As a core task and an important link in the fields of natural language understanding and information retrieval, information extraction (IE) can structure and semanticize unstructured multi-modal information. In recent years, deep learning (DL) has attracted considerable research attention to IE tasks. Deep learning-based entity relation extraction techniques have gradually surpassed traditional feature- and kernel-function-based methods in terms of the depth of feature extraction and model accuracy. In this paper, we explain the basic concepts of IE and DL, primarily expounding on the research progress and achievements of DL technologies in the field of IE. At the level of IE tasks, it is expounded from entity relationship extraction, event extraction, and multi-modal information extraction three aspects, and creates a comparative analysis of various extraction techniques. We also summarize the prospects and development trends in DL in the field of IE as well as difficulties requiring further study. It is believed that research can be carried out in the direction of multi-model and multi-task joint extraction, information extraction based on knowledge enhancement, and information fusion based on multi-modal at the method level. At the model level, further research should be carried out in the aspects of strengthening theoretical research, model lightweight, and improving model generalization ability.

With the exponential development of an ecological and sustainable economy and society, the concept and practice of environmental, social, and governance (ESG) investments are being popularized in the capital market of China. ESG disclosure is an important supplement to financial disclosure and plays an increasingly significant role in asset pricing. In this paper, we selected corporate bond data in China’s secondary bond market from 2015 to 2020, and introduced the Nelson–Siegel model to study the influence of ESG disclosure on corporate bond credit spreads in the secondary market. This model passed robustness tests when we used alternative data fitted by the modified Nelson–Siegel model. Results show that ESG disclosure significantly reduces credit spreads on corporate bonds in the secondary market. State ownership and industry play significant roles in moderating the impact of ESG disclosure on corporate bond credit spreads. Specifically, the ESG disclosure of non-state-owned companies and companies in non-high-pollution and -energy-consumption industries has a greater impact on reducing corporate bond credit spreads. Therefore, we urge regulatory departments to establish a sound ESG disclosure evaluation system, and the issue companies to improve the quality of their ESG disclosure, especially non-state-owned companies, and those in non-high-pollution and -energy-consumption industries. Corporate bond investors would benefit from integrating ESG information into their investment decision-making process.

Energy security has become a worldwide issue in recent years. Coal resources security (CRS), an important part of energy security, has been an emerging concern in many countries, due to the diminishing fossil energy reserve and unbalanced energy structure. However, there is no universally agreed method of constructing indicator system for CRS assessment. Subjectivity in the process of evaluation also affects the results of assessment. Moreover, CRS is a complex system that should be evaluated scientifically under diverse methods. Therefore, we constructed an indicator system and evaluation model of CRS and used a case study of China and 31 provinces in its mainland to evaluate CRS at both national and provincial levels. The indicator system included two subsystems—long-term CRS and short-term CRS. We also chose a few elements and factors that are consistent with China’s reality. Different research methods were used: the entropy-weight-based TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution) method is applied to evaluate the degree of CRS, which avoids the subjectivity of weight determination and reflects the relative merit of each indicator; the BP (Back-Propagation) Neural Network method is used to analyze the sensitivity of CRS to each index. The results show that the national level of CRS dropped in the early years but slowly picked up with the help of government intervention. Investment in coal industry development resulted in the immediate effect of improving CRS. The positive impact of maintaining environmental sustainability is stable over either the short, medium, or long term. The degrees of CRS vary significantly across provinces, even between those with similar coal stock levels. Extra attention should be paid to the transportation of coal resources among provinces and intervention to balance supply and demand within the regions.

Standard digitalization is a crucial step in social and economic development and the transformation of digital technology. Standard digitalization is of great significance in the promotion of sustainable economic and social development. This paper proposes a standard digitalization modeling method for emergency response (ERSDMM) based on knowledge graph (KG). Firstly, this paper analyzes the knowledge structure of emergency response standards (ERS) and constructs a “seven-dimensional” model of ERS based on the public safety triangle theory. An ontology model of the emergency response domain is then created. Secondly, ERS and emergency scenario fine-grained knowledge are extracted. Thirdly, a standard reorganization model is constructed to meet the needs of the scenario response. Finally, the ERSDMM is applied to the GB 21734-2008, which proves that the ERSDMM is available. Taking RES as an example, this paper explores the path and practice of standard digitalization. ERSDMM solves standards-related problems, such as overlapping content, coarse knowledge granularity, incomplete coverage of elements, and difficulty in acquiring knowledge.

Enterprises engaged in transnational operations are confronted with increasingly complex environmental policies and compliance challenges. A critical hurdle to achieving sustainable development lies in rapidly and accurately extracting environmental protection requirements from vast volumes of policy. To address this, our study introduces an automated framework for knowledge graph construction, termed iteration–extraction–optimization (IEO), driven by a large language model (LLM). Diverging from conventional linear extraction methods, the IEO framework employs an iterative enhancement process to progressively build and refine a policy knowledge network, capturing the intricate relationships among legislation, institutions, and environmental obligations. As a case study, we applied the framework to Niger’s environmental policy, constructing a large-scale knowledge graph with 61,912 entities and 81,389 relations. Preliminary evaluations demonstrate the framework’s high performance in knowledge capture completeness, achieving a recall of 0.93 and an F1-score of 0.84. This research presents a novel paradigm for the intelligent parsing of environmental policy texts, providing a knowledge graph that serves as a vital decision-support tool for corporate environmental risk management and strategic sustainability planning.

The industrialization of using crop straw as energy is currently hindered by systemic bottlenecks, including high collection and storage costs, a poorly coordinated industrial chain, and underdeveloped market mechanism. This study takes Guangdong province as a case study to construct a tripartite evolutionary game model on the transition of straw to energy among the government, enterprises, and farmers. Different from previous studies that focused on the strategy of penalizing the open burning of straw by farmers, this work investigated the cooperation of farmers for straw removal from field, the operational strategies of enterprises for straw utilization as energy, and the selection of government-guided incentive policies. It analyzes the behavioral evolution of these stakeholders under various incentive policies and cooperative scenarios. Numerical simulations were performed to identify the system’s evolutionary stable strategies and assess the potential of expanding straw for energy utilization. It indicated that mild government intervention could lead to a stable equilibrium through facilitating the removal of straw from fields and the utilization of straw as energy by enterprises. Farmers were sensitive to the fluctuation of acquisition price, and their willingness to cooperate would be negatively impacted by a large-scale price reduction. Enterprise expansion was exposed to significant risk under intensive policy intervention. The feasible pathway to increase the proportion of straw utilization as energy in Guangdong began at a small scale. Under mild incentive policies, a scenario targeting a 20% increase was more likely to achieve a market equilibrium for large-scale production than that targeting a 55% increase. The government should draw up positive incentive policies to promote the utilization of straw as energy. By guiding farmers in straw removal from the field and improving the energy enterprises’ competitiveness, the government should curb irrational industry expansion and corporate speculation, and shift from investment support to incentive policies. Meanwhile, the ecological construction of industry and supply chains should be enhanced, and the scale should be used to reduce the high supply-side costs of the straw. It would overcome the central barrier to the commercialization of straw utilization as energy. This work sets an example for conducting dynamic analysis of multi-stakeholder interactions for straw utilization.