# 模型 SQL 与当前库表结构核对及改写报告

## 执行概况

- 执行时间：2026-03-17
- 源文件：[assets/模型信息.csv](/Users/wkc/Desktop/ccdi/ccdi/assets/模型信息.csv)
- 数据库配置来源：[ruoyi-admin/src/main/resources/application-dev.yml](/Users/wkc/Desktop/ccdi/ccdi/ruoyi-admin/src/main/resources/application-dev.yml)
- 目标数据库：`MySQL 5.7.44`，库名 `ccdi`
- 报告目标：
  - 保留 CSV 原始内容并转存为 Markdown
  - 检查模型 SQL 与当前数据库表结构是否匹配
  - 检查 SQL 在当前 MySQL 方言下的语法兼容性
  - 将可落地 SQL 改写为适配当前库结构的版本

## 核对基线

### 当前库存在的核心表

- `ccdi_base_staff`
- `ccdi_bank_statement`
- `ccdi_staff_fmy_relation`
- `ccdi_asset_info`
- `ccdi_biz_intermediary`
- `ccdi_cust_fmy_relation`
- `ccdi_cust_enterprise_relation`

### 当前库不存在的外部对象

- `odsdb.blfmconf`
- `sjfx_pro.bdfmhqaa_orc`
- `xdzx.assure_infomation`
- `中介名单`

### 当前库关键字段实际情况

- `ccdi_bank_statement` 存在 `TRX_DATE`，不存在 `trx_time`
- `ccdi_asset_info` 存在 `update_time`，不存在 `updated_at`
- `ccdi_bank_statement` 的金额字段为 `AMOUNT_DR`、`AMOUNT_CR`
- `ccdi_bank_statement` 的摘要字段为 `USER_MEMO`
- `ccdi_bank_statement` 的对手方字段为 `CUSTOMER_ACCOUNT_NAME`、`CUSTOMER_ACCOUNT_NO`

### 本次改写原则

- 保持原始业务意图，不随意增加新的业务规则
- 优先适配 `MySQL 5.7`，去除 `WITH`、`add_months()` 等不兼容写法
- 将 `PROJECT_ID`、`$$$`、`$$$$` 改为 MySQL 会话变量
- 对于当前库无法独立支持的外部依赖，给出“部分可执行”的改写版，并明确缺失项
- 对于原 SQL 与业务口径不完全一致的地方，在说明中单独标注

---

## CSV 原始内容与逐条改写

### CSV 第 1 行

- 序号：`2.1`
- 模型名称：`异常交易`
- 核心异常点（展示在前端页面）：`与客户之间非正常资金往来`
- 业务口径：`员工及关系人与客户及关系人之间有超过1000元以上的资金往来；客户指信贷类客户包括贷款户、担保人，中介库人员，包括中介注册的主体及主体关系人。`
- 相关指标：`与特定客户交易总额`
- 指标英文名：`空`
- 风险筛查对象：`员工本人及亲属、贷款客户、担保人、中介`
- 技术口径：`空`
- 限制阈值指标：`/`
- 可疑结果返回：`流水明细`
- 风险等级：`高风险`
- 原始代码：

```sql
--员工及其亲属与贷款客户、担保户、中介有异常交易
with loan_cust_acct as (
select t2.aa01ac15
from
(
select substr(nfabcsid,4) as nfabcsid
    from odsdb.blfmconf --贷款合同文件
    where nfaacost in ('3','5','7') --合同状态
    and substr(nfaabrno,1,3) = '902' --机构
    and del_f = '0'
    group by substr(nfabcsid,4)
) t1
inner join
(
select
        aa01ac15        --账号
,aa62cfno
from sjfx_pro.bdfmhqaa_orc
where del_f = 0
    and substr(trim(aa47brno),1,3) = '902'     --机构号修改
and rcstrs1b <>'9'
    AND aa15zhzt ='1'    -- 账户状态 1-正常 2-销户 3-新开户 4-结清
group by  aa01ac15 ,aa62cfno
) t2
on t1.nfabcsid = t2.aa62cfno
) ,
assure_cust_acct as (
select t2.aa01ac15
from
(
select asseure_sign
from xdzx.assure_infomation
where del_f= '0'
and assure_state <> '2'
and substr(create_org,1,3)='902'
group by asseure_sign
) t1
inner join
(
select
        aa01ac15        --账号
,aa03csno
from sjfx_pro.bdfmhqaa_orc
where del_f = 0
    and substr(trim(aa47brno),1,3) = '902'     --机构号修改
and rcstrs1b <>'9'
    AND aa15zhzt ='1'    -- 账户状态 1-正常 2-销户 3-新开户 4-结清
group by  aa01ac15 ,aa03csno
) t2
on t1.asseure_sign = t2.aa03csno
)
select a.bank_statement_id
from
(
select t1.id_card
,t2.bank_statement_id
,customer_account_no
from
ccdi_base_staff t1
inner join
ccdi_bank_statement t2
on t1.id_card = t2.cret_no
where project_id = PROJECT_ID
and (amount_dr>1000 or amount_cr>1000)
and customer_account_no is not null
union all
select t1.person_id
,t2.bank_statement_id
,customer_account_no
from
ccdi_staff_fmy_relation t1
inner join
ccdi_bank_statement t2
on t1.relation_cert_no = t2.cret_no
where t1.status = 1
and t2.project_id = PROJECT_ID
and (amount_dr>1000 or amount_cr>1000)
and customer_account_no is not null
) a
where exists (select 1 from loan_cust_acct b on a.customer_account_no = b.aa01ac15)
or exists (select 1 from assure_cust_acct c on a.customer_account_no = c.aa01ac15)
or exists (select 1 from 中介名单 d on a.customer_account_no = d.中介账号);
```

**核对结论**

- 原 SQL 依赖 3 个当前库不存在的外部 schema 和 1 个不存在的中介表
- 原 SQL 使用 `WITH`，当前 `MySQL 5.7` 不支持
- 原 SQL 中 `exists (select 1 from ... on ...)` 是明确语法错误
- 当前 `ccdi` 库没有贷款客户账号、担保人账号、中介账号的现成对照表，无法完全在现库独立落地

