Abstract: The present disclosure describes method and apparatus for counting items in a storehouse. The method includes selecting one or more images from the plurality of images and pre-processing the selected images. The method includes processing the pre-processed images using a boundary detection model for determining bounding boxes of visible items present in the pre-processed images while removing partially visible items, side surfaces, and items of neighboring pallets present in the pre-processed images. The method further includes determining 3D coordinates of each bounding box and estimating height-depth levels of each visible item using the 3D coordinates to generate a 2D stacking pattern of each item layer. The method includes determining the item count by correlating the 2D stacking pattern of each layer with predefined stacking patterns.

Abstract: A method and a system for providing AI-assisted navigation assistance to a user within a region of interest (ROI) is disclosed. A processor receives one or more navigation queries from a user device. A first set of locations within the ROI is determined by querying a retrieval augmented generation (RAG) model based on query embeddings of the one or more navigation queries, global spatial embeddings relevant to the query embeddings, and first metadata associated to the global spatial embeddings. Further, the processor by employing one or more predefined functions determines a second set of locations within the ROI. A set of navigation instructions is determined to reach the at least one desired location from the second set of locations.

Abstract: This disclosure relates to method and system of advanced summarization of documents using topic intelligence-based Retrieval Augmented Generation (RAG). The method may include receiving, through a GUI, a set of documents and summarization instructions for the set of documents. For each of the set of documents, the method may further include determining a set of topics in a document LSI and a hybrid ensemble of statistical techniques. For each of the set of topics, the method may further include identifying a set of relevant sentence chunks from the plurality of sentence chunks through the LSI based on the summarization instructions. For each of the set of topics, the method may further include generating, through an LLM, a topic summary based on the set of relevant sentence chunks using a RAG model, and generating an advanced summary of document based on topic summary of set of topics and general RAG-based summary.

Abstract: A method and a system for migrating a source code from a source programming language to a target programming language using a Large Language Model (LLM) is disclosed. A processor receives a set of user instructions comprising a number of iterations and a set of code migration instructions. A preliminary target code is determined in the target programming language based on prompting the LLM using one or more of a set of optimized prompts and the source code. An evaluation report is determined for the preliminary target code based on prompting the LLM using one from the set of optimized prompts, the set of code migration instructions and the preliminary target code of a current iteration. The preliminary target code of the current iteration is rendered as a target code on an output device.

Abstract: A method and system for maintaining service continuity of a roaming user across multiple networks is disclosed. The method includes receiving a request for handover of the roaming user from a source network to a target network. The method includes assessing a capability of the target network to accommodate the roaming user arriving from the source network. The method includes performing a Service Level Agreement (SLA) fulfilment negotiation by the target network with the source network. The method further includes configuring the target network to facilitate the handover of the roaming user from the source network to the target network. The method includes transferring the roaming user from the source network to the target network along with the plurality of services. The method includes monitoring efficacy of the service continuity for the transferred roaming user after movement of the roaming user from the source network to the target network.

Abstract: The method of contextualized skill extraction from electronic documents. The method includes receiving, via user interface, electronic document from user device. The method further includes generating plurality of words in the electronic document using pre-trained embedding model. The method further includes generating plurality of second embeddings from the plurality of first embeddings based on weighted averaging operation using first ANN layer. The method further includes generating plurality of contextualized embeddings from the plurality of second embeddings and the plurality of first embeddings using addition and normalization layer. The method further includes predicting named entity tag from set of named entity tags for each of the plurality of contextualized embeddings using fine-tuned second ANN layer. The method further includes extracting one or more skills from the electronic document based on the named entity tag corresponding to each of the plurality of contextualized layers.

Abstract: A system and method for providing functional safety in a software defined vehicle (SDV) is disclosed. The system includes a Central Controller (CC), a plurality of Zonal Controllers (ZCs) coupled with the CC, an Emergency Controller (EC) coupled to the CC and each of the plurality of ZCs. The CC or one of the plurality of ZCs is dynamically configurable as a shadow-VSM (SVSM), based on a determination of one of a plurality of modes of the SDV. The VSM is configured to monitor the EC and the plurality of ZCs and the SVSM is configured to monitor the VSM to determine the one of the plurality of modes of the SDV.

