mirror of
https://github.com/Nezumi-2711/astrbot_plugin_qq_group_daily_analysis.git
synced 2026-09-22 20:01:04 +00:00
refactor(增量分析): 从按天存储改为滑动窗口批次架构
- IncrementalBatch: 独立批次实体,每次增量分析产生一个,按批次独立存储到KV - IncrementalState: 聚合视图,不再持久化,报告时由merge_batches合并产生 - IncrementalStore: 批次索引+数据KV持久化,支持按时间窗口查询和过期清理 - IncrementalMergeService: 新增merge_batches方法,负责批次合并和话题/金句去重 - AnalysisApplicationService: 增量分析存独立批次,最终报告按窗口查询合并 - AutoScheduler: 报告发送后清理2×窗口外的过期批次 - main.py: /增量状态命令改为滑动窗口查询展示 - 消除天然日期隔离问题,24h图表展示完整数据
This commit is contained in:
@@ -6,9 +6,11 @@
|
||||
|
||||
import asyncio
|
||||
import datetime as dt
|
||||
import time as time_mod
|
||||
from collections import defaultdict
|
||||
from typing import Any
|
||||
|
||||
from ...domain.entities.incremental_state import IncrementalBatch
|
||||
from ...domain.models.data_models import TokenUsage
|
||||
from ...domain.repositories.analysis_repository import IAnalysisProvider
|
||||
from ...domain.repositories.report_repository import IReportGenerator
|
||||
@@ -185,10 +187,10 @@ class AnalysisApplicationService:
|
||||
self, group_id: str, platform_id: str | None = None
|
||||
) -> dict[str, Any]:
|
||||
"""
|
||||
执行一次增量分析用例。
|
||||
执行一次增量分析用例(滑动窗口批次架构)。
|
||||
|
||||
与每日分析不同,增量分析每次仅处理最近一段时间的消息,
|
||||
提取少量话题和金句,将结果合并到当天的累积状态中。
|
||||
提取少量话题和金句,将结果作为独立批次存储到 KV。
|
||||
不生成用户称号(留到最终报告时再做),不生成报告。
|
||||
|
||||
流程:
|
||||
@@ -199,8 +201,8 @@ class AnalysisApplicationService:
|
||||
5. 检查最小消息阈值
|
||||
6. 计算基础统计(小时分布、用户活跃、表情)
|
||||
7. LLM 增量分析(仅话题 + 金句)
|
||||
8. 构建合并参数并合并到 IncrementalState
|
||||
9. 持久化状态
|
||||
8. 构建 IncrementalBatch 并保存
|
||||
9. 更新最后分析消息时间戳
|
||||
10. 返回批次结果
|
||||
|
||||
Args:
|
||||
@@ -208,7 +210,7 @@ class AnalysisApplicationService:
|
||||
platform_id: 平台标识,缺省为默认
|
||||
|
||||
Returns:
|
||||
dict: 包含 success、batch_record、state_summary 等信息
|
||||
dict: 包含 success、batch_summary 等信息
|
||||
"""
|
||||
if not self.incremental_store:
|
||||
raise RuntimeError("增量分析未初始化:缺少 IncrementalStore")
|
||||
@@ -241,15 +243,16 @@ class AnalysisApplicationService:
|
||||
raw_messages, bot_self_ids=bot_self_ids, filter_commands=True
|
||||
)
|
||||
|
||||
# 4. 获取当天增量状态并按时间戳去重
|
||||
today_str = dt.datetime.now().strftime("%Y-%m-%d")
|
||||
state = await self.incremental_store.get_or_create_state(group_id, today_str)
|
||||
# 4. 按时间戳去重:获取最后分析消息时间戳
|
||||
last_analyzed_ts = await self.incremental_store.get_last_analyzed_timestamp(
|
||||
group_id
|
||||
)
|
||||
|
||||
if state.last_analyzed_message_timestamp > 0:
|
||||
if last_analyzed_ts > 0:
|
||||
unified_messages = [
|
||||
msg
|
||||
for msg in unified_messages
|
||||
if msg.timestamp > state.last_analyzed_message_timestamp
|
||||
if msg.timestamp > last_analyzed_ts
|
||||
]
|
||||
|
||||
# 5. 检查最小消息阈值
|
||||
@@ -297,7 +300,7 @@ class AnalysisApplicationService:
|
||||
)
|
||||
)
|
||||
|
||||
# 8. 构建合并参数
|
||||
# 8. 构建 IncrementalBatch
|
||||
# 8a. 转换话题: SummaryTopic -> dict
|
||||
new_topics = [
|
||||
{"topic": t.topic, "contributors": t.contributors, "detail": t.detail}
|
||||
@@ -322,7 +325,7 @@ class AnalysisApplicationService:
|
||||
"total_tokens": token_usage.total_tokens,
|
||||
}
|
||||
|
||||
# 8d. 转换用户统计: AnalysisDomainService 格式 -> IncrementalState 格式
|
||||
# 8d. 转换用户统计: AnalysisDomainService 格式 -> IncrementalBatch 格式
|
||||
user_stats = self._convert_user_activity_for_merge(
|
||||
user_activity, unified_messages
|
||||
)
|
||||
@@ -338,7 +341,7 @@ class AnalysisApplicationService:
|
||||
}
|
||||
|
||||
# 8f. 获取参与者 ID 和最后消息时间戳
|
||||
participant_ids = {msg.sender_id for msg in unified_messages}
|
||||
participant_ids = list({msg.sender_id for msg in unified_messages})
|
||||
last_message_timestamp = max(
|
||||
(msg.timestamp for msg in unified_messages), default=0
|
||||
)
|
||||
@@ -346,35 +349,38 @@ class AnalysisApplicationService:
|
||||
# 8g. 计算本批次总字符数
|
||||
characters_count = sum(msg.get_text_length() for msg in unified_messages)
|
||||
|
||||
# 9. 合并到增量状态
|
||||
batch_record = state.merge_batch(
|
||||
# 构建批次对象
|
||||
batch = IncrementalBatch(
|
||||
group_id=group_id,
|
||||
timestamp=time_mod.time(),
|
||||
messages_count=len(unified_messages),
|
||||
characters_count=characters_count,
|
||||
hourly_msg_counts=hourly_msg_counts,
|
||||
hourly_char_counts=hourly_char_counts,
|
||||
hourly_msg_counts={str(k): v for k, v in hourly_msg_counts.items()},
|
||||
hourly_char_counts={str(k): v for k, v in hourly_char_counts.items()},
|
||||
user_stats=user_stats,
|
||||
emoji_stats=emoji_stats,
|
||||
new_topics=new_topics,
|
||||
new_quotes=new_quotes,
|
||||
topics=new_topics,
|
||||
golden_quotes=new_quotes,
|
||||
token_usage=token_usage_dict,
|
||||
last_message_timestamp=last_message_timestamp,
|
||||
participant_ids=participant_ids,
|
||||
)
|
||||
|
||||
# 10. 持久化状态
|
||||
await self.incremental_store.save_state(state)
|
||||
# 9. 保存批次并更新最后分析时间戳
|
||||
await self.incremental_store.save_batch(batch)
|
||||
await self.incremental_store.update_last_analyzed_timestamp(
|
||||
group_id, last_message_timestamp
|
||||
)
|
||||
|
||||
logger.info(
|
||||
f"群 {group_id} 增量分析完成: "
|
||||
f"本批次消息={len(unified_messages)}, "
|
||||
f"新话题={len(new_topics)}, 新金句={len(new_quotes)}, "
|
||||
f"累计分析次数={state.total_analysis_count}"
|
||||
f"新话题={len(new_topics)}, 新金句={len(new_quotes)}"
|
||||
)
|
||||
|
||||
return {
|
||||
"success": True,
|
||||
"batch_record": batch_record.to_dict(),
|
||||
"state_summary": state.get_summary(),
|
||||
"batch_summary": batch.get_summary(),
|
||||
"messages_count": len(unified_messages),
|
||||
}
|
||||
|
||||
@@ -382,19 +388,21 @@ class AnalysisApplicationService:
|
||||
self, group_id: str, platform_id: str | None = None
|
||||
) -> dict[str, Any]:
|
||||
"""
|
||||
基于当天增量累积状态生成最终报告。
|
||||
基于滑动窗口内的增量批次生成最终报告。
|
||||
|
||||
将一天内多次增量分析积累的话题、金句、统计数据汇总,
|
||||
额外执行用户称号分析(需要完整的累积数据),然后生成
|
||||
与传统每日分析格式完全一致的 analysis_result。
|
||||
按 analysis_days × 24h 的时间窗口查询所有批次,
|
||||
合并为 IncrementalState,额外执行用户称号分析,
|
||||
然后生成与传统每日分析格式完全一致的 analysis_result。
|
||||
|
||||
流程:
|
||||
1. 加载当天增量状态
|
||||
2. 检查状态有效性
|
||||
3. 执行用户称号 LLM 分析(基于累积数据)
|
||||
4. 使用 IncrementalMergeService 构建 analysis_result
|
||||
5. 持久化到 history_manager
|
||||
6. 返回结果
|
||||
1. 计算滑动窗口范围
|
||||
2. 查询窗口内的所有批次
|
||||
3. 检查批次有效性
|
||||
4. 合并批次为 IncrementalState
|
||||
5. 执行用户称号 LLM 分析(基于合并后的累积数据)
|
||||
6. 使用 IncrementalMergeService 构建 analysis_result
|
||||
7. 持久化到 history_manager
|
||||
8. 返回结果
|
||||
|
||||
Args:
|
||||
group_id: 群组 ID
|
||||
@@ -410,34 +418,42 @@ class AnalysisApplicationService:
|
||||
|
||||
logger.info(f"开始增量最终报告: 群 {group_id}, 平台 {platform_id or '默认'}")
|
||||
|
||||
# 1. 加载当天增量状态
|
||||
today_str = dt.datetime.now().strftime("%Y-%m-%d")
|
||||
state = await self.incremental_store.get_state(group_id, today_str)
|
||||
# 1. 计算滑动窗口范围
|
||||
analysis_days = self.config_manager.get_analysis_days()
|
||||
