Dialogflow - restructured

Introduction

The dialogflow service allows using the Google Dialogflow platform within your application. Dialogflow is used to translate human speech into intents (intent recognition). In other words, not only does it (try to) convert an audio stream into readable text, it also processes this text into an intent (possibly with some additional parameters). For example, an audio stream can translate to the string "I am 15 years old", which is, in turn, converted to the intent 'answer_age' with the parameter 'age = 15'.

The service is available in multiple languages.

Docker name: `dialogflow`

Input

sensors: Microphone
- Audio input can also be provided in the form of an audio file
- the audio input sent to the Google API has to be a bytestream
- the audio length for one request can be maximum 1 minute, as per https://cloud.google.com/dialogflow/quotas#es-agent_2
actuators: None
services: stream_audio
parameters:
- audio:
  - value: the audio to be interpreted
  - type: bytestream

Service Configuration

The following steps will help you get a keyfile, project ID and select a language:

Create a Dialogflow agent by clicking the following link: https://dialogflow.cloud.google.com/
Use the ‘Create Agent' button at the left top to start your first project. Press the settings icon next to your agent's name at the left top to see the Project ID.
Follow the steps here to retrieve your private key file in JSON format. If you don’t have a service account, you can create one by pressing the “Create Service Account” button in the upper part of the screen.
- Note: the JSON file can be changed in the application at runtime using the BasicSICConnector's set_dialogflow_key(<path to keyfile>) method
Choose a language for the agent from https://cloud.google.com/dialogflow/es/docs/reference/language
- Note: the language can be changed in the application at runtime using the BasicSICConnector's set_dialogflow_voice(<voice ID>) method

Output

sensors: none
actuators: none

The output consists of a collection of information of the type dict:

{'intent': '[YOUR_INTENT]', 
'parameters': 
    {'[YOUR_PARAMETER]': '[PARAMETER_RESPONSE]'}, 
'confidence': [CONFIDENCE_VALUE], 
'text': '[RESPONSE_TEXT]', 
'source': 'audio'}

'intent': str
- the intent on which the audio was recognised, corresponding to the intent set on the agent
‘parameters’: dict
- the parameters defined in the agent
- each parameter is a str key, with the its response as str value pairing
'confidence': int
- number ranging from 0 to 100 that defines how confident the API is with the intent and text detection
‘text’: str
- speech-to-text response from the API
'source': str
- for the SIC framework Dialogflow usage, the source is always ‘audio’

Initialisation

Using the service

In order to use our service for your purposes, an instance of the BasicSICConnector class has to be created. You can find the details of this class here. You may also need a class to manage speech_recognition attempts and a callback function for retrieving a recognized entity from the detection result.

In order to run this service, the following steps must be taken into consideration:

You have the relevant services and drivers running.
To pass your local IP address, Dialogflow key file path, and Dialogflow agent ID, when creating an instance of BasicSIC connector.
A partial function is set up for retrieving a recognized entity from the detection result.

Example

The following file, , is available for the purpose of demonstration. Two questions are dealt with in this example. The first is an entity question where the point of interest is the name of the user. The second is a yes, no, or don’t know question.

Setting up the agent

In order to deal with the first question, an intent needs to be set up. An intent is a value recognised from an end-user. In our example, the name of the person. The following steps will set an intent of your Dialogflow agent:

Navigate to the agent’s page to set the intent, training phrases and parameters.
Create an agent intent.
- It is recommended that the name suggests the kind of answer you are looking for in the audio. In our example, the name of the user (‘answer_name’).
- the intent defined in the agent should correspond to the intent used in the code
Create a context.
- the number next to the context corresponds to the number of responses expected from the user in that context. In our example, that number is 0
Create training phrases for the intent
- the training phrases should be input examples that contain the intent. In our example, 'my name is name`
- Dialogflow learns from these phrases and matches future user inputs based on them
Create parameters for the intent
- select words from the training phrases as parameters by double-clicking on them, then match them with their corresponding entity. They automatically appear in the ‘Action and parameters’ section. In our example, we are only interested in the ‘name’ of the user

Our complete intent example thus looks like this (note: using sys.given-name is usually preferred):

Figure 1

Events

onAudioIntent
- a new intent is detected
IntentDetectionDone
- a new intent has finished being detected
onAudioLanguage
- the audio language has been changed
LoadAudioDone
- if an audio file is used, the event is raised when the file has finished being loaded

Known Issues

There is a rare bug where sometimes Dialogflow will suddenly only respond with ‘UNAUTHENTICATED’ errors. Restarting Docker and/or your entire machine seems to be the only way to resolve this.