WO2025169244A1

WO2025169244A1 - A system and method for message template validation

Info

Publication number: WO2025169244A1
Application number: PCT/IN2025/050188
Authority: WO
Inventors: Mohit Bansal; Aldena SUPRAJA; Koya SATISH; Cherukuri PADMAJA; Sunil BACHAVAL
Original assignee: Tanla Platforms Ltd
Current assignee: Tanla Platforms Ltd
Priority date: 2024-02-11
Filing date: 2025-02-11
Publication date: 2025-08-14
Anticipated expiration: 2026-08-11

Abstract

Disclosed herein is a system to validate Short Messaging Services (SMS) template data to register in a validation database. The system receives SMS template data, comprising an SMS template and a header and associated with an entity, processes the SMS template data to determine template parameters and identifies relevant regulatory guidelines based on the template parameters. The system determines regulatory compliance status of the SMS template data based on the relevant regulatory guidelines, presence of malicious elements and determines entity scores based on historical registration data of the entity. The system further validates the SMS template data to register in the validation database based on the regulatory compliance, presence of malicious elements and the entity scores. Upon successful validation, the system automatically updates a validation database with the SMS template data and the entity may send a plurality of SMSs to a plurality of individuals using the SMS template data.

Description

A SYSTEM AND METHOD FOR MESSAGE TEMPLATE VALIDATION

FIELD OF THE DISCLOSURE

[001] The following disclosure relates to Short Messaging Services (SMS) and in particular to a method and a system for validating SMS template data for registration in a validation database.

BACKGROUND

[002] Recently, there have been umpteen number of cybercrime attacks which have been taken place through various modes of communication including e-mails, social media platforms, voice communications, SMS communications and the like. One particular form of such a cybercrime attack includes scam or spam SMS. For instance, bulk spam SMS transmission may include a spammer or a fraudster who sends unsolicited messages to users. Such SMS may be similar to an Application to Person (A2P) message that may originate from an application and may be addressed to a person. Examples of such A2P messages include appointment reminders from healthcare providers, bank notifications about transactions, and one-time verification codes from e-commerce platforms.

[003] Regulatory authorities across the globe have initiated various precautionary measures to avoid cyber-crime attacks happening through the Application to Person (A2P) messages. One such measure includes registration of an SMS template and/or a header of such messages, by entities, with the regulatory bodies and/or one or more telecommunication operators. Further, the regulatory bodies would approve or reject the SMS template and/or the header by analyzing the content in the SMS template and/or the header based on guidelines of regulatory bodies and/or telecommunication operators. For instance, the guidelines of telecommunication operators may include guidelines set by code of practices. However, the existing procedure is highly manual in nature where each request takes significant time to receive approval/ refusal. Further, there is a limitation in terms of understanding of the guidelines among the individuals who examine the template data as per the guidelines to approve or refuse the template data. Also, there is a factor of human bias since various individuals have a varied understanding of guidelines and hence there is lot of information asymmetry among the individuals.

[004] Hence, there is a need for a system and a method to provide one or more solutions to the above-mentioned problems.

[005] The information disclosed in this background of the disclosure section is only for enhancement of understanding of the general background of the disclosure and should not be taken as acknowledgment or any form of suggestion that this information forms prior art already known to a person skilled in the art.

SUMMARY

[006] Disclosed herein is a method of validating Short Message Services (SMS) template data. The method comprises receiving, via a communication network, the SMS template data associated with an entity. The method comprises processing the SMS template data to determine a plurality of template parameters associated with the SMS template data using a set of feature extraction models and identifying one or more relevant regulatory guidelines based on the plurality of template parameters. The method comprises determining a regulatory compliance status of the SMS template data by correlating the SMS template data with the one or more relevant regulatory guidelines using an agentic Artificial Intelligence (Al) model and determining presence of at least one malicious element in the SMS template data. The method further comprises determining at least an entity compliance score based on historical registration data of the entity. The method comprises validating the SMS template data based at least on the regulatory compliance status, the presence of the at least one malicious element and the entity compliance score using a machine learning based decision tree and automatically updating a validation database with the SMS template data upon successfully validating the SMS template data.

[007] Further disclosed herein is a system to validate Short Messaging Services (SMS) template data comprising a memory and a processor coupled with the memory. The processor is configured to receive, via a communication network, SMS template data associated with an entity. The processor is configured to process the SMS template data to determine a plurality of template parameters associated with the SMS template data using a set of feature extraction models and identify one or more relevant regulatory guidelines based on the plurality of template parameters. The processor is configured to determine a regulatory compliance status of the SMS template data by correlating the SMS template data with the one or more relevant regulatory guidelines using an agentic Artificial Intelligence (Al) model and determining presence of at least one malicious element in the SMS template data. The process is configured to determine at least an entity compliance score based on historical registration data of the entity. The processor is further configured to validate the SMS template data based at least on the regulatory compliance status, the presence of the at least one malicious element and the entity compliance score using a machine learning based decision tree and automatically update the validation database with the SMS template data upon successfully validating the SMS template data.

[008] Disclosed herein as a non-transitory computer-readable medium having program instructions stored thereon, when executed by a Short Message Service (SMS) template validation system, facilitate the SMS template validation system for validating SMS template data by performing operations. The operations comprise receiving, via a communication network, the SMS template data associated with an entity and processing the SMS template data to determine a plurality of template parameters associated with the SMS template data using a set of feature extraction models. The operations comprise identifying one or more relevant regulatory guidelines based on the plurality of template parameters and determining a regulatory compliance status of the SMS template data by correlating the SMS template data with the one or more relevant regulatory guidelines using an agentic Al model. The operations comprise determining presence of at least one malicious element in the SMS template data and determining at least an entity compliance score based on historical registration data of the entity. The operations comprise validating the SMS template data based at least on the regulatory compliance status, the presence of the at least one malicious element in the SMS template data and the entity compliance score using machine learning based decision tree. The operations comprise automatically updating a validation database with the SMS template data upon successfully validating the SMS template data.

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

BRIEF DESCRIPTION OF DRAWINGS

[0010] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the figures to reference like features and components. Some embodiments of device or system and/or methods in accordance with embodiments of the present subject matter are now described, by way of example only, and with reference to the accompanying figures, in which: [0011] Fig. 1 illustrates an exemplary architecture of a system to validate SMS template data to register in a validation database in accordance with embodiments of the present disclosure; [0012] Fig. 2 illustrates a detailed block diagram of the system to validate the SMS template data in accordance with an embodiment of the present disclosure;

[0013] Fig. 3 illustrates an exemplary flowchart of a method for validating the SMS template data in accordance with an embodiment of the present disclosure;

[0014] Fig. 4 illustrates an exemplary flowchart of a method for validating the SMS template data in accordance with another embodiment of the present disclosure; and

[0015] Fig. 5 illustrates a block diagram of an exemplary computer system for implementing embodiments consistent with the present disclosure.

[0016] The figures depict embodiments of the disclosure for purposes of illustration only. One skilled in the art will readily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.

DETAILED DESCRIPTION

[0017] In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

[0018] While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and will be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the scope of the disclosure.

[0019] The terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a device or system or apparatus proceeded by “comprises. . . a” does not, without more constraints, preclude the existence of other elements or additional elements in the device or system or apparatus.

[0020] The present disclosure relates to various methods and systems to validate Short Message Services (SMS) template data to register in a validation database, such as a distributed database upon validation. The system receives the SMS template data including an SMS template and an SMS header from an entity to validate the SMS template data. SMS template is a predefined structure for composing Short Message Service (SMS) messages, commonly used for promotional, transactional, or service communications. The SMS header is an alphanumeric identifier assigned to a specific individual, business, or legal entity to transmit a plurality of SMSs based on the SMS template. The system processes the SMS template data to determine a plurality of template parameters associated with the SMS template data indicating features of the SMS template data. The plurality of template parameters include a type of the template, a template usage scenario, a presence of an entity keyword within one or more of the SMS template and the header, the entity keyword, an entity associated with the entity keyword, a relevance of the entity keyword with a pre-registered list of entity keywords of the entity, a count of consecutive variables within the SMS template, one or more formats of one or more variables within the SMS template, and a validation of the one or more formats.

[0021] The system comprises identifying one or more regulatory guidelines based on the plurality of template parameters and determining whether the SMS template data complies with the one or more regulatory guidelines. The system also verifies whether the SMS template data comprises malicious content such as restricted words, phrases or any other elements and determines a maliciousness of the SMS template data as ‘malicious’ or ‘non-malicious’. Further, the system evaluates an entity compliance score and an entity quality score of the entity based on historical SMS template data registered by the entity. Thereafter, the system validates the SMS template data by determining whether the SMS template data satisfies a plurality of validation criteria based on the regulatory guidelines, maliciousness, the plurality of template parameters, the entity compliance score and the entity quality score. If the SMS template data satisfies the plurality of validation criteria, the system successfully validates the SMS template data and registers the SMS template data in the validation database. Further, the entity may initiate sending SMSs using the header and in the format of the SMS template to a plurality of individuals.

[0022] On the other hand, if the SMS template data fails to satisfy at least one of the plurality of validation criteria, the system provides recommendations to the entity to modify the SMS template data to satisfy the plurality of validation criteria. A user associated with the entity may review the recommendations and may modify the SMS template data based on the recommendations. Further, the system may re-validate the modified SMS template data and may determine whether the modified SMS template data can be approved or refused. Alternatively, the system sends the SMS template data to a service operator for manual verification if the SMS template data fails to satisfy at least one of the plurality of validation criteria. Further, the system approves or refuses the SMS template data to be registered in the validation database based on the manual verification. Thus, the systems and methods of the present disclosure automate faster validation of the SMS template data and enables automatic registering of the SMS template data in the validation database upon successfully validating the SMS template data, thereby reducing delays in manual verification and increasing accuracy of the validation by automating the manual processing.

[0023] In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.

[0024] Fig. 1 illustrates an exemplary architecture of a system to validate SMS template data in accordance with an embodiment of the present disclosure.

