Quick Audience:User Behavior

A user behavior table records user actions such as browsing, purchasing, collecting, and purchasing. Based on this data, you can perform Audience Filtering and generate custom tags such as AIPL Model and Preference Tags. AIPL models can be used for AIPL User Analysis, AIPL Flow Analysis, and Audience Filtering.

Prerequisites

• Your user behavior table must be stored in the MaxCompute data source that you configured. For the required data format, see User Behavior Table Data Requirements.

• Ensure that all user ID types in your user behavior table are listed in the ID Type List of this workspace.

• If the user ID field is AES-encrypted, enter the key in the Organization System Configuration to decrypt it before pushing or using it.

Procedure

1. Choose Workspace> Configuration Management> Data Import> Table Structure Configuration.

2. In the upper-right corner, choose Create Table Configuration > User Behavior. The Create User Behavior page appears.

3. Select the computing source and data table that you want to import.

   You can select either a table or a view as the data table.

   • If you select Table, the system automatically detects whether the table contains time partitions.

     • If the table contains time partitions, select the Time Partition field and specify the partition value format. The following figure shows the supported formats.

       Then select an update method:

       • Incremental update: retains historical data and stores new data in a new partition. You must select whether to pull historical data for the first scheduling.

       • Full update: clears all historical data before each update. No partitioning is used.

     • If the table does not contain time partitions, no selection is required. Full update will be used.

   • If you select a view, manually specify whether it includes time partitions. The remaining configuration is the same as for tables.

   If your account does not have read permission on the selected table, an error message appears as shown below. Grant read permission on the data table to the Quick Audience account in the MaxCompute project. Click Authorize SQL to obtain the authorization statement. After authorization, click Update to continue.

4. Enter an alias for the data table.

   Note

   The table alias is used for the behavioral data source information on the Create AIPL Model and Crowd Filter pages.

   

5. Map each field to the corresponding behavior time, behavior channel, behavior type, statistical indicator, behavior attribute, or user ID, and set the ID type and encryption method for each ID field.

   You can also configure these settings in the field list.

6. In the field list, turn off the Import switch for fields that you do not want to import. Disabled fields cannot be used in any application, but you can enable them later when editing the table configuration.

7. Set the field alias, field type, and field classification for each field to import. Set the ID type and encryption method for each ID field.

8. Click Complete.

   If you set the Update Method to Full Update, you are prompted to select whether to pull historical data for the first scheduling when you save the configuration.

   • If you select Yes, all historical partition data will be pulled and saved when you import data for the first time.

   • If you select No, only the latest partition data is pulled when the data is imported for the first time.

After you configure the table structure, configure a scheduling task to import data. For more information, see Scheduling Task. For more information about managing table structures, see Table structure configuration management.

FAQ

The behavior object field was previously available when configuring user behavior tables. Why is it no longer present?

Answer: Starting from V4.4.0, the behavior object field was renamed to the behavior attribute field to support storing reported Event data as user behavior tables. Existing behavior attribute fields remain unchanged, and you can continue using your original table schema. Any behavior object fields in previously configured schemas are automatically converted to behavior attribute fields. The behavior attribute configuration items are added to the original behavior object configuration items during Audience Filtering, AIPL generation, and Preference Tags generation.