System and method for providing a contextual response to a user

Abstract

The present subject matter relates to a system (100) and a method (300) for providing contextual responses to users through an advanced natural language processing (NLP) framework. The system (100) receives natural language input queries from users, identifies the intent of the queries using vector embeddings, and classifies the queries into transactional, non-domain specific, or non-transactional domain-specific categories. Based on the classified intent, the system (100) generates responses using a generic large language model (LLM) or domain-specific resolution models. Additionally, the system (100) translates the response from a second language to a user's preferred language, ensuring a contextual and relevant output. The response is then delivered through a virtual assistant, with the system's design enabling seamless multilingual communication and improving user experience. The system (100) significantly enhances the speed and accuracy of providing relevant and personalized responses to users, improving operational efficiency and communication in diverse linguistic environments.

Description

[0001] Title of Invention

[0002] SYSTEM AND METHOD FOR PROVIDING A CONTEXTUAL RESPONSE TO A USER

[0003] CROSS-REFERENCE TO RELATED APPLICATIONS AND PRIORITY

[0004] The present application claims priority from the Indian provisional patent application, having application number 202411031361, filed on 19thApril 2024, incorporated herein by a reference.

[0005] FIELD OF INVENTION

[0006] The present invention, in general, relates to the field of artificial intelligence and natural language processing and more particularly, relates to a system and a method for providing a contextual response to a user.

[0007] BACKGROUND OF THE INVENTION

[0008] This section is intended to introduce the reader to various aspects of art, which may be related to various aspects of the present disclosure that are described or claimed below. This discussion is believed to be helpful in providing the reader with background information to facilitate a better understanding of the various aspects of the present disclosure. Accordingly, it should be understood that these statements in this background section are to be read in this light, and not as admissions of prior art. Similarly, a problem mentioned in the background section or associated with the subject matter of the background section should not be assumed to have been previously recognized in the prior art. The subject matter in the background section merely represents different approaches, which in and of themselves may also correspond to implementations of the claimed technology.

[0009] In the domain of digital communication, interactions between users and systems have become increasingly multifaceted. Users often engage with such systems using various languages and dialects, encompassing a broad range of topics. These interactions may include transactional activities, such as completing a payment or reporting fraud, or non-transactional engagements, such as posing inquiries or seeking information. The system’s capacity to comprehend and respond to such interactions in a contextually relevant and meaningful manner is essential for ensuring effective communication. Similarly, in the rapidly advancing realm of online gaming, delivering a seamless and personalized user experience is of critical importance. A fundamental aspect of this experience is enabling natural and conversational interaction with the gaming platform. This requirement is particularly significant in the context of vernacular gaming applications, where users may not possess fluency in English or other widely spoken languages.

[0010] Moreover, the gaming industry encounters a diverse spectrum of user queries and requests, which can be broadly categorized as transactional queries, non-transactional domain- specific queries, and non-domain-specific queries. Transactional queries pertain to game-related actions, such as initiating a game session or making a purchase. Non-transactional domainspecific queries relate to topics such as game mechanics, rules, or strategies, while non- domain- specific queries involve subjects unrelated to the gaming context.

[0011] Addressing this wide array of queries in a timely and accurate manner presents significant challenges, particularly in light of the extensive and heterogeneous user bases of gaming platforms. Conventional customer service mechanisms, such as email and telephonic support, are often ill-equipped to manage the query volume or deliver the rapid response times expected by users. Furthermore, these channels may lack the ability to provide personalized responses tailored to the user’s language, geographic location, or gaming history.

[0012] Additionally, maintaining the context of a conversation is vital for providing relevant and meaningful responses. However, traditional customer service systems frequently encounter challenges in sustaining conversational context over multiple interactions, particularly when users interact with different representatives.

[0013] Further, the accurate detection of the language used in user input, classification of input into appropriate categories, and generation of corresponding responses represent complex technical challenges. Furthermore, the system’s ability to learn from past interactions and enhance response accuracy over time is an essential component of effective communication. Consequently, there is a need for a robust system capable of addressing these complexities and delivering a seamless, context-aware, and efficient communication experience for users.

[0014] In light of the above stated discussion, there exists a need for an improved system and a method for providing a contextual response to a user.

[0015] SUMMARY OF THE INVENTION

[0016] Before the present system and device and its components are summarized, it is to be understood that this disclosure is not limited to the system and its arrangement as described, as there can be multiple possible embodiments which are not expressly illustrated in the present disclosure. The present disclosure overcomes one or more shortcomings of the prior art and provides additional advantages discussed throughout the present disclosure. Additional features and advantages are realized through the techniques of the present disclosure. It is also to be understood that the terminology used in the description is for the purpose of describing the versions or embodiments only and is not intended to limit the scope of the present application. This summary is not intended to identify essential features of the claimed subject matter nor is it intended for use in detecting or limiting the scope of the claimed subject matter.

[0017] According to embodiments illustrated herein, a method for providing a contextual response to a user is disclosed. In one implementation of the present disclosure, the method may involve various steps performed by a processor. The method may involve a step of receiving a natural language input query from a user. In an embodiment, the natural language input query may be in a first language. Further, the method may involve a step of identifying an intent of the natural language input query based on one or more vector embeddings associated with the natural language input query. Furthermore, the method may involve a step of classifying the intent into one of a transactional query, a non-domain specific query, or a non-transactional domain specific query. Furthermore, the method may involve a step of generating a response to the natural language input query based on the classified intent using at least one of a generic LLM, a non-transactional resolution model, and a transactional query resolution model. In an embodiment, the response may be in a second language. Additionally, the method may involve a step of translating the response from the second language to the first language to create the contextual response. Moreover, the method may involve a step of providing the contextual response to the user. In an embodiment, the contextual response may be in the first language associated with the natural language input query from the user.

[0018] According to embodiments illustrated herein, a system to provide the contextual response to the user is disclosed. In one implementation of the present disclosure, the system may involve a processor and a memory. The memory is communicatively coupled to the processor. Further, the memory is configured to store one or more executable instructions. Further, the processor may be configured to receive the natural language input query from the user. In an embodiment, the natural language input query may be in the first language. Further, the processor may be configured to identify the intent of the natural language input query based on the one or more vector embeddings associated with the natural language input query. Furthermore, the processor may be configured to classify the intent into one of the transactional query, the non-domain specific query, or the non-transactional domain specific query. Furthermore, the processor may be configured to generate the response to the natural language input query based on the classified intent using at least one of the generic LLM, the non- transactional resolution model, and the transactional query resolution model. In an embodiment, the response may be in the second language. Additionally, the processor may be configured to translate the response from the second language to the first language to create the contextual response. Moreover, the processor may be configured to provide the contextual response to the user. In an embodiment, the contextual response may be in the first language associated with the natural language input query from the user.

[0019] According to embodiments illustrated herein, there is provided a non-transitory computer- readable storage medium having stored thereon, a set of computer-executable instructions causing a computer comprising one or more processors to perform various steps. The steps may involve receiving the natural language input query from the user. In an embodiment, the natural language input query may be in the first language. Further, the steps may involve identifying the intent of the natural language input query based on the one or more vector embeddings associated with the natural language input query. Furthermore, the steps may involve classifying the intent into one of the transactional query, the non-domain specific query, or the non-transactional domain specific query. Furthermore, the steps may involve generating the response to the natural language input query based on the classified intent using at least one of the generic LLM, the non-transactional resolution model, and the transactional query resolution model. In an embodiment, the response may be in the second language. Additionally, the steps may involve translating the response from the second language to the first language to create the contextual response. Moreover, the steps may involve providing the contextual response to the user. In an embodiment, the contextual response may be in the first language associated with the natural language input query from the user.

