Patents by Inventor Vikrant Kaulgud
Vikrant Kaulgud has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20260350176Abstract: System and method for securing software supply chains is disclosed.Type: ApplicationFiled: April 30, 2025Publication date: November 5, 2026Applicant: ACCENTURE GLOBAL SOLUTIONS LIMITEDInventors: Vikrant KAULGUD, Teresa Sheausan TUNG, Adam Patten BURDEN, Kuntal DEY, Samarth SIKAND, Kapil SINGI, Vibhu Saujanya SHARMA
-
Patent number: 12783814Abstract: System and method for assessing and enhancing quality of prompts in generative AI-driven software coding is disclosed. The method includes, receiving a user input, wherein the user input comprises at least one keyword associated with a task, predicting an intent of the user input based on the at least one keyword, the task, and a context of the at least one keyword, and predicting a plurality of target elements applicable to the user input based on the predicted intent, wherein the plurality of target elements comprise entities and actions in the user input.Type: GrantFiled: January 8, 2025Date of Patent: November 3, 2026Assignee: ACCENTURE GLOBAL SOLUTIONS LIMITEDInventors: Kuntal Dey, Samdyuti Suri, Sankar Narayan Das, Kapil Singi, Vibhu Saujanya Sharma, Vikrant Kaulgud, Teresa Sheausan Tung, Adam Patten Burden
-
Publication number: 20260340397Abstract: Systems and methods for optimizing prompts in a generative Artificial-Intelligence (AI) model are disclosed. The system receives an input prompt data from data sources, and determines prompt attributes corresponding to the input prompt data based on tokens. Furthermore, the system generates a sub-prompt for the input prompt data and estimates response tokens for each of the sub-prompt based on a set of parameters. Furthermore, the system generates a contextual dependency matrix between each of the sub-prompt and generate a merged prompt. Further, the system generates a Large Language Model (LLM) response for the merged prompt. Furthermore, the system validates the LLM response to determine whether the LLM response matches the task in the input prompt data using the trained LLM. Further, the system fine tunes the LLM response, the estimated plurality of response tokens and the sub-prompt and outputs the fine-tuned LLM response.Type: ApplicationFiled: April 28, 2025Publication date: October 29, 2026Applicant: ACCENTURE GLOBAL SOLUTIONS LIMITEDInventors: Kapil SINGI, Kuntal Dey, Vikrant Kaulgud, Vibhu Saujanya Sharma, Adam Patten Burden, Manish Ahuja, Niel Eyde, Alison Detwiler
-
Patent number: 12770392Abstract: A remote location monitoring system identifies a place of interest and a subset of artificial satellites that can capture images of the place of interest within a threshold period. The next available artificial satellite with image sensors that can capture images of the place of interest earliest is selected and the cache heating signal is transmitted to be stored in a cache associated with the next available image sensor. The cache heating signal activates particular image sensors for image capture and enables the transmission of meaningful images that enable monitoring the place of interest.Type: GrantFiled: June 21, 2023Date of Patent: October 20, 2026Assignee: ACCENTURE GLOBAL SOLUTIONS LIMITEDInventors: Kuntal Dey, Venkatesh Subramanian, Rambhau Eknath Rote, Senthil Kumaresan, Satyasai Srinivas Abbabathula, Nataraj Kuntagod, Vikrant Kaulgud, Sanjay Podder
-
Publication number: 20260301250Abstract: A system for generating primary graphical representation for the provenance management is disclosed. The system receives a primary graphical dataset, including a prompt, source documents and artifacts from a data sources. The system generates a primary graphical representation including primary entities based on a primary unique identifier associated with the primary graphical dataset. The system generates a plurality of primary time-stamped relations for each of the primary entities by correlating the primary entities with similar pre-determined entities. The system determines an occurrence of an event corresponding to the primary graphical dataset, followed by, generating a plurality of primary hypernodes, event nodes, event-to-event relations, event to entity relations, and/or entity-to-entity relations. The system validates the determined occurrence of the event using Artificial-Intelligence based model and modifies the generated primary entities.Type: ApplicationFiled: March 25, 2025Publication date: October 1, 2026Applicant: ACCENTURE GLOBAL SOLUTIONS LIMITEDInventors: Adam Kerry Mills-Campisi, Ramya Narasimhan, Ravi Kiran Velama, Sankar Narayan Das, Kuntal Dey, Vikrant Kaulgud, Adam Patten Burden, Kaushik Amar Das
