This document describes an analysis of ICONNET service area segmentation within a VLAN-Based MPLS (Multi-Protocol Label Switching) network and its impact on customer satisfaction in the Depok Region. Along with technological advancement, internet usage has become an essential need for both personal and business purposes. PLN ICON Plus, a subsidiary of PT PLN (Persero), develops its business through ICONNET products. However, full traffic on the backbone (BNG), which integrates ICONNET and corporate broadband networks, causes service degradation. To overcome this issue, VLAN-based regional segmentation and separate BNG implementations were introduced in each region. This innovation aims to distinguish backbone and corporate services, reduce congestion, and improve service quality. The analysis results are expected to contribute to network optimization and enhance customer satisfaction.

Customer experience extends beyond the scope of basic service standards and is increasingly recognized as a strategic asset that influences both operational efficiency and long-term profitability, while also playing a critical role in establishing competitive advantage. This study aims to examine the components of customer experience, experience-centric service, service quality, customer satisfaction, and revisit intention, to investigate the direct and indirect impacts of customer experience, experience-centric service, service quality, customer satisfaction, and revisit intention, and to propose a new model for creating the customer service experience for the hotel in the context of Nakhon-Chai-Bu-Rin Provincial Cluster, Thailand. A quantitative research design was employed, utilizing both descriptive and inferential statistical metho ds. Structural equation modeling (SEM) was applied for path analysis. Data were collected via an online survey administered through Google Forms, targeting a purposive sample of 400 Thai and international guests who had utilized hotel services at least once in the last 3 years (2023-2025) within the Nakhon-Chai-Bu-Rin Provincial Cluster in Thailand. The 67 items of observable variables were used to analyse the model. The fit index values in model testing consist of: X2 /Df = 2.249, GFI = 1.000, CFI = 0.936, NFI = 0.892, TLI = 0.923, RFI = 0.869, RMSEA = 0.056, and RMR = 0.014, all are considered to pass the criteria. The findings led to the development of a new model for enhancing customer service experience in this context, comprising five key components: customer experience, experience-centric service, service quality, customer satisfaction, and revisit intention. The new model also demonstrates statistical consistency with the empirical data, confirming that five key factors have a statistically significant direct impact on customer experience. It can increase satisfaction that leads to revisit intention and hotel sustainable revenue. Nonetheless, individual hotels must assess their specific capacities and contextual factors when implementing this model.

The worldwide exponential growth of technology and artificial intelligence (AI) associated with robotization, the globalization of markets, and the detriment of the workforce, have made the service industry an attractive sector for emerging technological innovation (Tuomi et al., 2021). Service robots are beginning to perform service deliveries that used to be completed by human employees. The service industry has been recognized for achieving customer satisfaction in any service delivery through the emotional intelligence skills that are naturally given to human employees, so it is expected that the mission of service robots is to maintain this satisfaction in customers (Sayed and Proches, 2021; Torres et al., 2019). Previous research has shown that replacing traditional employees with service robots has generated customer dissatisfaction and decreased quality-of-service provision. Although high technology and artificial intelligence have taken over service robots, the lack of emotional intelligence skills in service robots has hindered their popularity from customers' perception. (Paluch and Wirtz, 2020; Park and del Pobil, 2013). The purpose of this current study is to explore the importance of the customer-machine relationship in the provision of services and the role that emotional intelligence plays in the perception of customers. It reviews the literature on the importance of emotions in the service industry and offers three propositions. The literature review indicates that, despite the natural abilities given to clients, they prefer to delegate the execution of repetitive tasks to robots. The development of social/emotional skills in service robots is essential to fit into the service industry and maintain the social status of service robots by providing customer satisfaction. Once these social/emotional skills, technological advances, and artificial intelligence enhancements are fully developed in robots, the impact on customer and employee perception will likely be more substantial.

