Mr.V.Shakthivel, Mr.N.Venkatesh BrabhuComputer Sceience Department Computer Sceience DepartmentKPR Institution Of Engineering And Technology KPR Institution Of Engineering And TechnologyCoimbatore,India. Coimbatore,India. mailto:[email protected] As the days passing the world keepsmoving forward with various technologies which improve the standard of thepeople.
In this modern era, the people have different life style and way ofapproach to their life. These modern approaches lead them to face various problemsin their work place and society. As a result they get stress, tension or frustrationwhich put their day off. So they searcha way to get out from their problem. In this paper shows the implementation of counseling chatbot which is builtbased on Artificial intelligence. It provides counseling to the users to getout of the problems faced by them. The chatbot provide counseling to the userbased on their mood.
To establish a near – natural conversation with people,chatbots must analyze the input given by the user and find out their mood andanswer for their query.INTRODUCTION Artificial intelligence is the keymethodology used to build those intelligence bots. Artificial intelligence (AI) is an area of computer sciencethat emphasizes the creation of intelligent machines that work and react likehumans. ArtificialIntelligence is nothing new to computing, its roots can be tracked back in1940s. Right from the old days Scientists have been using AI to test their experiments about how the human brainfunctions. Artificial Intelligence is all about training computer systems tolearn, analyze, think and make decisions like humans at a greater speed. UsingAI, machines could ponder, deliberate, contemplate, consider and then mediatedecisions on their own 1. Making choices to arrive at a conclusion, thenjudging and offering a verdict or predicting something just like humancognitive processes.
The cognitive process is the selection of a belief or acourse of action among several alternative possibilities. With constructs likemachine learning and deep learning expanding 2. AI is maturing at a rapidpace. It is increasingly adept at various complex tasks and is infiltratinginto many fields. Figure:1.
Artificial Intelligence In recent days artificial Intelligence is gaining moreimportance than the olden days. This can be attributed to the advancement in cheapsuperfast computing power, rapid connectivity and bandwidths, growing IoTcapabilities, and massive investments on cloud based computing andinfrastructure offerings. Due to such huge development AI gained more place inthe industries. HISTORYOF CHATBOTS The history of chatbots can betraced way back to 1950, when Alan Turing published his paper “ComputingMachinery and Intelligence”. This paper is widely regarded as one of the basicfoundations of Artificial Intelligence and the Turing Test he proposed in thispaper can be considered as a benchmark for evaluating the intelligence of acomputer system. The fame of his proposed test drew a lot of attention toJoseph Weizenbaum’s program ELIZA developed in 1966 at the MIT AI Laboratory 3.
ELIZA simulated a simple, text based conversation between a human user and thecomputer posing as a Rogerian psychotherapist. Weizenbaum’s main intention increating ELIZA was to exhibit the superficiality of human-computer interaction.However, he did not anticipate how a lot of people easily attributed human-likefeelings to the program.
However, the first chatbots were not actuallyintelligent, but were programs that had a collection of predefined setresponses corresponding to specific inputs. They were rudimentary and usedpattern matching and string processing to keep conversation moving between thecomputer and human. They merely created an illusion of intelligence of thecomputer, Figure:2. Classification of BotsRELATEDWORKS Chat botsare computer programs that conversation with people using artificialintelligence. They can transform the way you interact with the internet from aseries of self-initiated task. There are various chatbots where few are genericchatbots and others are specific chatbots. Chatbots find it’s place in variousfields like health care, entertainment, hotel reservation, house maintenance.
A. Health care In health care bots reduce the man power inhelp desk and detail enquiry process. It can also provide the details of theuser last visit to the hospital and the treatment details provide to him by thehospital.B. Hotel reservation In hotel reservation system thechatbot can act as a receptionist who can book or reserve the table for thevisitor. This implementation will also provide the automatic customermaintenance system as well.
C. Enterprise Enterprise chatbot helps in maintaining the projects,stock maintenance, provide initial security. The improve the performance of thesystem and remove the man errors.D. Personal shoppingassistance It interact with your and get some primary data and it provide you theassistant. you can get to your products faster and on-the-go, whenever andwherever you need them. The chatbot will also notify you when prices change forproducts on your boards and show other places to buy, when available. E.
