Integrating the OpenAI API for in-depth comment analysis, with usability to be debugged.

views/page/page.py

@@ -9,6 +9,11 @@ from utils.getTopicPageData import *
 from utils.yuqingpredict import *
 from utils.logger import app_logger as logging
 from utils.cache_manager import prediction_cache
+from utils.ai_analyzer import ai_analyzer
+from models.ai_analysis import AIAnalysis
+from sqlalchemy.orm import Session
+from sqlalchemy import create_engine
+import asyncio
 import torch
 from BCAT_front.predict import model_manager
 
@@ -31,6 +36,11 @@ try:
 except Exception as e:
     logging.error(f"模型加载失败: {e}")
 
+# 数据库配置
+DATABASE_URL = "sqlite:///ai_analysis.db"
+engine = create_engine(DATABASE_URL)
+AIAnalysis.metadata.create_all(engine)
+
 def predict_sentiment(text):
     """使用改进版模型预测单个文本的情感"""
     try:
@@ -294,3 +304,99 @@ def articleChar(id):
     except Exception as e:
         logging.error(f"获取文章详情时发生错误: {e}")
         return render_template('error.html', error_message="加载文章详情失败")
+
+@pb.route('/api/analyze_messages', methods=['POST'])
+async def analyze_messages():
+    try:
+        # 获取最近50条消息
+        messages = getRecentMessages(50)  # 需要实现这个函数
+        
+        # 调用AI进行分析
+        analysis_results = await ai_analyzer.analyze_messages(messages)
+        
+        # 保存到数据库
+        with Session(engine) as session:
+            for result in analysis_results:
+                analysis = AIAnalysis(
+                    message_id=result['message_id'],
+                    sentiment=result['sentiment'],
+                    sentiment_score=float(result['sentiment_score']),
+                    keywords=result['keywords'],
+                    key_points=result['key_points'],
+                    influence_analysis=result['influence_analysis'],
+                    risk_level=result['risk_level']
+                )
+                session.add(analysis)
+            session.commit()
+        
+        # 格式化结果用于显示
+        display_results = [
+            ai_analyzer.format_analysis_for_display(result)
+            for result in analysis_results
+        ]
+        
+        return jsonify({
+            'success': True,
+            'data': display_results
+        })
+    
+    except Exception as e:
+        logging.error(f"AI分析过程出错: {e}")
+        return jsonify({
+            'success': False,
+            'error': str(e)
+        }), 500
+
+@pb.route('/api/get_analysis/<int:message_id>')
+def get_message_analysis(message_id):
+    """获取特定消息的分析结果"""
+    try:
+        with Session(engine) as session:
+            analysis = session.query(AIAnalysis)\
+                .filter(AIAnalysis.message_id == message_id)\
+                .order_by(AIAnalysis.created_at.desc())\
+                .first()
+            
+            if analysis:
+                return jsonify({
+                    'success': True,
+                    'data': analysis.to_dict()
+                })
+            else:
+                return jsonify({
+                    'success': False,
+                    'error': '未找到分析结果'
+                }), 404
+    
+    except Exception as e:
+        logging.error(f"获取分析结果时出错: {e}")
+        return jsonify({
+            'success': False,
+            'error': str(e)
+        }), 500
+
+def getRecentMessages(limit=50):
+    """获取最近的消息"""
+    # 这里需要根据你的数据库结构实现具体的查询逻辑
+    messages = []
+    try:
+        # 示例查询逻辑
+        with Session(engine) as session:
+            results = session.execute(
+                """
+                SELECT id, content 
+                FROM comments 
+                ORDER BY created_at DESC 
+                LIMIT :limit
+                """,
+                {'limit': limit}
+            ).fetchall()
+            
+            messages = [
+                {'id': row[0], 'content': row[1]}
+                for row in results
+            ]
+    except Exception as e:
+        logging.error(f"获取最近消息时出错: {e}")
+    
+    return messages

views/page/templates/yuqingpredict.html

@@ -445,8 +445,157 @@
                </div>
               </div>
           </div>
+
+<!-- AI分析结果展示区域 -->
+<div class="row">
+    <div class="col-lg-12">
+        <div class="card">
+            <div class="card-header d-flex justify-content-between">
+                <div class="header-title">
+                    <h4 class="card-title">AI深度分析</h4>
+                </div>
+                <button class="btn btn-primary" onclick="requestAIAnalysis()">
+                    开始AI分析
+                </button>
+            </div>
+            <div class="card-body">
+                <div id="ai-analysis-results" class="analysis-container">
+                    <!-- 分析结果将在这里动态显示 -->
+                </div>
+            </div>
+        </div>
+    </div>
 </div>
 