The research examines the mediating role (through digital technologies) of the relationship between social media and hospitality performance in Jordan. As the scope of using online platforms to engage customers, their services, and communication with brand has intensified, knowledge of their direct and indirect effects on performance has become more relevant particularly as the digital transformation redefines operations within the hospitality sector. The study was done with a quantitative, cross-sectional research design where a structured questionnaire was given to 167 professionals working in hospitality related organizations in Jordan. Partial Least Squares Structural Equation Modeling (PLS-SEM) was used to analyze the received data. It has been established that social media has strong direct influence on the performance of the hospitality industry, and its influence seems to be better mediated by means of the use of digital technologies. It is worth mentioning that the digital integration proves to be a strong mediator that has contributed to the impact of social media on customer satisfaction, service quality, and operational efficiency. These findings highlight the strategic value of integrating digital technologies in the social media models in a bid to initiate sustainable performance gains. The study adds value to the literature in that it empirically proves the concept of digital integration as a dynamic capability, as well as introduces a model that can be applied to the development policy of the hospitality sector in emerging economies. It also provides valuable professional knowledge to managers and policymakers in the hospitality industry by indicating that they should invest in the infrastructural development of technology, digital solutions, and workforce skills to take full advantage of the potential of social media. Through digital innovations coupled with social media strategies, the hospitality organizations in the emerging economies such as Jordan will be in a position to leverage sustainable growth and competitive edge in the digital age.

The high growth rate of online tourism platforms has created a huge amount of reviews by customers which include valuable opinions concerning the tourism services. The reviews are unstructured making it hard to analyze them manually. In this study an aspect-based sentiment analysis (ABSA) system for tourism company reviews is proposed by applying machine learning techniques. The given data was pre-processed by cleaning, tokenization, removing stop words, and feature extraction using TF.IDF values. For sentiment classification, four machine learning classifiers were used: Support Vector Machine (SVM), Random Forest (RF), XGBoost, and Gradient Boosting (GB). The models were tested on the basis of the accuracy, precision, recall, and F1 score. Experimental results revealed that all classifiers had an accuracy rate of more than 97% for excellent performance. The best model was Gradient Boosting with an accuracy of 98.47% among the evaluated models. The proposed framework is able to accurately detect the sentiment of the aspects and can offer valuable insights into the customer’s opinion. The results can be used to boost the quality of services offered by the tourism industry, increase customer satisfaction and aid in decision making processes.

Superior seeds play an important role in increasing cayenne pepper productivity; however, studies specifically examining farmer satisfaction with particular seed products remain limited. This study aimed to analyze the satisfaction level of farmers using Absolut 69 cayenne pepper seeds produced by PT. Mitra Merdeka Tani in the Special Region of Yogyakarta (DIY) using the Customer Satisfaction Index (CSI) method. The research was conducted from November 2025 to April 2026 in Sleman, Bantul, and Kulon Progo Regencies. A total of 100 farmers were selected through purposive sampling, with the criterion that they had used Absolut 69 seeds for at least two consecutive planting seasons. Data were collected using a structured questionnaire with a 1–4 Likert scale covering 21 satisfaction attributes grouped into five dimensions. The results showed a CSI value of 80.12%, indicating that farmers were highly satisfied with the product. The attribute with the highest importance level (MIS) was fruit quality, including color, size, and shape (3.29), while the lowest importance level was found in the benefits of promotional activities (3.04). In terms of performance (MSS), ease of access to seed sellers or distributors achieved the highest score (3.41), reflecting good distribution accessibility for farmers. Conversely, seed stock availability during the planting season recorded the lowest performance score (3.06), indicating supply constraints during periods of high demand. Overall, farmers expressed a very high level of satisfaction with Absolut 69 seeds; however, improvements in distribution management and stock availability should be prioritized to sustain farmer satisfaction in the long term. Keywords: Absolut 69, cayenne pepper seeds, Customer Satisfaction Index, farmer satisfaction, seed products

In fulfilling human needs and responding to the competitive challenges of business activities, a well-directed and targeted market segmentation innovation is required. This can be achieved by implementing a carefully planned marketing mix strategy covering aspects of product, service, distribution, and promotion. Business potential in product marketing is always influenced by surrounding external factors and conditions. In this case, the phenomenon occurring at Geprek Mas Boy is the inadequate service provided to consumers, while the quality of the products served has still received negative evaluations from several customers. This is reflected in the Google ratings received by Geprek Mas Boy, which scored 3.8 out of 5.0. This study involved 63 respondents who completed the questionnaire. The results of this research are: 1) SPSS testing showed that the t-count value for service quality was 0.745 with a significance probability of 0.459. 2) SPSS testing showed that the t-count value for product quality was 4.598 with a significance probability of 0.001. This means that both variables have a positive and significant effect on customer satisfaction.

