Multi-language text and speech generation method for procedural model map

Abstract

The invention discloses a multi-language text and speech generation method for a procedural model map, and belongs to the field of procedure mining. The method comprises the following steps that: firstly, identifying a model element, a model node text and a model directed edge in the procedural model map, and storing the identified procedural model as a standard procedural model file; then, usingmultilingual semantic dependence to analyze a model element text, using an RPST (Real Time Streaming Protocol) algorithm to analyze a model structure, and using a procedural structure tree with an annotation to store the model element text and the procedural model structure information; then, according to the text information amount and structure complexity, dividing the procedural structure treewith the annotation; using a deep syntax tree to generate the multilingual text of the procedural model from the procedural structure tree with the annotation; and finally, generating the multilingualspeech of the procedural model from the multilingual text. By use of the method, the procedural model in the procedural model map can be correctly identified, the text and the structure of the procedural model can be correctly analyzed, and the text with the correct grammar and the speech with correct pronunciation can be generated.

Description

Technical field [0001] The invention belongs to the field of process mining, and specifically relates to a method for generating multilingual text and voice of process model diagrams. Background technique [0002] By consulting the existing invention patents and documents, there is no way to automatically generate multilingual text and speech from the process model diagram. The existing research focuses on the recognition of the process model diagram, the text generation of the process model and the speech synthesis. aspect. [0003] Process model diagram recognition studies how to recognize the process model structure from pictures. It uses knowledge representation, graph matching, symbol recognition, geometric reasoning, semantic extraction and other technologies to obtain information such as model nodes, model node text and model directed edges. . [0004] Process model text generation research how to generate process model explanatory text, process model text needs to consider ...

AI Technical Summary

Problems solved by technology

Existing technologies study different directions separately, resulting in different input and output formats between different modules. For example, process model diagram recognition obtains the structure of the process model and stores it in a custom directed graph format, while the text of the process model Generate studies how to generate text from process models whose input is standard process model files

Images