Mr.V.Shakthivel, Mr.N.Venkatesh Brabhu
Computer Sceience Department Computer Sceience Department
KPR Institution Of Engineering And Technology KPR Institution Of Engineering And Technology
As the days passing the world keeps
moving forward with various technologies which improve the standard of the
people. In this modern era, the people have different life style and way of
approach to their life. These modern approaches lead them to face various problems
in their work place and society. As a result they get stress, tension or frustration
which put their day off. So they search
a way to get out from their problem. In this paper shows the implementation of counseling chatbot which is built
based on Artificial intelligence. It provides counseling to the users to get
out of the problems faced by them. The chatbot provide counseling to the user
based 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 and
answer for their query.
Artificial intelligence is the key
methodology used to build those intelligence bots. Artificial intelligence (AI) is an area of computer science
that emphasizes the creation of intelligent machines that work and react like
Intelligence is nothing new to computing, its roots can be tracked back in
1940s. Right from the old days Scientists have been using AI to test their experiments about how the human brain
functions. Artificial Intelligence is all about training computer systems to
learn, analyze, think and make decisions like humans at a greater speed. Using
AI, machines could ponder, deliberate, contemplate, consider and then mediate
decisions on their own 1. Making choices to arrive at a conclusion, then
judging and offering a verdict or predicting something just like human
cognitive processes. The cognitive process is the selection of a belief or a
course of action among several alternative possibilities. With constructs like
machine learning and deep learning expanding 2. AI is maturing at a rapid
pace. It is increasingly adept at various complex tasks and is infiltrating
into many fields.
1. Artificial Intelligence
In recent days artificial Intelligence is gaining more
importance than the olden days. This can be attributed to the advancement in cheap
superfast computing power, rapid connectivity and bandwidths, growing IoT
capabilities, and massive investments on cloud based computing and
infrastructure offerings. Due to such huge development AI gained more place in
The history of chatbots can be
traced way back to 1950, when Alan Turing published his paper “Computing
Machinery and Intelligence”. This paper is widely regarded as one of the basic
foundations of Artificial Intelligence and the Turing Test he proposed in this
paper can be considered as a benchmark for evaluating the intelligence of a
computer system. The fame of his proposed test drew a lot of attention to
Joseph 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 the
computer posing as a Rogerian psychotherapist. Weizenbaum’s main intention in
creating ELIZA was to exhibit the superficiality of human-computer interaction.
However, he did not anticipate how a lot of people easily attributed human-like
feelings to the program. However, the first chatbots were not actually
intelligent, but were programs that had a collection of predefined set
responses corresponding to specific inputs. They were rudimentary and used
pattern matching and string processing to keep conversation moving between the
computer and human. They merely created an illusion of intelligence of the
2. Classification of Bots
are computer programs that conversation with people using artificial
intelligence. They can transform the way you interact with the internet from a
series of self-initiated task. There are various chatbots where few are generic
chatbots and others are specific chatbots. Chatbots find it’s place in various
fields like health care, entertainment, hotel reservation, house maintenance.
In health care bots reduce the man power in
help desk and detail enquiry process. It can also provide the details of the
user last visit to the hospital and the treatment details provide to him by the
In hotel reservation system the
chatbot can act as a receptionist who can book or reserve the table for the
visitor. This implementation will also provide the automatic customer
maintenance system as well.
Enterprise chatbot helps in maintaining the projects,
stock maintenance, provide initial security. The improve the performance of the
system and remove the man errors.
It interact with your and get some primary data and it provide you the
assistant. you can get to your products faster and on-the-go, whenever and
wherever you need them. The chatbot will also notify you when prices change for
products on your boards and show other places to buy, when available.
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 assistance
in the various feilds.
The following figure shows a
generic flow of working of a chatbot. Once the user has entered the query, the
chatbot sends it to the machine learning NLP (Natural Language Processing)
Engine. The NLP returns the entities in the phrase which are then used to find
the relevant data 4. This data is given back to the chatbot and it is
converted to an appropriate response to be given to the user.
3. Generic Chatbot Workflow
One of the approaches of
implementing a chatbot is a domain specific chatbot. The hypothesis that a
domain specific chatbot yields better efficiency than a generic chatbot can be
proved using this approach. Such a chatbot can be used in a variety of domains
which include education, desks, e-commerce and so on. In the proposed system
the user input is given to the semantic mapper, which maps the input to
semantic elements. These elements are given to conflict mediator in order to
resolve conflicts by having further conversation with user, and are passed to
the topic navigator5. If there are no conflicts then the elements are
directly given to topic navigator which finds the appropriate answer in the
information repository. This answer is given to the response generator for
generating a natural language response to be given to the user. Three kinds of
chatbot namely Basebot (contains converstional knowledge), Domainbot (contains
domain related faqs), Repbot(hybrid) were used to test the efficiency of the
proposed system. It was found that a hybrid chatbot yielded best response
satisfaction rate and least topic switching rate. According to the results,
conversational knowledge Basebot combined with topic specific knowledge should
be adopted for future applications. Another approach of implementing a chatbot
is the smart answering OCR based chatbot. This approach uses the Optical
Character Recognition technology (OCR), Over generating transformations and
ranking algorithm and Artificial Intelligence Markup Language(AIML)6. OCR
technology is a mechanism of converting a scanned document, images of hand
written text into machine encoded text. Over generating transformations and
ranking algorithm generates logically equivalent questions from source
sentences. AIML is an XML dialect for creating natural language software
agents. The proposed system has three phases Plain text extraction, Question
Generation and Question and Answers. Plain text is extracted from pdf documents
or images using OCR technology. Questions are generated from the extracted text
via the over generating transformations and ranking algorithms. The
question-answer pairs that are generated are stored as the chatbot knowledge
using AIML 7. A pattern matching algorithm is used to match the user input to
the data stored in AIML. The corresponding responses are given to the user.
