公开(公告)号：US10901811B2

公开(公告)日：2021-01-26

申请号：US15665123

申请日：2017-07-31

Applicant: Splunk Inc.

Inventor： Dipock Das ,  Aungon Nag Radon ,  Dayanand Pochugari ,  Adam Oliner

IPC: G06F16/00 ,  G06F9/54 ,  G06F16/242 ,  G06F16/2452 ,  G06N5/02 ,  G06N5/04

Abstract: In various embodiments, a natural language (NL) application enables users to more effectively access various data storage systems based on NL requests. As described, the NL application includes functionality for selecting an optimal interpretation algorithm, generating a dashboard, and/or generating an alert based on an NL request. Advantageously, the operations performed by the NL application reduce the amount of time and user effort associated with accessing data storage systems and increase the likelihood of properly addressing NL requests.

公开(公告)号：US10565196B2

公开(公告)日：2020-02-18

申请号：US15663726

申请日：2017-07-29

Applicant: Splunk Inc.

Inventor： Dipock Das ,  Dayanand Pochugari ,  Neeraj Verma ,  Nikesh Padakanti ,  Aungon Nag Radon ,  Anand Srinivasabagavathar ,  Adam Oliner

IPC: G06F16/30 ,  G06F16/2453 ,  G06N20/00 ,  G06F16/248 ,  G06F16/2452 ,  G06N5/04 ,  G06N3/08 ,  G06N5/02 ,  G06N20/10

Abstract: In various embodiments, a natural language (NL) application implements functionality that enables users to more effectively access various data storage systems based on NL requests. As described, the operations of the NL application are guided by, at least in part, on one or more templates and/or machine-learning models. Advantageously, the templates and/or machine-learning models provide a flexible framework that may be readily tailored to reduce the amount of time and user effort associated with processing NL requests and to increase the overall accuracy of NL application implementations.

公开(公告)号：US20190034813A1

公开(公告)日：2019-01-31

申请号：US15663725

申请日：2017-07-29

Applicant: Splunk Inc.

Inventor： Dipock Das ,  Dayanand Pochugari ,  Neeraj Verma ,  Nikesh Padakanti ,  Aungon Nag Radon ,  Anand Srinivasabagavathar ,  Adam Oliner

IPC: G06N5/04 ,  G06N99/00 ,  G06F17/30

Abstract: In various embodiments, a natural language (NL) application implements functionality that enables users to more effectively access various data storage systems based on NL requests. As described, the operations of the NL application are guided by, at least in part, on one or more templates and/or machine-learning models. Advantageously, the templates and/or machine-learning models provide a flexible framework that may be readily tailored to reduce the amount of time and user effort associated with processing NL requests and to increase the overall accuracy of NL application implementations.

公开(公告)号：US11670288B1

公开(公告)日：2023-06-06

申请号：US17328887

申请日：2021-05-24

Applicant: SPLUNK INC.

Inventor： Dipock Das ,  Dayanand Pochugari ,  Aungon Nag Radon

IPC: G10L15/18 ,  G06F16/242 ,  G06N20/00 ,  G06F16/2457 ,  G10L15/22 ,  G06F16/903 ,  G06F16/9032

CPC classification number: G10L15/18 ,  G06F16/243 ,  G06F16/24578 ,  G06F16/903 ,  G06N20/00 ,  G10L15/22 ,  G06F16/9032 ,  G06F16/90324 ,  G10L2015/225

Abstract: In various embodiments, a natural language (NL) application receives a partial NL request associated with a first context, and determining that the partial NL request corresponds to at least a portion of a first next NL request prediction included in one or more next NL request predictions generated based on a first natural language (NL) request, the first context associated with the first NL request, and a first sequence prediction model, where the first sequence prediction model is generated via a machine learning algorithm applied to a first data dependency model and a first request prediction model. In response to determining that the partial NL request corresponds to at least the portion of the first next NL request prediction, the NL application generates a complete NL request based on the first NL request and the partial NL request, and causes the complete NL request to be applied to a data storage system.

公开(公告)号：US11475053B1

公开(公告)日：2022-10-18

申请号：US16147428

申请日：2018-09-28

Applicant: Splunk Inc.

Inventor： Dipock Das ,  Dayanand Pochugari ,  Aungon Nag Radon

IPC: G06F16/332 ,  G06N20/00 ,  G06F16/33 ,  G06F40/205 ,  G06F40/274 ,  G06F3/0482

Abstract: In various embodiments, a natural language (NL) application receives a first incomplete natural language (NL) request, and generates one or more request completion recommendations based on at least the first incomplete NL request and a first recommendation model, where the first recommendation model is generated via a machine learning algorithm applied to a first data dependency model and a first request completion model. The NL application receives a selection of a first request completion recommendation included in the one or more request completion recommendations, generates a complete request based on the first incomplete NL request and the first request completion recommendation, and causes the complete request to be applied to the data storage system.