window_end = time_mod.time()
|
||||
window_start = window_end - (analysis_days * 24 * 3600)
|
||||
|
||||
# 2. 检查状态有效性
|
||||
if not state or state.total_analysis_count == 0:
|
||||
# 2. 查询窗口内的所有批次
|
||||
batches = await self.incremental_store.query_batches(
|
||||
group_id, window_start, window_end
|
||||
)
|
||||
|
||||
# 3. 检查批次有效性
|
||||
if not batches:
|
||||
logger.warning(
|
||||
f"群 {group_id} 无当天增量分析数据,无法生成最终报告"
|
||||
f"群 {group_id} 滑动窗口内无增量分析数据,无法生成最终报告"
|
||||
)
|
||||
return {"success": False, "reason": "no_incremental_data"}
|
||||
|
||||
# 3. 获取适配器(报告发送需要)
|
||||
# 4. 合并批次为 IncrementalState
|
||||
state = self.incremental_merge_service.merge_batches(
|
||||
batches, window_start, window_end
|
||||
)
|
||||
|
||||
# 5. 获取适配器(报告发送需要)
|
||||
adapter = self.bot_manager.get_adapter(platform_id)
|
||||
if not adapter:
|
||||
raise ValueError(f"未找到平台 {platform_id} 的适配器")
|
||||
|
||||
# 4. 执行用户称号 LLM 分析
|
||||
# 6. 执行用户称号 LLM 分析
|
||||
user_titles = []
|
||||
user_title_enabled = self.config_manager.get_user_title_analysis_enabled()
|
||||
|
||||
if user_title_enabled and state.user_activities:
|
||||
max_user_titles = self.config_manager.get_max_user_titles()
|
||||
# 从累积的 user_activities 中取出 top 用户
|
||||
# 从合并后的 user_activities 中取出 top 用户
|
||||
top_users = state.get_user_activity_ranking(max_user_titles)
|
||||
|
||||
# 准备用户称号分析所需的 legacy 消息格式
|
||||
# 因为增量模式不保存原始消息,这里用空列表
|
||||
# 用户称号分析器主要依赖 user_analysis 和 top_users,消息内容非必需
|
||||
unified_msg_origin = (
|
||||
f"{platform_id}:GroupMessage:{group_id}"
|
||||
if platform_id
|
||||
@@ -468,20 +484,20 @@ class AnalysisApplicationService:
|
||||
state.total_token_usage.get("total_tokens", 0)
|
||||
+ title_token_usage.total_tokens
|
||||
)
|
||||
await self.incremental_store.save_state(state)
|
||||
except Exception as e:
|
||||
logger.error(f"增量最终报告用户称号分析失败: {e}", exc_info=True)
|
||||
|
||||
# 5. 构建 analysis_result
|
||||
# 7. 构建 analysis_result
|
||||
analysis_result = self.incremental_merge_service.build_analysis_result(
|
||||
state, user_titles
|
||||
)
|
||||
|
||||
# 6. 持久化到 history_manager
|
||||
# 8. 持久化到 history_manager
|
||||
await self.history_manager.save_analysis(group_id, analysis_result)
|
||||
|
||||
logger.info(
|
||||
f"群 {group_id} 增量最终报告完成: "
|
||||
f"窗口={state.get_window_date_str()}, "
|
||||
f"累计消息={state.total_message_count}, "
|
||||
f"话题={len(state.topics)}, 金句={len(state.golden_quotes)}, "
|
||||
f"批次={state.total_analysis_count}"
|
||||
@@ -528,7 +544,7 @@ class AnalysisApplicationService:
|
||||
) -> dict[str, dict]:
|
||||
"""
|
||||
将 AnalysisDomainService.analyze_user_activity() 的返回格式
|
||||
转换为 IncrementalState.merge_batch() 所需的 user_stats 格式。
|
||||
转换为 IncrementalBatch 所需的 user_stats 格式。
|
||||
|
||||
转换映射:
|
||||
- nickname -> name
|
||||
@@ -540,7 +556,7 @@ class AnalysisApplicationService:
|
||||
messages: 本批次的消息列表(用于提取每个用户的最后发言时间)
|
||||
|
||||
Returns:
|
||||
dict: IncrementalState.merge_batch() 所需的 user_stats 格式
|
||||
dict: IncrementalBatch 所需的 user_stats 格式
|
||||
"""
|
||||
# 预先计算每个用户的最后消息时间戳
|
||||
user_last_time: dict[str, int] = {}
|
||||
|
||||
@@ -4,8 +4,8 @@
|
||||
该模块导出所有领域实体类,包括:
|
||||
- AnalysisTask: 分析任务聚合根
|
||||
- GroupAnalysisResult: 群聊分析结果实体
|
||||
- IncrementalState: 增量分析状态实体
|
||||
- BatchRecord: 增量分析批次记录
|
||||
- IncrementalBatch: 增量分析独立批次实体
|
||||
- IncrementalState: 增量分析聚合视图(报告时使用)
|
||||
"""
|
||||
|
||||
from .analysis_result import (
|
||||
@@ -19,7 +19,7 @@ from .analysis_result import (
|
||||
UserTitle,
|
||||
)
|
||||
from .analysis_task import AnalysisTask, TaskStatus
|
||||
from .incremental_state import BatchRecord, IncrementalState
|
||||
from .incremental_state import IncrementalBatch, IncrementalState
|
||||
|
||||
# 别名,保持向后兼容
|
||||
AnalysisResult = GroupAnalysisResult
|
||||
@@ -36,6 +36,6 @@ __all__ = [
|
||||
"EmojiStatistics",
|
||||
"ActivityVisualization",
|
||||
"GroupStatistics",
|
||||
"IncrementalBatch",
|
||||
"IncrementalState",
|
||||
"BatchRecord",
|
||||
]
|
||||
|
||||
@@ -1,88 +1,171 @@
|
||||
"""
|
||||
增量分析状态实体
|
||||
增量分析实体 — 滑动窗口批次存储架构
|
||||
|
||||
存储单个群聊在一天内累积的增量分析数据。
|
||||
每次增量分析产生一个批次(batch),批次结果合并到此状态中。
|
||||
最终报告时从此状态中提取完整的统计数据和分析内容。
|
||||
核心概念:
|
||||
- IncrementalBatch: 单次增量分析产生的独立批次数据,按批次独立存储
|
||||
- IncrementalState: 报告生成时由多个批次合并而成的聚合视图(不再持久化)
|
||||
|
||||
滑动窗口设计:
|
||||
- 每次增量分析产生一个 IncrementalBatch,独立存储到 KV
|
||||
- 最终报告时按 analysis_days × 24h 的时间窗口查询批次并合并
|
||||
- 支持同一天多次发送报告,每次都基于当前时间窗口内的所有批次
|
||||
"""
|
||||
|
||||
import time
|
||||
import uuid
|
||||
from dataclasses import dataclass, field
|
||||
from datetime import datetime
|
||||
|
||||
|
||||
@dataclass
|
||||
class BatchRecord:
|
||||
"""单次增量分析批次记录"""
|
||||
class IncrementalBatch:
|
||||
"""
|
||||
单次增量分析批次数据
|
||||
|
||||
batch_id: int = 0
|
||||
timestamp: float = 0.0
|
||||
message_count: int = 0
|
||||
new_topics_count: int = 0
|
||||
new_quotes_count: int = 0
|
||||
token_usage: dict = field(default_factory=dict)
|
||||
每次增量分析执行完毕后产生一个 IncrementalBatch,
|
||||
包含该批次的所有统计数据和 LLM 分析结果,独立存储到 KV。
|
||||
|
||||
Attributes:
|
||||
group_id: 群组 ID
|
||||
batch_id: 批次唯一标识(UUID)
|
||||
timestamp: 批次创建时间戳(epoch)
|
||||
messages_count: 本批次分析的消息数量
|
||||
characters_count: 本批次的总字符数
|
||||
hourly_msg_counts: 按小时的消息计数 {hour_str: count}
|
||||
hourly_char_counts: 按小时的字符计数 {hour_str: count}
|
||||
user_stats: 用户统计 {user_id: {name, message_count, char_count, ...}}
|
||||
emoji_stats: 表情统计 {emoji_type: count}
|
||||
topics: 本批次提取的话题列表
|
||||
golden_quotes: 本批次提取的金句列表
|
||||
token_usage: 本批次 token 消耗 {prompt_tokens, completion_tokens, total_tokens}
|
||||
last_message_timestamp: 本批次最后一条消息的时间戳
|
||||
participant_ids: 本批次参与者 ID 列表
|
||||
"""
|
||||
|
||||
group_id: str = ""
|
||||
batch_id: str = field(default_factory=lambda: str(uuid.uuid4()))
|
||||
timestamp: float = field(default_factory=time.time)
|
||||
|
||||
# 统计数据
|
||||
messages_count: int = 0
|
||||
characters_count: int = 0
|
||||
hourly_msg_counts: dict[str, int] = field(default_factory=dict)
|
||||
hourly_char_counts: dict[str, int] = field(default_factory=dict)
|
||||
|
||||
# 用户活跃数据
|
||||
user_stats: dict[str, dict] = field(default_factory=dict)
|
||||
|
||||
# 表情统计
|
||||
emoji_stats: dict[str, int] = field(default_factory=dict)
|
||||
|
||||
# LLM 分析结果
|
||||
topics: list[dict] = field(default_factory=list)
|
||||
golden_quotes: list[dict] = field(default_factory=list)
|
||||
|
||||
# Token 消耗
|
||||
token_usage: dict = field(default_factory=lambda: {
|
||||
"prompt_tokens": 0,
|
||||
"completion_tokens": 0,
|
||||
"total_tokens": 0,
|
||||
})
|
||||
|
||||
# 增量追踪
|
||||
last_message_timestamp: int = 0
|
||||
participant_ids: list[str] = field(default_factory=list)
|
||||
|
||||
def to_dict(self) -> dict:
|
||||
"""序列化为字典"""
|
||||
"""序列化为字典,用于 KV 存储"""
|
||||
return {
|
||||
"group_id": self.group_id,
|
||||
"batch_id": self.batch_id,
|
