Abstract: Systems and methods include causing presentation of a first cluster in association with an event of the first cluster, the first cluster from a first set of clusters of events. Each event includes a time stamp and event data. Based on the presentation of the first cluster, an extraction rule corresponding to the event of the first cluster is received from a user. Similarities in the event data between the events are determined based on the received extraction rule. The events are grouped into a second set of clusters based on the determined similarities. Presentation is caused of a second cluster in association with an event of the second cluster, where the second cluster is from the second set of clusters.

Abstract: A modular visualization framework registers definitions for a variety of visualization types. The definitions are tagged with visualization characteristics. During a working session, likely interactive, a user identifies a search query used to produce data to be visualized. The working context, including the search query and data produced by its execution, is tagged for its visualization characteristics. Information about the working context, including its visualization characteristics, is then used to produce a customized list of candidates suited for the working context from which the user may select a visualization type.

Abstract: Disclosed herein is a computer-implemented tool that facilitates data analysis by use of machine learning (ML) techniques. The tool cooperates with a data intake and query system and provides a graphical user interface (GUI) that enables a user to train and apply a variety of different ML models on user-selected datasets of stored machine data. The tool can provide active guidance to the user, to help the user choose data analysis paths that are likely to produce useful results and to avoid data analysis paths that are less likely to produce useful results.

Abstract: 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.

Abstract: Network connections are established between machines of an operating environment to be monitored and a server group of a data intake and query system (DIQS). Data reflecting machine and component operations of the environment is conveyed via the network to the DIQS where it is reflected as timestamped entries in a field-searchable datastore. Monitoring components may search the datastore and identify and record instances of notable events. Triaging models are selectively applied against the notable event instances to produce an enhanced notable event instance representation with modeled results effective to automatically perform or assist in triaging the notable events so they are dispatched in an optimal, effective, and efficient, manner.

Abstract: Machine data reflecting operation of a monitored system is ingested and made available for search by a data intake and query system (DIQS). Ingested data includes log data entries produced by an application that represent low-level instances of user interface or interaction events. Inference processing generates a new collection of data instances that each identifies a higher-level task performed by a user in a sequence of the low-level events without regard to any explicit task affiliation data component of the low-level instances. Information for the task may include a measure of confidence that each low-level event of the sequence is properly associated with the task. Tasks of the new collection may be advantageously visualized and included in downstream processing.

Abstract: In some implementations, sequences of time series values determined from machine data are obtained. Each sequence corresponds to a respective time series. A plurality of predictive models is generated for a first time series from the sequences of time series values. Each predictive model is to generate predicted values associated with the first time series using values of a second time series. For each of the plurality of predictive models, an error is determined between the corresponding predicted values and values associated with the first time series. A predictive model is selected for anomaly detection based on the determined error of the predictive model. Transmission is caused of an indication of an anomaly detected using the selected predictive model.

Abstract: Systems and methods include causing presentation of a first cluster in association with an event of the first cluster, the first cluster from a first set of clusters of events. Each event includes a time stamp and event data. Based on the presentation of the first cluster, an extraction rule corresponding to the event of the first cluster is received from a user. Similarities in the event data between the events are determined based on the received extraction rule. The events are grouped into a second set of clusters based on the determined similarities. Presentation is caused of a second cluster in association with an event of the second cluster, where the second cluster is from the second set of clusters.

Abstract: In some implementations, sequences of time series values determined from machine data are obtained. Each sequence corresponds to a respective time series. A plurality of predictive models is generated for a first time series from the sequences of time series values. Each predictive model is to generate predicted values associated with the first time series using values of a second time series. For each of the plurality of predictive models, an error is determined between the corresponding predicted values and values associated with the first time series. A predictive model is selected for anomaly detection based on the determined error of the predictive model. Transmission is caused of an indication of an anomaly detected using the selected predictive model.

Abstract: Systems and methods include obtaining a set of events, each event in the set of events comprising a time-stamped portion of raw machine data, the raw machine data produced by one or more components within an information technology or security environment and reflects activity within the information technology or security environment. Thereafter, a first neural network is used to automatically identify variable text to extract as a field from the set of events. An indication of the variable text is provided as a field extraction recommendation, for example, to a user device for presentation to a user.