Quality Function Deployment (QFD) is a customer-oriented product development methodology that translates customer requirements into engineering characteristics for designing high-quality products and services. Traditional QFD relies heavily on expert judgment, manual evaluation, and subjective decisionmaking, which often lead to inconsistencies, increased development time, and limited adaptability to rapidly changing customer expectations. Recent advancements in Artificial Intelligence (AI), Machine Learning (ML), Data Analytics, and Natural Language Processing (NLP) have introduced data-driven approaches that enhance the efficiency and accuracy of Quality Function Deployment. This paper proposes a datadriven intelligent QFD framework that integrates customer feedback analytics, sentiment analysis, machine learning, and predictive modeling to automatically capture the Voice of the Customer (VoC) and transform it into engineering design requirements. The proposed framework combines structured and unstructured customer data collected from surveys, product reviews, social media platforms, and online feedback systems to generate intelligent House of Quality (HoQ) matrices. Comparative evaluation demonstrates that the proposed approach significantly improves customer requirement prioritization, decision-making accuracy, product quality, development efficiency, and customer satisfaction compared with conventional manual QFD techniques. Furthermore, the framework enables continuous learning from evolving customer preferences through intelligent analytics and automated recommendation mechanisms. The proposed research contributes to modern quality engineering by bridging traditional Quality Function Deployment methodologies with AI-powered data intelligence, thereby supporting customer-centric product innovation, strategic decision-making, and sustainable competitive advantage in intelligent manufacturing and service industries.

Consumer concerns about food safety have intensified in recent years, as transparency and accountability in the food sector have become essential to maintaining public trust. This study examines how consumer-oriented corporate social responsibility (CSR) practices influence food safety perceptions, emphasizing the mediating role of customer satisfaction and the moderating role of loyalty. Drawing on stakeholder theory and signaling theory, we developed and tested a model using survey data from 498 chain restaurant consumers in China. Partial least squares structural equation modeling (PLS-SEM) results show that consumer/product safety CSR, ethical procurement and supply chain CSR, and environmental/social CSR all positively affect perceived food safety, although the effect of environmental/social CSR is relatively weaker. Moreover, customer satisfaction mediates the relationships between consumer/product safety CSR and perceived food safety, and between ethical procurement and supply chain CSR and perceived food safety, while customer loyalty strengthens the impact of satisfaction on safety perceptions. These findings contribute to consumer behavior and CSR literature by uncovering the psychological mechanisms through which CSR enhances food safety perceptions. For practitioners, the study highlights how CSR strategies can simultaneously improve satisfaction, strengthen loyalty, and build sustainable consumer trust in food safety.

This manuscript aims to describe methods used to measure satisfaction among Centers for Disease Control and Prevention (CDC)-funded state, tribal, local, and territorial (STLT) jurisdictions throughout the grants management lifecycle. We also illustrate how CDC's development of a customer experience model was used to engage staff in consideration of agencywide improvements to strengthen grantmaking systems, operations, and procedures. The American Customer Satisfaction Index methodology was used to assess strengths and opportunities for improvement in operational support and customer service provided to CDC-funded STLT jurisdictions. In May 2024, a survey was sent to 2032 principal investigators or project directors for directly funded CDC grants and cooperative agreements to STLTs, active in December 2023. Survey data were used to create a CDC-specific cause-and-effect model that measured customer experience across the grants management lifecycle. The model identified 7 satisfaction drivers (partnership, flexibility, monitoring and reporting, communication, application process, overall support and guidance, and training and technical assistance), a customer satisfaction index measure, and 2 future behaviors linked to satisfaction. The satisfaction survey response rate was 47% (n = 947). On a 100-point scale, overall satisfaction with the agency's services and support, as measured by customer satisfaction index, was 70. Satisfaction driver scores ranged from 65 (application process) to 77 (training and technical assistance). Segmenting findings by subgroups yielded insight into sources of variation. Results of modeling suggested that recipient satisfaction might be best improved by prioritizing actions in 4 areas: partnership, flexibility, monitoring and reporting, and application process. CDC benefited from undertaking an intentional process to learn from its STLT-funded recipients. The structured approach used in this study has produced valuable data to examine recipients' experience and opportunities not just with individual CDC programs but across broader agency systems and practices.

