Patents by Inventor Iryna Vogler-Ivashchanka
Iryna Vogler-Ivashchanka 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).
-
Patent number: 11960575Abstract: Embodiments of the present invention are directed to facilitating data preprocessing for machine learning. In accordance with aspects of the present disclosure, a training set of data is accessed. A preprocessing query specifying a set of preprocessing parameter values that indicate a manner in which to preprocess the training set of data is received. Based on the preprocessing query, a preprocessing operation is performed to preprocess the training set of data in accordance with the set of preprocessing parameter values to obtain a set of preprocessed data. The set of preprocessed data can be provided for presentation as a preview. Based on an acceptance of the set of preprocessed data, the set of preprocessed data is used to train a machine learning model that can be subsequently used to predict data.Type: GrantFiled: October 27, 2022Date of Patent: April 16, 2024Assignee: Splunk Inc.Inventors: Manish Sainani, Sergey Slepian, Di Lu, Adam Oliner, Jacob Leverich, Iryna Vogler-Ivashchanka, Iman Makaremi
-
Patent number: 11921799Abstract: Operational machine components of an information technology (IT) or other microprocessor- or microcontroller-permeated environment generate disparate forms of machine data. Network connections are established between these components and processors of an automatic data intake and query system (DIQS). The DIQS conducts network transactions on a periodic and/or continuous basis with the machine components to receive the disparate data and ingest certain of the data as measurement entries of a DIQS metrics datastore that is searchable for DIQS query processing. The DIQS may receive search queries to process against the received and ingested data via an exposed network interface. In one example embodiment, a query building component conducts a user interface using a network attached client device. The query building component may elicit search criteria via the user interface using a natural language interface, construct a proper query therefrom, and present new information based on results returned from the DIQS.Type: GrantFiled: January 31, 2023Date of Patent: March 5, 2024Assignee: Splunk Inc.Inventors: Iman Makaremi, Gyanendra Rana, Iryna Vogler-Ivashchanka, Adam Oliner, Harsh Keswani, Manish Sainani, Alexander Kim
-
Patent number: 11720824Abstract: Techniques are described for providing a machine learning (ML) data analytics application including guided ML workflows that facilitate the end-to-end training and use of various types of ML models, where such guided workflows may also be referred to as ML “experiments.” One such model is an outlier detection model to assist in the monitoring of computer network traffic and computer performance. For example, the ML data analytics application may generate an outlier detection model using user-identified data from a data source and parameter information. The generates outlier detection model can include distribution functions of distribution types selected from a plurality of distribution types by a distribution fitting algorithm.Type: GrantFiled: October 19, 2022Date of Patent: August 8, 2023Assignee: Splunk Inc.Inventors: Iryna Vogler-Ivashchanka, Iman Makaremi
-
Publication number: 20230237094Abstract: Systems and methods are described for processing ingested data in an asynchronous manner as the data is being ingested to detect potential anomalies. For example, one or more streaming data processors can convert data as the data is ingested into a comparable data structure, determine whether the comparable data structure should be assigned to an existing data pattern or a new data pattern, and optionally update a characteristic of the data pattern to which the comparable data structure is assigned. The streaming data processor(s) can perform these operations automatically in real-time or in periodic batches. Once one or more comparable data structures have been assigned to one or more data patterns, the streaming data processor(s) can analyze the comparable data structures assigned to a particular data pattern to determine whether any of the comparable data structures appear to be anomalous.Type: ApplicationFiled: March 27, 2023Publication date: July 27, 2023Inventors: Ram Sriharsha, Kristal Lyn Curtis, Iryna Vogler-Ivashchanka, Clark Eugene Mullen
-
