{"id":2073,"date":"2025-04-03T07:47:00","date_gmt":"2025-04-02T23:47:00","guid":{"rendered":"https:\/\/blog.laoyulaoyu.top\/?p=2073"},"modified":"2025-03-16T14:20:49","modified_gmt":"2025-03-16T06:20:49","slug":"ai%e9%a2%84%e6%b5%8b%e6%b6%a8%e8%b7%8c%e8%b6%85%e5%87%86%ef%bc%81%e8%bf%99%e4%ba%94%e4%b8%aa%e6%99%ba%e8%83%bd%e9%87%8f%e5%8c%96%e6%8c%87%e6%a0%87%e4%bb%a3%e7%a0%81%e5%ae%9e%e6%88%98%ef%bc%8c","status":"publish","type":"post","link":"https:\/\/laoyulaoyu.com\/index.php\/2025\/04\/03\/ai%e9%a2%84%e6%b5%8b%e6%b6%a8%e8%b7%8c%e8%b6%85%e5%87%86%ef%bc%81%e8%bf%99%e4%ba%94%e4%b8%aa%e6%99%ba%e8%83%bd%e9%87%8f%e5%8c%96%e6%8c%87%e6%a0%87%e4%bb%a3%e7%a0%81%e5%ae%9e%e6%88%98%ef%bc%8c\/","title":{"rendered":"AI\u9884\u6d4b\u6da8\u8dcc\u8d85\u51c6\uff01\u8fd9\u4e94\u4e2a\u667a\u80fd\u91cf\u5316\u6307\u6807+\u4ee3\u7801\u5b9e\u6218\uff0c\u624b\u628a\u624b\u5e26\u4f60\u5b66\u4f1a\uff01"},"content":{"rendered":"\n

\u4f5c\u8005\uff1a\u8001\u4f59\u635e\u9c7c<\/a><\/p>\n\n\n\n

\u539f\u521b\u4e0d\u6613\uff0c\u8f6c\u8f7d\u8bf7\u6807\u660e\u51fa\u5904\u53ca\u539f\u4f5c\u8005\u3002<\/mark><\/strong><\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n
\n
\u5199\u5728\u524d\u9762\u7684\u8bdd\uff1a<\/strong>AI+\u673a\u5668\u5b66\u4e60\u6b63\u5728\u5f7b\u5e95\u6539\u53d8\u6211\u4eec\u7684\u6295\u8d44\u65b9\u5f0f\u3002\u4eca\u5929\u6211\u76f4\u63a5\u7529\u51fa5\u4e2aAI\u4ea4\u6613\u6307\u6807\uff0c\u5168\u662f\u5b9e\u6218\u5e72\u8d27\u3002<\/mark>\u7528\u673a\u5668\u5b66\u4e60\u4f18\u5316\u6b62\u635f\u70b9\u3001\u9884\u5224\u677f\u5757\u8f6e\u52a8\u3001\u9884\u6d4b\u4ef7\u683c\u62d0\u70b9\u2026\u2026\u64cd\u4f5c\u7b80\u5355\uff0c\u4e0d\u73a9\u865a\u7684\uff0c\u8fde\u4ee3\u7801\u90fd\u7ed9\u4f60\u4e86\uff0c\u770b\u5b8c\u4e5f\u8bb8\u4f60\u4f1a\u60f3\u9a6c\u4e0a\u5f00\u7535\u8111\u8bd5\u4e00\u8bd5\uff01<\/pre>\n<\/blockquote>\n\n\n\n
1. \u667a\u80fd\u6b62\u635f\uff1a\u5e84\u5bb6\u90fd\u9a97\u4e0d\u8fc7\u7684\u201c\u9003\u9876\u795e\u5668\u201d<\/strong><\/h2>\n\n\n\n