[0025] As shown in Fig. 1, the exemplary architecture 100 comprises a Short Messaging Services (SMS) template validation system (ST VS) 102 to validate SMS template data received from an entity device 104 of an entity 106. The SMS template data may comprise at least an SMS template and optionally, an SMS header. The SMS template may be defined as a predefined structure for composing Short Message Service (SMS) messages, commonly used for promotional, transactional, or service communications. The SMS template may comprise a combination of fixed content and variable content. The fixed content may remain uniform across all instances of the SMS template, ensuring consistency in core message structure. The variable content may comprise content that is dynamically populated with specific data such as, but not limited to, recipient data, transaction data, dates, times, locations, or other contextual elements to personalize the communication and meet diverse messaging requirements. The SMS header, also referred to herein as header, may be an alphanumeric identifier (ID) assigned to a specific individual, business, or legal entity to send a plurality of SMSs to a plurality of individuals. The header may enable the sender to authenticate while sending the plurality of SMSs. The header may function as a sender ID that may aid the recipients in recognizing the sender and may play a crucial role in ensuring compliance with regulatory requirements for SMS communications. The headers may indicate an origin of the SMS message to the recipient. [0026] The architecture 100 may also comprise at least a validation database 108 to store validated SMS template data and a regulatory guidelines database 110 to retrieve relevant regulatory guidelines and validate the SMS template data based on the relevant regulatory guidelines. The architecture 100 may also comprise at least a telecommunication server 112 and a regulatory server 114. The STVS 102 may be implemented at a computing device such as, but not limited to, a centralized server. The STVS 102 may be communicatively coupled with the entity device 104, the telecommunication server 112, the regulatory server 114, the validation database 108 and the regulatory guidelines database 110 using a wired or a wireless network connection (indicated as a solid line), such as, but not limited to, Local Area Network or the Internet. In some embodiments, the STVS 102 may be implemented at the telecommunication server 112 or the regulatory server 114 or both.

[0027] The STVS 102 may be configured to receive the SMS template data from the entity 106 and may validate the SMS template data based at least on the plurality of template parameters, one or more relevant regulatory guidelines, historical registration data of the entity 106, and maliciousness of the SMS template data, as may be explained in more detail below. Further, the STVS 102 may automatically register the SMS template data in the validation database 108 upon successfully validating the SMS template data and may transmit the SMS template data for manual verification if the SMS template data fails the validation.

[0028] The entity device 104, also referred to herein as a device of the entity 106, may be a computing device of the entity 106 that is configured to send a request to validate the SMS template data from the entity 106 and receive one or more notifications from the STVS 102 related to validation of the SMS template data. The one or more notifications may indicate whether the validation of the SMS template data is successful or failed. In case of failed validation, the one or more notifications may also include one or more modifications that may be made to the SMS template data to increase probability of successful validation. In some embodiments, the entity device 104 may be a computing device that may be configured to transmit a plurality of SMSs, such as, but not limited to, a plurality of Application to Person (A2P) messages, to a plurality of individuals as per the SMS template and the header upon successfully validating the SMS template data. The entity device 108 may be a server computing device of an entity that may transmit the plurality of SMSs to the plurality of individuals.

[0029] The entity 106 may be associated with the entity that may transmit the plurality of SMSs to the plurality of individuals. The entity 106 may send the request to validate the SMS template data to the STVS 102. The entity 106 may also modify the SMS template data based on one or more notifications received from the STVS 102 when the validation of the SMS template data is failed.

[0030] The validation database 108 may be configured to store validated SMS template data received from a plurality of entities and successfully validated. The validation database 108 may be a centralized database or a distributed database, such as, but not limited to, a distributed ledger table (DLT). In some embodiments, the validation database 108 may be coupled with the telecommunication server 112 or the regulatory server 114. For example, the validation database 108 may be a DLT of the telecommunication server 112. In these embodiments, the validation database 108 of a telecommunication operator may be communicatively coupled or has access to the validation database 108 of another telecommunication operator. Alternatively, the validation database 108 may be a combination of the validation databases 108 of a plurality of telecommunication operators and the regulatory server 114. For example, the validation database 108 may be a consortium of DLTs of the plurality of telecommunication operators and/or the regulatory server 114. The validation database 108 may be implemented as a hardware memory or a blockchain network. The STVS 102 may have access to the validation database 108 to add one or more blocks, and/or retrieve information from the one or more blocks to the validation database 108.

[0031] The validation database 108 may store historical registration data related to the plurality of entities 106. The historical registration data of each entity 106 comprises one or more identifiers, one or more names, a list of pre-registered entity keywords, one or more preregistered SMS templates, one or more pre-registered headers, one or more blacklisted SMS templates and/or headers of the entity 106, one or more rejected SMS templates and/or headers, timestamps of the one or more pre-registered SMS templates and/or headers, one or more complaints received against the entity 106, a plurality of SMSs transmitted by the entity 106 based on each pre-registered SMS template and timestamps of transmission of the plurality of SMSs. The entity keywords may be defined as one or more brand names of the entity 106.

[0032] The regulatory guidelines database 110 may store a plurality of regulatory guidelines of one or more regulatory authorities that must be complied by the SMS template data for registering in the validation database 108. For example, the regulatory authorities may include, but not be limited to, US Federal Communications Commission (FCC), Telecom Regulatory Authority of India (TRAI), Communications, Space and Technology Commission (CST) at Kingdom of Saudi Arabia, Telecommunications and Digital Government Regulatory Authority at United Arab Emirates and Ministry of Communication and Digital Affairs Indonesia. The regulatory guidelines database 110 may also comprise one or more compliance rules associated with each regulatory guideline to verify whether the SMS template data complies with each regulatory guideline. In some embodiments, the regulatory guidelines database 110 may be implemented at the regulatory server 114.

[0033] The telecommunication server 112, also referred to as telecom server 112, may be a serving computing device associated with a telecommunication operator, also referred to as telecom operator. The telecom server 112 may be configured to receive a plurality of requests to validate a plurality of SMS template data from the plurality of entities and register validated SMS template data in the validation database 108. In some embodiments, the telecom server 112 may comprise the validation database 108. The telecom server 112 may also be configured to perform other operations such as, but not limited to, receiving A2P SMSs from a plurality of entities 106 and transmitting to a plurality of recipients. The telecom server 112 may be configured to perform various other operations that have not been described herein.

[0034] The regulatory server 114 may be a serving computing device associated with a regulatory authority that may be configured to verify whether the SMS template data complies with one or more relevant regulatory guidelines and may store the SMS template data in the validation database 108 upon successful validation. In some embodiments, one or more service operators associated with the regulatory server 114 may validate the SMS template data to register in the validation database 108. In some embodiments, the regulatory server 114 may comprise the regulatory guidelines database 110. In some other embodiments, the regulatory server 114 may comprise the validation database 108 to register the validated SMS template data of the plurality of entities 106.

[0035] The one or more components of the architecture 100 may be communicatively coupled with each other via the communication network. The communication network may include, without limitation, a direct interconnection, a Local Area Network (LAN), a Wide Area Network (WAN), a wireless network, a point-to-point network, or any other network configuration. One of the most common types of networks in current use is a Transfer Control Protocol and Internet Protocol (TCP/IP) network for communication between a database client and a database server. Other common Internet Protocols (IP) that may be used for such communication include Hyper Text Transfer Protocol Secure (HTTPS), File Transfer Protocol (FTP), and Wireless Application Protocol (WAP) and other secure communication protocols etc.

[0036] In operation, the STVS 102 may receive the SMS template data from the entity 106, for example through the entity device 104, to validate the SMS template data for registering in the validation database 108. The SMS template data may comprise at least a template of an SMS and a header. The template of the SMS or SMS template may be defined as a format of a sequence of words and/or numbers and other types of message data that the entity 106 would be sending to a plurality of individuals. The SMS may be any text message that may be sent by the entity 106, such as, for example, an entity, to the plurality of individuals in the format of the SMS template with the header. In one example, the SMS template may be an A2P message sent by the entity to an individual. One or more numbers or usernames specific to individuals in the SMS may be replaced with variables in the SMS template. In one embodiment, the SMS may be sent to the plurality of individuals when an action that has been performed by the individual, or as a promotional message to the individual or as a password to the individual. In other embodiments, the SMS may be related to any other aspect that may follow the SMS template. For example, the SMS template may be "Dear {#var#}, your account ending with {#var#} has been debited by USD {#var#} - XYZ Bank". The header may be a sender name of the entity 106 and that may be displayed as the sender’s name to the individual upon receiving the SMS. For example, the header may be XYZBK.

[0037] The ST VS 102 may analyze the SMS template data to extract a plurality of template parameters indicating one or more textual features of the SMS template and/or the header. Further, the ST VS 102 may identify one or more relevant regulatory guidelines from the regulatory guidelines database 110 based on the plurality of template parameters. The one or more relevant guidelines may be applicable to the SMS template data and the SMS template data must comply with the one or more relevant regulatory guidelines in order to send the SMS to the plurality of individuals. Further, the STVS 102 verifies whether the SMS template data complies with the one or more relevant regulatory guidelines or not. For example, if the SMS template is related to sending a One Time Password (OTP), the STVS 102 verifies whether the SMS is of a specified length as per the regulatory guidelines.

[0038] Further, the STVS 102 determines a maliciousness of the SMS template data by verifying if the SMS template and/or the header includes any malicious content, such as, but not limited to, restricted words or phrases. The STVS 102 also computes an entity compliance score and an entity quality score of the entity 106 based on historical registration data of the entity 106. The entity compliance score may indicate a level of compliance of historical SMS template data requested by the entity 106 in the past to register in the validation database 108. The entity quality score may indicate an overall SMS transmission behavior of the entity 106, as compared to other entities of same group. For example, other entities may be peers in an industry same as that of the entity 106. The STVS 102 may determine whether the plurality of template parameters, the maliciousness, regulatory compliance, the entity compliance score and the entity quality score satisfy a plurality of validation criteria, as may be explained in detail below.

