Abstract: A computer-implemented method for unsupervised task segmentation. The computer-implemented method includes receiving a stream of data of desktop-actions. Each desktop-action relates to UI data-handling operations of applications, and labeled with an action-related integer id, operating an unsupervised task segmentation module on the stream of data of desktop-actions to identify sequences of desktop-actions.

Abstract: A system to create new automation routines includes a processor to: Over time, store a group of actions taken by a group of agents within applications. From the stored group of actions, identify a repeating pattern of actions in a subset of the applications, and construct a binary vector, each position within the binary vector storing a 1 for an occurrence of any action within any application of the subset, and a 0 otherwise. From the binary vector and the repeating pattern, extract a sentence including at least one action within at least one application. Based on the repeating pattern, an application type, or a business goal, create a constraint. If the sentence meets the constraint, accept the sentence and add it to a pool of accepted sentences. From the pool of accepted sentences, identify a pattern of occurrences of the accepted sentence, and create a new automation routine.

Abstract: A computerized system and method may generate computer automation opportunities based on segmenting action sequences from action data and/or information items. A computerized system including a processor or a plurality of processors, and a memory including a data store of a plurality of data items describing actions input to a computer may be used to receive an input query or a plurality of actions input to a computer; segment action sequences from the stored data items based on the query; and produce automation candidates based on the segmented sequences. Embodiments of the invention may include generating, by a machine learning model, vector embeddings for action sequences, calculating similarity scores for sequences based on the embeddings, and mining a plurality of action subsequences based on, a group or set of similar sequences, as well as additional and/or auxiliary procedures and operations.

Abstract: A system and method may identify computer-based processes involving the use of text templates which may be candidates for automation. Using one or more computers, embodiments of the invention may sort low-level user action information for a given process which may be received as input; search for a plurality of strings pasted multiple times in the sorted information; discard one or more of the strings found from the search which correspond to a set of criteria (e.g., found to be shorter, or pasted, or edited fewer times than a predetermined threshold); group the strings according to an identifier of the target app where each string was pasted; iteratively calculate a similarity score for strings or groups of strings, and cluster strings or groups for which the similarity score is below a predetermined threshold, to form final clusters; and suggest the final clusters as automation opportunities to, e.g., a business analyst.