Patent number: 11615101Abstract: Systems and methods are described for processing ingested data in an asynchronous manner as the data is being ingested to detect potential anomalies. For example, one or more streaming data processors can convert data as the data is ingested into a comparable data structure, determine whether the comparable data structure should be assigned to an existing data pattern or a new data pattern, and optionally update a characteristic of the data pattern to which the comparable data structure is assigned. The streaming data processor(s) can perform these operations automatically in real-time or in periodic batches. Once one or more comparable data structures have been assigned to one or more data patterns, the streaming data processor(s) can analyze the comparable data structures assigned to a particular data pattern to determine whether any of the comparable data structures appear to be anomalous.Type: GrantFiled: January 31, 2020Date of Patent: March 28, 2023Assignee: Splunk Inc.Inventors: Ram Sriharsha, Kristal Lyn Curtis, Iryna Vogler-Ivashchanka, Clark Eugene Mullen
-
Patent number: 11593443Abstract: Operational machine components of an information technology (IT) or other microprocessor- or microcontroller-permeated environment generate disparate forms of machine data. Network connections are established between these components and processors of an automatic data intake and query system (DIQS). The DIQS conducts network transactions on a periodic and/or continuous basis with the machine components to receive the disparate data and ingest certain of the data as measurement entries of a DIQS metrics datastore that is searchable for DIQS query processing. The DIQS may receive search queries to process against the received and ingested data via an exposed network interface. In one example embodiment, a query building component conducts a user interface using a network attached client device. The query building component may elicit search criteria via the user interface using a natural language interface, construct a proper query therefrom, and present new information based on results returned from the DIQS.Type: GrantFiled: September 30, 2021Date of Patent: February 28, 2023Assignee: SPLUNK Inc.Inventors: Iman Makaremi, Gyanendra Rana, Iryna Vogler-Ivashchanka, Adam Oliner, Harsh Keswani, Manish Sainani, Alexander Kim
-
Patent number: 11574242Abstract: Techniques are described for providing a ML data analytics application including guided ML workflows that facilitate the end-to-end training and use of various types of ML models, where such guided workflows may also be referred to as ML “experiments.” For example, the ML data analytics application may enable users to create experiments related to prediction of numeric fields (for example, using linear regression techniques), predicting categorical fields (for example, using logistic regression), detecting numerical outliers (for example, using various distribution statistics), detecting categorical outliers (for example, using probabilistic statistics), forecasting time series data, and clustering numeric events (for example, using k-means, density-based spatial clustering of applications with noise (DBSCAN), spectral clustering, or other techniques), among other possible uses of various types of ML models to analyze data.Type: GrantFiled: April 30, 2019Date of Patent: February 7, 2023Assignee: Splunk Inc.Inventors: Cory Eugene Burke, Gyanendra Rana, Sergey Slepian, Andrew Stein, Iryna Vogler-Ivashchanka
-
Patent number: 11537942Abstract: Techniques are described for providing a machine learning (ML) data analytics application including guided ML workflows that facilitate the end-to-end training and use of various types of ML models, where such guided workflows may also be referred to as ML “experiments.” One such model is an outlier detection model to assist in the monitoring of computer network traffic and computer performance. For example, the ML data analytics application may generate an outlier detection model using user-identified data from a data source and parameter information. The generates outlier detection model can include distribution functions of distribution types selected from a plurality of distribution types by a distribution fitting algorithm.Type: GrantFiled: July 31, 2019Date of Patent: December 27, 2022Assignee: Splunk Inc.Inventors: Iryna Vogler-Ivashchanka, Iman Makaremi
-
Patent number: 11514278Abstract: Embodiments of the present invention are directed to facilitating data preprocessing for machine learning. In accordance with aspects of the present disclosure, a training set of data is accessed. A preprocessing query specifying a set of preprocessing parameter values that indicate a manner in which to preprocess the training set of data is received. Based on the preprocessing query, a preprocessing operation is performed to preprocess the training set of data in accordance with the set of preprocessing parameter values to obtain a set of preprocessed data. The set of preprocessed data can be provided for presentation as a preview. Based on an acceptance of the set of preprocessed data, the set of preprocessed data is used to train a machine learning model that can be subsequently used to predict data.Type: GrantFiled: September 23, 2020Date of Patent: November 29, 2022Assignee: SPLUNK Inc.Inventors: Manish Sainani, Sergey Slepian, Di Lu, Adam Oliner, Jacob Leverich, Iryna Vogler-Ivashchanka, Iman Makaremi
