llm-quant/app/data/prompt_templates/news_dept@1.1.0.json
2025-10-06 15:43:20 +08:00

28 lines
1.6 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"news_dept": {
"name": "新闻情绪部门模板",
"description": "情绪脉冲量化版",
"template": "部门:新闻情绪部门\n股票代码{ts_code}\n交易日{trade_date}\n\n【情绪脉冲拆解】\n- 舆情亮点:\n{features}\n- 市场反馈:\n{market_snapshot}\n- 数据补充:\n{supplements}\n- 数据范围:\n{data_scope}\n\n【分析步骤】\n1. 将新闻分为“正面/负面/中性”并评估强度0-1。\n2. 识别是否存在事件驱动催化,给出时间窗口与触发条件。\n3. 检查情绪与价格表现是否一致,如不一致需给出交易策略提示。\n\n【输出格式】\n仅输出 JSON\n{{\n \"action\": \"BUY|BUY_S|BUY_M|BUY_L|SELL|HOLD\",\n \"confidence\": 小数,\n \"summary\": \"一句话\",\n \"signals\": [\n {{\n \"headline\": \"事件/主题\",\n \"sentiment\": \"positive|negative|neutral\",\n \"intensity\": 小数,\n \"impact_window\": \"时间窗口\"\n }}\n ],\n \"risks\": [\n {{\n \"threat\": \"潜在风险\",\n \"monitor\": \"监控指标\",\n \"mitigation\": \"对冲或等待条件\"\n }}\n ]\n}}\n如需更多数据请在 `risks` 中新增条目并说明来源。",
"variables": [
"ts_code",
"trade_date",
"data_scope",
"features",
"market_snapshot",
"supplements"
],
"max_length": 4000,
"required_context": [
"ts_code",
"trade_date",
"features",
"market_snapshot"
],
"version": "1.1.0",
"metadata": {
"label": "sentiment_pulse",
"notes": "引导强度和窗口化输出。"
},
"activate": false
}
}