Method and electronic device for generating an adaptive message

Abstract

Disclosed herein is a method comprising identifying one or more messages from a real-time upstream of the one or more messages from chatroom including one or more users and at least one engagement bot; determining at least one of a message flow rate, an emotion drift of the chatroom, or interaction of one or more users in the chatroom from the obtained real-time upstream of one or more messages; identifying one or more user profiles corresponding to the one or more users from the real-time upstream of one or more messages; determining whether to perform a proactive message initiation or a reactive message initiation; generating a prompt, based on the determination to perform the proactive message initiation or the reactive message initiation; and generating the adaptive message for the chatroom based on at least one language model based on the generated prompt.

Description

METHOD AND ELECTRONIC DEVICE FOR GENERATING AN ADAPTIVE MESSAGE

[0001] The present disclosure relates to the generation of contextual content, and more particularly, to a method and an electronic device for generating an adaptive message for a chatroom.

[0002] The information in this section merely provides background information related to the present disclosure and may not constitute prior art(s) for the present disclosure.

[0003] An open conversation representing a chatting environment, commonly known as chatrooms are a platform where multiple users accumulate for the transfer of thoughts. Further, it is noticed that often the existing chatrooms suffer from a situation where people either don't try to initiate chat or may quit the chatroom if initially accumulated users' activity or interaction is zero or very low. Fig. 1 illustrates a schematic block diagram depicting an environment 100 of a chatroom 102, in accordance with the related art. The chatroom is established at time t=0 Minutes with zero messages in the chatroom. As time progressed from time t=1 Minute to t=3 Minutes one or more users 104 joins the chatroom 102. The user 104a joins the chatroom 102 at t=1 Minute and drops zero messages. The user 104b joins the chatroom 102 at t=2 Minutes and drops zero messages. The user 104c joins the chatroom 102 at t=3 Minutes and drops zero messages. The chatroom 102 at time t=4 Minutes shows zero messages indicating there has been no activity or interaction between the one or more users 104 that joined the chatroom 102. Eventually, the one or more users 104 may lose interest and may plan to quit the chatroom 102. Accordingly, the user 104a quits the chatroom 102 at t=4 Minutes, the user 104b quits the chatroom 102 at t=5 Minutes, and the user 104c quits the chatroom 102 at t=5 Minutes.

[0004] Further, it is noticed that such chatting platforms often experience a good message exchange in case of specific gaming events wherein the one or more users 104 already have a cognitive bias or enthusiasm about the event. Whereas, in most of the other cases, the one or more users 104 don't tend to start a message exchange until provoked or triggered by one or more messages of any other user 104a-104c of the chatroom 102.

[0005] Further, some of the chatroom 102 may initiate chatbots to generate messages. However, the messages generated by the chatbot may not be useful due to their irrelevancy and inappropriate context which may not be eye catchy to the one or more users 104. For example, the chatbot may be randomly initiating messages in the chatroom irrespective of whether people are interacting or not. Further, the messages initiated by the chatbot may not be relevant to the one or more users 104 and may be considered as spam messages, thereby often ignored by the one or more users 104 in the chatroom.

[0006] Therefore, there exists a need to have an improved solution to overcome the above-mentioned problems associated with the generation of messages in a chatroom.

[0007] This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention. This summary is neither intended to identify essential inventive concepts of the invention nor is it intended for determining the scope of the invention.

[0008] According to an embodiment of the present disclosure, a method is disclosed. The method includes identifying one or more messages from a real-time upstream of the one or more messages from chatroom including one or more users and at least one engagement bot representing a virtual user that interacts with the one or more users, wherein the real-time upstream indicates an inflow of the one or more messages sent by the one or more users in the chatroom. The method includes determining at least one of a message flow rate, an emotion drift of the chatroom , or interaction of one or more users in the chatroom from the obtained real-time upstream of one or more messages. The method includes identifying one or more user profiles corresponding to the one or more users from the obtained real-time upstream of one or more messages. The method includes determining whether to perform a proactive message initiation or a reactive message initiation based on the determined at least one of the message flow rate, the emotion drift of the chatroom, or the user profile of the one or more users, The proactive message initiation indicates initiating a message by the at least one engagement bot in the chatroom. The reactive message initiation indicates initiating a reply by the at least one engagement bot to the one or more messages obtained from the real-time upstream. The method includes generating a prompt, based on the determination to perform the proactive message initiation or the reactive message initiation. The method includes generating the adaptive message for the chatroom based on at least one language model based on the generated prompt.

[0009] According to an embodiment of the present disclosure, an electronic device comprising at least one processor comprising processing circuitry; and at least one memory including one or more instructions is disclosed. The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device to identify one or more messages from a real-time upstream of the one or more messages from chatroom including one or more users and at least one engagement bot representing a virtual user that interacts with the one or more users, wherein the real-time upstream indicates an inflow of the one or more messages sent by the one or more users in the chatroom. The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device to determine at least one of a message flow rate, an emotion drift of the chatroom, or interaction of one or more users in the chatroom from the obtained real-time upstream of one or more messages. The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device to identify one or more user profiles corresponding to the one or more users from the obtained real-time upstream of one or more messages. The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device to determine whether to perform a proactive message initiation or a reactive message initiation based on the determined at least one of the message flow rate, the emotion drift of the chatroom, or the user profile of the one or more users. The proactive message initiation indicates initiating a message by the at least one engagement bot in the chatroom. The reactive message initiation indicates initiating a reply by the at least one engagement bot to the one or more messages obtained from the real-time upstream. The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device to generate a prompt, based on the determination to perform the proactive message initiation or the reactive message initiation. The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device to generate the adaptive message for the chatroom based on at least one language model based on the generated prompt.

[0010] According to an embodiment of the present disclosure, a computer-readable medium containing instructions, wherein the instructions, when executed by at least one processor, cause the electronic device to perform the method disclosed herein is disclosed. To further clarify the advantages and features of the present disclosure, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which are illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail in the accompanying drawings.

[0011] These and other features, aspects, and advantages of the present disclosure will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein:

[0012] FIG. 1 illustrates a schematic block diagram depicting an environment of a chatroom, in accordance with the related art;

[0013] FIG. 2 illustrates a schematic block diagram depicting an environment for generating an adaptive message for the chatroom, in accordance with an embodiment of the present disclosure;

[0014] FIG. 3 illustrates a schematic block diagram depicting an exemplary system for generating the adaptive message for the chatroom, in accordance with an embodiment of the present disclosure;

[0015] FIG. 4 illustrates a schematic block diagram depicting the one or more modules, in accordance with an embodiment of the present disclosure;

[0016] FIG. 5 illustrates a block diagram depicting the bootstrapping module, in accordance with an embodiment of the present disclosure;

[0017] FIG. 6 illustrates a block diagram depicting the orchestration module, in accordance with an embodiment of the present disclosure;

[0018] FIG. 7 illustrates bifurcation of the real-time upstream into a plurality of streams for further processing, in accordance with an embodiment of the present disclosure.

[0019] FIG. 8 illustrates a graphical representation of the determination of the message flow rate using the sliding window aggregation operation, in accordance with an embodiment of the present disclosure;

[0020] FIG. 9 illustrates a functional block diagram depicting the determination of the emotion drift of the chatroom, in accordance with an embodiment of the present disclosure;

[0021] FIG. 10 illustrates a functional block diagram depicting creation of vocabulary vector, in accordance with an embodiment of the present disclosure;

[0022] FIG. 11 illustrates a block diagram depicting the decision module, in accordance with an embodiment of the present disclosure;

[0023] FIG. 12 illustrates a block diagram depicting the message generation module, in accordance with an embodiment of the present disclosure;

[0024] FIG. 13 illustrates a functional block diagram depicting language model selection by the message generation module, in accordance with an embodiment of the present disclosure;

[0025] FIG. 14 illustrates a functional block diagram depicting the generation of the prompt by the message generation module, in accordance with an embodiment of the present disclosure;

[0026] FIG. 15 illustrates a block diagram depicting the publishing module, in accordance with an embodiment of the present disclosure;

[0027] FIG. 16 illustrates a flowchart depicting an exemplary method for generating an adaptive message for a chatroom, in accordance with an embodiment of the present disclosure.

[0028] Further, skilled artisans will appreciate that elements in the drawings are illustrated for simplicity and may not have necessarily been drawn to scale. For example, the flow charts illustrate the method in terms of the most prominent steps involved to help improve understanding of aspects of the present disclosure. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the drawings with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

[0029] For the purpose of promoting an understanding of the principles of the invention, reference will now be made to the various embodiments and specific language will be used to describe the same. It should be understood at the outset that although illustrative implementations of the embodiments of the present disclosure are illustrated below, the present invention may be implemented using any number of techniques, whether currently known or in existence. The present disclosure is not necessarily limited to the illustrative implementations, drawings, and techniques illustrated below, including the exemplary design and implementation illustrated and described herein, but may be modified within the scope of the present disclosure.

[0030] It will be understood by those skilled in the art that the foregoing general description and the following detailed description are explanatory of the invention and are not intended to be restrictive thereof.

[0031] Reference throughout this specification to "an aspect", "another aspect" or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment.

[0032] It is to be understood that as used herein, terms such as, "includes," "comprises," "has," etc. are intended to mean that the one or more features or elements listed are within the element being defined, but the element is not necessarily limited to the listed features and elements, and that additional features and elements may be within the meaning of the element being defined. In contrast, terms such as, "consisting of" are intended to exclude features and elements that have not been listed.

[0033] The embodiments herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting embodiments that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted to not unnecessarily obscure the embodiments herein. Also, the various embodiments described herein are not necessarily mutually exclusive, as some embodiments can be combined with one or more other embodiments to form new embodiments. The term "or" as used herein, refers to a non-exclusive or unless otherwise indicated. The examples used herein are intended merely to facilitate an understanding of ways in which the embodiments herein can be practiced and to further enable those skilled in the art to practice the embodiments herein. Accordingly, the examples should not be construed as limiting the scope of the embodiments herein.

[0034] As is traditional in the field, embodiments may be described and illustrated in terms of blocks that carry out a described function or functions. These blocks, which may be referred to herein as units or modules or the like, are physically implemented by analog or digital circuits such as logic gates, integrated circuits, microprocessors, microcontrollers, memory circuits, passive electronic components, active electronic components, optical components, hardwired circuits, or the like, and may optionally be driven by firmware and software. The circuits may, for example, be embodied in one or more semiconductor chips, or on substrate supports such as printed circuit boards and the like. The circuits constituting a block may be implemented by dedicated hardware, by a processor (e.g., one or more programmed microprocessors and associated circuitry), or by a combination of dedicated hardware to perform some functions of the block and a processor to perform other functions of the block. Each block of the embodiments may be physically separated into two or more interacting and discrete blocks without departing from the scope of the invention. Likewise, the blocks of the embodiments may be physically combined into more complex blocks without departing from the scope of the invention. It should be appreciated that the blocks in each flowchart and combinations of the flowcharts may be performed by one or more computer programs which include computer-executable instructions. The entirety of the one or more computer programs may be stored in a single memory or the one or more computer programs may be divided with different portions stored in different multiple memories.

[0035] Any of the functions or operations described herein can be processed by one processor or a combination of processors. The one processor or the combination of processors is circuitry performing processing and includes circuitry like an application processor (AP), a communication processor (CP), a graphical processing unit (GPU), a neural processing unit (NPU), a microprocessor unit (MPU), a system on chip (SoC), an IC, or the like.

[0036] The processor may include various processing circuitry and / or multiple processors.　 For example, as used herein, including the claims, the term "processor" may include various processing circuitry, including at least one processor, wherein one or more of at least one processor, individually and / or collectively in a distributed manner, may be configured to perform various functions described herein. As used herein, when "a processor", "at least one processor", and "one or more processors" are described as being configured to perform numerous functions, these terms cover situations, for example and without limitation, in which one processor performs some of recited functions and another processor(s) performs other of recited functions, and also situations in which a single processor may perform all recited functions. Additionally, the at least one processor may include a combination of processors performing various of the recited / disclosed functions, e.g., in a distributed manner.　 At least one processor may execute program instructions to achieve or perform various functions.

[0037] The accompanying drawings are used to help easily understand various technical features and it should be understood that the embodiments presented herein are not limited by the accompanying drawings. As such, the present disclosure should be construed to extend to any alterations, equivalents, and substitutes in addition to those which are particularly set out in the accompanying drawings. Although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are generally only used to distinguish one element from another.

[0038] The present disclosure delineates an improved electronic device and method for generating an adaptive message for a chatroom.

[0039] FIG. 2 illustrates a schematic block diagram depicting an environment 200 for generating an adaptive message for the chatroom, in accordance with an embodiment of the present disclosure.

[0040] The environment may include an electronic device 202 for generating an adaptive message for the chatroom 204. The electronic device 202 may establish the chatroom 204. The electronic device 202 may obtain (e.g. receive) a real-time upstream 206 of a flow of one or more messages from the chatroom 204 for real time analysis of the chatroom 204. In an embodiment, a real-time upstream 206 may be continuous. At the time of establishment of the chatroom 204, i.e., at time t=0 Minutes, there may be zero messages in the chatroom. In an embodiment, one or more users 208 may join the chatroom 204, for example, a user 208a may join at time t=1 Minute, and may observe zero messages with a total message count m=0 messages in the chatroom 204, and a user 208b may join at time t=2 Minutes, and may also observe zero messages. In an example, the user 208a and user 208b may also not initiate any message into the chatroom 204.

[0041] The electronic device 202, may analyze the real-time upstream 206 at every time interval. Based on analyzing the real-time upstream 206 at every time interval, the electronic device 202 may detect of zero messages in the chatroom 204 and the presence of one or more users 208. The electronic device 202 may engage at least one engagement bot 210 to join the chatroom 204. The at least one engagement bot 210 may indicate a virtual user (e.g. chatbot) implemented by the electronic device 202. The at least one engagement bot 210 may indicate an automated participant in the chatroom 204, designed to enhance engagement, interaction, and information flow within a chatroom. As shown in FIG. 2, in an example scenario, at time t=3 Minutes (e.g. defined time, predetermined time) the electronic device 202 may generate two (e.g. predetermined number of, random number of, a plurality of) adaptive messages and publish the generated adaptive message into the chatroom 204 via the at least one engagement bot 210, raising the total message count of the chatroom 204 to m=2 (e.g. predetermined number of, random number of, a plurality of) messages. The electronic device 202 ensures that the generated adaptive messages are relevant and appropriate for the context, for instance, of when to generate messages, when to stop sending messages, and what kind of messages to be produced.

[0042] Accordingly, the one or more users 208 may be able to connect to the context of the generated adaptive message and may engage in a conversation by replying to the messages published by the at least one engagement bot 210. For example, at time t=4 Minutes, the user 208b may drop three messages, raising the total message count of the chatroom 204 to m=5 messages. In an embodiment, the user 208a may also relate to the context of the generated adaptive messages published by the at least one engagement bot 210, and with the messages dropped by the user 208b, thereby the user 208a may generate an interest to engage with the conversations in the chatroom 204. Accordingly, at time t=5 Minutes, the user 208a may drop three messages, raising the total message count of the chatroom 204 to m=8 messages.

[0043] The electronic device 202 may further analyze the real-time upstream 206 at every interval to check (e.g. identify, determine) if there is sufficient exchange of conversation in the chatroom 204 in response to every new message. In an embodiment, the electronic device 202 may identify that there isn't sufficient exchange of conversation in the chatroom 204. Accordingly, the electronic device 202 may decide to continue publishing the generated adaptive message into the chatroom 204 via the at least one engagement bot 210. As shown in FIG. 2, in an example scenario, at time t=6 Minutes the electronic device 202 may generate two adaptive messages and publish the generated adaptive message into the chatroom 204 via the at least one engagement bot 210, raising the total message count of the chatroom 204 to m=10 messages.

[0044] Accordingly, the one or more users 208, on seeing the relatable messages, may gain interest in the chatroom 204 and may get inspired to engage in the conversations. For example, at time t=7 Minutes, the user 208a may drop two messages, raising the total message count of the chatroom 204 to m=12 messages. In a similar example, at time t=8 Minutes, the user 208b may engage in the conversation and drop three messages, raising the total message count of the chatroom 204 to m=15 messages. Therefore, the one or more users 208 may choose to retain their presence in the chatroom 204, thereby engaging and maintaining the conversation.