||||
"timestamp": self.timestamp,
|
||||
"message_count": self.message_count,
|
||||
"new_topics_count": self.new_topics_count,
|
||||
"new_quotes_count": self.new_quotes_count,
|
||||
"messages_count": self.messages_count,
|
||||
"characters_count": self.characters_count,
|
||||
"hourly_msg_counts": self.hourly_msg_counts,
|
||||
"hourly_char_counts": self.hourly_char_counts,
|
||||
"user_stats": self.user_stats,
|
||||
"emoji_stats": self.emoji_stats,
|
||||
"topics": self.topics,
|
||||
"golden_quotes": self.golden_quotes,
|
||||
"token_usage": self.token_usage,
|
||||
"last_message_timestamp": self.last_message_timestamp,
|
||||
"participant_ids": self.participant_ids,
|
||||
}
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, data: dict) -> "BatchRecord":
|
||||
def from_dict(cls, data: dict) -> "IncrementalBatch":
|
||||
"""从字典反序列化"""
|
||||
return cls(
|
||||
batch_id=data.get("batch_id", 0),
|
||||
group_id=data.get("group_id", ""),
|
||||
batch_id=data.get("batch_id", ""),
|
||||
timestamp=data.get("timestamp", 0.0),
|
||||
message_count=data.get("message_count", 0),
|
||||
new_topics_count=data.get("new_topics_count", 0),
|
||||
new_quotes_count=data.get("new_quotes_count", 0),
|
||||
token_usage=data.get("token_usage", {}),
|
||||
messages_count=data.get("messages_count", 0),
|
||||
characters_count=data.get("characters_count", 0),
|
||||
hourly_msg_counts=data.get("hourly_msg_counts", {}),
|
||||
hourly_char_counts=data.get("hourly_char_counts", {}),
|
||||
user_stats=data.get("user_stats", {}),
|
||||
emoji_stats=data.get("emoji_stats", {}),
|
||||
topics=data.get("topics", []),
|
||||
golden_quotes=data.get("golden_quotes", []),
|
||||
token_usage=data.get("token_usage", {
|
||||
"prompt_tokens": 0,
|
||||
"completion_tokens": 0,
|
||||
"total_tokens": 0,
|
||||
}),
|
||||
last_message_timestamp=data.get("last_message_timestamp", 0),
|
||||
participant_ids=data.get("participant_ids", []),
|
||||
)
|
||||
|
||||
def get_summary(self) -> dict:
|
||||
"""获取批次摘要信息"""
|
||||
return {
|
||||
"batch_id": self.batch_id[:8],
|
||||
"timestamp": datetime.fromtimestamp(self.timestamp).strftime(
|
||||
"%Y-%m-%d %H:%M:%S"
|
||||
),
|
||||
"messages_count": self.messages_count,
|
||||
"topics_count": len(self.topics),
|
||||
"quotes_count": len(self.golden_quotes),
|
||||
"participants": len(self.participant_ids),
|
||||
}
|
||||
|
||||
|
||||
@dataclass
|
||||
class IncrementalState:
|
||||
"""
|
||||
增量分析状态聚合实体
|
||||
增量分析聚合视图(报告时使用)
|
||||
|
||||
该实体代表一个群聊在一天内的增量分析累积状态。
|
||||
随着当天多次增量分析的执行,话题、金句、统计数据会不断合并更新。
|
||||
由多个 IncrementalBatch 合并而成,不直接持久化。
|
||||
IncrementalMergeService.merge_batches() 负责从批次列表构建此对象。
|
||||
|
||||
Attributes:
|
||||
group_id: 群组 ID
|
||||
date_str: 日期字符串 (YYYY-MM-DD)
|
||||
topics: 累积的话题列表(每个元素为 dict,包含 topic/contributors/detail)
|
||||
golden_quotes: 累积的金句列表(每个元素为 dict,包含 content/sender/reason)
|
||||
hourly_message_counts: 每小时消息计数 {hour_int: count}
|
||||
hourly_character_counts: 每小时字符计数 {hour_int: count}
|
||||
user_activities: 用户活跃数据 {user_id: {name, message_count, char_count, ...}}
|
||||
emoji_counts: 表情统计 {emoji_type: count}
|
||||
batch_records: 已完成的增量分析批次记录
|
||||
total_message_count: 当天总消息数
|
||||
total_character_count: 当天总字符数
|
||||
total_analysis_count: 当天已执行的增量分析次数
|
||||
window_start: 滑动窗口起始时间戳
|
||||
window_end: 滑动窗口结束时间戳
|
||||
topics: 合并去重后的话题列表
|
||||
golden_quotes: 合并去重后的金句列表
|
||||
hourly_message_counts: 合并后的每小时消息计数 {hour_str: count}
|
||||
hourly_character_counts: 合并后的每小时字符计数 {hour_str: count}
|
||||
user_activities: 合并后的用户活跃数据
|
||||
emoji_counts: 合并后的表情统计
|
||||
total_message_count: 窗口内总消息数
|
||||
total_character_count: 窗口内总字符数
|
||||
total_analysis_count: 窗口内批次数量
|
||||
total_token_usage: 累计 token 消耗
|
||||
last_analyzed_message_timestamp: 上次分析的最后一条消息时间戳(用于去重)
|
||||
last_analyzed_message_timestamp: 最后分析消息时间戳
|
||||
all_participant_ids: 所有参与者 ID 集合
|
||||
created_at: 状态创建时间
|
||||
updated_at: 状态最后更新时间
|
||||
"""
|
||||
|
||||
# 标识信息
|
||||
group_id: str = ""
|
||||
date_str: str = ""
|
||||
window_start: float = 0.0
|
||||
window_end: float = 0.0
|
||||
|
||||
# 累积的 LLM 分析结果
|
||||
# 合并后的 LLM 分析结果
|
||||
topics: list[dict] = field(default_factory=list)
|
||||
golden_quotes: list[dict] = field(default_factory=list)
|
||||
|
||||
# 累积的统计数据(按小时)
|
||||
# 合并后的统计数据(按小时)
|
||||
hourly_message_counts: dict[str, int] = field(default_factory=dict)
|
||||
hourly_character_counts: dict[str, int] = field(default_factory=dict)
|
||||
|
||||
@@ -92,9 +175,6 @@ class IncrementalState:
|
||||
# 表情统计
|
||||
emoji_counts: dict[str, int] = field(default_factory=dict)
|
||||
|
||||
# 批次记录
|
||||
batch_records: list[BatchRecord] = field(default_factory=list)
|
||||
|
||||
# 汇总统计
|
||||
total_message_count: int = 0
|
||||
total_character_count: int = 0
|
||||
@@ -113,205 +193,6 @@ class IncrementalState:
|
||||
created_at: float = field(default_factory=time.time)
|
||||
updated_at: float = field(default_factory=time.time)
|
||||
|
||||
def merge_batch(
|
||||
self,
|
||||
messages_count: int,
|
||||
characters_count: int,
|
||||
hourly_msg_counts: dict[int, int],
|
||||
hourly_char_counts: dict[int, int],
|
||||
user_stats: dict[str, dict],
|
||||
emoji_stats: dict[str, int],
|
||||
new_topics: list[dict],
|
||||
new_quotes: list[dict],
|
||||
token_usage: dict,
|
||||
last_message_timestamp: int,
|
||||
participant_ids: set[str],
|
||||
) -> "BatchRecord":
|
||||
"""
|
||||
合并一次增量分析的结果到当前状态中。
|
||||
|
||||
Args:
|
||||
messages_count: 本批次分析的消息数量
|
||||
characters_count: 本批次的总字符数
|
||||
hourly_msg_counts: 本批次按小时的消息计数 {hour: count}
|
||||
hourly_char_counts: 本批次按小时的字符计数 {hour: count}
|
||||
user_stats: 本批次用户统计 {user_id: {name, message_count, char_count, ...}}
|
||||
emoji_stats: 本批次表情统计 {emoji_type: count}
|
||||
new_topics: 本批次提取的新话题
|
||||
new_quotes: 本批次提取的新金句
|
||||
token_usage: 本批次 token 消耗 {prompt_tokens, completion_tokens, total_tokens}
|
||||
last_message_timestamp: 本批次最后一条消息的时间戳
|
||||
participant_ids: 本批次参与者 ID 集合
|
||||
|
||||
Returns:
|
||||
BatchRecord: 本次批次的记录
|
||||
"""
|
||||
# 更新统计汇总
|
||||
self.total_message_count += messages_count
|
||||
self.total_character_count += characters_count
|
||||
self.total_analysis_count += 1
|
||||
|
||||
# 合并小时统计
|
||||
for hour, count in hourly_msg_counts.items():
|
||||
hour_key = str(hour)
|
||||
self.hourly_message_counts[hour_key] = (
|
||||
self.hourly_message_counts.get(hour_key, 0) + count
|
||||
)
|
||||
for hour, count in hourly_char_counts.items():
|
||||
hour_key = str(hour)
|
||||
self.hourly_character_counts[hour_key] = (
|
||||
self.hourly_character_counts.get(hour_key, 0) + count
|
||||
)
|
||||
|
||||
# 合并用户活跃数据
|
||||
for user_id, stats in user_stats.items():
|
||||
if user_id in self.user_activities:
|
||||
existing = self.user_activities[user_id]
|
||||
existing["message_count"] = (
|
||||
