训练和测试旨在检测洗钱的模型

本快速入门将引导您完成使用 Anti Money Laundering AI (AML AI) API 检测洗钱的模型的端到端实现。在本指南中，您将通过以下步骤了解如何训练和测试模型以检测洗钱活动：

  1. 准备云环境并创建 AML AI 实例。
  2. 以 BigQuery 表的形式提供合成交易数据。
  3. 使用输入数据训练模型并进行回测。
  4. 注册参与方并进行模型预测。

在创建预测结果后，本指南将分析一个通过资金结构化进行洗钱的示例当事方的单一案例。

准备工作

本部分介绍了如何设置 Google Cloud 账号、启用所需的Google Cloud 服务，以及授予运行快速入门所需的权限。

如果您要使用自己不拥有的现有项目，可能需要管理员授予您访问该现有项目的某些权限。如需了解详情，请参阅创建和管理项目。

  1. Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

  2. Install the Google Cloud CLI.

  3. If you're using an external identity provider (IdP), you must first sign in to the gcloud CLI with your federated identity.

  4. To initialize the gcloud CLI, run the following command: 

    gcloud init

  5. Create or select a Google Cloud project.

    • Create a Google Cloud project:

      gcloud projects create PROJECT_ID

      Replace PROJECT_ID with a name for the Google Cloud project you are creating.

    • Select the Google Cloud project that you created:

      gcloud config set project PROJECT_ID

      Replace PROJECT_ID with your Google Cloud project name.

  6. Make sure that billing is enabled for your Google Cloud project.

  7. Enable the required APIs: 

    gcloud services enable financialservices.googleapis.com bigquery.googleapis.com cloudkms.googleapis.com bigquerydatatransfer.googleapis.com

  8. If you're using a local shell, then create local authentication credentials for your user account: 

    gcloud auth application-default login

    You don't need to do this if you're using Cloud Shell.

    If an authentication error is returned, and you are using an external identity provider (IdP), confirm that you have signed in to the gcloud CLI with your federated identity.

  9. Grant roles to your user account. Run the following command once for each of the following IAM roles: roles/financialservices.admin, roles/cloudkms.admin, roles/bigquery.admin 

    gcloud projects add-iam-policy-binding PROJECT_ID --member="user:USER_IDENTIFIER" --role=ROLE
    • Replace PROJECT_ID with your project ID.

    • Replace USER_IDENTIFIER with the identifier for your user account. For example, user:myemail@example.com.

    • Replace ROLE with each individual role.

  10. Install the Google Cloud CLI.

  11. If you're using an external identity provider (IdP), you must first sign in to the gcloud CLI with your federated identity.

  12. To initialize the gcloud CLI, run the following command: 

    gcloud init

  13. Create or select a Google Cloud project.

    • Create a Google Cloud project:

      gcloud projects create PROJECT_ID

      Replace PROJECT_ID with a name for the Google Cloud project you are creating.

    • Select the Google Cloud project that you created:

      gcloud config set project PROJECT_ID

      Replace PROJECT_ID with your Google Cloud project name.

  14. Make sure that billing is enabled for your Google Cloud project.

  15. Enable the required APIs: 

    gcloud services enable financialservices.googleapis.com bigquery.googleapis.com cloudkms.googleapis.com bigquerydatatransfer.googleapis.com

  16. If you're using a local shell, then create local authentication credentials for your user account: 

    gcloud auth application-default login

    You don't need to do this if you're using Cloud Shell.

    If an authentication error is returned, and you are using an external identity provider (IdP), confirm that you have signed in to the gcloud CLI with your federated identity.

  17. Grant roles to your user account. Run the following command once for each of the following IAM roles: roles/financialservices.admin, roles/cloudkms.admin, roles/bigquery.admin 

    gcloud projects add-iam-policy-binding PROJECT_ID --member="user:USER_IDENTIFIER" --role=ROLE
    • Replace PROJECT_ID with your project ID.

    • Replace USER_IDENTIFIER with the identifier for your user account. For example, user:myemail@example.com.

    • Replace ROLE with each individual role.
    18.  这些角色可满足以下必需的权限：

    所需权限

    您需要拥有以下权限才能完成本快速入门：

    权限 说明
    resourcemanager.projects.get获取 Google Cloud 项目
    resourcemanager.projects.list列出 Google Cloud 个项目
    cloudkms.keyRings.create创建 Cloud KMS 密钥环
    cloudkms.cryptoKeys.create创建 Cloud KMS 密钥
    financialservices.v1instances.create创建 AML AI 实例
    financialservices.operations.get获取 AML AI 操作
    cloudkms.cryptoKeys.getIamPolicy获取 Cloud KMS 密钥的 IAM 政策
    cloudkms.cryptoKeys.setIamPolicy为 Cloud KMS 密钥设置 IAM 政策
    bigquery.datasets.create创建 BigQuery 数据集
    bigquery.datasets.get获取 BigQuery 数据集
    bigquery.transfers.get获取 BigQuery Data Transfer Service 转移作业
    bigquery.transfers.update创建或删除 BigQuery Data Transfer Service 转移作业
    bigquery.datasets.setIamPolicy在 BigQuery 数据集上设置 IAM 政策
    bigquery.datasets.update更新 BigQuery 数据集
    financialservices.v1datasets.create创建 AML AI 数据集
    financialservices.v1engineconfigs.create创建 AML AI 引擎配置
    financialservices.v1models.create创建 AML AI 模型
    financialservices.v1backtests.create创建 AML AI 回测结果
    financialservices.v1backtests.exportMetadata从 AML AI 回测结果导出元数据
    financialservices.v1instances.importRegisteredParties将已注册的当事人导入 AML AI 实例
    financialservices.v1predictions.create创建 AML AI 预测结果
    bigquery.jobs.create创建 BigQuery 作业
    bigquery.tables.getData从 BigQuery 表中获取数据
    financialservices.v1predictions.delete删除 AML AI 预测结果
    financialservices.v1backtests.delete删除 AML AI 回测结果
    financialservices.v1models.delete删除 AML AI 模型
    financialservices.v1engineconfigs.delete删除 AML AI 引擎配置
    financialservices.v1datasets.delete删除 AML AI 数据集
    financialservices.v1instances.delete删除 AML AI 实例
    bigquery.datasets.delete删除 BigQuery 数据集