[0045] Further, the purpose of the electronic device 202 is not to generate adaptive messages all the time, but only when adaptive message generation is actually required. For example, from time t=8 Minutes to time t=9 Minutes, the electronic device 202 may determine that there has been an increase in the rate of flow of one or more messages resulting in the total message count of m=1500 messages in the chatroom 204 with one or more users 208 (e.g. the user 208a, the user 208b, ... the user 208n). This increase in the rate of flow of one or more messages beyond a predetermined (e.g. defined) threshold level may indicate that sufficient message exchange has been established in the chatroom 204. Accordingly, the electronic device 202 may decide (e.g. determine) not to generate any more adaptive messages until a decline in the rate of flow of one or more messages in a successive time duration is determined by the electronic device 202. In an embodiment, the electronic device may stop to generate any more adaptive messages until a decline in the rate of flow of one or more messages in a successive time duration is determined by the electronic device 202.

[0046] Therefore, the purpose of the electronic device 202 is not to generate the adaptive messages all the time. The electronic device 202 initiates the generation of the adaptive messages only when message generation is required. Accordingly, the electronic device 202 may provide enhanced user experience, engagement, and retention of the one or more users 208 in the chatroom 204.

[0047] FIG. 3 illustrates a schematic block diagram depicting an exemplary electronic device 202 for generating the adaptive message for the chatroom 204, in accordance with an embodiment of the present disclosure.

[0048] The electronic device 202 may include, but is not limited to, one or more processors 302, a memory 304 and I / O interface 306. The memory 304 may include one or more modules 308 and data 310. The memory 304 may be coupled to the one or more processors 302.

[0049] As a non-limiting example, the one or more processors 302 may be a single processing unit or several units, all of which could include multiple computing units. The one or more processors 302 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and / or any devices that manipulate signals based on operational instructions. Among other capabilities, the one or more processors 302 are adapted to fetch and execute computer-readable instructions and data stored in the memory 304. Among other capabilities, the one or more processors 302 may be configured to fetch and execute computer-readable instructions and data stored in the memory 304. The one or more processors 302 include one or a plurality of processors. The plurality of processors may be further implemented as a general-purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, a graphics-only processing unit, such as a graphics processing unit (GPU), a visual processing unit (VPU), and / or an AI-dedicated processor such as a neural processing unit (NPU). The plurality of processors controls the processing of the input data in accordance with a predefined operating rule or an artificial intelligence (AI) model stored in the memory 304. The predefined operating rule or the AI model is provided through training or learning.

[0050] The one or more processors 302 may be disposed in communication with one or more input / output (I / O) devices via an Input / Output (I / O) interface 306. The I / O interface 306 may employ communication code-division multiple access (CDMA), high-speed packet access (HSPA+), global system for mobile communications (GSM), long-term evolution (LTE), WiMax, and the like, etc. In another embodiment of the present disclosure, the I / O interface 306 employs ethernet, industrial wireless Local Area Network (LAN), Process Field Bus (PROFIBUS), Actuator Sensor (AS) Interface, and the like.

[0051] The memory 304 is configured to store instructions executable by the one or more processors 302. The memory may include one or more instructions executable by the one or more processors 302. In one embodiment, the memory 304 communicates via a bus within the electronic device 202. The memory 304 includes but is not limited to, a non-transitory computer-readable storage media, such as various types of volatile and non-volatile storage media including, but not limited to, random access memory, read-only memory, programmable read-only memory, electrically programmable read-only memory, electrically erasable read-only memory, flash memory, magnetic tape or disk, optical media and the like. In one example, the memory includes a cache or random-access memory (RAM) for the one or more processors 302. In an embodiment, the memory 304 is separate from the one or more processors 302 such as a cache memory of a processor, the system memory, or other memory. The memory 304 may be an external storage device or a database for storing data. The memory 304 is operable to store instructions executable by the one or more processors 302. The functions, acts, or tasks illustrated in the figures or described are performed by the programmed processor for executing the instructions stored in the memory 304. The functions, acts, or tasks are independent of the particular type of instruction set, storage media, processor, or processing strategy and may be performed by software, hardware, integrated circuits, firmware, micro-code, and the like, operating alone or in combination. Likewise, processing strategies include multiprocessing, multitasking, parallel processing, and the like.

[0052] The one or more modules 308, amongst other things, include routines, programs, objects, components, data structures, etc., which perform particular tasks or implement data types. The one or more modules 308 included in the electronic device 202 of FIG. 3 are configurations categorized by function or purpose. The one or more modules 308 (e.g. a bootstrapping module 312, an orchestration module 314, a decision module 316, a message generation module 318, and a publishing module 320) of the memory 304 of FIG. 3 may be software configurations implemented by the processor 302 of the electronic device 202 executing programs stored in the memory 304, which will be described later with reference to FIG. 4 to FIG. 16, or they may be hypothetical configurations for which no actual matching hardware device exists. In an embodiment, the operations that the processor 302 of the electronic device 202 performs by executing programs or instructions stored in the memory 304 may be categorized into a plurality of groups by function or purpose, and the entities that perform the actions included in each of the categorized groups may be represented by the one or more modules 308 of FIG. 3. Thus, the actions described as being performed by the one or more modules 308 of the electronic device 202 illustrated in FIG. 3 can be viewed as actually being performed by the processor 302 of the electronic device 202 by executing programs or instructions stored in the memory 304.

[0053] While one electronic device 202 is illustrated in FIG. 2 as including all modules 312, 314, 316, 318 and 320 at least some of the modules 312, 314, 316, 318 and 320 may be implemented to be included in separate devices, or any one module may be implemented to be included in another module, without limitation. As such, the modules 312, 314, 316, 318 and 320 included in the electronic device 202 according to one embodiment of the present disclosure may be hardware configurations or software configurations, and may be implemented in the form of various electronic devices (e.g., one electronic device or a combination of two or more electronic devices).In an embodiment of the present disclosure, the one or more modules 308 may be machine-readable instructions (software) which, when executed by a processor / processing unit 302, perform any of the described functionalities.

[0054] In an embodiment, the one or more modules 308 may include a bootstrapping module 312, an orchestration module 314, a decision module 316, a message generation module 318, and a publishing module 320. The bootstrapping module 312, the orchestration module 314, the decision module 316, the message generation module 318, and the publishing module 320 may be in communication with each other. The data 310 serves, amongst other things, as a repository for storing data processed, received, and generated by one or more of the one or more modules 308. In an embodiment, the plurality of modules 308 may be configured to perform various operations or steps that may be discussed and explained in detail in conjunction with Fig. 16.

[0055] FIG. 4 illustrates a schematic block diagram depicting the one or more modules 308, in accordance with an embodiment of the present disclosure. The one or more modules 308 may include the one or more instructions that may be executed to cause the electronic device 202, in particular, the processor 302 of the electronic device 202, to execute the one or more instructions.

[0056] The bootstrapping module 312 may be configured to establish the chatroom 204 to allow one or more users 208 and at least one engagement bot 210 to join and interact in the chatroom, wherein the engagement bot indicates a virtual user.

[0057] The orchestration module 314 may be configured to obtain (e.g. capture) one or more messages from the real-time upstream 206 of the one or more messages from the established chatroom 204. The real-time upstream 206 may indicate an inflow of the one or more messages sent by the one or more users in the chatroom 204. The orchestration module 314 may further be configured to determine at least one of a message flow rate, an emotion drift of the chatroom 204, or one or more users 208 interacting in the chatroom 204 from the captured real-time upstream 206 of one or more messages. The orchestration module 314 may further be configured to determine one or more user profiles associated with the one or more users 208 from the captured real-time upstream 206 of one or more messages.

[0058] The decision module 316 may be configured to determine at least one of, a proactive message initiation or a reactive message initiation based on the determined at least one of the message flow rate, the emotion drift of the chatroom 204, and the user profile of the one or more users 208. The proactive message initiation indicates a requirement for initiating a message by the at least one engagement bot 210 in the chatroom 208. The reactive message initiation indicates a requirement for initiating a reply by the at least one engagement bot 210 to the one or more messages captured from the real-time upstream 206. In an embodiment, the decision module 316 may be configured to generate an event message for an event 402 streaming on a video content being consumed by the one or more users 208. In an embodiment, , the decision module 316 may be configured to generate an event message based on N event objects for an event 402 streaming on a video content.

[0059] The message generation module 318 may be configured to generate a prompt based on the determined one of, the proactive message initiation and the reactive message initiation. The message generation module 318 may further be configured to generate the adaptive message for the chatroom 204 using at least one language model based on the generated prompt.

[0060] The publishing module 320 may be configured to validate the generated adaptive message based on one or more predefined parameters. In an embodiment, the one or more predefined parameters may include at least one of a profanity check parameter, a hallucination check parameter, or a bias check parameter. The publishing module 320 may further be configured to publish the generated adaptive message in the chatroom 204 based on the validation. The publishing module 320 may further be configured to publish the generated event message for an event 402 into the chatroom 204 via the at least one engagement bot 210.

[0061] FIG. 5 illustrates a block diagram depicting the bootstrapping module 312, in accordance with an embodiment of the present disclosure.

[0062] In an embodiment, at block 502, the bootstrapping module 312 may establish the chatroom 204 by defining a context of the chatroom 204. The context of the chatroom 204 may indicate actual content on which the chatting session takes place. For example, the context of the chatroom 204 may correspond to the channel that the chatting session takes place. For example, the context of the chatroom 204 may include at least one of topic, category or purpose of the chatroom 204. For example, gaming context for a game streaming channel, live TV context for live TV streaming channel, and the like. The bootstrapping module 312 may be configured to assign a communication channel to allow participants to join a session of the chatroom 204 with the defined context. In an embodiment, the bootstrapping module 312 may be configured to establish the chatroom 204 by scheduling a first predefined time duration for the session to remain active. In an embodiment, the bootstrapping module 312 may be configured to associate chatroom metadata with the chatroom 204. The chatroom metadata may include room content, room schedule, and the like. In one example, the room content may include whether the stream for which the chatroom is established is live or recorded. Further, the room schedule may include the start and end time of the chatroom 204.

[0063] At block 504, the bootstrapping module 312 may allow the one or more users 208 to join the session of the chatroom 204 with the defined context for making conversation.

[0064] At block 506, the bootstrapping module 312 may allow the at least one engagement bot 210 to join the chatroom 204. In an embodiment, the engagement bot 210 may be the virtual user with logical ability. In an embodiment, the engagement bot may be generated by the electronic device 202 aiming to increase engagement of the one or more users 208. In an embodiment, there may be a plurality of engagement bots 210 present in the chatroom 204. In an embodiment, the engagement bot 210 may be configured to play a plurality of roles. In one example, the engagement bot 210 may be configured as an unbiased bot, such that the engagement bot 210 may not have any bias or preconceived notion. In an embodiment, all the messages published by the engagement bot 210 may not have any bias in his message generation. Further, the response generated by the engagement bot 210 may directly depend on the chat messages being sent by the one or more users 208 who have joined the chatroom 204.

[0065] In an embodiment, the engagement bot 210 may be configured as a biased bot, where the bias may include one of, a predetermined (e.g. defined) notion based on a pre-set opinion, a pre-set context, and a pre-set knowledge. In an embodiment, the engagement bot 210 may be built to perform a specific task and all the messages published by the engagement bot 210 may have a preconceived notion. In an embodiment, the engagement bot 210 may be configured as multiple opinionated bots, where the engagement bot 210 with different or mutually opposite opinions may join the chatroom 204. In an embodiment, the engagement bot 210 as multiple opinionated bots may be utilized in chatrooms with sports context for sports channel or news context for news channel, in order to generate an interesting engaging environment in the chatroom 204. In particular, each engagement bot 210 may cheer or support a different team in the game or support a different political party in a political debate.

[0066] FIG. 6 illustrates a block diagram depicting the orchestration module 314, in accordance with an embodiment of the present disclosure. As mentioned above, the orchestration module 314 may obtain (e.g. capture) one or more messages from a real-time upstream 206 of the one or more messages from the established chatroom 204. In an embodiment, the orchestration module 314 provisions a pipeline or a workflow for obtaining (e.g. capturing) a continuous (e.g. real-time) stream of one or more message metadata (Oi). In an embodiment, each of the one or more message metadata (Oi) may include information relating to at least one of, a message content (mi), sender's information (si), a message timestamp (ti), a message category (ci), a message action (ai), or an emotion of the message (ei). The message content (mi) may include the actual message (e.g. body of the actual message). The sender's information (si) may include information related to who sent the message, e.g., the identity of the one or more users 208 or identity of the at least one engagement bot 210. The message timestamp (ti) may include information related to when the message was sent. The message category (ci) may include information related to the type of the message, for example, text message, voice message, emoticon, etc. The message action (ai) may include information related to whether the message was generated (e.g. created), updated, deleted, or redacted. The emotion of the message (ei) may include information related to implicit emotion information associated with the message.

[0067] At block 602, the orchestration module 314 may determine the message flow rate in the chatroom 204 to check (e.g. identify, determine) the message flow sufficiency of the chatroom 204 in the real time. The message flow sufficiency of the chatroom 204 may indicate if a sufficient exchange of conversation is taking place in the chatroom 204. In an embodiment, the orchestration module 314 may bifurcate the real-time upstream 206 into a plurality of streams for parallel processing wherein each of the plurality of streams may include one or more message metadata (Oi). In an embodiment, the orchestration module 314 may filter the plurality of streams based on at least one of the one or more message metadata (Oi). In an embodiment, the orchestration module 314 may capture the one or more messages based on the filtered plurality of streams. Further, the orchestration module 314 may determine the message flow rate based on the captured real-time upstream 206 of one or more messages. In an embodiment, the orchestration module 314 may extract a time instance of a second predefined time duration from the captured real-time upstream 206 of one or more message flows. Further, the orchestration module 314 may extract a further time instance of the second predefined time with a shift of a third predefined time duration from the first time instance. Further, the orchestration module 314 may aggregate the extracted time instances, wherein the aggregation may comprise at least one of, sliding window aggregation operation, tumbling window aggregation operation, time sliding aggregation operation, or eviction sliding aggregation operation. Furthermore, the orchestration module 314 may determine the message flow rate based on the aggregation.

[0068] At block 604, the orchestration module 314 may determine the emotion drift of the chatroom 204. In particular, the orchestration module 314 may extract one or more messages from the captured real-time upstream 206 of one or more message flows, where the one or more messages include at least one of text or emoticons. The orchestration module 314 may further extract an emotion vector from the extracted one or more messages. In an embodiment, the orchestration module 314 may compute the extracted emotion vector with an initial emotion vector of the chatroom 204. In an embodiment, the initial emotion vector of the chatroom 204 may be predetermined (e.g. defined). Furthermore, the orchestration module 314 may determine the emotion drift of the chatroom 204 based on the computation of the extracted emotion vector with an initial emotion vector of the chatroom 204. The determination of the emotion drift of the chatroom 204 shall be explained in detail with respect to FIG. 9.

[0069] At block 606, the orchestration module 314 may determine the one or more user profiles (U) associated with the one or more users 208. In an embodiment, the orchestration module 314 may be configured to retrieve historic involvement patterns data (H) for each of the one or more users 208 from an internal database. The historic involvement patterns data (H) may indicate an interaction history for each of the one or more users 208. In an embodiment, the orchestration module 314 may be configured to determine real-time involvement patterns for each of the one or more users 208. The real-time involvement patterns may indicate a count of interactions of the one or more users 208. In one embodiment, the real-time involvement patterns may be determined based on a frequency of interaction (N) data of each of the one or more users 208 with the at least one engagement bot 210 based on a reply message sent by each of the one or more users 208 to the one or more adaptive messages published by the least one engagement bot 210 in the chatroom 204. In an embodiment, the real-time involvement patterns may be determined based on an emotion data ( ) associated with the reply message sent by each of the one or more users 208 in the chatroom 204. The emotion data ( ) may indicate real time emotional reaction associated with the reply message sent by each of the one or more users 208 in the chatroom 204. In an embodiment, the orchestration module 314 may be configured to determine the one or more user profiles (U) associated with the one or more users 208 based on the determined historic involvement patterns data (H), the frequency of interaction data (N), and the emotion data ( ). The same is illustrated in equation (1):

[0070] U = f (H, N, ) ... (1)

[0071] In an embodiment, the orchestration module 314, to retrieve the historic involvement patterns data (H) for each of the one or more users 208 from the internal database, may be configured to retrieve a retention factor (R), an involvement factor (I), a diversity quotient ( ), and a genre group orientation ( ) of each of the one or more users 208. In an embodiment, the determination of the historic involvement patterns data (H) for each of the one or more users 208 may be based on the determination of the retention factor (R), the involvement factor (I), the diversity quotient ( ), and the determined genre group orientation ( ) of each of the one or more users 208.