[0020] The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, examples, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.

[0021] BRIEF DESCRIPTION OF DRAWINGS

[0022] The detailed description is described with reference to the accompanying figures. In the figures, same numbers are used throughout the drawings to refer like features and components. Embodiments of a present disclosure will now be described, with reference to the following diagrams below wherein: Figure 1 illustrates a block diagram describing a system (100) to provide a contextual response to a user in accordance with at least one embodiment of present subject matter.

[0023] Figure 2 illustrates a block diagram (200) showing an overview of various components of an application server (101) configured for providing the contextual response to the user, in accordance with at least one embodiment of present subject matter.

[0024] Figure 3 illustrates a flowchart describing a method (300) for providing the contextual response to the user, in accordance with at least one embodiment of present subject matter, and

[0025] Figure 4 illustrates a block diagram (400) of an exemplary computer system (401) for implementing embodiments consistent with the present subject matter.

[0026] It should be noted that the accompanying figures are intended to present illustrations of exemplary embodiments of the present disclosure. These figures are not intended to limit the scope of the present disclosure. It should also be noted that accompanying figures are not necessarily drawn to scale.

[0027] DETAILED DESCRIPTION OF THE INVENTION

[0028] Reference throughout the specification to “various embodiments,” “some embodiments,” “one embodiment,” or “an embodiment” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, appearances of the phrases “in various embodiments,” “in another embodiments,” “in some embodiments,” “in one embodiment,” or “in an embodiment” in places throughout the specification are not necessarily all referring to the same embodiment. Furthermore, the features, structures or characteristics may be combined in any suitable manner in one or more embodiments.

[0029] The words "comprising," "having," "containing," and "including," and other forms thereof, are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items or meant to be limited to only the listed item or items. It must also be noted that, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise. Although any methods similar or equivalent to those described herein can be used in the practice or testing of embodiments of the present disclosure, the exemplary methods are described. The disclosed embodiments are merely exemplary of the disclosure, which may be embodied in various forms. The terminology “one or more vector embeddings” and “vector embeddings” has the same meaning and are used alternatively throughout the specification. Further, the terminology “one or more document embeddings” and “document embeddings” has the same meaning and are used alternatively throughout the specification. Furthermore, the terminology “natural language input query”, “input query”, “input queries” and “user queries” has the same meaning and are used alternatively throughout the specification.

[0030] The present disclosure relates to a system to provide a contextual response to a user. The system includes a processor and a memory storing instructions that enable the processor to receive a natural language input query from a user, and the natural language input query may be in a first language. Further, the system may identify an intent of the natural language input query based on one or more vector embeddings associated with the natural language input query and classify the intent into one of a transactional query, a non-domain specific query, or a non-transactional domain specific query. Furthermore, the system may generate a response to the natural language input query based on the classified intent using at least one of a generic large language model (LLM), a non-transactional resolution model, and a transactional query resolution model. The response may be generated in a second language and translated to the first language to create a contextual response, which may be then provided to the user. This approach leverages vector embeddings and specialized models to ensure accurate, domainspecific, and contextually personalized responses. This process significantly improves the user experience by delivering intuitive, multilingual support while optimizing resource utilization and ensuring scalability across diverse domains and applications.

[0031] To address the limitations of conventional systems in contextual query resolution, the disclosed system focuses on integrating advanced technologies, including the vector embeddings and the intent classification, to efficiently interpret and respond to natural language queries. Further, by classifying queries into transactional, non-domain-specific, or non-transactional domainspecific categories, the system ensures precise resolution through the appropriate resolution models, including generic LLMs and specialized resolution models. Furthermore, the system generates responses in a second language and translates the responses into the user’s native language, ensuring accurate and contextually relevant and personalized answers. Moreover, by automating this process and providing multilingual support, the system significantly enhances user interaction, reduces response time, and improves the overall efficiency of query handling across diverse domains, allowing resources to focus on more complex and strategic challenges. Referring to Figure 1 is a block diagram that illustrates a system (100) to provide a conversational assistant, in accordance with at least one embodiment of the present subject matter. The system (100) typically comprises an application server (101), a database server (102), a communication network (103), and a user computing device (104). The application server (101), the database server (102), and the user computing device (104) are typically communicatively coupled with each other via the communication network (103). In an embodiment, the application server (101) may communicate with the database server (102), and the user computing device (104) using one or more protocols such as, but not limited to, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol / Intemet Protocol (TCP / IP), Wireless Application Protocol (WAP), RF mesh, Bluetooth Low Energy (BLE), and the like, to communicate with one another.

[0032] In an embodiment, the database server (102) may refer to a computing device that may be configured to store one or more vector databases, a context and the response associated with the natural language input query. Further, the one or more vector databases may store at least one of one or more vector embeddings and one or more document embeddings. In an embodiment, the one or more document embeddings may be generated based on at least one of a knowledge base, a documentation and a plurality of historical conversations and associated context. In an embodiment, the one or more document embeddings may be similar to the one or more vector embeddings associated with the natural language input query. In an exemplary embodiment, the database server (102) may store the one or more vector embeddings, the intent classifying rules, language datasets, and multilingual translation data to support the identification and classification of the user intent and the generation of accurate responses. Moreover, the database server (102) may refer to the computing device configured to perform a variety of database operations essential for providing contextual responses to the user’s natural language input queries. The database server (102) may include a centralized repository specifically configured for maintaining the configurations of the generic LLMs, the non- transactional resolution models, and the transactional query resolution models. The centralized repository may also store domain- specific data used to generate precise responses based on the classified intent of the query. Further, the centralized repository may be further configured to perform database operations, such as storing, searching, and identifying relevant text associated with the one or more document embeddings that are similar to the one or more vector embeddings. Moreover, the database server (102) may retrieve appropriate model configurations including the generic LLMs and specialized resolution models, searching for domain- specific content, and facilitating translation rules to convert responses into the user’s native language. Additionally, the database server (102) may log natural language queries, the context and the associated responses, and the user interaction history to support system operations starting from receiving the natural language input query from the user to identifying, classifying, generating, translating, and providing the contextual response to the user. Furthermore, the database server (102) may be configured to store received feedback from the user, associated with the contextual response, and perform training of at least one of the generic LLM, the non-transactional resolution model, and the transactional query resolution model based on the feedback for continuous improvement. In an exemplary embodiment, logging may correspond to maintaining a history of actions performed by the system, including the intent identification process, model selection, and response translation. Examples of database operations may include, but are not limited to, storing, retrieving, searching, identifying, managing, and logging data for efficient query resolution. In an embodiment, the database server (102) may include hardware and software capable of being realized through various technologies, such as, but not limited to, Microsoft SQL Server, Oracle, IBM DB2, Microsoft Access, PostgreSQL, MySQL, SQLite, or distributed database technologies. The database server (102) may also be configured to utilize the application server (101) for storage and retrieval of data required to generate contextual responses, ensuring seamless and efficient management of user interactions.

[0033] A person with ordinary skills in art will understand that the scope of the disclosure is not limited to the database server (102) as a separate entity. In an embodiment, the functionalities of the database server (102) can be integrated into the application server (101) or into the user computing device (104).

[0034] In an embodiment, the application server (101) may refer to a computing device or a software framework hosting an application or a software service. In an embodiment, the application server (101) may be implemented to execute procedures such as, but not limited to, programs, routines, or scripts stored in the database server (102) for supporting the hosted application or the software service. In an embodiment, the hosted application or the software service may be configured to perform one or more predetermined operations. The application server (101) may be realized through various types of application servers such as, but are not limited to, a Java application server, a .NET framework application server, a Base4 application server, a PHP framework application server, or any other application server framework.