  18. 本指南中的 API 请求使用相同的 Google Cloud 项目和位置，并对资源 ID 进行硬编码，以便更轻松地完成本指南。资源 ID 遵循 my-资源类型的模式（例如 my-key-ring 和 my-model）。

    请确保为本指南定义了以下替换项：

    • PROJECT_ID：IAM 设置中列出的 Google Cloud 项目 ID
    • PROJECT_NUMBER： 与 PROJECT_ID 关联的项目编号。您可以在 IAM 设置页面上找到项目编号。
    • LOCATION：API 资源的位置；请使用某个受支持的地区
      显示位置
      • us-central1
      • us-east1
      • asia-south1
      • europe-west1
      • europe-west2
      • europe-west4
      • northamerica-northeast1
      • southamerica-east1
      • australia-southeast1

创建实例

本部分介绍如何创建实例。AML AI 实例位于所有其他 AML AI 资源的根目录。每个实例都需要关联一个客户管理的加密密钥 (CMEK)，该密钥用于加密 AML AI 创建的所有数据。

创建密钥环

如需创建密钥环，请使用 projects.locations.keyRings.create 方法。

REST

如需发送请求，请选择以下方式之一：

curl

执行以下命令：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d "" \
     "https://cloudkms.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/keyRings?key_ring_id=my-key-ring"

PowerShell

执行以下命令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -Uri "https://cloudkms.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/keyRings?key_ring_id=my-key-ring" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/keyRings/my-key-ring",
  "createTime": CREATE_TIME
}

gcloud

执行以下命令：

Linux、macOS 或 Cloud Shell

gcloud kms keyrings create my-key-ring \
  --location LOCATION

Windows (PowerShell)

gcloud kms keyrings create my-key-ring `
  --location LOCATION

Windows (cmd.exe)

gcloud kms keyrings create my-key-ring ^
  --location LOCATION
 您应该会收到一个空响应： 
$

创建密钥

如需创建密钥，请使用 projects.locations.keyRings.cryptoKeys 方法。

REST

请求 JSON 正文：

{
  "purpose": "ENCRYPT_DECRYPT"
}

如需发送请求，请选择以下方式之一：

curl

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

cat > request.json << 'EOF'
{
  "purpose": "ENCRYPT_DECRYPT"
}
EOF

然后，执行以下命令以发送 REST 请求：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://cloudkms.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/keyRings/my-key-ring/cryptoKeys?crypto_key_id=my-key"

PowerShell

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

@'
{
  "purpose": "ENCRYPT_DECRYPT"
}
'@  | Out-File -FilePath request.json -Encoding utf8

然后，执行以下命令以发送 REST 请求：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://cloudkms.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/keyRings/my-key-ring/cryptoKeys?crypto_key_id=my-key" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/keyRings/my-key-ring/cryptoKeys/my-key",
  "primary": {
    "name": "projects/PROJECT_ID/locations/LOCATION/keyRings/my-key-ring/cryptoKeys/my-key/cryptoKeyVersions/1",
    "state": "ENABLED",
    "createTime": CREATE_TIME,
    "protectionLevel": "SOFTWARE",
    "algorithm": "GOOGLE_SYMMETRIC_ENCRYPTION",
    "generateTime": GENERATE_TIME
  },
  "purpose": "ENCRYPT_DECRYPT",
  "createTime": CREATE_TIME,
  "versionTemplate": {
    "protectionLevel": "SOFTWARE",
    "algorithm": "GOOGLE_SYMMETRIC_ENCRYPTION"
  },
  "destroyScheduledDuration": "86400s"
}

gcloud

在使用下面的命令数据之前，请先进行以下替换：

  • LOCATION：密钥环的位置；请使用某个受支持的地区
    显示位置
    • us-central1
    • us-east1
    • asia-south1
    • europe-west1
    • europe-west2
    • europe-west4
    • northamerica-northeast1
    • southamerica-east1
    • australia-southeast1

执行以下命令：

Linux、macOS 或 Cloud Shell

gcloud kms keys create my-key \
  --keyring my-key-ring \
  --location LOCATION \
  --purpose "encryption"

Windows (PowerShell)

gcloud kms keys create my-key `
  --keyring my-key-ring `
  --location LOCATION `
  --purpose "encryption"

Windows (cmd.exe)

gcloud kms keys create my-key ^
  --keyring my-key-ring ^
  --location LOCATION ^
  --purpose "encryption"
 您应该会收到一个空响应： 
$

