Abstract: Identification of content gaps based on relative user-selection rates between multiple discrete content sources. A system analyzes search log activity to determine whether users that are conducting particular types of search activities are ultimately selecting and relying upon content resources from a predefined content source of interest or, alternatively, whether such users are unsatisfied with the predefined content source of interest and are instead relying upon other third-party content sources. This particular type of analysis provides valuable insights into whether content gaps exist within the predefined content source of interest.

Abstract: Techniques are described herein that are capable of performing quality-based action(s) regarding engineer-generated documentation associated with code and/or an API. Features are extracted from data associated with the engineer-generated documentation, which includes engineer-generated document(s). Weights are assigned to the features. The quality-based action(s) are performed. The quality-based action(s) include generating quality score(s) for the engineer-generated document(s) and/or providing a recommendation to revise a subset of the engineer-generated document(s). Each quality score is based at least in part on the weights assigned to the features that correspond to the respective engineer-generated document. The recommendation recommends performance of an operation to increase the quality of each engineer-generated document in the subset based at least in part on the weights assigned to the features that correspond to the subset.

Abstract: A technique is described herein for capturing signals that indicate when any calling BOT delegates control to a called BOT, or when a calling BOT is preconfigured to contact a called BOT (e.g., as conveyed by a manifest file associated with the calling BOT). The technique can leverage these signals to facilitate the selection of BOTs. For example, the technique can use the signals to improve searches performed by a search engine and/or recommendation engine. The technique can also use the signals to generate metadata items that describe the properties of the available BOTs.

Abstract: Systems and methods for automatic recognition of entities related to cloud incidents are described. A method, implemented by at least one processor, for processing cloud incidents related information, including entity names and entity values associated with incidents having a potential to adversely impact products or services offered by a cloud service provider is provided. The method may include using at least one processor, processing the cloud incidents related information to convert at least words and symbols corresponding to a cloud incident into machine learning formatted data. The method may further include using a machine learning pipeline, processing at least a subset of the machine learning formatted data to recognize entity names and entity values associated with the cloud incident.

Abstract: Identification of content gaps based on relative user-selection rates between multiple discrete content sources. A system analyzes search log activity to determine whether users that are conducting particular types of search activities are ultimately selecting and relying upon content resources from a predefined content source of interest or, alternatively, whether such users are unsatisfied with the predefined content source of interest and are instead relying upon other third-party content sources. This particular type of analysis provides valuable insights into whether content gaps exist within the predefined content source of interest.

Abstract: A method for dynamically adjusting a number of virtual machines for a workload, includes: receiving a probability indicator for each of a plurality of N sequential stages, where N is a natural number greater than 1, of a likelihood that a virtual machine assigned to a workload will be evicted during the N sequential stages; predicting a target number of virtual machines to configure in a current stage for a subsequent stage from among the plurality of N sequential stages based on the probability indicator, a target capacity for the workload, and a current price for maintaining a virtual machine; and configuring a number of virtual machines for the workload during the current stage based on the target number to be loaded for the workload for the subsequent stage.

Abstract: A technique is described herein for capturing signals that indicate when any calling BOT delegates control to a called BOT, or when a calling BOT is preconfigured to contact a called BOT (e.g., as conveyed by a manifest file associated with the calling BOT). The technique can leverage these signals to facilitate the selection of BOTs. For example, the technique can use the signals to improve searches performed by a search engine and/or recommendation engine. The technique can also use the signals to generate metadata items that describe the properties of the available BOTs.

Abstract: Machine-learned prediction of a blame frame of a crash stack. Specifically, a crash stack associated with a crash is parsed into a sequence of frames. The blame frame of the crash stack is estimated by, for each of a plurality of the sequence of frames, identifying a plurality of features of the corresponding frame, feeding the plurality of features to a neural network, and using the output of the neural network to make a prediction on whether the corresponding frame is a blame frame of the crash. If this is done during training time, the predicted blame frame can be compared against the actual blame frame, resulting in an adjustment of the neural network. Through appropriate featurization of the frames, and by use of the neural network, the prediction can be made cross-application and considering the context of the frame within the crash stack.

Abstract: A computing system configured to execute a predictive program is provided. The predictive program, in a run-time phase, receives a current value for a remotely sourced forecast as run-time input into an artificial intelligence model. The artificial intelligence model has been trained on training data including a time series of locally sourced measurements for a parameter and a time series of remotely sourced forecast data for the parameter. The predictive program outputs a predicted forecast offset between the current value of a remotely sourced forecast and a future locally sourced measurement for the parameter. The predictive program outputs from the artificial intelligence model a predicted forecast offset based on the run-time input.

Abstract: A computing system configured to execute a predictive program is provided. The predictive program, in a run-time phase, receives a current value for a remotely sourced forecast as run-time input into an artificial intelligence model. The artificial intelligence model has been trained on training data including a time series of locally sourced measurements for a parameter and a time series of remotely sourced forecast data for the parameter. The predictive program outputs a predicted forecast offset between the current value of a remotely sourced forecast and a future locally sourced measurement for the parameter. The predictive program outputs from the artificial intelligence model a predicted forecast offset based on the run-time input.

