Patents by Inventor Ankit Singh
Ankit Singh 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: 20260350522Abstract: Techniques for simulating audits corresponding to an industrial process are described. In operation, a plurality of operational parameters corresponding to an industrial process within an industrial setup are obtained, where the plurality of operational parameters is indicative of a current operating state of the industrial process. At least one operational parameter from the plurality of operational parameters is then compared with at least one corresponding auditor threshold to identify a first deviation in the current operating state from an auditor operating protocol. A first audit finding is then generated based on the first deviation. At least a first corrective action corresponding to the first deviation is then determined based on the first audit finding. Subsequently, at least the first corrective action is recommended for mitigating the first deviation.Type: ApplicationFiled: April 30, 2025Publication date: November 5, 2026Inventors: ANKIT SINGH, Eric Hartye, Waad Subber
-
Patent number: 12783542Abstract: Various embodiments described herein relate to systems and methods for semantically mapping data associated with a facility. In this regard, initially first vectorial representations of the data in a database are generated. Using the first vectorial representations, a temporary database is created. Then, specifications related to parameters associated with at least one product of the facility is received from a user. The specifications are then converted to second vectorial representations. Further, the second vectorial representations are mapped with the first vectorial representations. Based on the mapping, at least one first vectorial representation is derived from the temporary database. Furthermore, a textual equivalent of the at least one first vectorial representation is rendered via a user interface.Type: GrantFiled: October 17, 2024Date of Patent: November 3, 2026Assignee: HONEYWELL INTERNATIONAL INC.Inventors: Kartikeyan Bollapalli, Ankit Singh, Srihari Narayanaiah
-
Patent number: 12784128Abstract: Disclosed methods provide a virtualized shared graphics processing unit (GPU) memory pool (VSGMP) to virtual machines running on an information handling system. The VSGMP may be implemented with a GPU memory pool (GMP) manager, featuring logic for abstracting the GPU memory pool from the physical memory resources of two or more GPUs. The GMP manager logic may be supported by a lightweight secure operating system (LSOS) capable of enabling functionality for virtualization and other use cases. Disclosed methods manage GPUs in an information handling system featuring two or more GPUs running virtual machines (VMs). When a GPU is assigned to a VM, disclosed methods perform one or more GPU resource allocation operations that support virtual shared pooling of the physical memory resources of two or more GPUs. In at least some embodiments, the GPU allocation operations include allocating at least some non-memory resources of the GPU exclusively to the applicable VM.Type: GrantFiled: April 23, 2024Date of Patent: November 3, 2026Assignee: Dell Products L.P.Inventors: Ankit Singh, Shrikant U. Hallur, Naveen Awasthy
-
Publication number: 20260340558Abstract: A system and method for performing impact analysis associated with a service outage of a service is disclosed. The system comprises a storage and a processor coupled to the storage. The processor is configured to receive a service outage alert message associated with the service. Further, the processor is configured to obtain a service description document associated with the service and one or more historic case reports associated with the service outage from one or more data storages. Further, the processor is configured to generate using an AI model, an impact analysis report comprising information about a business impact of the service outage based on the service description document, the one or more historic case reports, and at least one prompt which is provided as an input to the AI model.Type: ApplicationFiled: April 24, 2025Publication date: October 29, 2026Inventors: Kartikeyan Bollapalli, Ankit Singh, Sarath Kumar Ganesan
-
Publication number: 20260340006Abstract: Techniques for managing distribution of data are disclosed. A query comprising an input descriptor is received. The input descriptor indicates a retrieval parameter for querying a data intelligence repository. Further, datasets available in the data intelligence repository are parsed to identify set of relevant data based on semantic or contextual inference. For the identified set of relevant data, an adaptive data segmentation workflow is executed to manage distribution of the relevant data among segments. The distribution is based on at least one of a computational data dimension threshold, semantic relationships data in the set of relevant data, and a historical data partitioning schema derived based on partitioning of data indicated by a set of records historically recorded. Further, a record generation signal indicating segments comprising data from the relevant set is generated.Type: ApplicationFiled: April 29, 2025Publication date: October 29, 2026Inventors: ANKIT SINGH, Lakshminarayana Paila
-