The present study examines strategic human resource practices and their impact on marketing effectiveness in the electronic sector. In today’s competitive business environment, electronic sector organizations require skilled, trained, motivated, and customer-oriented employees to achieve better market performance. Strategic human resource practices such as training effectiveness, employee development, performance improvement, and customer-oriented behaviour play an important role in strengthening marketing outcomes. The study focuses on understanding how training effectiveness and market effectiveness contribute to employee customer orientation and how these factors support organizational growth in the electronic sector. The study is based on primary data collected from 180 respondents from the electronic sector. Statistical tools such as percentage analysis, correlation analysis, regression analysis, ANOVA, coefficient analysis, and SEM/path coefficient analysis were used for data analysis. The findings show that training effectiveness, market effectiveness, and employee customer orientation are positively and significantly related. The regression model indicates that market effectiveness and training effectiveness together explain a meaningful variation in employee customer orientation. The study concludes that effective training and strong market practices help employees become more customer-focused, which improves customer satisfaction, sales performance, brand image, and overall marketing effectiveness.

This research aims to analyze the influence of Service Quality and Price Fairness on Customer Loyalty through a dual mediation model involving Customer Satisfaction and Customer Trust, while comparing the effectiveness of transactional learning and relational learning pathways in building loyalty within an independent workshop context. A quantitative explanatory cross-sectional design was employed. Data were collected from customers who had visited Bengkel NM at least twice within the preceding eighteen months using purposive sampling, and were analyzed through Partial Least Squares Structural Equation Modeling. The findings reveal that Service Quality has a positive and significant direct effect on Customer Satisfaction, Customer Trust, and Customer Loyalty, while Price Fairness is only proven to significantly influence Customer Trust. The direct effect of Price Fairness on Customer Loyalty was not significant. Although all four specific mediation paths were individually non-significant, Service Quality was proven to operate through aggregate mediation, categorized as complementary partial mediation, whereas Price Fairness demonstrated a non-mediation pattern. The novelty of this research lies in testing a dual mediation model that simultaneously compares satisfaction and trust pathways within the context of an Indonesian independent workshop with premium pricing characteristics. The findings indicate an evaluative fusion phenomenon between Customer Satisfaction and Customer Trust, suggesting that in services characterized by high technical information asymmetry, customers tend to merge satisfaction and trust evaluations into a single holistic assessment, rendering the independence of both pathways unverifiable through cross-sectional design.

Systematic logistics plays a key role in fostering profitable development in supply chains. An intelligent logistics model can help create a more agile, sustainable, and resilient supply chain. In recent years, several brain-inspired deep learning architectures, such as long short-term memory networks, graph neural networks, and convolutional neural networks, have been introduced for intelligent decision-making tasks. From a biomimetic perspective, these models are inspired by biological information-processing mechanisms. Convolutional neural networks reflect hierarchical procedures similar to those in the visual cortex, graph neural networks mimic communication among biological neurons, and LSTM networks are motivated by short-term and long-term memory mechanisms in the brain. Inspired by these biomimetic computational principles, this study proposes a novel hybrid deep learning strategy composed of LSTM, convolutional layers and GraphSAGE geometric layers for smart supply chain logistics management. This strategy enables leveraging information pertaining to LSTM-based long-term dependencies, convolutional local patterns and graph-related hidden connections of the supply chain dataset for intelligent decision-making. The GraphSAGE framework helps with scalable graph learning, which enhances predictive accuracy in the case of unseen data. The optimizer in the proposed methodology performs sequential optimization using the biomimetic particle swarm optimizer and the Adam approach (PSO-Adam), considering the hybrid cost function. The prediction of logistics parameters is investigated using five datasets, including DataCo, Shipping, Smart Logistics, Hospital Supply Chain, and Pharmaceutical Supply Chain. The average accuracies of 97.8%, 100%, 96.6%, 98.7% and 99.4% are obtained for practical multi-category logistics parameter forecasts. The evaluation metrics for ten logistics predictions confirm the effectiveness of the proposed intelligent logistics model and highlight the potential of biomimetic geometric networks for complex supply chain decision-making. The model is a cost-efficient approach with consideration of the prediction capabilities, helping to reduce the occurrence of logistics risks, increase the productivity of the supply chain and affect the supply chain visibility, customer satisfaction, and industry reputation.