**改写 SQL**

以下改写版可在 `MySQL 5.7` 执行，但需要先准备 3 张引用表：

- `tmp_model_21_loan_cust_acct(account_no)`
- `tmp_model_21_assure_cust_acct(account_no)`
- `tmp_model_21_intermediary_acct(account_no)`

```sql
SET @project_id := 0;
SET @min_trade_amount := 1000;

SELECT DISTINCT a.bank_statement_id
FROM (
    SELECT
        t1.id_card AS person_id,
        t2.bank_statement_id,
        t2.CUSTOMER_ACCOUNT_NO AS customer_account_no
    FROM ccdi_base_staff t1
    INNER JOIN ccdi_bank_statement t2
        ON t1.id_card = t2.cret_no
    WHERE t2.project_id = @project_id
      AND (t2.AMOUNT_DR > @min_trade_amount OR t2.AMOUNT_CR > @min_trade_amount)
      AND t2.CUSTOMER_ACCOUNT_NO IS NOT NULL

    UNION ALL

    SELECT
        t1.person_id,
        t2.bank_statement_id,
        t2.CUSTOMER_ACCOUNT_NO AS customer_account_no
    FROM ccdi_staff_fmy_relation t1
    INNER JOIN ccdi_bank_statement t2
        ON t1.relation_cert_no = t2.cret_no
    WHERE t1.status = 1
      AND t2.project_id = @project_id
      AND (t2.AMOUNT_DR > @min_trade_amount OR t2.AMOUNT_CR > @min_trade_amount)
      AND t2.CUSTOMER_ACCOUNT_NO IS NOT NULL
) a
WHERE EXISTS (
    SELECT 1
    FROM tmp_model_21_loan_cust_acct b
    WHERE b.account_no = a.customer_account_no
)
   OR EXISTS (
    SELECT 1
    FROM tmp_model_21_assure_cust_acct c
    WHERE c.account_no = a.customer_account_no
)
   OR EXISTS (
    SELECT 1
    FROM tmp_model_21_intermediary_acct d
    WHERE d.account_no = a.customer_account_no
);
```

**未解决依赖**

- 当前库没有贷款客户账号、担保人账号、中介账号映射表
- 如果后续需要完全落地，应先把外部客户账号清单同步到 `ccdi` 或建立中间表

---

### CSV 第 2 行

- 序号：`2.2`
- 模型名称：`空`
- 核心异常点（展示在前端页面）：`低收入亲属大额交易`
- 业务口径：`关系人中没有收入或月收入低于3000元的人员，累计交易金额超过10万元。`
- 相关指标：`低收入亲属的累计交易额`
- 指标英文名：`空`
- 风险筛查对象：`员工亲属`
- 技术口径：`关联员工及其亲属，筛选平均月收入<3000的亲属的账户，在流水中单笔或累计 >10 万元，按员工汇总`
- 限制阈值指标：`/`
- 可疑结果返回：`个人、累积金额`
- 风险等级：`一般`
- 原始代码：

```sql
--员工亲属低收入但交易金额高
select t1.person_id
,t2.trans_amount
from
(
select person_id
,relation_cert_no
,avg(amount_cr) as avg_amount_cr
from
(
select t1.person_id
,t1.relation_cert_no
,substr(trx_time,1,7)
,sum(amount_cr) as amount_cr--收入金额
from
ccdi_staff_fmy_relation t1
inner join
ccdi_bank_statement t2
on t1.relation_cert_no = t2.cret_no
where t1.status = 1
and t2.project_id = PROJECT_ID
and t2.le_account_name <> t2.customer_account_name --排除同名交易
group by t1.person_id,t1.relation_cert_no,substr(trx_time,1,7)
)
group by person_id,relation_cert_no
having avg(amount_cr)<=3000 ---月均收入不超过3000
) t1
left join
(
select t1.relation_cert_no
,sum(amount_cr + amount_dr) as trans_amount
,max(amount_cr) as max_amount_cr
,max(amount_dr) as max_amount_dr
from
ccdi_staff_fmy_relation t1
inner join
ccdi_bank_statement t2
on t1.relation_cert_no = t2.cret_no
where t1.status = 1
and t2.project_id = PROJECT_ID
group by t1.relation_cert_no
having sum(amount_cr + amount_dr) >= 100000
) t2
on t1.relation_cert_no = t2.relation_cert_no
where t2.relation_cert_no is not null
;
```

**核对结论**

- 原 SQL 引用了不存在的 `trx_time`
- 原 SQL 的内层派生表缺少别名
- 业务意图可完全映射到当前库

**改写 SQL**

```sql
SET @project_id := 0;
SET @monthly_income_ceiling := 3000;
SET @total_trade_floor := 100000;

SELECT
    low_income.person_id,
    low_income.relation_cert_no,
    risky.trans_amount,
    risky.max_amount_cr,
    risky.max_amount_dr
FROM (
    SELECT
        monthly.person_id,
        monthly.relation_cert_no,
        AVG(monthly.month_income) AS avg_amount_cr
    FROM (
        SELECT
            t1.person_id,
            t1.relation_cert_no,
            LEFT(t2.TRX_DATE, 7) AS income_month,
            SUM(t2.AMOUNT_CR) AS month_income
        FROM ccdi_staff_fmy_relation t1
        INNER JOIN ccdi_bank_statement t2
            ON t1.relation_cert_no = t2.cret_no
        WHERE t1.status = 1
          AND t2.project_id = @project_id
          AND t2.LE_ACCOUNT_NAME <> t2.CUSTOMER_ACCOUNT_NAME
        GROUP BY t1.person_id, t1.relation_cert_no, LEFT(t2.TRX_DATE, 7)
    ) monthly
    GROUP BY monthly.person_id, monthly.relation_cert_no
    HAVING AVG(monthly.month_income) <= @monthly_income_ceiling
) low_income
INNER JOIN (
    SELECT
        t1.relation_cert_no,
        SUM(IFNULL(t2.AMOUNT_CR, 0) + IFNULL(t2.AMOUNT_DR, 0)) AS trans_amount,
        MAX(t2.AMOUNT_CR) AS max_amount_cr,
        MAX(t2.AMOUNT_DR) AS max_amount_dr
    FROM ccdi_staff_fmy_relation t1
    INNER JOIN ccdi_bank_statement t2
        ON t1.relation_cert_no = t2.cret_no
    WHERE t1.status = 1
      AND t2.project_id = @project_id
    GROUP BY t1.relation_cert_no
    HAVING SUM(IFNULL(t2.AMOUNT_CR, 0) + IFNULL(t2.AMOUNT_DR, 0)) >= @total_trade_floor
) risky
    ON low_income.relation_cert_no = risky.relation_cert_no;
```