Abstract: Techniques are disclosed for providing adaptive thresholding technology for Key Performance Indicators (KPIs) that are updated using training data. Adaptive thresholding technology may automatically assign new values or adjust existing values for one or more thresholds of one or more time policies. Assigning threshold values using adaptive thresholding may involve identifying training data (e.g., historical data, simulated data, or example data) for the time frames and analyzing the training data to identify variations within the data (e.g., patterns, distributions, trends). A threshold value may be determined based on the variations and may be assigned to one or more of the thresholds without additional user intervention.

Abstract: A facility for defining an event subtype using examples is described. The facility displays events identified among machine-generated data. The facility receives user input selecting a first subset of the events as examples of an event subtype. In response to receiving the user input, the facility displays a second subset of the events predicted to belong to the event subtype on the basis of the examples of the event subtype.

Abstract: Systems and methods include obtaining a set of events, each event in the set of events comprising a time-stamped portion of raw machine data, the raw machine data produced by one or more components within an information technology or security environment and reflects activity within the information technology or security environment. Thereafter, a first neural network is used to automatically identify variable text to extract as a field from the set of events. An indication of the variable text is provided as a field extraction recommendation, for example, to a user device for presentation to a user.

Abstract: Disclosed herein is a computer-implemented tool that facilitates data analysis by use of machine learning (ML) techniques. The tool cooperates with a data intake and query system and provides a graphical user interface (GUI) that enables a user to train and apply a variety of different ML models on user-selected datasets of stored machine data. The tool can provide active guidance to the user, to help the user choose data analysis paths that are likely to produce useful results and to avoid data analysis paths that are less likely to produce useful results.

Abstract: Disclosed herein is a computer-implemented tool that facilitates data analysis by use of machine learning (ML) techniques. The tool cooperates with a data intake and query system and provides a graphical user interface (GUI) that enables a user to train and apply a variety of different ML models on user-selected datasets of stored machine data. The tool can provide active guidance to the user, to help the user choose data analysis paths that are likely to produce useful results and to avoid data analysis paths that are less likely to produce useful results.

Abstract: Techniques are disclosed for anomaly detection. A search query can be executed over a period of time to produce values for a key performance indicator (KPI), the search query defining the KPI and deriving a value indicative of the performance of a service at a point in time or during a period of time, the value derived from machine data pertaining to one or more entities that provide the service. A graphical user interface (GUI) enabling a user to indicate a sensitivity setting can be displayed. A user input indicating the sensitivity setting can be received via the GUI. Zero or more of the values as anomalies can be identified in consideration of the sensitivity setting indicated by the user input. A GUI including information related to the values identified as anomalies can be caused to be displayed.

Abstract: Disclosed is a technique that can be performed by an electronic device. The technique can include generating timestamped events, where the timestamped events include raw data generated by electronic device. The technique can further include obtaining results by performing a operation on the timestamped events, in accordance with instructions. The technique can further include sending the results or indicia thereof over a network to a server computer system, and receiving back new instructions generated by the server computer system based on the sent results. Lastly, the technique can include performing a new operation on timestamped events including raw data generated based by the electronic device, where the new operation can be performed in accordance with the new instructions to obtain new results.

Abstract: Disclosed is a technique that can be performed by an electronic device. The electronic device can generate time-stamped events, extract training data from the time-stamped events, and sending the training data over a network to a remote computer. The electronic device can receive model data generated by the remote computer from the training data by use of a machine learning process, update a local model of the electronic device based on the received model data, and generate an output by processing locally sourced data of the electronic device with the updated local model.

Abstract: Techniques are disclosed for providing a graphical user interface (GUI) for displaying and configuring adaptive or static thresholds for Key Performance Indicators (KPIs). The GUI may include one or more presentation schedules that may display threshold information associated with time policies. Each presentation schedule may include multiple time slots and span a portion of one or more time cycles. Some of the time slots may be associated with a specific time policy and may have a unifying appearance that distinguishes the time slots from timeslots associated with other time policies. The presentation schedules may arrange the time slots in a time grid arrangement (e.g., calendar grid view) or a graph arrangement with depictions (e.g., points, lines) that may illustrate KPI values and threshold markers that may illustrate the threshold values.

Abstract: Disclosed is a technique that can be performed by an electronic device. The technique can include generating raw data based on inputs to the electronic device, and sending the raw data or data items over a network to a server computer system. The sent raw data or the data items can include training data. The technique can further include receiving global model data from the server computer system over the network. The global model data may have been derived from the training data in accordance with a machine learning process. The technique can further include generating an updated local model by updating a local model associated with the electronic device based on the received global model data, and processing local data based on the updated local model to generate output data. The local data can include raw data or data items generated based on inputs to the electronic device.