Personal assistance This type of bot provide you a complete assistance of your work flow,weather, news, health tracking. These types of bot will provide the personal assistancein the various feilds.PROPOSEDSYSTEM The following figure shows ageneric flow of working of a chatbot. Once the user has entered the query, thechatbot sends it to the machine learning NLP (Natural Language Processing)Engine. The NLP returns the entities in the phrase which are then used to findthe relevant data 4. This data is given back to the chatbot and it isconverted to an appropriate response to be given to the user.
Figure:3. Generic Chatbot Workflow One of the approaches ofimplementing a chatbot is a domain specific chatbot. The hypothesis that adomain specific chatbot yields better efficiency than a generic chatbot can beproved using this approach. Such a chatbot can be used in a variety of domainswhich include education, desks, e-commerce and so on. In the proposed systemthe user input is given to the semantic mapper, which maps the input tosemantic elements.
These elements are given to conflict mediator in order toresolve conflicts by having further conversation with user, and are passed tothe topic navigator5. If there are no conflicts then the elements aredirectly given to topic navigator which finds the appropriate answer in theinformation repository. This answer is given to the response generator forgenerating a natural language response to be given to the user. Three kinds ofchatbot namely Basebot (contains converstional knowledge), Domainbot (containsdomain related faqs), Repbot(hybrid) were used to test the efficiency of theproposed system. It was found that a hybrid chatbot yielded best responsesatisfaction rate and least topic switching rate. According to the results,conversational knowledge Basebot combined with topic specific knowledge shouldbe adopted for future applications. Another approach of implementing a chatbotis the smart answering OCR based chatbot.
This approach uses the OpticalCharacter Recognition technology (OCR), Over generating transformations andranking algorithm and Artificial Intelligence Markup Language(AIML)6. OCRtechnology is a mechanism of converting a scanned document, images of handwritten text into machine encoded text. Over generating transformations andranking algorithm generates logically equivalent questions from sourcesentences. AIML is an XML dialect for creating natural language softwareagents. The proposed system has three phases Plain text extraction, QuestionGeneration and Question and Answers.
Plain text is extracted from pdf documentsor images using OCR technology. Questions are generated from the extracted textvia the over generating transformations and ranking algorithms. Thequestion-answer pairs that are generated are stored as the chatbot knowledgeusing AIML 7.
A pattern matching algorithm is used to match the user input tothe data stored in AIML. The corresponding responses are given to the user.This approach provides an efficient way of converting documents into thechatbot knowledge. This system can be used in call center services andeducational field for answering frequently asked questions.
An application ofchatbots lies in the field of E-business and e-commerce 8. The main problemthat almost every e-business model currently faces is that of quality customerservice in the least amount of time. As a solution to this problem, a solutionis proposed by Thomas N T that consists of a chatbot system to generateimmediate responses, which is a combination of AIML and LSA. Template basedquestions and greetings are answered by using AIML and other general questions areanswered by using LSA. The user query is first passed to the AIML block, whichchecks if the query is template based 9.
If yes, then a pattern based answeris generates as response. Otherwise, the query is routed to the LSA block wheretrained data is required to match the user query with expected output. The FAQsin any particular e-business domain is used for training the model. The FAQ ismade using online data from the internet. The FAQ corpus passes through aseries of steps beginning with tokenization where tokens are formed. Then stopword removal is performed by using Porter stemmer algorithm. After this, aword-document matrix is generated and then SVD is computed.
Cosine similarityis used to evaluate result with minimum distance from user query and thisresult is generated as the response. User queries are stored in HBase and AIMLdatabase is updated to improve answers to template based questions. The modelachieved 0.97 precision and LSA based questions gave correct responses 10.When the user provides insufficient information to answer his querysuccessfully, the chatbot needs to be inquisitive, that is it must proactivelyask the user questions in order to mimic a more natural human interaction. Thisapproach details the implementation of such an inquisitive chatbot whichrecognizes missing data from a query and probes the user to obtain the same inorder to answer his query.
