International Journal of Engineering Intelligent Systems

Intelligent Decision-Making System for Power Grid Dispatching Based on Generative AI

Yu Liu, Weihua He, Jianfei Zhu, Ran Yang, Xinrui Yang — Thu, 01 Jan 2026 00:00:00 -0800

With the current intelligent decision-making system for the power grid (PG), it is difficult for dispatching mechanisms to automatically update theirdecision logic according to the changing PG status and external environment, and to predict new risks in advance and make adaptive adjustments. In this study, an intelligent decision-making system is constructed for PG dispatching to improve itsintelligence and risk response capabilities. This study collected historical load, grid status and meteorological conditions data, sampled them in 5-minute units, and constructed a data set. The CGAN (Conditional Generative Adversarial Network) was used to take grid status, historical load data, meteorological conditions, etc., as conditional inputs, and generates different risk scenario data through adversarial training. CNN (Convolutional Neural Network) was used to extract local features, which were then input into Bi-LSTM (Bidirectional Long Short-Term Memory Network) for sequence modeling and grid risk identification. The identified risk category and current grid status are used as input, and DQN (Deep Q-Network) uses experience replay and ?-greedy strategy to make scheduling decisions. The results show that the average risk identification accuracy rate in various risk scenarios reached 98.1%, and the average identification precision rate reached 97.8%. Compared with the average response time of 7.4s for traditional systems, the average response time of this system was 1.2s. In various risk scenarios, the average supply and demand balance rates of this system and traditional systems were 0.97 and 0.93 respectively.
Therefore, the intelligent decision-making system proposed in this paper can cope with the changing grid status and external environment, accurately identify risks and respond quickly, showing its broad potential in smart grid applications.

Keywords: Power Grid Dispatching, Intelligent Decision-making System, Generative Artificial Intelligence, Conditional Generative Adversarial Networks, Risk Identification

Cite As

Y. Liu, W. He, J. Zhu, R. Yang, X. Yang, "Intelligent Decision-Making System for Power Grid Dispatching Based on
Generative AI", Engineering Intelligent Systems, vol. 34 no. 1, pp. 5-16, 2026.

Exploration of Enhancement Effect in Natural Language Understanding Task Based on BERT Model with Integrated Power Knowledge Graph

Weidong Guo, Yubin Xu, Zhifeng Shi, Xuefeng Hu, Huiping Zhang, Lei Feng — Thu, 01 Jan 2026 00:00:00 -0800

In response to the problems of poor domain adaptability and the weak knowledge fusion ability of traditional language models in NLU (Natural Language Understanding) tasks, which prevent them from fully capturing deep relationships in context, this studyaims to integrate power knowledge graphs to enhance the effectiveness of BERT (Bidirectional Encoder Representations from Transformers) models in NLU tasks, enabling them to more accurately infer the terminology and contextual meanings pertaining tothe electricityfield, thereby improving training efficiency and model performance, and promoting the development of automation in this field. The performance evaluation results of the BERT model integrating power knowledge graph in NLU tasks were: an average path length of 3.8, language similarity of 0.9, and vocabulary coverage of 0.8, all of which were superior to other models used for comparison. The experimental results showed that the BERT model integrating a power knowledge graph had better performance compared to other models commonly used for processing NLU tasks.

Keywords: power knowledge graph; BERT model; natural language understanding; power sector; knowledge fusion

Cite As

W. Guo, Y. Xu, Z. Shi, X. Hu, H. Zhang, L. Feng, "Exploration of Enhancement Effect in Natural Language Understanding Task
Based on BERT Model with Integrated Power Knowledge Graph", Engineering Intelligent Systems, vol. 34 no. 1, pp. 17-26, 2026.

Experimental Detection Data Collection Based on Intelligent Access Adaptation

Shu Yang, Ziqiang Zhou, Wei Gao, Qiang Xue, Jiani Zhang — Thu, 01 Jan 2026 00:00:00 -0800