existing.get("message_count", 0) + stats.get("message_count", 0)
|
||||
)
|
||||
existing["char_count"] = (
|
||||
existing.get("char_count", 0) + stats.get("char_count", 0)
|
||||
)
|
||||
existing["emoji_count"] = (
|
||||
existing.get("emoji_count", 0) + stats.get("emoji_count", 0)
|
||||
)
|
||||
# 合并活跃小时集合
|
||||
existing_hours = set(existing.get("active_hours", []))
|
||||
new_hours = set(stats.get("active_hours", []))
|
||||
existing["active_hours"] = list(existing_hours | new_hours)
|
||||
# 更新最后发言时间
|
||||
if stats.get("last_message_time", 0) > existing.get("last_message_time", 0):
|
||||
existing["last_message_time"] = stats["last_message_time"]
|
||||
else:
|
||||
self.user_activities[user_id] = dict(stats)
|
||||
|
||||
# 合并表情统计
|
||||
for emoji_type, count in emoji_stats.items():
|
||||
self.emoji_counts[emoji_type] = (
|
||||
self.emoji_counts.get(emoji_type, 0) + count
|
||||
)
|
||||
|
||||
# 合并话题(带去重)
|
||||
for new_topic in new_topics:
|
||||
if not self._is_duplicate_topic(new_topic):
|
||||
self.topics.append(new_topic)
|
||||
|
||||
# 合并金句(带去重)
|
||||
for new_quote in new_quotes:
|
||||
if not self._is_duplicate_quote(new_quote):
|
||||
self.golden_quotes.append(new_quote)
|
||||
|
||||
# 更新 token 消耗
|
||||
self.total_token_usage["prompt_tokens"] = (
|
||||
self.total_token_usage.get("prompt_tokens", 0)
|
||||
+ token_usage.get("prompt_tokens", 0)
|
||||
)
|
||||
self.total_token_usage["completion_tokens"] = (
|
||||
self.total_token_usage.get("completion_tokens", 0)
|
||||
+ token_usage.get("completion_tokens", 0)
|
||||
)
|
||||
self.total_token_usage["total_tokens"] = (
|
||||
self.total_token_usage.get("total_tokens", 0)
|
||||
+ token_usage.get("total_tokens", 0)
|
||||
)
|
||||
|
||||
# 更新增量追踪
|
||||
if last_message_timestamp > self.last_analyzed_message_timestamp:
|
||||
self.last_analyzed_message_timestamp = last_message_timestamp
|
||||
self.all_participant_ids.update(participant_ids)
|
||||
|
||||
# 更新时间戳
|
||||
self.updated_at = time.time()
|
||||
|
||||
# 创建批次记录
|
||||
batch = BatchRecord(
|
||||
batch_id=self.total_analysis_count,
|
||||
timestamp=time.time(),
|
||||
message_count=messages_count,
|
||||
new_topics_count=len(new_topics),
|
||||
new_quotes_count=len(new_quotes),
|
||||
token_usage=dict(token_usage),
|
||||
)
|
||||
self.batch_records.append(batch)
|
||||
|
||||
return batch
|
||||
|
||||
def _is_duplicate_topic(self, new_topic: dict, threshold: float = 0.6) -> bool:
|
||||
"""
|
||||
检测话题是否与已有话题重复。
|
||||
|
||||
使用简单的字符重叠相似度判断。
|
||||
当新话题的名称与已有话题名称相似度超过阈值时,认为是重复话题。
|
||||
|
||||
Args:
|
||||
new_topic: 待检测的新话题
|
||||
threshold: 相似度阈值(0-1),默认 0.6
|
||||
|
||||
Returns:
|
||||
bool: 是否重复
|
||||
"""
|
||||
new_name = new_topic.get("topic", "")
|
||||
if not new_name:
|
||||
return False
|
||||
|
||||
for existing in self.topics:
|
||||
existing_name = existing.get("topic", "")
|
||||
if not existing_name:
|
||||
continue
|
||||
similarity = self._char_overlap_similarity(new_name, existing_name)
|
||||
if similarity >= threshold:
|
||||
return True
|
||||
return False
|
||||
|
||||
def _is_duplicate_quote(self, new_quote: dict, threshold: float = 0.7) -> bool:
|
||||
"""
|
||||
检测金句是否与已有金句重复。
|
||||
|
||||
Args:
|
||||
new_quote: 待检测的新金句
|
||||
threshold: 相似度阈值(0-1),默认 0.7
|
||||
|
||||
Returns:
|
||||
bool: 是否重复
|
||||
"""
|
||||
new_content = new_quote.get("content", "")
|
||||
if not new_content:
|
||||
return False
|
||||
|
||||
for existing in self.golden_quotes:
|
||||
existing_content = existing.get("content", "")
|
||||
if not existing_content:
|
||||
continue
|
||||
similarity = self._char_overlap_similarity(new_content, existing_content)
|
||||
if similarity >= threshold:
|
||||
return True
|
||||
return False
|
||||
|
||||
@staticmethod
|
||||
def _char_overlap_similarity(s1: str, s2: str) -> float:
|
||||
"""
|
||||
计算两个字符串的字符重叠相似度。
|
||||
|
||||
使用 Jaccard 相似系数:交集大小 / 并集大小。
|
||||
|
||||
Args:
|
||||
s1: 第一个字符串
|
||||
s2: 第二个字符串
|
||||
|
||||
Returns:
|
||||
float: 相似度值(0-1)
|
||||
"""
|
||||
if not s1 or not s2:
|
||||
return 0.0
|
||||
set1 = set(s1)
|
||||
set2 = set(s2)
|
||||
intersection = set1 & set2
|
||||
union = set1 | set2
|
||||
if not union:
|
||||
return 0.0
|
||||
return len(intersection) / len(union)
|
||||
|
||||
def get_peak_hours(self, top_n: int = 3) -> list[int]:
|
||||
"""
|
||||
获取消息最活跃的时段。
|
||||
@@ -365,71 +246,22 @@ class IncrementalState:
|
||||
users.sort(key=lambda x: x["message_count"], reverse=True)
|
||||
return users[:top_n]
|
||||
|
||||
def to_dict(self) -> dict:
|
||||
def get_window_date_str(self) -> str:
|
||||
"""
|
||||
序列化为字典,用于 KV 存储持久化。
|
||||
获取窗口的日期范围字符串,用于报告显示。
|
||||
|
||||
Returns:
|
||||
dict: 可 JSON 序列化的字典
|
||||
str: 如 "2024-01-15" 或 "2024-01-14 ~ 2024-01-15"
|
||||
"""
|
||||
return {
|
||||
"group_id": self.group_id,
|
||||
"date_str": self.date_str,
|
||||
"topics": self.topics,
|
||||
"golden_quotes": self.golden_quotes,
|
||||
"hourly_message_counts": self.hourly_message_counts,
|
||||
"hourly_character_counts": self.hourly_character_counts,
|
||||
"user_activities": self.user_activities,
|
||||
"emoji_counts": self.emoji_counts,
|
||||
"batch_records": [b.to_dict() for b in self.batch_records],
|
||||
"total_message_count": self.total_message_count,
|
||||
"total_character_count": self.total_character_count,
|
||||
"total_analysis_count": self.total_analysis_count,
|
||||
"total_token_usage": self.total_token_usage,
|
||||
"last_analyzed_message_timestamp": self.last_analyzed_message_timestamp,
|
||||
"all_participant_ids": list(self.all_participant_ids),
|
||||
"created_at": self.created_at,
|
||||
"updated_at": self.updated_at,
|
||||
}
|
||||
if self.window_start <= 0 or self.window_end <= 0:
|
||||
return datetime.now().strftime("%Y-%m-%d")
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, data: dict) -> "IncrementalState":
|
||||
"""
|
||||
从字典反序列化。
|
||||
start_date = datetime.fromtimestamp(self.window_start).strftime("%Y-%m-%d")
|
||||
end_date = datetime.fromtimestamp(self.window_end).strftime("%Y-%m-%d")
|
||||
|
||||
Args:
|
||||
data: 从 KV 存储读取的字典数据
|
||||
|
||||
Returns:
|
||||
IncrementalState: 重建的状态实例
|
||||
"""
|
||||
state = cls(
|
||||
group_id=data.get("group_id", ""),
|
||||
date_str=data.get("date_str", ""),
|
||||
topics=data.get("topics", []),
|
||||
golden_quotes=data.get("golden_quotes", []),
|
||||
hourly_message_counts=data.get("hourly_message_counts", {}),
|
||||
hourly_character_counts=data.get("hourly_character_counts", {}),
|
||||
user_activities=data.get("user_activities", {}),
|
||||
emoji_counts=data.get("emoji_counts", {}),
|
||||
batch_records=[
|
||||
BatchRecord.from_dict(b)
|
||||
for b in data.get("batch_records", [])
|
||||
],
|
||||
total_message_count=data.get("total_message_count", 0),
|
||||
total_character_count=data.get("total_character_count", 0),
|
||||
total_analysis_count=data.get("total_analysis_count", 0),
