International Journal of Internet Protocol Technology (24 papers in press)

Regular Issues

• Optimising Student Performance Prediction Using DTC Enhanced with WOA and ECPO  
  by Lijuan Gao, Caiyan Chen 
  Abstract: To enhance academic outcomes in today's competitive educational environment, institutions must proactively predict student performance, classify students based on skill levels, and provide early guidance. Forecasting student success using past performance can help reduce failure rates and implement targeted interventions. Educational data exploration employs analytical techniques to identify trends in teacher and student data, offering valuable insights for planning and forecasting. This study combined two advanced optimization techniques: the Waldrus Optimization Algorithm (WOA) and Electric Charged Particles Optimization (ECPO), with Decision Tree Classification (DTC) to predict student outcomes. Standard performance metrics, including precision, accuracy, recall, and F1-score, were used for evaluation. Results indicated that both optimisers significantly improved the model's effectiveness. DTC+ECPO excelled in the "Acceptable" performance category, while DTC+WOA was highly effective in identifying "Poor" performance students. These findings validate WOA and ECPO as robust tools for predictive analytics and early academic intervention.
  Keywords: Student success; DTC; Walrus Optimization Algorithm; Electric Charged Particles Optimization.
  DOI: 10.1504/IJIPT.2026.10074169
   
  
• Time Series Prediction of Stock Market Movements by Utilising the BRO-SVR Hybrid Model: A Case Study of the Shanghai Stock Exchange  
  by Weishuang Xu, Daming Li, Siqi Hao 
  Abstract: Predicting future stock prices is challenging due to numerous uncontrollable factors. However, data-driven methods have enabled more accurate forecasts despite inherent uncertainties. Traditionally, such forecasts relied on technical and fundamental indicators. With advancements in Machine Learning (ML), prediction accuracy and accessibility have significantly improved. This study presents a novel approach that integrates the Battle Royale Optimisation (BRO) algorithm with an enhanced support vector regression model to predict stock prices. Applied to data from the Shanghai Stock Exchange, the proposed model demonstrated high prediction accuracy. It consistently outperformed existing methods, significantly improving time series forecasting of stock values. High R
  Keywords: Stock Price Prediction; Support Vector Regression (SVR); Battle Royale Optimization (BRO); Shanghai Stock Exchange (SSE); Machine Learning (ML); Metaheuristic Algorithms; Time Series Forecasting.
  DOI: 10.1504/IJIPT.2026.10074741
   
  
• RSSCE: A SAM-Based MapReduce Framework for Mining Uncertain Big Data in Cloud Environments  
  by Huiguo Dong, Jing Zhang, Qinlu He 
  Abstract: The exponential growth of data generation encompassing text, images and videos through social media and digital platforms has introduced significant challenges in extracting meaningful insights. While big data presents numerous opportunities, leveraging it effectively for business and decision-making remains a key focus of information technology. Data retrieval aims to transform vast, unstructured data sets into valuable information, with particular emphasis on identifying frequent patterns repeated items, substructures or sequences that meet user-defined thresholds. Owing to the immense data volume, users often operate on specific subsets, thereby limiting the search space. To address this, a technique utilising the Search Area Minimisation (SAM) approach integrates user-defined constraints to narrow the search field and highlight relevant patterns. Experimental results across deterministic and uncertain data sets. This proposed approach provides a scalable and reliable solution for frequent pattern mining in big data environments, enabling focused and effective analysis based on user preferences and uncertainty management.
  Keywords: Big Data; Uncertain Data; Frequent Pattern Extraction; Search Space Reduction; User Constraints; MapReduce Framework; SAM Technique; Data Analysis; Non-Deterministic Databases.
  DOI: 10.1504/IJIPT.2026.10074763
   