[0072] In an embodiment, the retention factor (R) may be determined on the basis of an amount of time for which one of the one or more users 208 stays in the current chatroom 204 and the total time span of the current chatroom 204. The same is illustrated in equation (2):

[0073] R = (Time for which a user stayed in the current chatroom / Total Room time span) ...(2)

[0074] In an embodiment, the involvement factor (I) may be determined on the basis of one or more messages sent by each of the one or more users 208 in the current chatroom 204 and the total messages exchanged in the current chatroom 204. In an embodiment, the involvement factor may be determined on the basis of one or more messages sent by each of the one or more users 208 in each one or more historic chatrooms combined and the total messages exchanged in each of the one or more historic chatrooms combined. The same is illustrated in equation (3):

[0075] Involvement Factor (I)= f ( , MR, MU) ....(3)

[0076] where: : Number of Token generated during the historic chatroom time span;

[0077] MR: Total messages exchanged in each of the one or more historic chatrooms combined; and

[0078] MU: Messages sent by each of the one or more users 208 in each one or more historic chatrooms combined.

[0079] In an embodiment, Number of Token ( ) generated during the historic chatroom time span may be determined using equation (4) illustrated below:

[0080] ...(4)

[0081] where: x: message sent by a particular user

[0082] In an embodiment, the diversity quotient ( ) may be determined on the basis of one or more historic chatrooms joined by one of the one or more users 208. In an embodiment, the more chatrooms the one or more users 208 join, the more is the diversity quotient ( ).

[0083] In an embodiment, the genre group orientation ( ) of each of the one or more users 208 may be evaluated based on a historic genre preference of each of the one or more users 208. In an embodiment, each chatroom genre group may be provided with a weightage based on the genre preference of each of the one or more users 208, where the chatroom genre group indicates each chatroom in association with one or more genres.

[0084] FIG. 7 illustrates bifurcation of the real-time upstream 206 into a plurality of streams 314a and 314b for further processing, in accordance with an embodiment of the present disclosure. In an embodiment, for different purposes the real-time upstream 206 can be divided into the plurality of streams 314a and 314b, in particular, multiple downstream as needed. In an example, there can be separate streams for data and emotions, where all the plurality of streams may get the same input of one or more message metadata (Oi) from the real-time upstream 206.

[0085] At block 702, the orchestration module 314 may obtain (e.g. receive) the real-time upstream 206 of one or more messages from the chatroom 204 which includes one or more message metadata (Oi). The one or more message metadata (Oi) may be illustrated in equation (5):

[0086] Message Metadata ...(5)

[0087] where: mi: message content;

[0088] si: sender's information;

[0089] ti: message timestamp;

[0090] ci : message category;

[0091] ai : message action; and

[0092] ei : emotion of the message.

[0093] The orchestration module 314 may utilize a message capturing agent configured to pick (e.g. identify) the one or more messages as soon as they appear. The orchestration module 314 may then transmit the one or more messages into a queue of the plurality of parallel streams 314a and 314b. In an embodiment, one parallel stream 314a may be a data instream 314a for extraction of data (Di) from the one or more messages, and another parallel stream 314b may be an emotion instream for extraction of emotion (Ei) from the one or more messages. Further, each of the plurality of parallel streams 314a and 314b may be parallelly processed in the successive blocks.

[0094] At block 704, a filtration of the data instream 314a may take place by initiating the extraction of data (Di) associated with each one or more messages. In an embodiment, the electronic device 202 may filter data instream 314a. The extraction of data (Di) may be based upon the message content (mi), the sender's information (si), the message category (ci), the message timestamp (ti), and the message action (ai). The extraction of data (Di) may include the message content (mi), the sender's information (si), the message category (ci), the message timestamp (ti), and the message action (ai). In an embodiment, the filtration may filter the one or more messages from the data instream 314a to keep only those messages that are associated with "created" message action (ai). The extraction of data (Di) may be represented by equation (6) given below:

[0095] Extraction of Data ( ) = ... (6)

[0096] where: mi : message content;

[0097] si : sender's information;

[0098] ci : message category;

[0099] ti : message timestamp; and

[0100] ai : message action.

[0101] At block 706, a transformation of the filtered data instream 314a may take place by applying one or more purpose driven techniques. In an example, the one or more purpose driven techniques may include data aggregation techniques, data enrichment techniques, and the like. This transforms the data instream 314a into the other desired form, in particular, into a consumable format, for example, Extract Transform and Load Pipeline (ETL) and flattening technique. In an embodiment, the extracted data (Di) may be transformed into transformed data (D'i). The process of the flattening or other transformation technique applied at the block 706 may prepare the transformed data (D'i) for aggregation.

[0102] At block 708, the schema mapping of the transformed data (D'i) may take place.

[0103] At block 710, the transformed data (D'i) may be stored to a well partitioned object storage. In an embodiment, the object storage may be partitioned with a timestamp. For example, the scheme mapped transformed data (D''i) may be stored to a well partitioned object storage.

[0104] At block 712, the stored transformed data (D'i) may be aggregated in one or more time instances for the each of the one or more message flows to determine aggregated data. The aggregated data may help in determining the message flow rate. In an embodiment, the aggregation may be based on at least one of an average, a sum, and an emotion of the stored transformed data (D'i). In an embodiment, the aggregation may be based on at least one of sliding window, tumbling window, time sliding or eviction sliding aggregations. In an embodiment, the scheme mapped transformed data (D''i) may be aggregated in one or more time instances for the each of the one or more message flows to determine aggregated data.

[0105] At block 714, a current point-in-time snapshot of the aggregated data may be stored to a service database 404 for immediate reference while determining the real-time message flow sufficiency of the chatroom 204. The current point in time snapshot may indicate an aggregation of one or more messages flowing through the real-time upstream 206 in any particular time- instance under consideration.

[0106] In an embodiment, the orchestration module 314 may aggregate the extracted time instances using a data stream management system, where the aggregation may include one of, sliding window aggregation operation, tumbling window aggregation operation, time sliding aggregation operation, and eviction sliding aggregation operation.

[0107] An example representation of the current point-in-time snapshot of a chatroom 204 and example chatroom 1 (R1) is illustrated in Table 1 below:

[0108] Room IDYearMonthDayHourMinutesCountR120238805421R120238805532R120238805634R12023880575R120238805811

[0109] At block 716, a filtration of the emotion instream 314b may take place by initiating the extraction of emotion (Ei) associated with each one or more messages. The extraction of emotion (Ei) may be based upon the emotion of the message (ei), the sender's information (si), the message timestamp (ti), and the message category (ci). The emotion extraction (Ei) may be represented by equation (7) given below:

[0110] Extraction of emotion ( ) = ... (7)

[0111] where: ei : emotion of the message

[0112] si : sender's information;

[0113] ti : message timestamp; and

[0114] ci : message category.

[0115] At block 718, the extracted emotion (Ei) associated with each one or more messages may be aggregated to determine the emotion of the entire chatroom 204. In an embodiment, the aggregated emotion of the entire chatroom 204 may be saved into a shared cache.

[0116] FIG. 8 illustrates a graphical representation 800 of the determination of the message flow rate using the sliding window aggregation operation, in accordance with an embodiment of the present disclosure. In an embodiment, determination of message flow rate by aggregation of the extracted time instances using the sliding window aggregation operation based on the average technique. As shown, the Y-axis may represent an event time, and the X-axis may represent a time duration of the session of the chatroom 204. For the purpose of explanation, time may be represented in Minutes, and an event time of 5 Minutes is considered ranging from 12:00 to 12:05 time duration. In an example embodiment, the total number of one or more messages captured from real-time upstream 206 are shown for the time duration of "T+0" to time "T+9". Further, as shown, a total of 10 messages may be captured from time "T+0" to time "T+1", a total of 21 messages may be captured from the time "T+1" to time "T+2", a total of 33 messages may be captured from the time "T+2" to time "T+3", a total of 27 messages may be captured from the time "T+3" to time "T+4", a total of 32 messages may be captured from the time "T+4" to time "T+5", a total of 17 messages may be captured from the time "T+5" to time "T+6", a total of 6 messages may be captured from the time "T+6" to time "T+7", a total of 19 messages may be captured from the time "T+7" to time "T+8", and a total of 33 messages may be captured from the time "T+8" to time "T+9".

[0117] In an embodiment, the orchestration module 314 may extract a first time instance 802a of the second predefined time duration from the captured real-time upstream 206 of one or more message flows from the stored transformed data (D'i). The first time instance 802a may correspond to a window size (W1) of the second predefined time duration. In a non-limiting example embodiment, the second predefined time duration may be of 5 Minutes duration. Further, the orchestration module 314 may extract further time instances 802b-802e of the second predefined time with the shift of the third predefined time duration from the first time instance 802a. In a non-limiting example embodiment, the third predefined time duration corresponds to a slide interval of 1 Minute duration. In an embodiment, the orchestration module 314 may determine a sliding average based on the one or more messages generated every minute for the next second predefined time duration (e.g. 5 Minutes of duration). The same is illustrated in equation (8):

[0118] Sliding average = ... (8)

[0119] where: : Sum of total messages in a given time instance

[0120] N : Second predefined time duration (5 Min)

[0121] Therefore, referring to the example depicted in FIG. 8, the sliding average of the first time instance 802a of window size (W1) may be evaluated by:

[0122] Sliding average of W1 = (10+ 21+33+27+32) / 5 = 24.6

[0123] In an embodiment, after every third predefined time duration, i.e., the slide interval of 1 Minute, the window size of 5 Minutes duration will move ahead by 1 Minute and the sliding average may be determined by recalculating the one or more messages generated in that window size of 5 Minutes duration for the event time of 5 Minutes. Further, the orchestration module 314 may determine the message flow rate of the chatroom 204 on the basis of aggregating the evaluated sliding average for all the extracted time instances 802a -802e to provide the aggregated data. Further, the aggregated data for extracted time instances 802a -802e of 5 Minutes of the second predetermined time duration may be stored in the service database 404 as the current point in time snapshot (as depicted in Table 1). The current point-in-time snapshot may include data regarding the message flow rate by providing details of the real-time message flow sufficiency of the chatroom 204 for determining the requirement for at least one of, the proactive message initiation or the reactive message initiation by the decision module 316 for message generation.

[0124] FIG. 9 illustrates a functional block diagram depicting the determination of the emotion drift of the chatroom 204, in accordance with an embodiment of the present disclosure.

[0125] According to an embodiment of the present disclosure, emotion drift refers to the gradual change in the emotional state of the one or more messages in the chatroom 204. Emotion drift may be quantified based on the variation (or, change) in the emotion vector from messages from real-time upstream 206. The emotion vector may represent the overall sentiment distribution of the chatroom 204.

[0126] At block 902, the orchestration module 314 may be configured to extract one or more messages from the captured real-time upstream 206 of one or more message flows that may include one or more message metadata (Oi). In an embodiment, the orchestration module 314 may extract one or more messages from the captured real-time upstream 206 of one or more message flows that may include one or more message metadata (Oi). In an embodiment, the one or more message metadata (Oi) present in the one or more message flows may include at least one of the message content (mi), the sender's information (si), the emotion of the message (ei), the message timestamp (ti), or message action (ai). The orchestration module 314 may further be configured to construe words and emoticons from the extracted one or more messages into one of, textual tokens and pictorial tokens, respectively. The orchestration module 314 may construe words and emoticons from the extracted one or more messages into one of, textual tokens and pictorial tokens, respectively. In an embodiment, to determine (e.g. calculate) the overall emotion of the chatroom 204, the orchestration module 314 express the textual tokens and pictorial tokens in a mathematical form. The chatroom chat in totality may include many sentences. Each sentence is further created with the help of words or emoticons. In an embodiment, words or pictures (emoticons) may be the minimum divisible tokens of any sentence. In an embodiment, even a character or syllable may be considered as a token.

[0127] At block 904, the orchestration module 314 may be configured to generate (e.g. create) a vocabulary vector. In an embodiment, the orchestration module 314 may generate (e.g. create) a vocabulary vector. In an embodiment, the vocabulary vector may be generated (e.g. created) based on defined emotion dimensions using available public (open source) datasets.

[0128] At block 906, the orchestration module 314 may be configured to extract (e.g. identify) the emotion vector from the extracted one or more messages by vectorization of the extracted one or more messages. In an embodiment the orchestration module 314 may identify the emotion vector from the extracted one or more messages by vectorization of the extracted one or more messages. In an embodiment, the emotion vector may represent the emotional state of a message or a chatroom (204) at a specific point in time and may include multiple emotional dimensions. For example, there can be multiple dimensions of emotion associated with the textual tokens and the pictorial token, such as admirations, amusement, anger, annoyance, approval, caring, confusion, curiosity, desire, disappointment, disapproval, disgust, embarrassment, excitement, fear, gratitude, grief, joy, love, nervousness, optimism, pride, realization, relief, remorse, sadness, surprise, neutral, and the like. In an embodiment, the orchestration module 314 may be configured to compute (e.g. determine) at least one of the textual tokens and the pictorial tokens into a vector based on a probability of one or more emotion dimensions associated with the construed textual tokens and pictorial tokens. In an embodiment, the orchestration module 314 may calculate (e.g. compute) at least one of the textual tokens or the pictorial tokens into a vector based on a probability of one or more emotion dimensions associated with the construed textual tokens and pictorial tokens. In an embodiment, the orchestration module 314 may be configured to extract the emotion vector from the extracted one or more messages based on the computed textual tokens and the pictorial tokens, thereby generating (e.g. creating) vector embeddings. In an embodiment, the orchestration module 314 may further utilize the vocabulary vector to extract the emotion vector from the extracted one or more messages. In an embodiment, the orchestration module 314 may extract the emotion vector from the extracted one or more messages based on the vocabulary vector. The emotion vector may be represented as Vi (d1, d2, d3, ...dn), where n may represent the dimension of the vector. In an embodiment, multiple dimensions may be clubbed (e.g. utilized) together to make a shorter set of dimensions for expressing emotions, in an embodiment, every token may be converted into the emotion vector of dimension 4, for example, happy, sad, angry, and surprised as its dimension. An example of the emotion vector of dimension 4 is illustrated in Table 2 below:

[0129] TokenHappySadAngrySurprisedVectorGood game1000{1,0,0,0}A win is a win0.9800.010.01{0.98,0, 0.01,0.01}

[0130] At block 908, orchestration module 314 may be configured to determine emotion drift. In an embodiment, orchestration module 314 may determine emotion drift using a momentum factor. In an embodiment, orchestration module 314 may be configured to update the emotion vector of the chatroom 204 based on the determined emotion drift using a momentum factor. The momentum factor may influence an impact of the emotion vector from the extracted one or more messages on the emotion drift of the chatroom 204, based on a predefined threshold value. The momentum factor would be between 0 and 1. For example, difference between emotion vector and the updated emotion vector may be a emotion drift.

[0131] In an embodiment, if the momentum factor is low, the extracted emotion vector of the one or more messages from the captured real-time upstream 206 may contribute more to the determination of the emotion drift of the chatroom 204. Similarly, if the momentum factor is high, the existing value or emotion drift of the chatroom 204 may contribute more to the determination of the emotion drift of the chatroom 204 rather than extracted emotion vector of the one or more messages from the captured real-time upstream 206. In an embodiment, if the momentum factor is lower than the defined threshold (e.g. 0.5), the extracted emotion vector of the one or more messages from the captured real-time upstream 206 may contribute more to the determination of the emotion drift of the chatroom 204. In an embodiment, if the momentum factor is higher than the defined threshold (e.g. 0.5), the existing value or emotion drift of the chatroom 204 may contribute more to the determination of the emotion drift of the chatroom 204 rather than extracted emotion vector of the one or more messages from the captured real-time upstream 206.

[0132] In an embodiment, an existing emotion vector (V0) of the chatroom 204 may be illustrated in equation (9):

[0133] Existing emotion vector ( ) = ... (9)

[0134] wherein, = dimension of the emotion vector

[0135] Here, in an embodiment, all the dimensions of the emotion vector may be equal. The same is illustrated by the equation (10):

[0136] ... (10)

[0137] Therefore, the existing emotion vector (V0) of the chatroom 204 may be illustrated in equation (11):

[0138] Existing emotion vector ( ) = (0.25, 0.25, 0.25, 0.25) ... (11)

[0139] Here, the initial Momentum (M) may be 0.1, and accordingly, more weightage may be to the extracted emotion vector of the one or more messages from the captured real-time upstream 206 for their contribution to the emotion drift of the chatroom 204.