[0039] If the SMS template data satisfies the plurality of validation criteria, the STVS 102 may successfully validate the SMS template data and may automatically register the SMS template data in the validation database 108. For example, the STVS 102 may add a block including the SMS template data to the blockchain network (validation database 108). The STVS 102 may notify the entity 106, for example, through the entity device, that the SMS template data is successfully validated and registered in the validation database 108. Further, the entity 106 may initiate transmission of the SMSs as per the SMS template in the name of the header to the plurality of individuals.

[0040] On the other hand, if the SMS template data fails to satisfy the plurality of validation criteria, the STVS 102 may determine failed validation and may transmit the SMS template data to a service operator for manual validation. The STVS 102 may validate the SMS template data based on one or more inputs received from the service operator. Alternatively, the STVS 102 may suggest one or more modifications that may be performed on the SMS template and/or the header to improve the probability of successful validation.

[0041] Thus, the STVS 102 enables faster and accurate validation of the SMS template data and automatically updates the validation database 108 upon successful validation of the SMS template data by avoiding manual waiting time periods. The STVS 102 improves accuracy of validation by taking into account various significant factors such as historical registration data of the entity 106, relevance of entity keywords with the list of pre-registered entity keywords and the like. By recommending modifications to the SMS templates in case of failed validations, the STVS 102 may enable the entities 106 to escalate a chance of successful validation.

[0042] Fig. 2 illustrates a detailed block diagram 200 of the STVS 102 to validate the SMS template data in accordance with an embodiment of the present disclosure.

[0043] The STVS 102 may comprise, without limiting to, a processor 202, a memory 204, and a plurality of modules 206 and data 208. The processor 202 may be any hardware processing system such as a microprocessor, a microcontroller, an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or System on Chip (SOC), Electronic Control unit (ECU) or any other type of processing system. The memory 204 may be any type of hardware data storage unit such as a Read Only Memory (ROM), Random Access Memory (RAM), a temporary or a permanent storage system. [0044] The plurality of modules 206 may include a data processing module 210, a regulatory compliance verification module 212, a maliciousness determination module 214, an entity behavior assessment module 216, and a template validation module 218. The data 208 may comprise the template parameters 220, regulatory compliance status 222, maliciousness 224, entity scores 226 and validation output 228. In some embodiments, the plurality of modules 206 may also be configured within the processor 202.

[0045] In an embodiment, the data processing module 210 may be configured to receive the SMS template data from the entity 106, for example, through the entity device 104 via the communication network. The data processing module 210 may process the SMS template data using one or more Machine Learning models to evaluate the plurality of template parameters 220. Initially, the STVS 102 may process the SMS template data with a language processing model to generate a plurality of numerical embeddings of the SMS template data. In one embodiment, the language processing model may be a word2vec model, that may be pretrained to generate a plurality of numerical vector embeddings from a plurality of SMS templates and/or headers in order to determine the semantic relationship between variable elements and/or fixed elements in the SMS template data.

[0046] Thereafter, the data processing module 210 may be configured to analyze the plurality of numerical embeddings using a set of feature extraction (FE) models. Each FE model may be an Artificial Intelligence/ML (AI/ML) model trained to analyze the plurality of numerical embeddings of the SMS template data and assign a value to the plurality of template parameters 220 based on the analysis. In one embodiment, the set of FE models may comprise extreme gradient boosting (XGBoost) classifier, Random Forest, and Light Gradient Boosting mechanism (LightGBM).

[0047] Each FE model may comprise at least a plurality of nodes, and one or more decision trees. Each FE model may be trained based on a plurality of training datasets comprising input training datasets including a plurality of SMS templates and/or headers and the output training datasets including corresponding plurality of template parameters 220. During training, the plurality of template parameters 220 may be determined for each input SMS template and/or header and the determined plurality of template parameters 220 may be compared with the corresponding output training datasets. Further, based on the comparison, one or more of the plurality of nodes, the plurality of decision trees and a plurality of input samples associated with the FE model may be modified to improve an accuracy and/or performance. In one embodiment, one or more hyperparameters may be tuned for the FE model until the model achieves a desired accuracy and/or performance criteria. The one or more hyperparameters may comprise at least a tree depth, a threshold number of nodes and a threshold number of samples to split. The tree depth may be a threshold length or depth of a decision tree used in the FE model. The threshold number of nodes may be a maximum number of nodes within the decision tree. The threshold number of samples may indicate a minimum number of data points that may be required to split a node within the decision tree.

[0048] The plurality of template parameters 220 may comprise, but not limited to, a type of the template, a template usage scenario, presence of an entity keyword within one or more of the SMS template and the header, the entity keyword, an entity identifier associated with the entity keyword, a relevance score of the entity keyword compared with a pre-registered list of entity keywords of the entity, presence of consecutive variables within the SMS template, one or more formats of one or more variables within the SMS template, or a validation of the one or more formats.

[0049] The type of template may be defined as a classification of the template or an objective of the SMS template. For example, the type of template may be one of promotional, transactional and OTP messages. The template usage scenario may be defined as a specific use case where the entity uses the SMS template to send an SMS to an individual. For example, the template usage scenarios related to a bank may be one of authentication, loan offer, or generic service. The entity keyword may be defined as a brand name associated with any entity. The entity identifier may be defined as an identifier, such as, but not limited to, an alphanumeric sequence, that may be assigned to the entity 106 to uniquely identify the entity 106. The entity identifier may be assigned by the regulatory server 114. Each entity 106 may be associated with a list of entity keywords that may have been pre-registered in the validation database 108. In other words, each entity 106 may be required to pre-register its brand names in the validation database 108 to validate the SMS template data and further to transmit a plurality of SMSs using the SMS template.

[0050] The relevance score of the entity keyword compared with the list of pre-registered entity keywords of the entity 106 may indicate an amount of relevance of the entity keyword with the entity. Each FE model may determine whether at least one entity keyword is present in the SMS template or the header. Further, when at least one entity keyword is present, each FE model may determine a relevance score of the at least one entity keyword with the at least one of the list of pre-registered entity keywords of the entity 106. In other words, each FE model may determine whether the brand name present within the SMS template and/or header belongs to the entity 106 or not. The relevance score may be high when the at least one entity keyword belongs to the entity 106 and may be low when the at least one entity keyword does not belong to the entity 106.

[0051] The variables may indicate a general value that may be replaced with a textual or numerical values later. For example, the variables may comprise, but not limited to {#var#}, present within the SMS template. Further, each FE model may determine a continuous or consecutive occurrence of the variables or the count of consecutive variables in the SMS template with any special character and space between the variables. This may be later used to verify compliance of the regulatory guidelines. The formats of the variables may indicate one various types of formats of each variable such as a textual format, numerical format or an alphanumerical format. Further the validation of the one or more formats may indicate whether the variables have been properly formatted within the SMS template or not. For example, each FE model may determine whether any textual or numerical values within the SMS have been replaced with general format of variables or not.

[0052] Each of the plurality of template parameters 220 may comprise a set of predefined values. For example, the predefined set of values for the presence of an entity keyword within one or more of the SMS template and the header, the presence of consecutive variables within the SMS template and the validation of the one or more formats may have two values ‘Positive’ or ‘Negative’. Each FE model may assign a value to each of these plurality of template parameters 220 from the corresponding set of predefined values.

[0053] Further, the data processing module 210 may be configured to compute a count of each value of the set of predefined values assigned to the template parameter 220 and may determine the value with maximum count as the value of the template parameter 220. For example, if two FE models have assigned ‘positive’ to the presence of entity keyword within the SMS template and one FE model has assigned a ‘negative’ value, the data processing module 210 determines the value for this template parameter 220 as ‘positive’ as the value has been assigned by a maximum number of FE models. In one embodiment, the data processing module 210 may be configured with a maximum voting classifier configured to determine the values of the plurality of template parameters 220 based on the maximum count.

[0054] The regulatory compliance verification module 212, also referred to herein as compliance module 212, may be configured to receive the plurality of template parameters 220 from the data processing module 210. The compliance module 212 may identify one or more relevant regulatory guidelines, from the regulatory guidelines database 110, that may be relevant and may be applicable to the SMS template data based on one or more of the plurality of template parameters 220. The compliance module 212 may retrieve the one or more relevant regulatory guidelines from the regulatory guidelines database 110. For example, the compliance module 212 may identify regulatory guidelines based at least on the type of template, the presence of entity keyword or the one or more formats of the one or more variables.

[0055] Further, the compliance module 212 may determine whether the SMS template data complies with the one or more relevant regulatory guidelines or not. The compliance module 212 may be be configured with an agentic Al model to divide a regulatory compliance verification task, herein also referred to as ‘task’, of determining the compliance of at least one regulatory guideline into a plurality of sub-tasks. For example, the plurality of sub-tasks for an OTP SMS template may comprise “Confirming that variable placeholders are correctly formatted” and “Ensuring adherence of the SMS template to specific length and content requirements”. The division of tasks by the agentic Al model may be based on a plurality of factors, such as, but not limited to, types of actions, a plurality of compliance models, and the like. Further, the plurality of sub-tasks may be executed simultaneously or in parallel to optimize or maximize the efficiency of the determination.

[0056] In one embodiment, the plurality of compliance models may comprise at least a websearch model, a Retrieval Augmented Generation (RAG) model, a database fetching model and a database submission model.

[0057] The web-search model may be trained to search a plurality of open resources, (for e.g., the Internet) to obtain detailed entity information related to the entity 106. The plurality of open resources may comprise, but not limited to, news outlets, regulatory websites, consumer forums, and social media platforms. The detailed entity information indicating entity profile data, that may include, but not limited to, the primary line of business and key operations, type of organization (for e.g., company, government, individual, or other), an estimate of communication volume across various communication channels (for e.g., SMS, WhatsApp, Rich Communication Services (RCS)), associated identifiers (for e.g., brands, products, trademarks), data related to legal cases or consumer complaints against the entity 106.