[0035] In an embodiment, the application server (101) may be configured to utilize the database server (102) and the user computing device (104) in conjunction to provide the contextual response to the user. In an implementation, the application server (101) corresponds to the execution of tasks necessary for natural language query processing, enabling the identification and classification of user intents, and generating precise responses. This ensures efficient and effective handling of user queries in real-time. Further, by leveraging the natural language input queries and integrating with the database server (102), the application server (101) ensures seamless query processing and contextual response delivery, thereby enhancing user experience and operational efficiency.

[0036] In an embodiment, the application server (101) may be configured to receive the natural language input query from the user. In an embodiment, the natural language input query may be in the first language.

[0037] In an embodiment, the application server (101) may be configured to identify the intent of the natural language input query based on the one or more vector embeddings associated with the natural language input query.

[0038] In an embodiment, the application server (101) may be configured to classify the intent into one of the transactional queries, the non-domain specific query, or the non-transactional domain specific query.

[0039] In an embodiment, the application server (101) may be configured to generate the response to the natural language input query based on the classified intent using at least one of the generic LLM, the non-transactional resolution model, and the transactional query resolution model. In an embodiment, the response may be in the second language.

[0040] In an embodiment, the application server (101) may be configured to translate the response from the second language to the first language to create the contextual response.

[0041] In an embodiment, the application server (101) may be configured to provide the contextual response to the user. In an embodiment, the contextual response may be in the first language associated with the natural language input query from the user.

[0042] In an embodiment, the communication network (103) may correspond to a communication medium through which the application server (101), the database server (102), and the user computing device (104) may communicate with each other. Such communication may be performed in accordance with various wired and wireless communication protocols. Examples of such wired and wireless communication protocols include, but are not limited to, Transmission Control Protocol and Internet Protocol (TCP / IP), User Datagram Protocol (UDP), Hypertext Transfer Protocol (HTTP), Wireless Application Protocol (WAP), File Transfer Protocol (FTP), ZigBee, EDGE, infrared IR), IEEE 802.11, 802.16, 2G, 3G, 4G, 5G, 6G, 7G cellular communication protocols, and / or Bluetooth (BT) communication protocols. The communication network (103) may either be a dedicated network or a shared network. Further, the communication network (103) may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, and the like. The communication network (103) may include, but is not limited to, the Internet, intranet, a cloud network, a Wireless Fidelity (Wi-Fi) network, a Wireless Local Area Network (WLAN), a Local Area Network (LAN), a cable network, the wireless network, a telephone network (e.g., Analog, Digital, POTS, PSTN, ISDN, xDSL), a telephone line (POTS), a Metropolitan Area Network (MAN), an electronic positioning network, an X.25 network, an optical network (e.g., PON), a satellite network (e.g., VSAT), a packet- switched network, a circuit-switched network, a public network, a private network, and / or other wired or wireless communications network configured to carry data.

[0043] In an embodiment, the user computing device may comprise one or more processors and one or more memory. The one or more memory may store computer-readable instructions that are executable by the one or more processors to facilitate the user’s interaction with the system. The device may be configured to receive natural language input queries from the user, which may be entered through text-based interfaces, voice recognition, or other multimodal input methods. Once the query is received, the device transmits it to the system for processing and the intent classification. Further, the user computing device may also be responsible for delivering the contextual response from the system to the user. In an exemplary embodiment, the user computing device may further display the response through visual interfaces, such as screens or dashboards, provide auditory feedback through speakers, or use haptic feedback where applicable. Moreover, the user computing device may also support language translation, displaying the response in the user’s preferred language. Additionally, the user computing device may maintain a history of past queries and responses to enhance user interaction, providing quick access to previous interactions. Examples of user computing devices include, but are not limited to, personal computers, laptops, mobile devices, tablets, or any other suitable computing device.

[0044] The system (100) can be implemented using hardware, software, or a combination of both, which includes using where suitable, one or more computer programs, mobile applications, or “apps” by deploying either on-premises over the corresponding computing terminals or virtually over cloud infrastructure. The system (100) may include various micro-services or groups of independent computer programs which can act independently in collaboration with other micro-services. The system (100) may also interact with a third-party or external computer system. Internally, the system (100) may be the central processor of all requests for transactions by the various actors or users of the system. A critical attribute of the system (100) is that it can concurrently and instantly generate responses and translate them back to the user's native language providing precise and contextually relevant answers in collaboration with other systems. In a specific embodiment, the system (100) is implemented to provide the contextual response to the user.

[0045] Now referring to Figure 2, illustrates a block diagram (200) showing an overview of various components of the application server (101) configured to provide the contextual response to the user, in accordance with at least one embodiment of the present subject matter. Figure 2 is explained in conjunction with elements from Figure 1. In an embodiment, the application server (101) includes a processor (201), a memory (202), a transceiver (203), an input / output unit (204), a user interface unit (205), a receiving unit (206), a computation unit (207), a language translation unit (208), and a display unit (209). The processor (201) may be communicatively coupled to the memory (202), the transceiver (203), the input / output unit (204), the user interface unit (205), the receiving unit (206), the computation unit (207), the language translation unit (208), and the display unit (209). The transceiver (203) may be communicatively coupled to the communication network (103) of the system (100).

[0046] In an embodiment, the system provides the contextual responses to the user. Further, the system processes the natural language input queries by identifying their intent using the vector embeddings. The system further classifies the query intent into categories such as the transactional query, the non-domain- specific query, or the non-transactional domain- specific query. Furthermore, based on the identified intent, the system selects the appropriate resolution model such as the generic large language model, the transactional query resolution model, or the non-transactional domain- specific query model. The system generates the response in the second language, further translates the response into the user's preferred language, and delivers the contextual response.

[0047] In an exemplary embodiment, the system processes the transactional query, such as a user requesting to make the purchase or initiate a game session. The system identifies this query as transactional and uses the transactional query resolution model to process the request, ensuring the action is carried out within the game environment. For non-transactional domain- specific queries, such as questions about the game’s mechanics, rules, or strategies, the system uses the domain- specific resolution model to generate the response with the relevant game-specific information. For non-domain- specific queries, such as general inquiries unrelated to the game, are handled by the generic large language model to provide an appropriate response. For example, the input query asking about how to achieve a specific goal in the game might trigger the domain- specific model to provide a strategy, while a question about the weather would be handled by the generic LLM.

[0048] The processor (201) comprises suitable logic, circuitry, interfaces, and / or code that may be configured to execute a set of instructions stored in the memory (202), and may be implemented based on several processor technologies known in the art. The processor (201) works in coordination with the memory (202), the transceiver (203), the input / output unit (204), the user interface unit (205), the receiving unit (206), the computation unit (207), the language translation unit (208), and the display unit (209) for providing the contextual response to the user. Examples of the processor (201) include, but not limited to, a standard microprocessor, microcontroller, central processing unit (CPU), an X86-based processor, a Reduced Instruction Set Computing (RISC) processor, an Application- Specific Integrated Circuit (ASIC) processor, and a Complex Instruction Set Computing (CISC) processor, distributed or cloud processing unit, state machines, logic circuitries, and / or any devices that manipulate signals based on operational instructions and / or other processing logic that accommodates the requirements of the present invention.