---

### CSV 第 3 行

- 序号：`3.1`
- 模型名称：`疑似赌博`
- 核心异常点（展示在前端页面）：`疑似赌博交易`
- 业务口径：`多人（2人及以上）、多次（2次以上）、相近时间（同一天）内，有转账、微信转账、支付宝转账发生，且额度在可疑区间。金额区间可在排查设置页面进行设置`
- 相关指标：`单日疑似赌博转账金额下限`
- 指标英文名：`空`
- 风险筛查对象：`员工本人`
- 技术口径：`员工本人账户中，24h内统计向不同对手方转账（cash_type='转账'）且金额在可疑区间，笔数≥2且对手方≥2`
- 限制阈值指标：`单日频繁转账金额下限`
- 可疑结果返回：`个人、日期、累计金额`
- 风险等级：`高风险`
- 原始代码：

```sql
--员工 疑似赌博
select id_card,trans_date
from
(
select t1.id_card,left(trx_time,10) as trans_date,customer_account_name
from
ccdi_base_staff t1
inner join
ccdi_bank_statement t2
on t1.id_card = t2.cret_no
where project_id = PROJECT_ID
and ((amount_dr>= $$$ and amount_dr<=$$$) or (amount_cr>= $$$ and amount_cr<=$$$))  -----转入转出金额区间
and customer_account_name is not null
and (user_memo rlike '转帐|转账|红包|网转|转入' or cash_type rlike '转帐|转账|红包|网转|转入')
and user_memo not like '%款%'
and t2.le_account_name <> t2.customer_account_name --排除同名交易
group by t1.id_card,left(trx_time,10),customer_account_name
having count(1)>2
)
group by id_card,trans_date
having count(distinct customer_account_name)>=2;
```

**核对结论**

- 原 SQL 引用了不存在的 `trx_time`
- 外层 `from (...)` 缺少别名
- 原技术口径写“24h 内”，原 SQL 实际按自然日统计
- 原 SQL 内层 `having count(1)>2` 与“2次以上”的自然语言描述并不完全一致

**改写 SQL**

```sql
SET @project_id := 0;
SET @amount_min := 1000;
SET @amount_max := 5000;

SELECT
    daily.id_card,
    daily.trans_date,
    COUNT(DISTINCT daily.customer_account_name) AS counterparty_count,
    SUM(daily.trade_count) AS trade_count
FROM (
    SELECT
        t1.id_card,
        LEFT(t2.TRX_DATE, 10) AS trans_date,
        t2.CUSTOMER_ACCOUNT_NAME AS customer_account_name,
        COUNT(*) AS trade_count
    FROM ccdi_base_staff t1
    INNER JOIN ccdi_bank_statement t2
        ON t1.id_card = t2.cret_no
    WHERE t2.project_id = @project_id
      AND (
            (t2.AMOUNT_DR BETWEEN @amount_min AND @amount_max)
         OR (t2.AMOUNT_CR BETWEEN @amount_min AND @amount_max)
      )
      AND t2.CUSTOMER_ACCOUNT_NAME IS NOT NULL
      AND (
            t2.USER_MEMO REGEXP '转帐|转账|红包|网转|转入'
         OR t2.CASH_TYPE REGEXP '转帐|转账|红包|网转|转入'
      )
      AND (t2.USER_MEMO IS NULL OR t2.USER_MEMO NOT LIKE '%款%')
      AND t2.LE_ACCOUNT_NAME <> t2.CUSTOMER_ACCOUNT_NAME
    GROUP BY t1.id_card, LEFT(t2.TRX_DATE, 10), t2.CUSTOMER_ACCOUNT_NAME
    HAVING COUNT(*) >= 2
) daily
GROUP BY daily.id_card, daily.trans_date
HAVING COUNT(DISTINCT daily.customer_account_name) >= 2;
```

**说明**

- 改写版将“多次”按 `>= 2` 处理，更贴近中文业务口径
- 如果后续必须按原 SQL 的严格条件执行，可将 `HAVING COUNT(*) >= 2` 改回 `> 2`

---

### CSV 第 4 行

- 序号：`空`
- 模型名称：`空`
- 核心异常点（展示在前端页面）：`空`
- 业务口径：`空`
- 相关指标：`单日疑似赌博转账金额上限`
- 指标英文名：`空`
- 风险筛查对象：`员工本人`
- 技术口径：`空`
- 代码：`空`
- 限制阈值指标：`单日频繁转账金额上限`
- 可疑结果返回：`空`
- 风险等级：`空`

**核对结论**

- 该行不是独立模型 SQL，而是对 `3.1` 的上限参数补充
- 建议在模型参数表中为 `3.1` 同时维护下限和上限两个阈值字段，不应单独落成 SQL

---

### CSV 第 5 行

- 序号：`3.2`
- 模型名称：`空`
- 核心异常点（展示在前端页面）：`疑似敏感交易`
- 业务口径：`备注或交易摘要、对手有“游戏、抖币、体彩、福彩”等字眼。`
- 相关指标：`赌博关键词支出`
- 指标英文名：`空`
- 风险筛查对象：`员工本人`
- 技术口径：`员工本人账户中，筛选备注或交易摘要、对手方名称有“游戏、抖币、体彩、福彩”等字眼关键词，汇总金额`
- 限制阈值指标：`/`
- 可疑结果返回：`流水明细`
- 风险等级：`高风险`
- 原始代码：

```sql
--员工 网络赌博、体彩
select t2.bank_statement_id
from
ccdi_base_staff t1
inner join
ccdi_bank_statement t2
on t1.id_card = t2.cret_no
where project_id = PROJECT_ID
and amount_dr> 0
and (user_memo rlike '游戏|抖币|体彩|福彩|彩票|赌|球|外围|博彩|六合|时时彩|赛车|赌场|筹码|盘口|返水|洗码|庄家|闲家|百家乐|斗牛|炸金花|牌九|麻将|捕鱼|电子游艺|投注'
or customer_account_name rlike '游戏|抖币|体彩|福彩|彩票|赌|球|外围|博彩|六合|时时彩|赛车|赌场|筹码|盘口|返水|洗码|庄家|闲家|百家乐|斗牛|炸金花|牌九|麻将|捕鱼|电子游艺|投注')
;
```