-
Patent number: 12743631Abstract: A first device may provide, via a global digital twin of the first device, a communication mode assignment, of a communication mode, to a local digital twin of a second device. The communication mode assignment is to cause the local digital twin to communicate with the global digital twin via the communication mode. The first device may generate, via the global digital twin, a task assignment, and may provide, via the global digital, the task assignment to the local digital twin. The first device may update, via the global digital twin, a model based on the task assignment, and may receive, via the global digital twin and from the local digital twin, a model update associated with the local digital twin. The first device may update, via the global digital twin, the model based on the model update.Type: GrantFiled: September 23, 2022Date of Patent: September 22, 2026Assignee: ACCENTURE GLOBAL SOLUTIONS LIMITEDInventors: Sankar Narayan Das, Kanchanjot Kaur Phokela, Kuntal Dey, Kapil Singi, Vikrant Kaulgud, Padmanaban Sukhumaran, Gopal Sarma Pingali
-
Patent number: 12737475Abstract: Systems and methods supporting discovery and quantification of vulnerabilities in software code are disclosed. The systems and methods provide functionality for using software code analysis and other types of tools to analyze the software code and determine whether it can be trusted. The software code tools may be able to discover various hidden issues in the software code and the outputs of such tools may be normalized to quantify the risk associated with vulnerabilities identified by the different tools. A labeling strategy is provided to label the software code to enable users to identify the best software among various available software options based on the label(s) and a set of criteria.Type: GrantFiled: June 23, 2023Date of Patent: September 15, 2026Assignee: Accenture Global Solutions LimitedInventors: Kanchanjot Kaur Phokela, Narendranath Sukhavasi, Kuntal Dey, Kapil Singi, Vikrant Kaulgud, Adam Patten Burden
-
Patent number: 12737680Abstract: A method and system for training a federated learning model are disclosed. The method may include receiving the global federated learning model from the server via the client. The client may control remote computing resources. The method may further include identifying a spare computing instance from the remote computing resources and determine a threshold training load for training the global federated learning model based on a training load assigned to the client. The method may further include, in response to a processing capacity of the spare computing instance being sufficient to process the threshold training load, offloading the threshold training load to the spare computing instance and training the global federated learning model on the spare computing instance with the training dataset stored in a data source maintained by the client.Type: GrantFiled: January 20, 2023Date of Patent: September 15, 2026Assignee: ACCENTURE GLOBAL SOLUTIONS LIMITEDInventors: Kaushik Amar Das, Kuntal Dey, Kapil Singi, Vikrant Kaulgud, Sanjay Podder, Gopal Sarma Pingali, Teresa Sheausan Tung
-
Patent number: 12730948Abstract: Aspects of the present disclosure provide methods, devices, and computer-readable storage media that support detection, effect monitoring, and recovery from failure modes in cloud computing application using a failure mode effect analysis (FMEA) engine. Historical metadata related to operation of a hierarchy of devices may be used as training data to train the FMEA engine to identify failure modes experienced by the hierarchy of devices. After training the FMEA engine, metadata from the hierarchy of devices may be input to the FMEA engine to identify a failure mode that may have occurred, and the FMEA engine may select a recovery process to recommend for addressing or mitigating the identified failure mode. In some implementations, the FMEA engine may output an indication of the recommended recovery process and/or initiate performance of one or more operations at the hierarchy of devices to recover from the failure event.Type: GrantFiled: April 4, 2023Date of Patent: September 8, 2026Assignee: Accenture Global Solutions LimitedInventors: Sankar Narayan Das, Kuntal Dey, Kapil Singi, Vikrant Kaulgud, Manish Ahuja, Reuben Rajan George, Mallika Fernandes, Mahesh Venkata Raman
