Authors - Manik Pratapwar, Priyank Shah, Suraj Padia, Sanjay T Gandhe Abstract - This paper introduces a novel chatbot system designed to aid in the diagnosis of diseases. Leveraging advanced deep learning techniques such as Siamese Long Short-Term Memory, attention algorithm, and the Aho-Corasick algorithm. The core of the chatbot's intelligence lies in its ability to analyze user input symptoms and provide relevant disease predictions. The Siamese LSTM architecture allows the model to effectively capture sequential dependencies in symptom descriptions, thereby improving the understanding of complex symptom patterns. Additionally, an attention mechanism is incorporated to focus on key symptoms and facilitate more accurate disease inference. Furthermore, the Aho-Corasick algorithm is utilized for efficient keyword matching, enabling the chatbot to recognize symptom keywords and extract pertinent information from user queries. The experimental results demonstrate the effectiveness of the proposed approach in disease diagnosis, achieving high accuracy rates and providing reliable recommendations to users. Moreover, user feedback indicates the usability and practicality of the chatbot in assisting individuals with symptom identification and health-related inquiries. Overall, this research contributes to the advancement of intelligent healthcare systems by leveraging advanced deep learning techniques and algorithmic innovations to enhance disease diagnosis and support patient care.