Entity Extraction Algorithm of Hybrid Network based on Attention Mechanism in Smart City

The rapid advancement of artificial intelligence and intelligent algorithms has led to the widespread adoption of natural language processing technology. Named entity recognition (NER), an important task in this field, takes a pivotal part in information extraction, machine translation, and knowledge graph construction. However, for a small language such as Lao, traditional methods have obvious deficiencies in recognition effectiveness due to its complex syllable structure, fuzzy word boundaries and scarce corpus resources. To address this problem, the study designs a named entity recognition model for Lao that incorporates a Bi-directional Long Short-Term Memory (BiLSTM) network, an attention mechanism and a conditional random field. The model first vectorizes multi-granularity features such as characters, syllables and lexemes through an embedding layer, then captures contextual dependencies by a BiLSTM network, introduces an Attention to highlight key information, and finally establishes a global label transfer relation through a conditional random field to ensure the consistency of the predicted sequence. The findings denote that the model achieves 91.5%, 91.0%, 90.7%, and 90.9% in accuracy rate, precision rate, recall rate, and F1 score, respectively, and the mean absolute error and mean square error are reduced to 0.062 and 0.011, which are significantly better than the comparison model. The results show that combining multi-level feature modeling and global constraint mechanism can effectively enhance the performance of named entity recognition in Lao, which provides a valuable reference and practical path for natural language processing in small languages.

In today's society, the rapid development of the Internet makes People's Daily life become more intelligent and diversified. Today's society has entered a multifaceted era where everything is interconnected. Artificial intelligence technology is gradually replacing some traditional human services, such as intelligent robot customer service instead of traditional human customer service, intelligent face scanning security check in railway stations instead of traditional manual ticket checking, unmanned supermarket automatic checkout has liberated some social labor costs. All these changes are the result of the development of artificial intelligence technology in today's society. In recent years, unicorn startups focused on biometrics have sprung up all around us, such as BTU and its MEG VII (Face ++). Thanks to the development of Internet and artificial intelligence technology, in many application fields, the traditional access control and identity authentication technology based on password verification is gradually transforming to the scheme based on biometric identification verification. Secure identity authentication is very important to the application of Internet. Face recognition is the most popular technology among all biometric identification technologies. In the field of biometric identification technology, it has become the most widely used technology in the field of identity authentication because of its unique non-invasive, support for infrared and visible light, no need for user cooperation and many other advantages. In the field of education, examinee identification, pedestrian identification detection at the entrance of railway stations, face electronic payment, intelligent video surveillance system, intelligent attendance and access control system, intelligent unmanned supermarkets and customs clearance ports become the pioneer fields of face recognition applications. It can be seen that the era of “national face brushing” has arrived, and the application of face recognition technology will only be more and more widespread in the current era and in the future. However, due to the sensitivity of biometric data and the heterogeneity and openness of network environment, the privacy leakage of biometric data is difficult to avoid. At present, fog computing and edge computing have been paid more and more attention in many fields. In the case that cloud service providers are unable to provide sufficient security, edge computing shows its advantages. In this paper, mobile edge computing is introduced for the first time into the face privacy protection identity authentication system based on cloud server outsourcing computing. It can not only greatly reduce the interaction frequency between users and cloud server, improve the availability and fault tolerance of the system, but also contribute to the implementation of privacy protection scheme. A deep constitutional neural network for face feature extraction is trained using deep learning framework Cafe. Cosine similarity is used to complete face verification. A privacy protection scheme based on the secure nearest neighbor algorithm is proposed, which can not only protect the security of the face feature data at the edge computing node, but also allow the edge computing node to complete the face recognition operation against the encrypted face feature data. In addition, the encryption scheme does not require large computing resources, and the accuracy of face recognition in cipher text is exactly the same as that in explain. At present, most of the solutions either have high computational complexity or poor security performance. How to reduce the computational complexity and improve the real-time performance of the system while ensuring the high security of the private data has important research significance and value. Therefore, in the cloud server outsourcing computing environment, how to complete biometric identification on the premise of protecting the privacy of biological data has become a research hot spot.

With the rapid development of artificial intelligence technology, digital transformation has opened up a new path for intelligent operation and maintenance of power grid production project management. Aiming at the problem that traditional operation and maintenance mode is difficult to dynamically adapt to real-time changes of equipment status, complex task scheduling and emergency response, this study proposes a new intelligent operation and maintenance decision-making optimization model based on deep reinforcement learning. The core adopts deep double-Q network algorithm. Through reinforcement learning framework, the model takes equipment operating parameters (temperature, current, voltage, etc.) as inputs, combines experience playback and target network mechanism, and dynamically generates operation and maintenance policies. Experiments show that compared with CNN, LSTM and the original DQN algorithm, the deep double-Q network performs best on cumulative reward (1,643.2) and discounted cumulative reward (2,198.5), and the convergence speed is improved by about 25%. The actual deployment in the regional power grid verifies its effectiveness in minute-level fault response and resource optimization, with an operation and maintenance cost reduction rate of 21.3%. This study provides a reusable methodological framework for grid intelligent operation and maintenance, and helps to improve the efficiency of life cycle management.