**核对结论**

- 主表和字段与当前库匹配
- 语法可兼容 `MySQL 5.7`
- 仍需用参数替换 `PROJECT_ID`

**改写 SQL**

```sql
SET @project_id := 0;

SELECT
    t2.bank_statement_id
FROM ccdi_base_staff t1
INNER JOIN ccdi_bank_statement t2
    ON t1.id_card = t2.cret_no
WHERE t2.project_id = @project_id
  AND t2.AMOUNT_DR > 0
  AND (
        t2.USER_MEMO REGEXP '游戏|抖币|体彩|福彩|彩票|赌|球|外围|博彩|六合|时时彩|赛车|赌场|筹码|盘口|返水|洗码|庄家|闲家|百家乐|斗牛|炸金花|牌九|麻将|捕鱼|电子游艺|投注'
     OR t2.CUSTOMER_ACCOUNT_NAME REGEXP '游戏|抖币|体彩|福彩|彩票|赌|球|外围|博彩|六合|时时彩|赛车|赌场|筹码|盘口|返水|洗码|庄家|闲家|百家乐|斗牛|炸金花|牌九|麻将|捕鱼|电子游艺|投注'
  );
```

---

### CSV 第 6 行

- 序号：`4`
- 模型名称：`可疑关系`
- 核心异常点（展示在前端页面）：`特殊金额交易`
- 业务口径：`除与配偶、子女外，发生特殊金额交易，如1314元、520元等具有特殊含义的金额。`
- 相关指标：`特殊金额交易`
- 指标英文名：`空`
- 风险筛查对象：`员工本人`
- 技术口径：`员工本人账户中，筛选交易金额匹配特殊值（如1314），且对手方名称非配偶/子女，统计笔数`
- 限制阈值指标：`/`
- 可疑结果返回：`流水明细`
- 风险等级：`空`
- 原始代码：

```sql
--员工 可疑关系
select distinct t2.bank_statement_id
from
ccdi_base_staff t1
inner join
ccdi_bank_statement t2
on t1.id_card = t2.cret_no
left join
ccdi_staff_fmy_relation t3
on t1.id_card = t3.person_id
and t2.customer_account_name = t3.relation_name
where t2.project_id = PROJECT_ID
and t2.le_account_name <> t2.customer_account_name --排除同名交易
and t3.relation_type not in (配偶，子女) --关系类型按实际数据的码值确定
and (amount_dr in (520,1314) or amount_cr in (520,1314))
;
```

**核对结论**

- 原 SQL 中 `not in (配偶，子女)` 缺少引号，且使用了全角逗号，语法错误
- 使用 `left join + not in` 会把未匹配到亲属关系的记录误伤为 `null not in (...)`
- 当前库的 `relation_type` 实际可能存码值，不能直接假定一定是中文

**改写 SQL**

```sql
SET @project_id := 0;

SELECT DISTINCT
    t2.bank_statement_id
FROM ccdi_base_staff t1
INNER JOIN ccdi_bank_statement t2
    ON t1.id_card = t2.cret_no
WHERE t2.project_id = @project_id
  AND t2.LE_ACCOUNT_NAME <> t2.CUSTOMER_ACCOUNT_NAME
  AND (t2.AMOUNT_DR IN (520, 1314) OR t2.AMOUNT_CR IN (520, 1314))
  AND NOT EXISTS (
      SELECT 1
      FROM ccdi_staff_fmy_relation t3
      WHERE t3.person_id = t1.id_card
        AND t3.status = 1
        AND t3.relation_name = t2.CUSTOMER_ACCOUNT_NAME
        AND t3.relation_type IN ('配偶', '子女')
  );
```

**说明**

- 如果 `relation_type` 在现网存的是码值，需要把 `'配偶'`、`'子女'` 替换成真实码值

---

### CSV 第 7 行

- 序号：`5.1`
- 模型名称：`可疑兼职`
- 核心异常点（展示在前端页面）：`疑似兼职`
- 业务口径：`除本行工资收入外，每月有固定收入，固定收入金额自行设置。`
- 相关指标：`月度非本行工资收入金额`
- 指标英文名：`MONTHLY_FIXED_INCOME`
- 风险筛查对象：`员工本人`
- 技术口径：`员工本人账户中，筛选 amount_cr>0，除本行工资收入外，每月有固定收入，固定收入金额自行设置。`
- 限制阈值指标：`非本行工资收入金额`
- 可疑结果返回：`个人、累积金额`
- 风险等级：`空`
- 原始代码：

```sql
--员工 可疑兼职
select id_card
FROM
(
select t1.id_card
,left(TRX_DATE,7) as incm_mnth
,sum(t2.amount_cr) as sum_amount_cr
from
ccdi_base_staff t1
inner join
ccdi_bank_statement t2
on t1.id_card = t2.cret_no
where project_id = PROJECT_ID
and t2.le_account_name <> t2.customer_account_name --排除同名交易
and not (customer_account_name = '浙江兰溪农村商业银行股份有限公司'
and (user_memo rlike '代发|工资|分红|红利|奖金|薪酬|薪金|补贴|薪|年终奖|年金|加班费|劳务费|劳务外包|提成|劳务派遣|绩效|酬劳|批量代付|PAYROLL|SALA|CPF|directors.*fees'
or cash_type rlike '代发|工资|劳务费' ))
and customer_account_name is not null
and left(TRX_DATE,10) >= add_months(current_date(),-12)     --近一年
and amount_cr>0
group by t1.id_card,left(t2.TRX_DATE,7)
)
where sum_amount_cr > $$$$ --每月收入参数
group by id_card
having count(distinct incm_mnth)>=6   -----一年内6个月满足收入门槛
and STDDEV(sum_amount_cr)/AVG(sum_amount_cr) <= 0.3  --标准差与平均值的比值小，波动小
;
```