  
• Mitigating Subjective Bias in Football Player Valuation Using Hybrid ANFIS with Bio Inspired Optimisation Algorithms  
  by Pengyu Qi, Xia Liu, Tao Yan, Xin Zhou 
  Abstract: Football is one of the most extensively followed sports worldwide, with athletes from numerous countries participating in regional and international tournaments, demonstrating both skill and dedication. The market value of footballers serves as a critical metric for evaluating their actual worth and overall quality. To estimate the market value of football players, an Adaptive Neuro-Fuzzy Inference System (ANFIS) was employed. Additionally, two advanced metaheuristic algorithms the Weevil Damage Optimisation Algorithm (WDOA) and the Wild Geese Optimisation Algorithm (WGOA) were integrated to enhance the predictive accuracy of the ANFIS model. These integrations resulted in two hybrid models: ANFIS + WDOA (ANWD) and ANFIS + WGOA (ANWG). Among the models tested, ANWD exhibited the highest performance, achieving an R
  Keywords: Artificial intelligence; Machine learning; Market value; Football; Adaptive neuro-fuzzy inference system; Weevil damage optimization algorithm; Wild geese optimization algorithm.
  DOI: 10.1504/IJIPT.2026.10074764
   
  
• Predictive Modelling of Financial Crisis in the Environmental Protection Industry Using PCA-Enhanced BP Neural Network and SVM Approaches  
  by Yupeng Li, Ke Sun 
  Abstract: Corporate financial crises are complex and unpredictable, making the establishment of effective early warning mechanisms essential for minimising potential risks. This study assesses the forecasting capabilities of backpropagation neural networks (BPNNs) and support vector machines (SVMs) in predicting financial crises within enterprises. Using data from 92 listed companies in the environmental protection industry, a comprehensive early warning indicator system was created, incorporating 16 financial indicators and 2 non-financial indicators. Principal Component Analysis (PCA) was employed to reduce the dimensionality of financial indicators, extracting six main components. MATLAB-based training and testing revealed that BPNN achieved a precision of 98.39% in the training set, outperforming SVM by 5.17%, and a precision of 93.33% in the test set, surpassing SVM by 7.68%. These results highlight the superior performance of BPNN in early warning systems, offering a robust tool for enhancing financial risk management and decision-making.
  Keywords: corporate financial crisis early warning; principal component analysis; support vector machine; environmental protection industry; back propagation neural network.
  DOI: 10.1504/IJIPT.2026.10074918
   
  
• An Artifact-Centric Design for IoT Interoperability: Implementing Thing Artifacts with Simulation-Based Validation  
  by Fang Liu, JunHui Pang 
  Abstract: The Internet of Things (IoT) technologies have introduced a new generation of connected tools that form complex ecosystems requiring efficient and seamless design. Addressing challenges such as limited size, connectivity, and storage, this study proposes a novel conceptual pattern called the "Thing Artifact" (TA). Unlike previous approaches, which failed to provide comprehensive solutions, the TA pattern abstracts IoT tool roles into operations, lifecycles, and interactions, thereby enhancing collaboration and minimizing conflicts. This work applies the TA pattern to the design and realization of an IoT ecosystem, demonstrating how it facilitates interoperability among heterogeneous IoT devices and ensures smooth operation. The findings indicate that the TA pattern improves efficiency, simplifies operations, and reduces data exchange conflicts. Overall, the TA pattern marks a significant step toward a more holistic and harmonized design and implementation of IoT ecosystems, effectively addressing the typical challenges associated with such environments.
  Keywords: Internet of Things; Thing Artifacts; IoT Ecosystems; Collaborative Relationships.
  DOI: 10.1504/IJIPT.2026.10075156
   
  
• Empowering Education by Harnessing Machine Learning for Predicting Student Readability Score  
  by Huixian LI, Long LI 
  Abstract: Readability refers to the ease or difficulty with which a reader can understand a given text. In this study, machine learning techniques were used to predict students’ reading scores, with Random Forest Classification (RFC) demonstrating promising performance. The effectiveness of RFC, Sooty Tern Optimization Algorithm (RFST), and Gold Rush Optimiser (RFGR) was evaluated using 1,000 English texts based on accuracy, precision, and F1-score. Results show that RFST outperformed RFC and RFGR, achieving an average training accuracy of 0.968 across various reading levels. This superior performance is attributed to its enhanced ability to capture complex linguistic patterns. In contrast, RFC and RFGR achieved accuracies of 0.932 and 0.935, respectively. The study also emphasises the critical role of attribute selection, particularly lexical variables, in improving predictive accuracy. These findings contribute to the advancement of readability assessment and support the development of more accurate readability prediction frameworks.
  Keywords: Readability; Reading Score; Random Forest Classification; Sooty Tern Optimisation Algorithm; Gold Rush Optimiser.
  DOI: 10.1504/IJIPT.2026.10075157
   