使用 API 创建实例

如需创建实例，请使用 projects.locations.instances.create 方法。

请求 JSON 正文：

{
  "kmsKey": "projects/PROJECT_ID/locations/LOCATION/keyRings/my-key-ring/cryptoKeys/my-key"
}

如需发送请求，请选择以下方式之一：

curl

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

cat > request.json << 'EOF'
{
  "kmsKey": "projects/PROJECT_ID/locations/LOCATION/keyRings/my-key-ring/cryptoKeys/my-key"
}
EOF

然后，执行以下命令以发送 REST 请求：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances?instance_id=my-instance"

PowerShell

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

@'
{
  "kmsKey": "projects/PROJECT_ID/locations/LOCATION/keyRings/my-key-ring/cryptoKeys/my-key"
}
'@  | Out-File -FilePath request.json -Encoding utf8

然后，执行以下命令以发送 REST 请求：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances?instance_id=my-instance" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.OperationMetadata",
    "createTime": CREATE_TIME,
    "target": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance",
    "verb": "create",
    "requestedCancellation": false,
    "apiVersion": "v1"
  },
  "done": false
}

如果成功，响应正文将包含一个长时间运行的操作，其中包含一个 ID，可用于检索异步操作的当前状态。复制返回的 OPERATION_ID 以在下一部分中使用。

检查结果

使用 projects.locations.operations.get 方法检查实例是否已创建。如果响应包含 "done": false，请重复执行该命令，直到响应包含 "done": true。

本指南中的操作可能需要几分钟到几小时才能完成。 您必须等到某项操作完成后，才能继续学习本指南，因为该 API 会将某些方法的输出用作其他方法的输入。

在使用任何请求数据之前，请先进行以下替换：

  • OPERATION_ID：操作的标识符

如需发送请求，请选择以下方式之一：

curl

执行以下命令：

curl -X GET \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID"

PowerShell

执行以下命令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method GET `
    -Headers $headers `
    -Uri "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.OperationMetadata",
    "createTime": CREATE_TIME,
    "endTime": END_TIME,
    "target": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance",
    "verb": "create",
    "requestedCancellation": false,
    "apiVersion": "v1"
  },
  "done": true,
  "response": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.Instance",
    "name": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance",
    "createTime": CREATE_TIME,
    "updateTime": UPDATE_TIME,
    "kmsKey": "projects/KMS_PROJECT_ID/locations/LOCATION/keyRings/my-key-ring/cryptoKeys/my-key",
    "state": "ACTIVE"
  }
}

授予对 CMEK 密钥的访问权限

该 API 会自动在您的项目中创建一个服务账号。服务账号需要有权访问 CMEK 密钥，以便使用该密钥加密和解密底层数据。授予对密钥的访问权限。

gcloud kms keys add-iam-policy-binding "projects/PROJECT_ID/locations/LOCATION/keyRings/my-key-ring/cryptoKeys/my-key" \
  --keyring "projects/PROJECT_ID/locations/LOCATION/keyRings/my-key-ring" \
  --location "LOCATION" \
  --member "serviceAccount:service-PROJECT_NUMBER@gcp-sa-financialservices.iam.gserviceaccount.com" \
  --role="roles/cloudkms.cryptoKeyEncrypterDecrypter" \
  --project="PROJECT_ID"

创建 BigQuery 数据集

本部分介绍了如何创建输入和输出 BigQuery 数据集，然后将示例银行数据复制到输入数据集。

创建输出数据集

创建数据集，用于将 AML 流水线输出发送到该数据集。

Bash

bq mk \
  --location=LOCATION \
  --project_id=PROJECT_ID \
  my_bq_output_dataset

PowerShell

bq mk `
  --location=LOCATION `
  --project_id=PROJECT_ID `
  my_bq_output_dataset

创建输入数据集

创建一个数据集，用于将示例银行表复制到其中。

Bash

bq mk \
  --location=LOCATION \
  --project_id=PROJECT_ID \
  my_bq_input_dataset

PowerShell

bq mk `
  --location=LOCATION `
  --project_id=PROJECT_ID `
  my_bq_input_dataset

复制示例数据集

示例银行数据以 BigQuery 数据集的形式提供，位于 Google 的共享数据集项目中。您必须有权访问 AML AI API，才能访问此数据集。此数据集的主要特征包括：

  • 10 万个派对
  • 从 2020 年 1 月 1 日到 2023 年 1 月 1 日的核心时间范围，以及额外的 24 个月的回溯数据
  • 每月 300 个负面风险案例和 20 个正面风险案例
  • 具有以下属性的风险案例：
    • 一半的积极风险案例是针对在 AML_PROCESS_START 事件发生前两个月内发生的结构化活动
    • 另一半涵盖了在 AML_PROCESS_START 活动前两个月内收到资金最多的当事人
    • 负面示例是随机生成的
    • 风险案例以相反状态生成的几率为 0.1%（例如，随机方为正，或者有结构化活动或收入最高的方被报告为负）
  • AML 架构在 AML 输入数据模型中定义。

  1. 将示例银行数据复制到您创建的输入数据集中。

    Bash

    bq mk --transfer_config \
  --project_id=PROJECT_ID \
  --data_source=cross_region_copy \
  --target_dataset="my_bq_input_dataset" \
  --display_name="Copy the AML sample dataset." \
  --schedule=None \
  --params='{
    "source_project_id":"bigquery-public-data",
    "source_dataset_id":"aml_ai_input_dataset",
    "overwrite_destination_table":"true"
  }'

