是否可以将来自Unity中请求的另一个API的信息添加/发送到Watson Conversation Service并将该数据添加到某个对话节点的答案?
例如:我已经连接了与Unity连接的Watson Conversation,语音到文本和文本到语音转换服务。同样在Unity中,我已经对openweathermap.org进行了API调用。当前设置的连接是当用户说:柏林的天气是什么时候?机器人识别意图#QuestionWeather和实体@ city:柏林。它会触及关于天气的对话节点,机器人会响应:柏林当前的温度是......通过OpenWeatherMap API调用,我得到了温度,可以显示Unity中的温度。
但我真正想做的是将温度变量发送到Watson会话并将该信息添加到输出文本中,这样用户也可以听到温度,而不是从屏幕上读取它。
我正在考虑制作一个$ context变量来发送api温度信息,这可能吗?或者我正在尝试用C#中的Watson Conversation和Unity来实现这一目标?
这是我的Watson服务脚本:
using System.Collections;
using System.Collections.Generic;
using UnityEngine;
using IBM.Watson.DeveloperCloud.Services.TextToSpeech.v1;
using IBM.Watson.DeveloperCloud.Services.Conversation.v1;
//using IBM.Watson.DeveloperCloud.Services.Assistant.v1;
using IBM.Watson.DeveloperCloud.Services.ToneAnalyzer.v3;
using IBM.Watson.DeveloperCloud.Services.SpeechToText.v1;
using IBM.Watson.DeveloperCloud.Logging;
using IBM.Watson.DeveloperCloud.Utilities;
using IBM.Watson.DeveloperCloud.Connection;
using IBM.Watson.DeveloperCloud.DataTypes;
using MiniJSON;
using UnityEngine.UI;
using FullSerializer;
public class WatsonAgent : MonoBehaviour {
public string literalEntityCity;
public Text DestinationField;
public Text DepartureField;
public Text DepartureTime;
public Text StayingPeriod;
public Text AdultsField;
public Text KidsField;
public Text RoomsField;
public Text TransportationField;
public string destinationCity;
public string departureCity;
[SerializeField]
private fsSerializer _serializer = new fsSerializer();
[System.Serializable]
public class CredentialInformation
{
public string username, password, url;
}
[System.Serializable]
public class Services
{
public CredentialInformation
textToSpeech,
languageTranslator,
personality_insights,
conversation,
speechToText,
toneAnalyzer;
}
[Header("Credentials")]
[Space]
public Services
serviceCredentials;
[Space]
[Header("Agent voice settings")]
[Space]
public AudioSource
voiceSource;
public VoiceType
voiceType;
[Space]
[Header("Conversation settings")]
[Space]
public string
workspaceId;
[Space]
[Header("Feedback fields")]
[Space]
public Text
speechToTextField;
public Text
conversationInputField;
public Text
conversationOutputField;
[System.Serializable]
public class Emotion
{
public string
emotionId;
public float
power;
}
[Space]
[Header("Emotions (read only)")]
[Space]
public List<Emotion>
emotions = new List<Emotion>();
public enum SocialState
{
idle, listening, thinking, talking
}
[Space]
[Header("Agent social behaviour (read only)")]
[Space]
public SocialState
characterState;
// services
SpeechToText
speechToText;
private int
recordingRoutine = 0,
recordingBufferSize = 1,
recordingHZ = 22050;
private string
microphoneID = null;
private AudioClip
recording = null;
TextToSpeech
textToSpeech;
Conversation
conversation;
private Dictionary<string, object>
conversationContext = null;
ToneAnalyzer
toneAnalyzer;
private void Start()
{
PrepareCredentials();
Initialize();
}
void PrepareCredentials()
{
speechToText = new SpeechToText(GetCredentials(serviceCredentials.speechToText));
