Amazon Personalize 终端节点和配额 - Amazon Personalize
AWS 文档中描述的 AWS 服务或功能可能因区域而异。要查看适用于中国区域的差异,请参阅中国的 AWS 服务入门

本文属于机器翻译版本。若本译文内容与英语原文存在差异,则一律以英文原文为准。

Amazon Personalize 终端节点和配额

以下几节包含有关 Amazon Personalize 指南、配额和终端节点的信息。对于可调配额,您可以使用Service Quuta 控制台。有关更多信息,请参阅 请求增加配额

Amazon Personalize 终端节点和地区

有关亚马逊按地区个性化终端节点的列表,请参阅Amazon区域和终端节点中的Amazon Web Services 一般参考

Compliance

有关 Amazon 个性化合规性计划的更多信息,请参阅Amazon合规性Amazon合规性计划, 和Amazon合规性计划范围内的服务

服务配额

您的Amazon账户具有以下 Amazon Personalize 配额。

资源 配额
Interactions
Minimum number of unique combined historical and event interactions (after filtering by eventType and 事件价值保持, if provided) required to train a model (create a solution version). 1000
Maximum number of interactions that are considered by a model during training. 500 million
Maximum number of distinct event types combined with total number of optional metadata columns in Interactions datasets. 10
Maximum number of metadata columns, excluding reserved fields, in Interactions datasets. 5
Maximum number of characters for categorical data values. 1000
Users
Minimum number of unique users, with at least 2 interactions each, required to train a model (create a solution version). 25
Maximum number of users that are considered by a model during training. 50 million
Maximum number of metadata fields for a Users dataset. 5
Maximum number of characters for categorical data values. 1,000 characters
Items
Maximum number of items that are considered by a model during training. 750,000
Maximum number of metadata fields for an Items dataset. 50
Maximum number of characters for categorical data values. 1,000 characters
Maximum number of characters for textual data values. 200,000 characters
Data import APIs
Maximum rate of PutEvents requests. 1000/second
Maximum number of events in a PutEvents call. 10
Maximum size of an event. 10 KB
Maximum rate of PutItITEM requests. 10/second
Maximum number of items in a PutItITEM call. 10
Maximum rate of 推出用户 requests. 10/second
Maximum number of users in a 推出用户 call. 10
Recipes
Maximum amount of data for an individual dataset (Users, Items, or Interactions) for HRNN, SIMS, Popularity-Count, and Personalized-Ranking recipes. 100 GB
Maximum amount of data for Interactions dataset for HRNN-metadata and HRNN-coldstart recipes. 100 GB
Maximum amount of combined data for Users and Items datasets for HRNN-metadata and HRNN-coldstart recipes. 5 GB
Maximum number of cold start items the HRNN-Coldstart recipe supports to train a model (create a solution version). 80,000
Minimum number of cold start items the HRNN-Coldstart recipe requires to train a model (create a solution version). 100
Filters
Maximum number of filters per account 10 filters
Maximum number of parameters for a filter expression. 5 parameters
Maximum number of parameters across all filters in a dataset group. 10 parameters
GetRecommendations / GetPersonalizedRanking requests
Maximum transaction rate (GetRecommendations and 获取个性化排名 requests). 2500/sec
Maximum number of GetRecommendations requests per second per campaign. 500/sec
Maximum number of 获取个性化排名 requests per second per campaign. 500/sec
Batch inference jobs
Maximum number of input files in a batch inference job. 1000
Maximum size of batch inference job input. 1 GB
Maximum number of records per input file in a batch inference job. 50 million

您的Amazon账户针对 Amazon 个性化设置具有以下每个区域的配额。

资源 配额
有效架构的总数。 500
有效数据集的总数。 500
有效数据集组的总数。 500
有效事件跟踪程序的总数。 500
有效解决方案的总数。 500
有效市场活动的总数。 5
挂起或正在进行的数据集导入作业的总数。 5
待处理或正在进行的批量推理作业的总数。 5
挂起或正在进行的解决方案版本的总数。 20

请求增加配额

对于可调配额,您可以使用Service Quuta 控制台。以下 Amazon Personalize 配额可调整:

  • 有效市场活动的总数

  • 每个账户的最大筛选器数量

  • 待处理或正在进行的批量推理作业总数

  • 待处理或正在进行的解决方案版本总数

  • 最大速率PutEvents请求

要请求提高配额,请使用Service Quuta 控制台,然后按照请求增加配额的 部分Service Quotas a 用户指南