[0140] In an embodiment, the extracted emotion vector of each new message from the one or more messages from the captured real-time upstream 206 may be illustrated in equation (12):

[0141] New message emotion vector V1 = (d1, d2, d3, d4) ...(12)

[0142] In an embodiment, the updated emotion vector of the chatroom 204 based on the determined emotion drift may be illustrated in equation (13):

[0143] Updated emotion vector of chatroom (V"0) = (d'1, d'2, d'3, d'4) ...(13)

[0144] In an embodiment, each dimension of the emotion vector of the chatroom 204 may be updated. The same if illustrated in in equation (14):

[0145] ... (14)

[0146] In an embodiment, the momentum (M) for adaptive impact of the existing emotion vector of the chatroom 204 versus the new emotion vector of the chatroom 204 may be adjusted after every update in the emotion vector of the chatroom 204. In an embodiment, a new value of updated momentum (M') may be determined. The same is in in equation (15):

[0147] Updated Momentum ( ) = ... (15)

[0148] In an embodiment, for each determination of the emotion drift of the chatroom 204, an updated momentum (M') may be determined. In an embodiment, based on the updated momentum (M'), a new emotion vector of the chatroom 204 may be determined. The same is in equations (16) and (17):

[0149] Updated emotion vector of chatroom

[0150] Updated emotion vector of chatroom

[0151] ...(17)

[0152] FIG. 10 illustrates a functional block diagram depicting generation of the vocabulary vector, in accordance with an embodiment of the present disclosure.

[0153] At block 1002, the public domain (open-source) dataset may be acquired from various sources. The electronic device 202 may obtain the public domain (open-source) dataset from various sources.

[0154] At block 1004, the acquired public domain dataset may be tokenized into smaller units or tokens, such as into words or syllables. The electronic device 202 may tokenize the obtained public domain dataset into smaller units or tokens, such as into words or syllables.

[0155] At block 1006, vocabulary may be built based on the tokenized public domain dataset. The electronic device 202 may build vocabulary based on the tokenized public domain dataset.

[0156] At block 1008, layers may be embedded to facilitate capture of semantic meaning. The electronic device 202 may embed layers to facilitate capture of semantic meaning.

[0157] At block 1010, a vocabulary vector may be created (e.g. generated) for defined emotion dimensions based on the build vocabulary and embedding layers using a machine learning model. The electronic device 202 may generate the vocabulary vector for defined emotion dimensions based on the build vocabulary and embedding layers using a machine learning model (e.g. Average MLP) In an embodiment, the vocabulary vector may be in a form of JSON.

[0158] FIG. 11 illustrates a block diagram depicting the decision module 316, in accordance with an embodiment of the present disclosure.

[0159] At block 1102, the decision module 316 may generate the event message for the streamed event 402 on the video content. The streamed event 402 on the video content may be the video content that is being consumed by the one or more users 208. In an embodiment, the streamed event 402 may include the 3rd Party component. In an embodiment, the event stream 402 may include a plurality of event objects. In an embodiment, the decision module 316 may be configured to detect one of a scene and streamed event 402 being consumed by the one or more users 208 using a machine learning model. In an embodiment, the decision module 316 may identify one of a scene and streamed event 402 being consumed by the one or more users 208 using a machine learning model. Further, the decision module 316 may be configured to map a predefined time instance of the streamed event 402, with at least one of, a time stamp, context of the streamed event 402, and probability of occurrence of the streamed event 402. In an embodiment, the decision module 316 may be configured to generate a micro tag based on the mapped predefined time instance of the streamed event 402. In an embodiment, the decision module 316 may be configured to generate the event message for the event 402 streaming on the video content based on the generated micro tag. In an embodiment, the event message may be a decision ground.

[0160] At block 1104, the decision module 316 may be configured to determine one of, a proactive message initiation and a reactive message initiation.

[0161] The proactive message initiation may be required in a situation where there are one or more users 208 in the chatroom 204 but no one is initiating any conversation. The proactive message initiation may be performed in a situation where there are one or more users 208 in the chatroom 204 but no one is initiating any conversation. In an embodiment, if proactive action is not taken, the one or more users 208 may quit the chatroom 204. In an embodiment, the decision module 316, to determine the proactive message initiation by the at least one engagement bot 210 in the chatroom 204, may determine the presence of one or more users 208 in the chatroom 204. In an embodiment, the decision module 316 may be configured to evaluate (e.g. identify) a time of the proactive message initiation by the at least one engagement bot 210 based on a detection (e.g. identification) of the determined message flow rate being zero. In an embodiment, the initiated message may be based on the emotion drift of the chatroom 204 and the user profile of the one or more users 208. In an embodiment, the time of initiation of the message by the at least one engagement bot 210 may be periodically evaluated for the determination of the proactive message initiation. In an embodiment, the decision module 316 may be configured to evaluate a time of halting the proactive message initiation by the at least one engagement bot 210 based on the detection of the determined message flow rate being above a predetermined threshold level. In an embodiment, the decision module 316 may identify a time of halting the proactive message initiation by the at least one engagement bot 210 based on the detection of the determined message flow rate being above a predetermined threshold level. In an embodiment, the decision module 316 may determine the proactive message initiation by the at least one engagement bot 210 in the chatroom 204 based on one of the evaluated (e.g. determined) times.

[0162] Therefore, the proactive message initiation may help in achieving one or more of the following:

[0163] Invoking the chatroom 204 with greeting messages for the first few one or more users 208.

[0164] Addressing the one or more users 208 by their names or nicknames or usernames based on the user profile of the one or more users 208.

[0165] Using meta information of the chatroom 204 to share insights about the context of the chatroom 204, such as gaming context for game streaming channel, live TV context for live TV streaming channel, and the like.

[0166] Sending a text in a language that triggers the one or more users 208 to initiate conversation.

[0167] In an embodiment, the decision module 316, to determine the reactive message initiation by the at least one engagement bot 210 in the chatroom 204, may determine (e.g. identify) the presence of one or more users 208 in the chatroom. In an embodiment , the decision module 316 may be configured to evaluate (e.g. determine) a time for the reactive message initiation by the at least one engagement bot 210 based on the detection of the determined message flow rate being below a predetermined threshold level. In an embodiment, the initiated message may be based on the emotion drift of the chatroom 204, and the user profile of the one or more users 208. In an embodiment, the time of initiation of the message by the at least one engagement bot 210 may be determined in response to each new message among the one or more messages captured from the real-time upstream 206. In an embodiment, the decision module 316 may be configured to identify (e.g. evaluate) a time of halting the reactive message initiation by the at least one engagement bot 210 based on the detection of the determined message flow rate being above a predetermined threshold level. In an embodiment, the decision module 316 may determine the reactive message initiation by the at least one engagement bot 210 in the chatroom 204 based on one of the evaluated times.

[0168] Therefore, the reactive message initiation may help in achieving one or more of the following:

[0169] Replying to questions of the one or more users 208 in an engaging manner.

[0170] Triggering the one or more users 208 for encouraging their involvement into the chatroom 204.

[0171] Sharing fun facts about the chatroom 204.

[0172] Publishing quizzes / polls in the middle of the chatroom 204 and publishing scores of the published quizzes / polls based on the correctness and rapidness of the one or more users 208.

[0173] Preparing leaderboards of the scores of the published quizzes / polls.

[0174] Using mentioned names or nicknames or usernames of the one or more users 208 while replying.

[0175] Cheering teams / parties by the least one engagement bot 210.

[0176] FIG. 12 illustrates a block diagram depicting the message generation module 318, in accordance with an embodiment of the present disclosure. The message generation module 318 may be configured to suggest a novel way of how the adaptive message may be generated for the chatroom 204.

[0177] At block 1202, the message generation module 318 may acquire metadata information associated with the chatroom 204. The chatroom metadata may include room content, room schedule, and the like.

[0178] At block 1204, the message generation module 318 may be configured to generate the prompt on the determined one of, the proactive message initiation and the reactive message initiation. The message generation module 318 may generate the prompt on the determined one of, the proactive message initiation and the reactive message initiation. In an embodiment, the message generation module 318 may be configured to classify the determined one of, the proactive message initiation and the reactive message initiation based on a purpose comprising one of an interrogative, an imperative, an exclamatory, and a declarative message. The message generation module 318 may classify the determined one of, the proactive message initiation and the reactive message initiation based on a purpose comprising one of an interrogative, an imperative, an exclamatory, and a declarative message. In an embodiment, the message generation module 318 may be configured to select a pre-created prompt template from a set of pre-created prompt templates based on the classified purpose of the determined one of the proactive message initiation and reactive message initiation. In an embodiment, the message generation module 318 may select a pre-created prompt template from a set of pre-created prompt templates based on the classified purpose of the determined one of the proactive message initiation and reactive message initiation. Furthermore, the message generation module 318 may be configured to ingest the selected pre-created prompt template with information tags. Furthermore, the message generation module 318 may ingest the selected pre-created prompt template with information tags (e.g. cost metadata from the service metadata 404). The information tags (e.g. service metadata 404) correspond to at least one of, a title of the chatroom 204, a genre of the chatroom 204, a name of the communication channel, the generated micro tag, a date, and the username of one of the one or more users 208. In an embodiment, the information tags (e.g. service metadata 404) may include an identifier or a placeholder which could hold different information and different context. Accordingly, the message generation module 318 may generate the prompt using the ingested prompt pre-created template.

[0179] At block 1206, the message generation module 318 may be configured to generate the adaptive message for the chatroom 204 using at least one language model based on the generated prompt. The message generation module 318 may generate the adaptive message for the chatroom 204 using at least one language model based on the generated prompt. In an embodiment, the message generation module 318 may be configured to select at least one language model based on the classified purpose of the determined one of, proactive message initiation and reactive message initiation. The message generation module 318 may select at least one language model based on the classified purpose of the determined one of, proactive message initiation and reactive message initiation. Further, the message generation module 318 may be configured to infer the generated prompt using the selected at least one language model. The message generation module 318 may infer the generated prompt using the selected at least one language model. The at least one language model may include at least one of, a pre-set recommendation module and a large language (LLM) model such as generative Artificial Intelligence (genAI) based language models. Accordingly, the message generation module 318 may generate the adaptive message for the chatroom (204) based on the inference generated prompt.

[0180] FIG. 13 illustrates a functional block diagram depicting language model selection by the message generation module 318, in accordance with an embodiment of the present disclosure.

[0181] At block 1302, the decision module 316 may determine if there is a requirement of message generation in the chatroom 204.

[0182] At block 1304, the decision module 316 may determine if the requirement may be met with one of, the proactive message initiation and a reactive message initiation.

[0183] At block 1306, a language model may be selected for generating the adaptive message for the chatroom 204. The message generation module 318 may select a language model for generating the adaptive message for the chatroom 204. In an example, on determination of the requirement of the proactive message initiation at block 1304, the message generation module 318 may determine if greeting messages are to be sent to the one or more users 208, or a pre-set messages are to be sent to the one or more users 208.

[0184] At block 1308, the message generation module 318, on determination of the reactive message, may detect a sentence class. The message generation module 318 may classify the determined reactive message initiation based on a purpose comprising one of an interrogative, an imperative, an exclamatory, and a declarative message.

[0185] At block 1310, the message generation module 318 may determine if only expression is required for the adaptive message. The message generation module 318 may determine if the adaptive message may be generated from one of a pre-set recommendations or using the genAI-based language model.

[0186] Again, at the block 1306, the message generation module 318, on the determination of the requirement of only expression at the block 1310, may utilize the pre-set recommendation module and may generate the adaptive message comprising expression, emotions or text with similar emotions. In an embodiment, the message generation module 318 may select the genAI based language model.

[0187] At block 1312, to generate the adaptive message, the output of the language model from the block 1306 may be inferred with the prompt template. The message generation module 318 may infer the output of the language model from the block 1306 with the prompt template to generate the adaptive message.

[0188] In an embodiment, the genAI based language models may be selected from a pool of genAI models based on a prior knowledge of their performance for different sentence classes. The message generation module 318 may select the genAI based language models from a pool of genAI models based on a prior knowledge of their performance for different sentence classes.

[0189] In an embodiment, once the language model is selected, its prompts are prepared dynamically with the help of the context of the chatroom 204.

[0190] FIG. 14 illustrates a functional block diagram depicting the generation of the prompt by the message generation module 318, in accordance with an embodiment of the present disclosure.

[0191] At block 1402, a meta manager may acquire metadata information associated with the chatroom 204 from the service database 404. The chatroom metadata may include room content, room schedule, and the like. In an example, output at block 1402 may recite the following:

[0192] {

[0193] BOT_USER : Adam,

[0194] ROOM_GENRE: football

[0195] }

[0196] At block 1404, message appropriation may be initiated where an appropriate purpose for the generation of the adaptive message may be selected. Accordingly, an appropriate language model may be selected corresponding to the selected purpose of generation of the adaptive message. Further, to query the language model, the message generation module 318 may ensure that the preparation of a prompt is precise.

[0197] At block 1406, a pre-created prompt template may be at least one of, generated or selected from the set of pre-created prompt templates based on the purpose of generation of the adaptive message. In an embodiment, the set of pre-created prompt templates may include a introductory prompt template, a cheering game prompt template, a cheering team prompt template, a generic greetings prompt template, and the like. Further, the message generation module 318 may be configured to inference the prompt template using the selected at least one language model. In a non-limiting example, output at block 1406 may recite the following:

[0198] "Write few lines to engage people assuming that you are {BOT_USER} and a {ROOM_GENRE} freak."

[0199] At block 1408, a meta binding operation may be performed to combine the output of block 1402 and block 1406. In a non-limiting example, output at block 1408 may recite the following:

[0200] "Write few lines to engage people assuming that you are Adam and a football freak."

[0201] In an embodiment, prompt templates may be generic templates which when injected with some information tags, may become a specific input prompt for a language model. In an embodiment, each prompt template may be categorized based on the purpose of the generation of the adaptive message.

[0202] In an example, for the purpose of a generic reply, the prompt template may recite as template 1:

[0203] Template 1 : Prepare very short reply in　#system.language　Language for a group chat message on a LIVE game to engage people TOPIC :　#room.ChannelName　|　#room.RoomTitle　|　#room.Date. INPUT MESSAGE :　#user.inputMessage

[0204] In an example, for the purpose of the generic reply, the prompt template may be recited as template 2:

[0205] Template 2 : Prepare a one line reply for the input message -　#user.inputMessage

[0206] In an example, for the purpose of classification, the prompt template may be recited as template 3:

[0207] Template 3 : Classify the　#user.inputMessage　message among the one word classes [interrogative, imperative,　 declarative]

[0208] In an example, for the purpose of event based generation, the prompt template may recite as template 4:

[0209] Template 4 : For the chatroom of　#room.RoomGenre　type, create a 'single' very short Hooting or reaction message for the event of　#AicfMicrotags. Assuming that you are watching a live channel. make good use of emojis",

[0210] In an embodiment, the information tags may include #RoomTitle, #ChannelName, #RoomGenre #AicfMicrotags, #Actors #Date, #UserNickName, #CustomTag2.

[0211] In an example, the input message may be: "is it not a foul ?". Here, the input message may refer to at least one captured message from a real-time upstream 206 of the one or more messages from the established chatroom 204. The input message may be classified as a question sentence. Here, a prompt template based on the purpose generation of the adaptive message may be selected as "generic reply". In an embodiment, template 1 or template 2 may be selected. Therefore, the message generation module 318 may generate the prompt as:

[0212] "Prepare very short reply in　Spanish　Language for a group chat message on a LIVE game to engage people TOPIC :　ABC　|　Men's Football Final South Korea: Japan　|　Oct 7, 2023. INPUT MESSAGE :　is it not a foul ?"

[0213] FIG. 15 illustrates a block diagram depicting the publishing module 320, in accordance with an embodiment of the present disclosure.

[0214] At block 1502, the publishing module 320 may perform basic level of sanity check, as every generated adaptive message (e.g. generated message) may not be directly exposed to the one or more users 208 present in the chatroom 204. In an embodiment, the publishing module 320 may validate the received generated adaptive message (e.g. generated message) from the message generation module 318 based on one or more predefined parameters.

[0215] In an embodiment, the one or more predefined parameters may include a profanity check parameter. The profanity check parameter may be implemented using an AI model trained on public profanity data, thereby ensuring that the only good generated adaptive messages are published. In an embodiment, good generated adaptive messages may represent generated adaptive messages without at least one of a profanity, a hallucination or a bias. In an embodiment, the profanity check parameter may include building a corpus / bank of profane words, which may be based on language, country social conditions, and the like, and verifying against the corpus.

[0216] In an embodiment, the one or more predefined parameters may include a hallucination check.

