Process model graph automatic identification and understanding method

Abstract

The invention discloses a process model graph automatic identification and understanding method, and belongs to the field of process mining. The method comprises the steps of firstly constructing a basic graphic element template, matching a process model graph with the graphic element template, identifying model elements such as tasks, activities, events, gateways, arrowheads and the like in the process model graph, and removing repeated matching nodes and wrong matching regions by using a screening technology; secondly by using a process model graph cutting technology, obtaining pictures of regions where nodes comprising texts are located, and by using an OCR technology, recognizing the texts in the pictures; thirdly performing gray processing on the process model graph, and obtaining andstoring a gray value matrix of the process model graph; and finally according to the arrowheads in the model graph and the positions of nearest neighbor nodes, performing traversal in the gray valuematrix, and identifying a starting node and a terminating node of a directed edge. According to the method, the types and positions of the model nodes and the texts in the model nodes can be correctlyidentified, and also the directed edge in the process model graph can be correctly identified.

Description

technical field [0001] The invention belongs to the field of process mining, and in particular relates to an automatic identification and understanding method for a process model diagram. Background technique [0002] The identification and understanding of the current process model diagram mainly includes two types of schemes: one is to use the engineering drawing recognition system to identify the process model diagram, and the second is to complete the identification of the process model diagram through the static rule base. [0003] The first method uses the engineering drawing recognition system to identify the process model diagram. According to different engineering fields, the existing engineering drawing recognition systems include the Celesstin system of the French LORIA Institute, the MDUS system of the Israel University of Engineering Technology, and so on. When using the engineering drawing recognition system to identify the process model diagram, it is first ne...

AI Technical Summary

Problems solved by technology

[0007] Engineering map recognition is used to identify the primitives and semantics of engineering drawings in the proprietary field, so the engineering map recognition system has poor versatility, because there is no system dedicated to business flow chart recognition, so the types of nodes in the engineering map recognition system are related to the process model The nodes in the graph are not all of the same type

Therefore, when using the engineering map recognition system to identify the process model diagram, some nodes may not be recognized, resulting in the incomplete structure of the recognized process model, or the loss of the beginning and end nodes of the directed edge.

[0008] When the static rule base identifies the process model, it is first necessary to define the graphic element template of the basic unit of the process model diagram. The types of model nodes in the process model diagram are limited, so the basic graphic elements of the model nodes can be defined, but there are directed edges in the process model diagram. The coordinates of the start point, the end point, the number of inflection points, and the direction of the arrow are different, so it is not possible to define all the edges of the shape

Therefore, when using the static rule base to identify the process model diagram, the directed edges cannot be fully identified, and there will be isolated nodes in the final identified process model, resulting in an error in the process model structure

Images