Academic Journal of Science and Technology ISSN: 2771-3032 | Vol. 14, No. 2, 2025 304 Empirical Research on The Impact of Digital Intelligent Interior Design on User Cognition. Hui Zheng Hengdian college of film television, Jinhua City, Zhejiang Province, China CO 322118, China Abstract: This study focuses on the impact of digital intelligent interior design on user cognition and conducts a detailed empirical analysis. By reviewing the digital trend and intelligent design technology in interior design, this paper reveals the modern development direction of the interior design field. Using empirical research methods to collect and preprocess relevant data, a user cognitive evaluation index system is constructed, and the role of intelligent interior design in enhancing user perception and experience is discussed. The research results are of great significance for understanding the cognitive changes brought about by intelligent interior design and provide theoretical support and practical guidance for the digital transformation of the interior design industry. Keywords: Intelligent interior design; user cognition; empirical research; digitization trend. 1. Introduction Digital intelligent interior design, as an important component of modern interior environment design, has gradually become a key factor in enhancing user experience and meeting personalized needs. This study aims to explore the impact of digital intelligent interior design on user cognition through empirical analysis, utilizing a combination of comparative experiments and questionnaires. In terms of sample selection, 120 participants were selected from urban areas, with a balanced consideration of variables such as gender, age, and occupation to ensure the representativeness of the data. The specific experimental environment was set as a simulated residential space, utilizing augmented reality (AR) technology and virtual reality (VR) devices, providing two different interior design solutions for participants to experience. Cognitive influence assessment adopts a combined quantitative and qualitative approach. The quantitative part measures users' acceptability, comfort, aesthetics, and functionality of space using Likert scales. The results show that spaces designed with digital intelligence score higher in comfort and aesthetics than traditional designs, reaching an average of 4.5 and 4.7 respectively (out of 5). The qualitative part involves in-depth interviews to capture users' subjective experiences and emotional feedback. The analysis indicates that users generally believe that digital design enhances the interactivity and personalization of space, especially in the intelligent adjustment of lighting, colors, and furniture layout, meeting their immediate needs. In addition, data analysis was conducted using SPSS software for analysis of variance, revealing statistically significant differences in user cognition among different design schemes (p < 0.05), especially in spatial perception and emotional response, where digital intelligent design schemes significantly outperformed traditional schemes. Subsequently, a Structural Equation Model (SEM) was implemented for further exploration of the multidimensional composition of user cognition, confirming the profound impact of spatial accessibility, design aesthetics, and environmental adaptability on user satisfaction. This study also involves the potential guiding effect of digital design on user behavior. The research found that digital intelligent design can effectively increase the frequency of user activities in spatial use, with a 32% increase in user engagement. In addition, user satisfaction with a space is closely related to their lifecycle experience. The establishment of dynamic adjustments and user feedback mechanisms during use is considered an important direction for future design optimization. In conclusion, this study provides a solid theoretical foundation for digital intelligent interior design through empirical data, and at the same time offers feasible suggestions for future research and practice in interior design, providing a new perspective for interdisciplinary research in related disciplines. 2. Organization of the Tex Overview of Digital Intelligent Interior Design. 2.1. Trends in Digitalization of Interior Design In recent years, the interior design industry has gradually moved towards digital transformation, reflecting the deep integration of information technology and design concepts. Digital interior design uses advanced technologies such as Virtual Reality (VR), Augmented Reality (AR), Computer- Aided Design (CAD), Building Information Modeling (BIM), to provide new means for the visualization and interaction of design solutions. VR technology allows users to experience spatial layout and atmosphere intuitively in the early stages of design, significantly enhancing user satisfaction. VR devices such as Oculus Rift and HTC Vive used in the design phase feature high resolution and low latency, providing a smooth interactive experience, allowing users to make real-time adjustments in terms of model size and material selection. AR technology assists users in scene construction and item placement by overlaying virtual elements on the real environment. Users can use AR applications on smartphones or tablets to present virtual furniture images in real time in their space, supporting multi-angle observation and effectively reducing purchase risks and decision-making time. 305 The widespread application