ca3780aa24
包含 CDC consumer、analytics/mastery/warning service、grpc server、repository、ClickHouse DDL 等
98 lines
3.8 KiB
SQL
98 lines
3.8 KiB
SQL
-- data-ana ClickHouse DDL（5 宽表）.
|
||
-- 负责人：ai11（总裁裁决 §2.12 授权 ai11 创建纯 DDL 文件，SRE AI 负责部署脚本）.
|
||
-- 对齐文档：services/data-ana/docs/02-architecture-design.md §3.
|
||
-- 引擎：ReplacingMergeTree 按 ORDER BY 去重 + version 列保留最新版本（幂等消费保证）.
|
||
-- 查询时必须加 FINAL 或使用 argMax 聚合确保去重生效（P0 整改项）.
|
||
--
|
||
-- 使用方式：
|
||
-- clickhouse-client --multiquery < infra/clickhouse/ddl/data_ana.sql
|
||
|
||
-- 数据库
|
||
CREATE DATABASE IF NOT EXISTS edu_analytics;
|
||
|
||
-- ===== 1. 学生学情宽表 =====
|
||
-- 每次成绩写入产生一行，按 ORDER BY 去重保留 last_updated 最大版本.
|
||
CREATE TABLE IF NOT EXISTS edu_analytics.student_dashboard_view
|
||
(
|
||
student_id String,
|
||
class_id String,
|
||
exam_id String,
|
||
subject_id String,
|
||
score Float64,
|
||
rank_in_class UInt32,
|
||
knowledge_point_id String,
|
||
mastery_level Float32, -- 0.0-1.0
|
||
error_count UInt32,
|
||
last_updated DateTime64(3, 'UTC')
|
||
)
|
||
ENGINE = ReplacingMergeTree(last_updated)
|
||
PARTITION BY toYYYYMM(last_updated)
|
||
ORDER BY (student_id, exam_id, knowledge_point_id)
|
||
SETTINGS index_granularity = 8192;
|
||
|
||
-- ===== 2. 学生错题本 =====
|
||
-- 同一 (student_id, question_id) 累计 error_count，按 last_error_time 去重.
|
||
CREATE TABLE IF NOT EXISTS edu_analytics.student_errors
|
||
(
|
||
student_id String,
|
||
question_id String,
|
||
knowledge_point_id String,
|
||
error_count UInt32,
|
||
last_error_time DateTime64(3, 'UTC'),
|
||
content String DEFAULT ''
|
||
)
|
||
ENGINE = ReplacingMergeTree(last_error_time)
|
||
PARTITION BY toYYYYMM(last_error_time)
|
||
ORDER BY (student_id, question_id);
|
||
|
||
-- ===== 3. 知识点掌握度历史快照 =====
|
||
-- 每次掌握度计算产生新版本，支持趋势查询.
|
||
CREATE TABLE IF NOT EXISTS edu_analytics.mastery_snapshot
|
||
(
|
||
student_id String,
|
||
knowledge_point_id String,
|
||
subject_id String,
|
||
mastery_level Float32, -- 0.0-1.0
|
||
calculated_at DateTime64(3, 'UTC'),
|
||
calculation_method LowCardinality(String) -- 'weighted_moving_avg' / 'simple_avg' / 'forgetting_curve'
|
||
)
|
||
ENGINE = MergeTree
|
||
PARTITION BY toYYYYMM(calculated_at)
|
||
ORDER BY (student_id, knowledge_point_id, calculated_at);
|
||
|
||
-- ===== 4. 学生考勤记录 =====
|
||
-- core-edu attendance 表 CDC 同步，同一记录多版本去重.
|
||
CREATE TABLE IF NOT EXISTS edu_analytics.attendance_logs
|
||
(
|
||
student_id String,
|
||
class_id String,
|
||
attendance_date Date,
|
||
status LowCardinality(String), -- 'present' / 'absent' / 'late' / 'leave'
|
||
recorded_by String, -- 教师用户 ID
|
||
remark String DEFAULT '',
|
||
occurred_at DateTime64(3, 'UTC')
|
||
)
|
||
ENGINE = ReplacingMergeTree(occurred_at)
|
||
PARTITION BY toYYYYMM(attendance_date)
|
||
ORDER BY (student_id, class_id, attendance_date);
|
||
|
||
-- ===== 5. AI 用量计费记录 =====
|
||
-- ai 服务通过 Kafka 事件投递，data-ana 消费落库，按 request_id 幂等去重.
|
||
CREATE TABLE IF NOT EXISTS edu_analytics.ai_usage_log
|
||
(
|
||
request_id String,
|
||
user_id String,
|
||
provider LowCardinality(String), -- 'openai' / 'anthropic' / 'baichuan' / 'local'
|
||
model LowCardinality(String),
|
||
prompt_tokens UInt32,
|
||
completion_tokens UInt32,
|
||
total_tokens UInt32,
|
||
latency_ms UInt32,
|
||
success Boolean,
|
||
cost_cents UInt32, -- 计费（分），便于聚合
|
||
occurred_at DateTime64(3, 'UTC')
|
||
)
|
||
ENGINE = ReplacingMergeTree(occurred_at)
|
||
PARTITION BY toYYYYMM(occurred_at)
|
||
ORDER BY (request_id);
|