-
Patent number: 12681854Abstract: A computer-implemented method for cost and carbon aware large language model (LLM) cache management is disclosed. The method includes: determining whether a prompt matching an input prompt exists in a plurality of prompts stored in a cache memory; upon determining that the prompt matching the input prompt exists in the cache memory, returning a response associated with the prompt from the cache memory; otherwise, (a) invoking the LLM and returning a response generated by the LLM, (b) updating the cache memory with the input prompt and the associated response obtained from the LLM as an entry in the cache memory, (c) estimating an operational cost and a carbon cost associated with generating the response to the input prompt, (d) fetching data associated with the LLM, and (e) updating the operational cost, the carbon cost and the data associated with the LLM as metadata of the entry in the cache memory.Type: GrantFiled: December 13, 2024Date of Patent: July 14, 2026Assignee: ACCENTURE GLOBAL SOLUTIONS LIMITEDInventors: Kaushik Amar Das, Sankar Narayan Das, Kuntal Dey, Samdyuti Suri, Vikrant Kaulgud, Teresa Sheausan Tung, Adam Patten Burden
-
Publication number: 20260195538Abstract: System and method for assessing and enhancing quality of prompts in generative AI-driven software coding is disclosed. The method includes, receiving a user input, wherein the user input comprises at least one keyword associated with a task, predicting an intent of the user input based on the at least one keyword, the task, and a context of the at least one keyword, and predicting a plurality of target elements applicable to the user input based on the predicted intent, wherein the plurality of target elements comprise entities and actions in the user input.Type: ApplicationFiled: January 8, 2025Publication date: July 9, 2026Applicant: ACCENTURE GLOBAL SOLUTIONS LIMITEDInventors: Kuntal DEY, Samdyuti SURI, Sankar Narayan DAS, Kapil SINGI, Vibhu Saujanya SHARMA, Vikrant KAULGUD, Teresa Sheausan TUNG, Adam Patten BURDEN
-
Publication number: 20260169916Abstract: A computer-implemented method for cost and carbon aware large language model (LLM) cache management is disclosed. The method includes: determining whether a prompt matching an input prompt exists in a plurality of prompts stored in a cache memory; upon determining that the prompt matching the input prompt exists in the cache memory, returning a response associated with the prompt from the cache memory; otherwise, (a) invoking the LLM and returning a response generated by the LLM, (b) updating the cache memory with the input prompt and the associated response obtained from the LLM as an entry in the cache memory, (c) estimating an operational cost and a carbon cost associated with generating the response to the input prompt, (d) fetching data associated with the LLM, and (e) updating the operational cost, the carbon cost and the data associated with the LLM as metadata of the entry in the cache memory.Type: ApplicationFiled: December 13, 2024Publication date: June 18, 2026Applicant: Accenture Global Solutions LimitedInventors: Kaushik Amar DAS, Sankar Narayan DAS, Kuntal DEY, Samdyuti SURI, Vikrant KAULGUD, Teresa SHEAUSAN TUNG, Adam Patten BURDEN
-