[0049] The memory (202) comprises suitable logic, circuitry, interfaces, and / or code that may be configured to store the set of instructions, which are executed by the processor (201). Preferably, the memory (202) is configured to store one or more programs, routines, or scripts that are executed in coordination with the processor (201). Additionally, the memory (202) may include any computer-readable medium or computer program product known in the art including, for example, volatile memory, such as static random-access memory (SRAM) and dynamic random-access memory (DRAM), and / or non-volatile memory, such as read-only memory (ROM), erasable programmable ROM, a Hard Disk Drive (HDD), flash memories, Secure Digital (SD) card, Solid State Disks (SSD), optical disks, magnetic tapes, memory cards, virtual memory and distributed cloud storage. The memory (202) may be removable, non-removable, or a combination thereof. Further, the memory (202) may include routines, programs, objects, components, data structures, etc., which perform particular tasks or implement particular abstract data types. The memory (202) may include programs or coded instructions that supplement the applications and functions of the system (100). In one embodiment, the memory (202), amongst other things, serves as a repository for storing data processed, received, and generated by one or more of the programs or the coded instructions. In yet another embodiment, the memory (202) may be managed under a federated structure that enables the adaptability and responsiveness of the application server (101).

[0050] The transceiver (203) comprises suitable logic, circuitry, interfaces, and / or code that may be configured to receive, process or transmit information, data or signals, which are stored by the memory (202) and executed by the processor (201). The transceiver (203) is preferably configured to receive, process or transmit, one or more programs, routines, or scripts that are executed in coordination with the processor (201). The transceiver (203) is preferably communicatively coupled to the communication network (103) of the system (100) for communicating all the information, data, signals, programs, routines or scripts through the communication network (103).

[0051] The transceiver (203) may implement one or more known technologies to support wired or wireless communication with the communication network (103). In an embodiment, the transceiver (203) may include but is not limited to, an antenna, a radio frequency (RF) transceiver, one or more amplifiers, a tuner, one or more oscillators, a digital signal processor, a Universal Serial Bus (USB) device, a coder-decoder (CODEC) chipset, a subscriber identity module (SIM) card, and / or a local buffer. Also, the transceiver (203) may communicate via wireless communication with networks, such as the Internet, an Intranet and / or a wireless network, such as a cellular telephone network, a wireless local area network (LAN) and / or a metropolitan area network (MAN). Accordingly, the wireless communication may use any of a plurality of communication standards, protocols and technologies, such as: Global System for Mobile Communications (GSM), Enhanced Data GSM Environment (EDGE), wideband code division multiple access (W-CDMA), code division multiple access (CDMA), time division multiple access (TDMA), Bluetooth, Wireless Fidelity (Wi-Fi) (e.g., IEEE 802.11a, IEEE 802.1 lb, IEEE 802.11g and / or IEEE 802.1 In), voice over Internet Protocol (VoIP), WiMAX, a protocol for email, instant messaging, and / or Short Message Service (SMS).

[0052] The input / output (EG) unit (204) comprises suitable logic, circuitry, interfaces, and / or code that may be configured to receive or present information. The input / output unit (204) comprises various input and output devices that are configured to communicate with the processor (201). Examples of the input devices include but are not limited to, a keyboard, a mouse, a joystick, a touch screen, a microphone, a camera, and / or a docking station. Examples of the output devices include, but are not limited to, a display screen and / or a speaker. The EG unit (204) may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like. The I / O unit (204) may allow the system (100) to interact with the user directly or through the user computing devices (104). Further, the VO unit (204) may enable the system (100) to communicate with other computing devices, such as web servers and external data servers (not shown). The I / O unit (204) can facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for example, LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite. The VO unit (204) may include one or more ports for connecting a number of devices to one another or to another server. In one embodiment, the I / O unit (204) allows the application server (101) to be logically coupled to other user computing devices (104), some of which may be built in. Illustrative components include tablets, mobile phones, wireless devices, etc.

[0053] Further, the input / output (I / O) unit (204) may be configured to manage the exchange of data between the application server and the user computing device, ensuring that both input queries and contextual responses are transmitted efficiently. In an embodiment, the I / O unit (204) facilitates the reception of natural language input queries from the user, which are then forwarded to the receiving unit (206) for intent identification and processing. Additionally, the I / O unit (204) plays an important role in transmitting the contextual responses generated by the system back to the user computing device (104), ensuring that the responses are delivered in the user’ s preferred language and in a suitable format for display. In an embodiment, the I / O unit (204) may also handle communication with external systems or databases, ensuring seamless data exchange and real-time updates. For example, the I / O unit (204) may manage the interaction with external language models, the translation system, or data storage systems to retrieve or update relevant information as required. Moreover, the I / O unit (204) may be responsible for receiving feedback from the user and sending alerts, or notifications to the user computing device (104), ensuring that the user is informed about ongoing activities or issues that require attention. By managing this data flow, the VO unit (204) supports the responsiveness and interactivity of the system, enhancing user experience and operational efficiency.

[0054] Further, the user interface unit (205) may facilitate interaction between the user and the system (100) by presenting relevant data, alerts, and contextual responses about user input queries and their resolution status. The user interface unit (205) may allow the user to view the status of ongoing query processing and to receive real-time updates on the resolution progress. Furthermore, the user interface unit (205) may include interfaces for various content formats such as text, image, video, and audio, enabling a seamless and intuitive interaction experience for the user. Further, the user interface unit (205) may provide the platform for users to input their natural language queries and review the contextual responses generated by the system. Further, the user interface unit (205) may display additional details such as query classification such as transactional, non-transactional domain- specific, or non-domain specific, the rationale behind the response, and any supporting information. Moreover, these components work together to enhance the user experience by providing an interactive, responsive, and user- friendly interface, thereby enabling efficient handling of user queries within the system.

[0055] Further, the receiving unit (206) may be configured to receive the natural language input query from the user in the first language. In an embodiment, the first language may correspond to the user's preferred language or the default language setting of the system. In an embodiment, the natural language input query may correspond to a voice input, a text input, or combination of the same.

[0056] Furthermore, the receiving unit (206) may also be configured to receive feedback from the user associated with the contextual response provided by the system. In an embodiment, the feedback may include user suggestions, corrections, or satisfaction levels regarding the contextual response. Moreover, the receiving unit (206) may relay this feedback to the system for refining and enhancing the response generation process.

[0057] In an exemplary embodiment, the feedback received by the receiving unit (206) may be utilized to train at least one of the generic LLM, the non-transactional resolution model, and the transactional query resolution model. Further, the training process may involve incorporating the feedback into existing models, improving their accuracy, contextual understanding, and ability to provide relevant and domain- specific responses.

[0058] In an exemplary embodiment, the receiving unit (206) may integrate with APIs or frameworks supporting voice recognition, text processing, or multimedia input analysis. Additionally, the receiving unit (206) may apply initial preprocessing tasks, such as language detection, format standardization, and noise filtration, ensuring the input is ready for intent classification and further processing.

[0059] Further, the computation unit (207) may be configured to process the natural language input query to generate the contextual response. In an embodiment, the computation unit (207) may identify the intent of the natural language input query by leveraging the one or more vector embeddings associated with the input query.

[0060] In another embodiment, the computation unit (207) may further store the query's context and its response in the database server (102). This stored information may be utilized to generate future contextual responses using attention-based techniques, ensuring continuity and accuracy in subsequent interactions. By incorporating feedback mechanisms, the computation unit (207) may continuously refine the models and response generation process, enhancing the system's adaptability and performance over time. Furthermore, the computation unit (207) may search the vector database for the one or more document embeddings similar to the query's vector embeddings. Moreover, the computation unit (207) may further identify the relevant text associated with the one or more document embeddings and use this text as input to the one of the models such as the generic LLM, the non-transactional resolution model, and the transactional query resolution model to generate the contextual response to the user.

