diff --git a/bigwork/final_models/crisis_index_model.pkl b/bigwork/final_models/crisis_index_model.pkl index c0be13b..85528b5 100644 Binary files a/bigwork/final_models/crisis_index_model.pkl and b/bigwork/final_models/crisis_index_model.pkl differ diff --git a/bigwork/final_models/propagation_risk_model.pkl b/bigwork/final_models/propagation_risk_model.pkl index cfc0bb8..e128c57 100644 Binary files a/bigwork/final_models/propagation_risk_model.pkl and b/bigwork/final_models/propagation_risk_model.pkl differ diff --git a/bigwork/final_models/trend_analysis_model.pkl b/bigwork/final_models/trend_analysis_model.pkl index da6340a..2509e8a 100644 Binary files a/bigwork/final_models/trend_analysis_model.pkl and b/bigwork/final_models/trend_analysis_model.pkl differ diff --git a/bigwork/src/crisis_warning_app.py b/bigwork/src/crisis_warning_app.py index 9846da2..409a087 100644 --- a/bigwork/src/crisis_warning_app.py +++ b/bigwork/src/crisis_warning_app.py @@ -573,7 +573,8 @@ class CrisisWarningApp: user_input = st.text_area( "请输入推文内容或事件描述", "", # 默认空白 - height=150 + height=150, + key="crisis_input_text" ) # 自动情感分析 @@ -641,7 +642,7 @@ class CrisisWarningApp: st.metric("传播风险等级", result['propagation_analysis']['risk_level']) st.write("**生成的公关声明:**") - st.text_area("", result['ai_solutions']['pr_statement'], height=100, disabled=True) + st.text_area("", result['ai_solutions']['pr_statement'], height=100, disabled=True, key=f"history_pr_{i}") def _perform_integrated_analysis(self, text_content, retweet_count=0, sentiment="negative"): """执行整合分析，调用所有模块并生成综合结果""" @@ -723,7 +724,7 @@ class CrisisWarningApp: # 4. 危机公关方案 st.markdown("

📝 危机公关方案

", unsafe_allow_html=True) - st.text_area("生成的公关声明", result['ai_solutions']['pr_statement'], height=300) + st.text_area("生成的公关声明", result['ai_solutions']['pr_statement'], height=300, key="result_pr") # 风险等级解释 if result['crisis_analysis']['risk_level'] == "高风险": @@ -744,7 +745,8 @@ class CrisisWarningApp: st.subheader("公关声明生成") event_details = st.text_area( "请输入事件详情", - "因天气原因，我公司今日有200多个航班延误，影响乘客约3000人" + "因天气原因，我公司今日有200多个航班延误，影响乘客约3000人", + key="event_details" ) target_audience = st.text_input("目标受众", "乘客") tone = st.text_input("语气要求", "道歉且负责任") @@ -756,7 +758,7 @@ class CrisisWarningApp: target_audience, tone ) - st.text_area("生成的公关声明", pr_statement, height=400) + st.text_area("生成的公关声明", pr_statement, height=400, key="ai_pr") # 运行应用 if __name__ == "__main__": diff --git a/bigwork/src/smart_care_system.py b/bigwork/src/smart_care_system.py index 66323ce..e8024dd 100644 --- a/bigwork/src/smart_care_system.py +++ b/bigwork/src/smart_care_system.py @@ -47,7 +47,13 @@ USER_TYPES = { } # DeepSeek API配置 -DEEPSEEK_API_KEY = "sk-eb8cc78f22ef443491d4199e56bde9a7" +import os +from dotenv import load_dotenv + +# 加载环境变量 +load_dotenv() + +DEEPSEEK_API_KEY = os.getenv("DEEPSEEK_API_KEY") DEEPSEEK_API_URL = "https://api.deepseek.com/v1/chat/completions" @@ -56,6 +62,21 @@ def call_deepseek_api(prompt: str, max_tokens: int = 500, temperature: float = 0 import time import requests + # 检查API Key是否配置 + if not DEEPSEEK_API_KEY: + print("DeepSeek API密钥未配置，返回模拟响应") + # 返回模拟响应 + if "问题分类" in prompt: + return json.dumps({"primary_category": "其他", "secondary_category": "其他"}, ensure_ascii=False) + elif "用户类型" in prompt: + return json.dumps({ + "main_type": "效率型", + "type_probabilities": {"效率型": 0.6, "舒适型": 0.2, "经济型": 0.1, "情感型": 0.1}, + "type_characteristics": USER_TYPES["效率型"] + }, ensure_ascii=False) + else: + return "API密钥未配置，返回模拟响应。这是一个智能生成的关怀方案描述。" + max_retries = 3 retry_delay = 2 timeout = 60 # 增加超时时间到60秒 diff --git a/bigwork/src/smart_customer_service.py b/bigwork/src/smart_customer_service.py index 8be34bc..484f62b 100644 --- a/bigwork/src/smart_customer_service.py +++ b/bigwork/src/smart_customer_service.py @@ -1068,11 +1068,21 @@ class SmartCustomerService: import requests import json + import os + from dotenv import load_dotenv + + # 加载环境变量 + load_dotenv() # DeepSeek API配置 - api_key = "sk-eb8cc78f22ef443491d4199e56bde9a7" + api_key = os.getenv("DEEPSEEK_API_KEY") api_url = "https://api.deepseek.com/v1/chat/completions" + # 检查API密钥是否配置 + if not api_key: + print("DeepSeek API密钥未配置，返回默认响应") + return "感谢您的反馈。我们的客服团队将尽快处理您的问题，并与您联系。" + # 构建系统提示 system_prompt = """ 你是一个专业的航空公司客服助手，需要基于用户的反馈和流失分析结果生成结构化的响应。 @@ -1299,11 +1309,21 @@ class SmartCustomerService: import requests import json + import os + from dotenv import load_dotenv + + # 加载环境变量 + load_dotenv() # 使用用户提供的DeepSeek API密钥 - api_key = "sk-eb8cc78f22ef443491d4199e56bde9a7" + api_key = os.getenv("DEEPSEEK_API_KEY") api_url = "https://api.deepseek.com/v1/chat/completions" + # 检查API密钥是否配置 + if not api_key: + print("DeepSeek API密钥未配置，返回默认情感分析结果") + return "neutral" + # 构建系统提示 system_prompt = """ 你是一个专业的情感分析助手，需要分析用户反馈的情感倾向。 @@ -1915,7 +1935,7 @@ def show_chat_interface(customer_service: SmartCustomerService): # 用户输入 st.markdown("### 💭 请输入您的查询") - user_query = st.text_area("您的消息", placeholder="请输入您的问题或反馈...", value=user_content) + user_query = st.text_area("您的消息", placeholder="请输入您的问题或反馈...", value=user_content, key="user_query") if st.button("发送", type="primary") and user_query: with st.spinner("正在分析您的查询并生成响应..."): @@ -1961,7 +1981,7 @@ def show_churn_analysis(customer_service: SmartCustomerService): # 手动输入区域 st.markdown("### 👤 手动输入分析") user_id = st.text_input("用户ID", placeholder="请输入用户ID，例如：user_001") - user_content = st.text_area("用户反馈内容", placeholder="请输入用户反馈内容...") + user_content = st.text_area("用户反馈内容", placeholder="请输入用户反馈内容...", key="user_feedback") if st.button("🔍 进行流失分析", type="secondary") and user_id and user_content: with st.spinner("正在基于输入内容分析用户流失风险..."):