Abstract: A system and method for providing functional safety in a software defined vehicle (SDV) using sensors framework is disclosed. The system includes an Emergency Controller (EC). A plurality of Zonal Controllers (ZCs), each corresponding to one of a plurality of zones of the SDV. A plurality of sets of Primary Sensors (PS), each set of PSs corresponding to one of the plurality of zones and coupled to a corresponding ZC of another zone. A plurality of sets of Tertiary Sensors (TSs), each set of TSs corresponding to one of the plurality of zones and coupled to the EC. The EC or the plurality of ZCs may be dynamically configured to receive sensor data from one of the plurality of sets of PSs, the set of SSs, or the plurality of sets of TSs based on a determination of one of a plurality of modes of the SDV.

Abstract: A software defined vehicle (SDV) is disclosed. The SDV includes control system that includes a set of controllers. A sensor system that includes a plurality of sets of sensors. A network system that includes a first network bus and a second network bus. One of the set of controllers is dynamically configurable to determine one of a plurality of modes of the SDV based on a monitoring of each of the controller system, the sensor system, and the network system. Each of the set of controllers is communicatively coupled with one or more of remaining of the set of controllers via one of the first network bus and the second network bus. Each of the set of controllers are dynamically configured to receive sensor data from at least one of set of sensors from the plurality of sets of sensors.

Abstract: A software defined vehicle (SDV) with functionally safe controller and method of providing functional safety is disclosed. The SDV includes a plurality of controllers. Each of the plurality of controllers includes a safety island configurable to perform a plurality of services corresponding to one or more automotive safety integrity levels (ASILs) from a plurality of ASILs. A performance island configurable to perform a plurality of micro-services corresponding to one or more remaining ASILs from the plurality of ASILs. The performance island includes at least one node that includes at least one container configurable to perform one or more of the plurality of micro-services.

Abstract: Embodiments of present disclosure relates to method and dimension determination system for determining dimensions of carton box. The dimension determination system receives plurality of datapoints associated with open carton box. The dimension determination system extracts depth datapoints from plurality of datapoints for identifying plurality of flaps. The dimension determination system determines height of open carton box using depth datapoints. The dimension determination system generates contour and estimates rectangle figure for contour of open carton box. Further, the dimension determination system determines width and length by extracting vertices of rectangle figure. Thereafter, the dimension determination system utilises width, length and height to obtain dimensions of open carton box. Thus, the present disclosure automatically determines dimensions of carton box.

Abstract: A method for generating precision diagnosis and precision treatment based on patient case twins is disclosed. The method includes receiving query patient case from user device. The method may further include identifying first set of case twins corresponding to query patient case using retrieval model base on similarity analysis between set of query medical parameters and set of patient case medical parameters of each of plurality of patient cases stored in database. The method may further include identifying second set of case twins from first set of case twins using GenAI model. The method may further include determining precision diagnosis for query patient case based on query patient case and second set of case twins. The method may further include generating precision treatment pathway for query patient case based on query patient case, second set of case twins, and determined precision diagnosis using GenAI model.

Abstract: A method for generating target concept-based knowledge graphs is disclosed. The method includes receiving, via a GUI, input data from a user device. The method further includes generating a factor-category list includes a plurality of factors, each associated with one of a set of categories, based on the input data using a Large Language Model (LLM). The method further includes creating a plurality of target concept embeddings from the input data and the factor-category list using an embedding model. The method further includes identifying a relevant set of a plurality of domain embeddings from a Retrieval Augmented Generation (RAG) model based on a similarity analysis of the plurality of target concept embeddings with the plurality of domain embeddings. The method further includes providing a knowledge graph generation prompt to the LLM. The method further includes recursively generating a knowledge graph based on the knowledge graph generation prompt, using the LLM.

Abstract: Embodiments of present disclosure relates to method and system of controlling operations of the vehicle based on the requirements of the occupants in the vehicle. The occupant support system receives data from a plurality of sources installed in the vehicle. The occupant support system identifies one or more unstated requirements of an occupant in the vehicle based on the data. The occupant support system determines one or more changes associated with one or more operations of the vehicle, based on the one or more unstated requirements. The occupant support system determines feasibility of implementing the one or more changes for controlling the one or more operations of the vehicle. Thereafter, the occupant support system controls the one or more operations of the vehicle, based on the feasibility.

