IA Conversazionale: Best Practice per lo Sviluppo di Chatbot
I sistemi di IA conversazionale consentono l'interazione uomo-computer tramite linguaggio naturale. In questa guida, esaminiamo le strategie di sviluppo di chatbot enterprise.
Architettura del Chatbot
Componenti Principali
1┌────────────────────────────────────────────────────┐ 2│ User Interface │ 3└───────────────────────┬────────────────────────────┘ 4 │ 5┌───────────────────────▼────────────────────────────┐ 6│ Input Processing Layer │ 7│ ┌──────────┐ ┌──────────┐ ┌────────────────┐ │ 8│ │ Speech │ │ Text │ │ Multimodal │ │ 9│ │ to Text │ │ Normalize│ │ Processing │ │ 10│ └──────────┘ └──────────┘ └────────────────┘ │ 1130: └───────────────────────┬────────────────────────────┘ 12 │ 13┌───────────────────────▼────────────────────────────┐ 14│ Dialog Manager │ 15│ ┌──────────┐ ┌──────────┐ ┌────────────────┐ │ 16│ │ Intent │ │ State │ │ Context │ │ 17│ │ Detection│ │ Manager │ │ Handler │ │ 18│ └──────────┘ └──────────┘ └────────────────┘ │ 1938: └───────────────────────┬────────────────────────────┘ 20 │ 21┌───────────────────────▼────────────────────────────┐ 22│ Response Generation │ 23│ ┌──────────┐ ┌──────────┐ ┌────────────────┐ │ 24│ │ LLM │ │ Template │ │ Action │ │ 25│ │ Response │ │ Engine │ │ Executor │ │ 26│ └──────────┘ └──────────┘ └────────────────┘ │ 2746: └────────────────────────────────────────────────────┘
Gestione del Contesto
Memoria della Conversazione
1from typing import List, Dict 2from datetime import datetime 3 4class ConversationMemory: 5 def __init__(self, max_turns: int = 10): 6 self.max_turns = max_turns 7 self.history: List[Dict] = [] 8 self.metadata: Dict = {} 9 10 def add_message(self, role: str, content: str): 11 message = { 12 "role": role, 13 "content": content, 14 "timestamp": datetime.now().isoformat() 15 } 16 self.history.append(message) 17 18 # Clean old messages 19 if len(self.history) > self.max_turns * 2: 20 self.history = self.history[-self.max_turns * 2:] 21 22 def get_context(self) -> List[Dict]: 23 return [{"role": m["role"], "content": m["content"]} 24 for m in self.history] 25 26 def summarize(self, llm_client) -> str: 27 """Summarize long conversations""" 28 if len(self.history) < 10: 29 return None 30 31 response = llm_client.chat.completions.create( 32 model="gpt-4-turbo", 33 messages=[ 34 {"role": "system", "content": "Summarize this conversation."}, 35 {"role": "user", "content": str(self.history)} 36 ] 37 ) 38 return response.choices[0].message.content
Stato di Sessione
1class SessionState: 2 def __init__(self, session_id: str): 3 self.session_id = session_id 4 self.user_info: Dict = {} 5 self.collected_data: Dict = {} 6 self.current_intent: str = None 7 self.current_step: str = None 8 self.awaiting_input: str = None 9 10 def set_slot(self, name: str, value: any): 11 self.collected_data[name] = value 12 13 def get_slot(self, name: str) -> any: 14 return self.collected_data.get(name) 15 16 def clear_slots(self): 17 self.collected_data = {} 18 19 def is_complete(self, required_slots: List[str]) -> bool: 20 return all(slot in self.collected_data for slot in required_slots) 21## Classificazione dell’Intento 22 23### Rilevamento dell’Intento basato su LLM 24 25```python 26def detect_intent(user_message: str, available_intents: List[Dict]) -> Dict: 27 intent_descriptions = "\n".join([ 28 f"- {intent['name']}: {intent['description']}" 29 for intent in available_intents 30 ]) 31 32 response = client.chat.completions.create( 33 model="gpt-4-turbo", 34 response_format={"type": "json_object"}, 35 messages=[ 36 { 37 "role": "system", 38 "content": f"""Determine the intent of the user message. 39 40Available intents: 41{intent_descriptions} 42 43Respond in JSON format: 44{{"intent": "intent_name", "confidence": 0.0-1.0, "entities": {{}}}} 45""" 46 }, 47 {"role": "user", "content": user_message} 48 ] 49 ) 50 51 return json.loads(response.choices[0].message.content)
Rilevamento Ibrido dell’Intento
1from sklearn.feature_extraction.text import TfidfVectorizer 2from sklearn.linear_model import LogisticRegression 3 4class HybridIntentClassifier: 5 def __init__(self): 6 self.ml_classifier = None 7 self.vectorizer = TfidfVectorizer() 8 9 def train_ml(self, texts: List[str], labels: List[str]): 10 X = self.vectorizer.fit_transform(texts) 11 self.ml_classifier = LogisticRegression() 12 self.ml_classifier.fit(X, labels) 13 14 def classify(self, text: str) -> Dict: 15 # ML prediction 16 X = self.vectorizer.transform([text]) 17 ml_intent = self.ml_classifier.predict(X)[0] 18 ml_confidence = max(self.ml_classifier.predict_proba(X)[0]) 19 20 # Ask LLM if confidence is low 21 if ml_confidence < 0.7: 22 llm_result = detect_intent(text, self.available_intents) 23 return llm_result 24 25 return {"intent": ml_intent, "confidence": ml_confidence}
Flusso di Dialogo
