e-ISSN: 2582-5208 International Research Journal of Modernization in Engineering Technology and Science Volume:02/Issue:09/September-2020
Impact Factor- 5.354
www.irjmets.com
MEDICAL CHATBOT ASSISTANCE USING AI AND DEEP LEARNING Suraj Yadav*1, Ravi Madhesiya* 2, Sahil Narkhede*3, Ajay Babar* 4, Vaibhav Muddebihalkar *5 *1,2,3,4Student, Department of COMPUTER Engineering, DIT Pimpri, Pune, Maharashatra, India. *5Professor, Department of COMPUTER Engineering, DIT Pimpri, Pune, Maharashatra, India.
ABSTRACT Medical services are basic needs for human life although they normally have limited resources. Modern technologies are utilized for increasing service capability and decreasing the operation cost. Humans with the regular access of internet are having new habit of searching their queries on open internet and mostly believe on the result received as a response. The major strength which can also be considered as drawback of internet is anyone can add information on the internet which can also to contradicting information and false information. The user without having clue that the response is false will believe in the response and may make a wrong assumption. Auto-response system or chatbot, which is widely known in the field of online businesses, can be applied to the medical services. Therefore, the objective of this work is to implement the medical assistance for allergies by using chatbot Technology. The concept of chatbot mainly focusses on the questions and answers computed by the software. It considers the symptoms of the users like head ache, rashes, swelling throat and many more. Every allergies have different symptoms and their are also be some allergies that have very similar symptoms with some minute difference, the chatbot using natural language processing can differ between similar allergies and give a accurate result. Keywords: Natural Language Processing, Artificial Intelligence, NLTK, Bag Of Words, Beam Search Decoder, Recurrent Neural Network, Human-Machine Interaction.
I.
INTRODUCTION
The number of people seeking for health information form the internet increases dramatically. There are several factors that influence people to use the internet for searching for health information. Trusted medical information such as diseases, symptoms, and treatment is necessary for people to handle with some general illness or being used as a decision support information before visiting a doctor A chatbot is a computer system, which can interact with users by using natural language. Normally, it is designed to serve in a certain domain such as online shopping, online frequently asked questions (FAQ) and also assistant system. Users can easily use it without background knowledge or experiences. Moreover, chatbot can serve many people at the same time with the same topic and without getting bored. Consequently, this may be the suitable capability to be adopted in public service such as the medical service. Hence, the objective of this work is to increase the service capability and decrease the operation cost of medical consultant service by using the chatbot. In this work, the allergic consultant system called “AllBot”.
II.
METHODOLOGY
Chat bot system is automating lot of customer care service and also company , institutions , organization’s websites. User get quick response to the questions which are more common are which are frequently asked. Here we have proposed chat bot system for patients. Patients definitely may have lots if queries related to diseases , medicines and other facilities. Instead of asking any random person they can get quick answer via this chat bot system. MACHINE LEARNING Machine Learning is a part of artificial intelligence wherein a process of self-learning happens without being directly programmed. A computer program learns with ExperienceE, against some Task- T and Performance Measure- P, if performance of the given task which is measured by P improves because of experience. The main distinction between machines and humans is that humans learn from experience www.irjmets.com
@International Research Journal of Modernization in Engineering, Technology and Science
[325]
e-ISSN: 2582-5208 International Research Journal of Modernization in Engineering Technology and Science Volume:02/Issue:09/September-2020
Impact Factor- 5.354
www.irjmets.com
whereas machines work based on instructions. But we can make even machines work from experience this is called data in technical language. That is how machine learning came into being. Learning means acquiring knowledge, behaviour or any skill through experience and studying. Machine learning is among the emerging fields of computer science technology. The process of learning begins with observations or data, such as examples, direct experience, or instruction, in order to look for patterns in data and make better decisions in the future based on the examples that we provide. The primary aim is to allow the computers learn automatically without human intervention or assistance and adjust actions accordingly.
Figure: 1 Machine Learning Diagram
III.
