Search results

The aim of this study is to (1) construct a standard framework for assessing the capability of bioenergy enterprises' digital green innovation partners; (2) quantify the choice of partners for digital green innovation by bioenergy enterprises; (3) propose based on a dual combination empowerment niche digital green innovation field model.

Fuzzy set theory is combined into field theory to investigate resource complementarity. The successful application of the model to a real case illustrates how the model can be used to address the problem of digital green innovation partner selection. Finally, the standard framework and digital green innovation field model can be applied to the practical partner selection of bioenergy enterprises.

Digital green innovation technology of superposition of complementarity, mutual trust and resources makes the digital green innovation knowledge from partners to biofuels in the enterprise. The index rating system included eight target layers: digital technology innovation level, bioenergy technology innovation level, bioenergy green level, aggregated digital green innovation resource level, bioenergy technology market development ability, co-operation mutual trust and cooperation aggregation degree.

This study helps to (1) construct the evaluation standard framework of digital green innovation capability based on the dual combination empowerment theory; (2) develop a new digital green innovation domain model for bioenergy enterprises to select digital green innovation partners; (3) assist bioenergy enterprises in implementing digital green innovation practices.

Intelligent new energy vehicles (INEVs) are becoming the competitive hotspot for the automobile industry. The major purpose of this study is to determine how to increase innovation efficiency through knowledge sharing and technology spill between new energy vehicle (NEV) enterprises and technology enterprises. This will help to improve the core competence of the automobile industry in China. Also, it serves as a guide for the growth of other strategic.

The authors construct a tripartite evolutionary game model to study the cross-border cooperative innovation problem. Firstly, the payment matrix of NEV enterprise, technology enterprise and government is established, and the expected revenue of each participant is determined. Then, the replication dynamic equations and evolutionary stability strategies are analyzed. Finally, the theoretical research is validated through numerical simulation.

Results showed that: (1) An optimal range of revenue distribution coefficient exists in the cross-border cooperation. (2) Factors like research and development (R&D) success rate, subsidies, resource and technology complementarity, and vehicles intelligence positively influence the evolution towards cooperative strategies. (3) Factors like technology spillover risk cost inhibit the evolution towards cooperative strategies. To be specific, when the technology spillover risk cost is greater than 2.5, two enterprises are inclined to choose independent R&D, and the government chooses to provide subsidy.

The research perspective and theoretical analysis are helpful to further explore the cross-border cooperation of the intelligent automobile industry. The findings suggest that the government can optimize the subsidy policy according to the R&D capability and resource allocation of automobile industry. Moreover, measures are needed to reduce the risk of technology spillovers to encourage enterprise to collaborate and innovate. The results can provide reference for enterprises’ strategic choice and government’s policy making.

The INEV industry has become an important development direction of the global automobile industry. However, there is limited research on cross-border cooperation of INEV industry. Hence, authors construct a tripartite evolutionary game model involving NEV enterprise, technology enterprise and the government, and explore the relationship of cooperation and competition among players in the INEV industry, which provides a new perspective for the development of the INEV industry.

This paper aims to propose a bed and breakfast (B&B) recommendation method that takes into account review timeliness and user preferences to help consumers choose the most satisfactory B&B.

This paper proposes a B&B ranking method based on improved intuitionistic fuzzy sets. First, text mining and cluster analysis are combined to identify the concerns of consumers and construct an attribute set. Second, an attribute-level-based text sentiment analysis is established. The authors propose an improved intuitionistic fuzzy set, which is more in line with the actual situation of sentiment analysis of online reviews. Next, subjective-objective combinatorial assignments are applied, considering the consumers’ preferences. Finally, the vlsekriterijumska optimizacija i kompromisno resenje (VIKOR) algorithm, based on the improved score function, is advised to evaluate B&Bs.

A case study is presented to illustrate the use of the proposed method. Comparative analysis with other multi-attribute decision-making (MADM) methods proves the effectiveness and superiority of the VIKOR algorithm based on the improved intuitionistic fuzzy sets proposed in this paper.