To solve the problem that offshore wind power generation is susceptible to extreme weather conditions that result in low accuracy of monitoring data, this work proposes a method for predicting offshore wind power generation output by combining convolution and attention mechanisms. The method combines bidirectional long and short-term memory (BiLSTM) network with attention mechanism (AM). The input data are first weighted with the AM for reducing the predictive weight of the interference data, and then the attention mechanism-weighted data are fed into the BiLSTM network. The bi-directional propagation neural network can effectively utilize all the input information, resulting in higher prediction accuracy. The method of combining BiLSTM network with AM is compared with the method employing long and short-term memory network, gated recurrent unit, and bidirectional long and short-term memory network alone through simulation. The mean square error (MSE) of the BiLSTM combined with AM method is 41.28% smaller than the MSE of the best LSTM method among the compared methods and 58.43% smaller than the average of the compared methods. The R2-R-Square is 14.21% larger than the R2-R-Square of the LSTM and 32.91% larger than the average of the compared methods. The results show that the proposed method of combining convolution and attention mechanism for offshore wind power generation output prediction has higher prediction accuracy.

With the rapid development of artificial intelligence (AI) technology, the field of education has ushered in new opportunities and challenges. Especially in college English teaching, the application of AI provides new possibilities for improving the teaching effect. This paper aims to explore how to effectively improve the quality of college English teaching in the context of AI. By analyzing the current situation and problems in college English teaching and combining them with the development of AI technology, this paper puts forward corresponding strategies and schemes, aiming to provide reference for college English teaching.

Modern science network technology and artificial intelligence have achieved rapid development in a short period of time, and have become the most critical scientific and technological elements of the contemporary era. With the continuous development of artificial intelligence technology, information technology teaching has also ushered in new opportunities and challenges. How to carry out effective information technology teaching research under the background of artificial intelligence is one of the topics that need to be deeply discussed in the current education field. On the one hand, the development of artificial intelligence technology provides more possibilities and means for information technology teaching. On the other hand, the development of artificial intelligence technology has also brought new challenges to information technology teaching. This paper takes artificial intelligence as the background, analyzes the influence of artificial intelligence on information technology education, and expounds the teaching application of information technology under the background of artificial intelligence.

In the rapidly evolving field of cybersecurity, the integration of multi-source, heterogeneous, and fragmented data into a coherent knowledge graph has garnered considerable attention. Such a graph elucidates semantic interconnections, thereby facilitating sophisticated analytical decision support. Central to the construction of a cybersecurity knowledge graph is Named Entity Recognition (NER), a critical technology that converts unstructured text into structured data. The efficacy of NER is pivotal, as it directly influences the integrity of the knowledge graph. The task of NER in cybersecurity, particularly within the Chinese linguistic context, presents distinct challenges. Chinese text lacks explicit space delimiters and features complex contextual dependencies, exacerbating the difficulty in discerning and categorizing named entities. These linguistic characteristics contribute to errors in word segmentation and semantic ambiguities, impeding NER accuracy. This paper introduces a novel NER methodology tailored for the Chinese cybersecurity corpus, termed CSBERT-IDCNN-BiLSTM-CRF. This approach harnesses Iterative Dilated Convolutional Neural Networks (IDCNN) for extracting local features, and Bi-directional Long Short-Term Memory networks (BiLSTM) for contextual understanding. It incorporates CSBERT, a pre-trained model adept at processing few-shot data, to derive input feature representations. The process culminates with Conditional Random Fields (CRF) for precise sequence labeling. To compensate for the scarcity of publicly accessible Chinese cybersecurity datasets, this paper synthesizes a bespoke dataset, authenticated by data from the China National Vulnerability Database, processed via the YEDDA annotation tool. Empirical analysis affirms that the proposed CSBERT-IDCNN-BiLSTM-CRF model surpasses existing Chinese NER frameworks, with an F1-score of 87.30% and a precision rate of 85.89%. This marks a significant advancement in the accurate identification of cybersecurity entities in Chinese text, reflecting the model’s robust capability to address the unique challenges presented by the language’s structural intricacies.

