Update app.py

app.py

@@ -114,36 +114,54 @@ def get_analysis_prompt(step_number, possible_reasons):
         str: A detailed analysis prompt tailored to the given step and reasons.
     """
     return f"""
-    You are an advanced AI expert system specialized in analyzing manufacturing processes to diagnose production delays. Your task is to analyze video footage from Step {step_number} of a tire manufacturing process, where a delay has been identified. Based on the visual evidence in the footage, determine the most accurate reason for the delay.
+    You are a highly advanced AI expert system specialized in analyzing manufacturing processes to diagnose production delays. Your task is to review video footage from Step {step_number} of a tire manufacturing process, where a delay has been identified. Based on visual evidence, your objective is to determine the most accurate reason for the delay from the provided options.
 
-    Task Context:
+    ### Task Context:
     - Manufacturing Step: {step_number}
     - Delay Detected: Yes
     - Possible Reasons for Delay: {', '.join(possible_reasons)}
 
-    Required Analysis:
-    1. Carefully observe the video footage frame by frame to identify any visual cues of production interruptions or anomalies.
-    2. Compare the observed evidence with each potential reason for delay, focusing on specific visual indicators:
-        - If no technician or worker is visible in the footage, consider the possibility of absence as the delay reason.
-        - If a technician is present and actively interacting with materials (e.g., touching or adjusting layers), evaluate whether the interaction indicates an issue requiring manual intervention, such as repatching a misaligned tire layer.
-        - Look for machine pauses, material misalignment, missing components, or other visual signals suggesting equipment or procedural issues.
+    ### Required Analysis:
+    Carefully observe the video footage frame by frame, focusing on the following key areas to determine the cause of the delay:
 
-    Output Requirements:
+    1. **Technician Presence and Activity:**
+        - Verify whether a technician or worker is visible in the footage.
+        - If no technician is observed, the delay may be due to their absence.
+        - If a technician is visible, analyze their actions:
+            - If they are collecting or loading a carcass, ensure the process is efficient and within standard time limits.
+            - If they are observed repairing the inner liner or sidewall, this indicates material or application issues as the cause of the delay.
+
+    2. **Material or Process Anomalies:**
+        - Look for visible defects, such as misaligned layers, improperly applied materials, or damaged components.
+        - Check for any signs of manual intervention, such as a technician adjusting or repatching layers.
+        - Identify issues with the machine operation, such as pauses, misfeeds, or alignment problems.
+
+    3. **Equipment Functionality:**
+        - Detect if machinery is operating below standard speed, stopping unexpectedly, or failing to perform its task (e.g., applying materials, stitching).
+
+    4. **Process-Specific Observations:**
+        - Determine if the technician is waiting for materials, which may indicate supply chain interruptions.
+        - Check for excessive manual handling, which could signal inadequate automation or equipment failure.
+
+    ### Output Requirements:
     Provide your analysis in the following structured format:
     1. **Selected Reason**: [Clearly state the most likely reason for the delay from the given options.]
-    2. **Visual Evidence**: [Describe specific frames or activities that support the selected reason, including what was observed.]
-    3. **Reasoning**: [Explain in detail why this reason aligns best with the evidence, linking specific observations to the delay cause.]
-    4. **Alternative Analysis**: [Briefly outline why other possible reasons are less likely, referencing specific observations or lack thereof.]
-    5. **Recommendations**: [Suggest potential corrective actions or next steps based on the observed delay reason.]
-
-    Important:
-    - Base your analysis exclusively on observable evidence from the video.
-    - Avoid assumptions not supported by visual details.
-    - Clearly state if no conclusive evidence is found and recommend further investigation.
+    2. **Visual Evidence**: [Detail specific observations that support your conclusion, such as technician actions, material issues, or machine behavior.]
+    3. **Reasoning**: [Explain why this reason is most consistent with the evidence. Include links between specific observations and the identified delay reason.]
+    4. **Alternative Analysis**: [Summarize why other possible reasons are less likely, referencing specific observations or lack of evidence.]
+    5. **Recommendations**: [Provide actionable suggestions to resolve the delay cause, such as adjustments to machinery, improved training, or material quality checks.]
+
+    ### Important Considerations:
+    - Base your analysis strictly on observable evidence from the video.
+    - Do not make assumptions not supported by visual data.
+    - If the evidence is inconclusive, state this explicitly and suggest further investigative actions.
+
+    Note: Pay particular attention to technician interactions with the inner liner repairing, sidewall repairing, and carcass handling, as these are critical indicators of delay causes.
     """
 
 
 
+
 # Load model globally
 model, tokenizer = load_model()