International Journal of Technology Intelligence and Planning (5 papers in press)

Regular Issues

• A Study on the Impact of Digital Transformation of Business Clusters on the Economic Performance of Innovation in the Context of the Digital Economy  
  by HaiKun Zhang  
  Abstract: This study focuses on evaluating the growth prospects of enterprises by analysing panel data of digitally listed companies. Principal component extraction is used to construct growth evaluation indicators, and the extreme gradient boosting (XGBoost) model is employed to predict enterprise growth. The study confirms the indicator system’s relevance through the Kaiser-Meyer-Olkin (KMO) test. In simulation experiments, the prediction performance of different classification algorithms was compared, and the prediction accuracy of XGBoost in the training dataset was 0.8366, which is higher than other algorithms under the same conditions. The proposed XGBoost model provides a more reliable and accurate method for financial status classification and growth prediction compared to traditional methods. This research aims to guide the ongoing development of enterprise innovation economy by offering an effective growth prediction method for digital cluster enterprises.
  Keywords: business clusters; digital economy; financial performance; XGBoost; growth.
  DOI: 10.1504/IJTIP.2024.10065489
   
  
• Application of Scenic Spot Recommendation Model Combined with TDRA in Tourism Service Management under the Background of Big Data  
  by Xiao Hu 
  Abstract: To improve the search efficiency of group travellers for travel information and optimise user experience, a model combining tourist attractions and travel route planning, namely the algorithm based on time, region, and popularity (TRPA), is proposed. The model first analyses the group travel recommendation algorithm that combines spatiotemporal factors and the popularity of travel attractions. Then it is introduced into the route algorithm based on time division (TDRA) model to further plan group travel routes, fully considering factors such as geography, time, and tourist attraction flow that affect people's travel decisions. The validation results on the dataset showed that the highest rating rate of TRPA-TDRA model reached 38%, which was about 30% higher than other models. This study fills the research gap in group travel attraction recommendation algorithms, providing new theoretical and methodological support for tourism management practices.
  Keywords: big data; internet; time; region; and popularity; TRPA; TDRA; tourist attraction recommendation; travel route planning; group travel.
  DOI: 10.1504/IJTIP.2024.10066363
   
  
• Research on Intelligent Management of Supply Chain Information Sharing Based on Blockchain  
  by Xiujian Lan, Chaopeng Lin 
  Abstract: Supply chain management faces significant challenges in the increasingly complex globalised business environment. The most notable of these challenges are information asymmetry, data security, and transparency issues. Traditional blockchain technology processes information slowly, which can cause delays and operational risks for modern enterprises. To address this issue, the experiment suggests an intelligent supply chain information management approach based on enhanced blockchain technology. First, the working principle of blockchain technology is analysed, and then blockchain technology is used to improve the management model of enterprise supply chain. Feasibility verification is conducted using the inventory-distribution model. The optimal solution was found when the model was run five times and iterated about ten times, and convergence was achieved at the same time. When the number of hidden nodes was 8 and the information index was 16, the research method's minimum value at this time was 5.92. The impact of hidden nodes on the error rate was observed. The results indicate that the proposed method can enhance information sharing efficiency and overall supply chain management optimisation, thereby facilitating the rapid growth of modern enterprises.
  Keywords: supply chain; blockchain; information sharing; intelligent management.
  DOI: 10.1504/IJTIP.2024.10066365
   
  
• Exploring the Evolution of Emerging Technologies using Text Mining Method based on Machine Learning: Evidence from Intelligent Ship Technology  
  by Jingyi Yao, Weiwei Liu, Kexin Bi 
  Abstract: Emerging technologies has reshaped multiple industries, notably the maritime sector, where intelligent ship technology has emerged as a pivotal innovation. However, little attention has been given to mapping its evolution. To address this gap, we introduce a framework, employing text mining and machine learning to unravel the evolution of intelligent ship technology. Our method applies LDA to identify topics over time, dissects evolution in intensity, content, and state, and maps evolution paths of topics to assess current research and forecast trends. The main findings are as follows: First, the topic distribution of intelligent ship technology gradually shows diversity over time. Second, the topic content shows crossover, penetration and integration among the research topics. Third, the evolution state presents complex evolutionary relationships of dividing, consolidating and inheritance. This extends research, offering a dynamic view of state and progress of intelligent ship technology, informing researchers, policymakers, and stakeholders to harness its potential.
  Keywords: intelligent ships; latent Dirichlet allocation; LDA model; topic identification; topic evolution analysis; technology evolution path.
  DOI: 10.1504/IJTIP.2025.10066548
   
  
• Application of Chaos Particle Swarm Optimisation Algorithm in Multi Project Management System of Heavy Enterprises  
  by Suping Feng  
  Abstract: Aiming at the problem that traditional project management methods are slow in processing problems, a multi-project management method for heavy-duty enterprises that integrates chaos search and particle swarm algorithm is proposed in the experiment. In this process, a multi-project management model for heavy-duty enterprises is first constructed, then the model is improved by adaptive inertia weight, and chaotic perturbation is added to the particle swarm algorithm to improve the particle optimisation process, and finally it is applied to enterprise project management. In the comparison of output and input correlation coefficients in different data sets, the correlation coefficient R values of the proposed method are 0.9677, 0.9431, 0.9603 and 0.9621 respectively. This shows that the algorithm proposed in this paper has a high operating efficiency in the management and scheduling of multi-projects in heavy-duty enterprises, which helps to improve the success rate of projects and reduce costs.
  Keywords: Heavy enterprises; Multi project management; Chaos theory; Particle swarm optimisation algorithm; Model building.
  DOI: 10.1504/IJTIP.2024.10066557