最新刊期
卷 12 ， 期 1 ， 2026
-
Strategies for sustainable integration and growth of “Artificial Intelligence +” across industries AI导读
摘要：The 2024 government work report emphasizes the further deepening of research and application of cutting-edge technologies such as big data and artificial intelligence. The report proposes to actively implement the "AI +" plan, cultivate and develop digital industry clusters with global competitiveness. At present, "AI +" is penetrating every corner of the economy and society at an unprecedented speed and scale. However, the integration of artificial intelligence and industries is not yet close enough. "AI +" is not simply adding up, but rather using new technologies to generate higher-quality productivity, bringing new industries, models, and driving forces to various aspects of the economy and society, thereby generating multiplier effects. Based on this, the article aims to explore the essence of the integration of artificial intelligence and industries, strengthen the deep integration of artificial intelligence technology with various industries, optimize the allocation of industry-related resources, and promote the sustainable integration and growth of "AI +" across industries.关键词：AI +;resource allocation174|77|0更新时间：2026-01-15
-
- 摘要：In recent years, research in the field of social bot detection has gradually evolved from individual feature analysis to group feature mining, and from traditional feature engineering to deep learning methods. Among them, graph network-based methods have shown significant advantages: they can integrate account behavior features, text semantic features, and network topology features, converting social bot detection into a graph node classification task. However, most existing detection methods adopt general models for detection and fail to consider the differences in fine-grainedfeatures among different types of social bots, which limits the detection accuracy across business scenarios. Based on this, a social bot detection method based on a fine-grained feature expert attention mechanism was proposed. The method constructed a business expert network, enabling each expert to focus on learning differentiated weight combinations of fine-grained features. Through multi-expert feature fusion and comprehensive analysis, it achieved integrated detection of potentially multi-type social bots across various business scenarios. Experimental results on a public Twitter dataset for social bot detection demonstrated that this method outperformed existing mainstream detection methods, with a relative improvement of 1.52% in the F1-score.关键词：fine-grained feature weight;mixture of experts network105|54|0更新时间：2026-01-15
- 摘要：A multi-dimensional framework for analyzing the evolution of online public opinion was proposed, aiming to address the limitations in current research, such as a single perspective, incomplete topic mining, shallow sentiment analysis, and inaccurate identification of group behavior. Firstly, the four life cycle stages of public opinion evolution were divided based on social influence. Secondly, the topic evolution process was analyzed using the BERTopic model and similarity calculation. Sentiment fluctuations were studied by leveraging large language models. User groups were classified and opinion leaders were identified based on interaction relationships. Finally, the differences in social influence and sentiment across different periods and regions were visualized. Taking the event of ''adjustment of stampduty'' in temporal public opinion data as an example, the study discovered that the topics of public concern, sentiment tendencies, user groups, and opinion leaders changed during the four life cycle stages of public opinion. The sentiment response in eastern regions was more positive, and the duration of public opinion topics and sentiments was longer. This study can provide technical support for revealing the laws of public opinion evolution and implementing effective public opinion monitoring.关键词：online public opinion;multidimensional evolution;topic evolution;sentiment fluctuation;user group134|162|0更新时间：2026-01-15
- 摘要：Inter-document event relation extraction aims to identify relations between document-thematic events. Specifically, a document-thematic event refers to the central event conveyed by a document, with the common assumption that each document contains only one document-thematic event. Existing methods face the following challenges: (1) difficulty in capturing event association cues. There is a lack of shared context between events, making it challenging to directly obtain relevant cues that indicate their relations; (2) a lack of sufficient evidence for event relation judgment. When two documents show no obvious content overlap, clear evidence to determine their event relation is often unavailable. To address these challenges, this paper proposes a knowledge-augmented cue mining model for inter-document eventrelation extraction, termed KACM. The KACM not only mines association cues from within the document content but also leverages external knowledge to assist in relation inference. Experimental results on the DTER dataset demonstrate that KACM can effectively perform inter-document event relation extraction in terms of causal, temporal, and coreference relations.关键词：document-thematic event;event relation extraction;knowledge augmented;cue mining82|72|0更新时间：2026-01-15