Short-term traffic flow prediction (STFP) is one of the key technologies in Intelligence Transportation System (ITS). With the development of artificial intelligence technology, deep learning has been employed to STFP and certain achievements have been obtained. However, further improvement of STFP accuracy is constrained by the presence of noise, modal aliasing in the modal components and insufficient feature extraction of neural networks. Therefore, to more accurately capture the changing trend of traffic flow in different time periods, and increase the reliability and interpretability of the prediction models, improved variational mode decomposition (IVMD) and self-attention mechanism (SAM) based hybrid convolutional neural network (CNN) and long short term memory network (LSTM) are proposed for STFP in this study, benefited from the modal decomposition of IVMD and redistribution of the neural weights in CNN-LSTM networks by SAM, the proposed IVMD-CNN-LSTM-SAM effectively suppresses the influence of randomness and volatility of traffic flow, and accurately predict the short-term lane occupancy in the designated area. Furthermore, this study analyses the mechanism of SAM and IVMD in STFP, and proves the superiority of IVMD and SAM in signal decomposition with physical significance and weight allocation respectively. Therefore, the interpretability of the proposed neural network model is significantly improved. Eleven competitive neural networks forecasting methods are used as benchmarks and numerical studies based on actual traffic flow validate the accuracy and stability of the proposed IVMD-CNN-LSTM-SAM. Mean absolute percentage error and goodness of fit of the proposed model are 0.81% and 0.9968, respectively.

随着人工智能技术的不断发展，AI学习工具在高等教育领域的应用日趋广泛。高等数学作为大学理工科学生的核心基础课程，其学习成效和解题效率直接影响学生的逻辑思维与专业素养。本文以大学生高等数学学习为研究对象，基于人工智能赋能的教育技术视角，分析了传统教学中学生解题效率低下的主要成因，包括学习动机不足、教师反馈滞后及教学资源碎片化等问题。在文献综述与案例分析的基础上，探讨了AI学习工具通过知识图谱构建、实时智能诊断与个性化练习推送等机制实现效率提升的内在逻辑。研究结果表明，AI学习工具能有效促进学生从“机械套用公式”向“逻辑化与系统化思维”转变，显著改善问题解决效率与思维质量。同时，文章指出了AI应用中存在的技术可靠性、学生依赖性及教学设计精准度不足等挑战，并提出了以“AI赋能—教师引导—学生反思”为核心的协同改进路径。研究旨在为高等数学课程的智能化教学提供理论参考与实践启示。With the continuous development of artificial intelligence technology, AI learning tools have been increasingly widely applied in the field of higher education. As a core foundational course for university students majoring in science and engineering, higher mathematics exerts a direct impact on students' logical thinking and professional literacy through its learning effectiveness and problem-solving efficiency. Focusing on college students' higher mathematics learning, this paper, from the perspective of educational technology empowered by artificial intelligence, analyzes the main causes of students' low problem-solving efficiency in traditional teaching, including insufficient learning motivation, delayed teacher feedback, and fragmented teaching resources. Based on a literature review and case analysis, the paper explores the internal logic through which AI learning tools enhance efficiency via mechanisms such as knowledge graph construction, real-time intelligent diagnosis, and personalized exercise recommendation. The research results show that AI learning tools can effectively promote the transformation of students' thinking from "mechanical application of formulas" to "logical and systematic thinking," significantly improving problem-solving efficiency and the quality of thinking. Meanwhile, the paper points out challenges existing in the application of AI, such as insufficient technical reliability, excessive student dependence, and inadequate accuracy in instructional design. It further proposes a collaborative improvement path centered on the "AI empowerment - teacher guidance - student reflection" model. The study aims to provide theoretical references and practical insights for the intelligent teaching of higher mathematics courses.

With the rapid development of artificial intelligence technology, its application in the field of education has gradually become a research hotspot. Aiming at the problems of strong subjectivity and poor assessment accuracy of traditional entrepreneurial intention assessment methods in entrepreneurship education (EE), the study proposes a method for assessing students’ entrepreneurial intention based on residual network and multi-attention mechanism. The method captures the local features of student data through multi-scale convolution and captures the global dependencies using the Transformer model, so as to realize the complementarity and fusion of features. On this basis, the study further introduces a multi-attention mechanism to weigh the features from multiple perspectives in order to capture the relationship between the features more comprehensively. Through the combination of the improved residual network and the multi-attention mechanism, an efficient model for assessing students’ entrepreneurial intention is constructed. The results indicated that the accuracy of the proposed model was as high as 0.923, which was improved by 16.7% compared with the traditional model, the area under the curve was improved by 13.0%, and the recall and F1 score of the model were increased by 17.2% and 15.4%, respectively. The results showed that the method outperformed all existing methods and provides data support for EE in colleges and universities by accurately assessing students’ entrepreneurial intentions. The results can help colleges and universities optimize their curriculum, resource allocation, and teaching mode, thus enhancing the overall efficiency of EE.