-
Patent number: 11188600Abstract: Operational machine components of an information technology (IT) or other microprocessor- or microcontroller-permeated environment generate disparate forms of machine data. Network connections are established between these components and processors of an automatic data intake and query system (DIQS). The DIQS conducts network transactions on a periodic and/or continuous basis with the machine components to receive the disparate data and ingest certain of the data as measurement entries of a DIQS metrics datastore that is searchable for DIQS query processing. The DIQS may receive search queries to process against the received and ingested data via an exposed network interface. In one example embodiment, a query building component conducts a user interface using a network attached client device. The query building component may elicit search criteria via the user interface using a natural language interface, construct a proper query therefrom, and present new information based on results returned from the DIQS.Type: GrantFiled: June 17, 2020Date of Patent: November 30, 2021Assignee: SPLUNK INC.Inventors: Iman Makaremi, Gyanendra Rana, Iryna Vogler-Ivashchanka, Adam Oliner, Harsh Keswani, Manish Sainani, Alexander Kim
-
Publication number: 20210117416Abstract: Systems and methods are described for processing ingested data in an asynchronous manner as the data is being ingested to detect potential anomalies. For example, one or more streaming data processors can convert data as the data is ingested into a comparable data structure, determine whether the comparable data structure should be assigned to an existing data pattern or a new data pattern, and optionally update a characteristic of the data pattern to which the comparable data structure is assigned. The streaming data processor(s) can perform these operations automatically in real-time or in periodic batches. Once one or more comparable data structures have been assigned to one or more data patterns, the streaming data processor(s) can analyze the comparable data structures assigned to a particular data pattern to determine whether any of the comparable data structures appear to be anomalous.Type: ApplicationFiled: January 31, 2020Publication date: April 22, 2021Inventors: Ram Sriharsha, Kristal Lyn Curtis, Iryna Vogler-Ivashchanka, Clark Eugene Mullen
-
Publication number: 20210004651Abstract: Embodiments of the present invention are directed to facilitating data preprocessing for machine learning. In accordance with aspects of the present disclosure, a training set of data is accessed. A preprocessing query specifying a set of preprocessing parameter values that indicate a manner in which to preprocess the training set of data is received. Based on the preprocessing query, a preprocessing operation is performed to preprocess the training set of data in accordance with the set of preprocessing parameter values to obtain a set of preprocessed data. The set of preprocessed data can be provided for presentation as a preview. Based on an acceptance of the set of preprocessed data, the set of preprocessed data is used to train a machine learning model that can be subsequently used to predict data.Type: ApplicationFiled: September 23, 2020Publication date: January 7, 2021Inventors: Manish Sainani, Sergey Slepian, Di Lu, Adam Oliner, Jacob Leverich, Iryna Vogler-Ivashchanka, Iman Makaremi
-
Patent number: 10817757Abstract: Embodiments of the present invention are directed to facilitating data preprocessing for machine learning. In accordance with aspects of the present disclosure, a training set of data is accessed. A preprocessing query specifying a set of preprocessing parameter values that indicate a manner in which to preprocess the training set of data is received. Based on the preprocessing query, a preprocessing operation is performed to preprocess the training set of data in accordance with the set of preprocessing parameter values to obtain a set of preprocessed data. The set of preprocessed data can be provided for presentation as a preview. Based on an acceptance of the set of preprocessed data, the set of preprocessed data is used to train a machine learning model that can be subsequently used to predict data.Type: GrantFiled: July 31, 2017Date of Patent: October 27, 2020Assignee: SPLUNK INC.Inventors: Manish Sainani, Sergey Slepian, Di Lu, Adam Oliner, Jacob Leverich, Iryna Vogler-Ivashchanka, Iman Makaremi
-