The real-time collection and processing of experimental and testing data are crucial for ensuring product quality and promoting technological innovation in the fields of industry and scientific research. However, traditional data collection methods suffer from issues such as insufficient standardization, inconsistent interfaces, and delayed data processing, which limit the effective utilization of data. This study investigated a method for collecting experimental detection data based on intelligent access adaptation, aiming to address the aforementioned challenges. The research involved the design of a RESTful API (Representative State Transfer Application Programming Interface) and a unified interface in JSON (JavaScript Object Notation)
format, and the construction of a real-time data stream processing platform based on Apache Kafka. ElasticSearch and Pandas libraries were used to intelligently adjust data formats, and gRPC (Google Remote Procedure Call) protocol and Protobuf (Protocol Buffer) data format was used to optimize data transmission efficiency. In regard to the effectiveness of the proposed method, the experimental group reduced data collection latency by about 28.7% compared to traditional methods, demonstrated by the reduction in the page loading time from 738 milliseconds to 526 milliseconds, and a performance score of 92 points, significantly higher than the control group’s 68 points. In terms of classification accuracy, the experimental group achieved an accuracy rate of over 96% in five data acquisition scenarios: electricity, meteorology, magnetic field, distance, and velocity. The recognition precision of the electricity category reached 0.988. The testing of interface compatibility showed that the experimental group exhibited total compatibility, while the control group had multiple compatibility deficiencies. The system throughput monitoring shows that the throughput of the experimental group is closer to the target value, indicating greater processing efficiency.

Keywords: intelligent access; data collection; real-time processing; experimental testing; Internet of Things; data adaptation

S. Yang, Z. Zhou, W. Gao, Q. Xue, J. Zhang, "Experimental Detection Data Collection Based on Intelligent Access Adaptation", Engineering Intelligent Systems, vol. 34 no. 1, pp. 27-38, 2026.

Construction of English Wisdom Classroom Based on Educational Big Data Mining

Hui Gao, Xiaotian Wei, Xiaohui Tang — Thu, 01 Jan 2026 00:00:00 -0800

The aim of this study is to explore the academic outcomes resulting from the implementation of an intelligent classroom based on educational big data mining in English teaching. Ninety-eight students at HS middle school were randomly divided into two groups: experimental and control. The experimental group were exposed to wisdom classroom teaching, while traditional teaching methods were used for the control group. The results showed that the experimental group performed significantly better than the control group in terms of English scores, online learning time, assignment submission frequency, class interaction frequency, and course satisfaction. Students in the experimental group showed higher learning motivation and self-efficacy. Moreover, the evaluation of technology use in the smart classroom also received positive feedback, indicating low frequency technical failure and high user-interface friendliness. These findings validate the effectiveness of the smart classroom in improving students’ learning outcomes, enhancing attitude to learning, and optimizing teaching-student interaction. The study results highlight the application potential of big data technology in the field of education and provides important a scientific basis and practical guidance for future education models.

Keywords: English wisdom classroom; Big data mining; Teaching application; Controlled experiment

Cite As

H. Gao, X. Wei, X. Tang, "Construction of English Wisdom Classroom Based on Educational Big
Data Mining", Engineering Intelligent Systems, vol. 34 no. 1, pp. 39-47, 2026.

College Students’ Entrepreneurial Intention and Personal Career Planning Based on Fuzzy Logic

Ming Dai — Thu, 01 Jan 2026 00:00:00 -0800

This study uses fuzzy logic analysis technology to explore the evaluation model of college students ‘entrepreneurial intention and its application in personal career planning. By identifying the key factors affecting entrepreneurial intention, such as personal ability, intrinsic motivation, self-efficacy, social network, family background and educational environment, and using fuzzy logic modeling, this study constructs a comprehensive evaluation model of entrepreneurial intention. In addition, the model considers external conditions such as economic environment, policies and regulations, and industry dynamics, providing a comprehensive decision support system for college students. Through empirical research, this study verifies the validity of the model in predicting and guiding college students ‘career planning. The model analyzes the degree of entrepreneurial intention and calculates the weight of influencing factors derived from the data collected via a questionnaire survey.

Keywords: entrepreneurial intention, fuzzy logic, college students, personal career planning

Cite As

M. Dai, "College Students’ Entrepreneurial Intention and Personal Career Planning Based on Fuzzy Logic", Engineering
Intelligent Systems, vol. 34 no. 1, pp. 49-60, 2026.

Discourse Strategies of Artificial Intelligence in Cross-Cultural Business Communication

Tingfang Zhang — Thu, 01 Jan 2026 00:00:00 -0800

This study explores the use of artificial intelligence to identify discourse strategies in cross-cultural business communication. By constructing and optimizing the BERT model, it aims to improve the efficiency and accuracy of business communication in different cultural contexts. The research comprises the application of cross-cultural business communication theory and discourse strategies, data collection and processing, BERT model construction and training, performance evaluation and optimization. The experimental results show that the optimized BERT model is excellent at identifying discourse strategies, significantly improving communication success and customer satisfaction, while reducing misunderstandings and conflicts. The research shows that AI technology has important application value in cross-cultural business communication, and provides strong technical support for efficient communication of enterprises in the context of globalization.