Customer satisfaction in fitness centres is critical for fostering loyalty, higher spending, cross-buying, and positive recommendations. This study seeks to develop a predictive model of gym users' satisfaction, identify its main determinants, and optimise predictive accuracy through machine learning techniques. Data from 10,368 users across five Spanish fitness centre chains were analysed. Five machine learning algorithms were applied: decision tree, random forest, logistic regression, gradient boosting, and Naïve Bayes. Model performance was evaluated using AUC, sensitivity, specificity, F-measure, Cohen's Kappa, and overall accuracy. The random forest model showed the highest accuracy (AUC = 0.954, sensitivity = 0.933, specificity = 0.825, F-measure = 0.91, Cohen's Kappa = 0.767, overall accuracy = 0.889). The most influential factors for satisfaction were the overall environment of the centre, employee trustworthiness, staff quality, and management of waiting times. This study extends prior research by applying machine learning algorithms to explain customer satisfaction in fitness centres, positioning satisfaction as the primary predictive outcome and providing interpretable insights into how environmental and service-related factors shape satisfaction beyond traditional retention-focused approaches.

The rapid advancement of digital transformation has driven organizations across various industries to integrate information and communication technologies into their operational processes to enhance efficiency, productivity, service quality, and organizational competitiveness. Within the security services industry, challenges related to human resource management, field supervision, operational monitoring, and compliance with customer service standards remain significant issues that require innovative and technology-driven solutions. This study aims to analyze the implementation of the Smart Field Service Management (Smart-FSM) model as a digital-based operational framework for security service management at PT Biner Sinergi Optima. This research employs a qualitative descriptive approach using documentation study methods, with data derived from the company’s operational planning documents and digital transformation initiatives. The Smart-FSM model integrates several advanced technologies, including cloud computing, the Internet of Things (IoT), Artificial Intelligence (AI), Machine Learning (ML), and drone-based patrol systems, to support real-time monitoring, data-driven decision-making, and operational optimization. The findings indicate that the implementation of Smart-FSM contributes significantly to improving supervisory effectiveness, accelerating response and decision-making processes, increasing transparency in service delivery, and strengthening compliance with operational standards. Furthermore, the system supports the achievement of a minimum Service Level Agreement (SLA) target of 90%, while simultaneously reducing operational inefficiencies and associated costs. The integration of these digital technologies also provides a sustainable competitive advantage through enhanced service quality, operational reliability, and customer satisfaction. Therefore, Smart-FSM can be considered a relevant and innovative operational model to support the digital transformation agenda of the security services industry in Indonesia and improve organizational performance in an increasingly technology-oriented business environment.

Online travel agencies (OTAs) increasingly rely on user-generated reviews to shape consumer perceptions and influence booking decisions. This study analyses 5921 customer reviews collected from MouthShut.com, an independent review platform, to examine customer concerns and sentiments across multiple OTA platforms in India. Using latent Dirichlet allocation (LDA), key discussion themes were identified, followed by an aspect-level sentiment analysis to evaluate customer perceptions across critical service dimensions. The findings reveal notable variations in service performance across platforms, particularly in areas such as booking experience, pricing transparency, customer support, and refund processes. These variations highlight the role of expectation–performance alignment in shaping customer satisfaction within digital travel services. By integrating LDA topic modeling with sentiment analysis, this study contributes to the literature on online service experience. The findings offer actionable insights for OTAs to improve service reliability, enhance transparency, and reduce friction in the customer journey.

Purpose This study investigates logistical challenges hindering sustainable online grocery retailing (SOGR) in Germany. It identifies critical factors for SOGR and improvement measures that interrelate these factors to strengthen economic, ecological and social sustainability simultaneously. An active-passive matrix determines the most impactful and receptive factors for cross-dimensional improvement. Design/methodology/approach Using a Grounded Theory approach, the study draws on fourteen semi-structured expert interviews. Sustainability challenges were coded into seven critical factors across the Triple Bottom Line (TBL). An active-passive matrix structures the recommended measures and illustrates their interrelationships across the three sustainability dimensions. Findings Optimized order picking, innovative food packaging, as well as punctuality and reliability emerged as the most impactful sustainability factors, each representing a different TBL dimension. The active-passive matrix shows how improvements in these factors generate positive effects across multiple other factors. Food waste was identified as having the greatest improvement potential. A previously unarticulated social factor (people's benefits) appeared during analysis, revealing latent impacts visible only through system-level evaluation. Practical implications The active-passive matrix offers retailers a practical tool to prioritize high-impact sustainability initiatives. By focusing on order picking, packaging and delivery punctuality and reliability, firms cannot only improve cost efficiency and reduce food waste but also enhance service quality, customer satisfaction and employee well-being. The findings highlight the importance of managing interdependencies across supply chain processes and offer guidance for different fulfillment models. Originality/value This study advances the literature by providing an integrated perspective on sustainability in online grocery retailing, linking economic, ecological and social dimensions within a single framework. It bridges home delivery and click-and-collect models, conceptualizes interactions between operational measures, and offers new insights from Germany's cost-sensitive market. By identifying leverage points that generate cross-dimensional synergies rather than trade-offs and distinguishing between the most impactful and most improvable factors, the study provides a more nuanced understanding of sustainability management in logistics-intensive retail contexts.

