BACKGROUND

Field of the invention

[001] The present invention relates to the field of instant messaging, and more specifically to a method and a system for providing automated responses to users in an interactive messaging environment.

Description of the related art

[002] With the advent in technology and easy availability of Internet everywhere, users demand and expect high quality, highly personalized interactions with Internet-based services. Simultaneously, service providers look forward in assisting their customers by giving quick responses to their queries for better customer satisfaction.

[003] Online chatting refers to communication over the Internet that offers a real-time transmission of text messages from a user to a service provider and vice-versa. The chat messages are generally short enabling the service providers to respond quickly. With the advent of smart phones and tabloids, one can chat with others while being on the move. For instance, while booking or planning a trip, a passenger may have some queries. Before making any booking, the passenger may want all their queries to be answered. The queries may be of general in nature or may be repetitive in nature. Further, sometime, while on the move, the passengers may have a lot of complaints with the travel operators or service providers, and they may want to get them resolved instantly.

[004] Also, there can be a time when multiple passengers may ask multiple queries at the same time. In such a case, it is very expensive and cumbersome for a travel operator or a service provider to provide a live help desk to the passengers. In order to solve this problem, various service providers have opted for Artificial Intelligence (Al) engines to provide responses to the queries of the users. However, such Al engines can only provide pre-stored responses, which may not be of any use to the users. Also, such Al engines are not easily integrated on the user devices, thereby making the entire process costly and cumbersome. Further, a professional person is required for the integration of such Al engines, thereby making the integration process a time-consuming process. Also, such Al engines cannot be integrated with any website and mobile application instantly. Furthermore, such Al engines do not process user’s queries multiple times to provide responses with better accuracy and less computing, making the process non-scalable and error prone. Also, the responses provided to the users are in a language in which the responses are pre-stored. Such Al engines do not provide responses in multiple languages. Further, the responses provided are only text-based responses. The Al engines do not provide any audio or video support to the users. Furthermore, Al engines do not help in any kind of revenue generation by allowing users to post advertisement for their propaganda.

OBJECTS OF THE INVENTION

[005] It is an object of the present invention to provide a system and a method that provides virtual chat service and that provides automated responses to user queries, without any human intervention.

[006] It is another object of the present invention to provide a platform that enables the passengers to chat with the travel operators in real-time, regarding their issues and complaints.

[007] It is yet another object of the present invention to provide a platform that supports multiple languages, speech to text features, that is easy to plug in, is highly scalable, and is easy to deploy.

SUMMARY

[008] According to an aspect of the present disclosure, there is provided a method for providing an automated response to a user in an interactive messaging environment. The method includes receiving a user query through a user interface; automatically suggesting a set of pre-defined queries based on the input query using an Artificial Intelligence (Al) engine; enabling the user to select a query from the set of pre-defined queries through the user interface; performing automated analysis on the selected query. The automated analysis includes performing pre-processing functions on the selected query to expand abbreviations, remove misspellings and suggest spellings to generate a first processed query, applying natural language processing (NLP) to understand a meaning and structure of the selected query to generate a second processed query, analyzing the selected query based on historical conversation log data to generate a third processed query, and applying machine learning (ML) and deep learning (DL) on the selected query to generate a fourth processed query. The method further includes applying deep multitasking learning on the first, second, third and fourth processed queries to generate a response, providing the response to the user, and receiving user feedback on the response.

