Update app.py

app.py

@@ -1,48 +1,63 @@
 import streamlit as st
 from transformers import pipeline
+import re
 
-# Load models
-emotion_classifier = pipeline(
-    "text-classification",
-    model="bhadresh-savani/distilbert-base-uncased-emotion",
-    top_k=3
-)
+# Load HuggingFace models
+emotion_classifier = pipeline("text-classification", model="bhadresh-savani/distilbert-base-uncased-emotion", top_k=3)
+intent_classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
 
-intent_classifier = pipeline(
-    "zero-shot-classification",
-    model="facebook/bart-large-mnli"
-)
-
-# Define emotion priority rules
-urgent_emotions = {"anger", "annoyance", "disgust", "frustration", "sadness"}
-moderate_emotions = {"confusion", "concern", "nervousness", "fear"}
-low_emotions = {"neutral", "approval", "excitement", "joy", "curiosity"}
-
-# Define candidate customer intents
+# Candidate intents
 candidate_tasks = [
-    "change data plan",
+    "change mobile plan",
     "upgrade phone",
     "top up balance",
-    "report network issue",
-    "ask for billing help",
+    "report service outage",
+    "ask for billing support",
     "request human support",
-    "check account status",
-    "suspend service",
-    "reactivate number",
-    "cancel subscription"
+    "reactivate service",
+    "cancel subscription",
+    "check account status"
 ]
 
-def assess_priority(emotion):
+# Define emotion priority rules
+urgent_emotions = {"anger", "annoyance", "disgust", "frustration", "sadness"}
+moderate_emotions = {"confusion", "concern", "nervousness", "fear"}
+
+# Helper: Calculate support score
+def calculate_support_score(text, emotion):
+    score = 0.0
+
+    # Emotion-based scoring
     if emotion in urgent_emotions:
-        return "🔴 High", "✅ Immediate human support is recommended."
+        score += 0.5
     elif emotion in moderate_emotions:
-        return "🟠 Moderate", "⚠️ Human support may be needed soon."
-    else:
-        return "🟢 Low", "❌ No human support needed. Automated response is sufficient."
+        score += 0.3
+
+    # Symbol analysis
+    if "!" in text:
+        score += 0.1 * min(text.count("!"), 3)  # max +0.3
+
+    # Keyword triggers
+    urgent_keywords = ["not working", "out of service", "no signal", "urgent", "immediately", "stopped"]
+    for kw in urgent_keywords:
+        if kw in text.lower():
+            score += 0.2
+            break
+
+    return min(score, 1.0)
+
+# Helper: Generate auto-response
+def generate_auto_reply(top_intent):
+    intent_responses = {
+        "change mobile plan": "You can change your mobile plan by visiting your account dashboard or exploring our latest offers here: [link].",
+        "top up balance": "To restore service, please top up your balance through our payment portal: [link].",
+        "check account status": "You can check your account status and active services via our self-service portal: [link].",
+    }
+    return intent_responses.get(top_intent.lower(), "We have received your request and are processing it.")
 
-# Streamlit App Interface
-st.set_page_config(page_title="AI Customer Support Analyzer", layout="centered")
-st.title("📞 AI Customer Emotion & Intent Analyzer")
+# App UI
+st.set_page_config(page_title="AI Customer Support Decision Engine", layout="centered")
+st.title("📞 AI Customer Emotion, Intent & Support Decision Analyzer")
 
 user_input = st.text_area("Please enter the customer's message or conversation:", height=150)
 
@@ -52,26 +67,58 @@ if st.button("Analyze"):
     else:
         with st.spinner("Analyzing..."):
 
-            # --- Emotion Classification ---
+            # 1. Emotion Analysis
             emotion_results = emotion_classifier(user_input)
             top_emotion = emotion_results[0][0]
             emotion_label = top_emotion['label']
             emotion_score = top_emotion['score']
-            priority_level, recommendation = assess_priority(emotion_label)
 
+            # 2. Support Score
+            support_score = calculate_support_score(user_input, emotion_label)
+
+            # 3. Intent Detection
+            intent_result = intent_classifier(user_input, candidate_tasks)
+            top_labels = intent_result['labels']
+            top_scores = intent_result['scores']
+            intent_pairs = list(zip(top_labels, top_scores))
+            filtered_intents = [(label, score) for label, score in intent_pairs if score > 0.15]
+
+            # Display emotion
             st.subheader("📌 Emotion Analysis")
             st.write(f"**Primary Emotion**: {emotion_label}")
             st.write(f"**Confidence Score**: {emotion_score:.2f}")
 
-            st.subheader("🛎️ Support Priority Recommendation")
-            st.write(f"**Priority Level**: {priority_level}")
-            st.success(recommendation)
+            # Display support recommendation
+            st.subheader("🛎️ Human Support Priority")
+            st.write(f"**Support Score**: {support_score:.2f}")
+            if support_score >= 0.7:
+                st.error("🔴 Strongly Recommend Human Support")
+            elif support_score >= 0.4:
+                st.warning("🟠 Consider Human Support")
+            else:
+                st.success("🟢 Automated Response is Sufficient")
+
+            # Output decision
+            st.subheader("🧠 System Recommendation")
+            if support_score < 0.4:
+                top_intent = top_labels[0]
+                st.markdown(f"🤖 **Auto-reply Recommendation**: _{top_intent}_")
+                st.info(generate_auto_reply(top_intent))
+            else:
+                st.markdown("👩‍💼 **Customer Intent Summary for Human Agent:**")
+
+                if filtered_intents:
+                    st.markdown("### 🔺 Priority Pyramid")
+                    st.markdown(f"- **Primary Intent**: {filtered_intents[0][0]} (confidence: {filtered_intents[0][1]:.2f})")
 
-            # --- Intent Detection ---
-            task_result = intent_classifier(user_input, candidate_tasks)
-            top_tasks = task_result['labels'][:3]
-            top_scores = task_result['scores'][:3]
+                    if len(filtered_intents) > 1:
+                        st.markdown("### 🔸 Secondary Intents")
+                        for label, score in filtered_intents[1:]:
+                            st.markdown(f"- {label} (confidence: {score:.2f})")
 
-            st.subheader("⚙️ Detected Possible Customer Intents")
-            for label, score in zip(top_tasks, top_scores):
-                st.write(f"🔸 **{label}** (confidence: {score:.2f})")
+                    st.markdown("### 🔹 Additional Clues")
+                    if "!" in user_input:
+                        st.write("- Urgent tone detected (multiple '!')")
+                    st.write(f"- Detected Emotion: {emotion_label}")
+                else:
+                    st.info("No clear customer intents detected.")