公开(公告)号：US20250124083A1

公开(公告)日：2025-04-17

申请号：US18928754

申请日：2024-10-28

Applicant: INFOSYS LIMITED

Inventor： Steven SCHILDERS

IPC: G06F16/901

Abstract: A method for loading run-time nodes of a template-based executable graph-based model is provided. A node instance manifest state is obtained based on a first node identifier associated with a node instance. The node instance manifest state includes a second node identifier associated with a node template. A node instance manifest is generated from the node instance manifest state. The node instance manifest comprises a first storage location and the first node identifier. A node instance state is obtained from the first storage location. The node template is obtained based on the second node identifier. The node instance is generated from the node instance manifest, the node instance state, and the node template. A run-time node, comprising a composition of the node instance and the node template, is generated.

公开(公告)号：US20250077595A1

公开(公告)日：2025-03-06

申请号：US18586042

申请日：2024-02-23

Applicant: INFOSYS LIMITED

Inventor： Syed AHMED ,  Ritarshi Chakraborty

IPC: G06F16/9535 ,  G06F16/9538

Abstract: This disclosure relates to method and system for generating user role-specific responses through Large Language Models (LLMs). The method includes receiving a user query from a user account. The user account is associated with a user role from a plurality of user roles. The method includes combining, based on the user role, the user query with contextual information corresponding to the user query to obtain a combined query. The method includes inputting the combined query to an LLM. The method includes generating a user role-specific response corresponding to the combined query through the LLM. The method includes rendering the user role-specific response to a display of a user device associated with the user account.

公开(公告)号：US12229191B2

公开(公告)日：2025-02-18

申请号：US18128984

申请日：2023-03-30

Applicant: Infosys Limited

Inventor： Steven Schilders

IPC: G06F16/24 ,  G06F16/25 ,  G06F16/901 ,  G06T11/20

Abstract: A system comprises an executable graph-based model. The executable graph-based model comprises a first overlay node. The first overlay node comprises processing logic that is operable to interact with one or more associated nodes of the executable graph-based model. Further, the executable graph-based model comprises a first node that has the first overlay node associated therewith. The system further comprises a processing unit configured to receive a first stimulus associated with the first overlay node and, in response to the first stimulus being received, cause execution of said processing logic of the first overlay node. Execution of said processing logic of the first overlay node is based on the first node.

公开(公告)号：US20250055758A1

公开(公告)日：2025-02-13

申请号：US18378006

申请日：2023-10-09

Applicant: Infosys Limited

Inventor： GAURAV SAXENA ,  KISHORE BABU THOTA ,  AMOL NILKANTHESHWAR JOSHI ,  SUBRAMANIAM SUBBIAH ,  SREEKANTH SREEDEVI SASIDHARAN

IPC: H04L41/084 ,  H04L41/0894 ,  H04L41/0896

Abstract: This disclosure relates to method and system for legacy network transformation. The method includes receiving data corresponding to a legacy WAN from one or more data sources. Further, the method includes analyzing the data to identify one or more transformation requirements for the legacy WAN, based on one of a statistical technique, or a machine learning technique. Further, the method includes determining one or more configuration parameters corresponding to the legacy WAN based on a set of pre-defined business policy rules and the one or more transformation requirements. Further, the method includes generating a high-level design for SD-WAN based on the one or more transformation requirements and the one or more configuration parameters. Further, the method includes generating a low-level design including configuration guidelines templates for the SD-WAN based on the high-level design. Each configuration guidelines template may facilitate the transformation of legacy WAN to the SD-WAN.

公开(公告)号：US20250053389A1

公开(公告)日：2025-02-13

申请号：US18432236

申请日：2024-02-05

Applicant: INFOSYS LIMITED

Inventor： SRINIVAS JAGGUMANTRI ,  MADHAVI LATHA PADAKANTI ,  NARESHKUMAR MANOHARAN

IPC: G06F8/35 ,  G06F8/51 ,  G06F40/20

Abstract: This disclosure relates to method and system for facilitating legacy code transformation. The method includes receiving legacy code data and natural language document from one or more data sources. Each of the one or more data sources is one of an external data source or an internal data source. Further, the method includes generating a first natural language output based on the legacy code data through a first LLM, and a second natural language output based on the natural language document through a second LLM. Further, the method includes fine-tuning one of the first LLM or the second LLM based on the first natural language output and the second natural language output, through a third LLM. Further, the method includes generating a natural language specification document corresponding to the legacy code data based on the first natural language output and the second natural language output through the third LLM.