Abstract: Machine-learned prediction of a blame frame of a crash stack. Specifically, a crash stack associated with a crash is parsed into a sequence of frames. The blame frame of the crash stack is estimated by, for each of a plurality of the sequence of frames, identifying a plurality of features of the corresponding frame, feeding the plurality of features to a neural network, and using the output of the neural network to make a prediction on whether the corresponding frame is a blame frame of the crash. If this is done during training time, the predicted blame frame can be compared against the actual blame frame, resulting in an adjustment of the neural network. Through appropriate featurization of the frames, and by use of the neural network, the prediction can be made cross-application and considering the context of the frame within the crash stack.

Abstract: Described herein is a system and method for detecting correlated changes (e.g., between code files and configuration files). For a plurality of code files and a plurality of configuration files, a correlated change model is trained to identify correlated changes across the code files and the configuration files using a machine learning algorithm that discovers change rules using a support parameter, and, a confidence parameter, and, a refinement algorithm that refines the discovered change rules. The correlated change model comprising the change rules is stored. The correlated change model can be used to identify potential issue(s) regarding a particular file (e.g., changed code or configuration file(s)). Information regarding the identified potential issue(s) can be provided to a user.

Abstract: A computer implemented method includes receiving an exception generated based on programming code, generating exception features from the received exception, the generated exception features being generated based on a set exception features derived from search logs, and executing a machine learning model on the received exception and generated exception features to provide information from the search logs identified as most helpful to resolve the received exception, wherein the machine learning model was trained on training data comprising extracted exceptions and the set of exception features derived from the search logs.

Abstract: Techniques are described herein that are capable of performing quality-based action(s) regarding engineer-generated documentation associated with code and/or an API. Features are extracted from data associated with the engineer-generated documentation, which includes engineer-generated document(s). Weights are assigned to the features. The quality-based action(s) are performed. The quality-based action(s) include generating quality score(s) for the engineer-generated document(s) and/or providing a recommendation to revise a subset of the engineer-generated document(s). Each quality score is based at least in part on the weights assigned to the features that correspond to the respective engineer-generated document. The recommendation recommends performance of an operation to increase the quality of each engineer-generated document in the subset based at least in part on the weights assigned to the features that correspond to the subset.

Abstract: The technology described herein generates automated workflows from trouble shooting guides. The automated workflow generation process described herein starts with existing TSGs as the input. A first step in the process may be identifying the computer commands in the TSG. In one aspect, the commands are identified using a sequence-to-sequence model. Once a command is identified as a command, the command is associated with an application of origin. In aspects, a second model is used to identify the application associated with the command. The second model may be a metric-based meta-learning approach to associate a command with an application. Once the commands are identified and associated with an application, they may be parsed or extracted using a regular expression, which is a special text string describing a search pattern. The structure of the natural text is then parsed to build an executable decision tree and merged with the parsed commands.

Abstract: Embodiments promote searcher productivity and efficient search engine usage by using extraquery context to detect a searcher's intent, and using detected intent to match searches to well-suited search providers. Extraquery context may include cursor location, open files, and other editing information, tool state, tool configuration or environment, project metadata, and other information external to actual search query text. Search intent may be code (seeking snippets) or non-code (seeking documentation), and sub-intents may be distinguished for different kinds of documentation or different programming languages. Search provider capabilities may reflect input formats such as natural language or logical operator usage, or content scope such as web-wide or local, or other search provider technical characteristics.

Abstract: A system is configured to replay a selected conversation with a selected agent. The selected conversation may be selected from a plurality of previously conducted conversations with other agents. The selected agent may be selected from a plurality of available agents. The system determines various tasks, named entities, and user preferences from the selected conversation. During a replay of the selected conversation with the selected agent, the system generates responses to messages received from the selected agent based on the determined tasks, named entities, and user preferences. The system also allows a user to select whether the replayed conversation should be conducted in a passive mode or in an active mode. In a passive mode, the system generally conducts the replayed conversation autonomously whereas, in an active mode, the system requests user input before sending a response to the selected agent.

Abstract: Identification of content gaps based on relative user-selection rates between multiple discrete content sources. A system analyzes search log activity to determine whether users that are conducting particular types of search activities are ultimately selecting and relying upon content resources from a predefined content source of interest or, alternatively, whether such users are unsatisfied with the predefined content source of interest and are instead relying upon other third-party content sources. This particular type of analysis provides valuable insights into whether content gaps exist within the predefined content source of interest.

Abstract: Embodiments promote searcher productivity and efficient search engine usage by using extraquery context to detect a searcher's intent, and using detected intent to match searches to well-suited search providers. Extraquery context may include cursor location, open files, and other editing information, tool state, tool configuration or environment, project metadata, and other information external to actual search query text. Search intent may be code (seeking snippets) or non-code (seeking documentation), and sub-intents may be distinguished for different kinds of documentation or different programming languages. Search provider capabilities may reflect input formats such as natural language or logical operator usage, or content scope such as web-wide or local, or other search provider technical characteristics.

Abstract: Systems and methods for automatic recognition of entities related to cloud incidents are described. A method, implemented by at least one processor, for processing cloud incidents related information, including entity names and entity values associated with incidents having a potential to adversely impact products or services offered by a cloud service provider is provided. The method may include using at least one processor, processing the cloud incidents related information to convert at least words and symbols corresponding to a cloud incident into machine learning formatted data. The method may further include using a machine learning pipeline, processing at least a subset of the machine learning formatted data to recognize entity names and entity values associated with the cloud incident.