[009] According to another aspect of the present disclosure, there is provided a system for providing an automated response to a user in an interactive messaging environment. The system includes an input module for receiving a user query through a user interface; an auto-suggestion module for automatically suggesting a set of pre-defined queries based on the input query using an Artificial Intelligence (Al) engine, and enabling the user to select a query from the set of pre-defined queries through the user interface; an automated analysis module for performing automated analysis on the selected query, wherein the automated analysis comprises performing pre-processing functions on the selected query to expand abbreviations, remove misspellings and suggest spellings to generate a first processed query; applying natural language processing (NLP) to understand a meaning and structure of the selected query to generate a second processed query, analyzing the selected query based on historical conversation log data to generate a third processed query, and applying machine learning (ML) and deep learning (DL) on the selected query to generate a fourth processed query. The system further includes a deep multitasking learning module for applying deep multitasking learning on the first, second, third and fourth processed queries to generate a response, and providing the response to the user, and a feedback module for receiving user feedback on the response. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] FIG.1 illustrates an integrated interactive messaging platform, in accordance with an embodiment of the present disclosure;

[0011] FIG.2A illustrates a high-level architecture of the interactive messaging platform, in accordance with an embodiment of the present disclosure;

[0012] FIG.2B illustrates the high-level architecture of FIG.2A in detail, in accordance with an embodiment of the present disclosure;

[0013] FIG.3 illustrates the query analysis module and the response generation module in detail, in accordance with an embodiment of the present disclosure;

[0014] FIG.4 illustrates various functional capabilities of the interactive messaging platform, in accordance with an embodiment of the present disclosure;

[0015] FIG.5A illustrates an exemplary screenshot of an application of Indian Railway Catering and Tourism Corporation (IRCTC) that includes a widget of the interactive messaging platform, in accordance with an embodiment of the present disclosure;

[0016] FIG.5B illustrates an exemplary screenshot of a user interface of the interactive messaging platform that appears upon clicking on the widget, in accordance with an embodiment of the present disclosure;

[0017] FIG.5C illustrates an exemplary screenshot of a user interface of the interactive messaging platform that shows the greeting messages sent by personal digital assistant when the user starts a conversation or send a query;

[0018] FIG.5D illustrates an exemplary screenshot of a user interface of the interactive messaging platform that enables the user to provide a feedback regarding their interaction with the platform;

[0019] FIG.6 illustrates an exemplary screenshot of a user interface of the interactive messaging platform that enables a user to chat with a bus operator;

[0020] FIG.7A illustrates various statistical details of the interactive messaging platform, in accordance with an embodiment of the present disclosure; [0021] FIG.7B illustrates benefits of the interactive messaging platform to organizations, in accordance with an embodiment of the present disclosure;

[0022] FIG.7C illustrates benefits of the interactive messaging platform to users, in accordance with an embodiment of the present disclosure;

[0023] FIG.8 is a flowchart illustrating a method for providing an automated response to the user in an interactive messaging environment, in accordance with an embodiment of the present disclosure;

[0024] FIG.9A is a flowchart illustrating a method for providing an automated response to the user using ChatBot Mark-up language (CBML), in accordance with an

embodiment of the present disclosure;

[0025] FIG.9B illustrates exemplary automated responses generated using CBML, in accordance with an embodiment of the present disclosure; and

[0026] FIG.9C is a flowchart illustrating exemplary automated responses generated using CBML, in accordance with an embodiment of the present disclosure.

[0027] The following detailed description of illustrative embodiments is better understood when read in conjunction with the appended drawings. For the purpose of illustrating the present invention, exemplary constructions of the invention are shown in the drawings. However, the invention is not limited to specific methods and instrumentalities disclosed herein. Moreover, those in the art will understand that the drawings are not to scale. Wherever possible, like elements have been indicated by identical numbers.

DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The invention is described in detail below with reference to several embodiments and numerous examples. Such discussion is for purposes of illustration only. Modifications to examples within the spirit and scope of the present invention, set forth in the appended claims, will be readily apparent to one of skill in the art. Terminology used throughout the specification and claims herein is given its ordinary meaning as supplemented by the discussion immediately below. As used in the specification and claims, the singular forms“a”,“an” and“the” include plural references unless the context clearly dictates otherwise. Those with ordinary skill in the art will appreciate that the elements in the Figures are illustrated for simplicity and clarity and are not necessarily drawn to scale.

[0029] FIG.1 illustrates an integrated interactive messaging platform 100, in accordance with an embodiment of the present disclosure.