\u4f60\u6709\u6ca1\u6709\u9047\u5230\u8fc7\u8fd9\u6837\u7684\u60c5\u51b5\uff1a\u660e\u660e\u5728\u505a\u4e00\u4e2a\u4e0d\u9519\u7684\u4ea4\u6613\uff0c\u7ed3\u679c\u6b62\u635f\u70b9\u8bbe\u7f6e\u5f97\u4e0d\u597d\uff0c\u8981\u4e48\u7528\u4f20\u7edf\u79fb\u52a8\u6b62\u635f\u6280\u672f\u88ab\u6d17\u76d8\u7529\u4e0b\u8f66\uff1f\u8981\u4e48\u4e8f\u5f97\u66f4\u591a\u3002SuperTrend AI \u5c31\u662f\u4e3a\u4e86\u89e3\u51b3\u8fd9\u4e2a\u95ee\u9898\u8bbe\u8ba1\u7684\u3002<\/p>\n\n\n\n
1.1 \u6838\u5fc3\u539f\u7406<\/strong><\/h3>\n\n\n\n
\u5b83\u7684\u5de5\u4f5c\u539f\u7406\u5f88\u7b80\u5355\uff1a\u5148\u7528 ATR\uff08\u771f\u5b9e\u6ce2\u52a8\u5e45\u5ea6\uff09\u6765\u8ddf\u8e2a\u5e02\u573a\u8d8b\u52bf\uff0c\u7136\u540e\u901a\u8fc7 K-means \u805a\u7c7b\u7b97\u6cd5\uff0c\u5bf9\u4e0d\u540c\u53c2\u6570\u7ec4\u5408\u8fdb\u884c\u6d4b\u8bd5\uff0c\u6700\u540e\u9009\u51fa\u8868\u73b0\u6700\u597d\u7684\u4e00\u7ec4\u3002\u8fd9\u5c31\u50cf\u662f\u8ba9\u4e00\u4e2a\u670b\u53cb\u5e2e\u4f60\u8bd5\u4e86\u6240\u6709\u53ef\u80fd\u7684\u65b9\u6848\uff0c\u76f4\u63a5\u544a\u8bc9\u4f60\u54ea\u4e2a\u6700\u597d\u7528\u3002<\/p>\n\n\n\n
    \n
  • \u6a21\u62df100\u79cd\u6b62\u635f\u53c2\u6570\u7684\u6548\u679c<\/li>\n\n\n\n
  • \u7528\u7b97\u6cd5\u81ea\u52a8\u5206\u6210\u201c\u8d5a\u94b1\u7ec4\u201d\u548c\u201c\u4e8f\u94b1\u7ec4\u201d<\/li>\n\n\n\n
  • \u53ea\u8ddf\u8d5a\u94b1\u7ec4\u7684\u53c2\u6570\u8d70<\/li>\n<\/ul>\n\n\n\n
    1.2 \u4e3a\u4ec0\u4e48\u725b\uff1f<\/strong><\/h3>\n\n\n\n
    \u672c\u6b21deepseek\u5e26\u6765\u7684\u66b4\u6da8\u884c\u60c5\uff0c\u8fd9\u5957\u7b56\u7565\u8ba9\u6211\u8eb2\u8fc73\u6b21\u5047\u8dcc\u7834\uff0c\u591a\u8d5a40%\uff01<\/p>\n\n\n\n
    \u4e3a\u4ec0\u4e48\u63a8\u8350\u5927\u5bb6\u4e5f\u8bd5\u8bd5\uff1f\u56e0\u4e3a\u8fd9\u4e2a\u65b9\u6cd5\u80fd\u7701\u53bb\u5927\u91cf\u8c03\u6574\u53c2\u6570\u7684\u65f6\u95f4\uff0c\u8fd8\u80fd\u66f4\u7cbe\u51c6\u5730\u627e\u5230\u5408\u9002\u7684\u6b62\u635f\u70b9\u3002
    <\/p>\n\n\n\n
    1.3 \u4ee3\u7801\u5b9e\u64cd\uff08Python\uff09<\/strong><\/h3>\n\n\n\n
    \u4e0b\u9762\u662f\u7b80\u5316\u7248\u7684\u4ee3\u7801\uff0c\u5927\u5bb6\u53ef\u4ee5\u8bd5\u7740\u8fd0\u884c\u4e00\u4e0b\uff1a<\/p>\n\n\n\n