[0058] The web-search model may be comprise one or more natural language processing (NLP) models that may systematically extract structured and unstructured data from the plurality of open resources to obtain the detailed entity information representing a comprehensive picture of the entity 106. Once the detailed entity information is obtained, the web-search model may analyze the detailed entity information to determine one or more regulatory status indicators of the entity 106 that may impact the regulatory compliance status for registering the SMS template data in the validation database 108. The one or more regulatory status indicators may indicate a status of one or more of unresolved legal disputes, a count of consumer grievances, mismatches in the type of SMS template and a primary line of business of the entity 106.

[0059] If there are a number of unresolved legal disputes, the web-search model may determine the regulatory status indicator for the unresolved legal disputes as negative status. When there are significant number of consumer grievances, the regulatory status indicator for consumer grievances may indicate a negative status. On the other hand, when the number of consumer grievances is less or close to zero, the regulatory status indicator may be determined as positive status. The web-search model may also incorporate a grounding mechanism that ensures the detailed entity information is cross-verified with reputable and authoritative sources, thereby mitigating risk of hallucinations.

[0060] The RAG model may be configured with a language processing model that is trained to retrieve the one or more relevant regulatory guidelines from secured databases such as, but not limited to, the regulatory guidelines database 110. In some embodiments, the RAG model may retrieve the one or more relevant regulatory guidelines from validated data sources. Further, the RAG model may generate a plurality of compliance rules to verify whether the SMS template data complies with the one or more relevant regulatory guidelines. For example, for the sub-task “ensuring adherence of the SMS template to specific length and content requirements”, the RAG model may generate a first compliance rule to check if the SMS template is of specific length and a second compliance rule to verify if specific content is present within the SMS template or not. Further, the RAG model may correlate the SMS template data with the plurality of compliance rules and verify whether the SMS template data satisfies the plurality of compliance rules and may generate an output based on the verification. The output may be ‘positive’ if the rule is satisfied or ‘negative’ if the rule is not satisfied.

[0061] The database fetching model may be trained to retrieve the one or more relevant regulatory guidelines or clauses, from the regulatory guidelines database 110 and/or the plurality of open resources, that are relevant to the sub-task. For example, when checking for mandatory disclaimers in promotional SMS templates, the database fetching model may retrieve the relevant clauses from the regulatory guidelines database 110. The database submission model may be trained to store the output of each sub-task in the validation database 108 or to update the validation database 108 with new interpretations or information in case of new scenarios. In some embodiments, the compliance module 212 may comprise any other language processing models, such as, but not limited to, large language models, to perform the sub-tasks. Utilizing various models may enhance flexibility to scale the tasks based on demand and adapt to different operational environments. The language processing models may be employed for more complex tasks like understanding nuanced regulatory language or identifying subtle violations.

[0062] In another exemplary embodiment, the compliance module 212 may be configured with an agentic Al model trained to autonomously decompose complex regulatory compliance tasks into a plurality of manageable sub-tasks. The agentic Al model may also be configured to strategically assign the execution of the plurality of manageable sub-tasks to specialized Al models. The agentic Al model may analyze the SMS template data and the one or more relevant regulatory guidelines to dynamically determine the plurality of sub-tasks to verify the compliance of the one or more relevant regulatory guidelines. For example, the plurality of sub-tasks may include, but not limited to, verifying proper formatting of variable placeholders and ensuring adherence to specific content and length requirements. Further, the agentic Al model may subsequently assign the plurality of sub-tasks to the plurality of compliance models. [0063] In one exemplary embodiment, the web-search model may search the Internet to identify relevant information on the entity 106 and the database fetching model may retrieve the plurality of clauses or guidelines from the regulatory guidelines database 110. The RAG model may generate the plurality of compliance rules to verify whether the SMS template data complies with the one or more relevant regulatory guidelines and may determine whether the SMS template data complies with the plurality of compliance rules. Further, the database submission model may receive the outputs of the sub-tasks from the RAG model and store the outputs in the memory 204.

[0064] By orchestrating the plurality of sub-tasks in parallel or concurrently, the agentic Al model optimizes processing efficiency while also generating a reason array that records the one or more identified regulatory guidelines, generated plurality of compliance rules, and the outcomes of each sub-task. The reason array facilitates traceability, auditing, and continuous learning, thereby enhancing the adaptability and scalability of the STVS 102 to accommodate evolving regulatory requirements and diverse operational environments.

[0065] In one embodiment, to mitigate the risk of hallucination (i.e., the generation of plausible but incorrect or fabricated information), each of the plurality of regulatory compliance models and the agentic Al model may be trained to retrieve data only from verified and authoritative data sources. For example, the RAG model may not only generate plurality of compliance rules based on internal processing but also may cross-validate the plurality of compliance rules against actual entries in the regulatory guidelines database 110. Similarly, the web-search model and the database fetching models may ensure that the entity information, the one or more relevant regulatory guidelines, clauses, or updates are directly sourced from validated repositories. Thus, the compliance module 212 ensures that any interpretation, rule generation, or compliance determination is firmly anchored in verified regulatory information, thereby significantly reducing the risk of erroneous outputs.

[0066] Further, the compliance module 212 may determine the outputs of the plurality of subtasks as one of ‘positive’ or ‘negative’ and may combine outputs of the plurality of sub-tasks to determine a regulatory compliance status 222 of the SMS template data as ‘positive’ or ‘negative’. When the output of each sub-task or each of the plurality of compliance rules is ‘positive’, the regulatory compliance status 222 is ‘positive’ and when the output of at least one sub-task or at least one of the plurality of compliance rules is ‘negative’, the regulatory compliance status 222 is ‘negative’. The ‘positive’ regulatory compliance status 222 indicates that the SMS template data has complied with all the one or more relevant regulatory guidelines. Whereas the ‘negative’ regulatory compliance status 222 indicates that the SMS template data has violated at least one of the one or more relevant regulatory guidelines. In case of violation, the compliance module 212 may store the details of violating at least one regulatory guideline in the memory 204 and/or the validation database 108 indicating that the entity 106 has violated the at least one regulatory guideline.

[0067] Further, the compliance module 212 may also store the identified one or more regulatory guidelines, the plurality of compliance rules generated and the outputs of each compliance rule in a reason array. The reason array may be later used for traceability and verification of correctness of the compliance models in case of future errors or audits. The reason array may be stored in a short-time memory such as, but not limited to, the memory 204 enabling the compliance module 212 to quickly access the results of previous sub-tasks without re-performing the same sub-tasks when there is a need. Alternatively, the reason array may be stored in a long-term memory such as the validation database 108 or any other database that enables one or more AI/ML models of the compliance module 212 or the STVS 102 to learn from the reason array for future validations of new SMS template data.

[0068] The maliciousness determination module 214 may be configured to analyze the SMS template data using one or more language models to generate one or more textual embeddings and may determine a maliciousness 224 of the SMS template data. The maliciousness 224 may indicate an amount of or a number of malicious elements, such as, for example, words, within the SMS template data. In one embodiment, the one or more language models comprise a deep learning model, Bidirectional Encoder Representations from Transformers (BERT) and Language-Agnostic BERT Sentence Embeddings (LaBSE). The one or more language models may be trained to identify relationships between words in the SMS template, language patterns and semantics, malicious words or phrases from different languages.

[0069] The one or more language models may be trained using a plurality of training datasets of SMS templates and/or headers of a plurality of languages. The plurality of training datasets may be labelled artificially or manually to indicate whether the SMS template and/or header has malicious content or not. During the training, one or more model parameters of the one or more In one embodiment, the fine-tuning may be implemented as hyperparameter fine-tuning. [0070] The one or more model parameters may comprise a plurality of tokenizer parameters and a plurality of model configuration parameters. The plurality of tokenizer parameters may comprise maximum length of the input sequence that the model can process, a padding value of shorter input sequences, truncation at a beginning or an end of the input sequence and a format of outputs. The plurality of model configuration parameters may comprise a plurality of hidden states from layers of the one or more language models, attention weights and gradient checkpointing. Further, the one or more language models may be trained based on one or more training parameters. The one or more training parameters may comprise a learning rate, a per device train batch size, a number of training epochs, a weight decay, a warmup steps and mixed precision training.

[0071] The one or more language models may compare the one or more textual embeddings with a plurality of predefined malicious elements and may detect a presence or absence of one or more malicious elements within the SMS template data based on the comparison. The malicious elements may be one or more of words, phrases, numbers, images, special characters, emoticons and the like. The maliciousness determination module 214 may receive the plurality of template parameters 220 from the data processing module 210 to determine one or more thresholds for the comparison. The one or more thresholds may be defined as a number of malicious elements that may be present in the SMS template to classify the SMS template as malicious. For example, the threshold for a promotional SMS (for example 2 words) may be different from the threshold for a transactional SMS (for example 0 words).

[0072] The maliciousness determination module 214 may determine if the SMS template data comprises at least one malicious element and may classify the maliciousness 224 of the SMS template data as ‘malicious template data’. On the other hand, if the SMS template data does not comprise any malicious element, the maliciousness determination module 214 may classify the maliciousness 224 of the SMS template data as ‘non-malicious template data’.

[0073] The entity behavior assessment module 216 may be configured to retrieve historical registration data of the entity 106 from the validation database 108 and may determine an entity compliance score and an entity quality score of the entity 106. The entity behavior assessment module 216 may determine a plurality of entity parameters by processing the historical registration data. The plurality of entity parameters may comprise a registration rate of SMS templates, a ratio of count of blacklisted SMS templates of the entity to a count of a plurality of historical SMS templates, a rate of SMS transmissions, and a count of complaints received. The registration rate may indicate a rate of registration of the SMS templates in the past.

[0074] Further, the entity behavior assessment module 216 may correlate values of the plurality of entity parameters of the entity 106 with corresponding values of the plurality of entity parameters of one or more other entities that may be of same field as that of the entity 106. Based on the correlation, the entity behavior assessment module 216 may determine correlation data based on the correlation. The correlation data may include correlation values of each of the plurality of entity parameters. For example, the registration rate of the entity 106 is 10 per day and the registration rate of other entities is 100 per day, the correlation value may be 10% and when the registration rate of other entities is 12 per day, the correlation value may be approximately 100%.