textToSpeech = new TextToSpeech(GetCredentials(serviceCredentials.textToSpeech));
conversation = new Conversation(GetCredentials(serviceCredentials.conversation));
toneAnalyzer = new ToneAnalyzer(GetCredentials(serviceCredentials.toneAnalyzer));
}
Credentials GetCredentials (CredentialInformation credentialInformation)
{
return new Credentials(credentialInformation.username, credentialInformation.password, credentialInformation.url);
}
void Initialize ()
{
conversation.VersionDate = "2017-05-26";
toneAnalyzer.VersionDate = "2017-05-26";
Active = true;
StartRecording();
}
// speech to text
public bool Active
{
get { return speechToText.IsListening; }
set
{
if (value && !speechToText.IsListening)
{
speechToText.DetectSilence = true;
speechToText.EnableWordConfidence = true;
speechToText.EnableTimestamps = true;
speechToText.SilenceThreshold = 0.01f;
speechToText.MaxAlternatives = 0;
speechToText.EnableInterimResults = true;
speechToText.OnError = OnSpeechError;
speechToText.InactivityTimeout = -1;
speechToText.ProfanityFilter = false;
speechToText.SmartFormatting = true;
speechToText.SpeakerLabels = false;
speechToText.WordAlternativesThreshold = null;
speechToText.StartListening(OnSpeechRecognize);
}
else if (!value && speechToText.IsListening)
{
speechToText.StopListening();
}
}
}
private void StartRecording()
{
if (recordingRoutine == 0)
{
UnityObjectUtil.StartDestroyQueue();
recordingRoutine = Runnable.Run(RecordingHandler());
}
}
private void StopRecording()
{
if (recordingRoutine != 0)
{
Microphone.End(microphoneID);
Runnable.Stop(recordingRoutine);
recordingRoutine = 0;
}
}
private void OnSpeechError(string error)
{
Active = false;
Log.Debug("ExampleStreaming.OnError()", "Error! {0}", error);
}
private IEnumerator RecordingHandler()
{
recording = Microphone.Start(microphoneID, true, recordingBufferSize, recordingHZ);
yield return null; // let _recordingRoutine get set..
if (recording == null)
{
StopRecording();
yield break;
}
bool bFirstBlock = true;
int midPoint = recording.samples / 2;
float[] samples = null;
while (recordingRoutine != 0 && recording != null)
{
int writePos = Microphone.GetPosition(microphoneID);
if (writePos > recording.samples || !Microphone.IsRecording(microphoneID))
{
Debug.Log("Microphone disconnected.");
StopRecording();
yield break;
}
if ((bFirstBlock && writePos >= midPoint) || (!bFirstBlock && writePos < midPoint))
{
// front block is recorded, make a RecordClip and pass it onto our callback.
samples = new float[midPoint];
recording.GetData(samples, bFirstBlock ? 0 : midPoint);
AudioData record = new AudioData();
record.MaxLevel = Mathf.Max(Mathf.Abs(Mathf.Min(samples)), Mathf.Max(samples));
record.Clip = AudioClip.Create("Recording", midPoint, recording.channels, recordingHZ, false);
record.Clip.SetData(samples, 0);
speechToText.OnListen(record);
bFirstBlock = !bFirstBlock;
}
else
{
// calculate the number of samples remaining until we ready for a block of audio,
// and wait that amount of time it will take to record.