    from sklearn.cluster import KMeans  \nimport numpy as np\n\n# \u5047\u8bbe\u8fd9\u662f10\u5929\u6536\u76ca\u6570\u636e  \nprofit_data = [[5%], [3%], [-2%], [7%], [1%]]  \n\n# \u4f7f\u7528 K-means \u5206\u6210\u4e24\u7ec4\u627e\u6700\u4f18\u53c2\u6570  \nkmeans = KMeans(n_clusters=2).fit(profit_data) \n\n \nprint(\"\u6700\u5f3a\u53c2\u6570\u7ec4\uff1a\", kmeans.cluster_centers_[1])  # \u8f93\u51fa\uff1a[6.2%]  <\/code><\/pre>\n\n\n\n
    2. \u62b1\u56e2\u80a1\u63a2\u6d4b\u5668\uff1a3\u79d2\u9501\u5b9a\u5173\u8054\u677f\u5757<\/strong><\/h2>\n\n\n\n
    \u4f60\u77e5\u9053\u54ea\u4e9b\u80a1\u7968\u4f1a\u4e00\u8d77\u6da8\u8dcc\u5417\uff1f\u76f8\u5173\u6027\u805a\u7c7b\u53ef\u4ee5\u5e2e\u4f60\u5feb\u901f\u627e\u5230\u7b54\u6848\u3002<\/p>\n\n\n\n
    2.1 \u6838\u5fc3\u539f\u7406<\/strong><\/h3>\n\n\n\n
    \u8fd9\u4e2a\u5de5\u5177\u7684\u539f\u7406\u4e5f\u5f88\u7b80\u5355\uff1a\u5148\u9009\u4e00\u53ea\u80a1\u7968\uff0c\u6bd4\u5982\u8305\u53f0\uff0c\u7136\u540e\u770b\u770b\u5176\u4ed6\u80a1\u7968\u548c\u5b83\u7684\u5173\u7cfb\u3002\u63a5\u7740\u7528 K-means \u7b97\u6cd5\u628a\u8fd9\u4e9b\u80a1\u7968\u5206\u6210\u51e0\u7ec4\uff0c\u65b9\u4fbf\u4f60\u6293\u4f4f\u884c\u4e1a\u53d8\u5316\u6216\u8005\u7ec4\u5efa\u4e00\u4e2a\u4ea4\u6613\u7ec4\u5408\u3002<\/p>\n\n\n\n
    2.2 \u5b9e\u6218\u6280\u5de7<\/strong><\/strong><\/h3>\n\n\n\n
    \u6211\u81ea\u5df1\u7528\u8fd9\u4e2a\u65b9\u6cd5\u53d1\u73b0\u4e86\u767d\u9152\u80a1\u5728\u5927\u6da8\u524d\u7684\u8054\u52a8\u4fe1\u53f7\uff0c\u7b80\u76f4\u5c31\u50cf\u4e00\u5f20\u85cf\u5b9d\u56fe\u3002<\/p>\n\n\n\n
      \n
    • \u8f93\u5165\u9f99\u5934\u80a1\uff08\u5982\u8305\u53f0\uff09<\/li>\n\n\n\n
    • \u7b97\u6cd5\u81ea\u52a8\u5339\u914d\u8d70\u52bf\u76f8\u4f3c\u7684\u80a1\u7968<\/li>\n\n\n\n
    • 2023\u5e74\u7528\u8fd9\u62db\u63d0\u524d3\u5929\u6293\u4f4f\u767d\u9152\u96c6\u4f53\u7206\u53d1<\/li>\n<\/ul>\n\n\n\n
      2.3 \u4ee3\u7801\u793a\u4f8b<\/strong><\/h3>\n\n\n\n
      \u4e0b\u9762\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u4ee3\u7801\u793a\u4f8b\uff1a<\/p>\n\n\n\n
