Abstract: The disclosure relates to a method and system of generating training data for fine-tuning of a Machine Learning (ML) model. The method includes generating one or more natural language interpretations of a dataset corresponding to one or more parameters associated with configuration of the dataset, and collating the one or more natural language interpretations of the dataset corresponding to one or more parameters, to generate a combined natural language interpretation of the dataset. The method further include generating a conceptual explanation of the dataset, based on the combined natural language interpretation of the dataset, and assigning one or more labels to each sub-dataset of the dataset, based on the conceptual explanation of the dataset, to generate training data for fine-tuning of the ML model, wherein the dataset comprises a plurality of sub-datasets.

Abstract: This disclosure relates to system and method for preserving privacy of telematic data. The method includes receiving telematic data from a vehicle and a set of predefined policies from an insurance provider. The telematic data and the set of predefined policies are homomorphically encrypted through a multi-key homomorphic encryption technique. The method further includes analyzing the telematic data and the set of predefined policies to obtain an analysis result. The method further includes sharing the analysis result with the vehicle in an encrypted format. The method further includes partially decrypting the analysis result to obtain a partially decrypted result. The method further includes sharing the partially decrypted result to the insurance provider. The method further includes decrypting the partially decrypted result to obtain fully decrypted result in a plain-text format.

Abstract: The disclosure relates to method and system for securing delivery of a package. The method may include receiving, from a token generating server, a security token corresponding to security data associated with the delivery of the package. The token generating server may be configured to generate the security token corresponding to the security data upon receiving the security data from a sender device. A security code representative of the security token may be attached to the package. The method may further include capturing the security code from the package at the time of delivery of the package to a receiver, correlating the security code with the security token, to identify a match between the security code and the security token, and upon successful matching of the security code with the security token, allowing access of the package to the receiver.

Abstract: A method and system for recording, organizing, and tracing events is disclosed. In some embodiments, the method includes obtaining real-time video data captured using a video capturing equipment. The real-time video data comprises a plurality of sequential image frames and audio data associated with each of a plurality of events. The method further includes extracting first timestamp data and first text data from each of the plurality of sequential image frames, extracting second timestamp data and second text data from the audio data, generating text data associated with each of the plurality of events based on the first timestamp data, the first text data, the second timestamp data, and the second text data, storing the generated text data for subsequent audit, and discarding the real-time video data associated with each of the plurality of events.

Abstract: The invention relates to method and system for enhancing computer network security. The method includes receiving a plurality of requests from client devices to avail a plurality of responses from services running on servers; determining a URL pattern for each of the plurality of requests based on URL associated with that request; determining a request data signature for each of the plurality of requests or a response data signature for each of the plurality of responses based on a set of request parameters associated with that request or based on a set of response parameters associated with that response, respectively, using a first machine learning model; and determining an authenticity of each of the plurality of requests based on the URL pattern and the data signature associated with that request, or an authenticity of each of the plurality of responses based on the data signature associated with that response.

Abstract: The invention relates to method and system for identifying a current location of a user in a closed premises. The method includes capturing user information associated with the user and object information associated with one or more static objects in proximity to the user, when the user and the one or more static objects are within a Field of View (FOV) of at least one camera; comparing the user information with historical user information corresponding a plurality of users visited the closed premises, and the object information with historical object information corresponding to a plurality of static objects within the closed premises; and identifying the current location of the user within the closed premises based on the comparing.

Abstract: A method and system of providing assistance during an operation performed on an equipment by a smart assistance device. A first set of image frames and a second set of image frames corresponding to forward steps and reverse steps respectively performed during the operation are received from an imaging device. Parts of the equipment are detected in each of first set of image frames and tagged. The smart assistance device detects parts of the equipment present in an image frame for each of the second set of the image frames. A discrepancy is determined in the reverse steps by comparing the parts of the equipment present in the frame of the second set of the image frames with the parts tagged in the corresponding first image frame of the first set of image frames. A notification and recommendation is provided to correct the discrepancy.

