{"id":475803,"date":"2023-08-09T07:23:51","date_gmt":"2023-08-09T07:23:51","guid":{"rendered":""},"modified":"2023-09-05T11:11:15","modified_gmt":"2023-09-05T11:11:15","slug":"adaboost","status":"publish","type":"wiki","link":"https:\/\/oneproxy.pro\/cn\/wiki\/adaboost\/","title":{"rendered":"\u81ea\u9002\u5e94\u589e\u5f3a\u7b97\u6cd5"},"content":{"rendered":"<p>AdaBoost \u662f Adaptive Boosting \u7684\u7f29\u5199\uff0c\u662f\u4e00\u79cd\u5f3a\u5927\u7684\u96c6\u6210\u5b66\u4e60\u7b97\u6cd5\uff0c\u5b83\u7ed3\u5408\u4e86\u591a\u4e2a\u57fa\u7840\u6216\u5f31\u5b66\u4e60\u8005\u7684\u51b3\u7b56\uff0c\u4ee5\u63d0\u9ad8\u9884\u6d4b\u6027\u80fd\u3002\u5b83\u7528\u4e8e\u673a\u5668\u5b66\u4e60\u3001\u6570\u636e\u79d1\u5b66\u548c\u6a21\u5f0f\u8bc6\u522b\u7b49\u5404\u4e2a\u9886\u57df\uff0c\u6709\u52a9\u4e8e\u505a\u51fa\u51c6\u786e\u7684\u9884\u6d4b\u548c\u5206\u7c7b\u3002<\/p>\n<h2>AdaBoost \u7684\u8d77\u6e90<\/h2>\n<p>AdaBoost \u6700\u521d\u7531 Yoav Freund \u548c Robert Schapire \u4e8e 1996 \u5e74\u63d0\u51fa\u3002\u4ed6\u4eec\u7684\u539f\u59cb\u8bba\u6587\u300a\u5728\u7ebf\u5b66\u4e60\u7684\u51b3\u7b56\u7406\u8bba\u6982\u62ec\u53ca\u5176\u5728 Boosting \u4e2d\u7684\u5e94\u7528\u300b\u4e3a Boosting \u6280\u672f\u5960\u5b9a\u4e86\u57fa\u7840\u3002Boosting \u7684\u6982\u5ff5\u5728\u4ed6\u4eec\u7684\u5de5\u4f5c\u4e4b\u524d\u5c31\u5df2\u7ecf\u5b58\u5728\uff0c\u4f46\u7531\u4e8e\u5176\u7406\u8bba\u6027\u8d28\u548c\u7f3a\u4e4f\u5b9e\u9645\u5b9e\u65bd\uff0c\u56e0\u6b64\u5e76\u672a\u5f97\u5230\u5e7f\u6cdb\u5e94\u7528\u3002Freund \u548c Schapire \u7684\u8bba\u6587\u5c06\u7406\u8bba\u6982\u5ff5\u8f6c\u5316\u4e3a\u5b9e\u7528\u4e14\u9ad8\u6548\u7684\u7b97\u6cd5\uff0c\u8fd9\u5c31\u662f\u4e3a\u4ec0\u4e48\u4ed6\u4eec\u7ecf\u5e38\u88ab\u8a89\u4e3a AdaBoost \u7684\u521b\u59cb\u4eba\u3002<\/p>\n<h2>\u6df1\u5165\u4e86\u89e3 AdaBoost<\/h2>\n<p>AdaBoost \u5efa\u7acb\u5728\u96c6\u6210\u5b66\u4e60\u7684\u539f\u7406\u4e4b\u4e0a\uff0c\u5373\u5c06\u591a\u4e2a\u5f31\u5b66\u4e60\u5668\u7ec4\u5408\u8d77\u6765\u5f62\u6210\u4e00\u4e2a\u5f3a\u5b66\u4e60\u5668\u3002\u8fd9\u4e9b\u5f31\u5b66\u4e60\u5668\uff08\u901a\u5e38\u662f\u51b3\u7b56\u6811\uff09\u7684\u9519\u8bef\u7387\u7565\u4f4e\u4e8e\u968f\u673a\u731c\u6d4b\u3002\u8be5\u8fc7\u7a0b\u4ee5\u8fed\u4ee3\u65b9\u5f0f\u8fdb\u884c\uff0c\u9996\u5148\u4e3a\u6570\u636e\u96c6\u4e2d\u7684\u6240\u6709\u5b9e\u4f8b\u5206\u914d\u76f8\u540c\u7684\u6743\u91cd\u3002\u6bcf\u6b21\u8fed\u4ee3\u540e\uff0c\u9519\u8bef\u5206\u7c7b\u7684\u5b9e\u4f8b\u7684\u6743\u91cd\u90fd\u4f1a\u589e\u52a0\uff0c\u6b63\u786e\u5206\u7c7b\u7684\u5b9e\u4f8b\u7684\u6743\u91cd\u4f1a\u964