Keywords: AI, business communication, cross-cultural, discourse strategy

Cite As

T. Zhang, "Discourse Strategies of Artificial Intelligence in Cross-Cultural Business Communication",
Engineering Intelligent Systems, vol. 34 no. 1, pp. 61-71, 2026.

Accounting Information Cloud Data Integrity Verification Algorithm Based on Data Mining

Yong Hou — Thu, 01 Jan 2026 00:00:00 -0800

This study was conducted to explore the accounting information cloud data integrity verification algorithm based on data mining technology, focusing on evaluating its effect and accuracy in practical applications. By choosing the decision tree algorithm and the association rule mining algorithm, the financial data of xx enterprise is verified by experiment. The results show that the decision tree algorithm is superior to the association rule mining algorithm in terms of classification accuracy and expansivity, and has high practical value. It was found that there is a significant correlation between revenue, cost, expense and profit, and that data mining technology can significantly improve data processing efficiency and decision support ability. This study provides strong support for improving the data integrity and security of accounting information systems, and provides a theoretical basis
and practical guidance for enterprise financial management and decision optimization.

Keywords: data mining; Accounting information; Integrity; Algorithm application

Cite As

Y. Hou, "Accounting Information Cloud Data Integrity Verification Algorithm Based on Data Mining",
Engineering Intelligent Systems, vol. 34 no. 1, pp. 73-83, 2026.

Intelligent Transformation of Fitness Industry Based on Experimental Analysis: Evidence from the Fitness Apps by Chinese College Students

Hua Wei, Juxiang Xiao, Deng Pan — Thu, 01 Jan 2026 00:00:00 -0800

The latest generation of digital technology raises new opportunities and challenges for the development of the physical fitness industry. How to improve the impact of fitness apps on college students’ exercise is a current research hot-spot. The purpose of this study was to explore the macro environment and micro scenario of the intelligent transformation of the physical fitness industry in the Chinese context. The study investigates the dynamic framework of China’s fitness industry and explores the influence of fitness apps on college students’(N=604) physical and mental well-being. SPSS 22.0 was used to conduct data analysis. The following conclusions were reached: (1) Fitness apps were positively associated with college students’ well-being(p<0.01); (2) Personal exercise via fitness apps mediated the relationship between college students’ mental and physical health; (3) College students exercise adherence as well as subjective exercise experience and exercise adherence.

Keywords: fitness apps; digital technology; intelligent transformation; college students

Cite As

H. Wei, J. Xiao, D. Pan, "Intelligent Transformation of Fitness Industry Based on Experimental
Analysis: Evidence from the Fitness Apps by Chinese College Students", Engineering Intelligent
Systems, vol. 34 no. 1, pp. 85-96, 2026.

Art Health Product Design and User Experience Optimization Based on Fuzzy Algorithm

Tingting Ma, Yodkwan Sawadee — Thu, 01 Jan 2026 00:00:00 -0800

With the improvement of living standards, consumers’ demand for health products that have both aesthetic qualities and health functions is increasing. However, due to the diversity and uncertainty of user needs, traditional design methods are unable to meet personalized and multidimensional design requirements. Hence, this study discusses the art health product design and user experience optimization based on fuzzy algorithm. The fuzzy algorithm quantifies the user requirements, builds the optimization model, and achieves the design optimization of functionality, appearance design, comfort and other dimensions. The results show that the fuzzy algorithm can significantly improve user satisfaction in terms of functionality, comfort and ease of use. After further analysis of user feedback, the research proposes future optimization directions in regard to personalized regulation and material improvement. Therefore, the research provides scientific theoretical support and practical reference for the innovative design of art health products, and helps to enhance user satisfaction with the product, and strengthen its market competitiveness.

Keywords: fuzzy algorithm; art health products; user experience optimization

Cite As

T. Ma, Y. Sawadee, "Art Health Product Design and User Experience Optimization Based on
Fuzzy Algorithm", Engineering Intelligent Systems, vol. 34 no. 1, pp. 97-108, 2026.

