"s1\">'_shards'<\/span>: <span class=\"o\">{<\/span><span class=\"s1\">'total'<\/span>: 2, <span class=\"s1\">'successful'<\/span>: 1, <span class=\"s1\">'failed'<\/span>: 0<span class=\"o\">}<\/span>, <span class=\"s1\">'_seq_no'<\/span>: 6, <span class=\"s1\">'_primary_term'<\/span>: 1<span class=\"o\">}<\/span>\r\n<span class=\"o\">{<\/span><span class=\"s1\">'_index'<\/span>: <span class=\"s1\">'document'<\/span>, <span class=\"s1\">'_type'<\/span>: <span class=\"s1\">'_doc'<\/span>, <span class=\"s1\">'_id'<\/span>: <span class=\"s1\">'PKHiyX0BxArSaCGZhmOv'<\/span>, <span class=\"s1\">'_version'<\/span>: 1, <span class=\"s1\">'result'<\/span>: <span class=\"s1\">'created'<\/span>, <span class=\"s1\">'_shards'<\/span>: <span class=\"o\">{<\/span><span class=\"s1\">'total'<\/span>: 2, <span class=\"s1\">'successful'<\/span>: 1, <span class=\"s1\">'failed'<\/span>: 0<span class=\"o\">}<\/span>, <span class=\"s1\">'_seq_no'<\/span>: 7, <span class=\"s1\">'_primary_term'<\/span>: 1<span class=\"o\">}<\/span>\r\n<span class=\"o\">{<\/span><span class=\"s1\">'_index'<\/span>: <span class=\"s1\">'document'<\/span>, <span class=\"s1\">'_type'<\/span>: <span class=\"s1\">'_doc'<\/span>, <span class=\"s1\">'_id'<\/span>: <span class=\"s1\">'PaHiyX0BxArSaCGZnmMi'<\/span>, <span class=\"s1\">'_version'<\/span>: 1, <span class=\"s1\">'result'<\/span>: <span class=\"s1\">'created'<\/span>, <span class=\"s1\">'_shards'<\/span>: <span class=\"o\">{<\/span><span class=\"s1\">'total'<\/span>: 2, <span class=\"s1\">'successful'<\/span>: 1, <span class=\"s1\">'failed'<\/span>: 0<span class=\"o\">}<\/span>, <span class=\"s1\">'_seq_no'<\/span>: 8, <span class=\"s1\">'_primary_term'<\/span>: 1<span class=\"o\">}<\/span>\r\n<span class=\"o\">{<\/span><span class=\"s1\">'_index'<\/span>: <span class=\"s1\">'document'<\/span>, <span class=\"s1\">'_type'<\/span>: <span class=\"s1\">'_doc'<\/span>, <span class=\"s1\">'_id'<\/span>: <span class=\"s1\">'PqHiyX0BxArSaCGZrGN4'<\/span>, <span class=\"s1\">'_version'<\/span>: 1, <span class=\"s1\">'result'<\/span>: <span class=\"s1\">'created'<\/span>, <span class=\"s1\">'_shards'<\/span>: <span class=\"o\">{<\/span><span class=\"s1\">'total'<\/span>: 2, <span class=\"s1\">'successful'<\/span>: 1, <span class=\"s1\">'failed'<\/span>: 0<span class=\"o\">}<\/span>, <span class=\"s1\">'_seq_no'<\/span>: 9, <span class=\"s1\">'_primary_term'<\/span>: 1<span class=\"o\">}<\/span>\r\n<span class=\"o\">{<\/span><span class=\"s1\">'_index'<\/span>: <span class=\"s1\">'document'<\/span>, <span class=\"s1\">'_type'<\/span>: <span class=\"s1\">'_doc'<\/span>, <span class=\"s1\">'_id'<\/span>: <span class=\"s1\">'P6HiyX0BxArSaCGZ0GPh'<\/span>, <span class=\"s1\">'_version'<\/span>: 1, <span class=\"s1\">'result'<\/span>: <span class=\"s1\">'created'<\/span>, <span class=\"s1\">'_shards'<\/span>: <span class=\"o\">{<\/span><span class=\"s1\">'total'<\/span>: 2, <span class=\"s1\">'successful'<\/span>: 1, <span class=\"s1\">'failed'<\/span>: 0<span class=\"o\">}<\/span>, <span class=\"s1\">'_seq_no'<\/span>: 10, <span