Abstract: Disclosed herein is a method and system for managing enterprise digital automation processes. In an embodiment, a plurality of automation requests, related to a plurality of enterprise digital automation processes is prioritized based on an automation requests information. Further, a plurality of tasks from a project application repository is selected for executing the plurality of automation requests. Subsequently, execution of the plurality of automation requests is monitored in real-time by generating a unified portfolio view of the plurality of tasks and by tracking a run-time cost and benefit for each of the plurality of tasks. Furthermore, one or more alerts related to the execution of the plurality of automation requests is generated. Finally, the execution of the plurality of automation requests is optimized by resolving each of one or more alerts using pretrained Artificial Intelligence (AI) model trained on one or more historical events associated with plurality of automation requests.

Abstract: The present invention relates to a method and system for execution of one or more AI workloads in an AI data center. The system is configured to create energy profiles for each AI workload, based on attributes associated with the AI workloads, which reflect their energy consumption characteristics. The system is configured to categorize AI workloads into execution categories based on the created energy profiles and a real-time energy availability of an electrical grid. The system is configured to create a dynamic schedule for execution of the AI workloads for a pre-defined time based on the execution categories. The dynamic schedule is based on the real-time energy availability of the electrical grid and user preferences for execution of the AI workloads. The system is configured to execute each of the AI workloads for the pre-defined time in the AI data center based on the dynamic schedule.

Abstract: This disclosure relates to method and system for implementing safety mechanism in vehicles. The method may include determining a fault parameter corresponding to a hazardous fault occurring in a vehicle. The method may include determining a set of safety requirements, mapped to the error parameter. The method may include identifying at least one diagnostic tests based on a mapping of set of safety requirements and the corresponding error parameter with at least one test identifiers from a plurality of test identifiers created for a plurality of diagnostic tests. The method may further include executing at least one diagnostic tests to determine a predefined component identifier corresponding to a faulty component. The method may further include at least one safety mechanism and at least one safety command associated to the faulty component. The method may include implementing the at least one safety mechanism and the at least one safety command.

Abstract: A method for authentication before deployment of microservices is disclosed. For a first microservice of one or more microservices provided by a vendor, the method includes receiving a microservice package corresponding to the first microservice from a server. The microservice package may include metadata of the first microservice. The metadata may include an encrypted Vendor ID (VID) corresponding to the first microservice, and an authentication identity. Upon receiving the microservice package, the method further includes decrypting the encrypted VID using a VID encryption key to obtain the VID; authenticating the first microservice by comparing the VID with each of a predefined list of VIDs; based on a successful authentication, validating the authentication identity based on an authentication technique; and managing deployment of the first microservice of the one or more microservices in a product.

Abstract: This disclosure relates to method and causal analysis server for identifying domain-specific service management hotspots. The method includes receiving raw data corresponding to plurality of domain-specific issues; generating plurality of chunks from the raw data using an optimal chunking and tokenizing algorithm selected from chunking and tokenizing algorithms to obtain chunked data; creating a plurality of embeddings from the chunked data through an embedding model; clustering the plurality of embeddings into a set of clusters and a set of sub-clusters associated with each of the set of clusters, based on a similarity analysis; determining a set of cluster labels corresponding to the set of clusters and a set of sub-cluster labels corresponding to the set of sub-clusters, via a Large Language Model (LLM); and identifying a plurality of hotspots corresponding to the plurality of domain-specific issues based on the set of cluster labels and the set of sub-cluster labels.

Abstract: This disclosure relates to method and system for mixed language text understanding for Generative Artificial Intelligence (GenAI) models. The method may include receiving a raw parallel corpus of two languages. The method may further include generating a cross-domain codemix parallel corpus and a first set of linguistic features from the raw parallel corpus using statistical and linguistic techniques. The method may further include determining a complexity of each of the plurality of samples of the cross-domain codemix parallel corpus based on a set of complexity parameters. The method may further include sequentially fine-tuning a pre-trained multilingual translation model using each of the plurality of samples in the curriculum learning dataset to obtain a generic pre-trained codemix understanding model.