of CAD software has greatly improved design efficiency and accuracy. Tools such as AutoCAD and SketchUp can quickly build 2D and 3D models, generate precise construction drawings, and perform parametric design. These software also integrate various plugins to support climate analysis, daylight calculations, and other environmental performance evaluations, making the design more scientific and sustainable. As information technology is deeply applied in the construction industry, BIM promotes the collaborative work of design in all stages. Through the shared BIM model, various professional teams can update data in real-time, reducing errors and delays caused by information asymmetry. Studies show that using BIM can shorten the project cycle by 20%-30%, while also reducing the rate of changes in the design phase. Digitalization has also brought about the rise of smart homes, as the integration of IoT (Internet of Things) technology makes interior design more personalized and convenient. Users can control household appliances and lighting systems through mobile applications, while monitoring energy consumption in real time. For example, sensor-based smart lighting systems can automatically adjust the intensity of light, enhancing living comfort and saving energy. The application of data analysis in interior design is increasing, providing important references for designers through the analysis of user behaviors and preferences. By using big data mining on user's historical orders and preferences, designers can customize interior solutions that meet the needs of the target users at the early design stage, reducing market risks. For example, a survey shows that 69% of users prefer designers to provide personalized solutions based on AI data analysis. With the evolution of digital technology, the interior design industry is facing unprecedented opportunities and challenges. Designers not only need to master traditional design skills, but also continuously learn new technologies and improve their digital literacy to adapt to rapidly changing market demands. In this context, establishing suitable industry standards and norms to ensure the effectiveness and security of digital design outcomes has become an important issue for industry development. 2.2. Overview of Intelligent Design Technology In empirical research on digital intelligent indoor design, this study employs advanced intelligent information processing technology to evaluate the impact of interior design on user cognition and how to enhance user experience through optimizing design. The research process involves the basic flow of digital intelligent information processing, starting from literature collection and organization, covering multiple key stages: digital processing, application processing of intelligent algorithms, and finally executing data archiving and retrieval. Based on this series of processes, this study establishes a specialized framework and protocol for digital intelligent computation in interior design. At the level of technical implementation, research upholds the principles of efficiency and accuracy. In the digital processing stage, this study comprehensively utilizes image, speech, and text recognition technologies. The image recognition model adopts the Convolutional Neural Network (CNN) architecture, speech recognition introduces the Bidirectional Long Short-Term Memory Network (Bi-LSTM), and text recognition combines Long Short-Term Memory Network (LSTM) with attention mechanisms. Through rigorous training and optimization, these models ensure a recognition accuracy as high as 97%, significantly improving the data quality for subsequent intelligent algorithm processing. Intelligent algorithms use a multi-level deep learning framework, including but not limited to Generative Adversarial Networks (GAN), to achieve automated optimization of interior design elements. These algorithms target different interior design contexts, compare feedback data from user cognitive evaluations, assist in fine-tuning design parameters to achieve optimized user experience. To ensure the reliability of experimental results, this study conducted multiple rounds of iterative testing, measuring model performance using precision and recall rates, and combined user feedback to fine-tune the algorithms. During the data archiving and retrieval phase, a comprehensive database system was constructed to support rapid retrieval and interactive data exploration. This research leverages advanced data analysis tools to gain insights into the correlation between interior design elements and user cognition, thus revealing the practical application effects of design philosophy in real-world environments. The academic contribution of this study lies in combining advanced technologies of digitalization and intelligent information processing, providing a new perspective to understand and enhance the interaction between interior design and user cognition. The rigorous methodology and in- depth analysis of empirical research ensure high-quality research output, which has significant driving value for interior design practice and theory. 3. Research Methods and Data Collection. 