  
• Validated Dynamic Modeling and PI-Based Speed Control of Level-One Smart Electric Vehicles Using GT-Suite and MATLAB Integration  
  by Lu Cheng, Junshuai Lu, Jihong Xie, Qiong Tang, Guojun Ye 
  Abstract: Given the imperative to reduce reliance on finite fossil fuel resources and mitigate associated environmental pollution, adopting cleaner energy alternatives becomes imperative. This underscores the significance of advancing electric and hybrid vehicle technologies. In recent times, academia and industries have focused on smart electric cars. They vary in many capabilities, which are the essential constituents of intelligent speed control. This work focuses on the dynamic modeling and longitudinal speed control of a level-one smart electric car employing GTSuite and MATLAB. In the validation of the GTSuite model, experimental open-loop tests are conducted. Next, a proportional-integral controller is designed on both software platforms in an integrated fashion, followed by carefully tuning its parameters. The developed controller is then tested for performance under various conditions: slope of the road, wind effects, and different forms of reference speed inputs.
  Keywords: GTsuite; electric vehicle; Simulink; speed control; dynamic modeling.
  DOI: 10.1504/IJIPT.2026.10075383
   
  
• Refining Mobile Price Predictions: Leveraging regulated Classification and Quadratic Discriminant Analysis for Enhanced Accuracy  
  by Chao Sheng Han  
  Abstract: Future mobile phone prices are forecasted using historical data and selected relevant features. Trends are analyzed by brand and statistical parameters through machine learning methods. This supports consumers in making informed purchasing decisions and enables businesses to develop more effective pricing strategies and manage inventories efficiently. Accurate forecasts enhance market responsiveness, drive competition, and streamline operations. In this study, Quadratic Discriminant Analysis (QDA) and Naive Bayes Classifier (NBC) were employed for price estimation. To optimize these models, two metaheuristic techniques Manta Ray Foraging Optimisation (MRFO) and Escape Bird Swarm Optimisation (EBSO) were applied. MRFO simulates manta ray foraging behaviour for parameter selection, while EBSO mimics bird escape behaviour for fine-tuning. These advanced approaches significantly improved forecasting accuracy and robustness. The QDA model optimised via EBSO, referred to as the QDEB model, achieved superior performance with an accuracy, precision and recall of 0.971, and an F1-score of 0.970.
  Keywords: Mobile Price; Classification; Naïve Bayes Classification; Quadratic Discriminant Analysis; Metaheuristic Algorithm.
  DOI: 10.1504/IJIPT.2026.10075391
   
  
• Application of improved Particle Swarm Optimisation in Intelligent Prediction of Construction Cost  
  by Liangqiong Chen, Hao Zhang, Fang Wang 
  Abstract: In order to understand the application of intelligent prediction of construction project cost, the author proposed an improved particle swarm optimization algorithm in the application of intelligent prediction of construction project cost. With the proposal of the core task of the State Grid Corporation to implement the strategic goal of "three types and two networks and world-class", the traditional cost management mode of the power transmission and transformation projects will be promoted to the information, intelligent and professional cost management mode. The author first introduces the significance of construction project cost prediction, the construction of construction project cost prediction index system, and data pre-processing methods. Secondly, the particle swarm optimisation model with local search is selected to simulate the case project. The results show that the optimal cost of the project is 1224600 yuan, which is consistent with the actual cost results obtained by traditional methods.
  Keywords: Particle swarm; architectural engineering; Intelligent prediction; construction cost.
  DOI: 10.1504/IJIPT.2027.10075422
   