Purpose: This study aims to evaluate customer satisfaction with employee performance at PT WIKA based on service quality dimensions using Service Quality (SERVQUAL) and Multi-Objective Optimization on the Basis of Ratio Analysis (MOORA) based decision support system approaches. Research Methodology: This study employed a quantitative descriptive method by integrating SERVQUAL with the MOORA decision-support system. Data were collected through questionnaire-based surveys distributed to 100 PT WIKA customers using 20 service quality indicators representing the tangibility, reliability, responsiveness, assurance, and empathy dimensions. The analysis compared customer perception and expectation scores to identify satisfaction gaps and determine the priority service dimensions. Results: The findings revealed that the average SERVQUAL satisfaction ratio was 1.01, indicating that overall service performance generally met customer expectations. A total of 14 out of 20 indicators (67%) were categorized as satisfactory, while six indicators (33%) remained unsatisfactory. Furthermore, the MOORA analysis identified reliability as the most dominant service quality dimension contributing to customer satisfaction and employee performance evaluations. Conclusions: Overall, customers were satisfied with the employee performance at PT WIKA. However, several indicators related to responsiveness and service consistency require improvement to enhance customer satisfaction. Limitations: This study was limited to a single company and a specific customer sample, which may reduce the generalizability of its findings. In addition, the weighting process in the MOORA method is determined subjectively. Contributions: This study contributes to service quality and human resource management literature by integrating SERVQUAL and MOORA in evaluating employee performance and supporting service improvement decision-making

Stockout risk is a persistent challenge in supply chain management, undermining both operational efficiency and customer satisfaction. This study adopts a multi-method approach to investigate the causal effect of lead time on stockout risk by integrating causal inference techniques with predictive analytics. The proposed framework combines Propensity Score Matching (PSM), Instrumental Variables (IV-2SLS), Inverse Probability Weighting (IPW), and Doubly Robust Estimation (DRE) alongside machine learning (ML) algorithms and time series forecasting. Using a dataset of 20,000 supply chain incidents, the study estimates the Average Treatment Effect (ATE) and evaluates predictive model performance. PSM generated the most credible ATE (0.882), confirming a strong causal link between lead time and stockout risk. IV analysis using supplier distance as an instrument yielded a reduced and statistically insignificant ATE (0.5535, p = 0.3148), suggesting instrument weakness. Among ML models, Random Forest and LightGBM achieved superior predictive accuracy (R2 = 0.25; MSE = 0.736), while Moving Average forecasting effectively captured stockout patterns over time (R2 = 0.883). The findings identify PSM as the most robust technique for causal inference. This study advances the literature by integrating causal inference, ML, and time series methods, offering practical, data-driven insights to strengthen operational resilience and guide proactive inventory management.

Accurately identifying user needs is critical for producing emotional design. However, traditional user evaluation often suffers from randomness and subjective bias, which often lead to the loss of key information. To address this problem, this study proposes an approach that integrates interval-valued intuitionistic fuzzy sets (IVIFS) with the DEMATEL method to explore product form element relationships and identify key design elements, and using a CNN-SE-LSTM model to determine optimal combination of design solutions. First, users’ emotional responses to products are systematically captured and categorised to reduce the dimensionality of target emotions. To handle uncertainty in expert evaluations and the directional relationships between product form elements, interval-valued intuitionistic fuzzy numbers (IVIFN) are employed, and IVIFS-DEMATEL method is then used to analyse the interaction relationships among smart cockpit form elements to extract core design elements. Second, the CNN-SE-LSTM model is applied to establish a nonlinear relationship between product form parameters and users’ emotional needs, which could construct a predictive model for multidimensional perceptual requirements. Finally, an intelligent design system is developed to optimise product parameters based on consumers’ perceptual needs. A case study of smart cockpit central control design demonstrates system effectiveness, with experimental results highlighting its potential to enhance customer satisfaction.