[0030] The interactive messaging platform 100 includes a user interface 102 (hereinafter also referred to as chatbot 102) executing on a user computing device such as a smart phone, tabloid, laptop and computer, a cognitive Al framework 104, a data store 106, a knowledge base 108, and a dashboard and analytics system 110. In an embodiment of the present disclosure, the user interface 102 may be provided by a server of a service provider to allow a user to initiate a query. The query and corresponding reply may be in the form of a text, audio or video input. The user interface 102 may be integrated with Web, iOS & Android, and with various websites and various mobile applications, thereby allowing users to initiate queries anytime and from anywhere.

[0031] Once the query has been initiated by the user, the user interface 102 may send the query to the cognitive Al framework 104. Upon receiving the query, the cognitive Al framework 104 may analyze the query based on Artificial Intelligence (Al), Machine Learning (ML) and Natural Language Processing (NLP) techniques, to generate a response for the user. The cognitive Al framework 104 then sends the query and the response to the data store 106.

[0032] The data store 106 stores the query and corresponding response for future use. The data store 106 is a repository for storing and managing collections of data in form of files, documents, etc.

[0033] In an embodiment of the present disclosure, the cognitive Al framework 104 sends the query to the knowledge base 108. The knowledge base 108 is a database that stores various questionnaires. Upon receiving the query, the knowledge base 108 checks the various questionnaires to see if the query asked by the user is present in the questionnaires. Upon finding a match, the knowledge base 108 sends a response corresponding to the query to the cognitive Al framework 104. If a match is not found, the knowledge base 108 informs the cognitive Al framework 104.

[0034] In an embodiment of the present disclosure, the cognitive Al framework 104 performs an elastic search using Kibana to provide real time metrics which may help service providers to see a usage pattern of the user and perform cost benefit analysis. The cognitive Al framework 104 may also provide detailed report of each use case - queries asked, responses, accuracy, and feedback.

[0035] The dashboard and analytics system 110 may be built on Elastic search and Kibana and provides real time metrics which may help client to see the usage pattern and cost benefit analysis. The dashboard and analytics system 110 may provide detailed report of each use case - queries asked, responses, accuracy, feedback and more.

[0036] Thus, the platform 100 enables the users to interact with the service providers in real-time, regarding their issues and complaints. The platform 100 provides virtual chat service that provides automated responses to user queries, without any human intervention.

[0037] FIG.2A illustrates a high-level architecture 200 of the interactive messaging platform 100, in accordance with an embodiment of the present disclosure. The architecture 200 includes a user device 202. The user device 202 may include a smart phone, a tabloid, a laptop or a computer. A user initiates a query on an interface provided on the user device 202. On receiving the query, the interface sends the query to a query analysis module 206 through a communication network 204.

[0038] The communication network 204 may be any suitable wired network, wireless network, a combination of these or any other conventional network, without limiting the scope of the present disclosure. Few examples may include a Local Area Network (LAN), wireless LAN connection, an Internet connection, a point-to-point connection, or other network connection and combinations thereof. [0039] The query analysis module 206 receives the query and performs analysis on the query based on Artificial Intelligence (Al), Machine Learning (ML) & Natural Language Processing (NLP) to generate a response. The query analysis module 206 then sends the response to the response generation module 208. In an embodiment of the present disclosure, the query analysis module 206 is in communication with a database 209 that stores one or more queries and corresponding pre-defined responses.

[0040] The response generation module 208 receives the response and displays the response on the user interface of the user device 202. Examples of the response include, but are not limited to static text, dynamic text, live chat, rich text, multimedia (photo, audio, video, maps, pdf, and URL), and API response from internal/external systems.

[0041] The feedback module 210 receives the user feedback in regards to the response provided by the response generation module 208. The feedback module 210 analyzes the feedback to determine how useful the response was to the user. The feedback module 210 then send their analysis to the query analysis module 206. The query analysis module 206 then updates and improves their analysis performed on the query, thereby making the analysis of the query more effective and efficient. The high-level architecture 200 has been further explained in detail with reference to FIG.2B.