  
• Comparative Evaluation of Machine Learning Based Algorithms for Clinical Treatment Prediction Using EHR Data from China  
  by Gui Wu, Shi Qian, Xin Luo, Rong Bie, Dandan Qu 
  Abstract: The study aimed to assess a variety of Machine Learning tools for predicting treatment outcomes for patients based on the patient's electronic health record. The research framework is about supervised learning and ensemble methods, where algorithms classify the status of patient care learning from clinical data with their labels. Eight ML models were used for comparison, which include Decision Tree, Random Forest, Gradient Boosting, SVM, Gaussian Naive Bayes, and Convolutional Neural Networks. Each model had been optimized by specific hyperparameter tuning, and their performance was assessed using metrics like mean absolute error, mean squared error, Matthew's correlation coefficient, F1 score, and Area Under the Curve of the Receiver Operating Characteristic. The evaluation metrics indicated that the best models are CNN, and AdaBoost. The comparative analysis serves as a reference for identifying apt ML methodologies in clinical decision support and opens a new path towards devising accurate and personalized treatment planning.
  Keywords: Predictions for patient treatment; Machine Learning algorithms; Analysis of clinical data; Comparative evaluations; Performance assessments; Clinical decision support; Electronic health records.
  DOI: 10.1504/IJIPT.2026.10075423
   
  
• Connected Graph with WiFi Network in Distance  
  by Selvaraj Thangaraj, Subramanian S 
  Abstract: This research investigates the optimisation of Wi-Fi networks using graph theory, where access points are modelled as nodes and communication links as edges. By analysing real-world Wi-Fi network data through various graph-theoretic metrics, we identify critical factors that influence network behaviour and performance, revealing significant correlations between these metrics and key performance indicators, such as latency, throughput, and packet loss. The study proposes a comprehensive graph-based framework for adapting Wi-Fi network settings, aiming to enhance network efficiency and user satisfaction. These findings provide valuable insights for the design, management, and optimisation of wireless networks, addressing the complexities inherent in modern digital communication environments and contributing to more reliable and effective connectivity solutions.
  Keywords: Wi-Fi networks; graph theory; performance evaluation; optimisation; access points; user satisfaction; network dynamics; distance metrics; graph metrics; efficiency.
  DOI: 10.1504/IJIPT.2026.10075921
   
  
• Intelligent Support and Content Delivery for ESP Terminology Learning: Design and Validation of NeuroXL-CRFNet  
  by Zhu Lingyi 
  Abstract: This study proposes a teaching assistance model for the cultivation of building informatisation talents based on a distributed architecture. Through the integration of microservice architecture and cloud computing technology, the dynamic scheduling and efficient management of teaching resources are achieved. This model takes modular design as the core, combines key technologies such as service registration discovery and API gateway, and supports high concurrent access and elastic scalability. Experiments showed that the model significantly improved the prediction accuracy by introducing preference factors and attendance behaviour analysis in the performance prediction algorithm. Meanwhile, the system could still maintain a stable response speed in high-concurrency scenarios, and the delay was controlled within an acceptable range. The proposed distributed teaching assistance model is scalable, flexible, and highly available, providing theoretical and practical references for the cultivation of talents in building informatisation.
  Keywords: Edge Computing; Protocol-Aware Networks; Neuro-Symbolic Graph Convolution; Multilingual Content Dissemination; Intelligent Routing; Feature Fusion; Adaptive QoS; Distributed Inference;ESP Terminology.
  DOI: 10.1504/IJIPT.2027.10075943
   
  
• An Internet Protocol-Based IoT and Machine Learning Framework for Enhancing Context-Aware English Translation Services  
  by Yan Li 
  Abstract: This paper proposes an Internet Protocol-based IoT and machine learning framework to enhance context-aware English translation and personalized language learning Traditional English teaching methods often fail to address individual learning differences, leading to reduced student engagement To address this, an IoT-supported learning system is designed to collect real-time learner data including behaviour, emotion and progress across multiple networked devices. A fuzzy logic-based evaluation model is developed to quantify student engagement across four dimensions: learning attitude, learning process, learning effectiveness and emotional experience. The system employs machine learning algorithms to analyse this contextual data, enabling adaptive translation services and targeted engagement strategies. Using a case study involving first-year English majors, the framework demonstrates a significant increase in engagement scores from 71.37 to 88.49 after implementing the proposed improvement mechanism. Results validate the effectiveness of integrating IoT data and intelligent protocols to support adaptive English learning environments and enhance translation accuracy based on real-world context.
  Keywords: Internet of Things (IoT); Internet Protocols Fuzzy Mathematical Model; Student Engagement; Personalized English Learning.
  DOI: 10.1504/IJIPT.2027.10076240
   
