Semantic data grouping with machine-learned models via graphical user interfaces (GUIS)

A computing system, comprising:

• a processor device;
• and
• a non-transitory computer-readable storage medium containing instructions which, when executed on the processor device, causes the processor device to:
• receive information indicative of a first user input to a data analytics application, wherein the first user input selects a plurality of data elements;
• identify a first task for a machine-learned model to perform with the plurality of data elements from a plurality of candidate tasks;
• retrieve a first prompt corresponding to the first task from a plurality of prompts associated with the plurality of candidate tasks, wherein the first prompt instructs the machine-learned model to perform one or more first actions to complete the first task;
• process the first prompt and the plurality of data elements with the machine-learned model to generate a model output, wherein the model output comprises:
• information indicative of a plurality of categories, at least one of the plurality of categories being generated by the machine-learned model based on a first categorization criterion, wherein the first categorization criterion is identified by the machine-learned model;
• and
• category assignment information that assigns the plurality of data elements to the plurality of categories;
• and
• send the model output to the data analytics application.

A method, comprising:

• receiving, by a computing system comprising one or more processor devices, information indicative of a first user input to a data analytics application, wherein the first user input selects a plurality of data elements;
• identifying, by the computing system, a first task for a machine-learned model to perform with the plurality of data elements from a plurality of candidate tasks;
• retrieving, by the computing system, a first prompt corresponding to the first task from a plurality of prompts associated with the plurality of candidate tasks, wherein the first prompt instructs the machine-learned model to perform one or more first actions to complete the first task;
• processing, by the computing system, the first prompt and the plurality of data elements with the machine-learned model to generate a model output, wherein the model output comprises:
• information indicative of a plurality of categories, at least one of the plurality of categories being generated by the machine-learned model based on a first categorization criterion, wherein the first categorization criterion is identified by the machine-learned model;
• and
• category assignment information that assigns the plurality of data elements to the plurality of categories;
• and
• sending, by the computing system, the model output to the data analytics application.