[0061] In an embodiment, the computation unit (207) may classify the intent using the classifier built on top of a transformer model. Furthermore, the transactional query resolution model may determine a resolution type of the query, such as payment-related, user reported fraud, or non- actionable. The resolution type is identified based on classifier output trained on the past resolutions. Further, the identified intent may be classified into one of the transactional queries, non-domain-specific queries, or non-transactional domain- specific queries for further processing. If the resolution type corresponds to a non-actionable query, the computation unit (207) may generate a prompt to be processed by the generic LLM for response generation.

[0062] Further, the computation unit (207) may store the context, and the response associated with the natural language input query in the database server (102). Further, the computation unit (207) may utilize this stored context and response, along with the one or more attention-based techniques, to generate the contextual response. Further, the response may be generated using at least one of the generic LLM for non-domain- specific queries, the non-transactional resolution model for non-transactional domain- specific queries, and the transactional query resolution model for transactional queries. Additionally, the response is relevant to the context of the query and delivered in one of the domain-specific languages, the user's preferred language, or the system's default language setting.

[0063] Furthermore, the generic LLM may be utilized for generating the response for the non-domain specific query. In an embodiment, the non-transactional resolution model may be utilized for generating the response for the non-transactional domain specific query. In an embodiment, the transactional query resolution model may be utilized for generating the response for the transactional query.

[0064] In an exemplary embodiment, the computation unit (207) may generate the vector embeddings associated with the natural language input query by processing the input query against pretrained language models. Further, these vector embeddings, along with document embeddings generated from a knowledge base, a documentation, or a historical conversation, may be stored in the vector database. Furthermore, the transactional query resolution model may determine the resolution type of the query, such as payment-related, fraudulent, or non-actionable. However, if the resolution type corresponds to a non-actionable query, the computation unit (207) may further generate the prompt to be processed by the generic LLM for response generation. Moreover, the non-transactional resolution model and the transactional query resolution model may correspond to a domain expert LLMs, which are based on a decision tree architecture and trained using the knowledge base, the documentation, and the plurality of historical conversations and associated contexts.

[0065] In an exemplary embodiment, the computation unit (207) may generate the vector embeddings associated with the natural language input query. In the related embodiment, the vector embeddings may be generated by utilizing models such as BERT (Bidirectional Encoder Representations from Transformers), RoBERTa (Robustly Optimized BERT Pretraining Approach), GPT, T5, Word2Vec, GloVe, mBERT, or combination of the same.

[0066] In an exemplary embodiment, classifying the intent using the classifier built on top of the transformer model may leverage transfer learning techniques by fine-tuning a pre-trained RoBERTa model using the AdamW optimizer. This fine-tuning process allows the RoBERTa model to adapt to domain-specific intent classification by updating RoBERTa model’s parameters on a labeled dataset, leading to improved classification performance and stable convergence.

[0067] Furthermore, the language translation unit (208) may be configured to detect the first language associated with the natural language input query. In an exemplary embodiment, a language detection model may be configured to automatically detect the first language of the user input. The language detection model may employ machine learning algorithms or rule -based approach to accurately identify the language used by the user. In an embodiment, the first language corresponds to the user’s preferred language, whether spoken or written. In an embodiment, if the natural language input query corresponds to the voice input, the language translation unit (208) may convert the voice input into text for further query processing. Moreover, the system then translates the text input in the first language into a second language. In an embodiment, the second language corresponds to the domain- specific language required for query processing.

[0068] In an embodiment, the language translation unit (208) may further be configured to detect one of the user’ s preferred languages, the second language, or the system's default language setting, and ensure that the response is translated accordingly. Further, the translation process ensures that the generated response in the second language is then converted back into the first language to maintain contextual relevance. This allows the system to provide the response in the language that aligns with the user’s language preference, or default language settings of the system, thus ensuring a seamless and contextually accurate communication experience.

[0069] Furthermore, the display unit (209) may be configured to provide the contextual response to the user. In an embodiment, the contextual response may be delivered in the first language associated with the natural language input query from the user. In an embodiment, the contextual response may be presented using a virtual assistant. In an embodiment, the virtual assistant may be configured to provide the contextual response agnostic to the first language of the user and agnostic to a geographic location of the user. This ensures that the virtual assistant may serve users from different linguistic and geographical backgrounds without any constraints.

[0070] Furthermore, the display unit (209) may synthesize the contextual response into at least one of a voice output or a text output, and detect one of the user’ s preferred languages, or the system's default language setting. The response, whether in voice or text form, ensures that the user receives a comprehensive and accessible response to their query in the first language, providing a seamless and personalized interaction. This system allows the user to engage with the virtual assistant in their preferred language, while also adapting to their desired output format, enhancing the overall user experience.

[0071] Now referring to Figure 3, illustrates a flowchart describing a method (300) for providing the contextual response to the user, in accordance with at least one embodiment of the present subject matter. The flowchart is described in conjunction with Figure 1 and Figure 2. The method (300) starts at step (301) and proceeds to step (306).

[0072] In operation, the method (300) may involve a variety of steps, executed by the processor (201), providing the contextual response to the user.

[0073] At step (301), the method involves receiving the natural language input query from the user. In an embodiment, the natural language input query may be in the first language.

[0074] At step (302), the method involves identifying the intent of the natural language input query based on the one or more vector embeddings associated with the natural language input query.

[0075] At step (303), the method involves classifying the intent into one of the transactional query, the non-domain specific query, or the non-transactional domain specific query. At step (304), the method involves generating the response to the natural language input query based on the classified intent using at least one of the generic LLM, the non-transactional resolution model, the transactional query resolution model. In an embodiment, the response is in the second language.

[0076] At step (305), the method involves translating the response from the second language to the first language to create the contextual response.

[0077] At step (306), the method involves providing the contextual response to the user. In an embodiment, the contextual response is in the first language associated with the natural language input query from the user.

[0078] Let us delve into a detailed example of the present disclosure.

[0079] Imagine a digital assistant platform designed to provide contextually accurate, multilingual support in a healthcare organization, specifically for medical equipment -related queries. This platform integrates with existing healthcare IT systems to offer automated, domain- specific responses across multiple languages, ensuring users from diverse regions receive accurate guidance. For example, consider a scenario where a healthcare professional working in Spain needs assistance with calibrating an X-ray machine. The platform's processor receives the user query in Spanish and processes it in real time, using vector embeddings to identify the query's intent and classifying the input query as the non-transactional domain- specific query. The processor retrieves relevant procedural information from a medical equipment knowledge base. The response is initially generated in English (the second language) and then translated into Spanish. The response is delivered to the user in their preferred language — Spanish — in the form of the voice or text output via the virtual assistant, ensuring seamless interaction without requiring manual intervention.

[0080] Working Example 1:

[0081] Let's envision a medical equipment support system called "ABC" designed to automatically resolve domain- specific queries in a multilingual environment within a healthcare organization. Suppose a medical professional in Spain asks the system, "^Cual es el procedimiento para calibrar el equipo de rayos X?" (What is the procedure for calibrating the X-ray machine?). The ABC system detects the query is in Spanish, recognizes the user’s intent related to medical equipment calibration, and classifies the query as the non-transactional domain- specific query. The ABC system retrieves the necessary information from a technical knowledge base, generating the response in English, as this is the second language used for medical procedures. The ABC system’s language translation unit then translates the response into Spanish, ensuring that the healthcare professional receives the instructions in their preferred language. The virtual assistant of the ABC system then delivers the response in either text or voice format, depending on the user’ s preference. Throughout this process, ABC system ensures that the user receives contextually accurate and linguistically relevant assistance, significantly enhancing efficiency and user experience in a healthcare setting.