[0042] FIG.3 illustrates the query analysis module 206 and the response generation module 208 in detail, in accordance with an embodiment of the present disclosure. The query analysis module 206 includes an auto-suggestion module 301 that is Al based, a pre-processing module 302, a natural language processing (NLP) module 304, a log data analysis module 306, a machine learning (ML) and deep learning module (DL) 308, and a deep multi-tasking learning module 310.

[0043] In operation, the user query is received by the auto-suggestion module 301 , that analyzes the query by breaking it into a set of keywords. Based on the keywords, the auto-suggestion module 301 suggest a set of pre-defined queries. The set of suggested queries is hereinafter referred to as a first reply. If a suggested query matches with an already existing query stored in the data store 106 or the knowledge base 108 (as described in FIG. 1 ), the Al auto suggestion module 301 retrieves a response corresponding to the similar query and directly provides the response to the response generation module 208.

[0044] On the other hand, if none of the suggested queries are found in the data store 106, or the knowledge base 108, the user query is sent to the pre-processing module 302, the natural language processing module (NLP) module 304, the log data analysis module 308, and the ML and DL module 310. The pre-processing module 302 analyzes the query using Artificial Intelligence mark-up language (AIML) to generate a first processed query, hereinafter also referred to as second reply. The AIML is a text-based scripting language whose pattern syntax is a simple pattern language, substantially less complex than regular expression and as such less than level 3 in Chomsky hierarchy. The pre-processing module 302 performs a set of pre-processing functions on the query to expand abbreviations, remove misspellings, suggest corrections, etc. The pre processing module 302 then sends the second reply to the deep multitasking learning module 310.

[0045] The NLP module 304 applies algorithms on the user query to understand the meaning and structure of the set of keywords of the query to generate a third reply. . The NLP module 304 uses techniques such as syntactic and semantic analysis. The syntactic analysis includes, but not limited to, parsing (grammatical analysis of sentence), role labelling and understanding discourse, and tokenization (splitting the sentence into words). The semantic analysis includes, but not limited to, understanding deeper meaning, context analysis and disambiguation analysis. The NLP module 304 then sends the third reply to the deep multitasking learning module 310.

[0046] The log data analysis module 306 analyzes the user query based on historical chat log data (transcripts) to generate a fourth reply, without the need for any human labeling. The log data analysis module 306 builds a query/answer (Q/A) system, where each sentence in the conversation is both an answer to a previous sentence, and a question to the next sentence. Hence, each sentence appears in two Q/A pairs, thereby allowing the log data analysis module 306 to easily process the user query. The log data analysis module 306 then sends the fourth reply to the deep multitasking learning module 310.

[0047] The ML and DL module 308 receives the user query and a feedback from the feedback module 210. Based on the query and the feedback, the ML and DL module 308 uses deep learning to generate a fifth reply, and to upgrade its responses. The ML and DL module 308 then sends the fifth reply to the deep multitasking learning module 310.

[0048] The deep multitasking learning module 310 receives and analyzes the first through fifth replies, to generate a response. The deep multitasking learning module 312 applies human kind of learning to each of the replies, like human brain multitasks to focus on each word, then each sentence and then previous sentences to drive deeper understanding. Primarily, the deep multitasking learning module 310 makes sure that each word, context, current sentence and also the learning from other modules 304 till 310 are consolidated well to get deeper and better learning. The deep multitasking learning module 310 thus generates the response based on the learning and sends the response to the response generation module 208.

[0049] The response generation module 208 include a standard reply module 312 for generating a standard reply, if the user query is not being understood. Examples of the standard reply include“Rephrase your query, choose one of the given options, and ‘contact call center’.

[0050] The response generation module 208 further includes a response to query module 314 for generating an appropriate response to the user, if the query is being understood.