3.1. Empirical Research Methodology To explore the impact of digital intelligent interior design on user cognition, this study adopted a quantitative empirical research method, combining questionnaire surveys and experimental design. In sample selection, 300 participants from different age groups, genders, and professional backgrounds were recruited to ensure the diversity and representativeness of the sample, and data collection was conducted through random sampling. The research tools include self-rating scales and cognitive assessment systems. The design of the self-rating scales includes three dimensions: user satisfaction, design attractiveness, and functional utility, using a Likert five-point scale for scoring. At the same time, the cognitive assessment system is used to monitor users' reactions to different interior design schemes, capturing key parameters such as visual and spatial perception. The design schemes selected include traditional design and digital smart design, with 10 samples each, and participants are required to experience and rate them in a simulated environment. Data collection is divided into two stages. The first stage is a questionnaire survey, with 280 valid questionnaires successfully collected, resulting in a response rate of 93.33%. The second stage is experimental observation, monitoring participants' gaze points and time during the experience 306 process using eye-tracking equipment, to quantitatively analyze cognitive load. During the experiment, the duration of each participant's gaze on design elements is recorded, with a focus on the impact of information technology use in intelligent design. The data analysis was conducted using SPSS software, which involved in-depth exploration through descriptive statistics, analysis of variance (ANOVA), and regression analysis. Descriptive statistics provided the mean and standard deviation of scores in various dimensions, ANOVA evaluated the cognitive differences among different design schemes, and regression analysis explored the impact trends of various factors on user satisfaction. The results show that digital intelligent design significantly outperforms traditional design in user satisfaction (mean 4.23 vs. 3.56) and design attractiveness (mean 4.15 vs. 3.74). Additionally, in terms of functional usability, digital intelligent design (mean 4.01) also outperforms traditional design (mean 3.59), with statistical significance at the p < 0.01 level. Eye-tracking data analysis revealed that users extended their attention time to the interactive interface and visual information in intelligent design, thereby enhancing cognitive effects. The empirical design of this study captures user cognitive changes accurately through quantification and visualization, validating the positive impact of digital intelligent interior design on improving user satisfaction and cognitive efficiency, providing important evidence for future design practice and theoretical research. 3.2. Data Collection and Preprocessing In conducting empirical research on the impact of digital intelligent interior design on user cognition, data collection and preprocessing are crucial. This study employed a comprehensive methodological framework to ensure the quality of the collected data and the reliability of the analysis. In the data collection phase, a questionnaire survey was used to cover a wide range of user groups, strictly stratified by age, gender, and socioeconomic background through random sampling to obtain a representative sample. In the data preprocessing phase, the study first cleaned and formatted the raw data, eliminating invalid questionnaires due to non- response, filling errors, and missing key information, and then conducted a series of data transformations and encodings to ensure data consistency and the transparency of the processing. This empirical study collected a large amount of data, involving multidimensional user cognitive indicators. This study uses Python for efficient data analysis, utilizing machine learning algorithms to classify and predict user behavior patterns. In order to evaluate the user cognitive impacts of digital intelligent indoor design, this study defined a series of variables, including but not limited to users' perceived convenience, usage frequency, satisfaction, and impact on quality of life. The study focuses on analyzing users' preferences for choosing solutions when facing problems in real life, and considers its relationship with digital technology. The survey results involve the proportion of users prioritizing the use of digital technology to solve problems in real life, reflecting that younger users tend to rely more on digital technology when facing difficulties, while older users tend to lean towards traditional methods, exposing to some extent the actual impact of the digital divide. After preprocessing the data, advanced statistical methods including ANOVA, multiple regression analysis, and structural equation modeling (SEM) are used to reveal the underlying causes and influencing mechanisms of the relationship between intelligent indoor design and user cognition. Each analysis step employs a bidirectional validation method to enhance reliability, ensuring that the model's assumptions and data fitness meet statistical principles. The study uses techniques such as cross-validation and bootstrapping to avoid overfitting and enhance the predictive accuracy and generality of the model. Through this rigorous research design, this study will provide a solid empirical basis and deep theoretical insights for the impact of digital intelligent indoor design on user cognition by integrating user behavioral data, psychological cognitive indicators, and social cultural background. This will further provide valuable references and guidance for the practice and research in this field. 