Publication number: 20260340647Abstract: Example techniques for generation of a recall investigation report for a product are described. In an example, based on quality events data indicative of deviation in a predefined quality parameter of the product with respect to a predefined threshold, batches of the product with anomalies is identified. Further, one or more assessment parameters required for compiling the recall investigation report for assessing the deviation is defined. A PQR report is accessed from a database of a quality management system. Using a large language model (LLM), a chapter of the PQR report with content that has at least a preset degree of semantic similarity with the one or more assessment parameters is identified. A filter to the identified chapter is applied to extract content of the identified chapter corresponding to a batch of the product associated with the deviation. The recall investigation report is populated based on the extracted content.Type: ApplicationFiled: April 28, 2025Publication date: October 29, 2026Inventors: Ankit Singh, Waad Subber, Sophie Basak Atilgan, Lakshminarayana Paila
-
Publication number: 20260330132Abstract: Example techniques for generation of a product quality review (PQR) report are described. In an example, in response to a request to generate the PQR report for a product, previously created reports of a first set of products is accessed. Each of the previously created reports include content pertaining to a predefined quality parameter of the first set of products. Furthermore, the content of the previously created reports are analyzed to identify chapters to be included in the PQR report. Further, for each of the chapters of the PQR report, a list of keywords is generated that specify content to be included in the respective chapters. Furthermore, based on the generated keywords, the content to be included in the chapters of the PQR report is extracted from one or more document management systems. Thereafter, the chapters are populated with the extracted content to generate the PQR report.Type: ApplicationFiled: April 21, 2025Publication date: October 22, 2026Inventors: Ankit Singh, Waad Subber, Kartikeyan Bollapalli
-
Publication number: 20260320624Abstract: A system and method for identification of false duplicate consignees in a recall process is disclosed. The system comprises a storage and at least one processor coupled to the storage. The processor is configured to classify a plurality of consignees into a first list and a second list, wherein the first list comprises one or more unique consignees and the second list comprises one or more duplicate consignees from amongst the plurality of consignees. Further, the processor is configured to obtain metadata associated with the one or more duplicate consignees comprised in the second list. Further, the processor is configured to select for each of the one or more duplicate consignees, at least one false duplicate verification rule from a plurality of false duplicate verification rules that is to be used for determining a veracity of the one or more duplicate consignees present in the second list, based on the metadata associated with each of the said one or more duplicate consignees.Type: ApplicationFiled: April 10, 2025Publication date: October 15, 2026Inventors: Ankit Singh, Waad Subber, Lakshminarayana Paila
-
Publication number: 20260311189Abstract: Approaches for managing product recall effectiveness are described. According to an example, distribution data, that describes movement of various a plurality of units of a product among one or more entities involved in procurement and distribution of the plurality of units in a distribution chain of the product, is obtained. The distribution data is processed to identify a bottleneck entity, from the one or more entities, that are affecting recovery of the plurality of units of the product by an organization. Then, an optimal communication strategy is generated for communicating with the bottleneck entity to enable recovery of the plurality of units of the product by the organization.Type: ApplicationFiled: April 8, 2025Publication date: October 8, 2026Inventors: Ankit Singh, Waad Subber, Lakshminarayana Paila
-
Publication number: 20260310185Abstract: Techniques for identification of entities in a multistage entity coordination network are disclosed. An entity identification signal, indicating at least one of entity descriptors and resource descriptors, is received. An entity intelligence database, comprising empirical entity indicators and empirical resource indicators, is assessed. Each empirical entity indicator identifies one of the plurality of entities, and each empirical resource indicator is linked with an entity and indicates a resource attribute of that entity. A set of empirical entity indicators correlating with the entity descriptors and a set of empirical resource indicators correlating with the resource descriptors are identified. Based on these correlations, a set of entities is identified from amongst the plurality of entities that likely comply with specified resource characteristics. A multistage entity indication signal is then generated to cause rendering of the identified set of entities.Type: ApplicationFiled: April 8, 2025Publication date: October 8, 2026Inventors: Ankit Singh, Kartik Bollapalli
-
