Method for automatically converting process model into multilingual text

Abstract

The invention discloses a method for automatically converting a process model into a multilingual text, pertaining to the field of process mining. The method comprises the following steps: firstly, creating a multilingual text template, creating a multilingual-field work stock and recognizing a language type of a model element text; then, using text information of elements in a semantic dependencyanalysis model and a multilingual translation method to translate analyzed texts of model elements into multiple languages; and using a translation result screening and cross-linguistic syntactic structure adjusting method to optimize translation results in order to make the translation results more accurate; dividing the structure of the process model into sub-processes with an RPST algorithm, combining multilingual text information of the model elements with a process structure tree and generating the process structure tree with annotations; then, generating multilingual texts with a depthsyntax tree from the process structure tree with annotations; and ultimately, using subject clustering, verb clustering and object clustering to process the multilingual texts in order to generate a multilingual text description of process.

Description

technical field [0001] The invention belongs to the field of flow mining, and in particular relates to a method for automatically converting a flow model into a multilingual text. Background technique [0002] Currently, there are two types of schemes for generating multilingual texts from process models: one is to allow process experts to read and understand process models, and then generate multilingual texts. The second category is to first use translation tools to translate model element texts into a unified language, then use existing process model text generation methods to generate single-language texts, and then use translation tools to translate single-language texts into multilingual texts. [0003] The first type of method is to let process experts read and understand the process model, and then use multiple languages ​​to express the structure and meaning of the process model. The multilingual texts generated by this method are highly readable and grammatically ...

AI Technical Summary

Problems solved by technology

The second type of method has high efficiency in generating multilingual text and can handle complex process models, but the quality of the generated text depends on the translation quality of the translation tool and the ability to adjust the multilingual grammar structure of the translation tool. Looking at the technology proposed by the present invention as a whole The idea is innovative, which cannot be realized by the text generation method of the existing process model

[0007] Artificial generation methods cannot solve the problem of long and inefficient generation of multilingual texts

It is difficult to find multilingual process experts in the first place, and the cost of using process experts to generate multilingual texts is also very high

In addition, process experts generate multilingual texts of the process model based on their understanding of the process model and their own language expression habits. However, as the complexity of the process model structure increases, business experts will understand the process model more and more. The more difficult it is, the generated multilingual text is highly subjective, and process experts cannot guarantee that the information of the process model is fully and accurately expressed

[0008] The method of combining translation tools with process model text generation uses existing translation tools to unify the language of model element text information, and then uses process model text generation and translation tools to generate multilingual texts of process models. translation accuracy, and because translation tools are needed to translate texts in one language into multiple other languages, the ability of translation tools to understand and adjust cross-language grammatical structures directly determines the quality of the generated multilingual texts, and finally the translation tools generate The text contains a lot of repetitive information, which makes the generated text structure loose and affects the user's understanding of the process model

Images