    PowerShell

    bq mk --transfer_config `
--project_id=PROJECT_ID `
--data_source=cross_region_copy `
--target_dataset="my_bq_input_dataset" `
--display_name="Copy the AML sample dataset." `
--schedule=None `
--params='{\"source_project_id\":\"bigquery-public-data\",\"source_dataset_id\":\"aml_ai_input_dataset\",\"overwrite_destination_table\":\"true\"}'

  2. 监控数据转移作业。

    Bash

    bq ls --transfer_config \
--transfer_location=LOCATION \
--project_id=PROJECT_ID \
--filter="dataSourceIds:cross_region_copy"

    PowerShell

    bq ls --transfer_config `
--transfer_location=LOCATION `
--project_id=PROJECT_ID `
--filter="dataSourceIds:cross_region_copy"

    转移完成后，系统会创建一个显示名称为 Copy the AML sample dataset 的数据转移作业。

    您还可以使用 Google Cloud 控制台查看转移状态。

    您应该会看到类似以下输出的内容。

                         name                           displayName         dataSourceId       state
-------------------------------------------  -----------------------  -----------------  ---------
projects/294024168771/locations/us-central1  Copy AML sample dataset  cross_region_copy  SUCCEEDED

授予对 BigQuery 数据集的访问权限

该 API 会自动在您的项目中创建一个服务账号。服务账号需要有权访问 BigQuery 输入和输出数据集。

  1. 授予对输入数据集及其表的读取权限。

    Bash

    bq query --project_id=PROJECT_ID --use_legacy_sql=false \
  'GRANT `roles/bigquery.dataViewer` ON SCHEMA `PROJECT_ID.my_bq_input_dataset` TO "serviceAccount:service-PROJECT_NUMBER@gcp-sa-financialservices.iam.gserviceaccount.com"'

    PowerShell

    bq query --project_id=PROJECT_ID --use_legacy_sql=false "GRANT ``roles/bigquery.dataViewer`` ON SCHEMA ``PROJECT_ID.my_bq_input_dataset`` TO 'serviceAccount:service-PROJECT_NUMBER@gcp-sa-financialservices.iam.gserviceaccount.com'"

  2. 授予对输出数据集的写入权限。

    Bash

    bq query --project_id=PROJECT_ID --use_legacy_sql=false \
  'GRANT `roles/bigquery.dataEditor` ON SCHEMA `PROJECT_ID.my_bq_output_dataset` TO "serviceAccount:service-PROJECT_NUMBER@gcp-sa-financialservices.iam.gserviceaccount.com"'

    PowerShell

    bq query --project_id=PROJECT_ID --use_legacy_sql=false "GRANT ``roles/bigquery.dataEditor`` ON SCHEMA ``PROJECT_ID.my_bq_output_dataset`` TO 'serviceAccount:service-PROJECT_NUMBER@gcp-sa-financialservices.iam.gserviceaccount.com'"

创建 AML AI 数据集

创建 AML AI 数据集，以指定输入 BigQuery 数据集表和要使用的时间范围。

如需创建数据集，请使用 projects.locations.instances.datasets.create 方法。

请求 JSON 正文：

{
  "tableSpecs": {
    "party": "bq://PROJECT_ID.my_bq_input_dataset.party",
    "account_party_link": "bq://PROJECT_ID.my_bq_input_dataset.account_party_link",
    "transaction": "bq://PROJECT_ID.my_bq_input_dataset.transaction",
    "risk_case_event": "bq://PROJECT_ID.my_bq_input_dataset.risk_case_event",
    "party_supplementary_data": "bq://PROJECT_ID.my_bq_input_dataset.party_supplementary_data"
  },
  "dateRange": {
    "startTime": "2020-01-01T00:00:0.00Z",
    "endTime": "2023-01-01T00:00:0.00Z"
  },
  "timeZone": {
    "id": "UTC"
  }
}

如需发送请求，请选择以下方式之一：

curl

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

cat > request.json << 'EOF'
{
  "tableSpecs": {
    "party": "bq://PROJECT_ID.my_bq_input_dataset.party",
    "account_party_link": "bq://PROJECT_ID.my_bq_input_dataset.account_party_link",
    "transaction": "bq://PROJECT_ID.my_bq_input_dataset.transaction",
    "risk_case_event": "bq://PROJECT_ID.my_bq_input_dataset.risk_case_event",
    "party_supplementary_data": "bq://PROJECT_ID.my_bq_input_dataset.party_supplementary_data"
  },
  "dateRange": {
    "startTime": "2020-01-01T00:00:0.00Z",
    "endTime": "2023-01-01T00:00:0.00Z"
  },
  "timeZone": {
    "id": "UTC"
  }
}
EOF

然后，执行以下命令以发送 REST 请求：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets?dataset_id=my-dataset"