Publication number: 20200320145Abstract: Operational machine components of an information technology (IT) or other microprocessor- or microcontroller-permeated environment generate disparate forms of machine data. Network connections are established between these components and processors of an automatic data intake and query system (DIQS). The DIQS conducts network transactions on a periodic and/or continuous basis with the machine components to receive the disparate data and ingest certain of the data as measurement entries of a DIQS metrics datastore that is searchable for DIQS query processing. The DIQS may receive search queries to process against the received and ingested data via an exposed network interface. In one example embodiment, a query building component conducts a user interface using a network attached client device. The query building component may elicit search criteria via the user interface using a natural language interface, construct a proper query therefrom, and present new information based on results returned from the DIQS.Type: ApplicationFiled: June 17, 2020Publication date: October 8, 2020Inventors: Iman Makaremi, Gyanendra Rana, Iryna Vogler-Ivashchanka, Adam Oliner, Harsh Keswani, Manish Sainani, Alexander Kim
-
Patent number: 10726079Abstract: Operational machine components of an information technology (IT) or other microprocessor- or microcontroller-permeated environment generate disparate forms of machine data. Network connections are established between these components and processors of an automatic data intake and query system (DIQS). The DIQS conducts network transactions on a periodic and/or continuous basis with the machine components to receive the disparate data and ingest certain of the data as measurement entries of a DIQS metrics datastore that is searchable for DIQS query processing. The DIQS may receive search queries to process against the received and ingested data via an exposed network interface. In one example embodiment, a query building component conducts a user interface using a network attached client device. The query building component may elicit search criteria via the user interface using a natural language interface, construct a proper query therefrom, and present new information based on results returned from the DIQS.Type: GrantFiled: January 30, 2018Date of Patent: July 28, 2020Assignee: SPLUNK INC.Inventors: Iman Makaremi, Gyanendra Rana, Iryna Vogler-Ivashchanka, Adam Oliner, Harsh Keswani, Manish Sainani, Alexander Kim
-
Publication number: 20190236210Abstract: Operational machine components of an information technology (IT) or other microprocessor- or microcontroller-permeated environment generate disparate forms of machine data. Network connections are established between these components and processors of an automatic data intake and query system (DIQS). The DIQS conducts network transactions on a periodic and/or continuous basis with the machine components to receive the disparate data and ingest certain of the data as measurement entries of a DIQS metrics datastore that is searchable for DIQS query processing. The DIQS may receive search queries to process against the received and ingested data via an exposed network interface. In one example embodiment, a query building component conducts a user interface using a network attached client device. The query building component may elicit search criteria via the user interface using a natural language interface, construct a proper query therefrom, and present new information based on results returned from the DIQS.Type: ApplicationFiled: January 30, 2018Publication date: August 1, 2019Inventors: Iman Makaremi, Gyanendra Rana, Iryna Vogler-Ivashchanka, Adam Oliner, Harsh Keswani, Manish Sainani, Alexander Kim
-
Publication number: 20190034767Abstract: Embodiments of the present invention are directed to facilitating data preprocessing for machine learning. In accordance with aspects of the present disclosure, a training set of data is accessed. A preprocessing query specifying a set of preprocessing parameter values that indicate a manner in which to preprocess the training set of data is received. Based on the preprocessing query, a preprocessing operation is performed to preprocess the training set of data in accordance with the set of preprocessing parameter values to obtain a set of preprocessed data. The set of preprocessed data can be provided for presentation as a preview. Based on an acceptance of the set of preprocessed data, the set of preprocessed data is used to train a machine learning model that can be subsequently used to predict data.Type: ApplicationFiled: July 31, 2017Publication date: January 31, 2019Inventors: Manish Sainani, Sergey Slepian, Di Lu, Adam Oliner, Jacob Leverich, Iryna Vogler-Ivashchanka, Iman Makaremi
-
Patent number: D946024Type: GrantFiled: October 19, 2020Date of Patent: March 15, 2022Assignee: SPLUNK Inc.Inventors: Iryna Vogler-Ivashchanka, John C. Reed, Korryn Resetar, Amir Malekpour, FNU Sridhar Vinay
-
Patent number: D946025Type: GrantFiled: October 19, 2020Date of Patent: March 15, 2022Assignee: SPLUNK Inc.Inventors: Iryna Vogler-Ivashchanka, John C. Reed, Korryn Resetar, Amir Malekpour, FNU Sridhar Vinay
-
Patent number: D946026Type: GrantFiled: October 19, 2020Date of Patent: March 15, 2022Assignee: SPLUNK Inc.Inventors: Iryna Vogler-Ivashchanka, John C. Reed, Korryn Resetar, Amir Malekpour, FNU Sridhar Vinay