In the era of big data, the furniture manufacturing industry takes digitization and intelligence as its core, and its servitization degree is constantly improving. In this paper, based on input-output table data from major manufacturing countries throughout the world in the period 2000–2014, this study empirically analyzes the impact of servitization on the industrial performance and productivity of the furniture manufacturing industry and finds that servitization level of the global furniture industry is about 20%, showing small growth in the sample period. Developed countries are in the leading position in the process of servitization strategy, and the servitization level among countries is gradually converging. Furniture manufacturing industry does not show a servitization dilemma, and servitization has a positive impact on industry performance and total factor productivity.

In the context of dam deformation monitoring, the prediction task is essentially a time series prediction problem that involves non-stationarity and complex influencing factors. To enhance the accuracy of predictions and address the challenges posed by high randomness and parameter selection in LSTM models, a novel approach called sparrow search algorithm–long short-term memory (SSA–LSTM) has been proposed for predicting the deformation of concrete dams. SSA–LSTM combines the SSA optimization algorithm with LSTM to automatically optimize the model’s parameters, thereby enhancing the prediction performance. Firstly, a concrete dam was used as an example to preprocess the historical monitoring data by cleaning, normalizing, and denoising, and due to the specificity of the data structure, multi-level denoising of abnormal data was performed. Second, some of the data were used to train the model, and the hyperparameters of the long and short-term memory neural network model (LSTM) were optimized by the SSA algorithm to better match the input data with the network structure. Finally, high-precision prediction of concrete dam deformation was carried out. The proposed model in this study significantly improves the prediction accuracy in dam deformation forecasting and demonstrates effectiveness in long-term time series deformation prediction. The model provides a reliable and efficient approach for evaluating the long-term stability of dam structures, offering valuable insights for engineering practices and decision-making.

This paper uses Python programming to improve the existing price index method and calculate the integration level of the forest products market in China. Based on the model, the influencing factors of domestic forest product market integration were examined empirically. The results show that the integration degree of the forest product market in recent years lags behind the average level in China. In this paper, the improvement of the existing price index method can calculate the level of market integration more quickly and accurately, and this improvement has obvious advantages in the case of a large amount of data. In terms of development, the overall pattern shows an increasing trend, and the eastern, central, and western provinces are gradually converging, although the differences between provinces continue to expand. In terms of influencing factors, the coefficient of the local government’s emphasis on forestry, the prosperity of international trade in forest products, and highway density were significantly positive factors, while the number of foreign investors and the railway density had no significant effects. In this paper, the optimization of the measurement method of market integration makes it easier for scholars to obtain the data on the level of market integration and promote in-depth research in the field of market integration.

In this paper, we proposed an assessment system of forest environmental carrying capacity from many aspects and comprehensively evaluated and predicted the forest environmental carrying capacity of 40 cities in the Yangtze River Delta of China by using the proposed deep learning-based model. In addition, the proposed model is used to dynamically evaluate the comprehensive scores of forest environmental carrying capacity of 34 provinces and cities in China between 2015 and 2020. This paper also has the following contributions: (1) a deeply integrated unidirectional bidirectional LSTM considering the correlation of time series is proposed. The bidirectional LSTM network is used to deal with the backward dependence of input data to prevent the omission of some useful information, which is beneficial to the prediction results. (2) In terms of missing data processing, the Mask layer is added to subtly skip the processing of missing data, which will help to enhance the evaluation results.