Proposing a B&B recommendation method that takes into account review timeliness and user customization is the innovation of this paper. In this approach, the authors propose improved intuitionistic fuzzy sets. Compared with the traditional intuitionistic fuzzy set, the improved intuitionistic fuzzy set increases the abstention membership, which is more in line with the actual situation of attribute-level sentiment analysis of online reviews.

To predict the price of battery-grade lithium carbonate accurately and provide proper guidance to investors, a method called MFTBGAM is proposed in this study. This method integrates textual and numerical information using TCN-BiGRU–Attention.

The Word2Vec model is initially employed to process the gathered textual data concerning battery-grade lithium carbonate. Subsequently, a dual-channel text-numerical extraction model, integrating TCN and BiGRU, is constructed to extract textual and numerical features separately. Following this, the attention mechanism is applied to extract fusion features from the textual and numerical data. Finally, the market price prediction results for battery-grade lithium carbonate are calculated and outputted using the fully connected layer.

Experiments in this study are carried out using datasets consisting of news and investor commentary. The findings reveal that the MFTBGAM model exhibits superior performance compared to alternative models, showing its efficacy in precisely forecasting the future market price of battery-grade lithium carbonate.

The dataset analyzed in this study spans from 2020 to 2023, and thus, the forecast results are specifically relevant to this timeframe. Altering the sample data would necessitate repetition of the experimental process, resulting in different outcomes. Furthermore, recognizing that raw data might include noise and irrelevant information, future endeavors will explore efficient data preprocessing techniques to mitigate such issues, thereby enhancing the model’s predictive capabilities in long-term forecasting tasks.

The price prediction model serves as a valuable tool for investors in the battery-grade lithium carbonate industry, facilitating informed investment decisions. By using the results of price prediction, investors can discern opportune moments for investment. Moreover, this study utilizes two distinct types of text information – news and investor comments – as independent sources of textual data input. This approach provides investors with a more precise and comprehensive understanding of market dynamics.

We propose a novel price prediction method based on TCN-BiGRU Attention for “text-numerical” information fusion. We separately use two types of textual information, news and investor comments, for prediction to enhance the model's effectiveness and generalization ability. Additionally, we utilize news datasets including both titles and content to improve the accuracy of battery-grade lithium carbonate market price predictions.

This study investigates the heterogeneous impact of R&D capital market distortions (CMDs) on the quantity and quality of innovation in Chinese firms by exploring key pathways from a dual-arbitrage perspective.

Using data from Chinese A-share listed companies (2015–2021), we employ a multidimensional fixed effects model to validate the research hypotheses. Under the Systems of National Accounts (SNA, 2008) framework, we use the Bureau of Economic Analysis method to estimate enterprise R&D capital stock and the Cobb-Douglas production function to estimate R&D CMDs.

Results show that R&D CMDs drive firms toward strategic innovation, emphasizing quantity over quality. Policy arbitrage, including policy catering and rent-seeking, emerges as a pivotal mechanism under R&D CMDs, encouraging firms to prioritize quantity over quality in innovation. High-technology firms and those in the decline stage are more inclined to spearhead strategic innovation within the context of R&D CMDs.

These findings help policymakers promote high-quality innovation in Chinese enterprises by enhancing patent review mechanisms and shifting policies from quantity-driven to quality-oriented goals.

This study enriches the research on factor market distortions and innovation in emerging markets from the perspective of R&D CMDs, based on the “emerging + transitional” comprehensive framework. Unlike previous studies, which generally use enterprise R&D expenditure flow data, we apply the theory of R&D capitalization accounting to the micro-enterprise level under the SNA (2008) framework, enhancing the accuracy of R&D CMD estimations.

This paper aims to identify a suitable convolutional neural network (CNN) model to analyse where void(s) are formed in asymmetrical flip-chips with large amounts of the ball-grid array (BGA) during underfilling.

