Training data may include change-lists and descriptions associated with the change-lists. A change-list may specify a set of changes to a design or a test case, or both. The descriptions may be specified in a natural language. A machine learning (ML) model may be trained based on the training data. A first change-list and a first description for a first design may be received. The trained ML model may be used to predict a first set of test cases for testing the first design based on the first change-list and the first description.

The subject technology detects anomalies in media campaign configuration settings. The anomaly detection system may leverage one or more deep learning models to detect anomalies and identify particular configuration settings that contribute to the detected anomalies. In various embodiments, two or more of the deep learning models may be combined into an ensemble model that boosts the accuracy of anomaly predictions made by the anomaly detection system. The anomaly detection system may review the configuration settings of media campaigns during the configuration process and before the media campaigns run on a publication system in order to reduce the amount of unsuccessful campaigns and minimize the amount of wasted resources spent on running campaigns that have a low likelihood of achieving user defined goals.

The following relates generally to diagnosing problems with websites. In some embodiments, a webpage interaction processor receives a list of potential user experience problems. The webpage interaction processor then extracts click data from the website, and processes the extracted click data into grams. Subsequently, an analytics engine is trained based on the processed click data. The trained analytics engine may then diagnose the problem of the website with a potential user experience problem from the received list of potential user experience problems. In some embodiments, the process is entirely automated.

A process to train a machine learning model to predict fault location in a system includes generating a data set for training the machine learning model. The generating includes injecting, at a selected location of the system, a test fault into a simulation of the system using a workload, and recording a respective error syndrome generated by the simulation. Further, the generating includes repeating the injecting, at other selected location(s) of the system, of other test fault(s) into the simulation of the system, and the recording of respective, generated error syndromes. In addition, the process includes training, using the data set, the machine learning model, and providing the trained machine learning model for use in debugging the system, where the debugging includes predicting, using the trained machine learning model, a fault location within the system based on an error syndrome generated by the system due to the fault.

Disclosed herein are system, method, and computer program product embodiments for detecting anomalies during software testing. The methods include generating a plurality of test reports for the software program by executing one or more test cases on a plurality of versions of the software program, generating a control chart based on the plurality of test reports, generating an alert when at least one testing characteristic includes an anomaly over the plurality of versions of the software program as determined based on the control chart. The control chart includes a plot associated with at least one testing characteristic of the software program, and a historical context associated with execution of the one or more test cases on the plurality of versions of the software program.

A process to train a machine learning model to predict fault location in a system includes generating a data set for training the machine learning model. The generating includes injecting, at a selected location of the system, a test fault into a simulation of the system using a workload, and recording a respective error syndrome generated by the simulation. Further, the generating includes repeating the injecting, at other selected location(s) of the system, of other test fault(s) into the simulation of the system, and the recording of respective, generated error syndromes. In addition, the process includes training, using the data set, the machine learning model, and providing the trained machine learning model for use in debugging the system, where the debugging includes predicting, using the trained machine learning model, a fault location within the system based on an error syndrome generated by the system due to the fault.

A method for planning and executing a test of a DUT includes receiving a test description from a user via a GUI, where the test description identifies the DUT and an objective of the test; composing a prompt for querying a large language model (LLM) based on the test description, where LLM includes a trained machine learning algorithm; sending the prompt to the LLM via an API; determining, using the LLM, a test plan for executing the test to be performed in response to the prompt to achieve the objective of the test based on the test description and general testing information, where the test plan identifies a type of test, test instruments for performing the test, a test procedure using the instrument, and parameters of the DUT to be measured according to the test procedure; providing, via the GUI, the test plan to the user for testing the DUT.

Systems and methods include an Information Handling System (IHS) that is adapted to diagnose root causes of issues reported by hardware and/or software of the IHS. Telemetry is monitored that specifies operating status information for hardware components of the IHS. Stress event are detected that are related to the hardware components. One or more stress tests are identified for evaluation of each hardware component that is related to stress event. While monitoring the telemetry, the stress tests are conducted in order to replicate the detected stress event. When the detected stress event is replicated, a root cause hardware component of the IHS is determined based on machine learning evaluation of the telemetry generated during replication of the stress event.

Methods, apparatus, and processor-readable storage media for determining hardware issues and recommending corresponding actions using artificial intelligence techniques are provided herein. An example computer-implemented method includes obtaining input image data pertaining to at least one hardware item; identifying one or more portions of the at least one hardware item by processing at least a portion of the input image data using a first set of one or more artificial intelligence techniques; detecting, in the one or more identified portions, at least one defect of the at least one hardware item by processing the at least a portion of the input image data using a second set of one or more artificial intelligence techniques; generating at least one recommendation, associated with the at least one hardware item, in connection with the at least one detected defect; and performing one or more automated actions based on the at least one recommendation.

Examples of the present disclosure describe systems and methods for automating the identification of events in a text file. In examples, a computing system identifies a subset of a text file that comprises an unknown event using a set of rules. Each rule of the set of rules specifying a first pattern of characters is compared to the subset of the first text file. When the set of rules does not identify the unknown event, the subset of the text file is provided to a language model to generate a new rule with a second pattern of characters and an identifier of the new rule. The system then generates an updated set of rules by adding the new rule to the set of rules.