int remaining = bFirstBlock ? (midPoint - writePos) : (recording.samples - writePos);
float timeRemaining = (float)remaining / (float) recordingHZ;
yield return new WaitForSeconds(timeRemaining);
}
}
yield break;
}
private void OnSpeechRecognize(SpeechRecognitionEvent result)
{
if (result != null && result.results.Length > 0)
{
foreach (var res in result.results)
{
foreach (var alt in res.alternatives)
{
string text = string.Format("{0} ({1}, {2:0.00})\n", alt.transcript, res.final ? "Final" : "Interim", alt.confidence);
// Log.Debug("ExampleStreaming.OnRecognize()", text);
if (speechToTextField != null)
{
speechToTextField.text = text;
}
if (res.final)
{
if (characterState == SocialState.listening)
{
Debug.Log("WATSON | Speech to text recorded: \n" + alt.transcript);
StartCoroutine(Message(alt.transcript));
}
} else
{
if(characterState == SocialState.idle)
{
characterState = SocialState.listening;
}
}
}
}
}
}
// text to speech
private IEnumerator Synthesize(string text)
{
Debug.Log("WATSON CALL | Synthesize input: \n" + text);
textToSpeech.Voice = voiceType;
bool doSynthesize = textToSpeech.ToSpeech(HandleSynthesizeCallback, OnFail, text, true);
if(doSynthesize)
{
StartCoroutine(Analyze(text));
characterState = SocialState.talking;
}
yield return null;
}
void HandleSynthesizeCallback(AudioClip clip, Dictionary<string, object> customData = null)
{
if (Application.isPlaying && clip != null)
{
Invoke("ResumeIdle", clip.length);
voiceSource.clip = clip;
voiceSource.Play();
}
}
void ResumeIdle()
{
characterState = SocialState.idle;
}
// conversation
private IEnumerator Message (string text)
{
Debug.Log("WATSON | Conversation input: \n" + text);
MessageRequest messageRequest = new MessageRequest()
{
input = new Dictionary<string, object>()
{
{ "text", text }
},
context = conversationContext
};
bool doMessage = conversation.Message(HandleMessageCallback, OnFail, workspaceId, messageRequest);
if(doMessage)
{
characterState = SocialState.thinking;
if (conversationInputField != null)
{
conversationInputField.text = text;
}
}
yield return null;
}
void HandleMessageCallback (object resp, Dictionary<string, object> customData)
{
object _tempContext = null;
(resp as Dictionary<string, object>).TryGetValue("context", out _tempContext);
if (_tempContext != null)
conversationContext = _tempContext as Dictionary<string, object>;
string contextList = conversationContext.ToString();
Dictionary<string, object> dict = Json.Deserialize(customData["json"].ToString()) as Dictionary<string, object>;
// load output --> text;answer from Json node
Dictionary <string, object> output = dict["output"] as Dictionary<string, object>;
var context = dict["context"] as Dictionary<string, object>;
if (context["destination_city"] != null)
{
destinationCity = context["destination_city"].ToString();
Debug.Log("Destination city: " + destinationCity);
DestinationField.text = "Destination: " + destinationCity;
}
if (context["departure_city"] != null)
{
departureCity = context["departure_city"].ToString();
DepartureField.text = "Departure: " + departureCity;
}
if (context["DateBegin"] != null && context["date"] != null)
{
string dateBegin = context["DateBegin"].ToString();
string dateEnd = context["DateEnd"].ToString();
StayingPeriod.text = "Stay: " + dateBegin + " - " + dateEnd;
}
if (context["PeriodNumber"] != null && context["PeriodDate"] != null && context["DateEnd"] != null)
{
string periodNumber = context["PeriodNumber"].ToString();
string periodDate = context["PeriodDate"].ToString();
string dateEnd = context["DateEnd"].ToString();
StayingPeriod.text = "Stay: " + periodNumber + " " + periodDate + " - " + dateEnd;
}
if (context["time"] != null)
{
string timeInfo = context["time"].ToString();
DepartureTime.text = "Time: " + timeInfo;
}
List<object> text = output["text"] as List<object>;