Abstract: This disclosure relates to a privacy preserving geofencing system and method thereof. The method includes receiving a current location data of a vehicle. The current location data may homomorphically encrypted through a homomorphic encryption technique. The method further includes randomly generating at least two secure values corresponding to the current location data of the vehicle. The method further includes combining the at least two secure values with the current location data of the vehicle. The method further includes sharing a combination of the current location data and the at least two secure values to a computing server. The method further includes computing the current location data of the vehicle obfuscated with the at least two secure values to obtain a computed result. The computed result may determine if the vehicle is within a predefined geofencing region based on one or more geofencing criteria.

Abstract: The disclosure relates to method and system for securing delivery of a package. The method may include receiving, from a token generating server, a security token corresponding to security data associated with the delivery of the package. The token generating server may be configured to generate the security token corresponding to the security data upon receiving the security data from a sender device. A security code representative of the security token may be attached to the package. The method may further include capturing the security code from the package at the time of delivery of the package to a receiver, correlating the security code with the security token, to identify a match between the security code and the security token, and upon successful matching of the security code with the security token, allowing access of the package to the receiver.

Abstract: A method and system dynamically predicting driving range of vehicles is disclosed. In some embodiments, the method includes dynamically determining real-time values corresponding to in-transit parameters associated with vehicle; and determining, via trained Machine Learning (ML) model, variance in in-transit parameters when compared with pre-defined parameters. Determining the variance includes identifying overlapping subset of parameters between in-transit parameters and pre-defined parameters; identifying non-overlapping subset of parameters between in-transit parameters and pre-defined parameters; determining difference in each of the real-time values determined for overlapping subset of parameters with corresponding optimal value; and computing variance based on non-overlapping subset of parameters and difference in real-time values determined for the overlapping subset of parameters.

Abstract: This disclosure relates to method and system for identifying Personally Identifiable Information (PII) through secret patterns. The method includes receiving user data from at least one data source through a plurality of communication channels. The user data includes PII and non-PII. The user data is associated with a user. The PII includes a plurality of personal identifiers. The method further includes identifying the PII in user data through a predictive model. The method further includes generating a secret pattern based on the PII identified through the predictive model. The secret pattern is an identifiable label. The method further includes adding the secret pattern to each of the plurality of personal identifiers in PII. The method further includes identifying each of the plurality of personal identifiers through the secret pattern in real-time, when user data is transmitted from the at least one data source to at least one data destination.

Abstract: A method and system of providing assistance during an operation performed on an equipment by a smart assistance device. A first set of image frames and a second set of image frames corresponding to forward steps and reverse steps respectively performed during the operation are received from an imaging device. Parts of the equipment are detected in each of first set of image frames and tagged. The smart assistance device detects parts of the equipment present in an image frame for each of the second set of the image frames. A discrepancy is determined in the reverse steps by comparing the parts of the equipment present in the frame of the second set of the image frames with the parts tagged in the corresponding first image frame of the first set of image frames. A notification and recommendation is provided to correct the discrepancy.

Abstract: The present disclosure relates to a system and method for controlling data interception in a communication network. One or more requests from a user for accessing one or more microservices are received through an Application Programming Interface (API). Information associated with one or more requests is the detected and requests are classified as secured microservice request and non-secured microservice request. The information is detected through predefined rules. Authentication token is then issued for secured microservice based on the detecting. The authentication token stores information detected by the detector in a geo storage system. The one or more requests are then routed according to the authentication token towards one or more corresponding microservices of the one or more microservices.

Abstract: A method and system for recording, organizing, and tracing events is disclosed. In some embodiments, the method includes obtaining real-time video data captured using a video capturing equipment. The real-time video data comprises a plurality of sequential image frames and audio data associated with each of a plurality of events. The method further includes extracting first timestamp data and first text data from each of the plurality of sequential image frames, extracting second timestamp data and second text data from the audio data, generating text data associated with each of the plurality of events based on the first timestamp data, the first text data, the second timestamp data, and the second text data, storing the generated text data for subsequent audit, and discarding the real-time video data associated with each of the plurality of events.