MODELING AND ANALYSIS
SYSTEM ARCHITECTURE
MODULES Module 1: Press the button for voice input. Module 2: We need to give our question or query to system. Module 3: System will recognize the speech. Module 4: Recognize the query using Speech Recognition Module and convert to text using text Conversion. Module 5: Translate the query using translator. Module 6: Match the query in database (Use NLP). Module 7: Response to query by translating in quick way. MATHEMATICAL MODEL Let S is the Whole System Consist of www.irjmets.com
@International Research Journal of Modernization in Engineering, Technology and Science
[326]
e-ISSN: 2582-5208 International Research Journal of Modernization in Engineering Technology and Science Volume:02/Issue:09/September-2020
Impact Factor- 5.354
www.irjmets.com
S = I, P, O Where, I=CURLOC,SELOC,LOG,RE,PRO LOG = user login into system SEP = Select Voice input PRO = Dataset TI = Input through mike P = Process Step1 : user will login Step2 : User will select voice input Step3 : System will recognize speech Step3 : User will Apply Mathematical Algorithmic Method Step4:System will give response to query.
IV.
RESULT AND DISCUSSION
ALGORITHM DETAILS ALGORITHM ONE 1.
Speech Recognition Module is going to be used for voice recognition in our system.
2.
Google Speech-To-Text is a suitable solution for applications other than short web searches.
3.
NLP is used for sentiment analysis.
4.
Once query is fetched, we will find response by matching text string in from data base.
ALGORITHM TWO (DIVIDE AND CONQUER) 1. Breaking it into sub problems that are themselves smaller instances of the same type of problem. 2. Recursively solving these sub problems. 3. Appropriately combining the answers The real work is done piecemeal, in three different places: in the partitioning of problems into sub problems; at the very tail end of the recursion ,when the sub problems are so small that they are solved out right ;and in the glue ingoted the roof partial answers. 4. The sear held together and coordinated by the algorithm’ score recursive structure. OUTCOMES
www.irjmets.com
@International Research Journal of Modernization in Engineering, Technology and Science
[327]
e-ISSN: 2582-5208 International Research Journal of Modernization in Engineering Technology and Science Volume:02/Issue:09/September-2020
www.irjmets.com
Impact Factor- 5.354
www.irjmets.com
@International Research Journal of Modernization in Engineering, Technology and Science
[328]
e-ISSN: 2582-5208 International Research Journal of Modernization in Engineering Technology and Science Volume:02/Issue:09/September-2020
V.
Impact Factor- 5.354
www.irjmets.com
CONCLUSIONS
The framework we create to make client benefits simple. As there we are attempting to make framework simple to connect. There will be no compelling reason to press the catch to pick choice just as no compelling reason to hang tight for answer. Here we use Speech Recognition module, Speech to content change module and language interpreter module. Chatting bot service provider acts as a customer care for many organization / institutions / industries etc. or it may act as a personal assistant to all the people of the world. Bots developed on our site can also help to remember many things. It may also help in attracting customers nationwide for many companies. It can also be used to entertain people by sending them jokes, facts, quotes etc. whenever they are bored. At the top of all performance in the main concern while developing our project so that it can service millions of customers at a single moment of time. After best of testing results and responses from developed system proposed method came to the conclusion that methodology is provenly successful.
VI.
REFERENCES
[1] Augello A. Saccone G. Gaglio S. Pilato G., Humorist Bot: Bringing Computational Humour in a Chat-Bot System. Proceedings of the International Conference on “Complex, Intelligent and Software Intensive Systems (CISIS)”, 4-7 March 2018, Barcelona, Spain, pp.703- 708. [2] Gambino O. Augello A. Caronia A. Pilato G. Pirrone R. Gaglio S., Virtual conversation with a real talking head. Proceedings of the Conference on “Human System Interactions”, 25-27 May 2018,Kraow, Poland, pp. 263-268. [3] Vojtko J. Kacur J. Rozinaj G., The training of Slovak speech recognition system based on Sphinx 4 for GSM networks. Proceedings of International Symposium “EL, MAR (Electronics in Marine) focused on Mobile Multimedia”, 12-14 Sept. [4] 2017, Zadar, Croatia, pp. 147-150. [5] Sun Microsystems, Developer resources for JAVA technology. [Online] http://java.sun.com www.irjmets.com
@International Research Journal of Modernization in Engineering, Technology and Science
[329]
e-ISSN: 2582-5208 International Research Journal of Modernization in Engineering Technology and Science Volume:02/Issue:09/September-2020
Impact Factor- 5.354
www.irjmets.com
[6] (Accessed: 30 Oct. 2018) [7] The Apache Software Foundation, The Apache HTTP Server Project. [Online] http://www.apache.org (Accessed: 30 Oct. 2018) [8] Sun Microsystems, MySQL: The world’s most popular open source database. [Online] http://www.mysql.com(Accessed: 30 Oct. 2018)
www.irjmets.com
@International Research Journal of Modernization in Engineering, Technology and Science
[330]