公开(公告)号：US20240386316A1

公开(公告)日：2024-11-21

申请号：US18319395

申请日：2023-05-17

Applicant: Oracle International Corporation

Inventor： Vivek Kumar

IPC: G06N20/00

Abstract: A clustering model is used to partition a set of historical opportunity profiles representing historical opportunities into a plurality of opportunity profile clusters. A target opportunity profile that includes a plurality of target-opportunity parameters is obtained, and an opportunity profile cluster is identified that meets a matching criterion with the target opportunity profile. The plurality of historical opportunity profiles of the identified opportunity profile cluster are partitioned based on an outcome indicator associated respectively with each of the plurality of historical opportunity profiles, providing a first subset of historical opportunity profiles and a second subset of historical opportunity profiles. An insight generation model is applied to the target opportunity profile along with the first subset and/or the second subset to generate one or more insights for the target opportunity profile.

公开(公告)号：US12094458B2

公开(公告)日：2024-09-17

申请号：US17668968

申请日：2022-02-10

Applicant: Oracle International Corporation

Inventor： Vivek Kumar

IPC: G10L15/16 ,  G06F40/30 ,  G10L15/18 ,  H04L51/212 ,  G06F40/289 ,  G06F40/35 ,  G10L15/183 ,  G10L15/22

CPC classification number: G10L15/1815 ,  G06F40/30 ,  G10L15/16 ,  G10L15/1822 ,  H04L51/212 ,  G06F40/289 ,  G06F40/35 ,  G10L15/183 ,  G10L2015/225

Abstract: Techniques for extracting data from conversations across different types of communication channels are disclosed. A system applies a set of rules to extract data from conversations based, at least in part, on a type of communication channel used for conducting the conversation. The system applies a machine learning model to recognize semantic content in conversations. The system divides conversations into conversation segments and classifies the conversation segments based on the semantic content. The system selects conversation segments to be extracted based on the semantic content and the type of communication channel over which a conversation is conducted. The system maps conversation segments from different conversations conducted on different types of communication channels to a same set of transactions.

公开(公告)号：US11743211B2

公开(公告)日：2023-08-29

申请号：US17563690

申请日：2021-12-28

Applicant: ORACLE INTERNATIONAL CORPORATION

Inventor： Vivek Kumar

IPC: H04L12/00 ,  H04L51/02 ,  G06F8/36 ,  G06F9/451

CPC classification number: H04L51/02 ,  G06F8/36 ,  G06F9/451

Abstract: Systems, methods, and other embodiments associated with automatically expanding channels for bots are described. In one embodiment, a system includes a bot repository configured to identify each bot of a plurality of bots available in the computing system. A channel metadata repository is configured with channel configuration metadata for each channel of a plurality of channels available to the plurality of bots. The channel configuration metadata includes metadata that defines a specified format for communicating data with a target channel. A bot manager is configured to provide communication between each bot of the plurality of bots and each channel of the plurality of channels by at least converting output responses from each bot based on the channel configuration metadata associated with a target channel.

公开(公告)号：US10922216B1

公开(公告)日：2021-02-16

申请号：US16601937

申请日：2019-10-15

Applicant: Oracle International Corporation

Inventor： Vivek Kumar ,  Catherine You Francis ,  Meeten Bhavsar ,  Prabhakara Reddy Munnangi

IPC: G06F9/44 ,  G06F11/36

Abstract: Techniques are included for intelligently testing a software product using a limited number of test cases that are configured to test portions of the software product that have changed since a prior testing. To determine which test cases are best used for testing the implemented changes, a test case-to-programmatic flow mapping may be generated that relates each test case available for testing the software product with each programmatic flow that is tested by the test case. In addition, a programmatic flow-to-artifact mapping may be created that relates each programmatic flow discovered in the software product to each artifact that is accessed, created, changed, or dependent on the programmatic flow. Using these mappings, specific test cases may be determined for testing only those portions of the software product that have changed since the prior testing.

公开(公告)号：US20250086235A1

公开(公告)日：2025-03-13

申请号：US18812123

申请日：2024-08-22

Applicant: Oracle International Corporation

Inventor： Vivek Kumar

IPC: G06F16/9032 ,  G06N3/0475

Abstract: Techniques for filtering queries to a large language model (LLM) based on their relevance to an enterprise domain associated with the LLM involve training a machine learning model using historical LLM query data and associated relevance scores. These scores indicate how closely a query relates to the enterprise's operations. The trained model is then applied to new input queries, generating relevance scores for the input queries. Queries meeting a predetermined relevance threshold are passed to the LLM for processing. For queries falling below this threshold, remedial actions are taken instead of processing by the LLM. The techniques optimize computational resource allocation by prioritizing queries relevant to the enterprise while filtering out less pertinent ones. The techniques create a relevance-based gatekeeping mechanism for LLM query processing, enhancing efficiency and focusing the LLM's capabilities on enterprise-specific tasks.