Publication number: 20260300987Abstract: Approaches for proactive product risk assessment are described. According to one example, forum data available on public forums is parsed to retrieve recall and feedback (RF) data corresponding to a target product. The RF data is analyzed to identify analytical tools to be implemented for assessing the target product and determine an assessment workflow indicating a sequential order of analytical tools to be followed for assessing the target product. Tool-specific input data corresponding to each of the analytical tools may be generated and analyzed to obtain tool-specific output data from each of the analytical tools by implementing the analytical tools in accordance with the sequential order. Tool-specific output data obtained from the analytical tools are processed to identify probable quality concerns in the target product and generate an assessment report, including the probable quality concerns, corresponding to the target product.Type: ApplicationFiled: March 27, 2025Publication date: October 1, 2026Inventors: Waad Subber, Ankit Singh, Lakshminarayana Paila
-
Publication number: 20260300870Abstract: Techniques for assessment of a workflow and generation of recommendations are disclosed. A workflow record comprising operation specification for each of the interlinked operations is obtained. The operation specification is encoded into vector specifications, and a semantic conformity assessment is performed between the vector specifications and prescribed vector specifications derived from a reference workflow record. The reference workflow record includes prescribed operation specifications and linked data objects. Based on the assessment, a candidate set of prescribed operations semantically conforming with the operational workflow's operations is identified. A recommendation generation signal is then generated to cause rendering of the candidate set of prescribed operations and their linked data objects. The approach enables probable enhancement of the workflow by identifying and suggesting relevant operations and associated data from a reference workflow record.Type: ApplicationFiled: March 26, 2025Publication date: October 1, 2026Inventors: Ankit Singh, Shaun Vallejo, Lakshminarayana Paila
-
Publication number: 20260303611Abstract: Techniques for managing product recall drives are disclosed. In an example, a logon request is received from a computing device, where the logon request corresponds to a consignee of a product associated with a product recall drive and comprises a first information to facilitate logon of the consignee onto a consignee portal. A geographical location of the computing device is then determined to be within a predetermined range of at least one of expected geographical locations of the consignee. In response to the determination, authenticity of the consignee is verified, and the consignee is logged on onto the consignee portal. The consignee is logged on based on the first information to allow the consignee to provide information corresponding to the product associated with the product recall drive.Type: ApplicationFiled: March 28, 2025Publication date: October 1, 2026Inventors: Ankit Singh, Lakshminarayana Paila, Jignesh Kansara, Amit Kumar
-
Publication number: 20260277761Abstract: Techniques for domain-based quality management are disclosed. A domain-specific data to assess quality thereof is received and processed using the analysis model. One of a plurality of standardized domain-specific data framework that is to correspond to the domain-specific data is identified using the analysis model. Each of a plurality of fields of the domain-specific data is mapped with a field of the first plurality of fields of the identified standardized domain-specific data framework using the analysis model. Critical quality control factors are monitored using the analysis model. Alerts are generated in response to the monitoring. Customized visualizations and predictive analytics are displayed based on the monitoring.Type: ApplicationFiled: January 13, 2025Publication date: September 17, 2026Inventors: Ankit Singh, Lakshminarayana Paila, Zillery Fortner, Judith Fainor, Stephen McCarthy
-
Patent number: 12724864Abstract: Disclosed systems and methods for authenticating virtual machines, upon detecting a virtual machine launch (VML) request associated with a hypervisor and an unconfirmed VM, request a VM signing (VMS) certificate from a deployment/verification cloud server. The VMS certificate is forwarded to a certificate store of the hypervisor. After an unconfirmed VM is successfully authenticated, the VMS certificate may be deleted from the hypervisor certificate store. If an alert indicating a failed authentication associated is detected, termination operations are performed to prevent the unconfirmed VM from running under the hypervisor. The termination operations may include identifying a suspect key or signature associated with the unconfirmed VM and recording the suspect key or signature in a prohibited database store, such as a UEFI Secure Boot DBX variable store. For example, a suspect key or signature may be a key used to sign the unconfirmed VM.Type: GrantFiled: April 17, 2024Date of Patent: September 1, 2026Assignee: Dell Products L.P.Inventors: Ankit Singh, Shrikant U. Hallur, Naveen Awasthy
-
