Wipro

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.

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, for example using, 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 for example using, the LSI based on the summarization instructions. For each of the set of topics, the method may further include generating, through for example using, 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.

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.

A software defined vehicle (SDV) is disclosed. The SDV includes controller 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.

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.

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.

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.

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.

Zusammenfassung wird geladen …

Zusammenfassung wird geladen …