Abstract:
A system and method for predicting the class of future customer calls to a call center. Saved call data is analyzed using a robust tokenizer of a computerized device. The tokenizer transforms a sequence of characters in a call summary field of the saved call data into a sequence of tokens. Tokenized call data is produced. Multiple maximum entropy (MaxEnt) models are created based on the tokenized call data, using the computerized device. The MaxEnt models produce a probability distribution of all classes for a next call to a call center. A conditional random field (CRF) classifier is trained with the MaxEnt models and information from the saved call data, using the computerized device. The CRF classifier uses chronologically ordered sequences of prior calls to the call center and predicts a class for a new call to the call center based on the saved call data. A call class prediction is produced for the new call received from a returning customer based on the CRF classifier and the MaxEnt model.
Abstract:
The present invention generally relates to systems and methods for visual process analysis. The disclosed techniques can include: obtaining a theoretical and an empirical process model, generating a theoretical process layout corresponding to the theoretical process model, where the theoretical process layout is generated using a layout algorithm, generating an empirical process layout corresponding to the empirical process model, where the empirical process layout is generated using the layout algorithm, superposing the empirical process layout onto the theoretical process layout, such that a superposition layout is generated, annotating the superposition layout based on ugliness indicators, such that an annotated superposition layout is generated, and causing the annotated superposition layout to be displayed.
Abstract:
A process discovery system that includes an offline system training module configured to cluster similar process log traces using Non-negative Matrix Factorization (NMF) with each cluster representing a process model, and learn a Conditional Random Field (CRF) model for each process model and an online system usage module configured to decode new incoming log traces and construct a process graph in which transitions are shown or hidden according to a tuning parameter.
Abstract:
Disclosed are a method and a system for comparing established workflows against a workflow pattern to determine their degree of compatibility with this workflow pattern. In the method and system, compatibility scores between established workflows and a workflow pattern can be determined. To determine the compatibility score between a workflow pattern, which comprises first tasks, and an established workflow, which comprises second tasks, equivalent tasks in the established workflow can be identified. Then, dependency matrices can be constructed for the first tasks in the workflow pattern and the equivalent tasks in the established workflow. These dependency matrices can be compared in order to identify any dependency relation matches in corresponding task pairs. Values can be assigned to the dependency relation matches and compatibility scores can be determined based on the sum of those values.
Abstract:
The present invention generally relates to systems and methods for document redaction. The disclosed techniques adapt to the needs of different levels of data sensitivity and different needs for disclosure or analysis by using pre-defined templates related to use cases, and mapping those to the relative sensitivity of private data types both in their natural form and after redaction by various redaction types. In this way, data is given the appropriate level of protection within the needs of a given use case.
Abstract:
A system and method for characterizing textual data by generating a first data abstraction based on a set of textual data. The first data abstraction can be presented to a user, and the user can provide instructions to make changes to the first data abstraction to generate a second data abstraction. The textual data can be extracted and characterized from the set of textual data using the second data abstraction.
Abstract:
A process definition is partitioned for execution in a system architecture that enables the communication and meta-orchestration of multiple distributed engines. The partitioning method creates separate scripts for each group (execution engine, computer, distributed computer, etc.) where each script has the same representation as the original control flow, but keeps local services and replaces remote services with data flow messages and synchronization points. This method ensures that the resulting process has the same result as the original process executed with a single engine. Additional advantages include: the number of partitions of the process is minimized to equal to the number of distributed engines; the communication between engines is minimized to only data flow messages; there is no dependency on a specific process representation such as BPMN; and reduced implementation complexity.
Abstract:
The present invention generally relates to systems and methods for checking the conformance of a process behavior against a theoretical process model, and for further providing a detailed diagnostic regarding the process behavior's expectedness and frequency. The provision of this detailed diagnostic includes discovering the empirical models generated by the system's business processes, and matching the defined process model to its corresponding empirical model.
Abstract:
The present invention generally relates to systems and methods for document redaction. The disclosed techniques adapt to the needs of different levels of data sensitivity and different needs for disclosure or analysis by using pre-defined templates related to use cases, and mapping those to the relative sensitivity of private data types both in their natural form and after redaction by various redaction types. In this way, data is given the appropriate level of protection within the needs of a given use case.
Abstract:
A process definition is partitioned for execution in a system architecture that enables the communication and meta-orchestration of multiple distributed engines. The partitioning method creates separate scripts for each group (execution engine, computer, distributed computer, etc.) where each script has the same representation as the original control flow, but keeps local services and replaces remote services with data flow messages and synchronization points. This method ensures that the resulting process has the same result as the original process executed with a single engine. Additional advantages include: the number of partitions of the process is minimized to equal to the number of distributed engines; the communication between engines is minimized to only data flow messages; there is no dependency on a specific process representation such as BPMN; and reduced implementation complexity.