Digital Workaholics:A Click Away

GSJ: Volume 9, Issue 5, May 2021 ISSN 2320-9186 1479

GSJ: Volume 9, Issue 5, May 2021, Online: ISSN 2320-9186 www.globalscientificjournal.com

DIGITAL WORKAHOLICS:A CLICK AWAY

Tripti Srivastava Muskan Chauhan Rohit Pandey Galgotias University Galgotias University Galgotias University [email protected] muskanchauhansmile@g [email protected] m mail.com om

ABSTRACT:-In today’s world, Artificial Intelligence (AI) has become an 1. INTRODUCTION integral part of human life. There are many applications of AI such as Chatbot, AI defines as those device that understands network security, complex problem there surroundings and took actions which solving, assistants, and many such. increase there chance to accomplish its Artificial Intelligence is designed to have outcomes. Artifical Intelligence used as “a cognitive intelligence which learns from system’s ability to precisely interpret its experience to take future decisions. A external data, to learn previous such data, virtual assistant is also an example of and to use these learnings to accomplish cognitive intelligence. Virtual assistant distinct outcomes and tasks through supple implies the AI operated program which adaptation.” Artificial Intelligence is the can assist you to reply to your query or developing branch of computer science. virtually do something for you. Currently, Having much more power and ability to the virtual assistant is used for personal develop the various application. AI implies and professional use. Most of the virtual the use of a different algorithm to solve assistant is device-dependent and is bind to various problems. The major application a single user or device. It recognizes only being Optical character recognition, one user. Our project proposes an Handwriting Recognition, Speech Assistant that is not a device bind. It can Recognition, Video Manipulation, recognize the user using facial recognition. Robotics, Medical Implementation, Virtual It can be operated from any platform. It Assistant, etc. should recognize and interact with the user.Moreover, virtual assistants can be Considering all the applications, Virtual used in many areas of applications such as assistant is one of the most influencing education, medical ,vechicles, robotics, applications of AI and attracting the interest and curiosity of researcher home automation as well as security access control. scholars. The virtual assistant supports a wide range of applications and because of this, it is categorized into many types such as virtual personal assistant, smart :Artificial Intelligence, Keywords assistants, digital assistant, mobile Cognitive Intelligence, Virtual Assistant, assistant, or voice assistant. Some of the Facial Recognition, Chatbot well-known virtual assistants being Alexa powered by Amazon, Siri by Apple, Cortana by Microsoft, Google Assistant by GSJ© 2021 www.globalscientificjournal.com GSJ: Volume 9, Issue 5, May 2021 ISSN 2320-9186 1480

Google, Messenger ‘M’ by Facebook. diagram for an assistant. These companies act as different ways to implement and improve their assistants. There are such ways used to implement the assistants based on the usages and its complexity. For ex., Google uses the DNN for its components. Again, Microsoft uses its Azure Machine Learning Studio to develop Cortana’s components. However, their potential is limited by

some scathing security issues that they don’t support powerful authentication Fig-1: Data Flow Model mechanisms and they are bind to their The data flow model of the Interactive specific hardware. Face recognition or Animated Virtual Assistant is shown in other identification mechanisms used Fig.1. the flow of data from the user to the before accepting any voice commands and AI and the generation of the reply. they should not bind to any specific hardware. In this paper, we upcome with an 3. WORKING MECHANISM approach that will overcome the security issue with the help of Face and Speech This assistant is fully modular and has a recognition, and using browser-based set of services. Each service offers some assistant will overcome the hardware tasks to do which then combines its data to dedicated problem. give a fully functional virtual assistant. Following is a brief idea about how the virtual assistant is going to function. 2. BLOCK DIAGRAM It starts with the first step of facial recognition. If the user is detected it Virtual Assistants is one of the active areas transfers to the next step else the prompt is that many companies are trying their hands provided as “User not detected want to on to improve its efficiency and register as new user” and new user applications. Sereval techniques are used registration prompt is opened and the to implement the virtual assistants depends predefined quaternary is loaded and the on its application or complexity and there user is asked to answer the following are many different architectures for it. questions for the registration process. Once Based on this data we designed a data flow all the questions are answered the facial sample photo is collected and the user is registered successfully and the application starts from the beginning. Once the user is detected the application is connected to the database having the data of the particular user and the assistant is ready for the query. The user can start the conversation ask a question or do as the user wish. The speech recognition program

converts the speech of the user into the text which converts the text on the format and saves that information into the screen to the audio. user database as the future data for voice recognition , generated input is then 1.3 Dialogue Manager Service transferred to the Chatbot application or The Dialogue Manager is the soul can be called as dialogue manager. of a virtual assistant as it generates Then the proper reply is generated using the query reply using its knowledge the knowledge database. Once the reply is database. It has the functionality to generated the text is then converted into give the most effective and best speech and the output is produced through reply to the query asked by the speakers. user. The user input is mostly textual or vocal which the Digital Workaholics, A click Away is processed using the service which mainly divided into three services that is used in the Dialogue Manager. handle most of the data. The following is Dialogue Manager is the key the services we proposed in the project: service that has the most complex task to do and give an accurate reply to the query.