[0217] In an embodiment, the one or more predefined parameters may include a bias check parameter. The bias check parameter may be implemented to avoid biasing based on age, gender, race, and the like of the one or more users 208.

[0218] Further, at block 1502, if the generated adaptive message may be invalidated on the determination of being NOT GOOD, the publishing module 320 may reject the generated adaptive message. In an embodiment, the message generation may be re-attempted (e.g. retried) with a variation in the prompt template. In an embodiment, not good generated adaptive messages may represent generated adaptive messages with at least one of a profanity, a hallucination or a bias.

[0219] At block 1504, if the generated adaptive message may be validated on determination of being GOOD, the publishing module 320 may publish the generated adaptive message in the chatroom (204). For example, the publishing module 320 may publish the generated adaptive message to web socket.

[0220] FIG. 16 illustrates a flowchart depicting an exemplary method 1600 for generating an adaptive message for a chatroom 204, in accordance with an embodiment of the present disclosure. The method 1600 may be a computer-implemented method executed, for example, by the processor 302 and the modules 308. For the sake of brevity, constructional and operational features of the electronic device 202 that are already explained in the description of FIG. 1 to FIG. 15, are not explained in detail in the description of FIG. 16. Referring to FIG. 16, the method for generating an adaptive message for a chatroom 204 may include operations 1602 through 1614. In an embodiment of the present disclosure, operations 1602 through 1614 may be executed by at least one processor included in the electronic device 202. Methods of how the electronic device 202 manages memory are not limited to those illustrated in Figure 16, and in one or more embodiments, additional operations not illustrated in Figure 16 may be included, or some operations may be omitted.

[0221] The method 1600 may begin with operation 1602 which may include establishing the chatroom 204 to allow one or more users 208 and at least one engagement bot 210 to join and interact in the chatroom 204. The engagement bot 210 may indicate a virtual user. In an embodiment, the least one engagement bot 210 may be configured with one of, a predetermined notion based on a pre-set opinion, a pre-set context, and a pre-set knowledge.

[0222] At operation 1604, the method 1600 may include capturing one or more messages from a real-time upstream 206 of the one or more messages from the established chatroom 204. The real-time upstream 206 may indicate an inflow of the one or more messages sent by the one or more users 208 in the chatroom 204.

[0223] At operation 1606, the method 1600 may include determining at least one of a message flow rate, an emotion drift of the chatroom 204, and one or more users 208 interacting in the chatroom 204 from the captured real-time upstream 206 of one or more messages.

[0224] At operation 1608, the method 1600 may include determining one or more user profiles (U) associated with the one or more users 208 from the captured real-time upstream 206 of one or more messages.

[0225] At operation 1610, the method 1600 may include determining one of, a proactive message initiation and a reactive message initiation based on the determined at least one of the message flow rate, the emotion drift of the chatroom 204, and the user profile of the one or more users 208. The proactive message initiation indicates a requirement for initiating a message by the at least one engagement bot 210 in the chatroom 204. The reactive message initiation indicates a requirement for initiating a reply by the at least one engagement bot 210 to the one or more messages captured from the real-time upstream 206.

[0226] At operation 1612, the method 1600 may include generating a prompt based on the determined one of, the proactive message initiation and the reactive message initiation.

[0227] At operation 1614, the method 1600 may include generating the adaptive message for the chatroom 204 using at least one language model based on the generated prompt.

[0228] The method 1600 may further include publishing the generated adaptive message in the chatroom 204 by validating the generated adaptive message based on one or more predefined parameters. The one or more predefined parameters comprise a profanity check parameter, a hallucination check parameter, and a bias check parameter.

[0229] In an embodiment, the method 1600, for establishing the chatroom 204 at operation 1602, may include defining a context of the chatroom 204. The method 1600 may further include assigning a communication channel configured to allow one or more users 208 and the at least one engagement bot 210 to join a session of the chatroom 204 with the defined context. The method 1600 may further include establishing the chatroom 204 by scheduling a first predefined time duration for the session to remain active.

[0230] In an embodiment, the method 1600, for capturing the one or more messages from the real-time upstream 206 of the one or more messages from the established chatroom at step 1602, may include bifurcating the real-time upstream 206 into a plurality of streams for parallel processing wherein each of the plurality of streams includes one or more message metadata (Oi). The method 1600 may further include filtering the plurality of streams based on at least one of the one or more message metadata (Oi). Furthermore, the method 1600 may include capturing the one or more messages based on the filtered plurality of streams. In an embodiment, the one or more message metadata (Oi) may include information relating to at least one of, a message content (mi), sender's information (si), a message timestamp (ti), a message category (ci), a message action (ai), and an emotion of the message (ei).

[0231] In an embodiment, the method 1600, for determining the message flow rate at step 1606, may include extracting a time instance of a second predefined time duration from the captured real-time upstream 206 of one or more message flows. The method 1600 may further include extracting a further time instance of the second predefined time with a shift of a third predefined time duration from the first time instance. The method 1600 may further include aggregating the extracted time instances, wherein the aggregation may comprise one of, sliding window aggregation operation, tumbling window aggregation operation, time sliding aggregation operation, and eviction sliding aggregation operation. Furthermore, the method 1600 may include determining the message flow rate based on the aggregation.

[0232] In an embodiment, the method 1600, for determining the emotion drift of the chatroom 204 at step 1606, may include extracting one or more messages from the captured real-time upstream 206 of one or more message flows, wherein the one or more messages include at least one of a text and emoticons. The method 1600 may further include extracting an emotion vector from the extracted one or more messages. The method 1600 may further include computing the extracted emotion vector with an initial emotion vector of the chatroom 204, wherein the initial emotion vector of the chatroom 204 may be predetermined. Further, the method 1600 may include determining the emotion drift of the chatroom 204 based on the computation. The method 1600 may further include updating the emotion vector of the chatroom 204 based on the determined emotion drift using a momentum factor. The momentum factor, based on a predefined threshold value, may influence an impact of the emotion vector from the extracted one or more messages on the emotion drift of the chatroom 204. In an embodiment, for extracting the emotion vector from the extracted one or more messages the method 1600 may include construing words and emoticons from the extracted one or more messages into one of, textual tokens and pictorial tokens, respectively. The method 1600 may further include computing at least one of the textual tokens and the pictorial tokens into a vector based on a probability of one or more emotion dimensions associated with the construed textual tokens and pictorial tokens. Furthermore, the method 1600 may include extracting the emotion vector from the extracted one or more messages based on the computed textual tokens and the pictorial tokens.

[0233] In an embodiment, the method 1600, for determining the one or more user profiles (U) associated with the one or more users 208 at step 1606, may include retrieving historic involvement patterns data for each of the one or more users 208 from an internal database. The method 1600 may further include determining real-time involvement patterns. The real-time involvement patterns may be determined based on a frequency of interaction data of each of the one or more users 208 with the at least one engagement bot 210 based on a reply message sent by each of the one or more users 208 to the one or more adaptive messages published by the least one engagement bot 210 in the chatroom 204. The real-time involvement patterns may further be determined based on an emotion data associated with the reply message sent by each of the one or more users 208 in the chatroom 204. Furthermore, the method 1600 may include determining the one or more user profiles (U) associated with the one or more users 208 based on the retrieved historic involvement patterns data, the frequency of interaction data, and the emotion data.

[0234] In an embodiment, the method 1600, for retrieving the historic involvement patterns data for each of the one or more users 204 from the internal database, may include retrieving a retention factor of each of the one or more users 208. The retention factor is determined based on the amount of time which one of the one or more users 208 stays in the current chatroom 204 and the total time span of the current chatroom 204. The method 1600 may further include retrieving an involvement factor of each of the one or more users 208. The involvement factor may be determined based on one or more messages sent by each of the one or more users 208 in the current chatroom 204 and the total messages exchanged in the current chatroom 204. The involvement factor may further be determined based on one or more messages sent by each of the one or more users 208 in each one or more historic chatrooms and the total messages exchanged in each of the one or more historic chatrooms. The method 1600 may further include retrieving a diversity quotient of each of the one or more users. The diversity quotient may be determined based on one or more historic chatrooms joined by the one or more users 208. The method 1600 may further include determining genre group orientation of each of the one or more users 208, by evaluating a historic genre preference of each of the one or more users 208. Furthermore, the method 1600 may include determining the historic involvement patterns data for each of the one or more users 208 based on the determined retention factor, the determined involvement factor, the determined diversity quotient, and the determined genre group orientation.

[0235] In an embodiment, the method 1600 may include generating an event message for an event streaming on a video content being consumed by the one or more users 208. The method 1600 may include detecting one of a scene and event stream being consumed by the one or more users 208 using a machine learning model. The method 10800 may further include mapping a predefined time instance of the streamed event, with at least one of, a time stamp, context of the streamed event, and probability of occurrence of the streamed event. The method 1600 may further include generating a micro tag based on the mapped predefined time instance of the streamed event. Furthermore, the method 1600 may include generating the event message for the event streaming on the video content based on the generated micro tag. In an embodiment, the at least one engagement bot 210, based on the generated event message, publishes the generated event message into the chatroom 204.

[0236] In an embodiment, the method 1600, for determining the proactive message initiation by the at least one engagement bot 210 in the chatroom 204 at step 1610, may include determining presence of one or more users 208 in the chatroom 204, and evaluating a time of the proactive message initiation by the at least one engagement bot 210 based on a detection of the determined message flow rate being zero. In an embodiment, the initiated message may be based on the emotion drift of the chatroom 204, and the user profile of the one or more users 208. In an embodiment, the time of initiation of the message by the at least one engagement bot 210 may be periodically evaluated. The method 1600 may further include evaluating a time of halting the proactive message initiation by the at least one engagement bot 210 based on the detection of the determined message flow rate being above a predetermined threshold level. Furthermore, the method 1600 may include determining the proactive message initiation by the at least one engagement bot 210 in the chatroom 204 based on one of the evaluated times.

[0237] In an embodiment, the method 1600, for determining the reactive message initiation by the at least one engagement bot 210 in the chatroom 204 at step 1610, may include determining presence of one or more users 208 in the chatroom 204, and evaluating a time for the reactive message initiation by the at least one engagement bot 210 based on the detection of the determined message flow rate being below a predetermined threshold level. In an embodiment, the initiated message may be based on the emotion drift of the chatroom 204, and the user profile of the one or more users 208. In an embodiment, the time of initiation of the message by the at least one engagement bot 210 is determined in response to each new message among the one or more messages captured from the real-time upstream 206. The method 1600 may further include evaluating a time of halting the reactive message initiation by the at least one engagement bot 210 based on the detection of the determined message flow rate being above a predetermined threshold level. Furthermore, the method 1600 may include determining the reactive message initiation by the at least one engagement bot 210 in the chatroom 204 based on one of the evaluated times.

[0238] In an embodiment, the method 1600, for generating the prompt at step 1612, may include classifying the determined one of, the proactive message initiation and the reactive message initiation based on a purpose comprising one of an interrogative, an imperative, an exclamatory, and a declarative message. The method 1600 may further include selecting a pre-created prompt template from a set of pre-created prompt templates based on the classified purpose of the determined one of the proactive message initiation and reactive message initiation. The method 1600 may further include ingesting the selected pre-created prompt template with information tags, wherein the information tags correspond to at least one of, a title of the chatroom 204, a genre of the chatroom 204, a name of the communication channel, the generated micro tag, a date, and a username of one of the one or more users 208. Furthermore, the method 1600 may include generating the prompt using the ingested prompt pre-created template.

[0239] In an embodiment, the method 1600, for generating the adaptive message at step 1614, may include selecting at least one language model based on the classified purpose of the determined one of, proactive message initiation and reactive message initiation. The method 1600 may further include inferencing the generated prompt using the selected at least one language model, wherein the at least one language model comprises at least one of, a pre-set recommendation module and a generative Artificial Intelligence (genAI) based language model. Furthermore, the method 1600 may include generating the adaptive message for the chatroom (204) based on the inferenced generated prompt.

[0240] The present disclosure has several advantages over the related techniques, which are stated below.

[0241] The present disclosure may be implemented in a large panel displays like TV where one or more users 208 accumulate for transfer of thoughts while co-watching TV and may get inspired to involve more into the chatrooms.

[0242] The present disclosure provides a control mechanism for the genAI language model to control the start and stop of the generation of adaptive messages and may further enhance the conversation based on inputs from one or more users 208. This results in better user experience while being economical due to controlled use of Large Language Models.

[0243] The present disclosure further enhance user's experience in real time by analyzing the drift in the sentiments of the chatroom 204 and thereby enhancing the chatroom environment at various points of time giving one or more users 208 an interesting experience on large screens.

[0244] The present disclosure may further facilitate integration of in-house models or Purpose specific models along with 3rd Party large language (LLM) models (general Purpose).

[0245] According to an embodiment of the present disclosure, a method for generating an adaptive message for a chatroom (204) is disclosed. The method may include establishing (1602) the chatroom (204) to allow one or more users (208) and at least one engagement bot (210) to join and interact in the chatroom (204), wherein the engagement bot (210) indicates a virtual user. The method may include capturing (1604) one or more messages from a real-time upstream (206) of the one or more messages from the established chatroom (204), wherein the real-time upstream (206) indicates an inflow of the one or more messages sent by the one or more users (208) in the chatroom (204). The method may include determining (1606) at least one of a message flow rate, an emotion drift of the chatroom (204), and one or more users (208) interacting in the chatroom (204) from the captured real-time upstream (206) of one or more messages. The method may include determining (1608) one or more user profiles (U) associated with the one or more users (208) from the captured real-time upstream (206) of one or more messages. The method may include determining (1610) one of, a proactive message initiation and a reactive message initiation based on the determined at least one of the message flow rate, the emotion drift of the chatroom (204), and the user profile of the one or more users (208). In an embodiment, the proactive message initiation may indicate a requirement for initiating a message by the at least one engagement bot (210) in the chatroom (204). In an embodiment, reactive message initiation may indicate a requirement for initiating a reply by the at least one engagement bot (210) to the one or more messages captured from the real-time upstream (206). The method may include generating a prompt based on the determined one of, the proactive message initiation and the reactive message initiation. The method may include generating the adaptive message for the chatroom (204) using at least one language model based on the generated prompt.

[0246] According to an embodiment of the present disclosure, the method may include publishing the generated adaptive message in the chatroom (204) by validating the generated adaptive message based on one or more predefined parameters.

[0247] According to an embodiment of the present disclosure, the one or more predefined parameters comprise a profanity check parameter, a hallucination check parameter, and a bias check parameter. According to an embodiment of the present disclosure, the method may include defining a context of the chatroom (204). The method may include assigning a communication channel configured to allow one or more users (208) and the at least one engagement bot (210) to join a session of the chatroom (204) with the defined context. The method may include establishing the chatroom (204) by scheduling a first predefined time duration for the session to remain active.

[0248] According to an embodiment of the present disclosure, the least one engagement bot (210) may be configured with one of, a predetermined notion based on a pre-set opinion, a pre-set context, and a pre-set knowledge. According to an embodiment of the present disclosure, the method may include bifurcating the real-time upstream (206) into a plurality of streams for parallel processing wherein each of the plurality of streams includes one or more message metadata (Oi). the method may include filtering the plurality of streams based on at least one of the one or more message metadata (Oi). The method may include capturing the one or more messages based on the filtered plurality of streams.

[0249] According to an embodiment of the present disclosure, the one or more message metadata (Oi) comprises information relating to at least one of, a message content (mi), sender's information (si), a message timestamp (ti), a message category (ci), a message action (ai), and an emotion of the message (ei). According to an embodiment of the present disclosure, the method may include extracting a time instance of a second predefined time duration from the captured real-time upstream (206) of one or more message flows. The method may include extracting a further time instance of the second predefined time with a shift of a third predefined time duration from the first time instance. The method may include aggregating the extracted time instances, wherein the aggregation may comprise one of, sliding window aggregation operation, tumbling window aggregation operation, time sliding aggregation operation, and eviction sliding aggregation operation. The method may include determining the message flow rate based on the aggregation.

[0250] According to an embodiment of the present disclosure, the method may include extracting one or more messages from the captured real-time upstream (206) of one or more message flows, wherein the one or more messages include at least one of a text and emoticons. The method may include extracting an emotion vector from the extracted one or more messages. The method may include computing the extracted emotion vector with an initial emotion vector of the chatroom (204), wherein the initial emotion vector of the chatroom (204) is predetermined. The method may include determining the emotion drift of the chatroom (204) based on the computation.

