llm-quant/app/data/prompt_templates/department_base@1.2.0.json
2025-10-06 15:43:20 +08:00

31 lines
1.8 KiB
JSON
Raw Permalink 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.

{
"department_base": {
"name": "部门基础模板",
"description": "审慎分析骨架(结构化输出版)",
"template": "部门:{title}\n股票代码{ts_code}\n交易日{trade_date}\n\n【角色定位】\n- 研究职责:{description}\n- 执行要点:{instruction}\n\n【量化检查】\n- 数据覆盖:\n{data_scope}\n- 模型特征:\n{features}\n- 市场切片:\n{market_snapshot}\n- 附加观察:\n{supplements}\n\n【分析流程】\n1. 使用事实句描述当前市场位置(包含至少 1 项相对指标)。\n2. 归纳 2-3 条策略信号,每条需关联具体字段并给出方向。\n3. 对每条信号列出对应的风险验证指标与触发阈值。\n4. 最终给出操作建议,并在 `confidence` 中量化判断依据。\n\n【输出格式】\n仅输出 JSON不包含额外文字\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 \"statement\": \"现象描述\",\n \"evidence\": \"对应字段或数据来源\",\n \"direction\": \"bullish|bearish|neutral\"\n }\n ],\n \"risks\": [\n {\n \"threat\": \"风险描述\",\n \"monitor\": \"观测指标\",\n \"threshold\": \"触发阈值\"\n }\n ]\n}\n若缺少关键数据请在 `risks` 中新增一项 `monitor` 为 `data_gap`。",
"variables": [
"title",
"ts_code",
"trade_date",
"description",
"instruction",
"data_scope",
"features",
"market_snapshot",
"supplements"
],
"max_length": 4000,
"required_context": [
"ts_code",
"trade_date",
"features",
"market_snapshot"
],
"version": "1.2.0",
"metadata": {
"label": "structured_v2",
"notes": "增加信号与风险的结构化字段。"
},
"activate": false
}
}