**核对结论**

- 原 SQL 外层派生表缺少别名
- 原 SQL 使用 `add_months()`，当前 `MySQL 5.7` 不支持
- `TRX_DATE` 为字符串，必须显式转日期后再做时间比较

**改写 SQL**

```sql
SET @project_id := 0;
SET @monthly_income_floor := 5000;
SET @stable_month_count := 6;
SET @volatility_ratio_limit := 0.3;

SELECT
    monthly_income.id_card
FROM (
    SELECT
        t1.id_card,
        LEFT(t2.TRX_DATE, 7) AS incm_mnth,
        SUM(t2.AMOUNT_CR) AS sum_amount_cr
    FROM ccdi_base_staff t1
    INNER JOIN ccdi_bank_statement t2
        ON t1.id_card = t2.cret_no
    WHERE t2.project_id = @project_id
      AND t2.LE_ACCOUNT_NAME <> t2.CUSTOMER_ACCOUNT_NAME
      AND NOT (
            t2.CUSTOMER_ACCOUNT_NAME = '浙江兰溪农村商业银行股份有限公司'
        AND (
                t2.USER_MEMO REGEXP '代发|工资|分红|红利|奖金|薪酬|薪金|补贴|薪|年终奖|年金|加班费|劳务费|劳务外包|提成|劳务派遣|绩效|酬劳|批量代付|PAYROLL|SALA|CPF|directors.*fees'
             OR t2.CASH_TYPE REGEXP '代发|工资|劳务费'
        )
      )
      AND t2.CUSTOMER_ACCOUNT_NAME IS NOT NULL
      AND STR_TO_DATE(LEFT(t2.TRX_DATE, 10), '%Y-%m-%d') >= DATE_SUB(CURDATE(), INTERVAL 12 MONTH)
      AND t2.AMOUNT_CR > 0
    GROUP BY t1.id_card, LEFT(t2.TRX_DATE, 7)
) monthly_income
WHERE monthly_income.sum_amount_cr > @monthly_income_floor
GROUP BY monthly_income.id_card
HAVING COUNT(DISTINCT monthly_income.incm_mnth) >= @stable_month_count
   AND STDDEV(monthly_income.sum_amount_cr) / NULLIF(AVG(monthly_income.sum_amount_cr), 0) <= @volatility_ratio_limit;
```

---

### CSV 第 8 行

- 序号：`5.2`
- 模型名称：`空`
- 核心异常点（展示在前端页面）：`疑似兼职`
- 业务口径：`每季或每年从固定交易对手转入金额，金额可设区间值，如5000-10000。`
- 相关指标：`季度稳定收入金额`
- 指标英文名：`FIXED_COUNTERPARTY_TRANSFER`
- 风险筛查对象：`员工本人`
- 技术口径：`员工本人账户中，按季/年统计同一对手方累计流入金额在设定区间内`
- 限制阈值指标：`稳定季度收入金额`
- 可疑结果返回：`个人、累积金额`
- 风险等级：`空`
- 原始代码：

```sql
--员工 可疑固定收入
select id_card
from
(
select
id_card
,customer_account_name
,trans_qrt
,sum(amount_cr) as amount_total
from
(
select t1.id_card
,customer_account_name
,amount_cr
,concat(year(trx_time),'-Q',quarter(trx_time)) as trans_qrt  --每季度的固定收入
from
ccdi_base_staff t1
inner join
ccdi_bank_statement t2
on t1.id_card = t2.cret_no
where project_id = PROJECT_ID
and not (customer_account_name = '浙江兰溪农村商业银行股份有限公司'
and (user_memo rlike '代发|工资|分红|红利|奖金|薪酬|薪金|补贴|薪|年终奖|年金|加班费|劳务费|劳务外包|提成|劳务派遣|绩效|酬劳|批量代付|PAYROLL|SALA|CPF|directors.*fees'
or cash_type rlike '代发|工资|劳务费' ))
and customer_account_name is not null
and left(TRX_DATE,10) >= add_months(current_date(),-12)     --近一年
and amount_cr>0   --每笔收入金额
and t2.le_account_name <> t2.customer_account_name --排除同名交易
)
group by id_card,customer_account_name,trans_qrt
having sum(amount_cr) between $$$$ and $$$$    ---该季度总收入，区间自行设置
)
group by id_card
having count(distinct customer_account_name) < 3
;
```

**核对结论**

- 原 SQL 引用了不存在的 `trx_time`
- 两层派生表均缺少别名
- 原 SQL 使用 `add_months()`，当前 `MySQL 5.7` 不支持

**改写 SQL**

```sql
SET @project_id := 0;
SET @quarter_income_min := 5000;
SET @quarter_income_max := 10000;

SELECT
    quarter_income.id_card
FROM (
    SELECT
        src.id_card,
        src.customer_account_name,
        CONCAT(YEAR(src.trx_date), '-Q', QUARTER(src.trx_date)) AS trans_qrt,
        SUM(src.amount_cr) AS amount_total
    FROM (
        SELECT
            t1.id_card,
            t2.CUSTOMER_ACCOUNT_NAME AS customer_account_name,
            t2.AMOUNT_CR AS amount_cr,
            STR_TO_DATE(LEFT(t2.TRX_DATE, 10), '%Y-%m-%d') AS trx_date
        FROM ccdi_base_staff t1
        INNER JOIN ccdi_bank_statement t2
            ON t1.id_card = t2.cret_no
        WHERE t2.project_id = @project_id
          AND NOT (
                t2.CUSTOMER_ACCOUNT_NAME = '浙江兰溪农村商业银行股份有限公司'
            AND (
                    t2.USER_MEMO REGEXP '代发|工资|分红|红利|奖金|薪酬|薪金|补贴|薪|年终奖|年金|加班费|劳务费|劳务外包|提成|劳务派遣|绩效|酬劳|批量代付|PAYROLL|SALA|CPF|directors.*fees'
                 OR t2.CASH_TYPE REGEXP '代发|工资|劳务费'
            )
          )
          AND t2.CUSTOMER_ACCOUNT_NAME IS NOT NULL
          AND STR_TO_DATE(LEFT(t2.TRX_DATE, 10), '%Y-%m-%d') >= DATE_SUB(CURDATE(), INTERVAL 12 MONTH)
          AND t2.AMOUNT_CR > 0
          AND t2.LE_ACCOUNT_NAME <> t2.CUSTOMER_ACCOUNT_NAME
    ) src
    GROUP BY src.id_card, src.customer_account_name, CONCAT(YEAR(src.trx_date), '-Q', QUARTER(src.trx_date))
    HAVING SUM(src.amount_cr) BETWEEN @quarter_income_min AND @quarter_income_max
) quarter_income
GROUP BY quarter_income.id_card
HAVING COUNT(DISTINCT quarter_income.customer_account_name) < 3;
```