[0082] Working Example 2:

[0083] Suppose a customer in Germany wants to inquire about a refund for a recent online purchase and asks the system, "Wie kann ich eine Riickerstattung fur meine Bestellung beantragen?" (How can I request a refund for my order?). The ABC system detects the query is in German, identifies the intent as a transactional query related to payment processing, and classifies the transactional query accordingly. The system processes the request using the transactional query resolution model, retrieves relevant refund policy details from the payment processing system, and generates a response in English, as financial transactions are handled in this second language. The response is then translated into German by the language translation unit before being delivered to the customer in their preferred format. By leveraging domain -specific expertise and real-time translation, the ABC system ensures that the customer receives accurate and timely assistance.

[0084] Working Example 3:

[0085] Consider a scenario where an office employee in France asks the ABC system, "Quel est le meilleur moyen d'organiser mes e-mails?" (What is the best way to organize my emails?). The system identifies that the query is in French and classifies the intent as a non-domain specific query, as the query pertains to general productivity rather than a specific professional domain. Since non-domain specific queries are handled by the generic FEM, the system utilizes the pre-trained language model to generate a helpful response in English. The response is then translated back into French before being provided to the user. This approach enables the ABC system to handle a wide variety of inquiries efficiently, ensuring that users receive contextually appropriate guidance regardless of the subject matter.

[0086] A person skilled in the art will understand that the scope of the disclosure is not limited to scenarios based on the aforementioned factors and using the aforementioned techniques and that the examples provided do not limit the scope of the disclosure.

[0087] Now referring to Figure 4 illustrates a block diagram (400) of an exemplary computer system (401) for implementing embodiments consistent with the present disclosure. Variations of computer system (401) may be used as a method for providing the contextual response to the user. The computer system (401) may comprise a central processing unit (“CPU” or “processor”) (402). The processor (402) may comprise at least one data processor for executing program components for executing user- or system-generated requests. The user may include a person, a person using a device such as those included in this disclosure, or such a device itself. Additionally, the processor (402) may include specialized processing units such as integrated system (bus) controllers, memory management control units, floating point units, graphics processing units, digital signal processing units, or the like. In various implementations the processor (402) may include a microprocessor, such as AMD Athlon, Duron or Opteron, ARM’s application, embedded or secure processors, IBM PowerPC, Intel’s Core, Itanium, Xeon, Celeron or other line of processors, for example. Accordingly, the processor (402) may be implemented using mainframe, distributed processor, multi-core, parallel, grid, or other architectures. Some embodiments may utilize embedded technologies like application- specific integrated circuits (ASICs), digital signal processors (DSPs), or Field Programmable Gate Arrays (FPGAs), for example.

[0088] Processor (402) may be disposed in communication with one or more input / output (I / O) devices via I / O interface (403). Accordingly, the VO interface (403) may employ communication protocols / methods such as, without limitation, audio, analog, digital, monoaural, RCA, stereo, IEEE- 1394, serial bus, universal serial bus (USB), infrared, PS / 2, BNC, coaxial, component, composite, digital visual interface (DVI), high-definition multimedia interface (HDMI), RF antennas, S-Video, VGA, IEEE 802. n PolglnJx, Bluetooth, cellular (e.g., code-division multiple access (CDMA), high-speed packet access (HSPA+), global system for mobile communications (GSM), long-term evolution (LTE), WiMAX, or the like, for example.

[0089] Using the I / O interface (403), the computer system (401) may communicate with one or more I / O devices. For example, the input device (404) may be an antenna, keyboard, mouse, joystick, (infrared) remote control, camera, card reader, fax machine, dongle, biometric reader, microphone, touch screen, touchpad, trackball, sensor (e.g., accelerometer, light sensor, GPS, gyroscope, proximity sensor, or the like), stylus, scanner, storage device, transceiver, video device / source, or visors, for example. Likewise, an output device (405) may be a user’s smartphone, tablet, cell phone, laptop, printer, fax machine, video display (e.g., cathode ray tube (CRT), liquid crystal display (LCD), light- emitting diode (LED), plasma, or the like), or audio speaker, for example. In some embodiments, a transceiver (406) may be disposed in connection with the processor (402). The transceiver (406) may facilitate various types of wireless transmission or reception. For example, the transceiver (406) may include an antenna operatively connected to a transceiver chip (example devices include the Texas Instruments® WiLink WL1283, Broadcom® BCM4750IUB8, Infineon Technologies® X-Gold 618- PMB9800, or the like), providing IEEE 802.1 la / b / g / n, Bluetooth, FM, global positioning system (GPS), and / or 2G / 3G / 5G / 6G HSDPA / HSUPA communications, for example.

[0090] In some embodiments, the processor (402) may be disposed in communication with a communication network (408) via a network interface (407). The network interface (407) is adapted to communicate with the communication network (408). The network interface, coupled to the processor may be configured to facilitate communication between the system and one or more external devices or networks. The network interface (407) may employ connection protocols including, without limitation, direct connect, Ethernet (e.g., twisted pair 10 / 100 / 1000 Base T), transmission control protocol / intemet protocol (TCP / IP), token ring, or IEEE 802.11a / b / g / n / x, for example. The communication network (408) may include, without limitation, a direct interconnection, local area network (LAN), wide area network (WAN), wireless network (e.g., using Wireless Application Protocol), or the Internet, for example. Using the network interface (407) and the communication network (408), the computer system (401) may communicate with devices such as shown as a laptop (409) or a mobile / cellular phone (410). Other exemplary devices may include, without limitation, personal computer(s), server(s), fax machines, printers, scanners, various mobile devices such as cellular telephones, smartphones (e.g., Apple iPhone, Blackberry, Android-based phones, etc.), tablet computers, eBook readers (Amazon Kindle, Nook, etc.), laptop computers, notebooks, gaming consoles (Microsoft Xbox, Nintendo DS, Sony PlayStation, etc.), or the like. In some embodiments, the computer system (401) may itself embody one or more of these devices.

[0091] In some embodiments, the processor (402) may be disposed in communication with one or more memory devices (e.g., RAM 413, ROM 414, etc.) via a storage interface (412). The storage interface (412) may connect to memory devices including, without limitation, memory drives, removable disc drives, etc., employing connection protocols such as serial advanced technology attachment (SATA), integrated drive electronics (IDE), IEEE-1394, universal serial bus (USB), fiber channel, small computer systems interface (SCSI), etc. The memory drives may further include a drum, magnetic disc drive, magneto-optical drive, optical drive, redundant array of independent discs (RAID), solid-state memory devices, or solid-state drives, for example.

[0092] The memory devices may store a collection of program or database components, including, without limitation, an operating system (416), user interface application (417), web browser (418), mail client / server (419), user / application data (420) (e.g., any data variables or data records discussed in this disclosure) for example. The operating system (416) may facilitate resource management and operation of the computer system (401). Examples of operating systems include, without limitation, Apple Macintosh OS X, UNIX, Unix-like system distributions (e.g., Berkeley Software Distribution (BSD), FreeBSD, NetBSD, OpenBSD, etc.), Linux distributions (e.g., Red Hat, Ubuntu, Kubuntu, etc.), IBM OS / 2, Microsoft Windows (XP, Vista / 7 / 8, etc.), Apple iOS, Google Android, Blackberry OS, or the like.