  
• Protocol-Sensitive B5G-IoT Learning Architecture for Real-Time Civic-Political Education in College English Writing Streams  
  by Shali Zhou 
  Abstract: The way in which distributed learning frameworks provide real-time communication is being redefined by the fast integration of intelligent Internet of Things (IoT) ecosystems with Beyond 5G (B5G) networks. This study suggests a Protocol-Sensitive B5G-IoT Learning Architecture (PS-BILA) that uses adaptive protocol intelligence to ensure the synchronisation of distributed IoT nodes with cloud-based learning platforms, control latency and boost bandwidth. Utilisation of resources, routing and session continuity may be optimised across dense user contexts with the help of the architecture's protocol-aware control layer. Dynamic transmission protocols that adapt QoS attributes in response to network performance and learner interactions are essential to the PS-BILA architecture, which also includes multi-source data collecting and attention detection based on the Internet of Things. Through the use of mathematical performance metrics including Signal-to-Noise Ratio (SNR), end-to-end latency, content integrity and engagement fidelity, we may evaluate the systems responsiveness and data transfer efficiency. After testing on fifty IoT nodes made possible by B5G technology, the suggested design achieved a total protocol efficiency score of 0.95 with latency of 30 ms, audio SNR of 30 dB and content integrity of 99%.
  Keywords: Protocol-Sensitive Communication; B5G-IoT Framework; Intelligent Learning Systems; Real-Time Education; Civic-Political Learning; College English Writing; Adaptive Streaming.
  DOI: 10.1504/IJIPT.2027.10076295
   
  
• An Optimising English Online Teaching Mode based on Learning Process Data Mining  
  by Fang Wang 
  Abstract: In order to adapt to the development needs of English language ability in the context of globalisation and shorten the gap with current education mode optimisation methods, an optimising English online teaching via learning process data mining using K-prototype clustering and neural evaluation is proposed. Using the K-prototype algorithm to mine process data of English online learning, determine the evaluation index data of English online teaching quality and input the evaluation index data into a fully connected neural network to obtain the teaching quality evaluation results. Optimising English online teaching mode from four dimensions: technology integration, instructional design, teacher-student interaction and resource integration. The experimental results show that the proposed method has a minimum relative error rate of 4.18% in data mining, a maximum improvement rate of 13.19% in exam scores and a maximum knowledge retention rate of 76.37%, which can promote further innovation in the field of education.
  Keywords: Learning process data mining; English online teaching; Mode; Optimization; K-prototype algorithm; Fully connected neural network.
  DOI: 10.1504/IJIPT.2026.10076299
   
  
• Automated Sensor Node Failure Detection and Recovery Procedure in Mobile Wireless Sensor Networks  
  by Supratik Banerjee, Sanjay Kumar Biswash 
  Abstract: Sensor node failure detection and recovery is one of the active research areas. The current literature lacks focus on automated systems for detecting and replacing faulty sensor nodes. To address this gap, we propose two schemes for automatic identification and replacement of faulty sensor nodes deployed in inhospitable terrains. In the first scheme, we propose a methodology to deploy some backup Mobile Sensor Nodes (MSN). In case of MSN failure, a backup MSN is relocated to the area of interest. In the next scheme, we propose to deploy multiple sensor nodes on a single mobile vehicle. One of these sensor nodes is in an active state. The remaining backup sensor nodes stay in sleep mode. As node relocation is not necessary, it reduces the reaction time after sensor node failure. Results show that Scheme 1 requires a longer recovery period compared to Scheme 2. On the other hand, Scheme 2 incurs more deployment costs.
  Keywords: Mobile Wireless Sensor Networks; Named Data Networking; Reliability; Weibull Distribution; Zigbee.
  DOI: 10.1504/IJIPT.2026.10076317
   