PowerShell

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

@'
{
  "tableSpecs": {
    "party": "bq://PROJECT_ID.my_bq_input_dataset.party",
    "account_party_link": "bq://PROJECT_ID.my_bq_input_dataset.account_party_link",
    "transaction": "bq://PROJECT_ID.my_bq_input_dataset.transaction",
    "risk_case_event": "bq://PROJECT_ID.my_bq_input_dataset.risk_case_event",
    "party_supplementary_data": "bq://PROJECT_ID.my_bq_input_dataset.party_supplementary_data"
  },
  "dateRange": {
    "startTime": "2020-01-01T00:00:0.00Z",
    "endTime": "2023-01-01T00:00:0.00Z"
  },
  "timeZone": {
    "id": "UTC"
  }
}
'@  | Out-File -FilePath request.json -Encoding utf8

然后，执行以下命令以发送 REST 请求：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets?dataset_id=my-dataset" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.OperationMetadata",
    "createTime": CREATE_TIME,
    "target": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets/my-dataset",
    "verb": "create",
    "requestedCancellation": false,
    "apiVersion": "v1"
  },
  "done": false
}

您可以使用新的操作 ID 检查操作结果。（您可以对本指南中使用的其余 API 请求执行此操作。）

创建引擎配置

创建 AML AI 引擎配置，以根据给定的引擎版本和提供的数据自动调整超参数。引擎版本会定期发布，并对应于不同的模型逻辑（例如，面向零售业务线与面向商业业务线）。

如需创建引擎配置，请使用 projects.locations.instances.engineConfigs.create 方法。

此阶段涉及超参数调优，可能需要一些时间来处理。 如果您的数据没有发生重大变化，则可以使用此步骤创建和测试许多模型。

请求 JSON 正文：

{
  "engineVersion": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/engineVersions/aml-commercial.default.v004.008.202411-001",
  "tuning": {
    "primaryDataset": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets/my-dataset",
    "endTime": "2021-07-01T00:00:00Z"
  },
  "performanceTarget": {
    "partyInvestigationsPerPeriodHint": "30"
  }
}

如需发送请求，请选择以下方式之一：

curl

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

cat > request.json << 'EOF'
{
  "engineVersion": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/engineVersions/aml-commercial.default.v004.008.202411-001",
  "tuning": {
    "primaryDataset": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets/my-dataset",
    "endTime": "2021-07-01T00:00:00Z"
  },
  "performanceTarget": {
    "partyInvestigationsPerPeriodHint": "30"
  }
}
EOF

然后，执行以下命令以发送 REST 请求：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/engineConfigs?engine_config_id=my-engine-config"

PowerShell

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

@'
{
  "engineVersion": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/engineVersions/aml-commercial.default.v004.008.202411-001",
  "tuning": {
    "primaryDataset": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets/my-dataset",
    "endTime": "2021-07-01T00:00:00Z"
  },
  "performanceTarget": {
    "partyInvestigationsPerPeriodHint": "30"
  }
}
'@  | Out-File -FilePath request.json -Encoding utf8

然后，执行以下命令以发送 REST 请求：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/engineConfigs?engine_config_id=my-engine-config" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.OperationMetadata",
    "createTime": CREATE_TIME,
    "target": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/engineConfigs/my-engine-config",
    "verb": "create",
    "requestedCancellation": false,
    "apiVersion": "v1"
  },
  "done": false
}

创建模型

在此步骤中，您将使用截至 2021-07-01 的 12 个月的数据训练 AML AI 模型。

如需创建模型，请使用 projects.locations.instances.models.create 方法。

请求 JSON 正文：

{
    "engineConfig": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/engineConfigs/my-engine-config",
    "primaryDataset": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets/my-dataset",
    "endTime": "2021-07-01T00:00:00Z"
}

如需发送请求，请选择以下方式之一：

curl

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

cat > request.json << 'EOF'
{
    "engineConfig": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/engineConfigs/my-engine-config",
    "primaryDataset": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets/my-dataset",
    "endTime": "2021-07-01T00:00:00Z"
}
EOF

然后，执行以下命令以发送 REST 请求：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/models?model_id=my-model"

PowerShell

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

@'
{
    "engineConfig": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/engineConfigs/my-engine-config",
    "primaryDataset": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets/my-dataset",
    "endTime": "2021-07-01T00:00:00Z"
}
'@  | Out-File -FilePath request.json -Encoding utf8

然后，执行以下命令以发送 REST 请求：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/models?model_id=my-model" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.OperationMetadata",
    "createTime": CREATE_TIME,
    "target": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/models/my-model",
    "verb": "create",
    "requestedCancellation": false,
    "apiVersion": "v1"
  },
  "done": false
}

创建回测结果

回测预测功能会使用训练好的模型来分析现有的历史数据。基于截至 2023 年 1 月前 12 个月的数据（未用于训练）创建回测结果。这些月份用于确定，如果我们在 2022 年 1 月至 12 月期间在生产环境中使用了截至 2021 年 7 月训练的模型，可能需要处理多少支持请求。

如需创建回测结果，请使用 projects.locations.instances.backtestResults.create 方法。

请求 JSON 正文：

{
    "model": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/models/my-model",
    "dataset": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets/my-dataset",
    "endTime": "2023-01-01T00:00:00Z",
    "backtestPeriods": 12,
    "performanceTarget": {
      "partyInvestigationsPerPeriodHint": "150"
    }
}

如需发送请求，请选择以下方式之一：

curl

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

cat > request.json << 'EOF'
{
    "model": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/models/my-model",
    "dataset": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets/my-dataset",
    "endTime": "2023-01-01T00:00:00Z",
    "backtestPeriods": 12,
    "performanceTarget": {
      "partyInvestigationsPerPeriodHint": "150"
    }
}
EOF

