Abstract: Described are techniques for automated anomaly detection including a technique comprising training an ensemble of deep learning models using clustered time series training data from numerous components in an Information Technology (IT) infrastructure. The technique further comprises inputting aggregated time series data to the ensemble of deep learning models and identifying anomalies in the aggregated time series data based on respective portions of the aggregated time series data that are indicated as anomalous by a majority of deep learning models in the ensemble of deep learning models. The technique further comprises grouping the anomalies according to relationships between the anomalies and performing a mitigation action in response to grouping the anomalies.

Abstract: Methods, systems, and apparatus, including computer programs stored on computer-readable media, for integrating electronic card display at a client via a software development kit (SDK) provided at one or more data servers are disclosed. A client-side application such as a web browser may request the SDK based on a code snippet included in a data file, such as a HyperText Markup Language (HTML) file for a web page. Once the SDK is received at the client, the client-side application may perform various functionalities enabled by the SDK, including determining terms in the data file that match keywords associated with electronic cards, requesting and receiving electronic card rendering data associated with the electronic cards, and modifying a display generated based on the data file to display an electronic card, upon detecting a trigger event in relation to a term within the web page that corresponds to the electronic card.

Abstract: Methods, systems, and devices supporting managing a data processing flow are described. A device (e.g., an application server) may host a cloud-based collaboration application, such as an interactive document application. The device may receive an instance of a data processing flow for a flow application based on a first user input to the cloud-based collaboration application. The device may receive the instance of the data processing flow from a source device hosting the flow application. The device may embed the flow application in the cloud-based collaboration application. The device may then receive user inputs to the data processing flow from multiple users collaborating on the same flow in the cloud-based collaboration application. Based on the user inputs, the device may modify the instance of the data processing flow and transmit the modified instance back to the source device to synchronize the data processing flow in the flow application.

Abstract: Various embodiments, methods and systems for implementing a distributed computing system scene assembly engine are provided. Initially, a selection of a first synthetic data asset and a selection of a second synthetic data asset are received from a distributed synthetic data as a service (SDaaS) integrated development environment (IDE). A synthetic data asset is associated with asset-variation parameters and scene-variation parameters, the asset-variation parameters and scene-variation parameters are programmable for machine-learning. Values for generating a synthetic data scene are received. The values correspond to asset-variation parameters or scene-variation parameters. Based on the values, the synthetic data scene is generated using the first synthetic data asset and the second synthetic data asset.

Abstract: Provided is a system and method for detecting a SQL command from a natural language input using neural networks which works even when the SQL command has not been seen before by the neural networks. In one example, the method may include storing a candidate set comprising structured query language (SQL) templates paired with respective text values, reducing, via a first predictive network, the candidate set into a subset of candidates based on a natural language input and the text values included in the candidate set, selecting, via a second predictive network, an SQL template from among the subset of candidates based on the natural language input and text values included in the subset of candidates, and determining a SQL command that corresponds to the natural language input based on the selected SQL template and content from the natural language input.

Abstract: Systems and methods for multi-source reference class identification, base rate calculation, and prediction are disclosed. The systems and method can guide on, then elicit, information about reference class identification on a case-by-case basis, connects to a database in order to calculate historical base rates according to user reference class selections, and collect additional quantitative and qualitative information from users. The systems and methods can then generate predictive estimates based on the combination of the inputs by one or more users.

Abstract: Methods, systems, and techniques for performing a facet search include receiving facet search commencement user input indicating that a search for a facet is to commence; in response to the facet search commencement user input, searching one or more video recordings for the facet; and displaying, on a display, facet image search results depicting the facet, wherein the facet image search results are selected from the one or more video recordings. An artificial neural network may be used for the facet search, and that network may be trained by generating a facet image training set that comprises training images, with the training images depicting a type of facet common to the training images; and training, by using the facet image training set, that neural network to classify the type of facet when a sample image comprising the type of facet is input to that network.

Abstract: An inference system applies a machine-learning transformer model to a batch of requests with variable input length or variable target length or variable internal state length by selectively batching a subset of operations in the transformer model but processing requests in the batch individually for a subset of operations in the transformer model. In one embodiment, the operation to be processed individually is an attention operation of an encoder or a decoder of the transformer model. By selective batching, the inference system can allow batching operations to be performed for a batch of requests with variable input or target length or internal state length to utilize the parallel computation capabilities of hardware accelerators while preventing unnecessary computations that occur for workarounds that restrain the data of a batch of requests to a same length.

Abstract: Supervised partitioning is used to perform record matching. A request to identify matches between records is received. A graph representation that indicates similarities between the records is partitioned and an evaluation of the partitioning is performed according to a supervised machine learning technique to generate a confidence value in the partitioning. An indication of equivalent records according to the partitioning and the confidence value of the partitioning may be provided.

Abstract: A method of processing a database configuration parameter, performed by a computer device, is provided. The method includes: (a) obtaining a current configuration parameter of a database; (b) determining a current database state indicator value corresponding to the current configuration parameter; (c) generating, by using a parameter adjustment model, parameter adjustment data based on the current database state indicator value; (d) adjusting the current configuration parameter based on the parameter adjustment data, to obtain a new configuration parameter; (e) updating the current configuration parameter to the new configuration parameter; and (f) repeating operations (b)-(e) until an adjustment termination condition is met, to obtain the updated current configuration parameter as a recommended configuration parameter upon adjustment termination.