[0075] Thereafter, the entity behavior assessment module 216 may compute an initial entity quality score based on at least one the registration rate of SMS templates, the rate of message transmissions, the count of complaints received, or the correlation data. The entity behavior assessment module 216 may compute an initial entity compliance score based on at least one of the count of complaints received, or the ratio of the count of blacklisted templates of the entity to the count of the plurality of historical SMS templates. Further, the entity behavior assessment module 216 may monitor the plurality of entity parameters over time and may compare the plurality of entity parameters and the correlation data with corresponding predefined thresholds. If any of the plurality of entity parameters and the correlation data exceed the corresponding predefined thresholds, the entity behavior assessment module 216 may dynamically update the initial entity quality score and the initial entity compliance score. Further, the entity behavior assessment module 216 may also store a reason for the updation in a reason array in the memory 204.

[0076] For example, if the registration rate or a rate of SMS transmissions exceed corresponding predefined thresholds value within specific time periods, the initial entity quality score may be reduced. A sudden increase in the registration rate may indicate suspicious activity, such as attempts to bypass scrutiny or launch spam campaigns. The reason for the reduction may be stored as “high registration rate”. In another example, if the ratio of count of blacklisted SMS templates of the entity to the count of the plurality of historical SMS templates exceeds by a corresponding predefined threshold, the initial entity compliance score may be decreased by a second predefined value.

[0077] In some embodiments, the entity behavior assessment module 216 may determine one or more rules that may be applicable to dynamically update the entity quality score and the entity compliance score, collectively referred to herein as entity scores 226, when a change any of the plurality of entity parameters has been monitored. For example, the rule may indicate reduce the entity quality score by x value. Further, the entity behavior assessment module 216 may assign weights to each rule based on one or more of the plurality of entity parameters. For example, a rule related to blacklisted templates might have a much larger negative impact on the entity compliance score than a rule related to slightly higher than average registration rate. In these embodiments, the entity behavior assessment module 216 may store the rule as a reason along with the entity parameter in the reason array.

[0078] Further, the entity behavior assessment module 216 may determine the entity quality score and the entity compliance score as the dynamically updated values of the initial quality score and the initial entity compliance score. The entity quality score may indicate an SMS transmission behavior and an overall quality of the entity 106. The entity compliance score may indicate historical regulatory compliance of the entity 106. In other words, the entity compliance score may indicate adherence of the header and/or the SMS template to the regulatory guidelines. High values of the entity quality score and the entity compliance score may indicate higher quality and compliance.

[0079] In some embodiments, the compliance module 212, the maliciousness determination module 214 and the entity behavior assessment module 216 may be implemented in multiple processors or in multiple processors of a multi-core processor and may be configured to parallelly process the SMS template data and/or the plurality of template parameters 220 received from the data processing module 210.

[0080] The template validation module 218 may be configured to receive the plurality of template parameters 220 from the data processing module 210, the regulatory compliance status 222 from the compliance module 212, the maliciousness 224 from the maliciousness determination module 214, and the entity scores 226 from the entity behavior assessment module 216. Further, the template validation module 218 may be configured to combine the received values and may validate the SMS template data based on the combination. The template validation module 218 may be configured with a decision model to determine whether SMS template data satisfies a plurality of validation criteria. [0081] The decision model may comprise a machine learning based decision tree with a plurality of nodes and a plurality of decision rules associated with each of the plurality of nodes. The template validation module 218 may provide the received values as inputs to the decision model. The decision model may analyze the inputs by traversing the inputs through the plurality of nodes and evaluating the plurality of decision rules associated with the plurality of nodes and eventually reaches to a leaf node.

[0082] The plurality of nodes of the decision tree may verify whether the SMS template data satisfies the plurality of validation criteria. The plurality of nodes may comprise at least one root node, one or more intermediate nodes and a plurality of leaf nodes. The root node may be a starting node of the decision tree. Each intermediate node may be associated with a decision rule that may verify whether one or more conditions are met by the SMS template data. For example, an intermediate node may verify whether the SMS template is related to a transactional SMS. Further, based on the verification, the intermediate node may transfer the data or the feature to another suitable node, for example another intermediate node or a leaf node. For example, if the regulatory compliance status is ‘negative’, SMS template data may reach to a leaf node indicating ‘failed validation’. Alternatively, in another example, if the regulatory compliance status is ‘positive’, the SMS template data may transfer to another intermediate node which verifies the entity quality score.

[0083] The plurality of leaf nodes may be associated with validation outputs 228, such as, but not limited to, ‘successful’ or ‘failed’. Each leaf node may be associated with a probability of the validation output 228, such as, for example, probability of successful validation and probability of failed validation. For example, when the SMS template data reaches the ‘successful validation’ leaf node upon passing through a plurality of intermediate nodes satisfying a threshold number of plurality of validation criteria, may have a higher probability of successful validation (for example 95%). In another example, if the SMS template data reaches the ‘successful validation’ leaf node after passing through a ‘malicious template data’ node, the probability of successful validation is very less (for example, 5%).

[0084] The decision model may compare the probability of validation output 228 with a predefined safe threshold value. The predefined safe threshold value indicates that the SMS template data is safe to validate. If the probability of validation output 228 exceeds the predefined safe threshold value, the decision model may successfully validates the SMS template data. This may indicate a high confidence that the SMS template data is compliant, safe and is of good quality. Alternatively, if the probability of validation output 228 is below the predefined safe threshold, the decision model may indicate ‘failed validation’. [0085] The decision model may be pre-trained using historical SMS template data of a plurality of entities 106 and their corresponding validation outputs 228 and/or service operator inputs in failed validation cases. During the training, the decision model may learn various features of the SMS template data that may be persuasive for determining the validation outputs 228. For example, the decision model may learn that the ‘negative’ regulatory compliance status is highly responsible for a failed validation. The decision tree may create the plurality of decision rules based on the learned features for the plurality of nodes of the decision model to verify whether the SMS template data satisfies the plurality of validation criteria.

[0086] The plurality of validation criteria may include, but not limited to, each of the plurality of template parameters 220, the entity quality score, and the entity compliance score satisfy corresponding predefined thresholds, the maliciousness of the SMS template data is non- malicious template data, and the regulatory compliance status 222 is ‘positive’. If the SMS template data satisfies each of the plurality of validation criteria, the template validation module 218 may determine the validation output 228 as ‘successful validation’ with high probability. Further, the template validation module 218 may register the SMS template data in the validation database 108 or may update the validation database 108 with the SMS template data. The template validation module 218 may further notify the entity 106 about the validation output 228 of the SMS template data.

[0087] On the other hand, when the SMS template data fails to satisfy at least one of the plurality of validation criteria, the template validation module 218 may determine that the validation output 228 of the SMS template data is ‘failed validation’. Further, the template validation module 218 may transmit the SMS template data to a service operator. The service operator may be a person who may manually validate the SMS template data and/or manually verify the validation performed by the ST VS 102 based on the information stored in the reason array. For example, the service operator may verify a correctness of the one or more regulatory guidelines identified by the compliance module 212 and may check the outputs determined for each sub-task is correct or incorrect. Further, the service operator may manually provide an ‘approval’ or ‘refusal’ of the SMS template data based on the verification. The template validation module 218 may receive an input as one of ‘approval’ or ‘refusal’ from the service operator and may update the validation database 108 upon ‘approval’ or may not update the validation database 108 upon ‘refusal’. Further, the template validation module 218 may also use the inputs received from the service operator to train one or more AI/ML models of the STVS 102. [0088] In some embodiments, upon determining the failed validation, the template validation module 218 may determine one or more modifications that may be performed on the SMS template data to increase a probability of automatically approving the SMS template data. Further, the template validation module 218 may transmit one or more notifications, including the one or more modifications, to entity device 104. A user associated with the entity 106 may review the one or more modifications and may modify the SMS template data as at least one modified SMS template data. The template validation module 218 may receive the at least one modified SMS template data from the entity device 104 and may validate the at least one modified SMS template data to register in the validation database 108.

[0089] Thus, the ST VS 102 enables faster and accurate validation of the SMS template data and automatically updates the validation database 108 upon successful validation of the SMS template data by avoiding manual waiting time periods. The ST VS 102 improves accuracy of validation by taking into account various significant factors such as historical registration data of the entity 106, relevance of entity keywords with the list of pre-registered entity keywords and the like. Securing decision of each module and the corresponding reasons in the reason array may provide valuable insights to audit the results at a later stage. Furthermore, the STVS 102 may retrieve few compliance rules, such as relevant regulatory guidelines or sub-tasks, for known types of SMS templates from the reason array without performing similar steps again for each SMS template, thereby reducing computing resources and slashing down time consumption in validating the similar types of SMS templates.

[0090] Further, as the STVS 102 is trained with datasets of multiple languages to detect the maliciousness, the STVS 102 may generate finer and precise validation results along with reasons to the entities 106. By recommending modifications to the SMS templates in case of failed validations, the STVS 102 may enable the entities 106 to escalate a chance of successful validation. The STVS 102 also optimizes processing resources by performing parallel execution of sub-tasks, such as to determine the regulatory compliance status 222.

[0091] Fig. 3 illustrates an exemplary flowchart of a method for validating the SMS template data in accordance with an embodiment of the present disclosure.

[0092] At block 302, the STVS 102 may receive the SMS template data associated with the entity 106 from the entity device 104.

[0093] At block 304, the STVS 102 may process the SMS template data to determine the plurality of template parameters 220 associated with the SMS template data.

[0094] At block 305, the STVS 102 may perform various operations simultaneously as indicated in the blocks 306 through 316. [0095] At sub-block 306, the STVS 102 may identify one or more relevant regulatory guidelines based on the plurality of template parameters 220.