[0051] The response generation module 208 further includes a live chatting module 316 to initiate a live chat between the user and a customer care representative if the user query is not being understood, or further assistance is needed to the user. [0052] The feedback module 210 receives feedback from the user regarding the responses received and live chats, and enable automatic learning and updating of the interactive messaging platform 100.

[0053] FIG.4 illustrates various functional capabilities of the interactive messaging platform 100, in accordance with an embodiment of the present disclosure.

[0054] In an embodiment of the present disclosure, the interactive messaging platform 100 is available on mobile applications and websites. The proposed interactive messaging platform 100 works seamlessly on mobile applications such as Android and iOS, web browsers such as Chrome, Firefox and Internet Explorer, and social media channels.

[0055] In another embodiment of the present disclosure, the interactive messaging platform 100 is configured to handle different greeting notes for the users like Hi, Hello, how are you?

[0056] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to enable communication in multiple languages such as English and Hindi for the customer queries.

[0057] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to provide knowledge based support by enabling integration of the existing questionnaires to support user queries.

[0058] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to allow users to have a voice-based/video-based system where in user can talk and ask their queries

[0059] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to handle any typographical errors by the users and help them with the correct answers [0060] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to intelligently handle queries even if users are asking a word or a sentence.

[0061] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to capture user feedback.

[0062] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to show the historical conversations of the user(s).

[0063] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to allow users to talk to agents in case they want to receive more information or not satisfied with the answers provided.

[0064] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to have Video Bot features.

[0065] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to auto-suggest questions based on what users are asking.

[0066] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to allow advertisements in case the customers want to display advertisements of their products or new offers.

[0067] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to allow integration with different partners/services.

[0068] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to allow customers to view Chatbot usage, understand what kind of questions are being asked.

[0069] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to have the capability to answer user queries based on the user(s) intent and derive the entity.

[0070] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to have the capability to handle exceptions.

[0071] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to possess the conversational capabilities. [0072] In yet another embodiment of the present disclosure, the interactive messaging platform 100 is configured to integrate with different API’s existing for the clients.

[0073] In various embodiments of the present disclosure, the interactive messaging platform 100 can be used by a group of passengers travelling by a mode of transport such as air, train, and road. Each passenger may be provided with an option to download an instant messaging application of the platform 100 on their respective computing devices. The instant messaging application provides a social platform to the users to get connected to the travel operators, and register their complaints and issues. It has group chat as well as private chat options with privacy control & many other features. The platform 100 enables the tourists to connect with each other as well as with authorities and the service providers. The platform 100 may make a lot of difference to the travellers to seek help from each other especially in case of an urgency and if travelling alone.

[0074] The platform 100 connects the bus operators with the passengers, and establish a smooth flow of real-time communications. It enables bus operators with the latest chat-based technology to serve the passengers quickly and satisfactory. Further, it provides auto-replies to the passengers and reduces operational cost for the operators. For travel operators, the platform 100 reduces manpower cost and reduce hassle of replying to phone calls and answer to emails. It is convenient for passengers, provides quick responses, there is no hold-time, and allows multitasking.

[0075] The interactive messaging platform 100 provides a single universal and integrated chat-based service desk in which the user can select any service provider like bus operator, car service center, manufacturer, etc, and start messaging with the helpdesk/service desk staff. The users don’t need to know the phone number of the service provider and also does not need to install the applications of individual service providers.

[0076] The interactive messaging platform 100 implements Artificial Intelligence (Al) and Machine Learning (ML), to immediately provide quick replies and most relevant information to passengers based on available information. With client specific branding, interactive messaging platform 100 may be provided as a widget in the user’s website and mobile application.

[0077] FIG.5A illustrates an exemplary screenshot of an application 502 of Indian Railway Catering and Tourism Corporation (IRCTC) that includes a widget 504 of the interactive messaging platform 100, in accordance with an embodiment of the present disclosure.

