Nice Ltd

Eran Roseberg

Yaron Moshe Bialy

Yuval Shachaf

Aviv Yehezkel

Ariel Smutko

Natan Katz

Simone Mimun

Adi Levinshtein

Oz Granit

Eitan Oberman

Tal Greenberg

A computerized-method for identifying a contact-reason of a business-process that has been discovered by a desktop-analytics-tool. The computerized-method includes: (i) retrieving a random-sample of a preconfigured number of instances of a discovered-routine from the routines-datastore; (ii) for each instance in the random-sample of the preconfigured number of instances matching a related transcript-segment; (iii) identifying a contact-reason of each instance by operating a first-GEN-AI with LLM with a first-prompt-text including an embedded related transcript-segment; The first-GEN-AI with LLM has been trained to provide the contact-reason based on the transcript-segment embedded in the first-prompt-text, and (iv) identifying the contact-reason of the discovered-routine as the contact-reason of the business process by operating a second-GEN-AI with LLM with a second-prompt-text for aggregation of all the contact-reasons of all instances in the random-sample. The second-GEN-AI with LLM has been trained to provide a contact-reason based on the contact-reasons of all instances embedded in the second-prompt-text.

Method for identifying contact reason of a business process discovered by a desktop analytics tool

A system and method may identify computer-based processes which may be candidates for automation. Embodiments may involve a semi-supervised approach for identifying processes as automation opportunities. Transition probabilities for pairs of routines within a candidate process may be calculated based on a set of instances of the process (e.g., in a dataset of computer actions) using a dynamic time-window optimization procedure, where transition times may be measured for a plurality of instances of a first and second routines of a given pair of routines, and where statistical distributions may be calculated and used for deriving one or more time windows, describing a predetermined percentile (e.g., the 70percentile) of the measured transitions and used for estimating a transition probability for the pair of routines. In some embodiments, the input set of transitions and routines may be generated by a user or business analyst using a graphical user interface (GUI).

Systems and methods for automation discovery recalculation using dynamic time window optimization

A computerized-method for sensitive data redaction from screenshots, is provided herein. The computerized-method includes retrieving records of a sequence of screenshots from a database. Then, grouping the sequence-of-screenshots by one feature of one or more features to yield one or more groups. Each group includes screenshots having one common feature. Then, calculating a score for each pixel across all similar screenshots in each group. For each group of screenshots, blackening pixels in all screenshots having a score above a preconfigured threshold to yield data redacted screenshots. The score of each pixel above the preconfigured threshold indicates a high variance between screenshots in the group and a presence of sensitive data therein and then storing the data-redacted screenshots in a screenshots-database.

Computerized-method and computerized-system for sensitive data redaction from screenshots

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.

Methods for discovery of new automation routine types

A method and system for dynamically determining a minimum support for automation mining is provided. The method and system include modifying the minimum support pattern such that the minimum support can result pattern mining algorithms finding a sufficient number of patterns in a practical duration.

Systems and methods automatically adjusting minimum support for routing mining

A method and system for analyzing and connecting computer-based actions into sentences may include for a series of computer-based actions, determining the case ID for the action for each action where an identifier or case ID can be determined, creating sequences of subsets of the series of computer-based actions using the case ID, and merging sequences having computer-based actions having the same case ID. A set of case IDs may be extracted from the actions using a clustering algorithm based on features of potential case IDs such as gaps in appearance of potential case IDs in a sequence of actions and consecutive appearances of potential case IDs in a sequence of actions. The extracted case IDs may be used when creating sequences.

Systems and methods for analyzing and connecting automation sequences

A system and method analyzes computer actions to identify computer-based processes (e.g. computer-user interactions) which are automation candidates. A data gathering process executed by a processor on a computer may collect low-level user action information or items, each low-level user action information or item including for example an input type description, a user name, and screen window information. At a computer sequential pattern mining may be applied to determine a set of subprocesses, each subprocess including a series of low-level user actions, each user action associated with a user action vector, and each subprocess associated with a subprocess vector generated from user action vectors associated with (typically generalized) low-level user actions comprised in the subprocess. The subprocess vectors may be grouped or clustered to create processes. For each process, an automation score may be calculated using the actions in the subprocesses in the process.

Systems and methods for discovery of automation opportunities

A system is provided for an artificial intelligence engine adapted to identify robotic process automation' opportunities based on return on investment (ROI) potential for automation. The system includes a processor and a computer readable medium configured to perform operations comprising receiving an event log of a plurality of user actions, splitting the plurality of user actions into a plurality of user action sentences, determining a sequence of user actions in the plurality of user action sentences based on a recurrence for the sequence in the plurality of user action sentences, determining a score for the sequence based on a time duration in which the user completes the sequence and based on types of the plurality of user actions in the sequence, and filtering the sequence with a plurality of other sequences.

Robotic process automation for significant sequences of desktop events

A computerized-method for automatically documenting automatically-discovered actions of a business-process for automation thereof is provided herein. The computerized-method includes operating a build-automation-document module. The build-automation-document module includes: (i) retrieving the set of automatically-discovered actions of the business process for automation thereof. Each action is of a related type and related to an application to complete the business process via the applications portal. (ii) for each action of the set of automatically-discovered actions, extracting an associated routine-name of a routine; (iii) grouping similar actions by related window in related application and type of action into clusters of actions; (iv) removing clusters of actions which are not necessary to an automated business process; (v) sorting the clusters of actions in an order for automatically performing the business process; and (vi) saving the sorted automatically-discovered actions into a file to be presented on a display unit that is associated to the computerized system.

Click to document

A system and method may determine, e.g. for suggestion to an automation designer, a next action in an automation sequence of actions being created. The automation sequence may include actions executed by a computer system which substitute for actions taken by a user operating a computer system. A sequence of actions may be received, a database of action sequences may be searched for a set of action sequences corresponding to the sequence of actions, and the next action may be presented or determined as being the for example a subsequent new action immediately after the last action matching any action from the received sequence of actions in an action sequence in the set of action sequences.

Growing community of inventors

Hogla, Israel

Eran Roseberg