公开(公告)号：US20240281671A1

公开(公告)日：2024-08-22

申请号：US18112481

申请日：2023-02-21

申请人： Accenture Global Solutions Limited

发明人： Kanchanjot Kaur Phokela ,  Kapil Singi ,  Kuntal Dey ,  Vikrant Kaulgud ,  Teresa Sheausan Tung

IPC分类号： G06N5/022

CPC分类号： G06N5/022

摘要： Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support ontology driven processes to generate and/or update digital twins using a partially automated process. To generate the digital twin, an ontology may be obtained and used to generate a hierarchy model, from which a knowledge graph is generated and represents a digital twin. Similarity measurements may be performed on the knowledge graph, such as components thereof, to determine a similarity between the components. Components are ranked and clustered to identify clusters of similar components and new relationships between components. This new information may be used to update the knowledge model and/or knowledge graph. Updating the knowledge graph or model may enable generation of an updated digital twin and enable continued updating of additional different data structures for other similar elements.

公开(公告)号：US12019776B2

公开(公告)日：2024-06-25

申请号：US17733726

申请日：2022-04-29

申请人： ACCENTURE GLOBAL SOLUTIONS LIMITED

发明人： Kapil Singi ,  Vikrant Kaulgud ,  Kanchanjot Kaur Phokela ,  Kishore P. Durg ,  Swapnajeet Gon Choudhury

IPC分类号： G06N5/022 ,  G06F16/2455 ,  G06F16/2457 ,  G06F16/2458 ,  G06F21/62

CPC分类号： G06F21/6218 ,  G06F16/24564 ,  G06F16/2457 ,  G06F16/2458 ,  G06N5/022

摘要： In some examples, policy-based application architecture generation may include generating, based on a knowledge model schema, data residency policies, and a data classification ontology, a knowledge model, and determining, based on the knowledge model, whether an application includes regulated data. Based on an analysis of application data and user data, user location and regulated data insights may be generated to determine location specific data residency policies. Location specific regulated data in-flow and data source hosted location insights may be analyzed to determine a location compliance assessment that includes an indication of whether a location associated with the application is compliant or not compliant with the location specific data residency policies. Based on an indication of non-compliance, a strategy may be generated for compliance of application architecture for the application with the location specific data residency policies, and re-architecting of the application architecture may be implemented.

公开(公告)号：US20240311618A1

公开(公告)日：2024-09-19

申请号：US18602139

申请日：2024-03-12

申请人： Accenture Global Solutions Limited

发明人： Narendranath Sukhavasi ,  Kanchanjot Kaur Phokela ,  Kapil Singi ,  Kuntal Dey ,  Vikrant Kaulgud ,  Vibhu Saujanya Sharma ,  Adam Patten Burden

IPC分类号： G06N3/0455

CPC分类号： G06N3/0455

摘要： A method and system for evaluating and enhancing a prompt for use by a generative artificial intelligence processing model are disclosed. The method may include obtaining a prompt representing a natural language text for use by a generative artificial intelligence processing model, obtaining a prompt classifier trained to evaluate a classification of the prompt, and inputting the prompt to the prompt classifier to generate a classification of the prompt. The method may further include identifying an intent underlying the prompt and detecting an implicit constraint for the prompt based on the intent. The method may further include transforming the intent in the prompt into a constraint-enhanced intent based on the implicit constraint, generating an enhanced prompt based on the constraint-enhanced intent, and outputting the enhanced prompt for the generative artificial intelligence processing model.