DocsICP FilingConsole
Documentation
Home Page DataWorks User Guide Data Analysis Data exploration and visualization Data Insight

Use Data Insights for data analysis

Updated at:
Copy as MD
Product
My Favorites

Data Insight in DataWorks Data Analysis helps you explore and visualize data distributions, create data cards, and assemble them into data reports that can be shared as single-image reports. Powered by AI, it parses complex data and supports informed business decisions.

Usage notes

Accessing Data Insight

Log on to DataWorks Data Analysis, switch to the target region, and click Go to DataAnalysis. In the left-side navigation pane, click the image icon to open the Data Insight page.

Create a data insight task

Create a data insight task from the Data Insight list, a table in the SQL Query data catalog, or the results of an SQL query.

From the Data Insight list

  1. On the Data Insight page, click Create Data Insight Task. In the Create Data Insight Task dialog box, configure the table object for insight, and click Start Data Insight.

    The data source and data range default to your last used settings, with the most recent partition selected automatically.

    The configuration items include workspace, data source type, data source name, access identity mode (executor identity or default access identity of the data source), table name, column, and data range (Random 10,000 rows or full dataset). You can also select Use large model for computation.

  2. (Optional) If you have not enabled enhanced analysis, click Try Now as prompted.

From a table in SQL Query

Important

This feature is available only in the legacy version of Data Analysis and is not supported in the new version.

  1. In the left-side navigation pane, click the image icon to open the SQL Query page and add the table to the catalog on the left as shown below.

    In the top toolbar, click the catalog list icon to open the Add Catalog panel, select the Recommended Catalog tab, and click Add to Catalog next to the target table (such as My MaxCompute Tables).

  2. In the data catalog on the left, find the table you want to analyze with Data Insight.

    • On the table details page, click Data Insight.

    • Right-click the table name and select Data Insight from the context menu.

  3. In the Create Data Insight Task dialog box, the relevant parameters are automatically populated. Click Start Data Insight directly.

  4. (Optional) If you have not enabled enhanced analysis, click Try Now as prompted.

From SQL query results

New version of Data Analysis

  1. Hover over Individual Directory > My Files, and click the image > Create SQL File icon on the right.

  2. Write your SQL code, and in the top toolbar of the SQL editor, click Run and wait for the results.

  3. In the results, click the image icon, select Data Range, and then click Start Data Insight.

  4. (Optional) If you have not enabled enhanced analysis, click Try Now as prompted.

Legacy version of Data Analysis

  1. In the left-side navigation pane, click the image icon to open the SQL Query page. In My Files, click Create File, run your SQL query, and wait for the results.

  2. In the results, click the image icon, select Data Range, and then click Start Data Insight.

    In Data Range, select Only data displayed in the query results area, and select the columns you want to analyze (such as rank, cate_id, cate_name, total_sales_amount, order_count, and pt).

  3. (Optional) If you have not enabled enhanced analysis, click Try Now as prompted.

View data insight results

  1. Wait for the data insight task to complete.

    Note

    • Before the insight process is complete, you can also click Stop Analysis to terminate the entire insight task.

    • Data exploration on the full dataset may take a long time. You can check the results later on the Data Insight list page. Closing the current page does not affect the ongoing exploration.

    The Data Insight page displays a three-step workflow: Data Preparation (automatic data ingestion), Data Exploration (statistical distributions, high-frequency data proportions, min/max values, averages, etc.), and Generate Cards (save exploration conclusions and recommend data cards). These steps run sequentially. A Stop button is available in the upper-right corner.

  2. View data insight results: The system automatically generates visualization chart cards based on data type characteristics.

    After cards are generated, click Load More to display additional cards.

    image

    At the top of the results page, a collapsible Hide Statistics & Filter panel shows unique value counts and data distributions for each column in card format (for example, pv accounts for 98% and buy accounts for 2% in the behavior_type column). Use the pagination arrows (< and >) on the right to browse more statistical cards. The table below displays the raw data.

  3. If the Data Range is not set to full dataset, hover over the upper-right corner of a chart and save it to Cards as needed.

FAQ

  • Q: Why does the insight result show "No more cards"?

    A: The data volume is too small to generate insight results. We recommend that you perform data insight on results with more than 500 rows.

  • Q: How do I troubleshoot a failed table-based data insight?

    A: Make sure that the data source can be successfully connected and executed. You can first run the query in SQL Query to verify.

Previous：Data exploration and visualizationNext：Spreadsheet