College English Translation Intelligent Systems Technology Based on Multi-Source Information Corpus Acquisition and Data Fusion

Wentao Meng, Lei Yu, Yunyun Zhu — Thu, 01 Jan 2026 00:00:00 -0800

Translation scenarios for college English are moving in interdisciplinary and cross-disciplinary directions, meaning that traditional methods that rely on limited textbook materials are unable to meet the diverse needs of students. To solve the problems of insufficient coverage of multi-source corpora and limited adaptability of translation models, a corpus acquisition framework integrating knowledge discovery and domain discrimination was developed, and a translation model based on data fusion was designed. By using a web crawling system to capture bilingual discourse level corpora in new fields, and combining sentence segmentation strategies and dynamic programming to optimize alignment accuracy, high-quality parallel corpora
were generated. At the same time, a bidirectional encoder representation combined with WordPiece model was proposed to enhance sequence annotation performance by integrating part-of-speech and syntactic dependency features. The experiment outcomes showed that the proposed model had an accuracy of 0.92 and a processing time of only 12 seconds. For the translation, the proposed model had an accuracy close to 1.0 after 900 iterations, a false positive rate reduced to 0.05, and a translation time of 16 seconds, significantly better than traditional models. The results indicate that multi-source corpus acquisition and data fusion techniques can effectively enhance the processing capability of translation systems for complex contexts, providing high-precision solutions for interdisciplinary English translation.

Keywords: Multi-source information; Corpus; Data fusion; Bidirectional encoder; WordPiece

Cite As

W. Meng, L. Yu, Y. Zhu, "College English Translation Intelligent Systems Technology Based on Multi-Source
Information Corpus Acquisition and Data Fusion", Engineering Intelligent Systems, vol. 34 no. 1, pp. 109-118,
2026.

Optimization of Course Sequence in Private Universities Based on Random Forest and Association Rules

Junhong Liu, Yan Tu, Wensong Yu, Ruiping Hou — Thu, 01 Jan 2026 00:00:00 -0800

The learning process of college students is a gradual one. The study of prerequisite courses helps students build a knowledge foundation, enabling them to more easily achieve flow experience in subsequent courses, which has a significant impact on their course satisfaction. This study took 372 upgraded students majoring in Tourism Management at GuangzhouVocational and Technical University of Science and Technology as samples. The study investigated their satisfaction with 15 professional courses and overall course satisfaction, conducted decision tree model and random forest model analyses to identify the important professional courses affecting overall course satisfaction, and then used the association rules model to mine the prerequisite courses of these important professional courses. The results show that Tourism Psychology, Ecotourism, Tourism English,
Tourism Hospitality, and Tourism Consumer Behavior are important professional courses affecting overall course satisfaction, and there are valuable associations between important professional courses and other professional courses. The conclusion indicates that by scientifically formulating the teaching sequence of professional courses in private universities, this can significantly improve overall course satisfaction.

Keywords: flow theory, random forest, association rules, course sequence

Cite As

J. Liu, Y. Tu, W. Yu, "Optimization of Course Sequence in Private Universities Based on Random Forest
and Association Rules", Engineering Intelligent Systems, vol. 34 no. 1, pp. 119-127, 2026.

Identification and Guidance of Intimate Relationships Among Students Based on Reinforcement Learning

Guang Du, Xiao Ju, Yumo Ding — Thu, 01 Jan 2026 00:00:00 -0800

With regard to digital education management, the massive amounts of student behavioral data contain complex relationship information. Importantly, the intimate relationships of students have a significant impact on their mental health and the school’s education and teaching environment. Traditional student relationship management methods and existing analysis technologies have limitations in processing complex data and guiding student relationships. This study proposes an intelligent fusion network (IFN) model, which consists of a feature extractor, an information integrator, and a decision generator. By harnessing the collaborative operation of multiple components, it analyzes student relationship data. Experiments on a public campus social relationship dataset show that the IFN model has an 80% relationship recognition accuracy and scores 85% for the effectiveness
of guidance strategy, which is a significant improvement compared with the social network analysis model (recognition accuracy 40%, guidance strategy effectiveness 40%) and the support vector machine model (recognition accuracy 50%, guidance strategy effectiveness 50%). The research results confirm that the IFN model can effectively mine students’ intimate relationship information and provide reasonable guidance strategies. This study provides scientific and accurate decision support for school education management, enriches the theoretical content of educational technology in relationship analysis and intervention, and also provides a reference for subsequent research on the integration of technology and educational concepts.

Keywords: student intimacy, intelligent fusion network, relationship identification, guidance strategy, educational technology

Cite As

G. Du, X. Ju, Y. Ding, "Identification and Guidance of Intimate Relationships Among Students Based on
Reinforcement Learning", Engineering Intelligent Systems, vol. 34 no. 1, pp. 129-138, 2026.