公开(公告)号：US11429627B2

公开(公告)日：2022-08-30

申请号：US16147375

申请日：2018-09-28

Applicant: Splunk Inc.

Inventor： Ricky Gene Burnett ,  Dipock Das ,  Steven Shaun McIntyre ,  Darrell Sano

IPC: G06F16/248 ,  G06F16/242 ,  G06F16/25 ,  G06F16/28 ,  G06F16/2458 ,  G06F16/2455

Abstract: Machine data is collected from multiple sources of an operating environment such as an information technology system, factory floor, or the like, into a data intake and query system, in one embodiment. Metrics representative of the environment are included in or derived from the data. Users may interact with an interface to depict a representation of various metrics and interdependencies and that depiction is reflected in a computer storage model. Changes to the computer storage model based on the user interaction may also result in automatic changes to control information reflected in the computer storage model that directs the processing of various monitoring functions associated with the metrics.

公开(公告)号：US10922493B1

公开(公告)日：2021-02-16

申请号：US16147433

申请日：2018-09-28

Applicant: Splunk Inc.

Inventor： Dipock Das ,  Dayanand Pochugari ,  Aungon Nag Radon

IPC: G06F40/30 ,  G06F40/247 ,  G06F40/295 ,  G06N20/00 ,  G06F3/0482 ,  G06F40/205

Abstract: Various embodiments of the present application set forth a computer-implemented method that includes processing a first natural language (NL) request, where the first NL request includes a first artifact. The method further includes determining that a first relationship, associated with the first artifact and useable to process the first NL request, is unavailable in a first NL language processing system. The method further includes generating a first data relationship recommendation based on the first NL request. In addition, the method includes causing the first data relationship recommendation to be provided to a user.

公开(公告)号：US20190034499A1

公开(公告)日：2019-01-31

申请号：US15663723

申请日：2017-07-29

Applicant: Splunk Inc.

Inventor： Dipock Das ,  Dayanand Pochugari ,  Neeraj Verma ,  Nikesh Padakanti ,  Aungon Nag Radon ,  Anand Srinivasabagavathar ,  Adam Oliner

IPC: G06F17/30 ,  G06N3/08

Abstract: In various embodiments, a natural language (NL) application implements functionality that enables users to more effectively access various data storage systems based on NL requests. As described, the operations of the NL application are guided by, at least in part, on one or more templates and/or machine-learning models. Advantageously, the templates and/or machine-learning models provide a flexible framework that may be readily tailored to reduce the amount of time and user effort associated with processing NL requests and to increase the overall accuracy of NL application implementations.

公开(公告)号：US20190034247A1

公开(公告)日：2019-01-31

申请号：US15665123

申请日：2017-07-31

Applicant: Splunk Inc.

Inventor： Dipock Das ,  Aungon Nag Radon ,  Dayanand Pochugari ,  Adam Oliner

IPC: G06F9/54 ,  G06F17/30

Abstract: In various embodiments, a natural language (NL) application enables users to more effectively access various data storage systems based on NL requests. As described, the NL application includes functionality for selecting an optimal interpretation algorithm, generating a dashboard, and/or generating an alert based on an NL request. Advantageously, the operations performed by the NL application reduce the amount of time and user effort associated with accessing data storage systems and increase the likelihood of properly addressing NL requests.

公开(公告)号：US11947556B1

公开(公告)日：2024-04-02

申请号：US17891005

申请日：2022-08-18

Applicant: SPLUNK Inc.

Inventor： Ricky Gene Burnett ,  Dipock Das ,  Steven Shaun McIntyre ,  Darrell Sano

IPC: G06F16/248 ,  G06F16/242 ,  G06F16/2455 ,  G06F16/2458 ,  G06F16/25 ,  G06F16/28

CPC classification number: G06F16/248 ,  G06F16/243 ,  G06F16/24568 ,  G06F16/2477 ,  G06F16/252 ,  G06F16/288

Abstract: The disclosure includes methods and systems that perform operations of identifying a behavior of a metric, where the metric is associated with a node of included within a nodal graph displayed on a graphical user interface. Additionally, a root cause of the behavior is determined through automated, computerized analytics, which may include execution of a search query associated with the node, and a notification of the root cause may be provided via the graphical user interface. Additionally, the graphical user interface may be configured to receive user input that results in the generation of a nodal graph, where the user input includes placement of nodes on a display screen and edges representing a connection between two nodes, where the edges may represent a dependency between the nodes.