[0251] According to an embodiment of the present disclosure, the method may include updating the emotion vector of the chatroom (204) based on the determined emotion drift using a momentum factor, wherein the momentum factor, based on a predefined threshold value, influences an impact of the emotion vector from the extracted one or more messages on the emotion drift of the chatroom (204).

[0252] According to an embodiment of the present disclosure, the method may include construing words and emoticons from the extracted one or more messages into one of, textual tokens and pictorial tokens, respectively. The method may include computing at least one of the textual tokens and the pictorial tokens into a vector based on a probability of one or more emotion dimensions associated with the construed textual tokens and pictorial tokens. The method may include extracting the emotion vector from the extracted one or more messages based on the computed textual tokens and the pictorial tokens.

[0253] According to an embodiment of the present disclosure, the method may include retrieving historic involvement patterns data for each of the one or more users (208) from an internal database. The method may include determining real-time involvement patterns based on a frequency of interaction data of each of the one or more users (208) with the at least one engagement bot (210) based on a reply message sent by each of the one or more users (208) to the one or more adaptive messages published by the least one engagement bot (210) in the chatroom (204). The method may include determining real-time involvement patterns based on an emotion data associated with the reply message sent by each of the one or more users (208) in the chatroom (204). The method may include determining real-time involvement patterns based on determining the one or more user profiles (U) associated with the one or more users (208) based on the retrieved historic involvement patterns data, the frequency of interaction data, and the emotion data.

[0254] According to an embodiment of the present disclosure, the method may include retrieving a retention factor of each of the one or more users (208), wherein the retention factor is determined based on amount of time which one of the one or more users (208) stays in the current chatroom (204) and the total time span of the current chatroom (204). The method may include retrieving an involvement factor of each of the one or more users (208), wherein the involvement factor is determined based on at least one of: one or more messages sent by each of the one or more users (208) in the current chatroom (204) and the total messages exchanged in the current chatroom (204), or one or more messages sent by each of the one or more users (208) in each one or more historic chatrooms and the total messages exchanged in each of the one or more historic chatrooms. The method may include retrieving a diversity quotient of each of the one or more users, wherein the diversity quotient is determined based on one or more historic chatrooms joined by the one or more users (208). The method may include determining genre group orientation of each of the one or more users (208), by evaluating a historic genre preference of each of the one or more users (208). The method may include determining the historic involvement patterns data for each of the one or more users (208) based on the determined retention factor, the determined involvement factor, the determined diversity quotient, and the determined genre group orientation.

[0255] According to an embodiment of the present disclosure, the method may include generating an event message for an event streaming on a video content being consumed by the one or more users (208). The method may include detecting one of a scene and event stream being consumed by the one or more users (208) using a machine learning model. The method may include mapping a predefined time instance of the streamed event, with at least one of, a time stamp, context of the streamed event, probability of occurrence of the streamed event. The method may include generating a micro tag based on the mapped predefined time instance of the streamed event. The method may include generating the event message for the event streaming on the video content based on the generated micro tag.

[0256] According to an embodiment of the present disclosure, the at least one engagement bot (210), based on the generated event message, may publish the generated event message into the chatroom (204). According to an embodiment of the present disclosure, the method may include determining presence of one or more users (208) in the chatroom (204). The method may include evaluating a time of the proactive message initiation by the at least one engagement bot (210) based on a detection of the determined message flow rate being zero. According to an embodiment of the present disclosure, the initiated message may be based on the emotion drift of the chatroom (204), and the user profile of the one or more users (208). According to an embodiment of the present disclosure, the time of initiation of the message by the at least one engagement bot (210) may be periodically evaluated. According to an embodiment of the present disclosure, the method may include evaluating a time of halting the proactive message initiation by the at least one engagement bot (210) based on the detection of the determined message flow rate being above a predetermined threshold level. The method may include determining the proactive message initiation by the at least one engagement bot (210) in the chatroom (204) based on one of the evaluated time.

[0257] According to an embodiment of the present disclosure, the method may include determining presence of one or more users (208) in the chatroom (204). The method may include evaluating a time for the reactive message initiation by the at least one engagement bot (210) based on the detection of the determined message flow rate being below a predetermined threshold level. According to an embodiment of the present disclosure, the initiated message may be based on the emotion drift of the chatroom (204), and the user profile of the one or more users (208). According to an embodiment of the present disclosure, the time of initiation of the message by the at least one engagement bot (210) may be determined in response to each new message among the one or more messages captured from the real-time upstream (206). The method may include evaluating a time of halting the reactive message initiation by the at least one engagement bot (210) based on the detection of the determined message flow rate being above a predetermined threshold level. The method may include determining the reactive message initiation by the at least one engagement bot (210) in the chatroom (204) based on one of the evaluated time.

[0258] According to an embodiment of the present disclosure, the method may include classifying the determined one of, the proactive message initiation and the reactive message initiation based on a purpose comprising one of an interrogative, an imperative, an exclamatory, and a declarative message. The method may include selecting a pre-created prompt template from a set of pre-created prompt templates based on the classified purpose of the determined one of the proactive message initiation and reactive message initiation. The method may include ingesting the selected pre-created prompt template with information tags, wherein the information tags correspond to at least one of, a title of the chatroom (204), a genre of the chatroom (204), a name of the communication channel, the generated micro tag, a date, and a username of one of the one or more users (208). The method may include generating the prompt using the ingested prompt pre-created template.

[0259] According to an embodiment of the present disclosure, the method may include selecting at least one language model based on the classified purpose of the determined one of, proactive message initiation and reactive message initiation. The method may include inferencing the generated prompt using the selected at least one language model, wherein the at least one language model comprises at least one of, a pre-set recommendation module and a generative Artificial Intelligence (genAI) based language model. The method may include generating the adaptive message for the chatroom (204) based on the inferenced generated prompt.

[0260] According to an embodiment of the present disclosure, a system (202) for generating an adaptive message for a chatroom (204) is disclosed herein. The system (202) may include a bootstrapping module (312) configured to establish the chatroom (204) to allow one or more users (208) and at least one engagement bot (210) to join and interact in the chatroom (204), wherein the engagement bot (210) indicates a virtual user. The system (202) may include an orchestration module (314) configured to capture one or more messages from a real-time upstream (206) of the one or more messages from the established chatroom (204), wherein the real-time upstream (206) indicates an inflow of the one or more messages sent by the one or more users in the chatroom (204). The system (202) may include an orchestration module (314) configured to determine at least one of a message flow rate, an emotion drift of the chatroom (204), and one or more users (208) interacting in the chatroom (204) from the captured real-time upstream (206) of one or more messages. The system (202) may include an orchestration module (314) configured to determine one or more user profiles (U) associated with the one or more users (208) from the captured real-time upstream (206) of one or more messages. The system (202) may include a decision module (316) configured to determine one of, a proactive message initiation and a reactive message initiation based on the determined at least one of the message flow rate, the emotion drift of the chatroom (204), and the user profile of the one or more users (208), According to an embodiment of the present disclosure, the proactive message initiation may indicate a requirement for initiating a message by the at least one engagement bot (210) in the chatroom (208). According to an embodiment of the present disclosure, the reactive message initiation may indicate a requirement for initiating a reply by the at least one engagement bot (210) to the one or more messages captured from the real-time upstream (206). According to an embodiment of the present disclosure, a message generation module (318) may be configured to generate a prompt based on the determined one of, the proactive message initiation and the reactive message initiation. According to an embodiment of the present disclosure, a message generation module (318) may be configured to generate the adaptive message for the chatroom (204) using at least one language model based on the generated prompt.

[0261] According to an embodiment of the present disclosure, the system (202) may include a publishing module (320) configured to validate the generated adaptive message based on one or more predefined parameters. According to an embodiment of the present disclosure, the system (202) may include a publishing module (320) configured to publish the generated adaptive message in the chatroom (204) based on the validation.

[0262] According to an embodiment of the present disclosure, the one or more predefined parameters may include a profanity check parameter, a hallucination check parameter, and a bias check parameter.

[0263] According to an embodiment of the present disclosure, to establish the chatroom (204), the bootstrapping module (312) may be configured to define a context of the chatroom (204). According to an embodiment of the present disclosure, the bootstrapping module (312) may be configured to assign a communication channel configured to allow one or more users (208) and the at least one engagement bot (210) to join a session of the chatroom (204) with the defined context. According to an embodiment of the present disclosure, the bootstrapping module (312) may be configured to establish the chatroom (204) by scheduling a first predefined time duration for the session to remain active.

[0264] According to an embodiment of the present disclosure, the least one engagement bot (210) may be configured with one of, a predetermined notion based on a pre-set opinion, a pre-set context, and a pre-set knowledge. According to an embodiment of the present disclosure, to capture the one or more messages from the real-time upstream (206) of the one or more messages from the established chatroom (204), the orchestration module (314) may be configured to bifurcate the real-time upstream (206) into a plurality of streams for parallel processing wherein each of the plurality of streams includes one or more message metadata (Oi). According to an embodiment of the present disclosure, to capture the one or more messages from the real-time upstream (206) of the one or more messages from the established chatroom (204), the orchestration module (314) may be configured to filter the plurality of streams based on at least one of the one or more message metadata (Oi). According to an embodiment of the present disclosure, to capture the one or more messages from the real-time upstream (206) of the one or more messages from the established chatroom (204), the orchestration module (314) may be configured to capture the one or more messages based on the filtered plurality of streams.

[0265] According to an embodiment of the present disclosure, the one or more message metadata (Oi) may include information relating to at least one of, a message content (mi), sender's information (si), a message timestamp (ti), a message category (ci), a message action (ai), and an emotion of the message (ei).

[0266] According to an embodiment of the present disclosure, the orchestration module (314) may be configured to extract a time instance of a second predefined time duration from the captured real-time upstream (206) of one or more message flows. According to an embodiment of the present disclosure, the orchestration module (314) may be configured to extract a further time instance of the second predefined time with a shift of a third predefined time duration from the first time instance. According to an embodiment of the present disclosure, the orchestration module (314) may be configured to aggregate the extracted time instances, wherein the aggregation may comprise one of, sliding window aggregation operation, tumbling window aggregation operation, time sliding aggregation operation, and eviction sliding aggregation operation. According to an embodiment of the present disclosure, the orchestration module (314) may be configured to determine the message flow rate based on the aggregation.

[0267] According to an embodiment of the present disclosure, to determine the emotion drift of the chatroom, the orchestration module (314) may be configured to extract one or more messages from the captured real-time upstream (206) of one or more message flows, wherein the one or more messages include at least one of a text and emoticons. According to an embodiment of the present disclosure, to determine the emotion drift of the chatroom, the orchestration module (314) may be configured to extract an emotion vector from the extracted one or more messages. According to an embodiment of the present disclosure, to determine the emotion drift of the chatroom, the orchestration module (314) may be configured to compute the extracted emotion vector with an initial emotion vector of the chatroom (204), wherein the initial emotion vector of the chatroom (204) is predetermined. According to an embodiment of the present disclosure, to determine the emotion drift of the chatroom, the orchestration module (314) may be configured to determine the emotion drift of the chatroom (204) based on the computation.

[0268] According to an embodiment of the present disclosure, the orchestration module (314) may be configured to update the emotion vector of the chatroom (204) based on the determined emotion drift using a momentum factor, wherein the momentum factor, based on a predefined threshold value, influences an impact of the emotion vector from the extracted one or more messages on the emotion drift of the chatroom (204). According to an embodiment of the present disclosure, to extract the emotion vector from the extracted one or more messages, the orchestration module (314) may be configured to construe words and emoticons from the extracted one or more messages into one of, textual tokens and pictorial tokens, respectively. According to an embodiment of the present disclosure, to extract the emotion vector from the extracted one or more messages, the orchestration module (314) may be configured to compute at least one of the textual tokens and the pictorial tokens into a vector based on a probability of one or more emotion dimensions associated with the construed textual tokens and pictorial tokens. According to an embodiment of the present disclosure, to extract the emotion vector from the extracted one or more messages, the orchestration module (314) may be configured to extract the emotion vector from the extracted one or more messages based on the computed textual tokens and the pictorial tokens.

[0269] According to an embodiment of the present disclosure, to determine the one or more user profiles (U) associated with the one or more users (208), the orchestration module (314) may be configured to retrieve historic involvement patterns data for each of the one or more users (208) from an internal database. According to an embodiment of the present disclosure, to determine the one or more user profiles (U) associated with the one or more users (208), the orchestration module (314) may be configured to determine real-time involvement patterns based on a frequency of interaction data of each of the one or more users (208) with the at least one engagement bot (210) based on a reply message sent by each of the one or more users (208) to the one or more adaptive messages published by the least one engagement bot (210) in the chatroom (204). According to an embodiment of the present disclosure, to determine the one or more user profiles (U) associated with the one or more users (208), the orchestration module (314) may be configured to determine real-time involvement patterns based on a frequency of interaction data of each of the one or more users (208) with the at least one engagement bot (210) based on an emotion data associated with the reply message sent by each of the one or more users (208) in the chatroom (204). According to an embodiment of the present disclosure, to determine the one or more user profiles (U) associated with the one or more users (208), the orchestration module (314) may be configured to determine the one or more user profiles (U) associated with the one or more users (208) based on the retrieved historic involvement patterns data, the frequency of interaction data, and the emotion data.

[0270] According to an embodiment of the present disclosure, to retrieve the historic involvement patterns data for each of the one or more users (208) from the internal database, the orchestration module (314) may be configured to retrieve a retention factor of each of the one or more users (208), wherein the retention factor is determined based on amount of time which one of the one or more users (208) stays in the current chatroom (204) and the total time span of the current chatroom (204). According to an embodiment of the present disclosure, to retrieve the historic involvement patterns data for each of the one or more users (208) from the internal database, the orchestration module (314) may be configured to retrieve an involvement factor of each of the one or more users (208), wherein the involvement factor is determined based on at least one of: one or more messages sent by each of the one or more users (208) in the current chatroom (204) and the total messages exchanged in the current chatroom (204), or one or more messages sent by each of the one or more users (208) in each one or more historic chatrooms and the total messages exchanged in each of the one or more historic chatrooms. According to an embodiment of the present disclosure, to retrieve the historic involvement patterns data for each of the one or more users (208) from the internal database, the orchestration module (314) may be configured to retrieve a diversity quotient of each of the one or more users (208), wherein the diversity quotient is determined based on one or more historic chatrooms joined by the one or more users (208). According to an embodiment of the present disclosure, to retrieve the historic involvement patterns data for each of the one or more users (208) from the internal database, the orchestration module (314) may be configured to determine genre group orientation of each of the one or more users (208), by evaluating a historic genre preference of each of the one or more users (208). According to an embodiment of the present disclosure, to retrieve the historic involvement patterns data for each of the one or more users (208) from the internal database, the orchestration module (314) may be configured to determine the historic involvement patterns data for each of the one or more users (208) based on the determined retention factor, the determined involvement factor, the determined diversity quotient, and the determined genre group orientation.

[0271] According to an embodiment of the present disclosure, the decision module (316) may be further configured to generate an event message for an event (402) streaming on a video content being consumed by the one or more users (208) by detecting one of a scene and event (402) stream being consumed by the one or more users (208) using a machine learning model. According to an embodiment of the present disclosure, the decision module (316) may be further configured to generate an event message for an event (402) streaming on a video content being consumed by the one or more users (208) by mapping a predefined time instance of the streamed event (402), with at least one of, a time stamp, context of the streamed event (402), probability of occurrence of the streamed event (402). According to an embodiment of the present disclosure, the decision module (316) may be further configured to generate an event message for an event (402) streaming on a video content being consumed by the one or more users (208) by generating a micro tag based on the mapped predefined time instance of the streamed event (402). According to an embodiment of the present disclosure, the decision module (316) may be further configured to generate an event message for an event (402) streaming on a video content being consumed by the one or more users (208) by generating the event message for the event (402) streaming on the video content based on the generated micro tag.

[0272] According to an embodiment of the present disclosure, the publishing module (320) may be configured to publish the generated event message into the chatroom (204) via the at least one engagement bot (210). According to an embodiment of the present disclosure, to determine the proactive message initiation by the at least one engagement bot (210) in the chatroom (204), the decision module (316) may be configured to determine presence of one or more users (208) in the chatroom. According to an embodiment of the present disclosure, to determine the proactive message initiation by the at least one engagement bot (210) in the chatroom (204), the decision module (316) may be configured to evaluate a time of the proactive message initiation by the at least one engagement bot (210) based on a detection of the determined message flow rate being zero. According to an embodiment of the present disclosure, the initiated message may be based on the emotion drift of the chatroom (204), and the user profile of the one or more users (208). According to an embodiment of the present disclosure, the initiated message may be based on the time of initiation of the message by the at least one engagement bot (210) is periodically evaluated. According to an embodiment of the present disclosure, the publishing module (320) may be configured to evaluate a time of halting the proactive message initiation by the at least one engagement bot (210) based on the detection of the determined message flow rate being above a predetermined threshold level. According to an embodiment of the present disclosure, the publishing module (320) may be configured to determine the proactive message initiation by the at least one engagement bot (210) in the chatroom (204) based on one of the evaluated times.