Macchina a Stati
1from enum import Enum 2 3class OrderState(Enum): 4 START = "start" 5 PRODUCT_SELECTION = "product_selection" 6 QUANTITY = "quantity" 7 ADDRESS = "address" 8 CONFIRMATION = "confirmation" 9 COMPLETE = "complete" 10 11class OrderFlow: 12 def __init__(self): 13 self.state = OrderState.START 14 self.data = {} 15 16 def process(self, user_input: str, intent: str) -> str: 17 if self.state == OrderState.START: 18 if intent == "order": 19 self.state = OrderState.PRODUCT_SELECTION 20 return "Quale prodotto desideri ordinare?" 21 22 elif self.state == OrderState.PRODUCT_SELECTION: 23 self.data["product"] = user_input 24 self.state = OrderState.QUANTITY 25 return f"Hai selezionato {user_input}. Quanti ne desideri?" 26 27 elif self.state == OrderState.QUANTITY: 28 self.data["quantity"] = int(user_input) 29 self.state = OrderState.ADDRESS 30 return "Potresti fornire il tuo indirizzo di consegna?" 31 32 elif self.state == OrderState.ADDRESS: 33 self.data["address"] = user_input 34 self.state = OrderState.CONFIRMATION 35 return f"Riepilogo dell’ordine:\n{self.data}\nConfermi?" 36 37 elif self.state == OrderState.CONFIRMATION: 38 if "yes" in user_input.lower(): 39 self.state = OrderState.COMPLETE 40 return "Ordine ricevuto. Grazie!" 41 else: 42 self.state = OrderState.START 43 return "Ordine annullato." 44## Generazione delle Risposte 45 46### Template + LLM Ibrido 47 48```python 49class ResponseGenerator: 50 def __init__(self): 51 self.templates = { 52 "greeting": [ 53 "Hello! How can I help you?", 54 "Welcome! What would you like to do today?" 55 ], 56 "farewell": [ 57 "Have a good day! See you again.", 58 "I'm here if you have any other questions. Goodbye!" 59 ] 60 } 61 62 def generate(self, intent: str, context: Dict) -> str: 63 # Template for simple intents 64 if intent in self.templates: 65 return random.choice(self.templates[intent]) 66 67 # LLM for complex intents 68 return self.llm_generate(intent, context) 69 70 def llm_generate(self, intent: str, context: Dict) -> str: 71 system_prompt = f"""You are a helpful customer service assistant. 72User intent: {intent} 73Current context: {json.dumps(context, ensure_ascii=False)} 74 75Rules: 76- Give short and concise answers 77- Be friendly but professional 78- Ask follow-up questions if necessary 79""" 80 81 response = client.chat.completions.create( 82 model="gpt-4-turbo", 83 messages=[ 84 {"role": "system", "content": system_prompt}, 85 *context.get("history", []) 86 ] 87 ) 88 89 return response.choices[0].message.content
Gestione dei Fallback
1class FallbackHandler: 2 def __init__(self): 3 self.fallback_count = 0 4 self.max_fallbacks = 3 5 6 def handle(self, user_input: str, context: Dict) -> str: 7 self.fallback_count += 1 8 9 if self.fallback_count >= self.max_fallbacks: 10 self.fallback_count = 0 11 return self.human_handoff(context) 12 13 responses = [ 14 "I didn't understand. Could you rephrase that?", 15 "I cannot help with this. You can ask a different question.", 16 "I think I misunderstood you. could you try again?" 17 ] 18 19 return responses[self.fallback_count - 1] 20 21 def human_handoff(self, context: Dict) -> str: 22 # Hand off to human agent 23 create_support_ticket(context) 24 return "I am connecting you to a customer representative. Please wait."
Analytics e Monitoraggio
1class ChatAnalytics: 2 def __init__(self): 3 self.metrics = { 4 "total_conversations": 0, 5 "successful_resolutions": 0, 6 "fallback_rate": 0, 7 "avg_turns_per_conversation": 0, 8 "intent_distribution": {} 9 } 10 11 def log_conversation(self, conversation: Dict): 12 self.metrics["total_conversations"] += 1 13 14 # Intent tracking 15 for message in conversation["messages"]: 16 if "intent" in message: 17 intent = message["intent"] 18 self.metrics["intent_distribution"][intent] = \ 19 self.metrics["intent_distribution"].get(intent, 0) + 1 20 21 # Resolution tracking 22 if conversation.get("resolved"): 23 self.metrics["successful_resolutions"] += 1 24 25 def get_resolution_rate(self) -> float: 26 if self.metrics["total_conversations"] == 0: 27 return 0 28 return self.metrics["successful_resolutions"] / self.metrics["total_conversations"]
Checklist per la Produzione
Sicurezza
- Sanitizzazione degli input
- Limitazione del rate
- Mascheramento delle PII
- Protezione dalle injection
Prestazioni
- Tempo di risposta < 2s
- Supporto utenti concorrenti
- Livello di caching
- Auto-scaling
Esperienza Utente
- Indicatori di digitazione
- Messaggi di errore
- Cronologia delle conversazioni
- Supporto multilingua
Conclusione
La Conversational AI è una tecnologia potente che sta trasformando le interazioni con i clienti. È possibile costruire chatbot efficienti con un flusso di dialogo ben progettato, una gestione robusta degli errori e un miglioramento continuo.
In Veni AI sviluppiamo soluzioni enterprise per chatbot.
