# -*- coding: utf-8 -*- import json from typing import Dict, List class MemberContextPromptBuilder: """成员分层画像提示词构建器""" @staticmethod def build_group_daily_digest_prompt(chatroom_id: str, digest_date: str, member_labels: List[str], compressed_chat: str) -> str: return ( "你是微信群后台的成员日观察批量提取器。\n" "请基于给定的一天群聊记录，识别当天有参与发言的成员，并分别提取中性、克制的成员日观察摘要。\n" "不要做心理诊断、隐私猜测、负面评价，不要输出未在候选名单中的成员。\n" "你的输出将被后续系统按周、按月持续累积，因此优先提取可复用、可累计、可验证的行为信号，而不是一次性的情绪和玩笑。\n" "输出严格 JSON，不要 markdown。\n" "{" "\"members\":[" "{" "\"wxid\":\"成员wxid\"," "\"display_name\":\"成员显示名\"," "\"topics\":[\"主题1\"]," "\"discussion_scenarios\":[\"场景1\"]," "\"identity_clues\":[\"身份线索1\"]," "\"skill_signals\":[\"技能信号1\"]," "\"problem_solving_signals\":[\"处理方式1\"]," "\"family_signals\":[\"家庭线索1\"]," "\"life_stage_signals\":[\"阶段线索1\"]," "\"value_preferences\":[\"价值偏好1\"]," "\"interaction_style\":\"一句中文\"," "\"message_pattern\":\"一句中文\"," "\"response_style_hint\":\"一句中文\"," "\"habit_signals\":[\"信号1\"]," "\"expression_markers\":[\"表达标记1\"]," "\"engagement_traits\":[\"特征1\"]," "\"reply_entry_points\":[\"接话点1\"]," "\"decision_style\":\"一句中文\"," "\"social_role\":\"一句中文，描述当天在群中的角色表现\"," "\"reply_taboos\":[\"避坑1\"]," "\"temperament_signal\":\"一句中文，描述当天沟通倾向，必须克制\"," "\"summary_text\":\"一段不超过100字的日摘要\"," "\"representative_messages\":[\"原话1\",\"原话2\"]," "\"confidence\":0.0" "}" "]" "}\n" "要求：\n" "1. 只输出当天真正参与发言且能看出明确行为信号的成员；发言极少的人可以不输出。\n" "2. 每个成员的 topics、discussion_scenarios、identity_clues、skill_signals、problem_solving_signals、family_signals、life_stage_signals、value_preferences、habit_signals、expression_markers、engagement_traits、reply_entry_points 最多4个，reply_taboos 最多3个。\n" "3. representative_messages 只保留最能代表当天表达方式的短句，最多3条。\n" "4. 必须严格使用候选成员列表中的 wxid 和显示名。\n" "5. identity_clues、family_signals、life_stage_signals 只能写公开聊天中出现的线索，不可把弱线索写成确定事实。\n" "6. skill_signals 重点提炼成员解决问题、提供信息、组织表达、专业能力等信号。\n" "7. social_role 只描述当天在群里的角色表现，例如：问题提出者、信息补充者、气氛调节者、组织推进者。\n" "8. topics 更偏向持续关注的话题方向；discussion_scenarios 更偏向他通常在什么情境下发言，如求助排错、补充经验、分享资源、接梗互动。\n" "9. problem_solving_signals 要写得具体，比如先确认现象再给步骤、倾向贴链接/文档、会直接给结论和执行项，不要只写'善于解决问题'。\n" "10. expression_markers 记录可观察的表达标记，如常用句式、口头禅、是否爱列步骤/贴截图/贴日志；reply_entry_points 记录什么样的接话方式最容易接住他。\n" "11. value_preferences 只记录公开表达出的偏好，如效率优先、成本敏感、谨慎验证、乐于助人，不要写抽象大词。\n" "12. summary_text 应是后台观察摘要，不要写成对用户说的话。\n" f"群ID: {chatroom_id}\n" f"日期: {digest_date}\n" "候选成员:\n" + "\n".join(member_labels[:80]) + "\n" "压缩后的群聊记录:\n" + compressed_chat ) @staticmethod def build_period_digest_prompt(digest_type: str, chatroom_id: str, wxid: str, display_name: str, period_key: str, items: List[Dict]) -> str: structured_lines = [] for item in items: structured = item.get("structured", {}) or {} payload = { "period_key": item.get("period_key"), "summary_text": item.get("summary_text", ""), "topics": structured.get("topics") or structured.get("stable_topics") or structured.get("long_term_topics") or [], "discussion_scenarios": structured.get("discussion_scenarios") or structured.get("common_scenarios") or [], "identity_clues": structured.get("identity_clues") or