[0273] According to an embodiment of the present disclosure, the publishing module (320) may be configured to determine presence of one or more users (208) in the chatroom. According to an embodiment of the present disclosure, the publishing module (320) may be configured to evaluate a time for the reactive message initiation by the at least one engagement bot (210) based on the detection of the determined message flow rate being below a predetermined threshold level. According to an embodiment of the present disclosure, the initiated message may be based on the emotion drift of the chatroom (204), and the user profile of the one or more users (208). According to an embodiment of the present disclosure, the initiated message may be based on the time of initiation of the message by the at least one engagement bot (210) is determined in response to each new message among the one or more messages captured from the real-time upstream (206). According to an embodiment of the present disclosure, the publishing module (320) may be configured to evaluate a time of halting the reactive message initiation by the at least one engagement bot (210) based on the detection of the determined message flow rate being above a predetermined threshold level. According to an embodiment of the present disclosure, the publishing module (320) may be configured to determine the reactive message initiation by the at least one engagement bot (210) in the chatroom (204) based on one of the evaluated times.

[0274] According to an embodiment of the present disclosure, to generate the prompt, the message generation module (318) may be configured to classify the determined one of, the proactive message initiation and the reactive message initiation based on a purpose comprising one of an interrogative, an imperative, an exclamatory, and a declarative message. According to an embodiment of the present disclosure, to generate the prompt, the message generation module (318) may be configured to select a pre-created prompt template from a set of pre-created prompt templates based on the classified purpose of the determined one of the proactive message initiation and reactive message initiation. According to an embodiment of the present disclosure, to generate the prompt, the message generation module (318) may be configured to ingest the selected pre-created prompt template with information tags, wherein the information tags correspond to at least one of, a title of the chatroom (204), a genre of the chatroom (204), a name of the communication channel, the generated micro tag, a date, and a username of one of the one or more users (208). According to an embodiment of the present disclosure, to generate the prompt, the message generation module (318) may be configured to generate the prompt using the ingested prompt pre-created template.

[0275] According to an embodiment of the present disclosure, to generate the adaptive message, the message generation module (318) may be configured to select at least one language model based on the classified purpose of the determined one of, proactive message initiation and reactive message initiation. According to an embodiment of the present disclosure, to generate the adaptive message, the message generation module (318) may be configured to inference the generated prompt using the selected at least one language model, wherein the at least one language model comprises at least one of, a pre-set recommendation module and a generative Artificial Intelligence (genAI) based language model. According to an embodiment of the present disclosure, to generate the adaptive message, the message generation module (318) may be configured to generate the adaptive message for the chatroom (204) based on the inferenced generated prompt.

[0276] According to an embodiment of the present disclosure, a method (1600) is disclosed. The method may include identifying (1604) one or more messages from a real-time upstream (206) of the one or more messages from chatroom (204) including one or more users (208) and at least one engagement bot (210) representing a virtual user that interacts with the one or more users (208). The real-time upstream (206) may indicate an inflow of the one or more messages sent by the one or more users (208) in the chatroom (204). The method may include determining (1606) at least one of a message flow rate, an emotion drift of the chatroom (204), or interaction of one or more users (208) in the chatroom (204) from the obtained real-time upstream (206) of one or more messages. The method may include identifying (1608) one or more user profiles (U) corresponding to the one or more users (208) from the obtained real-time upstream (206) of one or more messages. The method may include determining (1610) whether to perform a proactive message initiation or a reactive message initiation based on the determined at least one of the message flow rate, the emotion drift of the chatroom (204), or the user profile of the one or more users (208). The proactive message initiation may indicate initiating a message by the at least one engagement bot (210) in the chatroom (204). The reactive message initiation may indicate initiating a reply by the at least one engagement bot (210) to the one or more messages obtained from the real-time upstream (206). The method may include generating (1612) a prompt, based on the determination to perform the proactive message initiation or the reactive message initiation. The method may include generating (1614) the adaptive message for the chatroom (204) based on at least one language model based on the generated prompt.

[0277] According to an embodiment of the present disclosure, the method may include publishing the generated adaptive message in the chatroom (204) by validating the generated adaptive message based on one or more predefined parameters.

[0278] According to an embodiment of the present disclosure, the one or more predefined parameters may include at least one of a profanity check parameter, a hallucination check parameter, or a bias check parameter.

[0279] According to an embodiment of the present disclosure, the method may include establishing the chatroom (204) to allow one or more users (208) and at least one engagement bot (210) to join and interact in the chatroom (204), wherein the engagement bot (210) indicates a virtual user.

[0280] According to an embodiment of the present disclosure, the method may include bifurcating the real-time upstream (206) into a plurality of streams for parallel processing wherein each of the plurality of streams includes one or more message metadata (Oi). The method may include filtering the plurality of streams based on at least one of the one or more message metadata (Oi). The method may include obtaining the one or more messages based on the filtered plurality of streams.

[0281] According to an embodiment of the present disclosure, the one or more message metadata (Oi) may include information relating to at least one of, a message content (mi), sender's information (si), a message timestamp (ti), a message category (ci), a message action (ai), or an emotion of the message (ei).

[0282] According to an embodiment of the present disclosure, the method may include identifying a time instance of a second predefined time duration from the obtained real-time upstream (206) of one or more message flows. The method may include identifying a further time instance of the second predefined time with a shift of a third predefined time duration from the first time instance. The method may include aggregating the identified time instances, wherein the aggregation may comprise one of, sliding window aggregation operation, tumbling window aggregation operation, time sliding aggregation operation, or eviction sliding aggregation operation. The method may include determining the message flow rate based on the aggregation.

[0283] According to an embodiment of the present disclosure, the method may include identifying one or more messages from the obtained real-time upstream (206) of one or more message flows, wherein the one or more messages include at least one of a text or emoticons. The method may include identifying an emotion vector from the identified one or more messages. The method may include determining the emotion drift of the chatroom (204) based on the identified emotion vector and an initial emotion vector of the chatroom (204), wherein the initial emotion vector of the chatroom (204) is predetermined.

[0284] According to an embodiment of the present disclosure, the method may include identifying historic involvement patterns data for each of the one or more users (208). The method may include determining real-time involvement patterns based on a frequency of interaction data of each of the one or more users (208) with the at least one engagement bot (210) based on a reply message sent by each of the one or more users (208) to the one or more adaptive messages published by the least one engagement bot (210) in the chatroom (204). The method may include determining real-time involvement patterns based on an emotion data associated with the reply message sent by each of the one or more users (208) in the chatroom (204). The method may include determining the one or more user profiles (U) corresponding to the one or more users (208) based on the identified historic involvement patterns data, the frequency of interaction data, and the emotion data.

[0285] According to an embodiment of the present disclosure, the method may include identifying presence of one or more users (208) in the chatroom (204). According to an embodiment of the present disclosure, the method may include determining a time of the proactive message initiation periodically by the at least one engagement bot (210) based on a detection of the determined message flow rate being zero. According to an embodiment of the present disclosure, the initiated message may be based on the emotion drift of the chatroom (204), and the user profile of the one or more users (208). According to an embodiment of the present disclosure, the method may include determining a time of halting the proactive message initiation by the at least one engagement bot (210) based on the detection of the determined message flow rate being above a predetermined threshold level. According to an embodiment of the present disclosure, the method may include determining the proactive message initiation by the at least one engagement bot (210) in the chatroom (204) based on one of the determined time.

[0286] According to an embodiment of the present disclosure, the method may include identifying presence of one or more users (208) in the chatroom (204). The method may include determining a time for the reactive message initiation by the at least one engagement bot (210) in response to each new message among the one or more messages obtained from the real-time upstream (206), based on the detection of the determined message flow rate being below a predetermined threshold level. The initiated message may be based on the emotion drift of the chatroom (204), and the user profile of the one or more users (208). The method may include determining a time of halting the reactive message initiation by the at least one engagement bot (210) based on the detection of the determined message flow rate being above a predetermined threshold level. The method may include determining the reactive message initiation by the at least one engagement bot (210) in the chatroom (204) based on one of the determined time.

[0287] According to an embodiment of the present disclosure, the method may include classifying the determined one of, the proactive message initiation and the reactive message initiation based on a purpose comprising one of an interrogative, an imperative, an exclamatory, and a declarative message. According to an embodiment of the present disclosure, the method may include selecting a pre-generated prompt template from a set of pre-generated prompt templates based on the classified purpose of the determined one of the proactive message initiation and reactive message initiation. According to an embodiment of the present disclosure, the method may include ingesting the selected pre-generated prompt template with information tags, wherein the information tags correspond to at least one of, a title of the chatroom (204), a genre of the chatroom (204), a name of the communication channel, the generated micro tag, a date, or a username of one of the one or more users (208). According to an embodiment of the present disclosure, the method may include generating the prompt using the ingested prompt pre-generated template.

[0288] According to an embodiment of the present disclosure, the method may include identifying at least one language model based on the classified purpose of the determined one of, proactive message initiation and reactive message initiation. The method may include inferencing the generated prompt using the identified at least one language model, wherein the at least one language model comprises at least one of, a pre-set recommendation module and a generative Artificial Intelligence (genAI) based language model. The method may include generating the adaptive message for the chatroom (204) based on the inferenced generated prompt.

[0289] According to an embodiment of the present disclosure, an electronic device (202) comprising at least one processor comprising processing circuitry; and at least one memory including one or more instructions is disclosed. The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to identify one or more messages from a real-time upstream (206) of the one or more messages from chatroom (204) including one or more users (208) and at least one engagement bot (210) representing a virtual user that interacts with the one or more users (208), wherein the real-time upstream (206) indicates an inflow of the one or more messages sent by the one or more users (208) in the chatroom (204). The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to　determine at least one of a message flow rate, an emotion drift of the chatroom (204), or interaction of one or more users (208) in the chatroom (204) from the obtained real-time upstream (206) of one or more messages. The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to identify one or more user profiles (U) corresponding to the one or more users (208) from the obtained real-time upstream (206) of one or more messages. The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine whether to perform a proactive message initiation or a reactive message initiation based on the determined at least one of the message flow rate, the emotion drift of the chatroom (204), or the user profile of the one or more users (208). The proactive message initiation indicates initiating a message by the at least one engagement bot (210) in the chatroom (204). The reactive message initiation indicates initiating a reply by the at least one engagement bot (210) to the one or more messages captured from the real-time upstream (206). The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to generate a prompt, based on the determination to perform the proactive message initiation or the reactive message initiation. The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to generate the adaptive message for the chatroom (204) based on at least one language model based on the generated prompt.

[0290] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to publish the generated adaptive message in the chatroom (204) by validating the generated adaptive message based on one or more predefined parameters.

[0291] According to an embodiment of the present disclosure, the one or more predefined parameters may include at least one of a profanity check parameter, a hallucination check parameter, or a bias check parameter.

[0292] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to establish the chatroom (204) to allow one or more users (208) and at least one engagement bot (210) to join and interact in the chatroom (204), wherein the engagement bot (210) indicates a virtual user.

[0293] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to bifurcate the real-time upstream (206) into a plurality of streams for parallel processing wherein each of the plurality of streams includes one or more message metadata (Oi). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to filter the plurality of streams based on at least one of the one or more message metadata (Oi). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to obtain the one or more messages based on the filtered plurality of streams.

[0294] According to an embodiment of the present disclosure, the one or more message metadata (Oi) may include information relating to at least one of, a message content (mi), sender's information (si), a message timestamp (ti), a message category (ci), a message action (ai), or an emotion of the message (ei).

[0295] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to identify a time instance of a second predefined time duration from the obtained real-time upstream (206) of one or more message flows. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to identify a further time instance of the second predefined time with a shift of a third predefined time duration from the first time instance. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to aggregate the identified time instances, wherein the aggregation may comprise one of, sliding window aggregation operation, tumbling window aggregation operation, time sliding aggregation operation, or eviction sliding aggregation operation. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine the message flow rate based on the aggregation.

[0296] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to identify one or more messages from the obtained real-time upstream (206) of one or more message flows, wherein the one or more messages include at least one of a text or emoticons. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to identify an emotion vector from the identified one or more messages. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine the emotion drift of the chatroom (204) based on the identified emotion vector and an initial emotion vector of the chatroom (204), wherein the initial emotion vector of the chatroom (204) is predetermined.

[0297] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to identify historic involvement patterns data for each of the one or more users (208). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine real-time involvement patterns based on a frequency of interaction data of each of the one or more users (208) with the at least one engagement bot (210) based on a reply message sent by each of the one or more users (208) to the one or more adaptive messages published by the least one engagement bot (210) in the chatroom (204). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine real-time involvement patterns based on an emotion data associated with the reply message sent by each of the one or more users (208) in the chatroom (204). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine the one or more user profiles (U) corresponding to the one or more users (208) based on the identified historic involvement patterns data, the frequency of interaction data, and the emotion data.

[0298] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to identify presence of one or more users (208) in the chatroom (204). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine a time of the proactive message initiation periodically by the at least one engagement bot (210) based on a detection of the determined message flow rate being zero. According to an embodiment of the present disclosure, the initiated message may be based on the emotion drift of the chatroom (204), and the user profile of the one or more users (208). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine a time of halting the proactive message initiation by the at least one engagement bot (210) based on the detection of the determined message flow rate being above a predetermined threshold level. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine the proactive message initiation by the at least one engagement bot (210) in the chatroom (204) based on one of the determined time.

[0299] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to identify presence of one or more users (208) in the chatroom (204). the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine a time for the reactive message initiation by the at least one engagement bot (210) in response to each new message among the one or more messages obtained from the real-time upstream (206), based on the detection of the determined message flow rate being below a predetermined threshold level. The initiated message may be based on the emotion drift of the chatroom (204), and the user profile of the one or more users (208). the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine a time of halting the reactive message initiation by the at least one engagement bot (210) based on the detection of the determined message flow rate being above a predetermined threshold level. the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine the reactive message initiation by the at least one engagement bot (210) in the chatroom (204) based on one of the determined time.

[0300] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to classify the determined one of, the proactive message initiation and the reactive message initiation based on a purpose comprising one of an interrogative, an imperative, an exclamatory, and a declarative message. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to select a pre-generated prompt template from a set of pre-generated prompt templates based on the classified purpose of the determined one of the proactive message initiation and reactive message initiation. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to ingest the selected pre-generated prompt template with information tags, wherein the information tags correspond to at least one of, a title of the chatroom (204), a genre of the chatroom (204), a name of the communication channel, the generated micro tag, a date, or a username of one of the one or more users (208). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to generate the prompt using the ingested prompt pre-generated template.

[0301] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to identify at least one language model based on the classified purpose of the determined one of, proactive message initiation and reactive message initiation. The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to inference the generated prompt using the identified at least one language model, wherein the at least one language model comprises at least one of, a pre-set recommendation module and a generative Artificial Intelligence (genAI) based language model. The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to generate the adaptive message for the chatroom (204) based on the inferenced generated prompt.

[0302] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to establish the chatroom (204) to allow one or more users (208) and at least one engagement bot (210) to join and interact in the chatroom (204), wherein the engagement bot (210) indicates a virtual user. The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to capture one or more messages from a real-time upstream (206) of the one or more messages from the established chatroom (204), wherein the real-time upstream (206) indicates an inflow of the one or more messages sent by the one or more users in the chatroom (204). The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine at least one of a message flow rate, an emotion drift of the chatroom (204), and one or more users (208) interacting in the chatroom (204) from the captured real-time upstream (206) of one or more messages. The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine one or more user profiles (U) associated with the one or more users (208) from the captured real-time upstream (206) of one or more messages. The one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine one of, a proactive message initiation and a reactive message initiation based on the determined at least one of the message flow rate, the emotion drift of the chatroom (204), and the user profile of the one or more users (208), According to an embodiment of the present disclosure, the proactive message initiation may indicate a requirement for initiating a message by the at least one engagement bot (210) in the chatroom (208). According to an embodiment of the present disclosure, the reactive message initiation may indicate a requirement for initiating a reply by the at least one engagement bot (210) to the one or more messages captured from the real-time upstream (206). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to generate a prompt based on the determined one of, the proactive message initiation and the reactive message initiation. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to generate the adaptive message for the chatroom (204) using at least one language model based on the generated prompt.