A set of void(s)-filled through-scan acoustic microscope (TSAM) images of BGA underfill is collected, labelled and used to train two CNN models (You Look Only Once version 5 (YOLOv5) and Mask RCNN). Otsu's thresholding method is used to calculate the void percentage, and the model's performance in generating the results with its accuracy relative to real-scale images is evaluated.

All discoveries were authenticated concerning previous studies on CNN model development to encapsulate the shape of the void detected combined with calculating the percentage. The Mask RCNN is the most suitable model to perform the image segmentation analysis, and it closely matches the void presence in the TSAM image samples up to an accuracy of 94.25% of the entire void region. The model's overall accuracy of RCNN is 96.40%, and it can display the void percentage by 2.65 s on average, faster than the manual checking process by 96.50%.

The study enabled manufacturers to produce a feasible, automated means to improve their flip-chip underfilling production quality control. Leveraging an optimised CNN model enables an expedited manufacturing process that will reduce lead costs.

BGA void formation in a flip-chip underfilling process can be captured quantitatively with advanced image segmentation.

The aim of this study is to examine the ownership impact on firm sustainable investments (FSIs). In particular, this research examines the link between institutional investor ownership (IIO), managerial ownership (MOWN) and FSIs in the tourism industry in Malaysia.

This study uses a data set of 346 firm-year observations from 2008 to 2020 and applies feasible generalized least squares (FGLS) regression analysis. The study sample is based on tourism firms listed on Bursa Malaysia (the Malaysian Stock Exchange).

There is a significant positive association between IIO and FSIs. When IIO is classified into foreign (FIIO) and local (LIIO), this significant association is mainly driven by FIIO. In addition, there is a significant, positive association between managerial ownership (MOWN) and firm sustainable investments (FSIs). These findings imply that firm ownership has an influence on FSIs in the tourism industry.

This is the first attempt to consider IIO and MOWN simultaneously in a single model estimation. The findings contribute to emerging capital markets where the involvement of ownership concentration in the governance of publicly listed firms is a common practice.

We introduce decision support tools aimed at optimizing perishable food supply chain management, effectively balancing conflicting objectives such as the exporter’s product collection cost and the importer’s profit. This involves considering factors like perishability, selling price, discount rate, and order quantity to achieve optimal outcomes.

This study considered a three-echelon supply chain comprising farmers, a single exporter, and a single importer providing a single, random-lifetime, perishable product under deterministic customer demand. The proposed mathematical model derived the optimal order quantity, selling price, and discount rate for the entire supply chain. This integrated optimization model treats both demand and supply sides as a multi-objective problem, employing a nonlinear program and a two-stage capacitated vehicle routing problem formulation. Numerical examples and a case study focusing on Thailand durian supply chain were conducted to illustrate the approach of the proposed model.

Taking into account both the importer’s profit and the exporter’s product collection cost, the proposed integrated supply chain model and tools maximize profitability, minimizes waste, and meets demand by optimizing perishable product collection costs and proposing a discount system for selling prices.

Limited to a single perishable product in a three-echelon international food supply chain. Future research can explore different products and supply chain contexts.

The tools enhance decision-making for supply chain managers, improving efficiency, reducing costs, and enhancing customer satisfaction in the perishable food industry.

The proposed model aids in local workforce management by forecasting required manpower for upcoming seasons. By factoring in product quality and pricing, it ensures customers receive fresh products at fair prices. Furthermore, the near-zero waste concept enhances storage conditions at importers' facilities, contributing to improved environmental hygiene.

The integrated model and decision support tools offer a novel approach to address complexities and conflicting objectives in perishable food supply chains, providing practical insights for researchers and practitioners.

This paper aims to systematically review the application of artificial intelligence (AI) in the tourism industry. By integrating human–computer interaction, machine learning, big data and other relevant technologies, the study establishes a comprehensive research framework that explores the systematic connections between AI and various facets of tourism.