公开(公告)号：US11960977B2

公开(公告)日：2024-04-16

申请号：US16447849

申请日：2019-06-20

Applicant: Oracle International Corporation

Inventor： Vivek Kumar ,  Catherine You Francis ,  Meeten Bhavsar

IPC: G06N20/00 ,  G06F16/953

CPC classification number: G06N20/00 ,  G06F16/953

Abstract: Techniques for enhancing actionable opportunities through machine learning are disclosed. In some embodiments, a system includes an event listener for detecting an opportunity to perform an action using one or more computing resources. When a new opportunity is detected, the system generates a set of search criteria, which is used to search a set of external web resources for current events. The system may then generate, using a machine learning model as a function of one or more features extracted from current events satisfying the search criteria, a score representing a likelihood of success that the action leads to an optimal result. The system may tune the machine learning model based on feedback received that is indicative of how the current events affected the likelihood of success for the action.

公开(公告)号：US20230236849A1

公开(公告)日：2023-07-27

申请号：US17585353

申请日：2022-01-26

Applicant: Oracle International Corporation

Inventor： Vivek Kumar ,  Kamyar Seradjfar

IPC: G06F9/451 ,  G06F16/14 ,  G06F8/656 ,  G06N20/00

CPC classification number: G06F9/451 ,  G06F16/14 ,  G06F8/656 ,  G06N20/00

Abstract: Techniques for runtime customization and management of user interfaces for enterprise applications are disclosed. In some embodiments, the techniques include tools, systems, and processes for building frontend, technology-independent user interfaces. A system may consume user input files that are language dependent and generate a metadata file that is language independent. The metadata file may be updated to customize or otherwise modify a user interface of an application at runtime. An event signal may be raised to notify the application when a new user interface is available. In response to detecting the signal, the application may refresh the user interface, including the application page being currently viewed, to modify the set of user interface components that are rendered and displayed to the end user. The system may store metadata for multiple versions of the user interface to allow users to quickly roll back to prior versions of a user interface.

公开(公告)号：US12143346B2

公开(公告)日：2024-11-12

申请号：US18216805

申请日：2023-06-30

Applicant: ORACLE INTERNATIONAL CORPORATION

Inventor： Vivek Kumar

IPC: H04L12/00 ,  G06F8/36 ,  G06F9/451 ,  H04L51/02

Abstract: Systems, methods, and other embodiments associated with a bot communication system for communicating between channels and bots are described. In one embodiment, a system includes a bot manager configured to provide communication between an individual bot from a plurality of bots and a target channel of a plurality of channels. The bot manager is configured to process a bot response from the individual bot to the target channel by at least: identifying channel configuration metadata from a channel metadata repository that defines a channel dependent format for communicating data with the target channel; converting the bot response to the channel dependent format associated with the target channel including formatting data components from the bot response according to the channel configuration metadata of the target channel; and transmitting, via a network connection, the converted bot response to the target channel in the channel dependent format of the target channel.

公开(公告)号：US20240404513A1

公开(公告)日：2024-12-05

申请号：US18807596

申请日：2024-08-16

Applicant: Oracle International Corporation

Inventor： Vivek Kumar

IPC: G10L15/18 ,  G06F40/289 ,  G06F40/30 ,  G06F40/35 ,  G10L15/16 ,  G10L15/183 ,  G10L15/22 ,  H04L51/212

Abstract: Techniques for extracting data from conversations across different types of communication channels are disclosed. A system applies a set of rules to extract data from conversations based, at least in part, on a type of communication channel used for conducting the conversation. The system applies a machine learning model to recognize semantic content in conversations. The system divides conversations into conversation segments and classifies the conversation segments based on the semantic content. The system selects conversation segments to be extracted based on the semantic content and the type of communication channel over which a conversation is conducted. The system maps conversation segments from different conversations conducted on different types of communication channels to a same set of transactions.

公开(公告)号：US20240289817A1

公开(公告)日：2024-08-29

申请号：US18115392

申请日：2023-02-28

Applicant: Oracle International Corporation

Inventor： Vivek Kumar

IPC: G06Q30/0201 ,  G06Q30/01

CPC classification number: G06Q30/0201 ,  G06Q30/01

Abstract: Techniques for sales orchestration using iterative machine learning are disclosed, including: obtaining, by a customer relationship management (CRM) system, opportunity-specific CRM data; generating, by the CRM system, one or more suggested sales actions applicable to the opportunity-specific CRM data, at least by applying a machine learning model to the opportunity-specific CRM data, wherein the machine learning model is configured to generate suggested sales actions based on CRM data; presenting, in a graphical user interface (GUI) of the CRM system, the one or more suggested sales actions; receiving, via the GUI of the CRM system, user input that indicates a chosen sales action associated with the opportunity-specific CRM data; obtaining, by the CRM system, data that indicates an outcome of the chosen sales action; updating the machine learning model based on the outcome of the chosen sales action.