Intuit, Inc.

Shreeshankar Chatterjee

Poonguzhali Balasubramanian

Cynthia Joann Osmon

Jason Michael Webb

Daniel Leontin Moise

Vijay Thomas

Tracy Fung

A method may include obtaining, for each period within a time interval, raw performance metric values for a performance metric of a service, encoding the raw performance metric values to generate inferred performance metric values for the performance metric, and selecting a portion of the inferred performance metric values. The portion corresponds to a representative period. The may method further include obtaining a service request for the service, generating a simulated response to the service request, and transmitting the simulated response using the portion of the inferred performance metric values.

Simulating service performance using machine learning

A method includes obtaining a help file including steps for a task and generating a knowledge graph including instructions corresponding to the steps. The method further includes extracting, from a user input of a user, an intent to complete the task. Responsive to extracting the intent to complete the task, obtaining the knowledge graph is obtained. Using the knowledge graph, an instruction of the knowledge graph is presented to perform an action in a workflow to complete the task.

Graphical user interface for conversational task completion

Techniques are disclosed to predict experience degradation in a microservice-based application comprising a plurality of microservices. Quality of service metrics are derived for each node from the historical event log data of nodes forming a plurality of directed acyclic graph (DAG) paths in the multiple-layer nodes. A clustering model clusters the plurality of quality of service metrics according to multiple levels of quality of experience and determines respective value ranges of each quality of service metric for the multiple levels of quality of experience. Each quality of service metric is labeled with one of the multiple levels of quality of service according to the respective value ranges. A support vector machine model predicts various experience degradation events which are expected to occur during the operation of the microservice-based application.

Method and apparatus for predicting experience degradation events in microservice-based applications

The present disclosure relates to automatically detecting software defects and determining the source of the defect. An example method generally includes receiving an output data set from a host server executing a test operation and comparing the output data set to a performance model. A test system identifies that a defect exists in software executing on the host server based on determining that the output data set deviates from the performance model by more than a threshold. The test system retrieves a source code update from a source code repository that was committed to the source code repository before the execution of the test operation. The test system compares a scope of the source code update to the defect and notifies a development team related to the source code update of the defect upon determining that the scope of the source code update and the defect match.

Variability system and analytics for continuous reliability in cloud-based workflows

A continuous integration and delivery (CID) pipeline may deploy code in a state of incomplete testing to at least one user. While the code is deployed, a callback address manager of at least one processor in communication with the CID pipeline may hand the code off to a simulation manager of the at least one processor. The simulation manager may test the code and generate a score decision based on a result of the testing. The simulation manager may send the score decision to the callback address manager. The callback address manager may modify deployment of the code based on the score decision.

Code release with automatic callback

A method for scaling web application execution is claimed. A simulation execution is deployed to server instances to obtain first gathered metrics. The server instances are partitioned into server types based on hardware processing capabilities, and arranged in tiers of computing resources. Server instances of a first selected type form a first selected configuration. A web application is executed, on the first selected configuration, in a web application container to gather the first gathered metrics. When a measured metric fails to meet a baseline, then: a second server type is selected; a second server instance of the second selected type forms a second selected configuration; the web application is executed on the second selected configuration in the web application container to gather second gathered metrics; and an execution model is generated from one of the first gathered metrics and the second gathered metrics.

Scalable web services execution

Scaling web application execution includes receiving a web application container that includes a web application, establishing a network connection with server instances, where the server instances are partitioned into server types, and deploying simulation executions to the server instances to obtain gathered metrics. For each simulation execution, deploying includes selecting a server type to obtain a selected type, selecting a number of the server instances of the selected type to obtain a selected configuration, and executing, on the server instances, web application in web application container using the selected configuration to gather metrics for the simulation execution. Scaling web application execution further includes generating an execution model from the gathered metrics.

Aspects of the present disclosure describe methods and systems for recommending prioritized performance test workloads. An example method generally includes searching one or more external resources using a keyword from a number of keywords associated with a baseline test workload for a software release. The method further includes creating a risk profile for the software release based, at least in part, on a number of matches found in search results resulting from the searching. In addition, the method includes generating a prioritized test workload for execution over one or more prioritized variability dimensions based on the risk profile and the baseline test workload. The method also includes executing a test of the software release based on the prioritized test workload.

Growing community of inventors

Mountain View, CA, United States of America

Shreeshankar Chatterjee