Abstract: The invention relates to method and system for enhancing computer network security. The method includes receiving a plurality of requests from client devices to avail a plurality of responses from services running on servers; determining a URL pattern for each of the plurality of requests based on URL associated with that request; determining a request data signature for each of the plurality of requests or a response data signature for each of the plurality of responses based on a set of request parameters associated with that request or based on a set of response parameters associated with that response, respectively, using a first machine learning model; and determining an authenticity of each of the plurality of requests based on the URL pattern and the data signature associated with that request, or an authenticity of each of the plurality of responses based on the data signature associated with that response.

Abstract: This disclosure relates to method and system for identifying Personally Identifiable Information (PII) through secret patterns. The method includes receiving user data from at least one data source through a plurality of communication channels. The user data includes PII and non-PII. The user data is associated with a user. The PII includes a plurality of personal identifiers. The method further includes identifying the PII in user data through a predictive model. The method further includes generating a secret pattern based on the PII identified through the predictive model. The secret pattern is an identifiable label. The method further includes adding the secret pattern to each of the plurality of personal identifiers in PII. The method further includes identifying each of the plurality of personal identifiers through the secret pattern in real-time, when user data is transmitted from the at least one data source to at least one data destination.

Abstract: Disclosed is a system for allowing secure access to a microservice. An Application Programming Interface (API) gateway receives a request comprising a Uniform Resource Locator (URL) associated to the microservice. A set of input parameters indicating information about the user device and the microservice is identified from the URL. The system performs validation of input parameters, extraction of request patterns, tracking of IP address, and detection of user credentials to provide output parameters. A decision tree comprising rules is generated by using a supervised machine learning technique on the output parameters. Further, the API gateway creates a stateless identity token to encrypt the request. The stateless identity token is created based on the user credentials and at least one rule applicable to the request. Once the stateless identity token is created, the stateless identity token is verified to allow the secure access to the microservice.

Abstract: The present disclosure relates to a system and method for controlling data interception in a communication network. One or more requests from a user for accessing one or more microservices are received through an Application Programming Interface (API). Information associated with one or more requests is the detected and requests are classified as secured microservice request and non-secured microservice request. The information is detected through predefined rules. Authentication token is then issued for secured microservice based on the detecting. The authentication token stores information detected by the detector in a geo storage system. The one or more requests are then routed according to the authentication token towards one or more corresponding microservices of the one or more microservices.

Abstract: Disclosed is a system for delegating access of sensitive information by a user device to a requestor device through a central server. A receiving module receives a first token Identification (ID) generated by the user device in an offline mode and a request, comprising a second token ID, from the requestor device. A validation module validates the request by comparing the first token ID and the second token ID. An identification module identifies a subset of the sensitive information based on a profile of the requestor, when the first token ID is matched with the second token ID. A watermarking module watermarks the subset of the sensitive information with a set of variables to generate watermarked sensitive information. Upon generating the watermarked sensitive information, the access delegation module delegates the access of the watermarked sensitive information to the requestor device.

Abstract: Disclosed is a system for allowing secure access to a microservice. An Application Programming Interface (API) gateway receives a request comprising a Uniform Resource Locator (URL) associated to the microservice. A set of input parameters indicating information about the user device and the microservice is identified from the URL. The system performs validation of input parameters, extraction of request patterns, tracking of IP address, and detection of user credentials to provide output parameters. A decision tree comprising rules is generated by using a supervised machine learning technique on the output parameters. Further, the API gateway creates a stateless identity token to encrypt the request. The stateless identity token is created based on the user credentials and at least one rule applicable to the request. Once the stateless identity token is created, the stateless identity token is verified to allow the secure access to the microservice.