diff --git a/preprocess/user_problem_preprocess.py b/preprocess/user_problem_preprocess.py
new file mode 100644
index 0000000000000000000000000000000000000000..d80b8bd451880851aa006acb51da41d8359d04ba
--- /dev/null
+++ b/preprocess/user_problem_preprocess.py
@@ -0,0 +1,34 @@
+import json
+
+# 定义处理函数
+def process_json(line):
+    data = json.loads(line)
+    if data['score'] == None:
+        return None
+    return {
+        'log_id': data['log_id'],
+        'is_correct': data['is_correct'],
+        'attempts': data['attempts'],
+        'score': data['score'],
+    }
+
+# 读取大型JSON文件
+file_path = '/Users/yr/code/data-mining/Dataset/MOOCCubeX/relations/user-problem.json'  # 替换为实际的JSON文件路径
+# file_path = 'pro/data/t.json'  # 替换为实际的JSON文件路径
+
+
+with open(file_path, 'r') as file:
+    for line in file:
+        processed_data = process_json(line)
+        if processed_data != None:
+            with open('/Users/yr/code/data-mining/Dataset/MOOCCubeX/pro/data/user-problem-pre.json', 'a+', encoding='utf-8') as f:
+                l = json.dumps(processed_data, ensure_ascii=False)
+                # print(l)
+                f.write(l+'\n')
+
+
+
+
+
+
+