[0078] FIG.5B illustrates an exemplary screenshot of a user interface 506 of the interactive messaging platform 100 that appears upon clicking on the widget 504, in accordance with an embodiment of the present disclosure. The user interface 506 enables the user to input a query, and is configured to automatically provide a response to the user query without manual intervention.

[0079] FIG.5C illustrates an exemplary screenshot of a user interface 508 of the interactive messaging platform 100 that shows the greeting messages sent by personal digital assistant when the user starts a conversation or send a query.

[0080] FIG.5D illustrates an exemplary screenshot of a user interface 512 of the interactive messaging platform 100 that enables the user to provide a feedback regarding their interaction with the platform 100. The feedback is then used to continuously update and improvise the features of the platform 100.

[0081] FIG.6 illustrates an exemplary screenshot of a user interface 602 of the interactive messaging platform 100 that enables a user to chat with a bus operator, and also another user interface 604 that enables the user to do live chatting with an available customer representative.

[0082] FIG.7A illustrates various statistics of the interactive messaging platform 100, in accordance with an embodiment of the present disclosure.

[0083] The interactive messaging platform 100, hereinafter also referred to as ChatBot is a conversational Al platform that improve sales, save cost by 33%, reduce support activities (70%) and improve customer/employee engagement and satisfaction. The CoRover ChatBot is highly accurate, has excellent user’s feedback, provides fast response, and there is no cost to operate the same.

[0084] In an example, IRCTC apparently saves INR 90 Lakhs Rupees a month by using the CoRover Powered chatbot and also earns INR 25 Lakhs by their share of advertisement revenue on chatbot.

[0085] In another example, for KSRTC, passengers’ phone calls reduced significantly after the launch of CoRover powered ChatBot as a service.

[0086] Chatbot has flexible attribute, as it can be quite easily be used in any industry, and is relatively easy to switch. The ChatBot can be easily trained by giving the right conversation structure and flow to switch its current field or industry.

[0087] ChatBot provides“Multi-language” and“Speech to Text” features to provide round the clock response to customer’s queries. Further, a personal assistance experience is provided to the users using ChatBot and LiveChat.

[0088] In an embodiment of the present disclosure, Enterprise level chatbot as a service (CaaS) can be integrated with any website and mobile application in 10 minutes. It is easy to plug-in, highly scalable, secure, light-weight, reliable, platform agnostic and easy to integrate with web and mobile.

[0089] In an embodiment of the present disclosure, it is very easy to train the interactive messaging platform 100 using Chatbot Markup Language (CBML).

[0090] In an embodiment of the present disclosure, Chatbot processes user’s queries in various layers to provide responses with better accuracy and less computing.

[0091] In an embodiment of the present disclosure, Enterprise level chatbot is ready to be used in multiple languages (Vernacular and Foreign Languages) without training the ML models in multi-languages. [0092] FIG.7B illustrates benefits of the interactive messaging platform 100 to the organizations, in accordance with an embodiment of the present disclosure. The benefits include:

1. Saving costing while catering to five passengers at a time

2. Getting rid of Toll-free numbers

3. Mobile and web-based messaging terminals

4. Enhancing customer loyalty

5. Seeking feedback and respond

6. Monetization: Up-sell or Cross-sell

7. Sending notifications and important information to passengers

8. Revenue sharing model for bus, hotel and taxi booking

9. Sending promotional offers to the passengers

10. In-house dedicated customer service tea on request

1 1. Virtual chat-bot for handling queries immediately

12. Reducing cost in Customer Support function and increasing customer satisfaction

13. Very small integration effort to be carried to integrate application with service provider

14. Reducing manpower cost and reduce hassle of replying phone calls and answer emails

[0093] FIG.7C illustrates benefits of the interactive messaging platform 100 to the users, in accordance with an embodiment of the present disclosure. The benefits include:

1. Communication with bus operators for any issues, complaints, feedback, support

2. Pressing of panic button and getting immediate help in case of emergency

3. No hold time and getting immediate response

4. Getting important updates, and notifications from bus operators

5. Cheaper and convenient bus, hotel and taxi booking

6. Getting offers and discounts [0094] FIG.8 is a flowchart illustrating a method 800 for providing an automated response to the user in an interactive messaging environment, in accordance with an embodiment of the present disclosure.