class=\"s1\">'_primary_term'<\/span>: 1<span class=\"o\">}<\/span>\r\n<\/code><\/pre>\n<h2>\u4f7f\u7528Elasticsearch\u8fdb\u884c\u641c\u7d22\u3002<\/h2>\n<p>\u6700\u540e\uff0c\u8ba9\u6211\u4eec\u4ece\u5728ES\u7cfb\u7edf\u4e2d\u6ce8\u518c\u7684\u5185\u5bb9\u4e2d\u8fdb\u884c\u5173\u952e\u8bcd\u641c\u7d22\u3002\u9996\u5148\uff0c\u6211\u4eec\u641c\u7d22\u201c\u7f16\u7a0b\u201d\u8fd9\u4e2a\u8bcd\u3002<\/p>\n<pre class=\"post-pre\"><code> <span class=\"o\">&gt;<\/span> curl <span class=\"nt\">-XPOST<\/span> http:\/\/localhost:9200\/document\/_search <span class=\"nt\">-H<\/span> <span class=\"s2\">\"Content-type: application\/json\"<\/span> <span class=\"nt\">-d<\/span> <span class=\"s1\">'{\r\n    \"_source\": \"file_name\",\r\n    \"query\": {\r\n    \"term\": {\r\n      \"text\": \"\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\"\r\n    }\r\n  }\r\n}'<\/span>     \r\n\r\n<span class=\"c\"># \u51fa\u529b<\/span>\r\n<span class=\"o\">{<\/span>\r\n  <span class=\"s2\">\"took\"<\/span>: 5,\r\n  <span class=\"s2\">\"timed_out\"<\/span>: <span class=\"nb\">false<\/span>,\r\n  <span class=\"s2\">\"_shards\"<\/span>: <span class=\"o\">{<\/span>\r\n    <span class=\"s2\">\"total\"<\/span>: 1,\r\n    <span class=\"s2\">\"successful\"<\/span>: 1,\r\n    <span class=\"s2\">\"skipped\"<\/span>: 0,\r\n    <span class=\"s2\">\"failed\"<\/span>: 0\r\n  <span class=\"o\">}<\/span>,\r\n  <span class=\"s2\">\"hits\"<\/span>: <span class=\"o\">{<\/span>\r\n    <span class=\"s2\">\"total\"<\/span>: <span class=\"o\">{<\/span>\r\n      <span class=\"s2\">\"value\"<\/span>: 6,\r\n      <span class=\"s2\">\"relation\"<\/span>: <span class=\"s2\">\"eq\"<\/span>\r\n    <span class=\"o\">}<\/span>,\r\n    <span class=\"s2\">\"max_score\"<\/span>: 1.0072792,\r\n    <span class=\"s2\">\"hits\"<\/span>: <span class=\"o\">[<\/span>\r\n      <span class=\"o\">{<\/span>\r\n        <span class=\"s2\">\"_index\"<\/span>: <span class=\"s2\">\"document\"<\/span>,\r\n        <span class=\"s2\">\"_type\"<\/span>: <span class=\"s2\">\"_doc\"<\/span>,\r\n        <span class=\"s2\">\"_id\"<\/span>: <span class=\"s2\">\"QaHyyX0BxArSaCGZB2Pl\"<\/span>,\r\n        <span class=\"s2\">\"_score\"<\/span>: 1.0072792,\r\n        <span class=\"s2\">\"_ignored\"<\/span>: <span class=\"o\">[<\/span>\r\n          <span class=\"s2\">\"text.keyword\"<\/span>\r\n        <span class=\"o\">]<\/span>,\r\n        <span class=\"s2\">\"_source\"<\/span>: <span class=\"o\">{<\/span>\r\n          <span class=\"s2\">\"file_name\"<\/span>: <span class=\"s2\">\"wiki-python.png\"<\/span>\r\n        <span class=\"o\">}<\/span>\r\n        ...\r\n        <span class=\"s2\">\"_source\"<\/span>: <span class=\"o\">{<\/span>\r\n          <span class=\"s2\">\"file_name\"<\/span>: <span class=\"s2\">\"wiki-advent-calendar.png\"<\/span>\r\n        <span class=\"o\">}<\/span>\r\n        ...\r\n        <span class=\"s2\">\"_source\"<\/span>: <span class=\"o\">{<\/span>\r\n          <span class=\"s2\">\"file_name\"<\/span>: <span class=\"s2\">\"wiki-ai.png\"<\/span>\r\n        <span class=\"o\">}<\/span>\r\n        ...