---

### CSV 第 9 行

- 序号：`空`
- 模型名称：`空`
- 核心异常点（展示在前端页面）：`疑似兼职`
- 业务口径：`转入资金摘要有“工资”、“分红”、“红利”、“利息（非银行结息）”等收入`
- 相关指标：`/`
- 指标英文名：`空`
- 风险筛查对象：`员工本人`
- 技术口径：`空`
- 限制阈值指标：`/`
- 可疑结果返回：`流水明细`
- 风险等级：`高风险`
- 原始代码：

```sql
select distinct t2.bank_statement_id
from
ccdi_base_staff t1
inner join
ccdi_bank_statement t2
on t1.id_card = t2.cret_no
where t2.project_id = PROJECT_ID
and t2.customer_account_name <> '浙江兰溪农村商业银行股份有限公司'
and (t2.user_memo rlike '代发|工资|分红|红利|奖金|薪酬|薪金|补贴|薪|年终奖|年金|加班费|劳务费|劳务外包|提成|劳务派遣|绩效|酬劳|批量代付|PAYROLL|SALA|CPF|directors.*fees'
or cash_type rlike '代发|工资|劳务费' )
;
```

**核对结论**

- 原 SQL 主表、字段、语法均基本匹配当前库
- 结合业务口径，建议增加 `AMOUNT_CR > 0`，避免把支出误判成收入类线索

**改写 SQL**

```sql
SET @project_id := 0;

SELECT DISTINCT
    t2.bank_statement_id
FROM ccdi_base_staff t1
INNER JOIN ccdi_bank_statement t2
    ON t1.id_card = t2.cret_no
WHERE t2.project_id = @project_id
  AND t2.AMOUNT_CR > 0
  AND t2.CUSTOMER_ACCOUNT_NAME <> '浙江兰溪农村商业银行股份有限公司'
  AND (
        t2.USER_MEMO REGEXP '代发|工资|分红|红利|奖金|薪酬|薪金|补贴|薪|年终奖|年金|加班费|劳务费|劳务外包|提成|劳务派遣|绩效|酬劳|批量代付|PAYROLL|SALA|CPF|directors.*fees'
     OR t2.CASH_TYPE REGEXP '代发|工资|劳务费'
  );
```

---

### CSV 第 10 行

- 序号：`6.1`
- 模型名称：`可疑财产`
- 核心异常点（展示在前端页面）：`购房交易与房产登记不匹配`
- 业务口径：`员工及关系人有购房交易，但名下房产无新增登记；有新增登记购房，但无相关购房交易记录。`
- 相关指标：`/`
- 指标英文名：`空`
- 风险筛查对象：`员工本人及亲属`
- 技术口径：`员工及其亲属账户中，存在购房支出，且在家庭负债表（ccdi_family_liability）中该员工名下无新增房产登记，则标记1`
- 限制阈值指标：`/`
- 可疑结果返回：`流水明细`
- 风险等级：`空`
- 原始代码：

```sql
--员工及其亲属购买房产但无资产登记
select distinct bank_statement_id
from
(
select t1.id_card
,bank_statement_id
,trx_time
from
ccdi_base_staff t1
inner join
ccdi_bank_statement t2
on t1.id_card = t2.cret_no
where project_id = PROJECT_ID
and (user_memo rlike '(购|买).*房|房款|首付'
or customer_account_name rlike '房地产|置业|置地|地产|房产|不动产|链家|贝壳|我爱我家|房管局')
and amount_dr > 0
union all
select t1.person_id
,bank_statement_id
,trx_time
from
ccdi_staff_fmy_relation t1
inner join
ccdi_bank_statement t2
on t1.relation_cert_no = t2.cret_no
where t1.status = 1
and t2.project_id = PROJECT_ID
and (user_memo rlike '(购|买).*房|房款|首付'
or customer_account_name rlike '房地产|置业|置地|地产|房产|不动产|链家|贝壳|我爱我家|房管局')
and amount_dr > 0
) t1
left join
(
select person_id
,max(updated_at) as updated_at
from ccdi_asset_info
where asset_main_type = 不动产    --根据具体数据确定码值
and asset_sub_type in (住宅,商铺) --根据具体数据确定码值
and asset_status = 正常 --根据具体数据确定码值
group by person_id
) t2
on t1.id_card = t2.person_id
where t1.trx_time > t2.updated_at --购买时间大于最近一次资产更新时间
or t2.person_id is null; --未登记房产
```

**核对结论**

- 原 SQL 引用了不存在的 `trx_time` 和 `updated_at`
- 原 SQL 使用了未加引号的中文常量
- 原技术口径提到 `ccdi_family_liability`，但当前库实际只有 `ccdi_asset_info`
- 资产表中房产相关枚举值需按现网实际码值替换