+<!-- 添加必要的CSS样式 -->
+<style>
+.analysis-container {
+    max-height: 600px;
+    overflow-y: auto;
+}
+
+.analysis-card {
+    border: 1px solid #eee;
+    border-radius: 8px;
+    padding: 15px;
+    margin-bottom: 15px;
+    background-color: #fff;
+    box-shadow: 0 2px 4px rgba(0,0,0,0.1);
+}
+
+.analysis-card:hover {
+    box-shadow: 0 4px 8px rgba(0,0,0,0.15);
+}
+
+.risk-level {
+    padding: 4px 8px;
+    border-radius: 4px;
+    font-weight: bold;
+}
+
+.risk-low {
+    background-color: #e8f5e9;
+    color: #2e7d32;
+}
+
+.risk-medium {
+    background-color: #fff3e0;
+    color: #f57c00;
+}
+
+.risk-high {
+    background-color: #ffebee;
+    color: #c62828;
+}
+
+.keywords-container {
+    display: flex;
+    flex-wrap: wrap;
+    gap: 8px;
+    margin: 10px 0;
+}
+
+.keyword-tag {
+    background-color: #e3f2fd;
+    color: #1976d2;
+    padding: 4px 8px;
+    border-radius: 16px;
+    font-size: 0.9em;
+}
+</style>
+
+<!-- 添加必要的JavaScript代码 -->
+<script>
+async function requestAIAnalysis() {
+    try {
+        const response = await fetch('/page/api/analyze_messages', {
+            method: 'POST',
+            headers: {
+                'Content-Type': 'application/json'
+            }
+        });
+        
+        const result = await response.json();
+        if (result.success) {
+            displayAnalysisResults(result.data);
+        } else {
+            alert('分析失败: ' + result.error);
+        }
+    } catch (error) {
+        console.error('AI分析请求失败:', error);
+        alert('请求失败，请稍后重试');
+    }
+}
+
+function displayAnalysisResults(results) {
+    const container = document.getElementById('ai-analysis-results');
+    container.innerHTML = ''; // 清空现有结果
+    
+    results.forEach(analysis => {
+        const card = document.createElement('div');
+        card.className = 'analysis-card';
+        
+        const riskLevelClass = 
+            analysis.risk_level === '高' ? 'risk-high' :
+            analysis.risk_level === '中' ? 'risk-medium' : 'risk-low';
+        
+        card.innerHTML = `
+            <div class="d-flex justify-content-between align-items-center">
+                <h5 class="mb-2">消息ID: ${analysis.id}</h5>
+                <span class="risk-level ${riskLevelClass}">
+                    风险等级: ${analysis.risk_level}
+                </span>
+            </div>
+            <div class="mb-2">
+                <strong>情感倾向:</strong> ${analysis.sentiment}
+                <span class="ml-2">(${analysis.sentiment_score})</span>
+            </div>
+            <div class="keywords-container">
+                ${analysis.keywords.split(',').map(keyword => 
+                    `<span class="keyword-tag">${keyword.trim()}</span>`
+                ).join('')}
+            </div>
+            <div class="mb-2">
+                <strong>核心观点:</strong>
+                <p class="mb-1">${analysis.key_points}</p>
+            </div>
+            <div class="mb-2">
+                <strong>影响分析:</strong>
+                <p class="mb-1">${analysis.influence}</p>
+            </div>
+            <div class="text-muted">
+                分析时间: ${analysis.analysis_time}
+            </div>
+        `;
+        
+        container.appendChild(card);
+    });
+}
+
+// 页面加载完成后自动请求一次AI分析
+document.addEventListener('DOMContentLoaded', requestAIAnalysis);
+</script>
+
 {% endblock %}
 
 {% block echarts %}