All Products
Search
Document Center

Preparations

Last Updated: Oct 14, 2021

Overview

The "Quick Start" document enables you to better use Artificial Intelligence Recommendation (AIRec). By reading topics in this document, you will learn the use process and can quickly find help information.

This topic describes the preparations required to deploy an AIRec instance and the main features of the AIRec console. After you complete the preparations, you must select an industry template and a scene template that suit your business requirements. You can select a method to upload data based on your data needs. This way, data quality is unaffected when you run recommendation tests and deploy online services.

1. Prepare data based on data specifications

The data specifications vary based on different industries. To prepare data, follow the instructions described in specific topics.

1. Content industry: For more information, see Content industry.

2. E-commerce industry: For more information, see E-commerce industry.

3. News industry: For more information, see News industry. If you want to test features or API operations first, upload the following test data.

Test data

AIRec provides data that can be used for tests. You can obtain the data from the following topic:

Download test data

2. Check whether the logic of event tracking on behavioral data meets specifications

Data about exposure and click operations is required for event tracking. The number of items that are exposed must be larger than the number of items that are clicked. For more information, see Use event tracking.

3. Determine a suitable method to upload data

Note: The method to upload data consists of two steps: push start data and push real-time data.

AIRec supports two data upload methods. You can select a method based on your data needs. When data changes, make sure that the changes can be synchronized to AIRec in real time.

Method

Use scenario

Implementation

1. Quickly start an instance

This method is suitable for scenarios where MaxCompute is not activated or you are not familiar with related operations.

1. If you have a large amount of event tracking data, upload all the data by using server SDKs. For more information, see the "Use server SDKs to upload all the data" section.

2. Use historical data to start an instance

This method is suitable for scenarios where MaxCompute is activated and you are familiar with related operations.

Use MaxCompute to import start data. Use server SDKs to upload real-time data in subsequent operations.

3.1 Quickly start an instance

3.1.1 Use server SDKs to upload all the data

Use server SDKs to upload all the data to quickly start an instance

Overview: Use server SDKs to upload user data, item data, and behavioral data.Use server SDKs to upload all the data to quickly start an instance

3.2 Use historical data to start an instance

Use historical data to start an instance

Overview: Upload behavioral data that was generated within the last one to two weeks, as well as user data and item data, to MaxCompute, and validate the data. Use server SDKs to synchronize the changes of user data and item data and to upload behavioral data that is generated in real time. We recommend that you use DataWorks instead of MaxCompute.Use historical data to start an instance