\r\n        <span class=\"s2\">\"_source\"<\/span>: <span class=\"o\">{<\/span>\r\n          <span class=\"s2\">\"file_name\"<\/span>: <span class=\"s2\">\"wiki-gcp.png\"<\/span>\r\n        <span class=\"o\">}<\/span>\r\n        ...\r\n        <span class=\"s2\">\"_source\"<\/span>: <span class=\"o\">{<\/span>\r\n          <span class=\"s2\">\"file_name\"<\/span>: <span class=\"s2\">\"wiki-elasticsearch.png\"<\/span>\r\n        <span class=\"o\">}<\/span>\r\n        ...\r\n        <span class=\"s2\">\"_source\"<\/span>: <span class=\"o\">{<\/span>\r\n          <span class=\"s2\">\"file_name\"<\/span>: <span class=\"s2\">\"wiki-docker.png\"<\/span>\r\n        <span class=\"o\">}<\/span>\r\n      <span class=\"o\">}<\/span>\r\n    <span class=\"o\">]<\/span>\r\n  <span class=\"o\">}<\/span>\r\n<span class=\"o\">}<\/span>\r\n\r\n<\/code><\/pre>\n<p>\u8f93\u51fa\u7ed3\u679c\u4e2d\u51fa\u73b0\u4e86Python\u3001\u5723\u8bde\u5012\u6570\u65e5\u3001\u4eba\u5de5\u667a\u80fd\u3001GCP\u3001Elasticsearch\u3001Docker\u7684\u56fe\u7247\u3002<br \/>\n\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c1d\u8bd5\u4f7f\u7528\u201c\u5723\u8bde\u8282\u201d\u8fd9\u4e2a\u5173\u952e\u8bcd\u8fdb\u884c\u641c\u7d22\u3002<\/p>\n<pre class=\"post-pre\"><code><span class=\"o\">&gt;<\/span> curl <span class=\"nt\">-XPOST<\/span> http:\/\/localhost:9200\/document\/_search <span class=\"nt\">-H<\/span> <span class=\"s2\">\"Content-type: application\/json\"<\/span> <span class=\"nt\">-d<\/span> <span class=\"s1\">'{\r\n    \"_source\": \"file_name\",\r\n    \"query\": {\r\n    \"term\": {\r\n      \"text\": \"\u30af\u30ea\u30b9\u30de\u30b9\"    \r\n    }\r\n  }\r\n}'<\/span>\r\n\r\n<span class=\"c\"># \u51fa\u529b<\/span>\r\n<span class=\"o\">{<\/span>\r\n  <span class=\"s2\">\"took\"<\/span>: 4,\r\n  <span class=\"s2\">\"timed_out\"<\/span>: <span class=\"nb\">false<\/span>,\r\n  <span class=\"s2\">\"_shards\"<\/span>: <span class=\"o\">{<\/span>\r\n    <span class=\"s2\">\"total\"<\/span>: 1,\r\n    <span class=\"s2\">\"successful\"<\/span>: 1,\r\n    <span class=\"s2\">\"skipped\"<\/span>: 0,\r\n    <span class=\"s2\">\"failed\"<\/span>: 0\r\n  <span class=\"o\">}<\/span>,\r\n  <span class=\"s2\">\"hits\"<\/span>: <span class=\"o\">{<\/span>\r\n    <span class=\"s2\">\"total\"<\/span>: <span class=\"o\">{<\/span>\r\n      <span class=\"s2\">\"value\"<\/span>: 2,\r\n      <span class=\"s2\">\"relation\"<\/span>: <span class=\"s2\">\"eq\"<\/span>\r\n    <span class=\"o\">}<\/span>,\r\n    <span class=\"s2\">\"max_score\"<\/span>: 2.8236375,\r\n    <span class=\"s2\">\"hits\"<\/span>: <span class=\"o\">[<\/span>\r\n      <span class=\"o\">{<\/span>\r\n        <span class=\"s2\">\"_index\"<\/span>: <span class=\"s2\">\"document\"<\/span>,\r\n        <span class=\"s2\">\"_type\"<\/span>: <span class=\"s2\">\"_doc\"<\/span>,\r\n        <span class=\"s2\">\"_id\"<\/span>: <span class=\"s2\">\"P6HiyX0BxArSaCGZ0GPh\"<\/span>,\r\n        <span class=\"s2\">\"_score\"<\/span>: 2.8236375,\r\n        <span class=\"s2\">\"_ignored\"<\/span>: <span class=\"o\">[<\/span>\r\n          <span class=\"s2\">\"text.keyword\"<\/span>\r\n        <span class=\"o\">]<\/span>,\r\n        <span class=\"s2\">\"_source\"<\/span>: <span class=\"o\">{<\/span>\r\n          <span class=\"s2\">\"file_path\"<\/span>: <span class=\"s2\">\"wiki-santa.png\"<\/span>\r\n        <span class=\"o\">}<\/span>\r\n        ...