|
||||
total_token_usage=data.get("total_token_usage", {
|
||||
"prompt_tokens": 0,
|
||||
"completion_tokens": 0,
|
||||
"total_tokens": 0,
|
||||
}),
|
||||
last_analyzed_message_timestamp=data.get("last_analyzed_message_timestamp", 0),
|
||||
all_participant_ids=set(data.get("all_participant_ids", [])),
|
||||
created_at=data.get("created_at", time.time()),
|
||||
updated_at=data.get("updated_at", time.time()),
|
||||
)
|
||||
return state
|
||||
if start_date == end_date:
|
||||
return end_date
|
||||
return f"{start_date} ~ {end_date}"
|
||||
|
||||
def get_summary(self) -> dict:
|
||||
"""
|
||||
@@ -440,7 +272,7 @@ class IncrementalState:
|
||||
"""
|
||||
return {
|
||||
"group_id": self.group_id,
|
||||
"date": self.date_str,
|
||||
"window": self.get_window_date_str(),
|
||||
"total_messages": self.total_message_count,
|
||||
"total_characters": self.total_character_count,
|
||||
"total_analyses": self.total_analysis_count,
|
||||
@@ -455,3 +287,88 @@ class IncrementalState:
|
||||
),
|
||||
"peak_hours": self.get_peak_hours(3),
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def is_duplicate_topic(
|
||||
new_topic: dict, existing_topics: list[dict], threshold: float = 0.6
|
||||
) -> bool:
|
||||
"""
|
||||
检测话题是否与已有话题重复。
|
||||
|
||||
使用简单的字符重叠相似度判断。
|
||||
当新话题的名称与已有话题名称相似度超过阈值时,认为是重复话题。
|
||||
|
||||
Args:
|
||||
new_topic: 待检测的新话题
|
||||
existing_topics: 已有话题列表
|
||||
threshold: 相似度阈值(0-1),默认 0.6
|
||||
|
||||
Returns:
|
||||
bool: 是否重复
|
||||
"""
|
||||
new_name = new_topic.get("topic", "")
|
||||
if not new_name:
|
||||
return False
|
||||
|
||||
for existing in existing_topics:
|
||||
existing_name = existing.get("topic", "")
|
||||
if not existing_name:
|
||||
continue
|
||||
similarity = IncrementalState.char_overlap_similarity(
|
||||
new_name, existing_name
|
||||
)
|
||||
if similarity >= threshold:
|
||||
return True
|
||||
return False
|
||||
|
||||
@staticmethod
|
||||
def is_duplicate_quote(
|
||||
new_quote: dict, existing_quotes: list[dict], threshold: float = 0.7
|
||||
) -> bool:
|
||||
"""
|
||||
检测金句是否与已有金句重复。
|
||||
|
||||
Args:
|
||||
new_quote: 待检测的新金句
|
||||
existing_quotes: 已有金句列表
|
||||
threshold: 相似度阈值(0-1),默认 0.7
|
||||
|
||||
Returns:
|
||||
bool: 是否重复
|
||||
"""
|
||||
new_content = new_quote.get("content", "")
|
||||
if not new_content:
|
||||
return False
|
||||
|
||||
for existing in existing_quotes:
|
||||
existing_content = existing.get("content", "")
|
||||
if not existing_content:
|
||||
continue
|
||||
similarity = IncrementalState.char_overlap_similarity(
|
||||
new_content, existing_content
|
||||
)
|
||||
if similarity >= threshold:
|
||||
return True
|
||||
return False
|
||||
|
||||
@staticmethod
|
||||
def char_overlap_similarity(s1: str, s2: str) -> float:
|
||||
"""
|
||||
计算两个字符串的字符重叠相似度(Jaccard 相似系数)。
|
||||
|
||||
Args:
|
||||
s1: 第一个字符串
|
||||
s2: 第二个字符串
|
||||
|
||||
Returns:
|
||||
float: 相似度值(0-1)
|
||||
"""
|
||||
if not s1 or not s2:
|
||||
return 0.0
|
||||
set1 = set(s1)
|
||||
set2 = set(s2)
|
||||
intersection = set1 & set2
|
||||
union = set1 | set2
|
||||
if not union:
|
||||
return 0.0
|
||||
return len(intersection) / len(union)
|
||||
|
||||
@@ -1,16 +1,20 @@
|
||||
"""
|
||||
增量合并领域服务
|
||||
|
||||
负责将 IncrementalState 累积数据转换为现有实体类型,
|
||||
负责将 IncrementalBatch 列表合并为 IncrementalState,
|
||||
以及将 IncrementalState 累积数据转换为现有实体类型,
|
||||
以便复用现有的报告生成器和分发器。
|
||||
|
||||
核心职责:
|
||||
- merge_batches: 将多个 IncrementalBatch 合并为一个 IncrementalState(滑动窗口聚合)
|
||||
- IncrementalState → GroupStatistics(含 ActivityVisualization、EmojiStatistics)
|
||||
- IncrementalState → list[SummaryTopic]
|
||||
- IncrementalState → list[GoldenQuote]
|
||||
"""
|
||||
|
||||
from ...domain.entities.incremental_state import IncrementalState
|
||||
import time
|
||||
|
||||
from ...domain.entities.incremental_state import IncrementalBatch, IncrementalState
|
||||
from ...domain.models.data_models import (
|
||||
ActivityVisualization,
|
||||
EmojiStatistics,
|
||||
@@ -26,10 +30,126 @@ class IncrementalMergeService:
|
||||
"""
|
||||
增量合并服务
|
||||
|
||||
将一天内累积的增量分析状态转换为现有报告系统所需的数据结构,
|
||||
将滑动窗口内的多个批次数据合并为报告所需的数据结构,
|
||||
确保增量模式下生成的最终报告与传统单次分析报告格式完全一致。
|
||||
"""
|
||||
|
||||
def merge_batches(
|
||||
self,
|
||||
batches: list[IncrementalBatch],
|
||||
window_start: float,
|
||||
window_end: float,
|
||||
) -> IncrementalState:
|
||||
"""
|
||||
从批次列表合并构建 IncrementalState。
|
||||
|
||||
遍历所有批次,累加统计数据并对话题和金句执行去重,
|
||||
生成可用于报告的聚合视图。
|
||||
|
||||
Args:
|
||||
batches: 时间窗口内的批次列表(按时间升序)
|
||||
window_start: 窗口起始时间戳(epoch)
|
||||
window_end: 窗口结束时间戳(epoch)
|
||||
|
||||
Returns:
|
||||
IncrementalState: 合并后的聚合视图
|
||||
"""
|
||||
state = IncrementalState(
|
||||
group_id=batches[0].group_id if batches else "",
|
||||
window_start=window_start,
|
||||
window_end=window_end,
|
||||
total_analysis_count=len(batches),
|
||||
created_at=window_start,
|
||||
updated_at=time.time(),
|
||||
)
|
||||
|
||||
for batch in batches:
|
||||
# 累加消息和字符计数
|
||||
state.total_message_count += batch.messages_count
|
||||
state.total_character_count += batch.characters_count
|
||||
|
||||
# 合并每小时消息分布(按键累加)
|
||||
for hour_key, count in batch.hourly_msg_counts.items():
|
||||
hour_str = str(hour_key)
|
||||
state.hourly_message_counts[hour_str] = (
|
||||
state.hourly_message_counts.get(hour_str, 0) + count
|
||||
)
|
||||
|
||||
# 合并每小时字符分布
|
||||
for hour_key, count in batch.hourly_char_counts.items():
|
||||
hour_str = str(hour_key)
|
||||
state.hourly_character_counts[hour_str] = (
|
||||
state.hourly_character_counts.get(hour_str, 0) + count
|
||||
)
|
||||
|
||||
# 合并用户统计(按用户累加消息数、字符数等)
|
||||
for user_id, stats in batch.user_stats.items():
|
||||
if user_id not in state.user_activities:
|
||||
state.user_activities[user_id] = {
|
||||
"name": stats.get("name", user_id),
|
||||
"message_count": 0,
|
||||
"char_count": 0,
|
||||
"emoji_count": 0,
|
||||
"active_hours": [],
|
||||
"last_message_time": 0,
|
||||
}
|
||||
existing = state.user_activities[user_id]
|
||||
existing["message_count"] += stats.get("message_count", 0)
|
||||
existing["char_count"] += stats.get("char_count", 0)
|
||||
existing["emoji_count"] += stats.get("emoji_count", 0)
|
||||
# 合并活跃小时(去重)
|
||||
existing_hours = set(existing.get("active_hours", []))
|
||||
existing_hours.update(stats.get("active_hours", []))
|
||||
existing["active_hours"] = list(existing_hours)
|
||||
# 取最后消息时间的较大值
|
||||
batch_last = stats.get("last_message_time", 0)
|
||||
if batch_last > existing.get("last_message_time", 0):
|
||||
existing["last_message_time"] = batch_last
|
||||
# 更新昵称(使用最新批次的昵称)
|
||||
name = stats.get("name", "")
|
||||
if name:
|
||||
existing["name"] = name
|
||||
|
||||
# 合并表情统计(按键累加)
|
||||
for emoji_key, count in batch.emoji_stats.items():
|
||||
state.emoji_counts[emoji_key] = (
|
||||