Patent number: 12632358Abstract: A device may receive system data identifying computational components and software components of a distributed and heterogeneous system executing a hybrid cloud application, and may create digital twins for the computational components and the software components. The device may create a central digital twin to receive functional data, operational data, and key performance indicators (KPIs) from the digital twins, and may create complex KPIs based on the functional data, the operational data, and the KPIs. The device may modify, based on the complex KPIs, one or more of the digital twins to generate additional KPIs, and process the additional KPIs, with a principal component analysis model and a self-organizing maps model, to detect anomalies in the distributed and heterogeneous system. The device may generate, based on the anomalies, a KPI cause vector identifying a root cause associated with the anomalies, and may perform actions based on the root cause.Type: GrantFiled: November 18, 2022Date of Patent: May 19, 2026Assignee: ACCENTURE GLOBAL SOLUTIONS LIMITEDInventors: Manish Ahuja, Kanchanjot Kaur Phokela, Swapnajeet Gon Choudhury, Kapil Singi, Kuntal Dey, Vikrant Kaulgud, Mahesh Venkataraman, Mallika Fernandes, Reuben Rajan George, Teresa Sheausan Tung
-
Patent number: 12602372Abstract: System and method for query augmentation for generating responses is disclosed. The method includes, receiving an input data from a user device, determining a context of the received input data, determining a domain specific graphical knowledge schema corresponding to the received input data, and identifying a plurality of missing entities by analyzing the determined context and at least one graphical instance corresponding to the determined appropriate domain specific graphical knowledge schema. The method further includes, prioritizing the identified plurality of missing entities, generating at least one sub-query for each of the identified plurality of missing entities and retrieving a relevant content corresponding to the generated at least one sub-query using a RAG-based system.Type: GrantFiled: April 3, 2025Date of Patent: April 14, 2026Assignee: ACCENTURE GLOBAL SOLUTIONS LIMITEDInventors: Adam Kerry Mills-Campisi, Ramya Narasimhan, Ravi Kiran Velama, Sankar Narayan Das, Kuntal Dey, Vikrant Kaulgud, Adam Patten Burden, Kaushik Amar Das
-
Publication number: 20260065177Abstract: Method, system, and computer-readable storage media for generating a foundation model pipeline including a set of foundation models for completion of a plurality of tasks. Each task of the plurality of tasks has a set of pre-conditions and a set of post-conditions. Based on the set of pre-conditions and the set of post-conditions, a set of possible plans for processing the plurality of tasks is generated. For each plan of the set of possible plans, the set of foundation models from a plurality of foundation models is identified for performing each task of the plurality of tasks according to the respective plan. Further, an efficiency score is estimated for each plan to perform the plurality of tasks according to the plan. Based on the estimated efficiency score of each plan, the set of foundation models is selected for the plurality of tasks.Type: ApplicationFiled: August 28, 2024Publication date: March 5, 2026Inventors: Sankar Narayan DAS, Kuntal Dey, Kapil Singi, Kaushik Amar Das, Vikrant Kaulgud, Vibhu Saujanya Sharma, Samdyuti Suri, Teresa Sheausan Tung, Adam Patten Burden
-
Publication number: 20260064450Abstract: System and method for managing virtual machines (VMs) is disclosed. The method includes, identifying, using a map of VMs, a set of candidate VMs that are predicted to consume less power over time than the first VM for a common workload, removing from consideration any of the candidate VM from the set of candidate VMs that fails to satisfy any predetermined criteria, performing tradeoff analysis on the remaining candidate VMs based on one or more parameters to identify the candidate VMs for redeploying the software operations and ranking the identified candidate VMs based on at least predicted power consumption data for the common workload. The method further includes, selecting, based on the ranking, one of the identified candidate VMs as the second VM, redeploying the software operations from the first VM to the second VM, rerouting data inflow to the first VM to the second VM, and terminating operations of the first VM.Type: ApplicationFiled: August 29, 2024Publication date: March 5, 2026Inventors: Priyavanshi Pathania, Rohit Mehra, Samarth Sikand, Nikhil Bamby, Vibhu Saujanya Sharma, Vikrant Kaulgud, Sanjay Podder
-