[0093] The user interface (417) is for facilitating the display, execution, interaction, manipulation, or operation of program components through textual or graphical facilities. For example, user interfaces may provide computer interaction interface elements on a display system operatively connected to the computer system (401), such as cursors, icons, check boxes, menus, scrollers, windows, or widgets, for example. Graphical user interfaces (GUIs) may be employed, including, without limitation, Apple Macintosh operating systems’ Aqua, IBM OS / 2, Microsoft Windows (e.g., Aero, Metro, etc.), Unix X-Windows, or web interface libraries (e.g., ActiveX, Java, JavaScript, AJAX, HTML, Adobe Flash, etc.), for example.

[0094] In some embodiments, the computer system (401) may implement a web browser (418) stored program component. The web browser (418) may be a hypertext viewing application, such as Microsoft Internet Explorer, Google Chrome, Mozilla Firefox, Apple Safari, or Microsoft Edge, for example. Secure web browsing may be provided using HTTPS (secure hypertext transport protocol), secure sockets layer (SSL), Transport Layer Security (TLS), or the like. Web browsers may utilize facilities such as AJAX, DHTML, Adobe Flash, JavaScript, Java, or application programming interfaces (APIs), for example. In some embodiments the computer system (401) may implement a mail client / server (419) stored program component. The mail server (419) may be an Internet mail server such as Microsoft Exchange, or the like. The mail server may utilize facilities such as ASP, ActiveX, ANSI C++ / C#, Microsoft .NET, CGI scripts, Java, JavaScript, PERL, PHP, Python, or WebObjects, for example. The mail server (419) may utilize communication protocols such as internet message access protocol (IMAP), messaging application programming interface (MAPI), Microsoft Exchange, post office protocol (POP), simple mail transfer protocol (SMTP), or the like. In some embodiments, the computer system (401) may implement a mail client (420) stored program component. The mail client (420) may be a mail viewing application, such as Apple Mail, Microsoft Entourage, Microsoft Outlook, or Mozilla Thunderbird. In some embodiments, the computer system (401) may store user / application data (421), such as the data, variables, records, or the like as described in this disclosure. Such databases may be implemented as fault-tolerant, relational, scalable, secure databases such as Oracle or Sybase, for example. Alternatively, such databases may be implemented using standardized data structures, such as an array, hash, linked list, struct, structured text file (e.g., XML), table, or as object-oriented databases (e.g., using Objectstore, Poet, Zope, etc.). Such databases may be consolidated or distributed, sometimes among the various computer systems discussed above in this disclosure. It is to be understood that the structure and operation of the any computer or database component may be combined, consolidated, or distributed in any working combination.

[0095] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present invention. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer- readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., non-transitory. Examples include Random Access Memory (RAM), Read- Only Memory (ROM), volatile memory, non-volatile memory, hard drives, Compact Disc (CD) ROMs, Digital Video Disc (DVDs), flash drives, disks, and any other known physical storage media.

[0096] In light of the above-mentioned advantages and the technical advancements provided by the disclosed method and system, the claimed steps as discussed above are not routine, conventional, or well understood in the art, as the claimed steps enable the following solutions to the existing problems in conventional technologies. Further, the claimed steps clearly bring an improvement in the functioning of the device itself as the claimed steps provide a technical solution to a technical problem.

[0097] Various embodiments of the disclosure provide a non-transitory computer readable medium and / or storage medium, and / or a non-transitory machine -readable medium and / or storage medium having stored thereon, a machine code and / or a computer program having at least one code section executable by a machine and / or a computer for providing the contextual response to the user. The at least one code section in the application server (101) causes the machine and / or computer including one or more processors to perform the steps, which includes receiving the natural language input query from the user. In an embodiment, the natural language input query may be in the first language. Further, the steps may involve identifying the intent of the natural language input query based on the one or more vector embeddings associated with the natural language input query. Further, the steps may involve classifying the intent into one of the transactional query, the non-domain specific query, or the non- transactional domain specific query. Furthermore, generating the response to the natural language input query based on the classified intent using at least one of the generic LLM, the non-transactional resolution model, and the transactional query resolution model. In an embodiment, the response may be in the second language. Additionally, the steps may involve translating the response from the domain specific language to the first language to create the contextual response. Moreover, the steps may involve providing the contextual response to the user. In an embodiment, the contextual response may be in the first language associated with the natural language input query from the user.

[0098] Various embodiments of the disclosure encompass numerous advantages including the system and the method for providing the contextual response to the user. The disclosed method and system have several technical advantages, but not limited to the following:

[0099] • Enhanced Accuracy in Intent Recognition: The method leverages vector embeddings to capture contextual response, enabling precise identification of user intent. By classifying queries into transactional, non-domain specific, and non-transactional domain- specific categories, the method ensures accurate and efficient handling of diverse user inputs.

[0100] • Personalized Responses for Better User Experience: The system generates responses in the second language to deliver highly relevant and specialized answers. It combines the capabilities of generic LLMs and domain-specific resolution models, ensuring scalability and adaptability across various contexts and industries.

[0101] • Seamless Multilingual Support: The method translates responses from second languages to the user’s original language, ensuring global accessibility and eliminating language barriers for a more inclusive user experience.

[0102] • Contextually Accurate Responses: By focusing on generating context-aware responses that align with user intent and linguistic preferences, the system enhances the relevance and quality of interactions.

[0103] • Streamlined Query Resolution: The use of separate resolution models for transactional and non-transactional queries optimizes processing efficiency and ensures effective resolution adaptive to the query type. • Improved User Engagement: The system’s natural language interface operates in the user’s preferred language, facilitating intuitive and conversational interactions that encourage continued engagement.

[0104] • Flexibility and Scalability: The system’s modular architecture supports seamless integration of new domains, languages, and advanced models, making it adaptable to a wide range of industries and evolving user needs.

[0105] • Increased Adoption Across Industries: The method’s applicability to specialized domains like legal, medical, and technical support, combined with its cross-language capabilities, enhances its usability in multilingual regions and global organizations.

[0106] • Cost-Effective Maintenance and Expansion: The separation of intent classification and response generation simplifies updates and reduces maintenance costs. Automating query resolution minimizes reliance on human support, further reducing operational expenses and errors.

[0107] In summary, the technical advantages of this invention address the challenges associated with conventional systems such as the problem of accurately detecting languages, classifying inputs into appropriate categories, generating suitable responses, and learning from past interactions to enhance future response accuracy, by introducing an advanced method for providing contextual, multilingual responses to users. By integrating the processor and the memory with sophisticated natural language processing (NLP) capabilities, the system automates the classification, resolution, and translation of user queries into relevant and personalized responses. The method utilizes a combination of the generic LLM and domain- specific resolution models to generate contextually relevant answers, which are then translated to the user’s preferred language, ensuring a seamless interaction. The system’s virtual assistant, agnostic to the user’s language and geographic location, delivers these responses in real-time, enhancing the user experience. By leveraging contextual embeddings, language detection, and feedback-driven model training, the system ensures highly accurate and personalized interactions. This approach overcomes the limitations of traditional systems, enabling dynamic and scalable multilingual communication while optimizing response generation, significantly improving efficiency and user satisfaction.

[0108] The claimed invention relates to the system and the method for providing contextual responses to users through multilingual natural language processing (NLP). The system consists of key components, including the processors, the language detection models, the vector embeddings generation modules, the domain-specific and the transactional query resolution models, translation engines, and response delivery mechanisms. These components work together to classify user intents, generate context-aware responses in the second language, and seamlessly translate the responses into the user’s preferred language, providing a personalized and efficient communication experience.