[0096] At sub-block 308, the STVS 102 may determine the regulatory compliance status 222 of the SMS template data by correlating the SMS template data with the one or more relevant regulatory guidelines.

[0097] At sub-block 310, the STVS 102 may evaluate textual embeddings from the SMS template data and may compare the textual embeddings with a plurality of predefined malicious elements.

[0098] At sub-block 312, the STVS 102 may determine the maliciousness 224 of the SMS template data based on the comparison.

[0099] At sub-block 314, the STVS 102 may retrieve historical registration data of the entity 106.

[00100] At sub-block 316, the STVS 102 may determine the entity scores of the entity 106 based on the historical registration data.

[00101] At block 318, the STVS 102 may validate the SMS template data based on the plurality of template parameters, the regulatory compliance status, the maliciousness and the entity scores.

[00102] At block 320, the STVS 102 may verify if the validation is successful and proceed to block 322 if the validation is successful or may proceed to blocks 322 and/or 326 if the validation is ‘failed’.

[00103] At block 322, the STVS 102 may update the validation database 108 with the SMS template data.

[00104] At block 324, the STVS 102 may send the SMS template data to a service operator for manual verification.

[00105] At block 326, the STVS 102 may update the validation database upon approval by the service operator or may not update the validation database upon refusal by the service operator. [00106] At block 328, the STVS 102 may transmit one or more notifications including one or more modifications that may be used to modify the SMS template data to increase the probability of successful validation of the SMS template data.

[00107] At block 330, the STVS 102 may receive at least one modified SMS template and/or header from the entity 106 based on the one or more notifications. The STVS 102 may further proceed to the block 302 to validate the at least one modified SMS template and/or header.

[00108] Fig. 4 illustrates an exemplary flowchart of a method for validating the SMS template data in accordance with another embodiment of the present disclosure. [00109] At block 402, the ST VS 102 may receive the SMS template data associated with the entity 106 from the entity device 104.

[00110] At block 404, the STVS 102 may process the SMS template data to determine the plurality of template parameters 220 associated with the SMS template data.

[00111] At block 406, the STVS 102 may identify one or more relevant regulatory guidelines based on the plurality of template parameters 220.

[00112] At block 408, the STVS 102 may determine a regulatory compliance status 222 of the SMS template data by correlating the SMS template data with the one or more relevant regulatory guidelines.

[00113] At block 410, the STVS 102 may determine presence of at least one malicious element in the SMS template data.

[00114] At block 412, the STVS 102 may determine at least the entity compliance score based on historical registration data of the entity 106.

[00115] At block 414, the STVS 102 may validate the SMS template data based at least on the presence of at least one malicious element, the regulatory compliance status 222 and the entity compliance score.

[00116] At block 416, the STVS 102 may automatically update the validation database 108 with the SMS template data upon successfully validating the SMS template data.

[00117] Thus, the STVS 102 enables faster and accurate validation of the SMS template data and automatically updates the validation database 108 upon successful validation of the SMS template data by avoiding manual waiting time periods. The STVS 102 improves accuracy of validation by taking into account various significant factors such as historical registration data of the entity 106, relevance of entity keywords with the list of pre-registered entity keywords and the like. Securing decision of each module and the corresponding reasons in the reason array may provide valuable insights to audit the results at a later stage. Furthermore, the STVS 102 may retrieve few compliance rules, such as relevant regulatory guidelines or sub-tasks, for known types of SMS templates from the reason array without performing similar steps again for each SMS template, thereby reducing computing resources and slashing down time consumption in validating the similar types of SMS templates.

[00118] Further, as the STVS 102 is trained with datasets of multiple languages to detect the maliciousness, the STVS 102 may generate finer and precise validation results along with reasons to the entities 106. By recommending modifications to the SMS templates in case of failed validations, the STVS 102 may enable the entities 106 to escalate a chance of successful validation. The STVS 102 also optimizes processing resources by performing parallel execution of sub-tasks, such as to determine the regulatory compliance status 222.

[00119] The methods 300 and 400 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions, which perform specific functions or implement specific abstract data types. The order in which the methods 300 and 400 is described is not intended to be construed as a limitation, and any number of the method blocks described can be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods without departing from the scope of the subject matter described herein. Furthermore, the methods 300 and 400 can be implemented in any suitable hardware, software, firmware, or combination thereof.

[00120] Fig. 5 illustrates a block diagram of an exemplary computer system for implementing embodiments consistent with the present disclosure.

[00121] In an embodiment, the computer system 500 may be the STVS 102 for validating the SMS template data. The computer system 500 may include a central processing unit (“CPU” or “processor”) 508. The processor 508 may comprise at least one data processor for executing program components for executing user or system-generated business processes. The processor 508 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, etc.

[00122] The processor 508 may be disposed in communication with one or more input/output (VO) devices 502 and 504 via I/O interface 506. The I/O interface 506 may employ communication protocols/methods such as, without limitation, audio, analog, digital, stereo, IEEE-1594, serial bus, Universal Serial Bus (USB), infrared, PS/2, BNC, coaxial, component, composite, Digital Visual Interface (DVI), high-definition multimedia interface (HDMI), Radio Frequency (RF) antennas, S-Video, Video Graphics Array (VGA), IEEE 802. n /b/g/n/x, Bluetooth, cellular (e.g., Code-Division Multiple Access (CDMA), High-Speed Packet Access (HSPA+), Global System For Mobile Communications (GSM), Long-Term Evolution (LTE) or the like), etc.

[00123] Using the EO interface 506, the computer system 500 may communicate with one or more EO devices 502 and 504. In some implementations, the processor 508 may be disposed in communication with a communication network 509 via a network interface 510. The network interface 510 may employ connection protocols including, without limitation, direct connect, Ethernet (e.g., twisted pair 10/100/1000 Base T), Transmission Control Protocol/Internet Protocol (TCP/IP), token ring, IEEE 802.1 la/b/g/n/x, etc. Using the network interface 510 and the communication network 509, the computer system 500 may be connected to the validation database 108, the regulatory guidelines database 110, the entity device 104 and the servers, including the telecom server 112 and the regulatory server 114 .

[00124] The communication network 509 can be implemented as one of several types of networks, such as intranet or any such wireless network interfaces. The communication network 509 may either be a dedicated network or a shared network, which represents an association of several types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), Wireless Application Protocol (WAP), etc., to communicate with each other. Further, the communication network 509 may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, etc. In some embodiments, the communication network 509 may be one or more of a V2V network, a V2C network and the like.

[00125] In some embodiments, the processor 508 may be disposed in communication with a memory 530 e.g., RAM 514, and ROM 516, etc. as shown in Fig. 4, via a storage interface 512. The storage interface 512 may connect to memory 530 including, without limitation, memory drives, removable disc drives, etc., employing connection protocols such as Serial Advanced Technology Attachment (SATA), Integrated Drive Electronics (IDE), IEEE-1594, 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, solid-state drives, etc.

[00126] The memory 530 may store a collection of program or database components, including, without limitation, user/application 518, an operating system 528, a web browser 524, a mail client 520, a mail server 522, a user interface 526, and the like. In some embodiments, computer system 500 may store user/application data 518, such as the data, variables, records, etc. as described in this invention. Such databases may be implemented as fault-tolerant, relational, scalable, secure databases such as Oracle or Sybase.

[00127] The operating system 528 may facilitate resource management and operation of the computer system 500. Examples of operating systems include, without limitation, Apple Macintosh TM OS X TM, UNIX TM, Unix-like system distributions (e.g., Berkeley Software Distribution (BSD), FreeBSD TM, Net BSD TM, Open BSD TM, etc.), Linux distributions (e.g., Red Hat TM, Ubuntu TM, K-Ubuntu TM, etc.), International Business Machines (IBM TM) OS/2 TM, Microsoft Windows TM (XP TM, Vista/7/8, etc.), Apple iOS TM, Google Android TM, Blackberry TM Operating System (OS), or the like. A user interface may facilitate 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 500, such as cursors, icons, checkboxes, menus, windows, widgets, etc. Graphical User Interfaces (GUIs) may be employed, including, without limitation, Apple TM Macintosh TM operating systems’ Aqua TM, IBM TM OS/2 TM, Microsoft TM Windows TM (e.g., Aero, Metro, etc.), Unix X-Windows TM, web interface libraries (e.g., ActiveX, Java, JavaScript, AJAX, HTML, Adobe Flash, etc.), or the like.

[00128] The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope of the disclosed embodiments. Also, the words "comprising," "having," "containing," and "including," and other similar forms 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 as used herein and in the appended claims, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise.

[00129] Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, the disclosure of the embodiments of the disclosure is intended to be illustrative, but not limiting, of the scope of the disclosure.

[00130] With respect to the use of substantially any plural and/or singular terms herein, those having skill in the art can translate from the plural to the singular and/or from the singular to the plural as is appropriate to the context and/or application. The various singular/plural permutations may be expressly set forth herein for sake of clarity.

Claims

We claim:

1. A method of validating Short Message Services (SMS) template data, the method comprising: receiving, via a communication network, the SMS template data associated with an entity; processing the SMS template data to determine a plurality of template parameters associated with the SMS template data using a set of feature extraction models; identifying one or more relevant regulatory guidelines based on the plurality of template parameters; determining a regulatory compliance status of the SMS template data by correlating the SMS template data with the one or more relevant regulatory guidelines using an agentic Artificial Intelligence (Al) model; determining presence of at least one malicious element in the SMS template data; determining at least an entity compliance score based on historical registration data of the entity; validating the SMS template data based at least on the regulatory compliance status, the presence of the at least one malicious element in the SMS template data and the entity compliance score using machine learning based decision tree; and automatically updating a validation database with the SMS template data upon successfully validating the SMS template data.

2. The method of claim 1, wherein the SMS template data includes one or more of an SMS template and a header, wherein the plurality of template parameters comprise at least one of a type of the template, a template usage scenario, presence of an entity keyword within one or more of the SMS template and the header, the entity keyword, an entity identifier associated with the entity keyword, a relevance score of the entity keyword compared with a list of pre-registered entity keywords of the entity, presence of consecutive variables within the SMS template, one or more formats of one or more variables within the SMS template, or a validation of the one or more formats.