      import pandas as pd  \n# 5\u53ea\u6d88\u8d39\u80a1\u7684\u76f8\u5173\u6027\u77e9\u9635  \ncorr_matrix = pd.DataFrame({  \n    '\u8305\u53f0': [1.0, 0.85, 0.7, 0.3, 0.2],  \n    '\u4e94\u7cae\u6db2': [0.85, 1.0, 0.6, 0.4, 0.1],  \n    # ...\u5176\u4ed6\u6570\u636e  \n})  \n# \u8f6c\u6362\u6210\u8ddd\u79bb\u77e9\u9635  \ndistance = 1 - corr_matrix  \n# \u805a\u7c7b\u627e\u961f\u53cb  \nclusters = KMeans(n_clusters=2).fit_predict(distance)  \nprint(\"\u8305\u53f0\u961f\u53cb\uff1a\", clusters[0])  # \u8f93\u51fa\uff1a\u4e94\u7cae\u6db2\u3001\u6cf8\u5dde\u8001\u7a96  <\/code><\/pre>\n\n\n\n
      3. \u9ad8\u65af\u9884\u6d4b\u6a21\u578b\uff1a\u63d0\u524d\u770b\u5230\u660e\u5929\u4ef7\u683c<\/strong><\/h2>\n\n\n\n
      \u9ad8\u65af\u8fc7\u7a0b\u56de\u5f52\uff08GPR\uff09\u662f\u4e00\u79cd\u975e\u5e38\u5f3a\u5927\u7684\u9884\u6d4b\u5de5\u5177\uff0c\u7528\u6765\u63a8\u6d4b\u672a\u6765\u4ef7\u683c\u8d70\u52bf\u7279\u522b\u597d\u7528\u3002\u7528\u5b83\u9884\u6d4b\u80a1\u4ef7\uff0c\u6bd4MACD\u51c610\u500d\uff01<\/p>\n\n\n\n
      3.1 \u6838\u5fc3\u539f\u7406<\/strong><\/h3>\n\n\n\n
      \u5b83\u7684\u6838\u5fc3\u601d\u60f3\u662f\u5206\u6790\u8fc7\u53bb\u7684\u4ef7\u683c\u6570\u636e\uff0c\u627e\u51fa\u5b83\u4eec\u4e4b\u95f4\u7684\u89c4\u5f8b\uff0c\u518d\u7ed3\u5408\u566a\u97f3\u56e0\u7d20\uff0c\u7ed9\u51fa\u672a\u6765\u7684\u9884\u6d4b\u503c\u3002\u4f60\u53ef\u4ee5\u6839\u636e\u81ea\u5df1\u7684\u9700\u6c42\uff0c\u8bbe\u7f6e\u6bcf\u5929\u66f4\u65b0\u4e00\u6b21\uff0c\u6216\u8005\u5b9e\u65f6\u66f4\u65b0\u3002<\/p>\n\n\n\n
      \u6211\u81ea\u5df1\u5f88\u559c\u6b22\u8fd9\u4e2a\u5de5\u5177\uff0c\u56e0\u4e3a\u5b83\u5728\u5e02\u573a\u5267\u70c8\u6ce2\u52a8\u65f6\u8868\u73b0\u5f88\u7a33\u3002<\/p>\n\n\n\n
      3.2 \u72ec\u5bb6\u53c2\u6570<\/strong><\/h3>\n\n\n\n
        \n
      • \u957f\u5ea6\u5c3a\u5ea6\u8c03\u81f30.5\uff08\u9002\u5408A\u80a1\u6ce2\u52a8\uff09<\/li>\n\n\n\n
      • \u52a0\u5165\u6210\u4ea4\u91cf\u6743\u91cd<\/li>\n\n\n\n
      • \u4eca\u5e74\u6d4b\u8bd5\u521b\u4e1a\u677f\u6307\uff0c5\u5929\u9884\u6d4b\u8bef\u5dee\u4ec51.8%<\/li>\n<\/ul>\n\n\n\n