\r\n        <span class=\"s2\">\"_source\"<\/span>: <span class=\"o\">{<\/span>\r\n          <span class=\"s2\">\"file_path\"<\/span>: <span class=\"s2\">\"wiki-advent-calendar.png\"<\/span>\r\n        <span class=\"o\">}<\/span>\r\n        ...\r\n        <span class=\"s2\">\"_source\"<\/span>: <span class=\"o\">{<\/span>\r\n          <span class=\"s2\">\"file_path\"<\/span>: <span class=\"s2\">\"wiki-cake.png\"<\/span>\r\n        <span class=\"o\">}<\/span>\r\n      <span class=\"o\">}<\/span>\r\n    <span class=\"o\">]<\/span>\r\n  <span class=\"o\">}<\/span>\r\n<span class=\"o\">}<\/span>\r\n\r\n<\/code><\/pre>\n<p>\u5723\u8bde\u8001\u4eba\uff0c\u5723\u8bde\u8282\u5012\u6570\u65e5\u5386\uff0c\u86cb\u7cd5\uff0c\u8fd9\u662f\u8f93\u51fa\u7ed3\u679c\u3002<br \/>\n\u770b\u8d77\u6765\u83b7\u53d6\u6b63\u786e\uff01<\/p>\n<p>\u8fd9\u6b21\u6211\u4eec\u53ea\u6267\u884c\u4e86\u7b80\u5355\u7684\u5173\u952e\u8bcd\u641c\u7d22\uff0c\u4f46\u662fES\u8fd8\u53ef\u4ee5\u8fdb\u884c\u591a\u5173\u952e\u8bcd\u641c\u7d22\u548c\u5404\u79cd\u6761\u4ef6\u641c\u7d22\u3002<br \/>\n\u4ee5\u4e0a\u662f\u901a\u8fc7OCR\u4ece\u56fe\u50cf\u4e2d\u63d0\u53d6\u6587\u5b57\uff0c\u5c06\u63d0\u53d6\u7684\u6587\u5b57\u6ce8\u518c\u5230Elasticsearch\u4e2d\uff0c\u7136\u540e\u4eceElasticsearch\u4e2d\u4f7f\u7528\u5173\u952e\u8bcd\u641c\u7d22\u83b7\u53d6\u6587\u4ef6\u7684\u5b8c\u6210\u8fc7\u7a0b\uff01<\/p>\n<p>\u5728\u8fd9\u7bc7\u6587\u7ae0\u4e2d\uff0c\u53ea\u8fdb\u884c\u4e86\u4ece\u6613\u4e8e\u8bc6\u522b\u7684\u56fe\u50cf\u6587\u4ef6\u8fdb\u884c\u7b80\u5355\u641c\u7d22\uff0c\u4f46\u5b9e\u9645\u4e0a\uff0c\u5f53\u4f7f\u7528\u6570\u5343\u751a\u81f3\u6570\u4e07\u4e2a\u6587\u4ef6\u8fdb\u884c\u641c\u7d22\u65f6\uff0c\u5f80\u5f80\u65e0\u6cd5\u5f88\u597d\u5730\u8bc6\u522b\uff0c\u4e5f\u65e0\u6cd5\u83b7\u53d6\u6240\u9700\u4fe1\u606f\u3002<br \/>\n\u5728\u8fd9\u79cd\u60c5\u51b5\u4e0b\uff0c\u8bf7\u5c1d\u8bd5\u5bf9\u56fe\u50cf\u8fdb\u884c\u9884\u5904\u7406\uff0c\u5904\u7406\u8bfb\u53d6\u7684\u6587\u5b57\uff0c\u6216\u8005\u5c1d\u8bd5\u5404\u79cd\u641c\u7d22\u65b9\u6cd5\uff0c\u4ee5\u521b\u5efa\u9488\u5bf9\u7279\u5b9a\u7528\u9014\u7684\u641c\u7d22\u5f15\u64ce\u3002<br \/>\nABEJA\u6b63\u5728\u901a\u8fc7\u8bc6\u522b\u6587\u6863\u4e2d\u7684\u56fe\u50cf\uff0c\u68c0\u6d4b\u56fe\u7eb8\u4e2d\u7684\u5404\u4e2a\u90e8\u4ef6\uff0c\u5bf9OCR\u63d0\u53d6\u7684\u6587\u5b57\u8fdb\u884c\u81ea\u7136\u8bed\u8a00\u5904\u7406\uff0c\u6784\u5efa\u66f4\u9ad8\u6027\u80fd\u7684\u641c\u7d22\u5f15\u64ce\uff01<\/p>\n<h2>\u7ed3\u675f<\/h2>\n<p>\u73fe\u5728\u5728ABEJA\u6211\u4eec\u6b63\u5728\u62db\u52df\u4e00\u8d77\u63a8\u8fdb\u4eba\u5de5\u667a\u80fd\u793e\u4f1a\u5b9e\u65bd\u7684\u4f19\u4f34\u3002<br \/>\n\u5982\u679c\u4f60\u5728\u9605\u8bfb\u4e86ABEJA 