3. The method of claim 1, wherein processing the SMS template data to determine the plurality of template parameters using the set of feature extraction models comprises: generating a plurality of numerical embeddings of the SMS template data by processing the SMS template data using a pre-trained language processing model; analyzing the plurality of numerical embeddings using the set of feature extraction models, wherein each feature extraction model comprises one or more decision trees and a plurality of nodes and is trained using input training datasets comprising historical SMS template data and output training datasets comprising corresponding template parameters; and for each template parameter of the plurality of template parameters, assigning a value to the template parameter using each of the set of feature extraction models, wherein the value is one of a set of predefined values for the template parameter; computing a count of each value of the set of predefined values assigned to the template parameter by the set of feature extraction models; and determining a value with maximum count as the value of the template parameter.

4. The method of claim 1, wherein the one or more relevant regulatory guidelines includes one or more regulatory guidelines retrieved from a regulatory guidelines database, applicable to each of the plurality of template parameters and the SMS template data.

5. The method of claim 1, wherein determining the regulatory compliance status of the SMS template data by correlating the SMS template data with the one or more relevant regulatory guidelines comprises: dynamically dividing, by the agentic Al model, a regulatory compliance verification task into a plurality of sub-tasks; executing the plurality of sub-tasks using a plurality of compliance models, wherein the plurality of compliance models comprises: a web-search model configured to retrieve detailed entity information from a plurality of open resources and to determine one or more regulatory status indicators, a database fetching model trained to retrieve one or more relevant regulatory guidelines related to each sub-task from the plurality of open resources, a Retrieval Augmented Generation (RAG) model trained to generate a plurality of compliance rules based on the one or more relevant regulatory guidelines, verify the SMS template data complies with the plurality of compliance rules, and determine an output for each of the plurality of sub-tasks as either positive or negative based on the verification, and a database submission model trained to store the output of each sub-task; and combining the outputs of the plurality of sub-tasks and the one or more regulatory status indicators to determine the regulatory compliance status as one of: positive, when the output of each sub-task is positive and each of the one or more regulatory status indicators indicate positive status, and negative, when the output of at least one sub -task is negative or at least one of the one or more regulatory status indicators indicates negative status, wherein the determination comprises storing the one or more relevant regulatory guidelines, generated plurality of compliance rules, and the output of each sub-task in a reason array.

6. The method of claim 1, wherein determining at least the entity compliance score based on the historical registration data comprises: retrieving the historical registration data of the entity from the validation database; determining a plurality of entity parameters by processing the historical registration data, wherein the plurality of entity parameters comprise a registration rate of SMS templates, a ratio of count of blacklisted SMS templates of the entity to a count of a plurality of historical SMS templates, a rate of SMS transmissions, and a count of complaints received; determining correlation data corresponding to the plurality of entity parameters by corelating the plurality of entity parameters with corresponding entity parameters of one or more other entities; computing an initial entity quality score based on at least one of: the registration rate of SMS templates, the rate of message transmissions, the count of complaints received, or the correlation data; computing an initial entity compliance score based on at least one of the count of complaints received, or the ratio of the count of blacklisted templates of the entity to the count of the plurality of historical SMS templates; comparing the plurality of entity parameters and the correlation data with corresponding predefined thresholds; and determining the entity compliance score and an entity quality score by dynamically updating the initial entity quality score and the initial entity compliance score based on the comparison, wherein the entity quality score indicates an SMS transmission behavior of the entity and the entity compliance score indicates historical regulatory compliance of the entity.

7. The method of claim 1, wherein processing the SMS template data to determine the presence of at least one malicious element in the SMS template data comprises: analyzing the SMS template data using one or more language models to generate one or more textual embeddings from the SMS template data, wherein the one or more language models comprises Bidirectional Encoder Representations from Transformers (BERT) and Language- Agnostic BERT Sentence Embeddings (LaBSE); and determining presence of at least one malicious element within the SMS template data by comparing the one or more textual embeddings with that of a plurality of predefined malicious elements, wherein the determining further comprising: classifying maliciousness of the SMS template data as one of: malicious template data, when the SMS template data comprises at least one malicious element; and non-malicious template data, when the SMS template data does not comprise any malicious element.

8. The method of claim 1, wherein validating the SMS template data comprises: analysing the plurality of template parameters, the regulatory compliance, maliciousness of the SMS template data, an entity quality score, and the entity compliance score using the machine learning based decision tree; determining, based on the analysis, whether the SMS template data satisfies a plurality of validation criteria, wherein the plurality of validation criteria comprises each of the plurality of template parameters, the entity quality score, and the entity compliance score satisfy corresponding predefined thresholds, the maliciousness of the SMS template data is non-malicious template data, and the regulatory compliance status is ‘positive’; successfully validating the SMS template data upon determining that the SMS template data satisfies the plurality of validation criteria; and determining that the validation of the SMS template data is failed upon determining that the SMS template data fails to satisfy at least one of the plurality of validation criteria.

9. The method of claim 8, further comprising: upon determination of failed validation of the SMS template data, determining one or more modifications to the SMS template data to approve the SMS template data; transmitting one or more notifications to a device of the entity, wherein the one or more notifications include the one or more modifications; receiving at least one modified SMS template data from the entity based on the one or more notifications; and validating the at least one modified SMS template data to register in the validation database.

10. The method of claim 8, further comprising: upon determination of failed validation of the SMS template data, transmitting the SMS template data to a service operator; receiving an input from the service operator indicating one of an approval of the SMS template data or a refusal of the SMS template data; updating the validation database with the SMS template data when the input indicates the approval; and not updating the validation database when the input indicates the refusal.

11. A system to validate Short Message Services (SMS) template data, the system comprising: a memory; and a processor coupled with the memory, wherein the processor is configured to: receive, via a communication network, the SMS template data associated with an entity; process the SMS template data to determine a plurality of template parameters associated with the SMS template data using a set of feature extraction models; identify one or more relevant regulatory guidelines based on the plurality of template parameters; determine a regulatory compliance status of the SMS template data by correlating the SMS template data with the one or more relevant regulatory guidelines using an agentic Al model; determine presence of at least one malicious element in the SMS template data; determine at least an entity compliance score based on historical registration data of the entity; validate the SMS template data based at least on the regulatory compliance status, the presence of the at least one malicious element in the SMS template data and the entity compliance score using machine learning based decision tree; and automatically update the validation database with the SMS template data upon successfully validating the SMS template data.

12. The system of claim 11, wherein the SMS template data includes one or more of an SMS template and a header, wherein the plurality of template parameters comprise at least one of a type of the template, a template usage scenario, presence of an entity keyword within one or more of the SMS template and the header, the entity keyword, an entity identifier associated with the entity keyword, a relevance score of the entity keyword compared with a list of pre-registered entity keywords of the entity, presence of consecutive variables within the SMS template, one or more formats of one or more variables within the SMS template, or a validation of the one or more formats.

13. The system of claim 11, wherein to process the SMS template data to determine the plurality of template parameters using the set of feature extraction models, the processor is configured to: generate a plurality of numerical embeddings of the SMS template data by processing the SMS template data using a language processing model; analyze the plurality of numerical embeddings using a set of feature extraction models, wherein each feature extraction model comprises one or more decision trees and a plurality of nodes and is trained using input training datasets comprising historical SMS template data and output training datasets comprising corresponding template parameters; for each template parameter of the plurality of template parameters: assign a value to the template parameter using each of the set of feature extraction models, wherein the value is one of a set of predefined values for the template parameter; compute a count of each value of the set of predefined values assigned to the template parameter by the set of feature extraction models; and determine a value with maximum count as the value of the template parameter.

14. The system of claim 11, wherein the one or more relevant regulatory guidelines includes one or more regulatory guidelines, retrieved from a regulatory guidelines database, applicable to each of the plurality of template parameters and the SMS template data.

15. The system of claim 11, wherein to determine the regulatory compliance status of the SMS template data by correlating the SMS template data with the one or more relevant regulatory guidelines, the processor is configured to: dynamically divide, by the agentic Al model, a regulatory compliance verification task into a plurality of sub-tasks; execute the plurality of sub-tasks using a plurality of compliance models, wherein the plurality of compliance models comprises: a web-search model configured to retrieve detailed entity information from a plurality of open resources and to determine one or more regulatory status indicators, a database fetching model trained to retrieve one or more relevant regulatory guidelines related to each sub-task from the plurality of open resources, a Retrieval Augmented Generation (RAG) model trained to generate a plurality of compliance rules based on the one or more relevant regulatory guidelines, verify the SMS template data complies with the plurality of compliance rules, and determine an output for each of the plurality of sub-tasks as either positive or negative based on the verification, and a database submission model trained to store the output of each sub-task; and combine the outputs of the plurality of sub-tasks and the one or more regulatory status indicators to determine the regulatory compliance status as one of: positive, when the output of each sub-task is positive and each of the one or more regulatory status indicators indicate positive status, and negative, when the output of at least one sub -task is negative or at least one of the one or more regulatory status indicators indicates negative status, wherein to determine the regulatory compliance status, the processor is configured to store the one or more relevant regulatory guidelines, generated plurality of compliance rules, and the output of each sub-task in a reason array.

16. The system of claim 11, wherein to determine at least the user compliance score based on the historical registration data, the processor is configured to: retrieve the historical registration data of the entity from the validation database; determine a plurality of entity parameters by processing the historical registration data, wherein the plurality of entity parameters comprise a registration rate of SMS templates, a ratio of count of blacklisted SMS templates of the entity to a count of a plurality of historical SMS templates, a rate of SMS transmissions, and a count of complaints received; determine correlation data corresponding to the plurality of entity parameters by corelating the plurality of entity parameters with corresponding entity parameters of one or more other entities; compute an initial entity quality score based on at least one of: the registration rate of SMS templates, the rate of message transmissions, the count of complaints received, or the correlation data; compute an initial entity compliance score based on at least one of: the count of complaints received, or the ratio of the count of blacklisted templates of the entity to the count of the plurality of historical SMS templates; compare the plurality of entity parameters and the correlation data with corresponding predefined thresholds; and determine the entity compliance score and an entity quality score by dynamically updating the initial entity quality score and the initial entity compliance score based on the comparison, wherein the entity quality score indicates an SMS transmission behavior of the entity and the entity compliance score indicates historical regulatory compliance of the entity.