string answer = text[0].ToString(); //returns only the first response
Debug.Log("WATSON | Conversation output: \n" + answer);
if (conversationOutputField != null)
{
conversationOutputField.text = answer;
}
fsData fsdata = null;
fsResult r = _serializer.TrySerialize(resp.GetType(), resp, out fsdata);
if (!r.Succeeded)
{
throw new WatsonException(r.FormattedMessages);
}
//convert fsdata to MessageResponse
MessageResponse messageResponse = new MessageResponse();
object obj = messageResponse;
r = _serializer.TryDeserialize(fsdata, obj.GetType(), ref obj);
if (!r.Succeeded)
{
throw new WatsonException(r.FormattedMessages);
}
if (resp != null)
{
//Recognize intents & entities
if (messageResponse.intents.Length > 0 && messageResponse.entities.Length > 0)
{
string intent = messageResponse.intents[0].intent;
string entity = messageResponse.entities[0].entity;
string literalEntity = messageResponse.entities[0].value;
if (entity == "city")
{
literalEntityCity = literalEntity;
}
if (intent == "weather" && entity == "city")
{
literalEntityCity = literalEntity;
}
}
if (messageResponse.intents.Length > 0)
{
string intent = messageResponse.intents[0].intent;
//intent name
Debug.Log("Intent: " + intent);
}
if (messageResponse.entities.Length > 0)
{
string entity = messageResponse.entities[0].entity;
//entity name
Debug.Log("Entity: " + entity);
string literalEntity = messageResponse.entities[0].value;
//literal spoken entity
Debug.Log("Entity Literal: " + literalEntity);
if (entity == "city")
{
literalEntityCity = literalEntity;
}
}
}
StartCoroutine(Synthesize(answer));
}
// tone analyzer
private IEnumerator Analyze (string text)
{
Debug.Log("WATSON | Tone analyze input: \n" + text);
bool doAnalyze = toneAnalyzer.GetToneAnalyze(HandleAnalyzeCallback, OnFail, text);
yield return null;
}
private void HandleAnalyzeCallback(ToneAnalyzerResponse resp, Dictionary<string, object> customData)
{
Dictionary<string, object> dict = Json.Deserialize(customData["json"].ToString()) as Dictionary<string, object>;
Dictionary<string, object> document_tone = dict["document_tone"] as Dictionary<string, object>;
List<object> tone_categories = document_tone["tone_categories"] as List<object>;
string debugOutput = "";
foreach (object tone in tone_categories)
{
Dictionary<string, object> category = (Dictionary<string, object>)tone;
List<object> newTone = category["tones"] as List<object>;
foreach (object insideTone in newTone)
{
Dictionary<string, object> tonedict = (Dictionary<string, object>)insideTone;
float score = float.Parse(tonedict["score"].ToString());
string id = tonedict["tone_id"].ToString();
bool emotionAvailable = false;
foreach(Emotion emotion in emotions)
{
if(emotion.emotionId == id)
{
emotionAvailable = true;
emotion.power = score;
debugOutput += emotion.emotionId + " : " + emotion.power.ToString() + " - ";
break;
}
}
if(!emotionAvailable)
{
Emotion newEmotion = new Emotion();
newEmotion.emotionId = id;
newEmotion.power = score;
emotions.Add(newEmotion);
debugOutput += newEmotion.emotionId + " : " + newEmotion.power.ToString() + " - ";
}
}
}
Debug.Log("WATSON | Tone analyze output: \n" + debugOutput);
}
private void OnFail(RESTConnector.Error error, Dictionary<string, object> customData)
{
Log.Error("WatsonAgent.OnFail()", "Error received: {0}", error.ToString());
}
}
答案 0 :(得分:2)
我不了解unity / C#,但是与您使用的语言无关,可以通过在发送之前更改上下文对象来操纵Conversation / Assistent将拥有的信息回来,创建一个新的索引,比如&#34; context.temperature&#34;,然后在对话中,你可以使用&#34;柏林当前的温度是$ temperature&#34;。
Conversation / Assistent是无状态的,因此系统将了解您的对话框的所有内容都在上下文对象中,这就是为什么您需要将其发送回新的请求。因此,只要您需要从其他来源向流添加信息,您需要做的就是在上下文中创建一个新索引。
答案 1 :(得分:0)
我觉得我看到你在另一个论坛上发帖了...但是如果不是你,这里是制作外部标注的模式。您可以通过IBM Cloud Functions在客户端或服务器端执行此操作: https://console.bluemix.net/docs/services/conversation/dialog-actions.html