AgentG: A user friendly and engaging bot to chat for e-commerce lovers

Regular customer assistance chatbots are generally based on dialogues delivered by humans. It faces symbolic issues usually related to data scaling and the privacy of one’s information. In this paper, we coeval AgentG, an intelligent chatbot used for customer assistance. It is built using deep neural network architecture. It clouts huge-scale and free publicly accessible e-commerce data. Different from existing counterparts, AgentG takes a great data advantage from in-pages that contain product descriptions along with user-generated data content from these online eCommerce websites. It results in more efficient from a practical point of view as well as cost-effective while answering questions that are repetitive. This helps in providing the freedom to people who work as customer service in order to answer questions with highly accurate answers. We have demonstrated how AgentG acts as an additional extension to the actual stream web browsers and how it is useful to users in having a better experience who are doing online shopping.

[1]  Xue Li,et al.  Greedy Optimization for K-Means-Based Consensus Clustering , 2018 .

[2]  Mariette Awad,et al.  Towards A Deep Learning Question-Answering Specialized Chatbot for Objective Structured Clinical Examinations , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[3]  Ferry Wahyu Wibowo,et al.  Chatbot Using a Knowledge in Database: Human-to-Machine Conversation Modeling , 2016, 2016 7th International Conference on Intelligent Systems, Modelling and Simulation (ISMS).

[4]  Giovanni Pilato,et al.  Expert chat-bots for cultural heritage , 2005, Intelligenza Artificiale.

[5]  Stewart Kowalski,et al.  Two Case Studies in Using Chatbots for Security Training , 2009, World Conference on Information Security Education.

[6]  Omar Khadeer Hussain,et al.  A Survey on Chatbot Implementation in Customer Service Industry through Deep Neural Networks , 2018, 2018 IEEE 15th International Conference on e-Business Engineering (ICEBE).

[7]  B. K. Tripathy,et al.  On the theory of bags and lists , 2001, Inf. Sci..

[8]  B. K. Tripathy,et al.  On demand analysis of learning experiences for adaptive content retrieval in an e-learning environment , 2015 .

[9]  B. K. Tripathy,et al.  Investigation of recurrent neural networks in the field of sentiment analysis , 2017, 2017 International Conference on Communication and Signal Processing (ICCSP).

[10]  B. K. Tripathy,et al.  Affinity-based learning object retrieval in an e-learning environment using evolutionary learner profile , 2016 .

[11]  B. K. Tripathy,et al.  An Object Oriented Approach to Improve the Precision of Learning Object Retrieval in a Self Learning Environment , 2012 .

[12]  B. K. Tripathy,et al.  A generic hybrid recommender system based on neural networks , 2014, 2014 IEEE International Advance Computing Conference (IACC).

[13]  B. K. Tripathy,et al.  Reinforcement learning approach towards effective content recommendation in MOOC environments , 2014, 2014 IEEE International Conference on MOOC, Innovation and Technology in Education (MITE).

[14]  Bibek Behera.  Chappie - A Semi-automatic Intelligent Chatbot , 2016 .

[15]  Ming Zhou,et al.  SuperAgent: A Customer Service Chatbot for E-commerce Websites , 2017, ACL.

[16]  Carmen Holotescu,et al.  MOOCBuddy: a Chatbot for personalized learning with MOOCs , 2016, RoCHI.

[17]  S. Sinha,et al.  An intelligent web-based voice chat bot , 2009, IEEE EUROCON 2009.

[18]  Vagelis Hristidis,et al.  Chatbot Technologies and Challenges , 2018, 2018 First International Conference on Artificial Intelligence for Industries (AI4I).

[19]  B. K. Tripathy,et al.  Multi Dimensional Analysis of Learning Experiences over the E-learning Environment for Effective Retrieval of LOs , 2014, 2014 IEEE Sixth International Conference on Technology for Education.

[20]  Tanupriya Choudhury,et al.  Designing and Developing a Chatbot Using Machine Learning , 2018, 2018 International Conference on System Modeling & Advancement in Research Trends (SMART).