Publication number: 20260065074Abstract: Methods, systems, and computer-readable storage media for selecting foundation models. For selecting the foundation models, tasks and contextual parameters are obtained. The contextual parameters include functional requirement values and user preferences. The functional requirement values describe operating characteristics of a foundation model of a plurality of foundation models. Based on the functional requirement values and the user preference values, utility values of the foundation model are estimated. Based on the estimated utility values, a set of foundation models from the plurality of foundation models is selected. The functional requirement values and the user preference values constrain the selection of the foundation models. The selected set of foundation models are outputted for performing the tasks.Type: ApplicationFiled: August 27, 2024Publication date: March 5, 2026Inventors: Sankar Narayan DAS, Kuntal Dey, Kaushik Amar Das, Samdyuti Suri, Vibhu Saujanya Sharma, Vikrant Kaulgud, Teresa Sheausan Tung
-
Publication number: 20260064493Abstract: Methods, systems, and computer-readable media for ranking large language models (LLMs). Input including list of LLMs, list of hardware and artificial intelligence (AI) prompt are provided by the user for ranking the LLMs. Based on the input, first estimating minimum number of hardware units needed to process AI prompt on each LLM/hardware combination and second estimating time to process the AI prompt using each LLM/hardware combination. Based on minimum number of hardware units and time to process AI prompt, third estimating amount of energy consumed by each LLM/hardware combination. Based on energy consumed, ranking LLM/hardware combinations for AI prompt. Based on ranking, selecting LLM and hardware, submitting AI prompt to LLM on hardware, and receiving response to submitted AI prompt from LLM.Type: ApplicationFiled: August 29, 2024Publication date: March 5, 2026Inventors: Samarth Sikand, Rohit Mehra, Priyavanshi Pathania, Nikhil Bamby, Vibhu Saujanya Sharma, Vikrant Kaulgud, Sanjay Podder, Adam Patten Burden
-
Patent number: 12566755Abstract: Methods, systems, and computer-readable storage media for information retrieval using query aware extended chunks. For retrieving relevant information from a foundation model, a plurality of chunks substantially relevant to a query are identified, the plurality of chunks containing information relevant to the query. Based on the plurality of chunks, one or more semantically similar chunks are identified for one or more of the plurality of chunks substantially relevant to the query. By combining the one or more semantically similar chunks with the respective one or more of the plurality of chunks, one or more extended chunks are generated. Based on one or more objectives, a subset of the one or more extended chunks is selected. The query and the selected subset are inputted as a context to the foundation model for retrieving relevant information from the foundation model.Type: GrantFiled: August 23, 2024Date of Patent: March 3, 2026Assignee: ACCENTURE GLOBAL SOLUTIONS LIMITEDInventors: Manish Ahuja, Narendranath Sukhavasi, Kapil Singi, Swapnajeet Choudhury, Vibhu Saujanya Sharma, Vikrant Kaulgud, Pragya Sharma, Teresa Sheausan Tung, Adam Patten Burden
-
Publication number: 20260056942Abstract: Methods, systems, and computer-readable storage media for information retrieval using query aware extended chunks. For retrieving relevant information from a foundation model, a plurality of chunks substantially relevant to a query are identified, the plurality of chunks containing information relevant to the query. Based on the plurality of chunks, one or more semantically similar chunks are identified for one or more of the plurality of chunks substantially relevant to the query. By combining the one or more semantically similar chunks with the respective one or more of the plurality of chunks, one or more extended chunks are generated. Based on one or more objectives, a subset of the one or more extended chunks is selected. The query and the selected subset are inputted as a context to the foundation model for retrieving relevant information from the foundation model.Type: ApplicationFiled: August 23, 2024Publication date: February 26, 2026Applicant: ACCENTURE GLOBAL SOLUTIONS LIMITEDInventors: Manish Ahuja, Narendranath Sukhavasi, Kapil Singi, Swapnajeet Choudhury, Vibhu Saujanya Sharma, Vikrant Kaulgud, Pragya Sharma, Teresa Sheausan Tung, Adam Patten Burden