17. The system of claim 11, wherein to process the SMS template data to determine the presence of at least one malicious element in the SMS template data, the processor is configured to: analyze the SMS template data using one or more language models to generate one or more textual embeddings from the SMS template data, wherein the one or more language models comprises Bidirectional Encoder Representations from Transformers (BERT) and Language- Agnostic BERT Sentence Embeddings (LaBSE); and determine presence of at least one malicious element within the SMS template data by comparing the one or more textual embeddings with that of a plurality of predefined malicious elements, wherein upon determining the presence of at least one malicious element, the processor is further configured to: classify maliciousness of the SMS template data as one of: malicious template data, when the SMS template data comprises at least one malicious element; and non-malicious template data, when the SMS template data does not comprise any malicious element.

18. The system of claim 11, wherein to validate the SMS template data, the processor is configured to: analyse the plurality of template parameters, the regulatory compliance, maliciousness of the SMS template data, an entity quality score, and the entity compliance score using the machine learning based decision tree; determine, based on the analysis, whether the SMS template data satisfies a plurality of validation criteria, wherein the plurality of validation criteria comprises: each of the plurality of template parameters, the quality score, and the compliance score satisfy corresponding predefined thresholds, the maliciousness of the SMS template data is non-malicious template data, and the regulatory compliance status is ‘positive’; successfully validate the SMS template data upon determining that the SMS template data satisfies the plurality of validation criteria; and determine that the validation of the SMS template data is failed upon determining that the SMS template data fails to satisfy at least one of the plurality of validation criteria.

19. The system of claim 18, wherein the processor is further configured to: upon failed validation of the SMS template, determine one or more modifications to the SMS template data to approve the SMS template data; transmit one or more notifications to a device of the entity, wherein the one or more notifications include the one or more modifications; receive at least one modified SMS template data from the entity based on the one or more notifications; and validate the at least one modified SMS template data to register in the validation database.

20. The system of claim 18, wherein the processor is further configured to: upon failed validation of the SMS template, transmit the SMS template data to a service operator; receive an input from the service operator indicating one of an approval of the SMS template data or a refusal of the SMS template data; update the validation database with the SMS template data when the input indicates the approval; and not update the validation database when the input indicates the refusal.

21. A non-transitory computer-readable medium having program instructions stored thereon, when executed by a Short Message Service (SMS) template validation system, facilitate the SMS template validation system for validating SMS template data by performing operations comprising: receiving, via a communication network, the SMS template data associated with an entity; processing the SMS template data to determine a plurality of template parameters associated with the SMS template data using a set of feature extraction models; identifying one or more relevant regulatory guidelines based on the plurality of template parameters; determining a regulatory compliance status of the SMS template data by correlating the SMS template data with the one or more relevant regulatory guidelines using an agentic Al model; determining presence of at least one malicious element in the SMS template data; determining at least an entity compliance score based on historical registration data of the entity; validating the SMS template data based at least on the regulatory compliance status, the presence of the at least one malicious element in the SMS template data and the entity compliance score using machine learning based decision tree; and automatically updating a validation database with the SMS template data upon successfully validating the SMS template data.

22. The non-transitory computer-readable medium of claim 21, wherein the SMS template data includes one or more of an SMS template and a header, wherein the plurality of template parameters comprise at least one of a type of the template, a template usage scenario, presence of an entity keyword within one or more of the SMS template and the header, the entity keyword, an entity identifier associated with the entity keyword, a relevance score of the entity keyword compared with a list of pre-registered entity keywords of the entity, presence of consecutive variables within the SMS template, one or more formats of one or more variables within the SMS template, or a validation of the one or more formats.

23. The non-transitory computer-readable medium of claim 21, wherein the program instructions configured to process the SMS template data to determine the plurality of parameters using the set of feature extraction models facilitate: generating a plurality of numerical embeddings of the SMS template data by processing the SMS template data using a language processing model; analyzing the plurality of numerical embeddings using a set of feature extraction models, wherein each feature extraction model comprises one or more decision trees and a plurality of nodes and is trained using input training datasets comprising historical SMS template data and output training datasets comprising corresponding template parameters; for each template parameter of the plurality of template parameters, assigning a value to the template parameter using each of the set of feature extraction models, wherein the value is one of a set of predefined values for the template parameter; computing a count of each value of the set of predefined values assigned to the template parameter by the set of feature extraction models; and determining a value with maximum count as the value of the template parameter.

24. The non-transitory computer-readable medium of claim 21, wherein the one or more relevant regulatory guidelines include one or more regulatory guidelines, retrieved from a regulatory guidelines database, applicable to each of the plurality of template parameters and the SMS template data.

25. The non-transitory computer-readable medium of claim 21, wherein the program instructions configured to determine the regulatory compliance status of the SMS template data by correlating the SMS template data with the one or more relevant regulatory guidelines facilitate: dynamically dividing, by the agentic Al model, a regulatory compliance verification task into a plurality of sub-tasks; executing the plurality of sub-tasks using a plurality of compliance models, wherein the plurality of compliance models comprises: a web-search model configured to retrieve detailed entity information from a plurality of open resources and to determine one or more regulatory status indicators, a database fetching model trained to retrieve one or more relevant regulatory guidelines related to each sub-task from the plurality of open resources, a Retrieval Augmented Generation (RAG) model trained to generate a plurality of compliance rules based on the one or more relevant regulatory guidelines, verify the SMS template data complies with the plurality of compliance rules, and determine an output for each of the plurality of sub-tasks as either positive or negative based on the verification, and a database submission model trained to store the output of each sub-task; and combining the outputs of the plurality of sub-tasks and the one or more regulatory status indicators to determine the regulatory compliance status as one of: positive, when the output of each sub-task is positive and each of the one or more regulatory status indicators indicate positive status, and negative, when the output of at least one sub -task is negative or at least one of the one or more regulatory status indicators indicates negative status, wherein the program instructions configured to determine the regulatory compliance comprises storing the one or more relevant regulatory guidelines, generated plurality of compliance rules, and the output of each sub-task in a reason array.

26. The non-transitory computer-readable medium of claim 21, wherein the program instructions configured to determine at least the entity compliance score based on the historical registration data facilitate: retrieving the historical registration data of the entity from the validation database; determining a plurality of entity parameters by processing the historical registration data, wherein the plurality of entity parameters comprise a registration rate of SMS templates, a ratio of count of blacklisted SMS templates of the entity to a count of a plurality of historical SMS templates, a rate of SMS transmissions, and a count of complaints received; determining correlation data corresponding to the plurality of entity parameters by corelating the plurality of entity parameters with corresponding entity parameters of one or more other entities; computing an initial entity quality score based on at least one of: the registration rate of SMS templates, the rate of message transmissions, the count of complaints received, or the correlation data; computing an initial entity compliance score based on at least one of the count of complaints received, or the ratio of the count of blacklisted templates of the entity to the count of the plurality of historical SMS templates; comparing the plurality of entity parameters and the correlation data with corresponding predefined thresholds; and determining the entity compliance score and an entity quality score by dynamically updating the initial entity quality score and the initial entity compliance score based on the comparison, wherein the entity quality score indicates an SMS transmission behavior of the entity and the entity compliance score indicates historical regulatory compliance of the entity.

27. The non-transitory computer-readable medium of claim 21, wherein the program instructions configured to process the SMS template data to determine the presence of at least one malicious element in the SMS template data facilitate: analyzing the SMS template data using one or more language models to generate one or more textual embeddings from the SMS template data, wherein the one or more language models comprises Bidirectional Encoder Representations from Transformers (BERT) and Language- Agnostic BERT Sentence Embeddings (LaBSE); and determining presence of at least one malicious elements within the SMS template data by comparing the one or more textual embeddings with that of a plurality of predefined malicious elements, wherein the determining further comprises: classifying maliciousness of the SMS template data as one of: malicious template data, when the SMS template data comprises at least one malicious element; and non-malicious template data, when the SMS template data does not comprise any malicious element.

28. The non-transitory computer-readable medium of claim 21, wherein the program instructions configured to validate the SMS template data facilitate: analysing the plurality of template parameters, the regulatory compliance, maliciousness of the SMS template data, an entity quality score, and the entity compliance score using the machine learning based decision tree; determining, based on the analysis, whether the SMS template data satisfies a plurality of validation criteria, wherein the plurality of validation criteria comprises: each of the plurality of template parameters, the entity quality score, and the entity compliance score satisfy corresponding predefined thresholds, the maliciousness of the SMS template data is non-malicious template data, and the regulatory compliance status is ‘positive’; successfully validating the SMS template data upon determining that the SMS template data satisfies the plurality of validation criteria; and determining that the validation of the SMS template data is failed upon determining that the SMS template data fails to satisfy at least one of the plurality of validation criteria.

29. The non-transitory computer-readable medium of claim 28, wherein, the program instructions configured to further facilitate: upon failed validation of the SMS template, determining one or more modifications to the SMS template data to approve the SMS template data; transmitting one or more notifications to a device of the entity, wherein the one or more notifications include the one or more modifications; receiving at least one modified SMS template data from the entity based on the one or more notifications; and validating the at least one modified SMS template data to register in the validation database.

30. The non-transitory computer-readable medium of claim 28, wherein, the program instructions configured to further facilitate: upon failed validation of the SMS template, transmitting the SMS template data to a service operator, receiving an input from the service operator indicating one of an approval of the SMS template data or a refusal of the SMS template data; updating the validation database with the SMS template data when the input indicates the approval; and not updating the validation database when the input indicates the refusal.