[0303] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to validate the generated adaptive message based on one or more predefined parameters. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to publish the generated adaptive message in the chatroom (204) based on the validation.

[0304] According to an embodiment of the present disclosure, the one or more predefined parameters may include a profanity check parameter, a hallucination check parameter, and a bias check parameter.

[0305] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to define a context of the chatroom (204). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to allow one or more users (208) and the at least one engagement bot (210) to join a session of the chatroom (204) with the defined context. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to establish the chatroom (204) by scheduling a first predefined time duration for the session to remain active.

[0306] According to an embodiment of the present disclosure, the least one engagement bot (210) may be configured with one of, a predetermined notion based on a pre-set opinion, a pre-set context, and a pre-set knowledge. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to bifurcate the real-time upstream (206) into a plurality of streams for parallel processing wherein each of the plurality of streams includes one or more message metadata (Oi). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to filter the plurality of streams based on at least one of the one or more message metadata (Oi). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to capture the one or more messages based on the filtered plurality of streams.

[0307] According to an embodiment of the present disclosure, the one or more message metadata (Oi) may include information relating to at least one of, a message content (mi), sender's information (si), a message timestamp (ti), a message category (ci), a message action (ai), and an emotion of the message (ei).

[0308] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to extract a time instance of a second predefined time duration from the captured real-time upstream (206) of one or more message flows. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to extract a further time instance of the second predefined time with a shift of a third predefined time duration from the first time instance. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to aggregate the extracted time instances, wherein the aggregation may comprise one of, sliding window aggregation operation, tumbling window aggregation operation, time sliding aggregation operation, and eviction sliding aggregation operation. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine the message flow rate based on the aggregation.

[0309] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to extract one or more messages from the captured real-time upstream (206) of one or more message flows, wherein the one or more messages include at least one of a text and emoticons. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to extract an emotion vector from the extracted one or more messages. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to compute the extracted emotion vector with an initial emotion vector of the chatroom (204), wherein the initial emotion vector of the chatroom (204) is predetermined. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine the emotion drift of the chatroom (204) based on the computation.

[0310] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to update the emotion vector of the chatroom (204) based on the determined emotion drift using a momentum factor, wherein the momentum factor, based on a predefined threshold value, influences an impact of the emotion vector from the extracted one or more messages on the emotion drift of the chatroom (204). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to construe words and emoticons from the extracted one or more messages into one of, textual tokens and pictorial tokens, respectively. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to compute at least one of the textual tokens and the pictorial tokens into a vector based on a probability of one or more emotion dimensions associated with the construed textual tokens and pictorial tokens. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to extract the emotion vector from the extracted one or more messages based on the computed textual tokens and the pictorial tokens.

[0311] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to retrieve historic involvement patterns data for each of the one or more users (208) from an internal database. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine real-time involvement patterns based on a frequency of interaction data of each of the one or more users (208) with the at least one engagement bot (210) based on a reply message sent by each of the one or more users (208) to the one or more adaptive messages published by the least one engagement bot (210) in the chatroom (204). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine real-time involvement patterns based on a frequency of interaction data of each of the one or more users (208) with the at least one engagement bot (210) based on an emotion data associated with the reply message sent by each of the one or more users (208) in the chatroom (204). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine the one or more user profiles (U) associated with the one or more users (208) based on the retrieved historic involvement patterns data, the frequency of interaction data, and the emotion data.

[0312] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to retrieve a retention factor of each of the one or more users (208), wherein the retention factor is determined based on amount of time which one of the one or more users (208) stays in the current chatroom (204) and the total time span of the current chatroom (204). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to retrieve an involvement factor of each of the one or more users (208), wherein the involvement factor is determined based on at least one of: one or more messages sent by each of the one or more users (208) in the current chatroom (204) and the total messages exchanged in the current chatroom (204), or one or more messages sent by each of the one or more users (208) in each one or more historic chatrooms and the total messages exchanged in each of the one or more historic chatrooms. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to retrieve a diversity quotient of each of the one or more users (208), wherein the diversity quotient is determined based on one or more historic chatrooms joined by the one or more users (208). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine genre group orientation of each of the one or more users (208), by evaluating a historic genre preference of each of the one or more users (208). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine the historic involvement patterns data for each of the one or more users (208) based on the determined retention factor, the determined involvement factor, the determined diversity quotient, and the determined genre group orientation.

[0313] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to generate an event message for an event (402) streaming on a video content being consumed by the one or more users (208) by detecting one of a scene and event (402) stream being consumed by the one or more users (208) using a machine learning model. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to generate an event message for an event (402) streaming on a video content being consumed by the one or more users (208) by mapping a predefined time instance of the streamed event (402), with at least one of, a time stamp, context of the streamed event (402), probability of occurrence of the streamed event (402). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to generate an event message for an event (402) streaming on a video content being consumed by the one or more users (208) by generating a micro tag based on the mapped predefined time instance of the streamed event (402). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to generate an event message for an event (402) streaming on a video content being consumed by the one or more users (208) by generating the event message for the event (402) streaming on the video content based on the generated micro tag.

[0314] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to publish the generated event message into the chatroom (204) via the at least one engagement bot (210). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine presence of one or more users (208) in the chatroom. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to evaluate a time of the proactive message initiation by the at least one engagement bot (210) based on a detection of the determined message flow rate being zero. According to an embodiment of the present disclosure, the initiated message may be based on the emotion drift of the chatroom (204), and the user profile of the one or more users (208). According to an embodiment of the present disclosure, the initiated message may be based on the time of initiation of the message by the at least one engagement bot (210) is periodically evaluated. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to evaluate a time of halting the proactive message initiation by the at least one engagement bot (210) based on the detection of the determined message flow rate being above a predetermined threshold level. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine the proactive message initiation by the at least one engagement bot (210) in the chatroom (204) based on one of the evaluated times.

[0315] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine presence of one or more users (208) in the chatroom. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to evaluate a time for the reactive message initiation by the at least one engagement bot (210) based on the detection of the determined message flow rate being below a predetermined threshold level. According to an embodiment of the present disclosure, the initiated message may be based on the emotion drift of the chatroom (204), and the user profile of the one or more users (208). According to an embodiment of the present disclosure, the initiated message may be based on the time of initiation of the message by the at least one engagement bot (210) is determined in response to each new message among the one or more messages captured from the real-time upstream (206). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to evaluate a time of halting the reactive message initiation by the at least one engagement bot (210) based on the detection of the determined message flow rate being above a predetermined threshold level. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to determine the reactive message initiation by the at least one engagement bot (210) in the chatroom (204) based on one of the evaluated times.

[0316] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to classify the determined one of, the proactive message initiation and the reactive message initiation based on a purpose comprising one of an interrogative, an imperative, an exclamatory, and a declarative message. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to select a pre-created prompt template from a set of pre-created prompt templates based on the classified purpose of the determined one of the proactive message initiation and reactive message initiation. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to ingest the selected pre-created prompt template with information tags, wherein the information tags correspond to at least one of, a title of the chatroom (204), a genre of the chatroom (204), a name of the communication channel, the generated micro tag, a date, and a username of one of the one or more users (208). According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to generate the prompt using the ingested prompt pre-created template.

[0317] According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to select at least one language model based on the classified purpose of the determined one of, proactive message initiation and reactive message initiation. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to inference the generated prompt using the selected at least one language model, wherein the at least one language model comprises at least one of, a pre-set recommendation module and a generative Artificial Intelligence (genAI) based language model. According to an embodiment of the present disclosure, the one or more instructions are executed by the at least one processor individually or collectively, to cause the electronic device (202) to generate the adaptive message for the chatroom (204) based on the inferenced generated prompt.

[0318] It is understood that terms including "unit" or "module" at the end may refer to the unit for processing at least one function or operation and may be implemented in hardware, software, or a combination of hardware and software.

[0319] While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.

[0320] The drawings and the forgoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not limited to the manner described herein.

[0321] Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts necessarily need to be performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples. Numerous variations, whether explicitly given in the specification or not, such as differences in structure, dimension, and use of material, are possible. The scope of embodiments is at least as broad as given by the following claims.

[0322] Benefits, other advantages, and solutions to problems have been described above with regard to specific embodiments. However, the benefits, advantages, solutions to problems, and any component(s) that may cause any benefit, advantage, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential feature or component of any or all the claims.

[0323] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of at least one embodiment, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.

Claims

1.A method (1600) comprising:identifying (1604) one or more messages from a real-time upstream (206) of the one or more messages from chatroom (204) including one or more users (208) and at least one engagement bot (210) representing a virtual user that interacts with the one or more users (208), wherein the real-time upstream (206) indicates an inflow of the one or more messages sent by the one or more users (208) in the chatroom (204);determining (1606) at least one of a message flow rate, an emotion drift of the chatroom (204), or interaction of one or more users (208) in the chatroom (204) from the obtained real-time upstream (206) of one or more messages;identifying (1608) one or more user profiles (U) corresponding to the one or more users (208) from the obtained real-time upstream (206) of one or more messages;determining (1610) whether to perform a proactive message initiation or a reactive message initiation based on the determined at least one of the message flow rate, the emotion drift of the chatroom (204), or the user profile of the one or more users (208),wherein the proactive message initiation indicates initiating a message by the at least one engagement bot (210) in the chatroom (204), andwherein the reactive message initiation indicates initiating a reply by the at least one engagement bot (210) to the one or more messages obtained from the real-time upstream (206);generating (1612) a prompt, based on the determination to perform the proactive message initiation or the reactive message initiation; andgenerating (1614) the adaptive message for the chatroom (204) based on at least one language model based on the generated prompt.2.The method (1600) as claimed in claim 1, further comprising publishing the generated adaptive message in the chatroom (204) by validating the generated adaptive message based on one or more predefined parameters.3.The method (1600) as claimed in claim 2, wherein the one or more predefined parameters comprise at least one of a profanity check parameter, a hallucination check parameter, or a bias check parameter.4.The method (1600) as claimed in any one of claims 1 to 3, further comprising establishing the chatroom (204) to allow one or more users (208) and at least one engagement bot (210) to join and interact in the chatroom (204), wherein the engagement bot (210) indicates a virtual user.5.The method (1600) as claimed in any one of claims 1 to 4, wherein identifying the one or more messages from the real-time upstream (206) of the one or more messages from the chatroom comprises:bifurcating the real-time upstream (206) into a plurality of streams for parallel processing wherein each of the plurality of streams includes one or more message metadata (Oi);filtering the plurality of streams based on at least one of the one or more message metadata (Oi); andobtaining the one or more messages based on the filtered plurality of streams.6.The method (1600) as claimed in any one of claims 1 to 5, wherein the one or more message metadata (Oi) comprises information relating to at least one of, a message content (mi), sender’s information (si), a message timestamp (ti), a message category (ci), a message action (ai), or an emotion of the message (ei).7.The method (1600) as claimed in any one of claims 1 to 6, wherein determining the message flow rate comprises:identifying a time instance of a second predefined time duration from the obtained real-time upstream (206) of one or more message flows;identifying a further time instance of the second predefined time with a shift of a third predefined time duration from the first time instance;aggregating the identified time instances, wherein the aggregation may comprise one of, sliding window aggregation operation, tumbling window aggregation operation, time sliding aggregation operation, or eviction sliding aggregation operation; anddetermining the message flow rate based on the aggregation.8.The method (1600) as claimed in any one of claims 1 to 7, wherein determining the emotion drift of the chatroom (204) comprises:identifying one or more messages from the obtained real-time upstream (206) of one or more message flows, wherein the one or more messages include at least one of a text or emoticons;identifying an emotion vector from the identified one or more messages; anddetermining the emotion drift of the chatroom (204) based on the identified emotion vector and an initial emotion vector of the chatroom (204), wherein the initial emotion vector of the chatroom (204) is predetermined.9.The method (1600) as claimed in any one of claims 1 to 8, wherein determining the one or more user profiles (U) corresponding to the one or more users (208) comprises:identifying historic involvement patterns data for each of the one or more users (208);determining real-time involvement patterns based on:a frequency of interaction data of each of the one or more users (208) with the at least one engagement bot (210) based on a reply message sent by each of the one or more users (208) to the one or more adaptive messages published by the least one engagement bot (210) in the chatroom (204); andan emotion data associated with the reply message sent by each of the one or more users (208) in the chatroom (204); anddetermining the one or more user profiles (U) corresponding to the one or more users (208) based on the identified historic involvement patterns data, the frequency of interaction data, and the emotion data.10.The method (1600) as claimed in any one of claims 1 to 9, wherein determining whether to perform the proactive message initiation or a reactive message initiation comprises:identifying presence of one or more users (208) in the chatroom (204);determining a time of the proactive message initiation periodically by the at least one engagement bot (210) based on a detection of the determined message flow rate being zero, wherein:the initiated message is based on the emotion drift of the chatroom (204), and the user profile of the one or more users (208)determining a time of halting the proactive message initiation by the at least one engagement bot (210) based on the detection of the determined message flow rate being above a predetermined threshold level; anddetermining the proactive message initiation by the at least one engagement bot (210) in the chatroom (204) based on one of the determined time.11.The method (1600) as claimed in any one of claims 1 to 10, wherein determining whether to perform the proactive message initiation or the reactive message initiation by the at least one engagement bot (210) in the chatroom comprises:identifying presence of one or more users (208) in the chatroom (204);determining a time for the reactive message initiation by the at least one engagement bot (210) in response to each new message among the one or more messages obtained from the real-time upstream (206), based on the detection of the determined message flow rate being below a predetermined threshold level, wherein:the initiated message is based on the emotion drift of the chatroom (204), and the user profile of the one or more users (208)determining a time of halting the reactive message initiation by the at least one engagement bot (210) based on the detection of the determined message flow rate being above a predetermined threshold level; anddetermining the reactive message initiation by the at least one engagement bot (210) in the chatroom (204) based on one of the determined time.12.The method (1600) as claimed in any one of claims 1 to 11, wherein generating the prompt comprises:classifying the determined one of, the proactive message initiation and the reactive message initiation based on a purpose comprising one of an interrogative, an imperative, an exclamatory, and a declarative message;selecting a pre-generated prompt template from a set of pre-generated prompt templates based on the classified purpose of the determined one of the proactive message initiation and reactive message initiation;ingesting the selected pre-generated prompt template with information tags, wherein the information tags correspond to at least one of, a title of the chatroom (204), a genre of the chatroom (204), a name of the communication channel, the generated micro tag, a date, or a username of one of the one or more users (208); andgenerating the prompt using the ingested prompt pre-generated template.13.The method (1600) as claimed in any one of claims 1 to 12, wherein generating the adaptive message comprises:identifying at least one language model based on the classified purpose of the determined one of, proactive message initiation and reactive message initiation;inferencing the generated prompt using the identified at least one language model, wherein the at least one language model comprises at least one of, a pre-set recommendation module and a generative Artificial Intelligence (genAI) based language model; andgenerating the adaptive message for the chatroom (204) based on the inferenced generated prompt.14.An electronic device (202) comprising:at least one processor comprising processing circuitry; andat least one memory including one or more instructions, executed by the at least one processor individually or collectively, to cause the electronic device (202) to:identify one or more messages from a real-time upstream (206) of the one or more messages from chatroom (204) including one or more users (208) and at least one engagement bot (210) representing a virtual user that interacts with the one or more users (208), wherein the real-time upstream (206) indicates an inflow of the one or more messages sent by the one or more users (208) in the chatroom (204);determine at least one of a message flow rate, an emotion drift of the chatroom (204), or interaction of one or more users (208) in the chatroom (204) from the obtained real-time upstream (206) of one or more messages;identify one or more user profiles (U) corresponding to the one or more users (208) from the obtained real-time upstream (206) of one or more messages;determine whether to perform a proactive message initiation or a reactive message initiation based on the determined at least one of the message flow rate, the emotion drift of the chatroom (204), or the user profile of the one or more users (208),wherein the proactive message initiation indicates initiating a message by the at least one engagement bot (210) in the chatroom (204), andwherein the reactive message initiation indicates initiating a reply by the at least one engagement bot (210) to the one or more messages obtained from the real-time upstream (206);generate a prompt, based on the determination to perform the proactive message initiation or the reactive message initiation; andgenerate the adaptive message for the chatroom (204) based on at least one language model based on the generated prompt.15.A computer-readable medium containing instructions, wherein the instructions, when executed by at least one processor, cause the electronic device (202) to perform the method of any one of claims 1 to 13.

Images