structured.get("identity_traits") or [], "skill_signals": structured.get("skill_signals") or structured.get("skill_profile") or [], "problem_solving_signals": structured.get("problem_solving_signals") or structured.get("problem_solving_profile") or [], "family_signals": structured.get("family_signals") or structured.get("family_profile") or [], "life_stage_signals": structured.get("life_stage_signals") or structured.get("life_stage_profile") or [], "value_preferences": structured.get("value_preferences") or structured.get("value_profile") or [], "habit_signals": structured.get("habit_signals") or structured.get("habit_patterns") or [], "expression_markers": structured.get("expression_markers") or structured.get("expression_profile") or [], "engagement_traits": structured.get("engagement_traits") or structured.get("stable_traits") or [], "reply_entry_points": structured.get("reply_entry_points") or structured.get("reply_entry_profile") or [], "reply_preferences": structured.get("reply_preferences") or structured.get("long_term_reply_preferences") or [], "social_role": structured.get("social_role") or structured.get("group_role") or "", "decision_style": structured.get("decision_style") or structured.get("decision_profile") or "", "temperament_signal": structured.get("temperament_signal") or structured.get("temperament_tendency") or "", "recent_state": structured.get("recent_state") or [], } structured_lines.append(json.dumps(payload, ensure_ascii=False)) if digest_type == "weekly": schema = ( "{" "\"stable_topics\":[\"主题1\"]," "\"common_scenarios\":[\"场景1\"]," "\"identity_traits\":[\"身份特征1\"]," "\"skill_profile\":[\"技能画像1\"]," "\"problem_solving_profile\":[\"处理方式1\"]," "\"family_profile\":[\"家庭线索1\"]," "\"life_stage_profile\":[\"阶段线索1\"]," "\"value_profile\":[\"价值偏好1\"]," "\"stable_traits\":[\"特征1\"]," "\"habit_patterns\":[\"习惯1\"]," "\"expression_profile\":[\"表达标记1\"]," "\"reply_entry_profile\":[\"接话点1\"]," "\"reply_preferences\":[\"偏好1\"]," "\"group_role\":\"一句中文\"," "\"decision_profile\":\"一句中文\"," "\"recent_state\":[\"状态1\"]," "\"temperament_tendency\":\"一句中文\"," "\"summary_text\":\"一段不超过120字的周摘要\"," "\"confidence\":0.0" "}" ) extra = "请从多个日摘要中提炼本周重复出现的模式，过滤单日噪音。" else: schema = ( "{" "\"long_term_topics\":[\"主题1\"]," "\"common_scenarios\":[\"场景1\"]," "\"identity_traits\":[\"身份特征1\"]," "\"skill_profile\":[\"技能画像1\"]," "\"problem_solving_profile\":[\"处理方式1\"]," "\"family_profile\":[\"家庭线索1\"]," "\"life_stage_profile\":[\"阶段线索1\"]," "\"value_profile\":[\"价值偏好1\"]," "\"stable_traits\":[\"特征1\"]," "\"habit_patterns\":[\"习惯1\"]," "\"expression_profile\":[\"表达标记1\"]," "\"reply_entry_profile\":[\"接话点1\"]," "\"long_term_reply_preferences\":[\"偏好1\"]," "\"group_role\":\"一句中文\"," "\"decision_profile\":\"一句中文\"," "\"phase_state\":[\"状态1\"]," "\"temperament_tendency\":\"一句中文\"," "\"summary_text\":\"一段不超过140字的月摘要\"," "\"confidence\":0.0" "}" ) extra = "请从多个周摘要中提炼阶段性稳定特征，只有反复出现的模式才能进入长期层。" return ( f"你是微信群后台的成员{digest_type}摘要生成器。\n" f"{extra}\n" "不可做心理诊断、负面评价、隐私猜测。