  
• Protocol-Aware AI Framework for 5G-Enabled English Translation in University Education Using Intelligent IoT and Machine Learning  
  by Qun Liu 
  Abstract: The integration of fifth-generation mobile communication (5G), artificial intelligence (AI), and smart Internet of Things (IoT) devices is transforming university instruction by enabling protocol or situational-awareness, real-time, and crypto-cognitive learning contexts. This study proposes the use of a protocol-aware AI framework for the English translation of instructional materials in higher education, employing 5G-enabled connections, intelligent IoT devices, and machine-learning algorithms to improve contextual awareness, learner engagement, and educational personalisation. In addition, the protocol-aware AI framework takes advantage of 5G's high bandwidth, ultra-low latency, and massive device connectivity capabilities to enable real-time data collection, intelligent learning analytics, and engaging immersive virtual learning experiences while providing secure and responsive communication between distributed university education modals. This method combines AI language models with IoT- enabled student interaction monitoring and adaptive content delivery to ensure that delivery of translated content and subsequent teaching remains fluid and relevant to the learning context. The experimental results demonstrate significantly improved translation accuracy, learner engagement and content personalisation using the protocol-aware framework versus conventional methods.
  Keywords: Protocol-Aware Framework; AI-Driven Translation; 5G-Enabled Education; Intelligent IoT Systems; Machine Learning in Education; Real-Time Language Processing; Context-Aware Learning; Adaptive Education.
  DOI: 10.1504/IJIPT.2027.10076393
   
  
• AI-Enhanced Nonlinear Economic Modelling for Sports Systems: Linking Material Performance and Cybersecurity Risk in Insurance Cost-Benefit Analysis  
  by Tang Shijie 
  Abstract: This research paper puts forward an AI-Driven Nonlinear Economics Modelling Framework (AI-NLEM) via a hybrid CNN-LSTM architecture aimed at supporting cost-benefit analysis of insurance systems within accountability measures in sport. It achieves this by merging manufacturer-quality material-performance data obtained from SEM and TEM imaging modalities along with logs of cyber vulnerabilities. Preprocessing of images consists of several steps including: denoising; histogram equalisation; augmentation; utilisation of cyber vulnerability data through tokenisation, BERT embeddings, TF-IDF, and DTW. The extraction of features from the images using LBP, Gabor Filters, ResNet50, and CC-GBD models. The optimisation and prediction model was performed using a novel approach called Deep Q-Guided Genetic Evolution which achieved superior predictive performance relative to all baseline models (Accuracy = 0.9957 and AUC = 0.9957). Data provides evidence that accurate risk prediction motivates superior safety equipment; future research will focus on creating real-time, scalable, multimodal systems.
  Keywords: AI-driven economic modeling,Nonlinear optimization,Sports system performance,Material property evaluation,Cybersecurity risk assessment,Insurance cost-benefit analysis,Predictive analytics in sports.
  DOI: 10.1504/IJIPT.2027.10076440
   
  
• Task scheduling optimisation for wireless sensor modules in cloud-based systems  
  by A. Ananya, B.V. Santhosh Krishna, A. Murugavel, C. Sivakumaran 
  Abstract: Scheduling algorithms demonstrate the critical function they play in the cloud data centres in determining a potential time table for the work. Since the goal is to achieve the shortest total execution time, existing research has demonstrated that the job scheduling issue is NP-complete. We address the problem of minimising total layover time by scheduling a set of l jobs across a set of |G| groups and m cloud resources. Here, we describe a pair-based work scheduling method based on the well-known optimisation process known as the Hungarian algorithm for cloud data centres. Two performance indicators, specifically makespan and averaged cloud utilisation, are used to assess their performances via simulation. The method will decrease task waiting times and increase resource efficiency as a consequence. The results of the experiment demonstrate that the suggested technique enhances resource consumption while decreasing task execution times.
  Keywords: task management; Hungarian method; normalisation; cloud computing; makespan cloud use; node weight method; Hopfield neural network.
  DOI: 10.1504/IJIPT.2026.10074204
   