d\u4f4e\u3002\u8fd9\u8feb\u4f7f\u4e0b\u4e00\u4e2a\u5206\u7c7b\u5668\u66f4\u591a\u5730\u5173\u6ce8\u9519\u8bef\u5206\u7c7b\u7684\u5b9e\u4f8b\uff0c\u56e0\u6b64\u6709\u201c\u81ea\u9002\u5e94\u201d\u4e00\u8bcd\u3002<\/p>\n<p>\u6700\u7ec8\u51b3\u7b56\u662f\u901a\u8fc7\u52a0\u6743\u591a\u6570\u6295\u7968\u505a\u51fa\u7684\uff0c\u5176\u4e2d\u6bcf\u4e2a\u5206\u7c7b\u5668\u7684\u6295\u7968\u90fd\u7531\u5176\u51c6\u786e\u6027\u52a0\u6743\u3002\u8fd9\u4f7f\u5f97 AdaBoost \u80fd\u591f\u62b5\u5fa1\u8fc7\u5ea6\u62df\u5408\uff0c\u56e0\u4e3a\u6700\u7ec8\u9884\u6d4b\u662f\u57fa\u4e8e\u6240\u6709\u5206\u7c7b\u5668\u7684\u96c6\u4f53\u8868\u73b0\u800c\u4e0d\u662f\u5355\u4e2a\u5206\u7c7b\u5668\u7684\u8868\u73b0\u505a\u51fa\u7684\u3002<\/p>\n<h2>AdaBoost \u7684\u5185\u90e8\u5de5\u4f5c\u539f\u7406<\/h2>\n<p>AdaBoost \u7b97\u6cd5\u4e3b\u8981\u5206\u4e3a\u56db\u4e2a\u6b65\u9aa4\uff1a<\/p>\n<ol>\n<li>\u9996\u5148\uff0c\u4e3a\u6570\u636e\u96c6\u4e2d\u7684\u6240\u6709\u5b9e\u4f8b\u5206\u914d\u76f8\u540c\u7684\u6743\u91cd\u3002<\/li>\n<li>\u5728\u6570\u636e\u96c6\u4e0a\u8bad\u7ec3\u5f31\u5b66\u4e60\u8005\u3002<\/li>\n<li>\u6839\u636e\u5f31\u5b66\u4e60\u5668\u7684\u9519\u8bef\u6765\u66f4\u65b0\u5b9e\u4f8b\u7684\u6743\u91cd\u3002\u5206\u7c7b\u9519\u8bef\u7684\u5b9e\u4f8b\u4f1a\u83b7\u5f97\u66f4\u9ad8\u7684\u6743\u91cd\u3002<\/li>\n<li>\u91cd\u590d\u6b65\u9aa4 2 \u548c 3\uff0c\u76f4\u5230\u8bad\u7ec3\u5b8c\u9884\u5b9a\u4e49\u6570\u91cf\u7684\u5f31\u5b66\u4e60\u8005\uff0c\u6216\u8005\u8bad\u7ec3\u6570\u636e\u96c6\u65e0\u6cd5\u5f97\u5230\u4efb\u4f55\u6539\u8fdb\u3002<\/li>\n<li>\u4e3a\u4e86\u505a\u51fa\u9884\u6d4b\uff0c\u6bcf\u4e2a\u5f31\u5b66\u4e60\u8005\u90fd\u4f1a\u505a\u51fa\u9884\u6d4b\uff0c\u6700\u7ec8\u7684\u9884\u6d4b\u7531\u52a0\u6743\u591a\u6570\u6295\u7968\u51b3\u5b9a\u3002<\/li>\n<\/ol>\n<h2>AdaBoost \u7684\u4e3b\u8981\u7279\u70b9<\/h2>\n<p>AdaBoost \u7684\u4e00\u4e9b\u663e\u8457\u7279\u70b9\u662f\uff1a<\/p>\n<ul>\n<li>\u5b83\u901f\u5ea6\u5feb\u3001\u7b80\u5355\u5e76\u4e14\u6613\u4e8e\u7f16\u7a0b\u3002<\/li>\n<li>\u5b83\u4e0d\u9700\u8981\u5173\u4e8e\u5f31\u5b66\u4e60\u8005\u7684\u5148\u9a8c\u77e5\u8bc6\u3002<\/li>\n<li>\u5b83\u7528\u9014\u5e7f\u6cdb\uff0c\u53ef\u4ee5\u4e0e\u4efb\u4f55\u5b66\u4e60\u7b97\u6cd5\u76f8\u7ed3\u5408\u3002<\/li>\n<li>\u5b83\u53ef\u4ee5\u62b5\u6297\u8fc7\u5ea6\u62df\u5408\uff0c\u5c24\u5176\u662f\u5728\u4f7f\u7528\u4f4e\u566a\u58f0\u6570\u636e\u65f6\u3002<\/li>\n<li>\u5b83\u6267\u884c\u7279\u5f81\u9009\u62e9\uff0c\u66f4\u52a0\u5173\u6ce8\u91cd\u8981\u7279\u5f81\u3002<\/li>\n<li>\u5b83\u5bf9\u566a\u58f0\u6570\u636e\u548c\u5f02\u5e38\u503c\u5f88\u654f\u611f\u3002<\/li>\n<\/ul>\n<h2>AdaBoost \u7684\u7c7b\u578b<\/h2>\n<p>AdaBoost \u6709\u51e0\u79cd\u53d8\u4f53\uff0c\u5305\u62ec\uff1a<\/p>\n<ol>\n<li><strong>\u79bb\u6563 AdaBoost\uff08AdaBoost.M1\uff09<\/strong>\uff1a\u539f\u59cb\u7684AdaBoost\uff0c\u7528\u4e8e\u4e8c\u5143\u5206\u7c7b\u95ee\u9898\u3002<\/li>\n<li><strong>\u771f\u6b63\u7684 AdaBoost (AdaBoost.R)<\/strong>\uff1aAdaBoost.M1 \u7684\u4fee\u6539\uff0c\u5176\u4e2d\u5f31\u5b66\u4e60\u8005\u8fd4\u56de\u5b9e\u503c\u9884\u6d4b\u3002<\/li>\n<li><strong>\u6e29\u548c\u7684 AdaBoost<\/strong>\uff1aAdaBoost \u7684\u8f83\u4f4e\u6fc0\u8fdb\u7248\u672c\uff0c\u5bf9\u5b9e\u4f8b\u6743\u91cd\u8fdb\u884c\u8f83\u5c0f\u7684\u8c03\u6574\u3002<\/li>\n<li><strong>\u5e26\u6709\u51b3\u7b56\u6811\u6869\u7684 AdaBoost<\/strong>\uff1aAdaBoost \u91c7\u7528\u51b3\u7b56\u6811\u6869\uff08\u5355\u7ea7\u51b3\u7b56\u6811\uff09\u4f5c\u4e3a\u5f31\u5b66\u4e60\u8005\u3002<\/li>\n<\/ol>\n<table>\n<thead>\n<tr>\n<th>AdaBoost \u7684\u7c7b\u578b<\/th>\n<th>\u63cf\u8ff0<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>\u79bb\u6563 AdaBoost\uff08AdaBoost.M1\uff09<\/td>\n<td>\u539f\u59cb AdaBoost \u7528\u4e8e\u4e8c\u5143\u5206\u7c7b<\/td>\n<\/tr>\n<tr>\n<td>\u771f\u6b63\u7684 AdaBoost (AdaBoost.R)<\/td>\n<td>\u4fee\u6539 AdaBoost.M1\uff0c\u8fd4\u56de\u5b9e\u503c\u9884\u6d4b<\/td>\n<\/tr>\n<tr>\n<td>\u6e29\u548c\u7684 AdaBoost<\/td>\n<td>\u4e00\u4e2a\u4e0d\u90a3\u4e48\u6fc0\u8fdb\u7684 AdaBoost \u7248\u672c<\/td>\n<\/tr>\n<tr>\n<td>\u5e26\u6709\u51b3\u7b56\u6811\u6869\u7684 AdaBoost<\/td>\n<td>AdaBoost \u4f7f\u7528\u51b3\u7b56\u6811\u6869\u4f5c\u4e3a\u5f31\u5b66\u4e60\u8005<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>\u4f7f\u7528 AdaBoost \u7684\u65b9\u6cd5<\/h2>\n<p>AdaBoost \u5e7f\u6cdb\u5e94\u7528\u4e8e\u4e8c\u5143\u5206\u7c7b\u95ee\u9898\uff0c\u4f8b\u5982\u5783\u573e\u90ae\u4ef6\u68c0\u6d4b\u3001\u5ba2\u6237\u6d41\u5931\u9884\u6d4b\u3001\u75be\u75c5\u68c0\u6d4b\u7b49\u3002\u867d\u7136 AdaBoost \u662f\u4e00\u79cd\u7a33\u5065\u7684\u7b97\u6cd5\uff0c\u4f46\u5b83\u5bf9\u566a\u58f0\u6570\u636e\u548c\u5f02\u5e38\u503c\u5f88\u654f\u611f\u3002\u5b83\u4e5f\u662f\u8ba1\u7b97\u5bc6\u96c6\u578b\u7684\uff0c\u5c24\u5176\u662f\u5bf9\u4e8e\u5927\u578b\u6570\u636e\u96c6\u3002\u53ef\u4ee5\u901a\u8fc7\u6267\u884c\u6570\u636e\u9884\u5904\u7406\u4ee5\u6d88\u9664\u566a\u58f0\u548c\u5f02\u5e38\u503c\u5e76\u4f7f\u7528\u5e76\u884c\u8ba1\u7b97\u8d44\u6e90\u6765\u5904\u7406\u5927\u578b\u6570\u636e\u96c6\u6765\u89e3\u51b3\u8fd9\u4e9b\u95ee\u9898\u3002<\/p>\n<h2>AdaBoost \u6bd4\u8f83<\/h2>\n<p>\u4ee5\u4e0b\u662f AdaBoost \u4e0e\u7c7b\u4f3c\u96c6\u6210\u65b9\u6cd5\u7684\u6bd4\u8f83\uff1a<\/p>\n<table>\n<thead>\n<tr>\n<th>\u65b9\u6cd5<\/th>\n<th>\u4f18\u52bf<\/th>\n<th>\u5f31\u70b9<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>\u81ea\u9002\u5e94\u589e\u5f3a\u7b97\u6cd5<\/td>\n<td>\u901f\u5ea6\u5feb\uff0c\u4e0d\u6613\u8fc7\u5ea6\u62df\u5408\uff0c\u53ef\u8fdb\u884c\u7279\u5f81\u9009\u62e9<\/td>\n<td>\u5bf9\u566a\u58f0\u6570\u636e\u548c\u5f02\u5e38\u503c\u654f\u611f<\/td>\n<\/tr>\n<tr>\n<td>\u5957\u888b<\/td>\n<td>\u51cf\u5c11\u65b9\u5dee\uff0c\u4e0d\u6613\u8fc7\u5ea6\u62df\u5408<\/td>\n<td>\u4e0d\u6267\u884c\u7279\u5f81\u9009\u62e9<\/td>\n<\/tr>\n<tr>\n<td>\u68af\u5ea6\u63d0\u5347<\/td>\n<td>\u5f3a\u5927\u800c\u7075\u6d3b\uff0c\u53ef\u4ee5\u9488\u5bf9\u4e0d\u540c\u7684\u635f\u5931\u51fd\u6570\u8fdb\u884c\u4f18\u5316<\/td>\n<td>\u5bb9\u6613\u8fc7\u5ea6\u62df\u5408\uff0c\u9700\u8981\u4ed4\u7ec6\u8c03\u6574\u53c2\u6570<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>\u4e0e AdaBoost \u76f8\u5173\u7684\u672a\u6765\u5c55\u671b<\/h2>\n<p>\u968f\u7740\u673a\u5668\u5b66\u4e60\u7684\u4e0d\u65ad\u53d1\u5c55\uff0cAdaBoost \u7684\u539f\u7406\u6b63\u5728\u5e94\u7528\u4e8e\u66f4\u590d\u6742\u7684\u6a21\u578b\uff0c\u4f8b\u5982\u6df1\u5ea6\u5b66\u4e60\u3002\u672a\u6765\u7684\u53d1\u5c55\u65b9\u5411\u53ef\u80fd\u5305\u62ec\u5c06 AdaBoost \u4e0e\u5176\u4ed6\u5f3a\u5927\u7b97\u6cd5\u76f8\u7ed3\u5408\u7684\u6df7\u5408\u6a21\u578b\uff0c\u4ee5\u63d0\u4f9b\u66f4\u597d\u7684\u6027\u80fd\u3002\u6b64\u5916\uff0c\u5728\u5927\u6570\u636e\u548c\u5b9e\u65f6\u5206\u6790\u4e2d\u4f7f\u7528 AdaBoost \u53ef\u80fd\u4f1a\u8fdb\u4e00\u6b65\u63a8\u52a8\u8be5\u6280\u672f\u7684\u8fdb\u6b65\u3002<\/p>\n<h2>\u4ee3\u7406\u670d\u52a1\u5668\u548c AdaBoost<\/h2>\n<p>\u4ee3\u7406\u670d\u52a1\u5668\u5728 AdaBoost \u5e94\u7528\u7a0b\u5e8f\u7684\u6570\u636e\u6536\u96c6\u4e2d\u53d1\u6325\u7740\u91cd\u8981\u4f5c\u7528\u3002\u4f8b\u5982\uff0c\u5728\u7528\u4e8e\u8bad\u7ec3 AdaBoost \u6a21\u578b\u7684 Web \u6293\u53d6\u4efb\u52a1\u4e2d\uff0c\u4ee3\u7406\u670d\u52a1\u5668\u53ef\u4ee5\u5e2e\u52a9\u7ed5\u8fc7 IP \u963b\u6b62\u548c\u901f\u7387\u9650\u5236\uff0c\u786e\u4fdd\u6570\u636e\u7684\u6301\u7eed\u4f9b\u5e94\u3002\u6b64\u5916\uff0c\u5728\u5206\u5e03\u5f0f\u673a\u5668\u5b66\u4e60\u573a\u666f\u4e2d\uff0c\u4ee3\u7406\u670d\u52a1\u5668\u53ef\u7528\u4e8e\u4fc3\u8fdb\u5b89\u5168\u3001\u5feb\u901f\u7684\u6570\u636e\u4ea4\u6362\u3002<\/p>\n<h2>\u76f8\u5173\u94fe\u63a5<\/h2>\n<p>\u6709\u5173 AdaBoost \u7684\u66f4\u591a\u4fe1\u606f\uff0c\u53ef\u4ee5\u53c2\u8003\u4ee5\u4e0b\u8d44\u6e90\uff1a<\/p>\n<ol>\n<li><a