输出严格 JSON，不要 markdown。\n" f"{schema}\n" "要求：\n" "1. 所有列表字段最多5项，必须中性克制。\n" "2. 只有多个下级摘要反复出现的特征，才允许写进 stable_traits / habit_patterns / long_term_reply_preferences。\n" "3. recent_state / phase_state 只描述当前阶段状态，不要冒充长期人格。\n" "4. identity_traits、family_profile、life_stage_profile 只能保留反复出现的公开线索，不可编造事实。\n" "5. common_scenarios 要总结这个人通常会在什么场景下参与，problem_solving_profile 要总结其典型处理问题方式，尽量具体到行为动作。\n" "6. skill_profile 要优先提炼稳定出现的能力、专业方向、擅长处理的问题类型。\n" "7. expression_profile 要保留反复出现的表达标记，如先说结论、爱列步骤、常贴原话/日志；reply_entry_profile 要总结适合接话的切入点。\n" "8. group_role 描述其在群中的长期角色位置，decision_profile 描述其决策与判断风格。\n" "9. value_profile 需要优先保留真正反复出现的判断偏好，如效率优先、成本敏感、风险谨慎、愿意分享。\n" f"成员: {display_name} ({wxid})\n" f"群ID: {chatroom_id}\n" f"周期: {period_key}\n" "下级摘要:\n" + ("\n".join(structured_lines) or "暂无") ) @staticmethod def build_final_context_prompt(chatroom_id: str, wxid: str, display_name: str, monthly_digests: List[Dict], weekly_digests: List[Dict], daily_digests: List[Dict]) -> str: monthly_lines = [json.dumps(item.get("structured", {}), ensure_ascii=False) for item in monthly_digests[:6]] weekly_lines = [json.dumps(item.get("structured", {}), ensure_ascii=False) for item in weekly_digests[:4]] daily_lines = [json.dumps(item.get("structured", {}), ensure_ascii=False) for item in daily_digests[:6]] return ( "你是微信群后台的最终成员交互画像整理器。\n" "请结合月级、周级、日级摘要，输出一个既有长期层又有近期层的后台交互画像。\n" "不要做敏感推断、心理诊断、隐私猜测。输出严格 JSON，不要 markdown。\n" "{" "\"activity_level\":\"高活跃|中活跃|低活跃|观察中\"," "\"message_pattern\":\"一句中文\"," "\"interaction_style\":\"一句中文\"," "\"response_style_hint\":\"一句中文\"," "\"topics_of_interest\":[\"主题1\"]," "\"recent_focus\":[\"近期主题1\"]," "\"common_scenarios\":[\"场景1\"]," "\"identity_traits\":[\"身份线索1\"]," "\"skill_profile\":[\"技能画像1\"]," "\"problem_solving_profile\":[\"处理方式1\"]," "\"family_profile\":[\"家庭线索1\"]," "\"life_stage_profile\":[\"阶段线索1\"]," "\"value_profile\":[\"价值偏好1\"]," "\"stable_traits\":[\"长期特征1\"]," "\"habit_patterns\":[\"习惯1\"]," "\"expression_profile\":[\"表达标记1\"]," "\"reply_entry_profile\":[\"接话点1\"]," "\"long_term_reply_preferences\":[\"偏好1\"]," "\"group_role\":\"一句中文\"," "\"decision_profile\":\"一句中文\"," "\"recent_state\":[\"近期状态1\"]," "\"temperament_tendency\":\"一句中文\"," "\"summary_text\":\"一段不超过150字的后台摘要\"," "\"confidence\":0.0," "\"engagement_traits\":[\"特征1\"]," "\"reply_taboos\":[\"避坑1\"]" "}\n" "要求：\n" "1. stable_traits、habit_patterns、long_term_reply_preferences 只从月级和多次重复证据中提取。\n" "2. recent_focus、recent_state 更依赖最近周级和日级。\n" "3. summary_text 要像后台备注，不要明显暴露在给用户做画像。\n" "4. identity_traits、family_profile、life_stage_profile 必须写成公开线索或长期观察，不得伪造事实。\n" "5. common_scenarios、problem_solving_profile、expression_profile、reply_entry_profile 要尽量写具体行为，不要只写抽象人格词。\n" "6. skill_profile 要尽量覆盖专业能力、问题解决能力、表达组织能力、资源协调能力等维度。\n" "7. group_role 要描述其在群中的角色定位，decision_profile 要描述其决策/判断方式。\n" "8. 如果月级与周级证据不足，宁可少写，也不要把短期状态写成长期人格。\n" f"成员: {display_name} ({wxid})\n" f"群ID: {chatroom_id}\n" "月级摘要:\n" + ("\n".join(monthly_lines) or "暂无") + "\n周级摘要:\n" + ("\n".join(weekly_lines) or "暂无") + "\n日级摘要:\n" + ("\n".join(daily_lines) or "暂无") )