Abstract: Systems and methods for performing data protection operations including replication management or data copy operations. Agent-less data protections are performed. A management server is configured to perform data operations on a production host without installing an agent on the production host. A driver is adapted to aid in performing the data protection operations and communications between the management server and the driver such as commands are achieved via a storage array.

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for utilizing focused aggregation of classification model outputs to classify variable length documents. For instance, the disclosed systems can utilize a classification model to determine category scores for segments from an electronic document. Furthermore, the disclosed systems can identify positive trigger segments from the segments by comparing the category scores to a threshold category score. Moreover, the disclosed systems can determine a positive trigger ratio for the target category based on the positive trigger segments and the segments. Additionally, the disclosed systems can generate an aggregated category score for the electronic document from the positive trigger segments (when the positive trigger ratio satisfies a threshold positive trigger ratio) and distribute the electronic documents to client devices based on the aggregated category score.

Abstract: A query processing system generates and employs a hybrid inverted index of predicates for predicate statement evaluation. The query processing system converts a collection of predicate statements to two parts, a matrix and a set of reduced predicate statements. The query processing system then generates a hybrid inverted index that maps values for variables to predicates from the matrix and the reduced predicate statements that evaluate to true for corresponding values. When querying data, the query processing system performs a lookup on the hybrid inverted index to identify predicates from the matrix and reduced predicate statements that evaluate to true for values of variables for the data. The query processing system identifies predicate statements that evaluate to true by evaluating the matrix and reduced predicate statements using treating predicates identified from the hybrid inverted index as true.

Abstract: A method for scheduling a user transport comprising receiving, at a server, a plurality of communications from a client device, interrogating, at the server, each communication of the plurality of communications, initiating, at the server, a transport request as a function of a user request, inputting, at the server, the terminus datum in the transport request as a function of a first selected communication, inputting, at the server, a first selected unit identifier in the transport request, and generating, at the server, a verification datum as a function of a user submission datum.

Abstract: A system for queuing deduplication backup operations comprises an input interface and a processor. The input interface configured to receive a request to perform a deduplication backup operation. The processor is configured to: a) determine a backup operation queue; b) determine whether the deduplication backup operation is at the head of the backup operation queue; c) determine whether the deduplication backup operation is qualified to be executed; and d) in the event the deduplication backup operation is qualified to be executed, execute the deduplication backup operation.

Abstract: A method includes integrating a file system recovery log layer in a file system. The file system buffers data in a cyclical manner, and transforms all incoming random requests into a series of synchronous sequential updates. The method determines a length value of a write transaction byte-range for a received write transaction. Upon the length value exceeding a threshold value, data for the write transaction byte-range is written to permanent storage in the file system. Upon the length value being less than the threshold value, the data for the write transaction byte-range is written to a recovery log that is stored in the file system recovery log layer. The threshold value is changed dynamically while the file system is mounted.

Abstract: A method includes creating a digital description of the well construction system, wherein the digital description of the well construction system describes the locational relationship of components in the well construction system, collecting multiple types of data from a well construction system, and tagging the collected data with an identification indicating at least one of a location of a source of collected data and a component in the well construction system from which the data is collected. The multiple types of data include sensor data collected from one or more sensors disposed along the well construction system and operational state data indicating an on/off status of one or more components in the well construction system.

Abstract: Techniques are described herein for training and/or utilizing a query canonicalization system. In various implementations, a query canonicalization system can include a classification model and a canonicalization model. A classification model can be used to determine if a search query is well-formed. Additionally or alternatively, a canonicalization model can be used to determine a well-formed variant of a search query in response to determining a search query is not well-formed. In various implementations, a canonicalization model portion of a query canonicalization system can be a sequence to sequence model.

Abstract: Techniques are described for enabling analysts and other users of an IT operations platform to identify certain data objects managed by the platform (for example, events, files, notes, actions results, etc.) as “evidence” when such data objects are believed to be of particular significance to an investigation or other matter. For example, an event generated based on data ingested from an anti-virus service and representing a security-related incident might include artifacts indicating an asset identifier, a hash value of a suspected malicious file, a file path on the infected endpoint, and so forth. An analyst can use various interfaces and interface elements of an IT operations platform to indicate which of such events and/or artifacts, if any, represent evidence in the context of the investigation that the analyst is conducting. In response, the IT operations platform can perform various automated actions.

Abstract: A method for organizing and searching objects from a plurality of databases includes querying an attribute of each entry stored in the plurality of databases; assigning a memory value for each of the attributes retrieved from each of the objects stored in the plurality of databases and storing the memory values for each of the attributes in a cache. At a client device, a search query is received and it is determined if the search query contains an attribute of the entry to be searched. Upon positive determination, a search is performed at the cache using the attribute contained in the search query; and upon negative determination, a search for the entry is performed at the plurality of databases.