Agent settings

This page describes the various settings you can apply to an agent. To access these settings:

  1. Go to the Dialogflow Console
  2. Select your agent near the top of the left sidebar menu
  3. Click the settings settings button next to the agent name

Agent edition and pricing plan

Agents default to Dialogflow Standard Edition. To change the edition or pricing plan for an agent:

  1. Scroll to the bottom of the left sidebar menu, where the agent pricing plan is shown
  2. Click the Edit or Upgrade link
  3. Select a plan

Dialogflow Pricing Plan

If you use multiple projects, the consumer project is used to determine the edition and pricing plan.

General

To access the general settings, click the General tab.

The following settings are available:

  • Description: Description of the agent.
  • Default Time Zone: Default time zone for the agent.
  • Google Project:
  • API Version: API version for the agent.
  • Beta Features: Toggle to enable beta features for the agent.
  • Log Settings:
  • Delete Agent: Completely deletes the agent and cannot be undone. If the agent is shared with other users, those users must be removed from the agent before you can delete it. See Agent management.

Languages

To access the language settings, click the Language tab.

You can set the default language and multiple additional languages. For some root languages, you can also add one or more locales. For more information, see Multilingual agents.

ML settings (machine learning)

To access the machine learning settings, click the ML Settings tab.

Dialogflow agents use machine learning algorithms to understand end-user expressions, match them to intents, and extract structured data. An agent learns from training phrases that you provide and the language models built into Dialogflow. Based on this data, it builds an algorithm for making decisions about which intent should be matched to an end-user expression. This algorithm is unique to your agent.

By default, Dialogflow updates your agent's machine learning algorithm every time you make changes to intents and entities, import or restore an agent, or train your agent.

The following settings are available:

  • Match Mode: This setting defines the algorithms that should be used for machine learning for all intents in which machine learning is enabled.
    • There are two types of algorithms used to match intents:
      • Rule-based grammar matching:
        • Pros:
          • Accurate with a small or large number of training phrase examples
          • Models are updated quickly
        • Cons:
          • Matching is slow if there are many training phrase examples
          • May produce incorrect results if the agent uses @sys.any or "Allow automated extension" frequently
      • ML matching:
        • Pros:
          • Accurate with a large number of training phrase examples
          • Matching is fast
        • Cons:
          • Inaccurate with a small number of training phrase examples
          • Models are updated slowly
          • Less accurate than grammar matching for agents with many/complex composite entities or training phrase templates
    • You can select one of two modes that use these algorithms:
      • Hybrid: This mode first attempts a rule-based grammar match. If a match is not made, it switches to ML matching. This mode is best for most cases.
      • ML Only: This mode only performs ML matching.
  • ML Classification Threshold: To filter out false positive results and still get variety in matched natural language inputs for your agent, you can tune the machine learning classification threshold. Intent matches have an intent detection confidence value in a range from 0.0 (completely uncertain) to 1.0 (completely certain). If the confidence value is less than the ML classification threshold, a fallback intent is triggered. If there are no fallback intents defined, no intent will be triggered.

  • Automatic Spell Correction:

    If this is enabled and user input has a spelling or grammar mistake, an intent will be matched as though it was written correctly. The detect intent response will contain the corrected user input. For example, if a user enters "I want an aple", it will be processed as though the user entered "I want an apple". This also applies to matches involving both system and custom entities.

    Spell correction is available for all languages supported by Dialogflow.

    Warnings and best practices:

    • Spell correction can't correct ASR (automatic speech recognition) errors, so we don't recommend enabling it for agents using ASR inputs.
    • It is possible for corrected input to match the wrong intent. You can fix this by adding commonly mismatched phrases to negative examples.
    • Spell correction increases the agent's response time slightly.
    • Spell correction should not be used with Actions on Google.
    • Spell correction is trained on general user queries. If an agent is defined using domain-specific jargon, the corrections may be undesired.
  • Automatic Training: Enable or disable automatic agent training each time the agent is modified.

  • Agent Validation: See the agent validation guide.

Export and import

To access the export and import settings, click the Export and Import tab.

This feature allows you to export/import an agent to/from a zip file for backing up agents or transferring them from one account to another. While you can edit the JSON files directly and re-import them, editing should be done using the Dialogflow Console or API. This ensures that changes are validated by the system and keeps troubleshooting to a minimum.

The following are not included in the export of an agent:

  • Inline editor files package.json and index.json
  • Integration settings for the agent.

The following options are available:

  • Export as ZIP: Exports the agent as a zip file.
  • Restore from ZIP: Overwrites the current agent with the supplied zip file.
  • Import from ZIP: Adds intents and entities to the current agent from the supplied zip file. If any existing intents or entities have the same name as those in the zip file, they will be replaced.

Environments BETA

To access the environments settings, click the Environments tab.

Versions and environments allow you to deploy multiple versions of your agent to separate, customizable environments. For more information, see Versions and Environments.

Speech

To access the speech settings, click the Speech tab.

These are the settings for speech recognition and speech synthesis. The following settings are available:

  • Improve Speech Recognition Quality
  • Text to Speech
    • Enable Automatic Text to Speech: Automatically convert default text responses to speech in all conversations. See Detect intent with audio output.
    • Voice Configuration:
      • Agent Language: Choose the default language for voice synthesis.
      • Voice: Choose a voice synthesis model.
      • Speaking Rate: Adjusts the voice speaking rate.
      • Pitch: Adjusts the voice pitch.
      • Volume Gain: Adjust the audio volume gain.
      • Audio Effects Profile: Select audio effects profiles you want applied to the synthesized voice. Speech audio is optimized for the devices associated with the selected profiles (for example, headphones, large speaker, phone call). For a list of available profiles, see Using device profiles for generated audio in Text to Speech documentation.

Share

To access the share settings, click the Share tab.

These settings are used to share agent access with other developers. See Access control for more information.

Advanced

To access the advanced settings, click the Advanced tab.

Currently, there is only one feature controlled from these settings. For more information, see Sentiment Analysis

Hai trovato utile questa pagina? Facci sapere cosa ne pensi:

Invia feedback per...

Dialogflow Documentation
Hai bisogno di assistenza? Visita la nostra pagina di assistenza.