state.emoji_counts.get(emoji_key, 0) + count
|
||||
)
|
||||
|
||||
# 合并话题(去重)
|
||||
for topic in batch.topics:
|
||||
if not IncrementalState.is_duplicate_topic(topic, state.topics):
|
||||
state.topics.append(topic)
|
||||
|
||||
# 合并金句(去重)
|
||||
for quote in batch.golden_quotes:
|
||||
if not IncrementalState.is_duplicate_quote(quote, state.golden_quotes):
|
||||
state.golden_quotes.append(quote)
|
||||
|
||||
# 累加 token 消耗
|
||||
for token_key in ("prompt_tokens", "completion_tokens", "total_tokens"):
|
||||
state.total_token_usage[token_key] = (
|
||||
state.total_token_usage.get(token_key, 0)
|
||||
+ batch.token_usage.get(token_key, 0)
|
||||
)
|
||||
|
||||
# 合并参与者 ID(取并集)
|
||||
state.all_participant_ids.update(batch.participant_ids)
|
||||
|
||||
# 记录最后分析消息时间戳(取最大值)
|
||||
if batch.last_message_timestamp > state.last_analyzed_message_timestamp:
|
||||
state.last_analyzed_message_timestamp = batch.last_message_timestamp
|
||||
|
||||
logger.info(
|
||||
f"合并批次完成: 群={state.group_id}, "
|
||||
f"窗口={state.get_window_date_str()}, "
|
||||
f"批次数={len(batches)}, "
|
||||
f"总消息={state.total_message_count}, "
|
||||
f"话题={len(state.topics)}, 金句={len(state.golden_quotes)}"
|
||||
)
|
||||
|
||||
return state
|
||||
|
||||
def build_final_statistics(self, state: IncrementalState) -> GroupStatistics:
|
||||
"""
|
||||
从增量状态构建最终的群组统计数据。
|
||||
@@ -38,7 +158,7 @@ class IncrementalMergeService:
|
||||
包含完整的 24 小时活跃度分布、表情统计和 token 消耗。
|
||||
|
||||
Args:
|
||||
state: 当天的增量分析状态
|
||||
state: 由 merge_batches 合并生成的增量分析状态
|
||||
|
||||
Returns:
|
||||
GroupStatistics: 与传统分析格式一致的统计数据
|
||||
@@ -58,7 +178,7 @@ class IncrementalMergeService:
|
||||
# 构建活跃度可视化数据
|
||||
activity_visualization = ActivityVisualization(
|
||||
hourly_activity=hourly_activity,
|
||||
daily_activity={state.date_str: state.total_message_count},
|
||||
daily_activity={state.get_window_date_str(): state.total_message_count},
|
||||
user_activity_ranking=user_ranking,
|
||||
peak_hours=peak_hours,
|
||||
activity_heatmap_data={},
|
||||
@@ -106,7 +226,7 @@ class IncrementalMergeService:
|
||||
将 IncrementalState 中累积的话题字典转换为 SummaryTopic 实例列表。
|
||||
|
||||
Args:
|
||||
state: 当天的增量分析状态
|
||||
state: 由 merge_batches 合并生成的增量分析状态
|
||||
|
||||
Returns:
|
||||
list[SummaryTopic]: 话题列表,格式与传统分析结果一致
|
||||
@@ -130,7 +250,7 @@ class IncrementalMergeService:
|
||||
将 IncrementalState 中累积的金句字典转换为 GoldenQuote 实例列表。
|
||||
|
||||
Args:
|
||||
state: 当天的增量分析状态
|
||||
state: 由 merge_batches 合并生成的增量分析状态
|
||||
|
||||
Returns:
|
||||
list[GoldenQuote]: 金句列表,格式与传统分析结果一致
|
||||
@@ -160,7 +280,7 @@ class IncrementalMergeService:
|
||||
返回的 analysis_result 完全一致,可直接传入 ReportDispatcher。
|
||||
|
||||
Args:
|
||||
state: 当天的增量分析状态
|
||||
state: 由 merge_batches 合并生成的增量分析状态
|
||||
user_titles: 用户称号列表(由最终报告时 LLM 分析生成)
|
||||
|
||||
Returns:
|
||||
@@ -182,7 +302,7 @@ class IncrementalMergeService:
|
||||
|
||||
logger.info(
|
||||
f"从增量状态构建完整分析结果: "
|
||||
f"群={state.group_id}, 日期={state.date_str}, "
|
||||
f"群={state.group_id}, 窗口={state.get_window_date_str()}, "
|
||||
f"消息={state.total_message_count}, "
|
||||
f"话题={len(topics)}, "
|
||||
f"金句={len(golden_quotes)}, "
|
||||
|
||||
@@ -1,186 +1,440 @@
|
||||
"""
|
||||
增量分析状态持久化存储 - 基础设施持久化层
|
||||
增量分析批次持久化存储 — 滑动窗口架构
|
||||
|
||||
负责增量分析状态的存储和读取。
|
||||
使用 AstrBot 的 put_kv_data/get_kv_data 实现,
|
||||
每个群聊每天对应一个独立的状态键。
|
||||
基于 AstrBot 的 put_kv_data/get_kv_data 实现按批次独立存储,
|
||||
支持按时间窗口查询批次、批次索引管理和过期批次清理。
|
||||
|
||||
键格式: incremental_state_{group_id}_{date_str}
|
||||
KV 键设计:
|
||||
- 批次索引: incr_batch_index_{group_id}
|
||||
值: [{"batch_id": "xxx", "timestamp": 1234567890.0}, ...]
|
||||
- 批次数据: incr_batch_{group_id}_{batch_id}
|
||||
值: IncrementalBatch.to_dict()
|
||||
- 最后分析消息时间戳: incr_last_ts_{group_id}
|
||||
值: int (epoch timestamp)
|
||||
"""
|
||||
|
||||
import datetime
|
||||
import time
|
||||
from typing import Any
|
||||
|
||||
from ...domain.entities.incremental_state import IncrementalState
|
||||
from ...domain.entities.incremental_state import IncrementalBatch
|
||||
from ...utils.logger import logger
|
||||
|
||||
|
||||
class IncrementalStore:
|
||||
"""
|
||||
增量分析状态持久化仓储
|
||||
增量分析批次持久化仓储
|
||||
|
||||
该类封装了增量分析状态在 KV 存储中的读写操作。
|
||||
每个群组每天的增量状态独立存储,支持创建、读取、更新和删除。
|
||||
|
||||
使用方式与 HistoryManager 一致,依赖 star_instance 提供的
|
||||
put_kv_data / get_kv_data 异步接口。
|
||||
核心职责:
|
||||
- save_batch: 保存单个批次数据并更新索引
|
||||
- query_batches: 按时间窗口查询批次列表
|
||||
- get_last_analyzed_timestamp / update_last_analyzed_timestamp: 跨批次去重
|
||||
- cleanup_old_batches: 清理过期批次
|
||||
- get_batch_count: 获取当前批次总数(状态查询用)
|
||||
"""
|
||||
|
||||
# KV 存储键前缀
|
||||
KEY_PREFIX = "incremental_state"
|
||||
# KV 键前缀
|
||||
INDEX_PREFIX = "incr_batch_index"
|
||||
BATCH_PREFIX = "incr_batch"
|
||||
LAST_TS_PREFIX = "incr_last_ts"
|
||||
|
||||
def __init__(self, star_instance: Any):
|
||||
"""
|
||||
初始化增量状态仓储。
|
||||
初始化批次持久化仓储。
|
||||
|
||||
Args:
|
||||
star_instance: Star 插件实例,用于访问底层 KV 存储引擎
|
||||
"""
|
||||
self.plugin = star_instance
|
||||
|
||||
def _build_key(self, group_id: str, date_str: str | None = None) -> str:
|
||||
# ================================================================
|
||||
# 键构建
|
||||
# ================================================================
|
||||
|
||||
def _index_key(self, group_id: str) -> str:
|
||||
"""构建批次索引键"""
|
||||
return f"{self.INDEX_PREFIX}_{group_id}"
|
||||
|
||||
def _batch_key(self, group_id: str, batch_id: str) -> str:
|
||||
"""构建单个批次数据键"""
|
||||
return f"{self.BATCH_PREFIX}_{group_id}_{batch_id}"
|
||||
|
||||
def _last_ts_key(self, group_id: str) -> str:
|
||||
"""构建最后分析消息时间戳键"""
|
||||
return f"{self.LAST_TS_PREFIX}_{group_id}"
|
||||
|
||||
# ================================================================
|
||||
# 批次索引操作
|
||||
# ================================================================
|
||||
|
||||
async def _get_index(self, group_id: str) -> list[dict]:
|
||||
"""
|
||||
构建 KV 存储键。
|
||||
获取指定群的批次索引列表。
|
||||
|
||||
Args:
|
||||
group_id: 群组 ID
|
||||
date_str: 日期字符串 (YYYY-MM-DD),缺省为当天
|
||||
|
||||
Returns:
|
||||
str: 格式为 "incremental_state_{group_id}_{date_str}" 的键
|
||||
list[dict]: 索引条目列表,每项包含 batch_id 和 timestamp
|
||||
"""
|
||||
if not date_str:
|
||||
date_str = datetime.datetime.now().strftime("%Y-%m-%d")
|
||||
return f"{self.KEY_PREFIX}_{group_id}_{date_str}"
|
||||
|
||||
async def get_state(
|
||||
self, group_id: str, date_str: str | None = None
|
||||
) -> IncrementalState | None:
|
||||
"""
|
||||
读取指定群组在指定日期的增量分析状态。
|
||||
|
||||
Args:
|
||||
group_id: 群组 ID
|
||||
date_str: 日期字符串 (YYYY-MM-DD),缺省为当天
|
||||
|
||||
Returns:
|
||||
IncrementalState | None: 状态实例,不存在则返回 None
|
||||
"""
|
||||
if not date_str:
|
||||
date_str = datetime.datetime.now().strftime("%Y-%m-%d")
|
||||
|
||||
key = self._build_key(group_id, date_str)
|
||||
|
||||
key = self._index_key(group_id)
