Automatically-generated labels for time series data and numerical lists to use in analytic and machine learning systems

One or more non-transitory computer-readable media storing instructions which, when executed by one or more hardware processors, cause:

• loading a set of time series datasets including a first time series dataset and a second time series dataset, wherein each respective time series dataset in the set of time series datasets includes a respective set of data points based on varying values of a respective metric of at least one computing resource over a particular window of time;
• automatically assigning, to each respective data point of a subset of data points in the respective set of data points for each respective time series, at least one label that is descriptive of a pattern reflected by the data point relative to other data points in the respective set of data points for the respective time series;
• executing at least one of a vertical or horizontal search for patterns of automatically assigned labels in the first time series dataset and one or more other time series datasets;
• based on at least one of the vertical or horizontal search, identifying a particular pattern of automatically assigned labels that is indicative of an event affecting the at least one computing resources, wherein the pattern is identified based at least in part on at least one occurrence of a first label assigned to a first data point and a second label assigned to a second data point within a threshold number of labels from each other in at least one of the first time series dataset or the one or more other time series datasets, wherein the first label is different than the second label;
• responsive to identifying the particular pattern of labels indicative of the event affecting the at least one computing resource, triggering a responsive action.

A system comprising:

• one or more hardware processors;
• one or more non-transitory computer-readable media storing instructions that, when executed by the one or more hardware processors, cause the system to perform operations comprising:
• loading a set of time series datasets including a first time series dataset and a second time series dataset, wherein each respective time series dataset in the set of time series datasets includes a respective set of data points based on varying values of a respective metric of at least one computing resource over a particular window of time;
• automatically assigning, to each respective data point of a subset of data points in the respective set of data points for each respective time series, at least one label that is descriptive of a pattern reflected by the data point relative to other data points in the respective set of data points for the respective time series;
• executing at least one of a vertical or horizontal search for patterns of automatically assigned labels in the first time series dataset and one or more other time series datasets;
• based on at least one of the vertical or horizontal search, identifying a particular pattern of automatically assigned labels that is indicative of an event affecting the at least one computing resources, wherein the pattern is identified based at least in part on at least one occurrence of a first label assigned to a first data point and a second label assigned to a second data point within a threshold number of labels from each other in at least one of the first time series dataset or the one or more other time series datasets, wherein the first label is different than the second label;
• responsive to identifying the particular pattern of labels indicative of the event affecting the at least one computing resource, triggering a responsive action.