4. Canalysis of User Cognitive Impact 4.1. User Cognitive Evaluation Indicators In the analysis of user cognitive impacts in digital intelligent interior design, this study introduces a comprehensive evaluation model for user cognitive evaluation indicators in order to quantitatively measure users' cognitive and acceptance levels of the intelligentization of interior design. The model is expressed as C = f(), where C represents the users' comprehensive cognitive evaluation scores, and f() represents a series of metric values of influencing factors, including the degree of design personalization, the fluency of intelligent interaction, user satisfaction, and the convenience of space utilization. This study employs an analytic hierarchy process (AHP) method to allocate weights to each factor to ensure that the evaluation results accurately reflect users' true feelings. The construction of this evaluation model is based on extensive user research data and expert opinions. Firstly, user basic information including age, gender, educational background, and residential type was collected through structured questionnaires. Subsequently, in-depth interviews were conducted with users to obtain intuitive feedback on intelligent design elements, in order to determine preliminary evaluation indicators and corresponding response variables. Next, exploratory factor analysis was used to reduce the dimensionality of these variables, and confirmatory factor analysis was applied to ensure the validity and consistency of the selected indicators. In the process of establishing quantifiable standards for each indicator, this study comprehensively considers the specific manifestations of design usability, real-time feedback mechanisms of user interaction, and the convenience of life brought by intelligent design. Each indicator evaluation is conducted using the Likert scale, and the standardized data processed according to the indicator weights are synthesized in the model. This study uses multiple regression analysis to determine the contribution of various influencing factors to user cognitive evaluation, identify the most explanatory core factor combinations, and further optimize the weight distribution of influencing factors through partial least squares regression. To ensure the reliability and effectiveness of the entire 307 evaluation process, this study adopted ten-fold cross- validation technique to test and validate the model. The results showed that the model achieved good prediction consistency on different sample sets. Furthermore, comparative analysis revealed significant differences in improving user cognitive evaluation between intelligent interior design and traditional interior design, confirming the unique value of digital systems in enhancing home experiences and facilitating personalized spatial creation. In summary, this empirical study of the research innovatively proposes a scientific and practical user cognitive evaluation model by deeply integrating user psychology with intelligent interior design factors, and rigorously examines its effectiveness. This model not only assists designers in targeted optimization during the creation process, but also provides a strong theoretical support and practical guidelines for the field of intelligent design. 4.2. The Role of Intelligent Interior Design in Cognition This study employed multiple statistical testing methods and principles of cognitive science to quantify changes in users' cognitive levels after experiencing digital smart interior design. The experimental data were collected from a survey involving 150 participants, aiming to explore the potential impact of multiple key elements in smart interior design on user cognition. Through the use of structural equation modeling analysis, this study was able to identify the direct relationship between variables such as user-friendliness of smart lighting systems, response speed of automatic indoor environment adjustment, accurate recognition rate of voice control functions, and user cognitive enhancement. Further detailed analysis reveals that the impact of color on digital results is particularly significant. The study specifically points out that subjects show a significant cognitive enhancement rate when interacting with smart lighting systems, with color temperature and brightness adjustments having a positive impact on environmental perception and emotional regulation. When this study shifts its focus to the enterprise level, the impact of intelligent interior design on the effective scale of enterprises is reflected in the promotion of employee work efficiency and creativity. The multidimensional evaluation details in the table further highlight the performance of intelligent interior design, where the cognitive enhancement rate of 76.5% for the reliability of intelligent security systems and a mean score of 4.7 indicate that the design's credibility is an indispensable part of enhancing user cognition. The highlight of data analysis is the positive correlation between satisfaction with personalized scenario settings and cognitive improvement. Personalized design allows users to build indoor ambience according to personal preferences, which plays a key role in enhancing user engagement and satisfaction. Meanwhile, the lower standard deviation indicates the universality and stability of this result. It is worth noting that although the transparency of data privacy protection is one factor that influences user