|
||||
try:
|
||||
data = await self.plugin.get_kv_data(key, None)
|
||||
if data is None:
|
||||
return None
|
||||
|
||||
state = IncrementalState.from_dict(data)
|
||||
logger.debug(f"已读取群 {group_id} 在 {date_str} 的增量状态 (Key: {key})")
|
||||
return state
|
||||
return []
|
||||
if isinstance(data, list):
|
||||
return data
|
||||
logger.warning(f"批次索引数据格式异常 (Key: {key}): {type(data)}")
|
||||
return []
|
||||
except Exception as e:
|
||||
logger.error(f"读取增量状态失败 (Key: {key}): {e}", exc_info=True)
|
||||
return None
|
||||
logger.error(f"读取批次索引失败 (Key: {key}): {e}", exc_info=True)
|
||||
return []
|
||||
|
||||
async def save_state(self, state: IncrementalState) -> bool:
|
||||
async def _save_index(self, group_id: str, index: list[dict]) -> None:
|
||||
"""
|
||||
持久化增量分析状态。
|
||||
|
||||
将状态序列化为字典后写入 KV 存储。
|
||||
如果已存在同键数据则覆盖更新。
|
||||
保存批次索引列表。
|
||||
|
||||
Args:
|
||||
state: 要保存的增量分析状态实例
|
||||
group_id: 群组 ID
|
||||
index: 索引条目列表
|
||||
"""
|
||||
key = self._index_key(group_id)
|
||||
try:
|
||||
await self.plugin.put_kv_data(key, index)
|
||||
except Exception as e:
|
||||
logger.error(f"保存批次索引失败 (Key: {key}): {e}", exc_info=True)
|
||||
raise
|
||||
|
||||
# ================================================================
|
||||
# 批次数据操作
|
||||
# ================================================================
|
||||
|
||||
async def save_batch(self, batch: IncrementalBatch) -> bool:
|
||||
"""
|
||||
保存单个批次数据并更新索引。
|
||||
|
||||
流程:
|
||||
1. 将批次数据写入独立 KV 键
|
||||
2. 将批次元数据(batch_id + timestamp)追加到索引
|
||||
|
||||
Args:
|
||||
batch: 要保存的增量分析批次
|
||||
|
||||
Returns:
|
||||
bool: 保存是否成功
|
||||
"""
|
||||
key = self._build_key(state.group_id, state.date_str)
|
||||
group_id = batch.group_id
|
||||
batch_key = self._batch_key(group_id, batch.batch_id)
|
||||
|
||||
try:
|
||||
data = state.to_dict()
|
||||
await self.plugin.put_kv_data(key, data)
|
||||
# 1. 保存批次数据
|
||||
await self.plugin.put_kv_data(batch_key, batch.to_dict())
|
||||
|
||||
# 2. 更新索引
|
||||
index = await self._get_index(group_id)
|
||||
index.append({
|
||||
"batch_id": batch.batch_id,
|
||||
"timestamp": batch.timestamp,
|
||||
})
|
||||
await self._save_index(group_id, index)
|
||||
|
||||
logger.debug(
|
||||
f"已保存群 {state.group_id} 在 {state.date_str} 的增量状态 "
|
||||
f"(Key: {key}, 批次数: {state.total_analysis_count})"
|
||||
f"已保存批次 {batch.batch_id[:8]}... "
|
||||
f"(群 {group_id}, 消息数={batch.messages_count})"
|
||||
)
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.error(f"保存增量状态失败 (Key: {key}): {e}", exc_info=True)
|
||||
logger.error(
|
||||
f"保存批次失败 (群 {group_id}, 批次 {batch.batch_id[:8]}...): {e}",
|
||||
exc_info=True,
|
||||
)
|
||||
return False
|
||||
|
||||
async def get_or_create_state(
|
||||
self, group_id: str, date_str: str | None = None
|
||||
) -> IncrementalState:
|
||||
async def query_batches(
|
||||
self,
|
||||
group_id: str,
|
||||
window_start: float,
|
||||
window_end: float,
|
||||
) -> list[IncrementalBatch]:
|
||||
"""
|
||||
获取或创建增量分析状态。
|
||||
按时间窗口查询批次列表。
|
||||
|
||||
如果指定群组在指定日期已有状态则返回现有状态,
|
||||
否则创建一个新的空白状态实例(不自动持久化)。
|
||||
从索引中筛选时间戳落在 [window_start, window_end] 范围内的批次,
|
||||
逐个加载完整批次数据。
|
||||
|
||||
Args:
|
||||
group_id: 群组 ID
|
||||
date_str: 日期字符串 (YYYY-MM-DD),缺省为当天
|
||||
window_start: 窗口起始时间戳(epoch)
|
||||
window_end: 窗口结束时间戳(epoch)
|
||||
|
||||
Returns:
|
||||
IncrementalState: 现有或新创建的状态实例
|
||||
list[IncrementalBatch]: 符合窗口范围的批次列表,按时间戳升序
|
||||
"""
|
||||
if not date_str:
|
||||
date_str = datetime.datetime.now().strftime("%Y-%m-%d")
|
||||
index = await self._get_index(group_id)
|
||||
|
||||
existing = await self.get_state(group_id, date_str)
|
||||
if existing is not None:
|
||||
return existing
|
||||
# 筛选在窗口范围内的批次
|
||||
matching_entries = [
|
||||
entry for entry in index
|
||||
if window_start <= entry.get("timestamp", 0) <= window_end
|
||||
]
|
||||
|
||||
# 创建新的空白状态
|
||||
new_state = IncrementalState(
|
||||
group_id=group_id,
|
||||
date_str=date_str,
|
||||
# 按时间戳升序排列
|
||||
matching_entries.sort(key=lambda x: x.get("timestamp", 0))
|
||||
|
||||
batches: list[IncrementalBatch] = []
|
||||
for entry in matching_entries:
|
||||
batch_id = entry.get("batch_id", "")
|
||||
if not batch_id:
|
||||
continue
|
||||
|
||||
batch_key = self._batch_key(group_id, batch_id)
|
||||
try:
|
||||
data = await self.plugin.get_kv_data(batch_key, None)
|
||||
if data is not None:
|
||||
batch = IncrementalBatch.from_dict(data)
|
||||
batches.append(batch)
|
||||
else:
|
||||
logger.warning(
|
||||
f"批次数据缺失 (群 {group_id}, 批次 {batch_id[:8]}...)"
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"加载批次数据失败 (群 {group_id}, 批次 {batch_id[:8]}...): {e}",
|
||||
exc_info=True,
|
||||
)
|
||||
|
||||
logger.debug(
|
||||
f"窗口查询完成: 群 {group_id}, "
|
||||
f"窗口 [{window_start:.0f}, {window_end:.0f}], "
|
||||
f"匹配 {len(batches)}/{len(index)} 个批次"
|
||||
)
|
||||
logger.info(f"为群 {group_id} 创建了 {date_str} 的新增量状态")
|
||||
return new_state
|
||||
|
||||
async def delete_state(
|
||||
self, group_id: str, date_str: str | None = None
|
||||
return batches
|
||||
|
||||
# ================================================================
|
||||
# 最后分析消息时间戳(跨批次去重用)
|
||||
# ================================================================
|
||||
|
||||
async def get_last_analyzed_timestamp(self, group_id: str) -> int:
|
||||
"""
|
||||
获取指定群的最后分析消息时间戳。
|
||||
|
||||
用于增量分析时过滤已分析过的消息。
|
||||
|
||||
Args:
|
||||
group_id: 群组 ID
|
||||
|
||||
Returns:
|
||||
int: 最后分析消息的 epoch 时间戳,不存在则返回 0
|
||||
"""
|
||||
key = self._last_ts_key(group_id)
|
||||
try:
|
||||
data = await self.plugin.get_kv_data(key, 0)
|
||||
return int(data) if data else 0
|
||||
except Exception as e:
|
||||
logger.error(f"读取最后分析时间戳失败 (Key: {key}): {e}", exc_info=True)
|
||||
return 0
|
||||
|
||||
async def update_last_analyzed_timestamp(
|
||||
self, group_id: str, timestamp: int
|
||||
) -> None:
|
||||
"""
|
||||
更新指定群的最后分析消息时间戳。
|
||||
|
||||
Args:
|
||||
group_id: 群组 ID
|
||||
timestamp: 最后分析消息的 epoch 时间戳
|
||||
"""
|
||||
key = self._last_ts_key(group_id)
|
||||
try:
|
||||
await self.plugin.put_kv_data(key, timestamp)
|
||||
logger.debug(
|
||||
f"更新最后分析时间戳: 群 {group_id}, ts={timestamp}"
|
||||
)
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"更新最后分析时间戳失败 (Key: {key}): {e}", exc_info=True
|
||||
)
|
||||
raise
|
||||
|
||||
# ================================================================
|
||||
# 过期批次清理
|
||||
# ================================================================
|
||||
|
||||
async def cleanup_old_batches(
|
||||
self, group_id: str, before_timestamp: float
|
||||
) -> int:
|
||||
"""
|
||||
清理指定群中早于给定时间戳的所有批次。
|
||||
|
||||
流程:
|
||||
1. 从索引中分离出过期条目和保留条目
|
||||
2. 逐个删除过期批次的 KV 数据
|
||||
3. 用保留条目覆盖索引
|
||||
|
||||
Args:
|
||||
group_id: 群组 ID
|
||||
before_timestamp: 清理此时间戳之前的所有批次
|
||||
|
||||
Returns:
|
||||