This paper conducts a keyword co-occurrence analysis of 4,048 articles related to AI in tourism. The analysis identifies and classifies dominant topics, which are further refined through thematic literature review and manual coding for detailed discussion.

The analysis reveals five main topics: AI’s impact on tourist experience, AI in tourism marketing and prediction, AI in destination management, AI’s role in tourism enterprises and AI integration in strategic and regulatory framework. Each topic is reviewed to construct an integrated discussion that maps the current landscape and suggests directions for future research.

This paper transcends the fragmented discourse commonly found in the literature by establishing a unified framework that not only enhances understanding of the existing methodologies, theories and applications of AI in tourism but also identifies critical areas for breakthroughs, aiming to inspire a more humane and sustainable integration of AI in the tourism industry.

本文旨在系统回顾人工智能（AI）在旅游业中的应用。通过整合人机交互、机器学习、大数据和其他相关技术, 本研究建立了一个全面的研究框架, 探索人工智能与旅游业各方面之间的系统联系。

本文对4048篇与旅游业人工智能相关的文章进行了关键词共现分析。分析确定了主要议题并对其进行了分类, 然后通过主题文献梳理和手动编码对其进行了进一步完善, 以便进行详细讨论。

分析揭示了五个主要主题：人工智能与旅游体验、人工智能与旅游营销和预测、人工智能与目的地管理、人工智能与旅游企业, 以及人工智能在战略和监管框架中的整合。每个主题都进行了回顾, 以构建一个综合讨论, 勾勒出当前的研究格局, 并提出了未来的研究方向。

研究力图突破目前关于旅游与人工智能的碎片化讨论, 建立了一个统一的框架, 旨在加强对旅游业中人工智能现有方法、理论和应用的理解, 还点明了需要突破的关键领域, 以助力旅游业与人工智能共同创造更加人性化和可持续发展的前景。

Este artículo pretende revisar sistemáticamente la aplicación de la inteligencia artificial (IA) en el sector turístico. Mediante la integración de la interacción humano-ordenador, el aprendizaje automático, big data y otras tecnologías relevantes, el estudio establece un marco de investigación exhaustivo que explora las conexiones sistemáticas entre la IA y diversas facetas del turismo.

Este trabajo realiza un análisis de co-ocurrencia de palabras clave de 4.048 artículos relacionados con la IA en el turismo. El análisis identifica y clasifica los temas dominantes, sobre los que se profundiza mediante una revisión temática de la literatura y una codificación manual para su discusión detallada.

El análisis presenta cinco temas principales: El impacto de la IA en la experiencia turística, la IA en el marketing y la predicción turística, la IA en la gestión de destinos, el papel de la IA en las empresas turísticas y la integración de la IA en el marco estratégico y normativo. Cada tema se revisa para construir un debate integrado que trace el panorama actual y sugiera direcciones para futuras investigaciones.

Este artículo expande el análisis fragmentado que suele encontrarse en la bibliografía al establecer un marco unificado que no sólo mejora la comprensión de las metodologías, teorías y aplicaciones existentes de la IA en el turismo, sino que también identifica las áreas críticas para los avances, con el objetivo de inspirar una integración más humana y sostenible de la IA en la industria turística.

This study aims to enhance the classification and processing of online appeals by employing a deep-learning-based method. This method is designed to meet the requirements for precise information categorization and decision support across various management departments.

This study leverages the ALBERT–TextCNN algorithm to determine the appropriate department for managing online appeals. ALBERT is selected for its advanced dynamic word representation capabilities, rooted in a multi-layer bidirectional transformer architecture and enriched text vector representation. TextCNN is integrated to facilitate the development of multi-label classification models.

Comparative experiments demonstrate the effectiveness of the proposed approach and its significant superiority over traditional classification methods in terms of accuracy.

The original contribution of this study lies in its utilization of the ALBERT–TextCNN algorithm for the classification of online appeals, resulting in a substantial improvement in accuracy. This research offers valuable insights for management departments, enabling enhanced understanding of public appeals and fostering more scientifically grounded and effective decision-making processes.