Under the concept of green development, coal and oil control policies were frequently introduced, but the “cold” thinking under the “hot” environment is more conducive to the smooth promotion of the “transitional period” of China’s power-structure transformation. How to better consider production efficiency and environmental benefits is the theme that thermal power enterprises need to constantly break through. The most feasible “transitional period” path for thermal power enterprises is improving the efficiency of energy saving, reducing emissions, and simultaneously ensuring benefits and social awareness. This paper selected 17 listed companies in China’s thermal power sector, combined with their input resources, output, and other indicators, using a slacks-based measure–data envelopment analysis (SBM–DEA) model with undesirable outputs, and comprehensively analyzed the relationship among the technical efficiency improvement and the industry status, including price earnings ratio (P/E ratio) in the recent two years. The results show that the improvement of energy efficiency can indeed optimize enterprises’ operations and improve P/E ratio. Although clean-energy power generation has better environmental benefits, it is still lacking in efficiency; therefore, the balance between efficiency and environment sustainability should concern us.

Purpose: Library intelligence institutions, which are a kind of traditional knowledge management organization, are at the frontline of the big data revolution, in which the use of unstructured data has become a modern knowledge management resource. The paper aims to discuss this issue. Design/methodology/approach: This research combined theme logic structure (TLS), artificial neural network (ANN), and ensemble empirical mode decomposition (EEMD) to transform unstructured data into a signal-wave to examine the research characteristics. Findings: Research characteristics have a vital effect on knowledge management activities and management behavior through concentration and relaxation, and ultimately form a quasi-periodic evolution. Knowledge management should actively control the evolution of the research characteristics because the natural development of six to nine years was found to be difficult to plot. Originality/value: Periodic evaluation using TLS-ANN-EEMD gives insights into journal evolution and allows journal managers and contributors to follow the intrinsic mode functions and predict the journal research characteristics tendencies.

This paper proposes a double-layer coupled network model to analyze the multi-stage innovation activities of online, and the model consists of two layers: the online layer, which represents the virtual interactions among innovators, and the offline layer, which represents the physical interactions among innovators. The model assumes that the innovation activities are influenced by both the online and offline network structures, as well as the coupling effect between them. And it simulates the entire innovation process including knowledge diffusion and knowledge recombination. The model also incorporates the concept of network density, which measures the degree of network connectivity and cohesion (network structure). Observing the network density influence on innovation efficiency during the innovation process is realized through setting the selection mechanism and the knowledge recombination mechanism. The coupling relationship between the two layers of network density on the three stages of innovation is further discussed under the theoretical framework of the innovation value chain. Simulation and experimental results suggest that when the offline network density is constant, a higher online network density is not always better. When the online network density is low, the sparse structure of the online network reduces innovation efficiency. When the online network density is high, the structural redundancy caused by the tight network structure prevents innovation efficiency from improving. The results of the study help enterprises to adjust and optimize the internal cooperation network structure at different stages of innovation in order to maximize its effectiveness and improve the innovation efficiency of enterprises.

Anomaly detection in multivariate time series is an important research direction, which helps to improve the security of industrial systems by detecting abnormally unreliable devices. Multivariate time series (MTS) anomalies not only need to pay attention to the time correlation between different time series but also need to consider the abnormal changes in the relationship between different variables. Once the influence relationship between two variables that influence each other is ignored, it will likely lead to false positives or false positives. At the same time, the degree of influence between different time series or different features is also inconsistent, just like what happened recently have radically different influences on the present. Furthermore, most of the existing models are weak in detecting no abnormality. To tackle these issues, in this paper, we propose a new model of multivariate time series anomaly detection based on reconstruction and forecast, named MTAD RF. First, we capture the temporal and feature correlations of MTS through two parallel GAT layers, and at the same time distinguish the influence degree between different time series or different features based on attention coefficients. Second, we leverage the generative power of VAE and the single-step forecast power of MLP to jointly detect known and unknown anomalies based on reconstructed and predicted models. Major practical implications of the proposed approach is missing. Finally, anomalies are detected and explained based on temporal and feature anomaly scores. Experiments demonstrate that our model outperforms current state-of-the-art methods on 4 real-world datasets, with an average F1 score of about 95% and excellent anomaly diagnostic ability.