2021\u5e74\u5723\u8bde\u65e5\u5386\u540e\u5bf9\u6b64\u611f\u5174\u8da3\uff0c\u6211\u4eec\u53ef\u4ee5\u5148\u8fdb\u884c\u4e00\u6b21\u8f7b\u677e\u7684\u4ea4\u8c08\u3002<br \/>\n\u53ef\u4ee5\u4ece\u8fd9\u91cc\u786e\u8ba4\u6211\u4eec\u76ee\u524d\u6b63\u5728\u62db\u8058\u7684\u804c\u4f4d\u3002\u671f\u5f85\u60a8\u7684\u7533\u8bf7\uff01<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u9996\u5148 \u8fd9\u662fABEJA 2021\u5e74\u5723\u8bde\u8282\u65e5\u5386\u7684\u7b2c17\u5929\u7684\u6587\u7ae0\u3002 \u672c\u6587\u4ecb\u7ecd\u4e86\u4f7f\u7528\u8c37\u6b4c\u7684Cloud Vision A [&hellip;]<\/p>\n","protected":false},"author":10,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-41225","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v21.5 (Yoast SEO v21.5) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\u7528OCR\u548cElasticsearch\u521b\u5efa\u56fe\u50cf\u6587\u4ef6\u641c\u7d22\u5f15\u64ce - Blog - Silicon Cloud<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.silicloud.com\/zh\/blog\/\u7528ocr\u548celasticsearch\u521b\u5efa\u56fe\u50cf\u6587\u4ef6\u641c\u7d22\u5f15\u64ce\u3002\/\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"\u7528OCR\u548cElasticsearch\u521b\u5efa\u56fe\u50cf\u6587\u4ef6\u641c\u7d22\u5f15\u64ce\" \/>\n<meta property=\"og:description\" content=\"\u9996\u5148 \u8fd9\u662fABEJA 2021\u5e74\u5723\u8bde\u8282\u65e5\u5386\u7684\u7b2c17\u5929\u7684\u6587\u7ae0\u3002 \u672c\u6587\u4ecb\u7ecd\u4e86\u4f7f\u7528\u8c37\u6b4c\u7684Cloud Vision A [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.silicloud.com\/zh\/blog\/\u7528ocr\u548celasticsearch\u521b\u5efa\u56fe\u50cf\u6587\u4ef6\u641c\u7d22\u5f15\u64ce\u3002\/\" \/>\n<meta property=\"og:site_name\" content=\"Blog - Silicon Cloud\" \/>\n<meta property=\"article:published_time\" content=\"2023-01-18T00:00:16+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-04-28T15:59:35+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d458837434c4406ca2cfb\/25-0.png\" \/>\n<meta name=\"author\" content=\"\u5b87, \u534e\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"\u5b87, \u534e\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"5 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e7%94%a8ocr%e5%92%8celasticsearch%e5%88%9b%e5%bb%ba%e5%9b%be%e5%83%8f%e6%96%87%e4%bb%b6%e6%90%9c%e7%b4%a2%e5%bc%95%e6%93%8e%e3%80%82\/\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e7%94%a8ocr%e5%92%8celasticsearch%e5%88%9b%e5%bb%ba%e5%9b%be%e5%83%8f%e6%96%87%e4%bb%b6%e6%90%9c%e7%b4%a2%e5%bc%95%e6%93%8e%e3%80%82\/\",\"name\":\"\u7528OCR\u548cElasticsearch\u521b\u5efa\u56fe\u50cf\u6587\u4ef6\u641c\u7d22\u5f15\u64ce - Blog - Silicon