[0109] The invention further incorporates a non-trivial combination of technologies and methodologies to address a technical challenge in conversational Al systems. While individual technologies such as NLP models, translation engines, and query resolution systems are known, their integration into a unified framework capable of detecting input language, generating domain- specific responses, classifying various query intents, and ensuring multilingual and contextual accuracy represents a significant advancement in the field. This integrated approach improves the effectiveness, efficiency, and user experience in handling diverse queries in dynamic and multilingual environments. In light of the above-mentioned advantages and the technical advancements provided by the disclosed method and system, the claimed steps as discussed above are not routine, conventional, or well understood in the art, as the claimed steps enable the following solutions to the existing problems in conventional technologies. Further, the claimed steps clearly bring an improvement in the functioning of the device itself as the claimed steps provide a technical solution to a technical problem.

[0110] The present disclosure may be realized in hardware, or a combination of hardware and software. The present disclosure may be realized in a centralized fashion, in at least one computer system, or in a distributed fashion, where different elements may be spread across several interconnected computer systems. A computer system or other apparatus adapted for carrying out the methods described herein may be suited. A combination of hardware and software may be a general-purpose computer system with a computer program that, when loaded and executed, may control the computer system such that it carries out the methods described herein. The present disclosure may be realized in hardware that comprises a portion of an integrated circuit that also performs other functions.

[0111] A person with ordinary skills in the art will appreciate that the systems, modules, and submodules have been illustrated and explained to serve as examples and should not be considered limiting in any manner. It will be further appreciated that the variants of the above disclosed system elements, modules, and other features and functions, or alternatives thereof, may be combined to create other different systems or applications. Those skilled in the art will appreciate that any of the aforementioned steps and / or system modules may be suitably replaced, reordered, or removed, and additional steps and / or system modules may be inserted, depending on the needs of a particular application. In addition, the systems of the aforementioned embodiments may be implemented using a wide variety of suitable processes and system modules, and are not limited to any particular computer hardware, software, middleware, firmware, microcode, and the like. The claims can encompass embodiments for hardware and software, or a combination thereof.

[0112] While the present disclosure has been described with reference to certain embodiments, it will be understood by those skilled in the art that various changes may be made, and equivalents may be substituted without departing from the scope of the present disclosure. In addition, many modifications may be made to adapt a particular situation or material to the teachings of the present disclosure without departing from its scope. Therefore, it is intended that the present disclosure is not limited to the particular embodiment disclosed, but that the present disclosure will include all embodiments falling within the scope of the appended claims.

Claims

WE CLAIM:

1. A method (300) for providing a contextual response to a user, characterized in that, the method (300) comprising: receiving (301), by a processor (201), a natural language input query from a user, wherein the natural language input query is in a first language; identifying (302), by the processor (201), an intent of the natural language input query based on one or more vector embeddings associated with the natural language input query; classifying (303), by the processor (201), the intent into one of a transactional query, a non-domain specific query, or a non-transactional domain specific query; generating (304), by the processor (201), a response to the natural language input query based on the classified intent using at least one of a generic LLM, a non- transactional resolution model, a transactional query resolution model, wherein the response is in a second language; translating (305), by the processor (201), the response from the second language to the first language to create the contextual response; and providing (306), by the processor (201), the contextual response to the user, wherein the contextual response is in the first language associated with the natural language input query from the user.

2. The method (300) as claimed in claim 1, wherein the natural language input query corresponds to a voice input, a text input, or a combination thereof.

3. The method (300) as claimed in claim 1, comprising receiving feedback, from the user, associated with the contextual response; training at least one of the generic LLM, the non-transactional resolution model, and the transactional query resolution model based on the feedback.

4. The method (300) as claimed in claim 1, comprises generating the one or more vector embeddings associated with the natural language input query.

5. The method (300) as claimed in claim 1, comprising: storing at least one of the one or more vector embeddings and one or more document embeddings in a vector database, wherein the one or more document embeddings beinggenerated based on at least one of a knowledge base, a documentation and a plurality of historical conversations and associated context; searching the vector database for the one or more document embeddings that are similar to the one or more vector embeddings associated with the natural language input query; and identifying relevant text associated with the one or more document embeddings that are similar to the one or more vector embeddings, wherein the relevant text is identified as an input for at least one of the generic LLM, the non-transactional resolution model, and the transactional query resolution model to generate the response.

6. The method (300) as claimed in claim 1, wherein classifying the intent being performed by a classifier built on top of a transformer model.

7. The method (300) as claimed in claim 1, wherein the transactional query resolution model is configured to determine a resolution type associated with the natural language input query, wherein the resolution type is identified based on classifier output trained on the past resolutions, wherein the resolution type is one of: payment query, user reporting fraud, or non- actionable query, wherein if the resolution type corresponds to the non- actionable query then generating a prompt which is provided as input to the generic LLM to generate the response.

8. The method (300) as claimed in claim 1, comprising storing context and the response associated with the natural language input query in a database, wherein the context and the response being utilized for generating the contextual response based on one or more attention-based techniques.

9. The method (300) as claimed in claim 1, wherein the generic LLM is utilized for generating the response for the non-domain specific query, wherein the non-transactional resolution model is utilized for generating the response for the non-transactional domain specific query, and wherein the transactional query resolution model is utilized for generating the response for the transactional query.

10. The method (300) as claimed in claim 1, wherein the non-transactional resolution model and the transactional query resolution model corresponds to a domain expert LLM.

11. The method (300) as claimed in claim 1, wherein each of the non-transactional resolution model and the transactional query resolution model are based on a decision tree architecture and being trained using at least one of the knowledge base, the documentation and the plurality of historical conversations and associated context.

12. The method (300) as claimed in claim 1, comprising performing one or more operations on the natural language input query, wherein the one or more operations comprises: detecting the first language associated with the natural language input query, wherein the first language corresponds to a language of the user, wherein the natural language input query corresponds to the voice input; converting the voice input to the text input in the first language; and translating the text input in the first language to the second language, wherein the second language corresponds to the domain specific language.

13. The method (300) as claimed in claim 1, wherein the contextual response being provided to the user using a virtual assistant, and wherein the virtual assistant is configured to provide the contextual response agnostic to the first language of the user and agnostic to a geographic location of the user.

14. The method as claimed in claim 1, wherein providing the response to the user comprises synthesizing the contextual response in the first language to at least one of a voice output or a text output.

15. A system (100) to provide a contextual response to a user, characterized in that, the system (100) comprises: a processor (201), a memory (202) communicatively coupled with the processor (201), wherein the memory (202) is configured to store one or more executable instructions, which cause the processor (201) to: receive (301) a natural language input query from a user, wherein the natural language input query is in a first language; identify (302) an intent of the natural language input query based on one or more vector embeddings associated with the natural language input query; classify (303) the intent into one of a transactional query, a non-domain specific query, or a non-transactional domain specific query; generate (304) a response to the natural language input query based on the classified intent using at least one of a generic LLM, a non-transactional resolution model, and a transactional query resolution model, wherein the response is in a second language;translate (305) the response from the second language to the first language to create the contextual response; and provide (306) the contextual response to the user, wherein the contextual response is in the first language associated with the natural language input query from the user.

16. A non-transitory computer-readable storage medium having stored thereon, a set of computer-executable instructions causing a computer comprising one or more processors to perform steps comprising: receiving (301) a natural language input query from a user, wherein the natural language input query is in a first language; identifying (302) an intent of the natural language input query based on one or more vector embeddings associated with the natural language input query; classifying (303) the intent into one of a transactional query, a non-domain specific query, or a non-transactional domain specific query; generating (304) a response to the natural language input query based on the classified intent using at least one of a generic LLM, a non-transactional resolution model, and a transactional query resolution model, wherein the response is in a second language; translating (305) the response from the second language to the first language to create the contextual response; and providing (306) the contextual response to the user, wherein the contextual response is in the first language associated with the natural language input query from the user.

Images