- 摘要：Open-source intelligence analysis plays an increasingly important role in supporting complex decision-making. However, traditional intelligence analysis processes are inefficient due to challenges such as the complexity and variability of tasks, the difficulty of processing multi-source heterogeneous information, and the reliance on expert experience for deep reasoning. To address these issues, this paper proposes a deep research agent framework for intelligence analysis. This framework simulates a human intelligence analysis team, constructing a system led by a "Task Planning Agent" and coordinated by specialized sub-agents, including the "Information Collection Agent," "Information Identification Agent," and "Insight Generation Agent." The framework aims to automate the entire process, from task decomposition to the production of complete intelligence reports. To validate the effectiveness of the framework, we constructed an evaluation dataset for complex intelligence tasks. The results show that the frameworksignificantly outperforms baseline models in terms of generated report quality (RACT), but still has room for improvement in terms of citation performance in web retrieval (FACT).关键词：deep research;multi-agent systems119|86|0更新时间：2026-01-15
- 摘要：To address the issues of modal fragmentation, insufficient structural processing capabilities, and poor user interactivity in open-source intelligence systems, an intelligent information processing system integrating computer vision, natural language processing, and text-to-speech technologies has been proposed. Based on multi-source heterogeneous data, a complete closed-loop workflow was designed, covering data acquisition, preprocessing, deep modeling, intelligent decision-making, and user interaction feedback. The study focused on breakthroughs in key technologies such as cross-modal data fusion, structured intelligence content processing, voice broadcasting, and multimedia visualization. Experimental results showed that the system achieved excellent performance in key indicators such as intelligenceextraction accuracy, response time, and user-interpretable feedback. The system is modular and scalable, making it suitable for applications in government security, financial risk control, and public opinion monitoring.关键词：computer vision;natural language processing;text-to-speech;automatic speech recognition;multimodal fusion;large language model;artificial intelligence158|96|0更新时间：2026-01-15
TOPIC
- 摘要：Artificial intelligence for research and development (AI4RD) has evolved into a highly interdisciplinary field, integrating knowledge and methods from diverse disciplines with broad applications in scientific research and industrial development. This paper will delve into the origins, development, and future trends of AI4RD. First, we will define the concept of AI4RD, clarifying its scope and core characteristics. Next, we will analyze the strategic policies of major global economies in this area. Following that, we will introduce the key technologies of AI4RD and examine its practical outcomes in different research fields. Finally, we will explore the future evolution of AI4RD. We believe that AI4RD will profoundly transform scientific discovery methods, reshape technological innovation processes, and provide significant support in addressing major challenges faced by human society.关键词：artificial intelligence for research and development;AI4RD;artificial intelligence for science;AI4S145|217|0更新时间：2026-01-15
- 摘要：Sharing personal financial data holds significant value for enhancing financial service efficiency, facilitating collaborative supervision, and promoting the development of a financial innovation ecosystem; however, it faces multiple legal barriers. Addressing controversies over data property rights, conflicts of interest among multiple stakeholders, and excessive regulatory constraints in the sharing of personal financial data, this study proposes a hierarchical governance framework from the perspective of data providers. For personal sensitive information, it advocates scenario-based governance centered on dynamic privacy expectations to balance privacy protection and utilization. For personal non-sensitive information, it proposes optimizing informed consent rules to moderate absolute protection requirements and facilitate circulation. For non-personal information, it recommends establishing data access rights and implementing mandatory sharing to dismantle monopolistic barriers. Key regulatory measures involve defining sensitive data identification standards, adapting non-sensitive data consent rules, constructing a non-personal data access rights system, and refining regulatory design based on this hierarchical framework while adapting to technological and contextual developments.关键词：data sharing;hierarchical regulation;data access rights185|156|0更新时间：2026-01-15
FORUM
-
Intelligent configuration and load-aware scheduling for optimizing integrated host virtual resource AI导读