        3.3 \u4ee3\u7801\u793a\u4f8b<\/strong><\/h3>\n\n\n\n
        from sklearn.gaussian_process import GaussianProcessRegressor  \n# \u5047\u8bbe\u524d5\u5929\u4ef7\u683c  \nX = [[1], [2], [3], [4], [5]]  \ny = [10.0, 10.5, 11.2, 10.8, 11.5]  \n# \u8bad\u7ec3\u9884\u6d4b\u6a21\u578b  \ngpr = GaussianProcessRegressor().fit(X, y)  \nprint(\"\u7b2c6\u5929\u9884\u6d4b\u4ef7\uff1a\", gpr.predict([[6]])[0])  # \u8f93\u51fa\uff1a11.9\u5143  <\/code><\/pre>\n\n\n\n
        4. AI\u5747\u7ebf\uff1a\u4f20\u7edf\u4e0e\u79d1\u6280\u7684\u5b8c\u7f8e\u7ed3\u5408<\/strong><\/h2>\n\n\n\n
        \u5747\u7ebf\u662f\u5f88\u591a\u6295\u8d44\u4eba\u559c\u6b22\u7528\u7684\u5de5\u5177\uff0c\u4f46\u4f20\u7edf\u7684\u5747\u7ebf\u6709\u4e2a\u95ee\u9898\uff0c\u5c31\u662f\u6ede\u540e\u6027\u592a\u5f3a\u3002AI\u5747\u7ebf\u901a\u8fc7\u9ad8\u65af\u8fc7\u7a0b\u6539\u8fdb\u4e86\u8fd9\u4e00\u70b9\uff0c\u8ba9\u5b83\u65e2\u80fd\u8ddf\u968f\u5e02\u573a\u53d8\u5316\uff0c\u53c8\u80fd\u63d0\u524d\u6355\u6349\u5230\u8d8b\u52bf\u3002<\/p>\n\n\n\n
        4.1 \u6838\u5fc3\u539f\u7406<\/strong><\/h3>\n\n\n\n
        \u4f7f\u7528 RBF \u5185\u6838\u5efa\u6a21\u4ef7\u683c\u6ce2\u52a8\uff0c\u751f\u6210\u66f4\u5177\u9002\u5e94\u6027\u7684\u79fb\u52a8\u5e73\u5747\u7ebf\u3002\u4f20\u7edf\u79fb\u52a8\u5e73\u5747\u7ebf\u7528\u4e8e\u5e73\u6ed1\u4ef7\u683c\u6570\u636e\uff0c\u8bc6\u522b\u8d8b\u52bf\uff0c\u4f46\u6ede\u540e\u95ee\u9898\u5728\u9707\u8361\u5e02\u573a\u4e2d\u663e\u8457\u3002ML Moving Average \u4f7f\u7528 GPR \u52a8\u6001\u8c03\u6574\uff0c\u51cf\u5c11\u6ede\u540e\uff0c\u63d0\u5347\u9884\u6d4b\u529b\u3002\u5728\u9707\u8361\u5e02\u573a\u4e2d\u8868\u73b0\u4f18\u4e8e\u4f20\u7edf\u79fb\u52a8\u5e73\u5747\u7ebf\u3002<\/p>\n\n\n\n
        4.2 \u5b9e\u6218\u6570\u636e<\/strong><\/h3>\n\n\n\n
        \u6211\u81ea\u5df1\u7528\u8fd9\u4e2a\u5de5\u5177\u540e\uff0c\u611f\u89c9\u5728\u9707\u8361\u5e02\u573a\u91cc\u7279\u522b\u987a\u624b\u3002<\/p>\n\n\n\n
          \n
        • \u57282024\u5e74\u79d1\u521b\u677f\u6d4b\u8bd5\uff1b<\/li>\n\n\n\n
        • \u6bd420\u65e5\u5747\u7ebf\u591a\u629362%\u7684\u4e70\u5356\u70b9\uff1b<\/li>\n\n\n\n
