A Method for Automatically Converting Chinese Process Models to English Natural Language Text

Abstract

The invention discloses a method for automatically converting a Chinese process model into an English natural language text, belonging to the field of process mining. The present invention first uses the label text information analysis technology to obtain and analyze the text information on the nodes and edges in the process model; then uses the process model structure conversion technology to convert the process model structure into a process structure tree; then uses the domain lexicon construction technology, Build the domain thesaurus of the process model; then use the label text information translation technology to translate the Chinese label text into English; then use the translation text screening technology to filter the correct text translation according to the domain thesaurus; then use the cross-language grammar structure conversion technology , convert the Chinese grammatical structure into English grammatical structure, and use the grammatical tree to generate natural language short texts describing node behaviors; finally, use natural language text generation technology to generate English natural language texts.

Description

technical field [0001] The invention belongs to the field of process mining, in particular to a method for automatically converting a Chinese process model into an English natural language text. Background technique [0002] At present, the generation of English natural language text from the Chinese process model mainly includes two types of solutions: one is to use the help of process experts to read and understand the Chinese process model, and then generate English natural language text. The second category is the technology that first uses the existing process model to generate Chinese natural language text. First, the Chinese process model generates Chinese natural language text, and then uses online translation tools to translate the Chinese natural language text into English natural language text. [0003] The first type of method is to use the help of process experts to express the process model in English through their understanding of the Chinese process model, an...

AI Technical Summary

Problems solved by technology

[0003] The first type of method is to use the help of process experts to express the process model in English through their understanding of the Chinese process model, and then generate English natural language texts. This method generates high-quality natural language texts and is highly readable. , but the efficiency of manual translation is low, and the translation cycle is long when the process model is complex

[0004] The second type of method first uses the existing process model to generate Chinese natural language text. The Chinese process model generates Chinese natural language text, and then uses an online translation tool to translate the Chinese natural language text into English. This method is simple to implement , the implementation efficiency is high, but the general translation tool cannot guarantee the correct translation of the domain vocabulary, nor can it guarantee the consistency of the generated text and the process model

[0005] Comprehensive analysis of the two methods, the Chinese natural language text generated by the first type is more correct, but it is difficult to find such a process expert

The second type of method uses an online translation tool to translate Chinese natural language text, but this does not guarantee the correctness of domain vocabulary translation, nor the consistency of the text and the model

[0007] Traditional artificial generation solutions cannot solve the problems of long time period and low generation efficiency

As the scale of the process model increases, for process experts, it is impossible to fully understand the meaning of the process model, and it is impossible to ensure that the text generated every time is correct, and the cost of manual generation is high and the efficiency is low

[0008] The online translation tool generation scheme first uses the process model to generate Chinese natural language text, and then uses the online translation tool to translate the Chinese natural language text into English. Using a general online translation tool to translate the Chinese text does not guarantee that the domain vocabulary is translated correctly, and there is no guarantee The consistency between the generated English text and the process model affects the user's understanding of the process model

Images