All Products
Search
Document Center

Quick Audience:AIPL Model

Last Updated:May 22, 2025

You can create an AIPL model based on the imported User Behavior table for AIPL User Analysis and Audience Filtering.

What is the AIPL model?

The AIPL model is a means of quantifying and linking brand user assets. A, I, P, L are used to describe the stage of intimacy between the consumer and the brand, where:

  • A(Awareness): brand awareness users, generally refers to users who have passive contact with the brand, such as brand advertising touch and category word search.

  • I(Interest): brand interest users, generally refers to users who actively contact with the brand, such as advertisement click, browse brand /store homepage, participate in brand interaction, browse product details page, brand word search, receive trial, subscribe /follow /join, add purchase collection.

  • P(Purchase): Brand buyers, including those who have made purchases.

  • L(Loyalty): Brand loyal users, such as those who have re-purchased or have positive comments and sharing on the brand.

Note

The stage order is A<I<P<L. If the user meets the conditions of multiple stages at the same time, it will be classified as the highest-level stage. For example, if a user satisfies P but does not satisfy L, the user is classified as P, regardless of whether A or I is satisfied.

As the data in the user behavior table is updated, the AIPL status of users in the AIPL model may change, or new users may enter the AIPL model. In this case, you can use AIPL Flow Analysis to measure the success of user operations over a period of time.

Create an AIPL model

When you create an AIPL model based on an imported user behavior table, you must distinguish four groups of users based on the behavior type, number of user behaviors, and purchase amount.

For more information about sample user behavior tables, see Quick Audience Import Data Table Requirements. For more information about how to import data from a user behavior table, see User Behavior.

Procedure

  1. Choose Workspace> User Insight > Marketing Model > AIPL Model. image

  2. Click New in the upper-right corner to go to the AIPL Model Configuration page.

  3. By default, User Behavior Data is selected as the analysis data source. Click Next. image.png

  4. Configure AIPL rules, as shown in the following figure. 4568

    Respectively for A, I, P, L four groups of people:

    1. Select a channel source from the drop-down list.

      The channel source is not a behavioral channel in the behavioral dataset. The channel source here will be used to distinguish the channel source when the AIPL model is pushed to the data bank. Some channel sources are preset in the system. You can click the 渠道icon to edit a channel source. For more information, see Edit Channel Source.

    2. Set rules based on your business requirements.

      • Set the behavior time interval, select the imported user behavior table (use the table alias set during import), and set the corresponding behavior channel and behavior type requirements.

        • You can use multiple methods to set the behavior time. For more information, see Time-based.

          Note

          If this parameter is set to a non-specific time, when the AIPL model is updated, the specified time is refreshed based on the update time and the AIPL model is calculated based on the new time. If this parameter is set to a specific time, the result remains unchanged after the update unless the behavior record itself changes.

        • You can select All or select Select All to select all search results.

      • Click + Statistical Metrics and + Behavior Attributes to set the requirements for statistical metrics and behavior attributes. You can specify a maximum of two statistical metrics and five behavioral attributes. Multiple requirements are in an intersection relationship, that is, they must be met at the same time.

      Click + AIPL Rules to add a rule. Adjacent rules support the AND, OR, and DIFFERENCE relationships. The default value is OR. You can click the corresponding text to switch between them, as shown in the following figure. 245

  5. After you configure the rules for the four groups of people, click OK. In the dialog box that appears, enter an AIPL model name and click OK.

You are redirected to the AIPL model list. You can view the newly created AIPL model in the list. For more information about how to manage AIPL models, see Manage AIPL Model.

Edit Channel Source

On the Configure AIPL Rule page, click the 渠道icon next to Channel Source. The Edit Channel Source dialog box appears, as shown in the following figure.

0

The system has set some default channel sources. You can add, edit, and delete them.

  • Click + on the right to add a channel.

  • Click an existing channel. The 编辑and 删除icons appear. You can click them to edit and delete the channel, respectively.

Manage AIPL models

AIPL models support edit, AIPL user analysis, update, push, push history, rename, delete, permission settings, and update settings.

image

  • Edit: Click Edit to edit the model.

  • User analysis and flow analysis: Analyze AIPL Users and AIPL Flow Analysi

  • for the AIPL model.

  • Update: Click Update to immediately update the model.

  • Rename: Choose image /> Rename to redefine the model name.

  • Delete: Select image /> Delete and confirm to delete the model.

    Note

    If the model generates a crowd, you cannot delete it.

  • Grant permissions to non-administrators the permissions to use or manage AIPL models. For more information, see Authorize Tags.

    Note
    • If a non-administrator is authorized, the AIPL model is displayed on the Authorized tab of the AIPL Models page.

    • By default, the administrator has the permissions to manage all AIPL models in the workspace. The administrator is displayed on the My tab of the AIPL Models page.

  • Update settings: Choose image /> Update Settings. In the Update Settings dialog box, you can turn on the Auto Update switch and set the update time. Within the specified date range, the model will be automatically updated each time the user behavior table is used to complete the scheduling task. 23

    Note

    If the update parallelism in the space has been set in the management center, the automatic update of the AIPL model that exceeds the limit needs to be queued. For more information, see Workspace System Configuration.