公开(公告)号：US12158892B2

公开(公告)日：2024-12-03

申请号：US17991619

申请日：2022-11-21

Applicant: INFOSYS LIMITED

Inventor： Megha Honna ,  Rajeshwari Ganesan

IPC: G06F16/25 ,  G06F16/22

Abstract: A method for transforming data organized in tabular structure is disclosed. In some embodiments, the method includes assigning a score to each of a plurality of cells within a table based on an associated set of orthogonal features characterizing a set of data. The set of orthogonal features comprises visual features, syntactic features, and language-based features. The method further includes identifying for each of the plurality of cells, a cell type based on the assigned score. The method further includes determining a table type based on the cell type and the set of orthogonal features determined for each of the plurality of cells. The table type comprises one of a row-oriented table, a column-oriented table, or a composite table.

公开(公告)号：US20240333691A1

公开(公告)日：2024-10-03

申请号：US18128120

申请日：2023-09-12

Applicant: Infosys Limited

Inventor： Ramaswami MOHANDOSS ,  Graceta Gnanaselvi Jesurajan

IPC: H04L9/40 ,  H04L9/00 ,  H04L9/08 ,  H04L9/32

CPC classification number: H04L63/0421 ,  H04L9/0861 ,  H04L9/321 ,  H04L9/50

Abstract: This disclosure relates to a method and a system for managing anonymized data across computing devices in a blockchain network. The method includes generating the blockchain network including a blockchain ledger based on a dataset associated with each of a plurality of end users. The method of generating the blockchain network includes constructing the blockchain ledger corresponding to the dataset associated with each of the plurality of end users; generating a unique ledger key corresponding to the dataset associated with each of the plurality of end users; and storing the dataset associated with each of the plurality of end users in the blockchain ledger based on the unique ledger key. The method further includes communicating a joining request to a second computing device for joining the blockchain network. The method further includes granting access to the second computing device to the dataset associated with the plurality of end users.

公开(公告)号：US20240329945A1

公开(公告)日：2024-10-03

申请号：US18128917

申请日：2023-03-30

Applicant: INFOSYS LIMITED

Inventor： Allahbaksh Mohammedali ASADULLAH ,  Monirul ISLAM ,  Manisha MITTAL ,  Vijyeta SAMVEDI ,  Zeeshan MEHBOOB ,  Jishu DAS ,  Hitesh CHAMPALAL ,  Anant PANDE ,  Trijeet KR MODAK

IPC: G06F8/38 ,  G06Q30/0201 ,  H04L67/50

CPC classification number: G06F8/38 ,  G06Q30/0201 ,  H04L67/535

Abstract: This disclosure relates to method and system for generation and presentation of User Experience (UX) recommendations. The method includes retrieving data corresponding to one or more users of an application from a database. The data includes one or more of user device screen recording data, application usage data, or user feedback data. The method further includes determining a set of UX parameter values and a set of UX recommendations based on the data using a first Artificial Intelligence (AI) model; generating a set of User Interface (UI) screen templates based on one or more of the set of UX parameter values, the set of UX recommendations, and the data, using a second AI model; and displaying a report through a Graphical User Interface (GUI) on a display of an administrator device.

公开(公告)号：US20240320595A1

公开(公告)日：2024-09-26

申请号：US18126868

申请日：2023-03-27

Applicant: INFOSYS LIMITED

Inventor： Vishal MANCHANDRA ,  Amit Kumar ,  Venugopal SUBBARAO ,  Janupalli PRANAY

IPC: G06Q10/0639 ,  G06F40/40

CPC classification number: G06Q10/0639 ,  G06F40/40 ,  H04M3/51

Abstract: This disclosure relates to method and system for determination of personality traits of agents in a contact center. The method includes retrieving textual data corresponding to a conversation between a first agent and a first customer. The method further includes generating a natural language justification corresponding to a set of personality traits of the first agent based on the textual data through a first Machine Learning (ML) model. The natural language justification may include one or more sentences. The one or more sentences may include a mapping of the textual data with the set of personality traits and a qualitative label associated with each of the set of personality traits. The method further includes determining a value corresponding to each of the set of personality traits of the first agent through the first ML model based on the natural language justification and the associated qualitative label.

公开(公告)号：US20240320588A1

公开(公告)日：2024-09-26

申请号：US18126169

申请日：2023-03-24

Applicant: INFOSYS LIMITED

Inventor： Arun GANESAN

IPC: G06Q10/0637 ,  G06F40/279

CPC classification number: G06Q10/0637 ,  G06F40/279

Abstract: The present disclosure relates to method and system for managing business rules in a process enterprise. Firstly, an input from a user is received for managing one or more business rules from a plurality of business rules associated with the process enterprise. The input is parses for extracting one or more business keywords. Further, one or more technical keywords corresponding to the one or more business keywords are identified based on a pre-stored mapping information, using a Natural Language Processing (NLP) model. Then, at least one business rule is identified from the plurality of business rules based on the one or more technical keywords. Further, one or more actions to be performed on the at least one business rule is identified based on the input. Finally, the at least one business rule is updated, based on the one or more actions.