1.4 Database 1.1 Face Detection Service In this Virtual Assistant we divided The Face Detection Service allows the database into two part which is our assistant to automatic detection as follows: the presence of the user which are 1.4.1 User Database going to use the device and verify its user data using the face in the The user database has all image and database. Face the information about the Detection Service simantanously user which its image and scans the video input from the vocal voice. It serves for camera or webcam. As soon as the user authentication and user face is detected virtual is available insertion. for further query. Face Detection 1.4.2 Knowledge Service uses the Deep Learning Database method to detect the face and authorize the user. The knowledge database can be local as well as 1.2 Speech Detection Service online which includes the facts about the user and its The Speech Detection Module queries and reply’s database allows the virtual assistant to which gives the idea about record the user’s voice data using how user and reply the microphone which then stores generation. into the user database for speech recognition. It also has the functionality of speech synthesis

In the paper [2], the authors have explained the AR-based Assistant which combines the human interface and location-aware digital system. It gives a much rich experience to the user. In this project, they are closer to create the virtual personal manager which gives the idea about it surrounding and location using augmented reality.

In the paper [4], the authors have explained smart assistants and smart home automation which gives the idea about speech- enabled virtual assistants which they find less secure so using a 4. RELATED WORK different technique they tried to overcome that issues.

In the paper [1], the authors have

explained how virtual private

assistant work and how they are being upgraded using various new 5. EVALUATION technology. It is the multimodal dialogue system. VPAs framework We evaluated the system in a has utilized discourse, illustrations, controlled environment and video, motions, and different different tasks as per the modules. modes for correspondence in both I.A.V.A. is an ongoing project. the info and yield channel. Many changes are being made and Likewise, the VPAs framework being tested each time. Currently, will be utilized to build the IAVA consist of three modules cooperation among clients and PCs being. by utilizing a few advances, for example, signal acknowledgment, 5.1 Face Detection Module: picture/video acknowledgment, In this module using various discourse acknowledgment, and the background and light in the Knowledge Base. Moreover, this testing environment, it has been system can enable a lengthy tested thoroughly and provided conversation with users by using a satisfactory result of detecting the vast dialogue knowledge base. and recognizing the face up to Our project emphasizes the VPA 80% time correctly. being device-independent which Optimization is being made to can be accessed whenever and the module as the project goes wherever wanted. further.

application, text to speech 5.2 New User Registration: translation. All this while providing It’s a second module and it an interactive animation. consists of adding a new user picture which can be added Based on our data we can find that using the webcam and it has this type of project can be very also been tested and its works popular in users since it can be 100%. accessed from any device and it can be used in the future project. 5.3 Speech to Text: This type of Project can be used for It’s the third module and it too medical purposes, business works with 100% proper purposes, and many other results. applications.

5.4 Reply Generation: It is done using AI. It is in 7. FUTURE SCOPE progress and the Chatbot is in a learning state and it can Following technology further can produce an accurate reply up to be upgraded with new budding 70%. techs such as emotion detection and live face interaction. The 5.5 Text to speech: interactive animation can be It’s the final module it converts upgraded to the facial animation the written reply from the for a more human-like feel. chatbot to text to be delivered to the user and it works with a 100% success rate. 8. ACKNOWLEDGMENT 5.6 WEB Site or CGI module: This module is currently under We might want to show our building state and has not yet appreciation to the teachers for been tested. offering their pearls of astuteness to us during this examination, and we say thanks to them for experiences and for their remarks 6. CONCLUSION that extraordinarily improved the report. We are additionally colossally thankful to our area of Our paper introduced IAVA – our expertise for giving all the Omni accessible virtual personal fundamental gear and offices. assistant which can be accessed from any device and can be used by any registered user. We propose 9. RESULT to utilize various AI techniques to