This approach provides an efficient way of converting documents into the
chatbot knowledge. This system can be used in call center services and
educational field for answering frequently asked questions. An application of
chatbots lies in the field of E-business and e-commerce 8. The main problem
that almost every e-business model currently faces is that of quality customer
service in the least amount of time. As a solution to this problem, a solution
is proposed by Thomas N T that consists of a chatbot system to generate
immediate responses, which is a combination of AIML and LSA. Template based
questions and greetings are answered by using AIML and other general questions are
answered by using LSA. The user query is first passed to the AIML block, which
checks if the query is template based 9. If yes, then a pattern based answer
is generates as response. Otherwise, the query is routed to the LSA block where
trained data is required to match the user query with expected output. The FAQs
in any particular e-business domain is used for training the model. The FAQ is
made using online data from the internet. The FAQ corpus passes through a
series of steps beginning with tokenization where tokens are formed. Then stop
word removal is performed by using Porter stemmer algorithm. After this, a
word-document matrix is generated and then SVD is computed. Cosine similarity
is used to evaluate result with minimum distance from user query and this
result is generated as the response. User queries are stored in HBase and AIML
database is updated to improve answers to template based questions. The model
achieved 0.97 precision and LSA based questions gave correct responses 10.
When the user provides insufficient information to answer his query
successfully, the chatbot needs to be inquisitive, that is it must proactively
ask the user questions in order to mimic a more natural human interaction. This
approach details the implementation of such an inquisitive chatbot which
recognizes missing data from a query and probes the user to obtain the same in
order to answer his query. In the existing chatbots, the chat engine uses
pattern-matching algorithms to search the knowledge base for. ALICE engine uses
AIML as a knowledge base to stores a set of predefined queries and its
variants. In order to make these hard-coded answers dynamic implement a hybrid
knowledge base model, involving AIML and another additional database. In this
model, more permanent answers are stored in the AIML, while the frequently
changing answers are stored in the database. In order to achieve such a
proposed system, an additional knowledge base engine (KB engine) is implemented
in the current system 11. This KB engine interfaces with a database for
fetching factual data for responding to certain queries. The Knowledge Base
Engine is designed to integrate the database functionality with the AIML and to
analyze missing information from a query at the primary level in order to
evaluate the query and come up with a response. The KB engine works with a two
phase evaluation methodology which constitutes identifying the missed data
field, obtaining the data from the user, and processing the retrieved answer
for the formation of right answers expected by the user.
Currently chatbots are providing
some general guide lines like proving some ideas which engage them in other
work. In future as per the current mood of the user it should provide the counseling
to the user and it keep tracking the daily activities of the user and maintain
a log based on his performance It will also provide the guidelines and
suggestion for yoga to maintain good health signs. Various counseling related
services are grouped into one single platform and pave the way for a truly
intelligent self-learning artificial entity.
1 Jackson, Joab
(February 17, 2011). “IBM Watson Vanquishes Human Jeopardy Foes”. PC
World. 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 the
spammer. Proceedings of the 9th ACM symposium on Information, computer and
communications security – ASIA CCS ’14, 2014.
4 G. S. Tanwar and V.
Goar. Tools, techniques and analysis of botnet. Proceedings of the 2014
International Conference on Information and Communication Technology for
Competitive Strategies – ICTCS ’14, 2014.
5 D. Zhao, I. Traore,
B. Sayed, W. Lu, S. Saad, A. Ghorbani, and D. Garant. Botnet detection based on
traffic 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,” in
Communications of the ACM, vol. 47, February 2004, no. 2, pp. 57-60.
7 NitishaPayal, Nidhi
Chaudhary, Parma NandAstya “JigCAPTCHA: An Advanced Image-Based CAPTCHA Integrated
with Jigsaw Piece Puzzle using AJAX” International Journal of Soft Computing
and 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 International
Information Security Conference (ISC 2004), Springer, September 2004, pp.
9 J.P. Bigham, and
A.C. Cavender, Evaluating existing audio CAPTCHAs and an interface optimized
for nonvisual use. In Proceedings of ACM CHI 2009 Conference on Human Factors
in Computing Systems, 2009, pp. 1829-1838.
10 Shirali-Shahreza. M and Shirali-Shahreza.
S “Motion CAPTCHA” Human System Interactions, 2008 Conference
11 NitishaPayal, Nidhi Chaudhary, Parma
NandAstya “JigCAPTCHA: An Advanced Image-Based CAPTCHA Integrated with Jigsaw
Piece Puzzle using AJAX” International Journal of Soft Computing and
Engineering (IJSCE) ISSN: 2231-2307, Volume-2, Issue-5, November 2012.