摘要：Addressing the issues of inaccurate virtualized resource allocation and low scheduling efficiency caused by the coexistence of heterogeneous applications and frequent dynamic loads in edge computing platforms, a jointoptimization method for virtualized resources of a converged host based on intelligent configuration and load-aware scheduling was proposed, using a train-related converged host as a typical application scenario. Firstly, by quantitatively analyzing the resource demand characteristics of typical applications of the converged host, a resource allocation prediction model based on random forest modeling and binary search method was constructed to achieve precise and forward-looking allocation of virtualized resources. Secondly, in response to dynamic load changes, an improved genetic algorithm was designed. This algorithm mapped virtualized applications to physical CPU cores and dynamically adjusted the scheduling strategy by combining a multi-objective fitness function that considers resource utilization and application performance. Experimental results showed that, compared to the traditional dominant resource fairness (DRF) algorithm, the resource allocation prediction model proposed provided configuration parameters superior to those initialized manually. Meanwhile, the improved genetic algorithm simultaneously increased the average CPU utilization from 13.5% to 22.07%, representing a relative increase of 63.5%. The objective function value increased from 0.035 to 0.204, a approximately 4.83-fold increase, reducing the total server resource consumption by 44%, and effectively saved hardware costs and energy consumption. The study provides a general method for resource optimization in edge computing platforms under highly dynamic scenarios, and verifies its feasibility using the train converged host as an example. It has universal reference value for the construction of intelligent edge systems.关键词：virtualization technology;resource configuration;dynamic scheduling;genetic algorithm;random forest48|40|0更新时间：2026-01-15 -
Dynamic graph convolutional traffic flow prediction model based on attention and linear layer fusion AI导读
摘要：Accurate traffic volume prediction is crucial for optimizing the operational efficiency of road networks and alleviating urban traffic congestion. Traditional models rely on predefined static graph structures, making it difficult to capture dynamic spatiotemporal correlations, and single-time-scale modeling struggles to comprehensively extract multi-scale features. To address these issues, a dual dynamic adaptive spatiotemporal modeling framework is proposed. In the temporal dimension, this framework employs a dynamic time feature extraction multi-head attention mechanism to adaptively adjust temporal weights to capture key dynamic features. In the spatial dimension, it designs a dynamic graph convolutional network that generates an adjacency matrix in real-time through a self-attention mechanism torepresent dynamic spatial dependencies between nodes, thus achieving spatiotemporal dual dynamic collaborative modeling. Furthermore, this framework introduces a learnable linear fusion layer to adaptively integrate multi-time-scale prediction results and collaboratively optimize local and global feature representations. Experiments on real road datasets demonstrate that this framework significantly outperforms the baseline model, validating its superior spatiotemporal feature capture and prediction performance.关键词：dynamic time feature extraction with multi head attention mechanism;dynamic graph convolution;linear layer fusion44|59|0更新时间：2026-01-15
APPLICATION
- 摘要：As a novel content creation method, AI-generated content (AIGC) technology provides new solutions to the challenges of digital intelligence in the digital economy. AIGC utilizes artificial intelligence to assist or replace manual content creation, generating various forms of content such as text, images, audio, and video based on user needs. In recent years, the rapid development of deep learning models has significantly enhanced the generative capabilities of AIGC, making it a research hotspot in the field of artificial intelligence. As a fundamental technology, AIGC has enormous application potential but also faces certain limitations. This paper provides a comprehensive overview of AIGC technology. Firstly, it introduces the related algorithms of AIGC, including generative adversarial networks, variational autoencoder, diffusion models, and large language models; then it explores the applications of AIGC in generating different content forms; finally, it summarizes the challenges faced by AIGC technology and discusses future development trends.关键词：generative adversarial networks;variational autoencoder;diffusion model;large language model424|530|0更新时间：2026-01-15
- 摘要：Data elements, as a new quality of productivity, can create significant value for society. In the era of big data, equitable pricing of data elements is crucial for realizing value. Given their unique characteristics, distinct from traditional production factors, traditional pricing methods are no longer viable. Therefore, we provide an overview of the relevant contents of data elements and pricing methods. Secondly, we consider the special characteristics of electric power data in the context of China’s ‘dual-carbon’ and summarize the progress of data element pricing research in the energy and electric power industry. Finally, we put forward the development trend of the energy and electric power industry’s data elements from the perspective of the problems and the development direction.关键词：pricing model;data elements;power industry204|290|0更新时间：2026-01-15
STUDY
- Postal code：100079
- Tel：（010）53879208、53859533 Email：bdr@bjxintong.com.cn
- Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19
京公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
- Total Visits：273110 Visits Today：16
0