然后，执行以下命令以发送 REST 请求：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/backtestResults?backtest_result_id=my-backtest-results"

PowerShell

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

@'
{
    "model": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/models/my-model",
    "dataset": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets/my-dataset",
    "endTime": "2023-01-01T00:00:00Z",
    "backtestPeriods": 12,
    "performanceTarget": {
      "partyInvestigationsPerPeriodHint": "150"
    }
}
'@  | Out-File -FilePath request.json -Encoding utf8

然后，执行以下命令以发送 REST 请求：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/backtestResults?backtest_result_id=my-backtest-results" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.OperationMetadata",
    "createTime": CREATE_TIME,
    "target": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/backtestResults/my-backtest-results",
    "verb": "create",
    "requestedCancellation": false,
    "apiVersion": "v1"
  },
  "done": false
}

导出回测结果元数据

回测运行完毕后，您需要将其结果导出到 BigQuery 才能查看。如需从回测结果中导出元数据，请使用 projects.locations.instances.backtestResults.exportMetadata 方法。

请求 JSON 正文：

{
  "structuredMetadataDestination": {
    "tableUri": "bq://PROJECT_ID.my_bq_output_dataset.my_backtest_results_metadata",
    "writeDisposition": "WRITE_TRUNCATE"
  }
}

如需发送请求，请选择以下方式之一：

curl

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

cat > request.json << 'EOF'
{
  "structuredMetadataDestination": {
    "tableUri": "bq://PROJECT_ID.my_bq_output_dataset.my_backtest_results_metadata",
    "writeDisposition": "WRITE_TRUNCATE"
  }
}
EOF

然后，执行以下命令以发送 REST 请求：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/backtestResults/my-backtest-results:exportMetadata"

PowerShell

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

@'
{
  "structuredMetadataDestination": {
    "tableUri": "bq://PROJECT_ID.my_bq_output_dataset.my_backtest_results_metadata",
    "writeDisposition": "WRITE_TRUNCATE"
  }
}
'@  | Out-File -FilePath request.json -Encoding utf8

然后，执行以下命令以发送 REST 请求：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/backtestResults/my-backtest-results:exportMetadata" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.OperationMetadata",
    "createTime": CREATE_TIME,
    "target": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/backtestResults/my-backtest-results",
    "verb": "exportMetadata",
    "requestedCancellation": false,
    "apiVersion": "v1"
  },
  "done": false
}

操作完成后，请执行以下操作：

  1. 在 Google Cloud 控制台中打开 BigQuery。

    前往 Google Cloud 控制台

  2. 在探索器窗格中，找到并展开您的项目。

  3. 展开 my_bq_output_dataset，然后点击 my_backtest_results_metadata。

  4. 在菜单栏中，点击预览。

  5. 在名称列中，找到包含 ObservedRecallValues 的行。

    BigQuery 中的观测召回率值。

  6. 假设您每月可处理 120 起调查。找到具有 "partyInvestigationsPerPeriod": "120" 的召回值对象。对于以下示例值，如果您将调查范围限定为风险得分高于 0.53 的当事方，那么您预计每月需要调查 120 个新当事方。在回测期（2022 年），您将发现之前系统发现的 86% 的案例（以及当前流程未发现的其他案例）。

    {
  "recallValues": [
    ...
    {
      "partyInvestigationsPerPeriod": "105",
      "recallValue": 0.8142077,
      "scoreThreshold": 0.6071321
    },
    {
      "partyInvestigationsPerPeriod": "120",
      "recallValue": 0.863388,
      "scoreThreshold": 0.5339603
    },
    {
      "partyInvestigationsPerPeriod": "135",
      "recallValue": 0.89071035,
      "scoreThreshold": 0.4739899
    },
    ...
  ]
}

如需详细了解回测结果中的其他字段，请参阅相关文档。

通过更改 partyInvestigationsPerPeriodHint 字段，您可以修改回测生成的研究数量。如需获取用于调查的分数，请注册当事方并针对这些当事方生成预测。

导入已注册的当事方

在创建预测结果之前，您需要导入已注册的当事方（即数据集中的客户）。

如需导入已注册的当事方，请使用 projects.locations.instances.importRegisteredParties 方法。

请求 JSON 正文：

{
  "partyTables": [
     "bq://PROJECT_ID.my_bq_input_dataset.party_registration"
  ],
  "mode": "REPLACE",
  "lineOfBusiness": "COMMERCIAL"
}

如需发送请求，请选择以下方式之一：

curl

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

cat > request.json << 'EOF'
{
  "partyTables": [
     "bq://PROJECT_ID.my_bq_input_dataset.party_registration"
  ],
  "mode": "REPLACE",
  "lineOfBusiness": "COMMERCIAL"
}
EOF

然后，执行以下命令以发送 REST 请求：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance:importRegisteredParties"

PowerShell

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

@'
{
  "partyTables": [
     "bq://PROJECT_ID.my_bq_input_dataset.party_registration"
  ],
  "mode": "REPLACE",
  "lineOfBusiness": "COMMERCIAL"
}
'@  | Out-File -FilePath request.json -Encoding utf8

然后，执行以下命令以发送 REST 请求：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance:importRegisteredParties" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.OperationMetadata",
    "createTime": CREATE_TIME,
    "target": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance",
    "verb": "importRegisteredParties",
    "requestedCancellation": false,
    "apiVersion": "v1"
  },
  "done": false
}

