Splunk Inc.

Cisco Technology, Inc.

Kristal Curtis

Adam Jamison Oliner

William Deaderick

Poonam Yadav

Ram Sriharsha

Abraham Starosta

Tanner Gilligan

Ross Andrew Lazerowitz

Nghi Huu Nguyen

Steve Yu Zhang

Archana Sulochana Ganapathi

Eric Sammer

Iman Makaremi

Zhaohui Wang

Sichen Zhong

Iryna Vogler-Ivashchanka

Clark Eugene Mullen

Chandrima Sarkar

Ralph Donald Thompson, Iii

Houwu Bai

Francis Beckert

Wei Jie Gao

Om Rajyaguru

Joseph Ari Ross

Alexander Nicholas Johnson

Alexander Stojanovic

Aleksander Stojanovic

Alexander Johnson

Implementations of the disclosure pertain to detecting mislabeling of a source type assigned to machine data through utilization of machine learning techniques. Operations of a computerized method for detecting the mislabeling include receiving machine data that has been assigned an initial source type upon receipt by a data intake and query system and parsing the data block into a plurality of events based on a source type definition of the initial source type. Further operations include generating a data representation of a first event being a portion of the machine data and is associated with a point in time, determining a predicted source type of the first event by at least analyzing the data representation through machine learning techniques, and performing a comparison between the predicted source type and the initial source type thereby determining whether the source type of the event was initially mislabeled.

Detecting source type mislabeling of machine data through determining prediction of source type through machine learning techniques

Computerized methodologies are disclosed that are directed to detecting anomalies within a time-series data set. A first aspect of the anomaly detection process includes analyzing the regularity of the data points of the time-series data set and determining whether a data aggregation process is to be performed based on the regularity of the data points, which results in a time-series data set having data points occurring at regular intervals. A seasonality pattern may be determined for the time-series data set, where a silhouette score is computed to measure the quality of the fit of the seasonality pattern to the time-series data. The silhouette score may be compared to a threshold and based on the comparison, the seasonality pattern or a set of heuristics may be utilized in an anomaly detection process. When the seasonality pattern is utilized, the seasonality pattern may be utilized to generate thresholds indicating anomalous behavior.

Anomaly detection system and method for implementing a data regularity check and adaptive thresholding

Computerized methodologies are disclosed that are directed to detecting anomalies within a time-series data set. An aspect of the anomaly detection process includes determining one or more seasonality patterns that correspond to a specific time-series data set by evaluating a set of candidate seasonality patterns (e.g., hourly, daily, weekly, day-start off-sets, etc.). The evaluation of a candidate seasonality pattern may include dividing the time-series data set into a collection of subsequences based on the particular candidate seasonality pattern. Further, the collection of subsequences may be divided into clusters and a silhouette score may be computed to measure the clustering quality of the candidate seasonality pattern. In some instances, the candidate seasonality pattern having the highest silhouette score is selected and utilized in anomaly detection process. In other instances, a plurality of seasonality patterns may be combined forming a time policy, where the time policy is utilized in anomaly detection process.

Anomaly detection through clustering of time-series data subsequences and determination of adaptive thresholding

Systems and methods are described for extracting data fields from logs ingested in a data processing pipeline or otherwise stored. For example, a log can be applied as an input to an artificial intelligence model trained to infer a log sourcetype of logs, and the artificial intelligence model can output an inferred log sourcetype of the log. The inferred log sourcetype can be used to select another artificial intelligence model trained to extract data fields from logs having the inferred log sourcetype, and the log can then be applied as an input to the other artificial intelligence model. The other artificial intelligence model may then output one or more data fields extracted from the log.

Data field extraction by a data intake and query system

A search assistant engine is described that integrates with a data intake and query system and provides an intuitive user interface to assist a user in searching and evaluating indexed event data. Additionally, the search assistant engine provides logic to intelligently provide data to the user through the user interface such as determining fields of events likely to be of interest based on determining a mutual information score for each field and determining groups of related fields based on determining a mutual information score for each field grouping. Some implementations utilize machine learning techniques in certain analyses such as when clustering events and determining an event templates for each cluster. Additionally, the search assistant engine may import terms or characters from user interaction into predetermined search query templates to generate tailored search query for the user.

Exploratory data analysis system for generation of wildcards within log templates through log clustering and analysis thereof

Systems and methods are disclosed that are directed to improving the prioritization, display, and viewing of system alerts through the use of machine learning techniques to group the alerts and further to prioritize the groupings. Additionally, a graphical user interface is generated that illustrates the prioritized listing of the plurality of groupings. Thus, a system administrator or other user receives an improved experience as the number of notifications provided to the system administrator are reduced due to the grouping of individual alerts into related groupings and further due to the prioritization of the groupings. Previously, or in current technology, system alerts may be automatically generated and provided immediately to a system administrator. In some instances, any advantage of detecting system errors or system monitoring provided by the alerts is negated by the vast number of alerts and provision of minimally important alerts in a manner that concealed more important alerts.