  
• Faultload sequences for the MQTT protocol services  
  by Amina Jandoubi, M.Taha Bennani, Olfa Mosbahi 
  Abstract: We have proposed preliminary results of a new approach to extract sequences of events that model the fault-injection times at the MQTT messaging protocol level to assess their reliability. After targeting the publish service, we identified seven possible scenarios that place the system in a faulty state. We introduced new algorithms to (1) extract send and receive events from CFGs, (2) identify send/receive pairs, (3) timestamp the events using a vector clock, (4) filter sending events and (5) generate alternative send sequences. In this paper, we extend the initial results by applying the approach to the services provided by the Publisher, the Subscriber and the MQTT Broker, which increased the number of scenarios up to 17 fault-injection sequences. This contribution is the first step in formalising the description of all possible attacks on the MQTT protocol, which is crucial to reinforce the reliability of its services.
  Keywords: faultload model; event-based sequences; MQTT services; message queuing telemetry transport.
  DOI: 10.1504/IJIPT.2026.10072721
   
  
• Intelligent retrieval method for legal information based on semantic knowledge graph  
  by Yuxia Gao 
  Abstract: To improve the average accuracy of retrieval results and the normalised discounted cumulative gain, this paper proposes an intelligent legal information retrieval method based on a semantic knowledge graph. First, the quality of legal information is ensured through data pre-processing. Next, natural language processing techniques are used to extract semantic features from legal information and to establish correlations among these features. Subsequently, a legal knowledge graph is constructed through entity recognition and relationship extraction, integrating knowledge from multiple data sources to form a comprehensive legal information association model. Finally, the Lagrange algorithm is applied to achieve intelligent retrieval. Experimental results show that the average accuracy of the proposed method remains above 0.95, while the normalised discounted cumulative gain fluctuates between 0.962 and 0.991, demonstrating its effectiveness and practicality. The proposed method provides legal practitioners with a faster and more accurate tool for legal information retrieval.
  Keywords: legal information; intelligent retrieval; semantic features; knowledge graph; Lagrange algorithm.
  DOI: 10.1504/IJIPT.2026.10074413
   
  
• Personalised recommendation method for network digital media information based on user interests  
  by Yaoyi Xu 
  Abstract: In the digital media era, information overload hampers effective data filtering, leading to cognitive fatigue and reduced decision-making efficiency. To address this challenge, we propose a personalised recommendation method for online digital media based on user interests. The proposed approach constructs a user interest model using term-frequency statistics and co-occurrence-based tag filtering, which is dynamically updated through a forgetting factor. An enhanced list-wise recommendation model based on deep neural networks is designed to process user and content features as vectorised inputs. The model integrates positional encoding and multi-head attention mechanisms with point-wise feedforward networks and residual connections, and predicts click-through rates while optimising ranking via a Softmax output layer. Experimental results indicate that our method achieves a stable MRR between 0.516 and 0.599 (fluctuation: 0.083) and maintains Precision above 95%, effectively mitigating the cognitive burden of information overload and delivering key content more accurately to target users.
  Keywords: personalised recommendation; user interest modelling; network digital media; deep neural networks; attention mechanism.
  DOI: 10.1504/IJIPT.2026.10074415
   
  
• AI-driven personalised curriculum framework for enhancing cross-cultural learning: a case study in Chinese cultural education at Guilin Tourism University  
  by Yun Tang, Chaohua Su 
  Abstract: With the accelerated pace of globalisation and the rapid advancement of artificial intelligence (AI) technology, international student education is confronted with unprecedented opportunities and challenges. Existing international education systems often suffer from a lack of personalisation and static content delivery, failing to fully address the diverse and personalised learning needs of international students. Drawing on the Constructivist Learning Theory and Intercultural Communication Competence Model, and integrating the application scenarios of AI technology, this study proposes a comprehensive AI-driven personalised curriculum framework for enhancing cross-cultural learning, taking Chinese cultural education for international students at Guilin Tourism University as a case study. The framework, structured around four key components - goal setting, content creation, teaching implementation, and evaluation feedback - utilises AI to dynamically tailor learning paths, generate multimodal resources and provide real-time feedback. Implementation at Guilin Tourism University has shown promising results, including increased student engagement, satisfaction and skill acquisition in Chinese cultural understanding. This framework not only improves the learning outcomes of Chinese culture among international students but also offers insights for broader applications in international education and policy-making, highlighting the potential of AI to revolutionise cross-cultural education.
  Keywords: AI-assisted teaching; international student education; Chinese culture; curriculum system; cross-cultural communication.
  DOI: 10.1504/IJIPT.2026.10074642