Current temperature prediction methods often focus on time-series information while neglecting the contributions of different meteorological factors and the context of varying time steps. Accordingly, this study developed a Dual-Attention-BiLSTM (a bidirectional long short-term memory network with dual attention mechanisms) network model, which integrates a bidirectional long short-term memory (BiLSTM) network model with random forest-based feature selection and two self-designed attention mechanisms. A sensitivity analysis was conducted to evaluate the influence of the attention mechanisms. This study focuses on Shijiazhuang City, China, which has a temperate continental monsoon climate with significant seasonal and daily variations. The data were sourced from ERA5-Land, comprising hourly near-surface temperature and related meteorological variables for the year of 2022. The results indicate that integrating the two attention mechanisms significantly improves the model’s prediction performance compared to using BiLSTM alone. The mean absolute error between simulation results ranges from 0.80 °C to 1.08 °C, with a reduction of 0.17 °C to 0.39 °C, and the root mean square error ranges from 1.17 °C to 1.37 °C, with a reduction of 0.12 °C to 0.22 °C.

With the development of artificial intelligence technology, the stock market has entered a new research stage. Machine learning algorithm is widely used in the prediction of financial time series. The highest price of a stock is an important factor to measure the price of a stock. For this reason, this paper uses three representative historical data of American stocks as the research object to analyze the short-term price trend. In addition to the original short and long term memory networks, in order to improve the accuracy of prediction, we put forward a prediction model combining particle swarm optimization algorithm and long - and short-term memory neural network. Through empirical research, the PSO optimization algorithm proposed for LSTM model can quickly find the optimal network weight of the neural network, reduce the loss function, achieve the effect of rapid fitting, and has a more accurately predicted results.

Marx's thought on the division of labor in the era of artificial intelligence requires new interpretation and understanding. The development of artificial intelligence technology has profoundly changed the mode and nature of the division of labor, leading to the disappearance of traditional labor methods and the lowering of occupational barriers, providing a realistic path for the "elimination of division of labor" proposed by Marx. Through the analysis of the concept and historical evolution of the division of labor, drawing on Marx's thought on the division of labor, this article explores in depth the refinement and transformation of the division of labor in the era of artificial intelligence. The article argues that the development of artificial intelligence technology helps to solve the problems brought about by the division of labor in the industrial era, promote the reform of the social division of labor, and promote the free and comprehensive development of human beings. KEYWORDS: Artificial Intelligence, Marx; Division of Labor, Labor Force, Productivity

The development of Artificial Intelligence technology can be used to speed up the process of resolving disputes in Islamic law, especially its use in resolving inheritance disputes. Artificial Intelligence technology has emerged as a potential tool for accelerating and increasing the efficiency of resolving disputes over Islamic inheritance. This article aims to analyze the use of Artificial Intelligence technology in accelerating the settlement of inheritance disputes in Islamic family law, policy formulations for the use of Artificial Intelligence technology in accelerating the settlement of inheritance disputes, and Opportunities and challenges of using Artificial Intelligence technology in accelerating the settlement of inheritance disputes in Islamic law in the era of the ASEAN community 5.0. This research method is juridical-normative through a conceptual approach. The data used is secondary data collected through library research. The results of this study indicate that the use of Artificial Intelligence in resolving Islamic inheritance disputes can assist the process of resolving inheritance disputes by automating several tasks, accelerating decision-making, and reducing costs. Artificial Intelligence technology can provide many benefits if it is implemented carefully and by prevailing Islamic principles, and the use of AI technology in the settlement of inheritance disputes in Islamic law in the era of the ASEAN Community 5.0 offers great opportunities to increase efficiency and accuracy. However, the use of Artificial Intelligence technology in resolving inheritance disputes also has several challenges.

Purpose: The development of artificial intelligence technology can undoubtedly trigger profound changes in the labor market. Empirical analysis of the impact of artificial intelligence on the employment environment and its mechanism can propose effective paths to optimize the employment environment, which can effectively promote the improvement of the employment environment for Chinese labors and the stability of the employment situation. Based on the limitations of the development of artificial intelligence technology in China, this study focuses on studying its impact on the employment environment in the short term, and the long-term effects on the employment environment in China will become the author's future focus and research direction. Methodology: This study uses quantitative research methods, based on Panel data of 30 provinces in China from 2009 to 2019, and uses program computer software Stata 17.0 for data processing and empirical analysis. Conclusion: AI technology has a significant positive role in promoting the employment environment, and the new Information infrastructure represented by the Internet is conducive to promoting the positive moderating of AI on the employment environment. Through further research, it was found that the employment environment improvement effect of AI technology has regional differences, with a greater impact on the employment environment in the eastern region than in the western region, while the impact on the central region is not significant.