Data collection
    • PDF

    Data collection

    • PDF

    Article summary

    Available in Classic and VPC

    Data collection is the process through which the model thinks and examines to provide appropriate answers to the user's questions. Through collecting and reviewing data, you can edit your model's thought process.

    Data collection screen

    The data collection screen is configured as follows:

    clovastudio-scenario_main_ko.png

    ItemDescription
    ① Data collection areaArea where you set the values for data collection and run the process
    • Engine / Version: select a language model or version to use
    • Skill: selected skill set and list of skills included in the version. You can only use skills whose task status is "completed"
    • Setting > Call option: run a user query to assign a specific value for calling API
    • Setting > Response format: check response format specified for skill set
    • User Query: enter user queries to collect. You need to select a skill set to activate this field
    • [Load] button: recall data you've previously worked on
    • [Run] button: run data collection
    ② Data collection areaArea where you review and collect the created data
    • Query analysis: user query analysis to choose which skill to use
    • Skill call: model's thought process to call an appropriate API
    • Final response: response processed based on call result
    ③ Function buttons
    • [Temporary save] button: save what you've worked on
    • [Task completed] button: complete what you've worked on. Only activated when the final answer has been created

    Run data collection

    The following walks you through the model's thought and judgment process to handle user queries through data collection.

    To run data collection, follow these steps:

    1. On the NAVER Cloud Platform console, click Services > AI Services > CLOVA Studio in order.
    2. From the My Product menu, click the [Go to CLOVA Studio] button.
    3. On CLOVA Studio, click the Skill trainer menu.
    4. Click the skill set you want to collect data for.
    5. Click the Data collection menu on the left of the screen.
    6. Set required information for data collection.
      • Engine / Version: select a language model or version to use
      • Skill: list of skills included in the skill set. You can only use skills whose task status is "completed"
      • Setting > Call option: specify a value for API call for user queries. For more information on how to create a call option, see Create call option
    7. Enter queries to collect in the User query area.
    8. Click the [Run] button.
      • The data collection steps are shown in order on the right side of the screen.
      • Click the [Suspend] button to suspend a specific step. Click the [Restart] button to restart the suspended task.
    Note

    You cannot edit Engine / Version and User query after running data collection. If you need to edit the content, click the [Initialize] button to restart the task. The [Initialize] button is activated once data collection is completed.

    Review and edit data

    After running the data collection, if there is any inaccurate judgment from the model at each step, you can improve the response by manually editing the parameters to generate more accurate answers.

    To review and edit the collected data, follow these steps:

    1. Run data collection.
    2. Check the skill call results after the query analysis.
    3. Click the [Next] button at each step to proceed to the next.
      • For a new data collection, you can skip to the final response stage without clicking the [Next] button.
    4. To edit your data, click a field, edit, and click the [Apply] button
      • Data creation is restarted for the next steps.
    5. Check the final response and click the [Task completed] button.
      • To save the task for later use, click the [Temporary save] button.
      • The [Task completed] button appears after the final response is created.

    Load data

    You can load, review, and edit data you previously worked on.

    To load data, follow these steps:

    1. On the NAVER Cloud Platform console, click Services > AI Services > CLOVA Studio in order.
    2. From the My Product menu, click the [Go to CLOVA Studio] button.
    3. On CLOVA Studio, click the Skill trainer menu.
    4. Click a skill set.
    5. Click the Data collection menu on the left side of the screen.
    6. Click the [Load] button in the Run data collection area.
    7. Check the temporarily saved task list.
      • You can search based on user queries from the top right of the Load window.
      • Click the [Data] button to check the data results.
      • To delete a task, hover your pointer over the task you want to delete and click the i-clovastudio_reset.png icon.
      • The task status shows "completed" only when you click the [Complete task] button on the data task screen.
    8. To edit the previous query task from the data collection screen, click the [Open] button.
      • The data collection screen appears, and you can continue to work on the previous queries.
      • You can also load the call option applied to the task.

    Data collection steps

    Data collection consists of query analysis, skill calls and final response, in order. The following describes the tasks run in each data collection step.

    Query analysis

    This is the step to decide which skill to use by analyzing user queries. Queries are classified by the call and mapped to relevant skills. If 2 or more queries are analyzed, two skill calls are made.

    Skill calls

    This step includes skill calls and the review of the model's thoughts. Skill calls are performed as many times as the number of queries classified during the query analysis step.

    Skill calls consist of 3 steps.

    • Step 1: querying API for the skill you want to call
      • Call method: model's thought process to find an API
      • Call skill: skill's model name
      • API query details: API Spec and Description for model of the skill
    • Step 2: checking the search results of the API query
      • API search result: model's thought process to call an API. Inferring the request variables (parameters) required for the API call
      • Action: API method. Only supports requests_get and requests_post
      • Action input: URL and parameters inferred by the model. Input fields differ depending on the action
        • If requests_get, action input field: API URL/parameter
        • If requests_post, action input field: API URL/parameter (Key, Value)
          • Click the [Add field] button to create an additional blank field
          • Click the i-clovastudio_reset.png icon to delete the field
      • Call result: API call result
    • Step 3: organizing content based on the call result
      • Thought: model's thought process to organize the content of the call
      • Result: result of model creation
    Note

    In the case of requests_post, when creating a new parameter in the action input field, make sure it is not redundant with the key of an existing parameter. If there are duplicate keys, the API may not be called.

    Final response

    In this step, the final response is created and reviewed. After the creation of the final response, click the [Task completed] button to complete data collection.

    Creating call options

    By creating call options, you can fix a certain value for the header and body parameters for the API spec operation ID.

    To create a call option, follow these steps:

    1. While running data collection, click the [Call option] button of the Setting menu on the left side of the screen.
      • The call option window appears.
    2. Enter the call option in JSON type in the call value input area.
      • Create it referring to the example format at the top of the screen.
      • For more information on call value input, see Detailed call option.
    3. Once the call value input is completed, click the [Apply] button.
      • If it fails to be applied, an error message will be displayed. Re-edit the call value.
    Note
    • If you re-enter the Data collection menu after exiting it, the call options are initialized.
    • After collecting data with the call options applied, even if you click the [Initialize] button, your options are maintained.
    • If you load your previous task with the [Load] button, the call options applied to the task are loaded as well.

    Detailed call option

    It is information on the fields that can be written in the call option.
    The call options are applied in the order of operations field, baseOperation field, and then the user query.

    FieldData typeDescription
    baseOperationobjectThe call option is applied to all APIs registered within the skill set
    baseOperation.headermap<string, string>Fixed values to be added to the HTTP header of all APIs
    baseOperation.querymap<string, string>Fixed values to be added to the HTTP query parameters of all APIs
    baseOperation.requestBodymap<string, object>Fixed values to be added to the HTTP request body of all APIs
    operationslistThe call option is applied only to the specified Operation ID among the APIs registered within the skill set
    operations[].operationIdstringAssign operation ID you want to apply the call option to
    operations[].headermap<string, string>Fixed values to be added to the HTTP header of the API mapped to the assigned operation ID
    operations[].querymap<string, string>Fixed values to be added to the HTTP query parameter of the API mapped to the assigned operation ID
    operations[].requestBodymap<string, object>Fixed values to be added to the HTTP request body of the API mapped to the assigned operation ID

    Was this article helpful?

    What's Next
    Changing your password will log you out immediately. Use the new password to log back in.
    First name must have atleast 2 characters. Numbers and special characters are not allowed.
    Last name must have atleast 1 characters. Numbers and special characters are not allowed.
    Enter a valid email
    Enter a valid password
    Your profile has been successfully updated.