        • \u6ede\u540e\u65f6\u95f4\u51cf\u5c1175%\u3002<\/li>\n<\/ul>\n\n\n\n
          4.3 \u6838\u5fc3\u4ee3\u7801<\/strong><\/h3>\n\n\n\n
          import numpy as np\nfrom sklearn.gaussian_process.kernels import RBF\nfrom sklearn.gaussian_process import GaussianProcessRegressor\n\n# \u5047\u8bbe\u8fd9\u662f\u8fc7\u53bb\u7684\u4ef7\u683c\u6570\u636e\nX = np.arange(1, 6).reshape(-1, 1)\ny = np.array([10, 11, 10.5, 12, 11.8])\n\n# \u4f7f\u7528\u9ad8\u65af\u8fc7\u7a0b\u8bad\u7ec3\u6a21\u578b\nkernel = RBF()\ngpr = GaussianProcessRegressor(kernel=kernel).fit(X, y)\n\n# \u9884\u6d4b\u4e0b\u4e00\u4e2a\u4ef7\u683c\nnext_price = gpr.predict([[6]])\nprint(\"\u4e0b\u4e00\u4e2a\u9884\u6d4b\u4ef7\u683c\uff1a\", next_price[0])<\/code><\/pre>\n\n\n\n
          5. \u4fe1\u53f7\u8bc4\u5206\u7cfb\u7edf\uff1a\u907f\u5f0095%\u7684\u5047\u7a81\u7834<\/strong><\/h2>\n\n\n\n
          \u6700\u540e\u4e00\u4e2a\u5de5\u5177\u662f\u6211\u6700\u559c\u6b22\u7684\uff1a\u4fe1\u53f7\u8bc4\u5206\u7cfb\u7edf\u3002\u5b83\u7528\u673a\u5668\u5b66\u4e60\u7684\u65b9\u6cd5\u7ed9\u6bcf\u4e00\u4e2a\u4ea4\u6613\u4fe1\u53f7\u6253\u5206\uff0c\u5206\u6570\u8d8a\u9ad8\uff0c\u8bf4\u660e\u4fe1\u53f7\u8d8a\u53ef\u9760\u3002<\/p>\n\n\n\n
          5.1 \u6838\u5fc3\u539f\u7406<\/strong><\/h3>\n\n\n\n
          \u57fa\u4e8e\u4ef7\u683c\u548c\u6210\u4ea4\u91cf\u7b49\u7279\u5f81\uff0c\u8bad\u7ec3\u6a21\u578b\u9884\u6d4b\u4fe1\u53f7\u5f3a\u5ea6\uff0c\u5e76\u6dfb\u52a0\u989d\u5916\u4fe1\u606f\u5982\u8d8b\u52bf\u5f3a\u5ea6\u3002\u5728\u5b9e\u7528\u6027\u65b9\u9762\uff0c\u5176\u51cf\u5c11\u4fe1\u53f7\u8bef\u5224\uff0c\u5e2e\u52a9\u4ea4\u6613\u8005\u7406\u89e3\u4fe1\u53f7\u80cc\u540e\u7684\u539f\u56e0\u3002<\/p>\n\n\n\n
          5.2 \u76f8\u5173\u53c2\u6570<\/strong><\/h3>\n\n\n\n
          \u8fd9\u4e2a\u5de5\u5177\u4e0d\u4ec5\u544a\u8bc9\u4f60\u8be5\u4e0d\u8be5\u51fa\u624b\uff0c\u8fd8\u4f1a\u89e3\u91ca\u539f\u56e0\uff0c\u6bd4\u5982\u8d8b\u52bf\u5f3a\u5ea6\u6216\u8005\u5e02\u573a\u6ce2\u52a8\u6027\u3002\u7ed9\u4e70\u5356\u4fe1\u53f7\u6253\u5206\uff1a<\/p>\n\n\n\n