In the existing chatbots, the chat engine usespattern-matching algorithms to search the knowledge base for. ALICE engine usesAIML as a knowledge base to stores a set of predefined queries and itsvariants. In order to make these hard-coded answers dynamic implement a hybridknowledge base model, involving AIML and another additional database. In thismodel, more permanent answers are stored in the AIML, while the frequentlychanging answers are stored in the database. In order to achieve such aproposed system, an additional knowledge base engine (KB engine) is implementedin the current system 11. This KB engine interfaces with a database forfetching factual data for responding to certain queries. The Knowledge BaseEngine is designed to integrate the database functionality with the AIML and toanalyze missing information from a query at the primary level in order toevaluate the query and come up with a response.
The KB engine works with a twophase evaluation methodology which constitutes identifying the missed datafield, obtaining the data from the user, and processing the retrieved answerfor the formation of right answers expected by the user.FUTUREWORK Currently chatbots are providingsome general guide lines like proving some ideas which engage them in otherwork. In future as per the current mood of the user it should provide the counselingto the user and it keep tracking the daily activities of the user and maintaina log based on his performance It will also provide the guidelines andsuggestion for yoga to maintain good health signs. Various counseling relatedservices are grouped into one single platform and pave the way for a trulyintelligent self-learning artificial entity.REFERENCES1 Jackson, Joab(February 17, 2011).
“IBM Watson Vanquishes Human Jeopardy Foes”. PCWorld. IDG News. Retrieved February 17, 2011.
2 Takahashi, Dean (February 17, 2011).”IBM researcher explains what Watson gets right and wrong”.VentureBeat. Retrieved February 18, 2011.3 G. Stringhini, O.Hohlfeld, C.
Kruegel, and G. Vigna. The harvester, the botmaster, and thespammer. Proceedings of the 9th ACM symposium on Information, computer andcommunications security – ASIA CCS ’14, 2014. 4 G. S. Tanwar and V.
Goar. Tools, techniques and analysis of botnet. Proceedings of the 2014International Conference on Information and Communication Technology forCompetitive Strategies – ICTCS ’14, 2014.
5 D. Zhao, I. Traore,B. Sayed, W. Lu, S. Saad, A. Ghorbani, and D.
Garant. Botnet detection based ontraffic behavior analysis and flow intervals. Elsevier, 39:2–16, 2013.6 L. von Ahn, M.Blum, and J. Langford, “Telling Human and Computers Apart Automatically,” inCommunications of the ACM, vol.
47, February 2004, no. 2, pp. 57-60.DOI:10.1145/966389.
966390.7 NitishaPayal, NidhiChaudhary, Parma NandAstya “JigCAPTCHA: An Advanced Image-Based CAPTCHA Integratedwith Jigsaw Piece Puzzle using AJAX” International Journal of Soft Computingand Engineering (IJSCE) ISSN: 2231-2307, Volume-2, Issue-5, November 2012.8 Monica Chew and J.D.
Tygar “Image Recognition CAPTCHAs” In Proceedings of the 7th InternationalInformation Security Conference (ISC 2004), Springer, September 2004, pp.268-279. 9 J.P. Bigham, andA.
C. Cavender, Evaluating existing audio CAPTCHAs and an interface optimizedfor nonvisual use. In Proceedings of ACM CHI 2009 Conference on Human Factorsin Computing Systems, 2009, pp. 1829-1838. 10 Shirali-Shahreza.
M and Shirali-Shahreza.S “Motion CAPTCHA” Human System Interactions, 2008 ConferenceDOI:10.1109/HSI.2008.4581589. 11 NitishaPayal, Nidhi Chaudhary, ParmaNandAstya “JigCAPTCHA: An Advanced Image-Based CAPTCHA Integrated with JigsawPiece Puzzle using AJAX” International Journal of Soft Computing andEngineering (IJSCE) ISSN: 2231-2307, Volume-2, Issue-5, November 2012.