href=\"http:\/\/cseweb.ucsd.edu\/~yfreund\/papers\/IntroToBoosting.pdf\" target=\"_new\" rel=\"noopener nofollow\">\u5728\u7ebf\u5b66\u4e60\u7684\u51b3\u7b56\u7406\u8bba\u6982\u62ec\u53ca\u5176\u5728 Boosting \u4e2d\u7684\u5e94\u7528 \u2013 Freund \u548c Schapire \u7684\u539f\u59cb\u8bba\u6587<\/a><\/li>\n<li><a href=\"https:\/\/www.amazon.com\/Boosting-Foundations-Algorithms-Adaptive-Computation\/dp\/0262017180\" target=\"_new\" rel=\"noopener nofollow\">Boosting\uff1a\u57fa\u7840\u4e0e\u7b97\u6cd5 \u2013 Robert Schapire \u548c Yoav Freund \u8457<\/a><\/li>\n<li><a href=\"https:\/\/www.cs.princeton.edu\/courses\/archive\/spring07\/cos424\/papers\/boosting-survey.pdf\" target=\"_new\" rel=\"noopener nofollow\">Adaboost \u6559\u7a0b \u2013 \u666e\u6797\u65af\u987f\u5927\u5b66<\/a><\/li>\n<li><a href=\"https:\/\/towardsdatascience.com\/understanding-adaboost-2f94f22d5bfe\" target=\"_new\" rel=\"noopener nofollow\">\u7406\u89e3 AdaBoost \u2013 \u9762\u5411\u6570\u636e\u79d1\u5b66\u7684\u6587\u7ae0<\/a><\/li>\n<\/ol>","protected":false},"featured_media":467478,"menu_order":0,"template":"","meta":{"_acf_changed":false,"content-type":"","inline_featured_image":false,"footnotes":""},"class_list":["post-475803","wiki","type-wiki","status-publish","has-post-thumbnail","hentry"],"acf":{"faq_title":"Frequently Asked Questions about <mark>AdaBoost: A Powerful Ensemble Learning Technique<\/mark>","faq_items":[{"question":"What is AdaBoost?","answer":"<p>AdaBoost, short for Adaptive Boosting, is a machine learning algorithm that combines the decisions from multiple weak or base learners to improve the predictive performance. It is commonly used in various domains like data science, pattern recognition, and machine learning.<\/p>"},{"question":"Who introduced AdaBoost?","answer":"<p>AdaBoost was introduced by Yoav Freund and Robert Schapire in 1996. Their research work transformed the theoretical concept of boosting into a practical and efficient algorithm.<\/p>"},{"question":"How does AdaBoost work?","answer":"<p>AdaBoost works by assigning equal weights to all instances in the dataset initially. It then trains a weak learner and updates the weights based on the errors made. The process is repeated until a specified number of weak learners have been trained, or no improvement can be made on the training dataset. Final predictions are made through a weighted majority vote.<\/p>"},{"question":"What are the key features of AdaBoost?","answer":"<p>Key features of AdaBoost include its speed, simplicity, and versatility. It does not require any prior knowledge about the weak learners, it performs feature selection, and it is resistant to overfitting. However, it can be sensitive to noisy data and outliers.