**改写 SQL**

```sql
SET @project_id := 0;
SET @asset_main_type_house := 'REAL_ESTATE';
SET @asset_sub_type_house_1 := 'HOUSE';
SET @asset_sub_type_house_2 := 'SHOP';
SET @asset_status_normal := 'NORMAL';

SELECT DISTINCT
    house_trade.bank_statement_id
FROM (
    SELECT
        t1.id_card AS person_id,
        t2.bank_statement_id,
        STR_TO_DATE(LEFT(t2.TRX_DATE, 10), '%Y-%m-%d') AS trx_date
    FROM ccdi_base_staff t1
    INNER JOIN ccdi_bank_statement t2
        ON t1.id_card = t2.cret_no
    WHERE t2.project_id = @project_id
      AND (
            t2.USER_MEMO REGEXP '(购|买).*房|房款|首付'
         OR t2.CUSTOMER_ACCOUNT_NAME REGEXP '房地产|置业|置地|地产|房产|不动产|链家|贝壳|我爱我家|房管局'
      )
      AND t2.AMOUNT_DR > 0

    UNION ALL

    SELECT
        t1.person_id,
        t2.bank_statement_id,
        STR_TO_DATE(LEFT(t2.TRX_DATE, 10), '%Y-%m-%d') AS trx_date
    FROM ccdi_staff_fmy_relation t1
    INNER JOIN ccdi_bank_statement t2
        ON t1.relation_cert_no = t2.cret_no
    WHERE t1.status = 1
      AND t2.project_id = @project_id
      AND (
            t2.USER_MEMO REGEXP '(购|买).*房|房款|首付'
         OR t2.CUSTOMER_ACCOUNT_NAME REGEXP '房地产|置业|置地|地产|房产|不动产|链家|贝壳|我爱我家|房管局'
      )
      AND t2.AMOUNT_DR > 0
) house_trade
LEFT JOIN (
    SELECT
        person_id,
        MAX(update_time) AS latest_asset_update_time
    FROM ccdi_asset_info
    WHERE asset_main_type = @asset_main_type_house
      AND asset_sub_type IN (@asset_sub_type_house_1, @asset_sub_type_house_2)
      AND asset_status = @asset_status_normal
    GROUP BY person_id
) asset
    ON house_trade.person_id = asset.person_id
WHERE asset.person_id IS NULL
   OR house_trade.trx_date > DATE(asset.latest_asset_update_time);
```

**说明**

- `REAL_ESTATE`、`HOUSE`、`SHOP`、`NORMAL` 只是占位值，必须替换成 `ccdi_asset_info` 的真实码值
- 原业务口径还提到“有新增登记购房，但无相关购房交易记录”，该反向校验不在原 SQL 中，本次未擅自补充为双向模型

---

### CSV 第 11 行

- 序号：`6.2`
- 模型名称：`可疑财产`
- 核心异常点（展示在前端页面）：`物业缴费与房产登记不匹配`
- 业务口径：`员工及关系人有物业缴费记录，但名下房产无新增登记。`
- 相关指标：`/`
- 指标英文名：`空`
- 风险筛查对象：`员工本人及亲属`
- 技术口径：`员工及其亲属账户中，存在物业费支出，且在家庭负债表中无新增房产登记，则标记1`
- 限制阈值指标：`/`
- 可疑结果返回：`流水明细`
- 风险等级：`空`
- 原始代码：

```sql
有物业缴费记录但无房产登记
select distinct bank_statement_id
FROM
(
select t1.id_card
,bank_statement_id
from
ccdi_base_staff t1
inner join
ccdi_bank_statement t2
on t1.id_card = t2.cret_no
where project_id = PROJECT_ID
and (user_memo rlike '物业|物业费|管理费|物业服务|综合服务'
or customer_account_name rlike '物业|小区|花园|苑|中心|大厦|业委会|业主委员会|置业|房地产|服务中心|管理处|社区')
and amount_dr > 0
union all
select t1.person_id
,bank_statement_id
from
ccdi_staff_fmy_relation t1
inner join
ccdi_bank_statement t2
on t1.relation_cert_no = t2.cret_no
where t1.status = 1
and t2.project_id = PROJECT_ID
and (user_memo rlike '物业|物业费|管理费|物业服务|综合服务'
or customer_account_name rlike '物业|小区|花园|苑|中心|大厦|业委会|业主委员会|置业|房地产|服务中心|管理处|社区')
and amount_dr > 0
) t1
left join
(
select person_id
,max(updated_at) as updated_at
from ccdi_asset_info
where asset_main_type = 不动产
and asset_sub_type in (住宅,商铺)
and asset_status = 正常
group by person_id
) t2
on t1.id_card = t2.person_id
where t2.person_id is null;
```

**核对结论**

- 原 SQL 引用了不存在的 `updated_at`
- 原 SQL 的资产枚举值写法不符合当前库
- 可完全改写为当前结构可执行版本

**改写 SQL**

```sql
SET @project_id := 0;
SET @asset_main_type_house := 'REAL_ESTATE';
SET @asset_sub_type_house_1 := 'HOUSE';
SET @asset_sub_type_house_2 := 'SHOP';
SET @asset_status_normal := 'NORMAL';

SELECT DISTINCT
    property_fee.bank_statement_id
FROM (
    SELECT
        t1.id_card AS person_id,
        t2.bank_statement_id
    FROM ccdi_base_staff t1
    INNER JOIN ccdi_bank_statement t2
        ON t1.id_card = t2.cret_no
    WHERE t2.project_id = @project_id
      AND (
            t2.USER_MEMO REGEXP '物业|物业费|管理费|物业服务|综合服务'
         OR t2.CUSTOMER_ACCOUNT_NAME REGEXP '物业|小区|花园|苑|中心|大厦|业委会|业主委员会|置业|房地产|服务中心|管理处|社区'
      )
      AND t2.AMOUNT_DR > 0

    UNION ALL

    SELECT
        t1.person_id,
        t2.bank_statement_id
    FROM ccdi_staff_fmy_relation t1
    INNER JOIN ccdi_bank_statement t2
        ON t1.relation_cert_no = t2.cret_no
    WHERE t1.status = 1
      AND t2.project_id = @project_id
      AND (
            t2.USER_MEMO REGEXP '物业|物业费|管理费|物业服务|综合服务'
         OR t2.CUSTOMER_ACCOUNT_NAME REGEXP '物业|小区|花园|苑|中心|大厦|业委会|业主委员会|置业|房地产|服务中心|管理处|社区'
      )
      AND t2.AMOUNT_DR > 0
) property_fee
LEFT JOIN (
    SELECT
        person_id
    FROM ccdi_asset_info
    WHERE asset_main_type = @asset_main_type_house
      AND asset_sub_type IN (@asset_sub_type_house_1, @asset_sub_type_house_2)
      AND asset_status = @asset_status_normal
    GROUP BY person_id
) asset
    ON property_fee.person_id = asset.person_id
WHERE asset.person_id IS NULL;
```