achieve so such as face detection, speech recognition, Chatbot

We evaluated the system in a This module is the front-end of controlled environment and our project which is design different tasks as per the modules. using web- It is an ongoing project. Many Scripting and programming. changes are being made and being tested each time. Currently, it consist of three modules being 10.REFERENCES 9.1 Face Detection Module: In this module using various [1] Next-age of virtual individual background and light in the colleagues ( Microsoft Cortana, testing environment, it has been Apple Siri, Amazon Alexa, and tested thoroughly and provided Google Home ) by Veton Këpuska; a satisfactory result of detecting Gamal Bohouta 2018 IEEE eighth and recognizing the face up to Annual Computing and 80% time correctly. Communication Workshop and Conference (CCWC) 9.2 New User Registration: This module consists of adding [2] MARA – A Mobile Augmented a new user picture that can be Reality-Based Virtual Assistant added using The webcam and it has also [3] G. Bohouta, V. Z. Këpuska, been tested and it works 100%. "Contrasting Speech Recognition Systems (Microsoft API Google 9.3 Speech to Text: API And CMU Sphinx)", Int. Diary This module convert’s user of Engineering Research and asked query into the input of Application 2017, 2017. the Chabot and it too works With 100% proper results. [4] A dream and discourse empowered, adaptable, menial 9.4 Reply Generation: helper for shrewd conditions This module gives the best possible reply with the help of [5] S. Arora, K. Batra, and S. deep learning Singh. Exchange System: A Brief According to the query asked Review. Punjab Technical by the user. University.

9.5 Text to speech: 8. Cowan, B.R.: What would i be This module converts the able to assist you with?: written reply from the Chatbot inconsistent users'experiences of to text to be delivered to the savvy individual colleagues. In: User and it works with a 100% 2015 IEEE tenth International success rate. Conference on Industrial and Data 9.6 WEB Site or CGI module: Systems, ICIIS 2015, Sri Lanka (201

[6] X. Lei, G. Tu, A. X. Liu, C. Li, experience.In: Mariani, J., Rosset, and T. Xie, "The weakness of S., Garnier-Rizet, M., Devillers, L. home advanced voice collaborators (eds.) Natural Interaction - Amazon Alexa as a contextual withRobots, Knowbots and investigation," CoRR, vol. Smartphones, pp. 3–14. Springer, abs/1712.03327, 2017. K. Wagner. New York (2014).

[7] Facebook's Virtual Assistant [14] Zhao, Y., Li, J., Zhang, S., 'M' Is Super Smart. It's Also Chen, L., Gong, Y.: Domain and Probably a Human. speaker transformation for https://www.recode.com. B. Marr. Cortanaspeech acknowledgment. In: ICASSP. [8] The Amazing Ways Google Uses Deep Learning AI. [15] Weeratunga, A.M., https://www.forbes.com. Jayawardana, S.A.U., Hasindu, P.M.A.K, Prashan, W.P.M., Thelij- [9] Y. Nung, A. Celikyilmaz.Deep jagoda, S.: Project Nethra - a clever Learning for Dialog Systems. partner for the outwardly crippled Profound Dialog. to communicate with internet providers. In: 2015 IEEE tenth [10] B. Martinez and M. F. Valstar, International Conference on Advances, Challenges, and Industrial and Information Opportunities in Automatic Facial Framework (2015) Expression Recognition, pp. 63– 100. Cham: Springer International [16] Kawamura, T., Ohsuga, A.: Publishing, 2016. Flower voice: remote helper for open information. [11] Lopez, G., Quesada, L., Guerrero, L.A.: Alexa [17] Tsiao, J.C.- S., Tong, P.P., vsSirivsCortanavs Google right Chao, D.Y.: Natural-Language hand: a examination of discourse Voice-Activated Personal based regular UIs. Meeting Paper, Collaborator, United States Patent January 2018 (10), Patent No.: US 7,216,080 B2 (45), 8 May 2007. [12] Purington, A., Taft, J.G., Sannon, S., Bazarova, N.N., [18] Kepuska, V., Bohouta, G.: Taylor, S.H.: Alexa is my new Next age of virtual individual aides BFF:social jobs, client fulfillment, (Microsoft Cortana,Apple Siri, and personiﬁcation of the amazon Amazon Alexa and Google Home). reverberation. ACM, 6–11 May In: IEEE Conference (2018) 2017. ISBN 978-1-4503-4656- 6/17/05 [19] Cowan, B.R.: What would i be [13] Bellegarda, J.R.: Spoken able to assist you with?: rare language understanding for users'experiences of smart characteristic connection: the siri individual associates. In: 2015

IEEE tenth International Conference on Industrial and Data [20] Kawamura, T., Ohsuga, A.: Systems, ICIIS 2015, Sri Lanka Flower voice: menial helper for (2015) open information,.