<\/p>"},{"question":"What types of AdaBoost exist?","answer":"<p>Several variations of AdaBoost exist, including Discrete AdaBoost (AdaBoost.M1), Real AdaBoost (AdaBoost.R), Gentle AdaBoost, and AdaBoost with Decision Stumps. Each type has a slightly different approach, but all follow the basic principle of combining multiple weak learners to create a strong classifier.<\/p>"},{"question":"How is AdaBoost used and what problems can occur?","answer":"<p>AdaBoost is used in binary classification problems such as spam detection, customer churn prediction, and disease detection. It can be sensitive to noisy data and outliers and can be computationally intensive for large datasets. Preprocessing of data to remove noise and outliers and utilizing parallel computing resources can mitigate these issues.<\/p>"},{"question":"How does AdaBoost compare with similar methods?","answer":"<p>AdaBoost is fast and less prone to overfitting compared to other ensemble methods like Bagging and Gradient Boosting. It also performs feature selection, unlike Bagging. However, it is more sensitive to noisy data and outliers.<\/p>"},{"question":"What are the future perspectives related to AdaBoost?","answer":"<p>In the future, AdaBoost may be applied to more complex models such as deep learning. Hybrid models combining AdaBoost with other algorithms could also be developed for improved performance. Also, its use in Big Data and real-time analytics could drive further advancements.<\/p>"},{"question":"How are proxy servers associated with AdaBoost?","answer":"<p>Proxy servers can be used in data collection for AdaBoost applications, such as in web scraping tasks to gather training data. Proxy servers can help bypass IP blocking and rate limits, ensuring a continuous supply of data. In distributed machine learning, proxy servers can facilitate secure and fast data exchanges.<\/p>"}]},"_links":{"self":[{"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/wiki\/475803","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/wiki"}],"about":[{"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/types\/wiki"}],"version-history":[{"count":0,"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/wiki\/475803\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/media\/467478"}],"wp:attachment":[{"href":"https:\/\/oneproxy.pro\/cn\/wp-json\/wp\/v2\/media?parent=475803"}],"curies":[{"name":"\u53ef\u6e7f\u6027\u7c89\u5242","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}