Machine-learning based prioritization of alert groupings

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.

Processing ingested data to identify anomalies

Implementations of this disclosure provide an anomaly detection system and methods of performing anomaly detection on a time-series dataset. The anomaly detection may include utilization of a forecasting machine learning algorithm to obtain a prediction of points of the dataset and comparing the predicted value of a point in the dataset with the actual value to determine an error value associated with that point. Additionally, the anomaly detection may include determination of a sensitivity threshold that impacts whether points within the dataset associated with certain error values are flagged as anomalies. The forecasting machine learning algorithm may implement a seasonality component determination process that accounts for seasonality or patterns in the dataset. A search query statement may be automatically generated through importing the sensitivity threshold into a predetermined search query statement that implements that forecasting machine learning algorithm.

Hyperparameter tuning for anomaly detection service implementing machine learning forecasting

Implementations of this disclosure provide a search assistant engine that integrates with a data intake and query system and provides an intuitive user interface to assist a user in searching and evaluating indexed event data. Additionally, the search assistant engine provides logic to intelligently provide data to the user through the user interface such as determining fields of events likely to be of interest based on determining a mutual information score for each field and determining groups of related fields based on determining a mutual information score for each field grouping. Some implementations utilize machine learning techniques in certain analyses such as when clustering events and determining an event templates for each cluster. Additionally, the search assistant engine may import terms or characters from user interaction into predetermined search query templates to generate tailored search query for the user.

Exploratory data analysis system for automated generation of search queries using machine learning techniques to identify certain log fields and correlation thereof

A computerized method is disclosed that includes operations of obtaining a data set, selecting candidate parameter pairs to be analyzed, wherein the candidate parameter pairs include a window length and a sensitivity multiplier, and wherein the window length is a number of data points, performing an anomaly detection process for each candidate parameter pair including importing each candidate parameter pair into a predetermined search query thereby generating a set of populated predetermined search queries, wherein the predetermined search query is configured to perform the anomaly detection process, executing each search query of the set of populated predetermined search queries on the data set to obtain a set of anomaly detection results, and scoring each anomaly detection result by applying a set of heuristics to the set of the anomaly detection results, and generating an auto-tuned search query by selecting a first candidate parameter pair based on a score of each of the set of anomaly detection results and importing the first candidate parameter pair into the predetermined search query.

System and method for automated determination of search query parameters for anomaly detection

Machine data of an operating environment is conveyed by a network to a data intake and query system (DIQS) which reflects the machine data as timestamped entries of a field-searchable datastore. Monitoring functionality may search the machine data to identify notable event instances. A notable event processing system correlates the notable event instance to one or more triaging models which are executed against the notable event to produce a modeled result. Information of the received notable event and the modeled results are combined into an enhanced representation of a notable event instance. The enhanced representation conditions downstream processing to automatically perform or assist triaging of notable event instances to optimize application of computing resources to highest priority conditions in the operating environment.

Triage model in service monitoring system

As described herein, a portion of machine data of a message may be analyzed to infer, using an inference model, a sourcetype of the message. The portion of machine data may be generated by one or more components in an information technology environment. Based on the inference, a set of extraction rules associated with the sourcetype may be selected. Each extraction rule may define criteria for identifying a sub-portion of text from the portion of machine data of the message to produce a value. The set of extraction rules may be applied to the portion of machine data of the message to produce a result set that indicates a number of values identified using the set of extraction rules. Based on the result set, at least one action may be performed on one or more of inference data associated with the inference model and one or more messages.

Data stream generation based on sourcetypes associated with messages

Embodiments of the present invention are directed to identifying related data, in particular, data associated with different source types. In embodiments, a first source type related to a second source type associated with a search query is identified. Field set pairs are identified from a first data set associated with the first source type and a second data set associated with the second source type. Each field set pair can include one field set associated with the first source type and another field set associated with the second source type. For each field set pair, an extent of similarity is determined between the corresponding field sets. Based on the extent of similarities between the corresponding field sets, at least one pair of related field sets is identified. An indication of the at least one pair of related field sets is provided, for example, for presentation to a user.

Identifying related field sets based on related source types

Feedback on inferred sourcetypes

A computerized method is disclosed for generating a prioritized listing of alerts based on scoring by a machine learning model and retraining the model based on user feedback. Operations of the method include receiving a plurality of alerts, generating a score for each of the plurality of alerts through evaluation of each of the plurality of alerts by a machine learning model, generating a prioritized listing of the plurality of alerts based on the generated scores, receiving user feedback on the prioritized listing, retraining the machine learning model based on the user feedback by generating a set of labeled alert pairs, wherein a labeled alert pair includes a first alert, a second alert, and an indication as to which of the first alert or the second alert is a higher priority in accordance with the user feedback, and evaluating subsequently received alerts with the retrained machine learning model.

Growing community of inventors

San Francisco, CA, United States of America

Kristal Curtis