Cloud\",\"isPartOf\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\"},\"datePublished\":\"2023-01-18T00:00:16+00:00\",\"dateModified\":\"2024-04-28T15:59:35+00:00\",\"author\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/513018e4e121d3add1b7c5de8be21458\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e7%94%a8ocr%e5%92%8celasticsearch%e5%88%9b%e5%bb%ba%e5%9b%be%e5%83%8f%e6%96%87%e4%bb%b6%e6%90%9c%e7%b4%a2%e5%bc%95%e6%93%8e%e3%80%82\/#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.silicloud.com\/zh\/blog\/%e7%94%a8ocr%e5%92%8celasticsearch%e5%88%9b%e5%bb%ba%e5%9b%be%e5%83%8f%e6%96%87%e4%bb%b6%e6%90%9c%e7%b4%a2%e5%bc%95%e6%93%8e%e3%80%82\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e7%94%a8ocr%e5%92%8celasticsearch%e5%88%9b%e5%bb%ba%e5%9b%be%e5%83%8f%e6%96%87%e4%bb%b6%e6%90%9c%e7%b4%a2%e5%bc%95%e6%93%8e%e3%80%82\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.silicloud.com\/zh\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u7528OCR\u548cElasticsearch\u521b\u5efa\u56fe\u50cf\u6587\u4ef6\u641c\u7d22\u5f15\u64ce\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#website\",\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/\",\"name\":\"Blog - Silicon Cloud\",\"description\":\"\",\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/513018e4e121d3add1b7c5de8be21458\",\"name\":\"\u5b87, \u534e\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/63cd45cbc05a35fc4ff7637a163c83c4962ef58d27472726c3a3e0c9c5194f0f?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/63cd45cbc05a35fc4ff7637a163c83c4962ef58d27472726c3a3e0c9c5194f0f?s=96&d=mm&r=g\",\"caption\":\"\u5b87, \u534e\"},\"url\":\"https:\/\/www.silicloud.com\/zh\/blog\/author\/yuhua\/\"},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.silicloud.com\/zh\/blog\/%e7%94%a8ocr%e5%92%8celasticsearch%e5%88%9b%e5%bb%ba%e5%9b%be%e5%83%8f%e6%96%87%e4%bb%b6%e6%90%9c%e7%b4%a2%e5%bc%95%e6%93%8e%e3%80%82\/#local-main-organization-logo\",\"url\":\"\",\"contentUrl\":\"\",\"caption\":\"Blog - Silicon Cloud\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"\u7528OCR\u548cElasticsearch\u521b\u5efa\u56fe\u50cf\u6587\u4ef6\u641c\u7d22\u5f15\u64ce - Blog - Silicon Cloud","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.silicloud.com\/zh\/blog\/\u7528ocr\u548celasticsearch\u521b\u5efa\u56fe\u50cf\u6587\u4ef6\u641c\u7d22\u5f15\u64ce\u3002\/","og_locale":"zh_CN","og_type":"article","og_title":"\u7528OCR\u548cElasticsearch\u521b\u5efa\u56fe\u50cf\u6587\u4ef6\u641c\u7d22\u5f15\u64ce","og_description":"\u9996\u5148 \u8fd9\u662fABEJA 2021\u5e74\u5723\u8bde\u8282\u65e5\u5386\u7684\u7b2c17\u5929\u7684\u6587\u7ae0\u3002 \u672c\u6587\u4ecb\u7ecd\u4e86\u4f7f\u7528\u8c37\u6b4c\u7684Cloud Vision A [&hellip;]","og_url":"https:\/\/www.silicloud.com\/zh\/blog\/\u7528ocr\u548celasticsearch\u521b\u5efa\u56fe\u50cf\u6587\u4ef6\u641c\u7d22\u5f15\u64ce\u3002\/","og_site_name":"Blog - Silicon Cloud","article_published_time":"2023-01-18T00:00:16+00:00","article_modified_time":"2024-04-28T15:59:35+00:00","og_image":[{"url":"https:\/\/cdn.silicloud.com\/blog-img\/blog\/img\/657d458837434c4406ca2cfb\/25-0.png"}],"author":"\u5b87, \u534e","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"\u5b87, \u534e","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"5 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e7%94%a8ocr%e5%92%8celasticsearch%e5%88%9b%e5%bb%ba%e5%9b%be%e5%83%8f%e6%96%87%e4%bb%b6%e6%90%9c%e7%b4%a2%e5%bc%95%e6%93%8e%e3%80%82\/","url":"https:\/\/www.silicloud.com\/zh\/blog\/%e7%94%a8ocr%e5%92%8celasticsearch%e5%88%9b%e5%bb%ba%e5%9b%be%e5%83%8f%e6%96%87%e4%bb%b6%e6%90%9c%e7%b4%a2%e5%bc%95%e6%93%8e%e3%80%82\/","name":"\u7528OCR\u548cElasticsearch\u521b\u5efa\u56fe\u50cf\u6587\u4ef6\u641c\u7d22\u5f15\u64ce - Blog - Silicon Cloud","isPartOf":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website"},"datePublished":"2023-01-18T00:00:16+00:00","dateModified":"2024-04-28T15:59:35+00:00","author":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/513018e4e121d3add1b7c5de8be21458"},"breadcrumb":{"@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e7%94%a8ocr%e5%92%8celasticsearch%e5%88%9b%e5%bb%ba%e5%9b%be%e5%83%8f%e6%96%87%e4%bb%b6%e6%90%9c%e7%b4%a2%e5%bc%95%e6%93%8e%e3%80%82\/#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.silicloud.com\/zh\/blog\/%e7%94%a8ocr%e5%92%8celasticsearch%e5%88%9b%e5%bb%ba%e5%9b%be%e5%83%8f%e6%96%87%e4%bb%b6%e6%90%9c%e7%b4%a2%e5%bc%95%e6%93%8e%e3%80%82\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e7%94%a8ocr%e5%92%8celasticsearch%e5%88%9b%e5%bb%ba%e5%9b%be%e5%83%8f%e6%96%87%e4%bb%b6%e6%90%9c%e7%b4%a2%e5%bc%95%e6%93%8e%e3%80%82\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.silicloud.com\/zh\/blog\/"},{"@type":"ListItem","position":2,"name":"\u7528OCR\u548cElasticsearch\u521b\u5efa\u56fe\u50cf\u6587\u4ef6\u641c\u7d22\u5f15\u64ce"}]},{"@type":"WebSite","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#website","url":"https:\/\/www.silicloud.com\/zh\/blog\/","name":"Blog - Silicon Cloud","description":"","inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/513018e4e121d3add1b7c5de8be21458","name":"\u5b87, \u534e","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/63cd45cbc05a35fc4ff7637a163c83c4962ef58d27472726c3a3e0c9c5194f0f?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/63cd45cbc05a35fc4ff7637a163c83c4962ef58d27472726c3a3e0c9c5194f0f?s=96&d=mm&r=g","caption":"\u5b87, \u534e"},"url":"https:\/\/www.silicloud.com\/zh\/blog\/author\/yuhua\/"},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.silicloud.com\/zh\/blog\/%e7%94%a8ocr%e5%92%8celasticsearch%e5%88%9b%e5%bb%ba%e5%9b%be%e5%83%8f%e6%96%87%e4%bb%b6%e6%90%9c%e7%b4%a2%e5%bc%95%e6%93%8e%e3%80%82\/#local-main-organization-logo","url":"","contentUrl":"","caption":"Blog - Silicon Cloud"}]}},"_links":{"self":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/41225","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/users\/10"}],"replies":[{"embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/comments?post=41225"}],"version-history":[{"count":2,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/41225\/revisions"}],"predecessor-version":[{"id":66727,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/posts\/41225\/revisions\/66727"}],"wp:attachment":[{"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/media?parent=41225"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/categories?post=41225"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.silicloud.com\/zh\/blog\/wp-json\/wp\/v2\/tags?post=41225"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}