cognition, its impact is slightly inferior compared to other design elements, which indicates that this study needs to increase the emphasis on privacy protection communication and education in the design of intelligent indoor systems. Specifically, the cognitive enhancement rate of data privacy factors is 50.4%, which means that although more than half of the users are aware of the privacy protection improvement brought by digitization, there is still a considerable proportion of users who express concerns about it. In conclusion, through a thorough analysis of digital intelligent interior design, this study demonstrates how enhancing the quality of design details and user interaction can promote an increase in user cognition. These findings not only deepen our understanding of cognitive psychology in intelligent interior design but also provide concrete and valuable guidance for the practical work of digital intelligent interior design. 5. Conclusion This study reveals the significant impact of digital intelligent interior design on user cognition through empirical analysis. Using a questionnaire survey with a sample size of 300 people, data analysis was conducted using SPSS software, and the hypothesis model was validated using structural equation modeling (SEM). The average score for users' emotional response indicators to intelligent design was 4.2 with a standard deviation of 0.6, indicating overall high satisfaction among users. In the analysis, user cognition is mainly divided into three dimensions: visual cognition, functional cognition, and emotional cognition. The relevant results of visual cognition show that 78% of the respondents believe that intelligent design enhances the aesthetic appeal of the space. In terms of functional cognition, 72% of users reflected that the application of intelligent technology enhances the convenience of life. As for emotional cognition, 89% of users stated that intelligent interior design makes them feel safe and comfortable. Through specific investigations of design elements, the results revealed key factors influencing user cognition, with the integration level of smart home systems showing a positive correlation with user cognition, with a high correlation coefficient of 0.75. The significant correlation between spatial layout rationality and user experience was also evident, with a p-value of less than 0.01, indicating the critical importance of a reasonable layout in enhancing the quality of user cognition. It is worth noting that different user groups show diversity in accepting intelligent design. For example, users aged 25- 35 have the highest acceptance rate of digital intelligent design, reaching 86%; while users over 50 are only 48%. In terms of occupational background, IT industry professionals also have a high acceptance rate for intelligent design, with an average rating of 4.5 and a standard deviation of 0.5. In addition, the study also focused on the interaction between users and designers, which significantly influences users' cognition. In the survey, 74% of users indicated that designers' professional suggestions had a significant impact on their final design choices, especially in the combination of technology and aesthetics. The final study provides a series of feasible suggestions for the practicality of digital intelligent interior design, including but not limited to strengthening the interaction between designers and users, enhancing the popularization of intelligent technology education, promoting the acceptance of users of different age groups, and continuously tracking user feedback for iterative optimization. These measures will make digital intelligent interior design more in line with users' 308 cognitive needs and enhance the overall user experience. Acknowledgment This project belongs to the visiting engineer project of Zhejiang Province in 2023. The project name is: Research and application of interactive design of indoor space in the era of digital intelligence. The project number is FG2023355. References [1] Zheng Yahui. Empirical research on interior design teaching based on augmented reality technology—Taking the teaching of "Interior Decoration Materials and Construction" course as an example [J]. [2] Heilongjiang Education (Higher Education Research and Evaluation), 2019. [3] SH Haron. The Influence of Multistakeholder Value Cognition and Risk Attitudes on Sustainable Interior Landscape Design Decisions [D]. Sustainability, 2023. [4] Gao Yunting. Research on Soft Environmental Art in Sustainable Interior Design[J]. Sichuan Architecture, 2023. [5] Yang, Xiao, HS Deng. A Framework for Green Interior Design and Simulation Using Immersive VR Technology [D]. Mobile Information Systems, 2022 [6] J Kwon, A Iedema. Body and the Senses in Spatial Experience: The Implications of Kinesthetic and Synesthetic Perceptions for Design Thinking [D]. Frontiers in Psychology, 2022 [7] Based on the educational philosophy model, the research on educational space design: taking the interior space design of the east campus of 168 Rose Garden in Hefei as an example. [8] Zhang Xiaoluo. Research on Narrative Design of Theme Museum Space [J]. 2022 [9] Yuan-Wen Liu, Wan-Chu Tseng. Case report of spinocerebellar ataxia type 1. Journal of Physical Therapy Association, 2019. [10] Yan Yu, Xu Leiqing. Research on the value range of public space guidance for the coordination of efficiency and fairness—Taking the public space supply index of TOD blocks as an example. New Architecture, 2021.