Patent number: 12724987Abstract: The present disclosure provides a method for processing data and service system thereof. The present disclosure comprises a steps for receiving a plurality of data from one or more users, wherein the plurality of data includes text in a source language. The present disclosure further comprises steps for storing the plurality of data in a delimited format, wherein the plurality of data is arranged in one or more rows and one or more columns based on the plurality of information associated with one or more users, wherein the data in the one or more rows and the one or more columns are stored in the form of one or more cells comprising one or more characters. The present disclosure further comprises steps for identifying the cell with largest character count from the one or more rows and selecting the row corresponding to the identified cell.Type: GrantFiled: April 30, 2024Date of Patent: September 1, 2026Assignee: HONEYWELL INTERNATIONAL INC.Inventors: Ankit Singh, Shashidhar Kotta
-
Patent number: 12718163Abstract: The present disclosure provides a method and system for embedding contextual video content for optimizing a user's workflow on a task. The method comprises selecting at least one task to be performed by one or more users and identifying the profile of the one or more users based on the selected task. The one or more current actions of the user on the workflow are assessed to obtain real time correlations between the one or more current actions and historical workflow metrics of the user, wherein the historical workflow metrics comprises one or more previous actions or preferences of the user for executing the workflow of the at least one selected task. The method further comprises determining that the one or more users requires contextual assistance to execute the workflow of the at least one selected task when the one or more current actions of the user reaches a pre-defined threshold.Type: GrantFiled: April 18, 2024Date of Patent: August 25, 2026Assignee: HONEYWELL INTERNATIONAL INC.Inventors: Ankit Singh, Judith Fainor, Abhishek Hiremath, Amy Spizzirri
-
Patent number: 12717826Abstract: Approaches for executing feedback techniques for processing of natural language queries are described. According to one example, upon receiving a customization request in relation to a visual indicator, data fields associated with the visual indicator are displayed. Each of the data fields represents a subset of data stored within one or more datasets, the data being graphically representable through the visual indicator. A first input, including additional synonyms to be assigned to a data field from the data fields, is received. A list of pre-assigned synonyms, associated with the data field for processing of natural language queries for one or more topics, is obtained. The additional synonyms are reconciled with the list of pre-assigned synonyms to obtain an updated list of pre-assigned synonyms for the data field. The updated list of pre-assigned synonyms may be used for future processing of natural language queries raised for the one or more topics.Type: GrantFiled: April 15, 2024Date of Patent: August 25, 2026Assignee: HONEYWELL INTERNATIONAL INC.Inventor: Ankit Singh
-
Patent number: 12711124Abstract: Techniques for validating and modifying file records are disclosed. A reference specification is obtained, indicating valid data labels and data points, where each data point is classified into a data label. A semantic assessment is performed between a file record and the reference specification to determine semantically conforming data descriptors and data labels. It is then determined whether aspects of data elements associated with the data descriptors conform with correlated aspects of data points linked to the data labels. Based on the determination, a data modification workflow is triggered to transform non-conforming aspects of data elements. The file record is subsequently modified to include the transformed data elements. The present subject matter may enable automated validation and modification of file records to ensure conformity with the reference specification.Type: GrantFiled: November 13, 2024Date of Patent: August 18, 2026Assignee: Honeywell International Inc.Inventors: Ankit Singh, Shaun Vallejo
-
Publication number: 20260228749Abstract: Examples techniques to manage workflow executed by product recall management system PRMS are described. Correlation information associated with a first step of the workflow for recall of a product is retrieved. The first step comprises first action item to be executed by a first user and correlation information identifies second action item, associated with a second step of workflow, initiation of execution of which depends upon completion of execution of first action item. A visual indicator depicting logical association of pendency of second action item with pendency of first action item is presented to first user based on correlation information. Status of first and second step is determined based on execution of respective action items. If status of first step is pending, a schedule for completion of execution of first action item is generated based on scheduled date of completion of recall and depicted to first user through visual indicator.Type: ApplicationFiled: February 5, 2025Publication date: August 6, 2026Inventors: Ankit Singh, Lakshminarayana Paila, Varun Shekhar Singh