---

### CSV 第 12 行

- 序号：`6.3`
- 模型名称：`可疑财产`
- 核心异常点（展示在前端页面）：`大额纳税与资产登记不匹配`
- 业务口径：`员工及关系人有5000元以上的纳税记录，但名下无房产车产新增登记。`
- 相关指标：`/`
- 指标英文名：`空`
- 风险筛查对象：`员工本人及亲属`
- 技术口径：`员工及其亲属账户中，存在单笔纳税 >5000 元，且在家庭负债表中无新增房产/车产登记，则标记1`
- 限制阈值指标：`/`
- 可疑结果返回：`流水明细`
- 风险等级：`空`
- 原始代码：

```sql
有5000元以上的纳税记录但无房产登记
select distinct bank_statement_id
FROM
(
select t1.id_card
,bank_statement_id
from
ccdi_base_staff t1
inner join
ccdi_bank_statement t2
on t1.id_card = t2.cret_no
where project_id = PROJECT_ID
and (user_memo rlike '税务|缴税|税款'
or customer_account_name rlike '税务|税务局|国库|国家金库|财政')
and amount_dr >= 5000
union all
select t1.person_id
,bank_statement_id
from
ccdi_staff_fmy_relation t1
inner join
ccdi_bank_statement t2
on t1.relation_cert_no = t2.cret_no
where t1.status = 1
and t2.project_id = PROJECT_ID
and (user_memo rlike '税务|缴税|税款'
or customer_account_name rlike '税务|税务局|国库|国家金库|财政')
and amount_dr >= 5000
) t1
left join
(
select person_id
,max(updated_at) as updated_at
from ccdi_asset_info
where asset_main_type = 不动产
and asset_sub_type in (住宅,商铺)
and asset_status = 正常
group by person_id
) t2
on t1.id_card = t2.person_id
where t2.person_id is null;
```

**核对结论**

- 原 SQL 仍然只校验“无房产登记”，与业务口径中的“无房产车产新增登记”不一致
- 原 SQL 引用了不存在的 `updated_at`
- 资产类型应按真实码值配置

**改写 SQL**

```sql
SET @project_id := 0;
SET @tax_amount_floor := 5000;
SET @asset_main_type_house := 'REAL_ESTATE';
SET @asset_main_type_car := 'VEHICLE';
SET @asset_status_normal := 'NORMAL';

SELECT DISTINCT
    tax_trade.bank_statement_id
FROM (
    SELECT
        t1.id_card AS person_id,
        t2.bank_statement_id
    FROM ccdi_base_staff t1
    INNER JOIN ccdi_bank_statement t2
        ON t1.id_card = t2.cret_no
    WHERE t2.project_id = @project_id
      AND (
            t2.USER_MEMO REGEXP '税务|缴税|税款'
         OR t2.CUSTOMER_ACCOUNT_NAME REGEXP '税务|税务局|国库|国家金库|财政'
      )
      AND t2.AMOUNT_DR >= @tax_amount_floor

    UNION ALL

    SELECT
        t1.person_id,
        t2.bank_statement_id
    FROM ccdi_staff_fmy_relation t1
    INNER JOIN ccdi_bank_statement t2
        ON t1.relation_cert_no = t2.cret_no
    WHERE t1.status = 1
      AND t2.project_id = @project_id
      AND (
            t2.USER_MEMO REGEXP '税务|缴税|税款'
         OR t2.CUSTOMER_ACCOUNT_NAME REGEXP '税务|税务局|国库|国家金库|财政'
      )
      AND t2.AMOUNT_DR >= @tax_amount_floor
) tax_trade
LEFT JOIN (
    SELECT
        person_id
    FROM ccdi_asset_info
    WHERE asset_status = @asset_status_normal
      AND asset_main_type IN (@asset_main_type_house, @asset_main_type_car)
    GROUP BY person_id
) asset
    ON tax_trade.person_id = asset.person_id
WHERE asset.person_id IS NULL;
```

**说明**

- 该改写版按业务口径补充了“车产”主类判断，但主类码值仍需按现网真实枚举替换

---

## 汇总结论

- CSV 共 `12` 行，其中：
  - `10` 行带 `sql<br>` 前缀 SQL
  - `1` 行带原始 SQL 但未写 `sql<br>` 前缀
  - `1` 行仅用于补充阈值参数，没有独立 SQL
- 当前库能直接承接并改写的模型：
  - `2.2`
  - `3.1`
  - `3.2`
  - `4`
  - `5.1`
  - `5.2`
  - `CSV 第 9 行补充规则`
  - `6.1`
  - `6.2`
  - `6.3`
- 当前库不能完全独立落地的模型：
  - `2.1`

## 语法校验结果

- 已使用 `EXPLAIN` 在当前 `MySQL 5.7.44 / ccdi` 上校验通过的改写 SQL：
  - `2.2`
  - `3.1`
  - `3.2`
  - `4`
  - `5.1`
  - `5.2`
  - `CSV 第 9 行补充规则`
  - `6.1`
  - `6.2`
  - `6.3`
- 未纳入自动语法校验的改写 SQL：
  - `2.1`
  - 原因：改写版依赖 `tmp_model_21_loan_cust_acct`、`tmp_model_21_assure_cust_acct`、`tmp_model_21_intermediary_acct` 三张引用表，当前库尚未创建

## 建议后续动作

1. 为 `2.1` 建立客户账号引用清单表，或者把外部客户库同步到 `ccdi`
2. 为资产模型补齐 `asset_main_type`、`asset_sub_type`、`asset_status` 的字典码值说明
3. 将 `PROJECT_ID`、上下限金额等参数沉淀到模型参数表，而不是保留在文本 SQL 中
4. 如果后续要在代码里执行这些 SQL，建议统一封装成 MyBatis XML，并配套 DTO/VO 与单元测试