int: 已清理的批次数量
|
||||
"""
|
||||
index = await self._get_index(group_id)
|
||||
if not index:
|
||||
return 0
|
||||
|
||||
# 分离过期和保留
|
||||
expired = []
|
||||
retained = []
|
||||
for entry in index:
|
||||
if entry.get("timestamp", 0) < before_timestamp:
|
||||
expired.append(entry)
|
||||
else:
|
||||
retained.append(entry)
|
||||
|
||||
if not expired:
|
||||
return 0
|
||||
|
||||
# 删除过期批次数据
|
||||
deleted_count = 0
|
||||
for entry in expired:
|
||||
batch_id = entry.get("batch_id", "")
|
||||
if not batch_id:
|
||||
continue
|
||||
batch_key = self._batch_key(group_id, batch_id)
|
||||
try:
|
||||
await self.plugin.put_kv_data(batch_key, None)
|
||||
deleted_count += 1
|
||||
except Exception as e:
|
||||
logger.error(
|
||||
f"删除过期批次失败 (群 {group_id}, 批次 {batch_id[:8]}...): {e}",
|
||||
exc_info=True,
|
||||
)
|
||||
|
||||
# 更新索引(仅保留未过期条目)
|
||||
await self._save_index(group_id, retained)
|
||||
|
||||
logger.info(
|
||||
f"清理过期批次: 群 {group_id}, "
|
||||
f"删除 {deleted_count} 个, 保留 {len(retained)} 个"
|
||||
)
|
||||
|
||||
return deleted_count
|
||||
|
||||
# ================================================================
|
||||
# 状态查询
|
||||
# ================================================================
|
||||
|
||||
async def get_batch_count(self, group_id: str) -> int:
|
||||
"""
|
||||
获取指定群的当前批次总数。
|
||||
|
||||
Args:
|
||||
group_id: 群组 ID
|
||||
|
||||
Returns:
|
||||
int: 批次总数
|
||||
"""
|
||||
index = await self._get_index(group_id)
|
||||
return len(index)
|
||||
|
||||
async def get_all_batch_summaries(
|
||||
self, group_id: str
|
||||
) -> list[dict]:
|
||||
"""
|
||||
获取指定群所有批次的摘要信息(不加载完整数据)。
|
||||
|
||||
用于状态查询命令展示批次概览。
|
||||
|
||||
Args:
|
||||
group_id: 群组 ID
|
||||
|
||||
Returns:
|
||||
list[dict]: 批次摘要列表,按时间升序
|
||||
"""
|
||||
index = await self._get_index(group_id)
|
||||
# 按时间戳升序排列
|
||||
index.sort(key=lambda x: x.get("timestamp", 0))
|
||||
return index
|
||||
|
||||
# ================================================================
|
||||
# 旧版兼容(迁移期间使用)
|
||||
# ================================================================
|
||||
|
||||
async def migrate_legacy_state(
|
||||
self, group_id: str, date_str: str
|
||||
) -> bool:
|
||||
"""
|
||||
删除指定群组在指定日期的增量分析状态。
|
||||
尝试迁移旧版按天存储的 IncrementalState 到新批次架构。
|
||||
|
||||
通过将键值设为 None 来实现删除效果。
|
||||
检查旧键 incremental_state_{group_id}_{date_str} 是否存在,
|
||||
如果存在则将其数据转换为一个 IncrementalBatch 并保存,
|
||||
然后删除旧键。
|
||||
|
||||
Args:
|
||||
group_id: 群组 ID
|
||||
date_str: 日期字符串 (YYYY-MM-DD),缺省为当天
|
||||
date_str: 日期字符串 (YYYY-MM-DD)
|
||||
|
||||
Returns:
|
||||
bool: 删除是否成功
|
||||
bool: 是否成功迁移(True=迁移了数据,False=无需迁移或失败)
|
||||
"""
|
||||
if not date_str:
|
||||
date_str = datetime.datetime.now().strftime("%Y-%m-%d")
|
||||
|
||||
key = self._build_key(group_id, date_str)
|
||||
old_key = f"incremental_state_{group_id}_{date_str}"
|
||||
|
||||
try:
|
||||
await self.plugin.put_kv_data(key, None)
|
||||
logger.info(f"已删除群 {group_id} 在 {date_str} 的增量状态 (Key: {key})")
|
||||
old_data = await self.plugin.get_kv_data(old_key, None)
|
||||
if old_data is None:
|
||||
return False
|
||||
|
||||
logger.info(
|
||||
f"发现旧版增量状态 (群 {group_id}, 日期 {date_str}),开始迁移"
|
||||
)
|
||||
|
||||
# 从旧数据中提取信息构建一个聚合批次
|
||||
batch = IncrementalBatch(
|
||||
group_id=group_id,
|
||||
timestamp=old_data.get("created_at", time.time()),
|
||||
messages_count=old_data.get("total_message_count", 0),
|
||||
characters_count=old_data.get("total_character_count", 0),
|
||||
hourly_msg_counts=old_data.get("hourly_message_counts", {}),
|
||||
hourly_char_counts=old_data.get("hourly_character_counts", {}),
|
||||
user_stats=old_data.get("user_activities", {}),
|
||||
emoji_stats=old_data.get("emoji_counts", {}),
|
||||
topics=old_data.get("topics", []),
|
||||
golden_quotes=old_data.get("golden_quotes", []),
|
||||
token_usage=old_data.get("total_token_usage", {
|
||||
"prompt_tokens": 0,
|
||||
"completion_tokens": 0,
|
||||
"total_tokens": 0,
|
||||
}),
|
||||
last_message_timestamp=old_data.get(
|
||||
"last_analyzed_message_timestamp", 0
|
||||
),
|
||||
participant_ids=list(
|
||||
old_data.get("all_participant_ids", [])
|
||||
),
|
||||
)
|
||||
|
||||
# 保存为新批次
|
||||
saved = await self.save_batch(batch)
|
||||
if not saved:
|
||||
logger.error(f"旧版数据迁移保存失败 (群 {group_id})")
|
||||
return False
|
||||
|
||||
# 迁移最后分析时间戳
|
||||
last_ts = old_data.get("last_analyzed_message_timestamp", 0)
|
||||
if last_ts > 0:
|
||||
await self.update_last_analyzed_timestamp(group_id, last_ts)
|
||||
|
||||
# 删除旧键
|
||||
await self.plugin.put_kv_data(old_key, None)
|
||||
|
||||
logger.info(
|
||||
f"旧版增量状态迁移完成 (群 {group_id}, 日期 {date_str}), "
|
||||
f"消息数={batch.messages_count}"
|
||||
)
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"删除增量状态失败 (Key: {key}): {e}", exc_info=True)
|
||||
logger.error(
|
||||
f"旧版增量状态迁移失败 (群 {group_id}): {e}", exc_info=True
|
||||
)
|
||||
return False
|
||||
|
||||
async def has_state(
|
||||
self, group_id: str, date_str: str | None = None
|
||||
) -> bool:
|
||||
"""
|
||||
判断指定群组在指定日期是否存在增量分析状态。
|
||||
|
||||
Args:
|
||||
group_id: 群组 ID
|
||||
date_str: 日期字符串 (YYYY-MM-DD),缺省为当天
|
||||
|
||||
Returns:
|
||||
bool: 是否存在状态
|
||||
"""
|
||||
state = await self.get_state(group_id, date_str)
|
||||
return state is not None
|
||||
|
||||
@@ -4,6 +4,7 @@
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import time as time_mod
|
||||
import weakref
|
||||
|
||||
from apscheduler.triggers.cron import CronTrigger
|
||||
@@ -575,12 +576,12 @@ class AutoScheduler:
|
||||
return result
|
||||
|
||||
# 增量分析只累积数据,不发送报告
|
||||
batch = result.get("batch_record", {})
|
||||
batch_summary = result.get("batch_summary", {})
|
||||
logger.info(
|
||||
f"群 {group_id} 增量分析完成: "
|
||||
f"消息数={result.get('messages_count', 0)}, "
|
||||
f"新话题={batch.get('topics_added', 0)}, "
|
||||
f"新金句={batch.get('quotes_added', 0)}"
|
||||
f"话题={batch_summary.get('topics_count', 0)}, "
|
||||
f"金句={batch_summary.get('quotes_count', 0)}"
|
||||
)
|
||||
return result
|
||||
|
||||
@@ -733,6 +734,24 @@ class AutoScheduler:
|
||||
else target_platform_id,
|
||||
)
|
||||
|
||||
# 清理过期批次(保留 2 倍窗口范围的数据作为缓冲)
|
||||
try:
|
||||
analysis_days = self.config_manager.get_analysis_days()
|
||||
before_ts = time_mod.time() - (analysis_days * 2 * 24 * 3600)
|
||||
incremental_store = self.analysis_service.incremental_store
|
||||
if incremental_store:
|
||||
cleaned = await incremental_store.cleanup_old_batches(
|
||||
group_id, before_ts
|
||||
)
|
||||
if cleaned > 0:
|
||||
logger.info(
|
||||
f"群 {group_id} 报告发送后清理了 {cleaned} 个过期批次"
|
||||
)
|
||||
except Exception as cleanup_err:
|
||||
logger.warning(
|
||||
f"群 {group_id} 过期批次清理失败(不影响报告): {cleanup_err}"
|
||||
)
|
||||
|
||||
logger.info(f"群 {group_id} 增量最终报告发送成功")
|
||||
return result
|
||||
|
||||
|
||||
Reference in New Issue
Block a user