From 330c84e7fce8be7d5ab8ebd3ccb4c3d6530d7773 Mon Sep 17 00:00:00 2001
From: pzb7h6yxf <1736289433@qq.com>
Date: Tue, 17 Sep 2024 10:00:59 +0800
Subject: [PATCH] =?UTF-8?q?=E7=BB=9F=E8=AE=A1AI=E6=8A=80=E6=9C=AF=E5=BA=94?=
 =?UTF-8?q?=E7=94=A8=E6=96=B9=E9=9D=A2=E7=9A=84=E6=AF=8F=E7=A7=8D=E5=BC=B9?=
 =?UTF-8?q?=E5=B9=95=E6=95=B0=E9=87=8F=EF=BC=8C=E5=B9=B6=E8=BE=93=E5=87=BA?=
 =?UTF-8?q?=E6=95=B0=E9=87=8F=E6=8E=92=E5=90=8D=E5=89=8D8=E7=9A=84?=
 =?UTF-8?q?=E5=BC=B9=E5=B9=95=20Initial=20commit(2-2)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 2.2.py | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)
 create mode 100644 2.2.py

diff --git a/2.2.py b/2.2.py
new file mode 100644
index 0000000..9d71ab3
--- /dev/null
+++ b/2.2.py
@@ -0,0 +1,35 @@
+from collections import Counter
+
+# 读取TXT文件并统计AI相关关键词
+def count_ai_keywords(file_path):
+    # 定义与AI技术相关的关键词列表
+    ai_keywords = [
+        "AI", "人工智能", "Machine learning", "机器学习", "Deep learning", "深度学习", 
+        "Neural network", "神经网络", "自然语言处理", "Natural language processing", 
+        "计算机视觉", "Computer vision", "Robotics", "机器人", "自动化", "Automation",
+        "人脸识别", "Face recognition", "大数据", "数据挖掘", "智能系统", "自动驾驶", "无人驾驶","AI技术"
+    ]
+
+    # 用来存储统计结果的Counter
+    keyword_count = Counter()
+
+    # 读取文件
+    with open(file_path, 'r', encoding='utf-8') as file:
+        for line in file:
+            # 遍历每个关键词，统计弹幕中包含关键词的数量
+            for keyword in ai_keywords:
+                if keyword.lower() in line.lower():  # 统计关键词忽略大小写
+                    keyword_count[keyword] += 1
+    
+    # 输出排名前8的关键词及其对应的数量
+    top_keywords = keyword_count.most_common(8)
+    
+    print("AI 技术相关的前8条弹幕关键词统计：")
+    for keyword, count in top_keywords:
+        print(f"{keyword}: {count} 条弹幕")
+
+# 文件路径
+file_path = "danmakus_2024_olympics.txt"
+
+# 调用函数并统计
+count_ai_keywords(file_path)