<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>According to the relationship between the economy and trade of the tea ceremony in foreign markets, this paper establishes the economic output model of tea in the tea ceremony in China and Russia, and at the same time, considering the spring tea frost disaster, combined with the probability model, the economic loss rate of tea frost is quantitatively evaluated. Through the analysis of social network and semantic network diagram, the semantic related high-frequency words were classified into the concept of tea culture, and the correlation between high-frequency words about tea culture was obtained. According to the comprehensive influence of domestic factors and foreign factors, the index system of influencing factors of tea export value was determined, and the prediction model of China’s tea export value based on CNN-BSO-LSTM algorithm was constructed by using big data technology, and the tea economy and culture from the perspective of Sino-Russian tea ceremony were studied and analyzed. The results showed that the three indexes of CNNBSO-LSTM were 0.9431, 8850212 and 4.112, respectively, which performed better than other models. The CNN-BSOLSTM model predicts that China’s tea exports will reach around RMB 3.5 billion in 2025, up significantly from RMB 2.3 billion in 2022. This study promotes the economic and cultural exchanges between China and Russia, and is of great significance for promoting the rise and development of urban belts along the Belt and Road.</p>
</abstract>

According to the relationship between the economy and trade of the tea ceremony in foreign markets, this paper establishes the economic output model of tea in the tea ceremony in China and Russia, and at the same time, considering the spring tea frost disaster, combined with the probability model, the economic loss rate of tea frost is quantitatively evaluated. Through the analysis of social network and semantic network diagram, the semantic related high-frequency words were classified into the concept of tea culture, and the correlation between high-frequency words about tea culture was obtained. According to the comprehensive influence of domestic factors and foreign factors, the index system of influencing factors of tea export value was determined, and the prediction model of China’s tea export value based on CNN-BSO-LSTM algorithm was constructed by using big data technology, and the tea economy and culture from the perspective of Sino-Russian tea ceremony were studied and analyzed. The results showed that the three indexes of CNNBSO-LSTM were 0.9431, 8850212 and 4.112, respectively, which performed better than other models. The CNN-BSOLSTM model predicts that China’s tea exports will reach around RMB 3.5 billion in 2025, up significantly from RMB 2.3 billion in 2022. This study promotes the economic and cultural exchanges between China and Russia, and is of great significance for promoting the rise and development of urban belts along the Belt and Road.

Research on Economic Trade and Cultural Value of the China-Russia Ten Thousand Mile Tea Route by Integrating Probabilistic Assessment Models

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

According to the relationship between the economy and trade of the tea ceremony in foreign markets, this paper establishes the economic output model of tea in...

Research on Economic Trade and Cultural Value of the China-Russia Ten Thousand Mile Tea Route by Integrating Probabilistic Assessment Models

Publicado en línea: 16 dic 2023

Páginas: -

Recibido: 27 ene 2023

Aceptado: 26 jun 2023

DOI: https://doi.org/10.2478/amns.2023.2.01513

Palabras clave
CNN, BSO, LSTM, Predictive modeling, Loss rate assessment, Tea economy

© 2023 Lankun Ma, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Research on Economic Trade and Cultural Value of the China-Russia Ten Thousand Mile Tea Route by Integrating Probabilistic Assessment Models

Publicado en línea: 16 dic 2023

Páginas: -

Recibido: 27 ene 2023

Aceptado: 26 jun 2023

DOI: https://doi.org/10.2478/amns.2023.2.01513

Palabras claveCNN, BSO, LSTM, Predictive modeling, Loss rate assessment, Tea economy

© 2023 Lankun Ma, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Palabras clave
CNN, BSO, LSTM, Predictive modeling, Loss rate assessment, Tea economy