持续检查该操作的结果，直到操作完成。完成后，您应该会在 JSON 输出中看到 10,000 个参与方已注册。

创建预测结果

针对数据集中的最后 12 个月创建预测结果；这些月份的数据在训练期间未使用。创建预测结果会为每个预测周期内每个月中的每个方创建得分。

如需创建预测结果，请使用 projects.locations.instances.predictionResults.create 方法。

请求 JSON 正文：

{
    "model": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/models/my-model",
    "dataset": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets/my-dataset",
    "endTime": "2023-01-01T00:00:00Z",
    "predictionPeriods": "12",
    "outputs": {
      "predictionDestination": {
        "tableUri": "bq://PROJECT_ID.my_bq_output_dataset.my_prediction_results",
        "writeDisposition": "WRITE_TRUNCATE"
      },
      "explainabilityDestination": {
        "tableUri": "bq://PROJECT_ID.my_bq_output_dataset.my_prediction_results_explainability",
        "writeDisposition": "WRITE_TRUNCATE"
      }
    }
}

如需发送请求，请选择以下方式之一：

curl

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

cat > request.json << 'EOF'
{
    "model": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/models/my-model",
    "dataset": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets/my-dataset",
    "endTime": "2023-01-01T00:00:00Z",
    "predictionPeriods": "12",
    "outputs": {
      "predictionDestination": {
        "tableUri": "bq://PROJECT_ID.my_bq_output_dataset.my_prediction_results",
        "writeDisposition": "WRITE_TRUNCATE"
      },
      "explainabilityDestination": {
        "tableUri": "bq://PROJECT_ID.my_bq_output_dataset.my_prediction_results_explainability",
        "writeDisposition": "WRITE_TRUNCATE"
      }
    }
}
EOF

然后，执行以下命令以发送 REST 请求：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/predictionResults?prediction_result_id=my-prediction-results"

PowerShell

将请求正文保存在名为 request.json 的文件中。在终端中运行以下命令，在当前目录中创建或覆盖此文件：

@'
{
    "model": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/models/my-model",
    "dataset": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets/my-dataset",
    "endTime": "2023-01-01T00:00:00Z",
    "predictionPeriods": "12",
    "outputs": {
      "predictionDestination": {
        "tableUri": "bq://PROJECT_ID.my_bq_output_dataset.my_prediction_results",
        "writeDisposition": "WRITE_TRUNCATE"
      },
      "explainabilityDestination": {
        "tableUri": "bq://PROJECT_ID.my_bq_output_dataset.my_prediction_results_explainability",
        "writeDisposition": "WRITE_TRUNCATE"
      }
    }
}
'@  | Out-File -FilePath request.json -Encoding utf8

然后，执行以下命令以发送 REST 请求：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/predictionResults?prediction_result_id=my-prediction-results" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.OperationMetadata",
    "createTime": CREATE_TIME,
    "target": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/predictionResults/my-prediction-results",
    "verb": "create",
    "requestedCancellation": false,
    "apiVersion": "v1"
  },
  "done": false
}

在 Google Cloud 控制台中分析单个结构化案例

  1. 在 Google Cloud 控制台中打开 BigQuery。

    前往 Google Cloud 控制台

  2. 在“详细信息”窗格中，点击无标题查询标签页以查看编辑器。

  3. 将以下 SQL 语句复制到编辑器中，然后点击运行。

    SELECT *
FROM `PROJECT_ID.my_bq_input_dataset.transaction`
WHERE account_id = '1E60OAUNKP84WDKB' AND DATE_TRUNC(book_time, MONTH) = "2022-08-01"
ORDER by book_time

    此语句会检查 2022 年 8 月的账号 ID 1E60OAUNKP84WDKB。此账号与当事方 ID EGS4NJD38JZ8NTL8 相关联。您可以使用 AccountPartyLink 表查找给定账号 ID 的当事方 ID。

    交易数据显示，在存入大笔现金后不久，针对单个账号频繁进行小额交易，这看起来很可疑。这些交易可能表明存在化整为零（即，将大额资金交易拆分为小额交易）或结构化交易。

    单个当事方的可疑交易数据。

  4. 将以下 SQL 语句复制到编辑器中，然后点击运行。

    SELECT *
FROM `PROJECT_ID.my_bq_input_dataset.risk_case_event`
WHERE party_id = 'EGS4NJD38JZ8NTL8'

    此语句表明存在导致此方退出的风险情况。风险问题是在可疑活动发生两个月后开始的。

    单个当事方的风险案例事件。

  5. 将以下 SQL 语句复制到编辑器中，然后点击运行。

    SELECT *
FROM `PROJECT_ID.my_bq_output_dataset.my_prediction_results`
WHERE party_id = 'EGS4NJD38JZ8NTL8'
ORDER BY risk_period_end_time

    通过检查预测结果，您可以看到，在可疑活动发生后的几个月内，当事方的风险得分从接近于零（请注意指数值）跃升至较高的值。您的结果可能与显示的结果有所不同。

    单个当事方的风险得分增加。

    风险评分不是概率。风险评分应始终相对于其他风险评分进行评估。例如，在其他风险得分较低的情况下，看似较小的值也可以被视为正值。

  6. 将以下 SQL 语句复制到编辑器中，然后点击运行。

    SELECT *
FROM `PROJECT_ID.my_bq_output_dataset.my_prediction_results_explainability`
WHERE party_id = 'EGS4NJD38JZ8NTL8'
AND risk_period_end_time = '2022-10-01'