[0095] At step 802, a user query is received through a user interface. In an embodiment of the present disclosure, the query includes text, audio and video input.

[0096] At step 804, a set of pre-defined queries is suggested based on the input query using an Artificial Intelligence (Al) engine.

[0097] At step 806, the user is enabled to select a query from the set of pre-defined queries through the user interface.

[0098] At step 808, automated analysis is being performed on the selected query. The automated analysis comprises performing pre-processing functions on the selected query to expand abbreviations, remove misspellings and suggest spellings to generate a first processed query, applying natural language processing (NLP) to understand a meaning and structure of the selected query to generate a second processed query, analyzing the selected query based on historical conversation log data to generate a third processed query, and applying machine learning (ML) and deep learning (DL) on the selected query to generate a fourth processed query. In an embodiment of the present disclosure, the applying the NLP includes applying syntactic and semantic analysis on the selected query.

[0099] At step 810, deep multitasking learning is applied on the first, second, third and fourth processed queries to generate a response.

[00100] At step 812, the response is provided to the user. In an embodiment of the present disclosure, the response is provided to the user in a language selected by the user. In another embodiment of the present disclosure, the response may include a standard pre-defined reply, when the user query is not understandable. In yet another embodiment of the present disclosure, the response may include an appropriate answer when the user query is understandable. In yet another embodiment of the present disclosure, the response provided to the user may include static text, dynamic text, live chat, rich text, multimedia response. In yet another embodiment of the present disclosure, the response includes facilitating the user to interact with another user in real-time.

[00101] At step 814, user feedback is received on the response. In an embodiment of the present disclosure, the ML, DL, deep multitasking learning and user feedback is used to update a database of queries and corresponding responses.

[00102] FIG.9A is a flowchart illustrating a method for providing an automated response to the user using ChatBot Mark-up language (CBML), in accordance with an embodiment of the present disclosure.

[00103] At step 902, a user query is received. At step 904, user response is provided. At step 906, it is checked if CBML is present. At step 908, user response is provided if CBML is not present. If CBML is present, then verbose response 910a is provided, and options 91 Ob-91 Od are provided. If CBML is present, further linked responses 912a-912c are provided to the user.

[00104] FIG.9B illustrates exemplary automated responses 914 generated using CBML, in accordance with an embodiment of the present disclosure. When the user query is“I want to buy pizza today”, the intent is to buy, and entity keeps on changing based on user choices, and accordingly, multiple automated user responses may be provided.

[00105] FIG.9C is a flowchart illustrating exemplary automated responses generated using CBML, in accordance with an embodiment of the present disclosure.

[00106] Various embodiments of the present disclosure provide an Artificial Intelligence (Al) based IVR which automatically provides responses and act on users queries/queries on telephone call, without pressing any phone keys. For example, checking account balance, booking appointments. The ChatBot as a Service (CaaS)® has Video, Voice, Text Chatbot beased on Artificial Intelligence (Al), Machine Learning (ML) & Natural Language Processing (NLP), for enterprises. Chatbot is very easy to be trained using Chatbot Markup Language(CBML), and can be integrated with a website.

[00107] While the invention has been described in detail, modifications within the spirit and scope of the invention will be readily apparent to those of skill in the art. Such modifications are also to be considered as part of the present invention. In view of the foregoing discussion, relevant knowledge in the art and references or information discussed above in connection with the Background of the Invention, the inventions of which are all incorporated herein by reference, further description is deemed

unnecessary. In addition, it should be understood that aspects of the invention and portions of various embodiments may be combined or interchanged either in whole or in part. Furthermore, those of ordinary skill in the art will appreciate that the foregoing description is by way of example only, and is not intended to limit the invention.