    通过检查可解释性结果，您可以看到正确的特征系列得分最高。

    预测的可解释性结果。

清理

为避免因本页面中使用的资源导致您的 Google Cloud 账号产生费用，请删除包含这些资源的 Google Cloud 项目。

删除预测结果

如需删除预测结果，请使用 projects.locations.instances.predictionResults.delete 方法。

如需发送请求，请选择以下方式之一：

curl

执行以下命令：

curl -X DELETE \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/predictionResults/my-prediction-results"

PowerShell

执行以下命令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method DELETE `
    -Headers $headers `
    -Uri "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/predictionResults/my-prediction-results" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.OperationMetadata",
    "createTime": CREATE_TIME,
    "target": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/predictionResults/my-prediction-results",
    "verb": "delete",
    "requestedCancellation": false,
    "apiVersion": "v1"
  },
  "done": false
}

删除回测结果

如需删除回测结果，请使用 projects.locations.instances.backtestResults.delete 方法。

如需发送请求，请选择以下方式之一：

curl

执行以下命令：

curl -X DELETE \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/backtestResults/my-backtest-results"

PowerShell

执行以下命令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method DELETE `
    -Headers $headers `
    -Uri "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/backtestResults/my-backtest-results" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.OperationMetadata",
    "createTime": CREATE_TIME,
    "target": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/backtestResults/my-backtest-results",
    "verb": "delete",
    "requestedCancellation": false,
    "apiVersion": "v1"
  },
  "done": false
}

删除模型

如需删除模型，请使用 projects.locations.instances.models.delete 方法。

如需发送请求，请选择以下方式之一：

curl

执行以下命令：

curl -X DELETE \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/models/my-model"

PowerShell

执行以下命令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method DELETE `
    -Headers $headers `
    -Uri "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/models/my-model" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.OperationMetadata",
    "createTime": CREATE_TIME,
    "target": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/models/my-model",
    "verb": "delete",
    "requestedCancellation": false,
    "apiVersion": "v1"
  },
  "done": false
}

删除引擎配置

如需删除引擎配置，请使用 projects.locations.instances.engineConfigs.delete 方法。

如需发送请求，请选择以下方式之一：

curl

执行以下命令：

curl -X DELETE \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/engineConfigs/my-engine-config"

PowerShell

执行以下命令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method DELETE `
    -Headers $headers `
    -Uri "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/engineConfigs/my-engine-config" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.OperationMetadata",
    "createTime": CREATE_TIME,
    "target": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/engineConfigs/my-engine-config",
    "verb": "delete",
    "requestedCancellation": false,
    "apiVersion": "v1"
  },
  "done": false
}

删除数据集

如需删除数据集，请使用 projects.locations.instances.datasets.delete 方法。

如需发送请求，请选择以下方式之一：

curl

执行以下命令：

curl -X DELETE \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets/my-dataset"

PowerShell

执行以下命令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method DELETE `
    -Headers $headers `
    -Uri "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets/my-dataset" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.OperationMetadata",
    "createTime": CREATE_TIME,
    "target": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance/datasets/my-dataset",
    "verb": "delete",
    "requestedCancellation": false,
    "apiVersion": "v1"
  },
  "done": false
}

删除实例

如需删除实例，请使用 projects.locations.instances.delete 方法。

如需发送请求，请选择以下方式之一：

curl

执行以下命令：

curl -X DELETE \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance"

PowerShell

执行以下命令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method DELETE `
    -Headers $headers `
    -Uri "https://financialservices.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/instances/my-instance" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应：

{
  "name": "projects/PROJECT_ID/locations/LOCATION/operations/OPERATION_ID",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.OperationMetadata",
    "createTime": CREATE_TIME,
    "target": "projects/PROJECT_ID/locations/LOCATION/instances/my-instance",
    "verb": "delete",
    "requestedCancellation": false,
    "apiVersion": "v1"
  },
  "done": false
}

删除 BigQuery 数据集

bq rm -r -f -d PROJECT_ID:my_bq_input_dataset

bq rm -r -f -d PROJECT_ID:my_bq_output_dataset

删除转移作业配置

  1. 列出项目中的转移作业。

    Bash

    bq ls --transfer_config \
  --transfer_location=LOCATION \
  --project_id=PROJECT_ID  \
  --filter="dataSourceIds:cross_region_copy"

    PowerShell

    bq ls --transfer_config `
  --transfer_location=LOCATION `
  --project_id=PROJECT_ID `
  --filter="dataSourceIds:cross_region_copy"

  2. 系统应会返回类似如下所示的输出。

    name                                                                                       displayName                    dataSourceId       state
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
projects/PROJECT_NUMBER/locations/LOCATION/transferConfigs/TRANSFER_CONFIG_ID    Copy the AML sample dataset.   cross_region_copy   SUCCEEDED

    复制整个名称，从 projects/ 开始，到 TRANSFER_CONFIG_ID 结束。

  3. 删除转移配置。

    Bash

    bq rm --transfer_config TRANSFER_CONFIG_NAME

    PowerShell

    bq rm --transfer_config TRANSFER_CONFIG_NAME

后续步骤