With the advancement of digital and intelligent tools, digital intelligence empowerment has become a key concept in rural revitalization, and it is being widely applied in rural planning and design (Tim et al., 2021). Digital intelligence enhances rural development efficiency through digital technologies and smart tools, fostering a sense of participation and belonging among residents while promoting sustainable development (Goel and Vishnoi, 2022). Tools like BIM (Building Information Modeling) and GIS (Geographic Information System) enable the accurate planning and optimization of rural environments (Marzouk and Othman, 2020), while big data and AI technologies provide real-time ecological monitoring and design support. Smart infrastructure, such as smart lighting and waste disposal systems, can improve rural life quality and promote sustainability.

Although digital intelligence has made progress in rural revitalization, integrating bionic design with digital technologies and quantifying the optimization of rural human settlements remain challenging. This study offers a new theoretical framework and application path for optimizing rural human settlements by combining bionic design, fuzzy semantic computing, and other digital intelligence technologies.

Fuzzy semantic computing is a computational method that combines fuzzy logic with semantic networks, and it is widely used in artificial intelligence, data analysis, emotion computing, and other fields (Vashishtha et al., 2023). Unlike traditional quantitative analysis methods, fuzzy semantic computing effectively handles fuzzy, uncertain, and qualitative information, so it is particularly suitable for studying human emotional experiences and psychological cognition (Liu et al., 2024).

In the context of rural human settlement environment optimization, fuzzy semantic computing is increasingly being used to assess the impacts of subjective factors, such as the emotional resonance and ecological identity of residents, on design outcomes (Fang et al., 2024). By using fuzzy semantic computing, qualitative perception data can be converted into quantitative evaluation results, which provides more accurate feedback for design solutions (D’Aniello et al., 2018). For instance, Zhang et al. (2018) applied fuzzy semantic computing to develop an urban ecological environment quality assessment model based on the residents’ perceptions, effectively capturing the impact of environmental design on their emotions and ecological identity, which served as a theoretical foundation for urban greening design.

As a technology for handling complex and fuzzy information, fuzzy semantic computing holds significant potential for optimizing rural human settlement environments (Ibeh et al., 2025). By using fuzzy semantic computing, qualitative emotional and cognitive data can be transformed into quantitative information, thus providing a scientific and comprehensive evaluation and optimization path for rural design (Jetter and Kok, 2014). Although the application of fuzzy semantic computing in rural revitalization still faces some challenges, with further advances in technology and data accumulation, it is expected to become a vital tool for optimizing rural human settlements in the future and generating more sustainable solutions for rural revitalization.

Current research on the optimization of rural human settlement environments mainly focuses on individual disciplines, such as architecture, landscape science, or ecology, and lacks interdisciplinary theoretical integration. Many studies are limited to the practical level and lack a unified theoretical framework to guide specific design methods and technical approaches. Particularly in the application of advanced technologies like bionic design and fuzzy semantic computing, theoretical research is still in its early stages and lacks systematic theoretical support and standardized implementation paths.

The optimization of rural human settlement environments requires extensive empirical data, especially regarding subjective factors such as emotions, ecological identity, and environmental satisfaction of residents. However, most current studies rely on expert assessments or a limited number of surveys and lack large-scale, systematic survey data. In addition, the existing evaluation systems have limitations, especially in the quantitative evaluation of qualitative factors like emotional resonance and ecological identity, which remain underdeveloped.

While digital intelligence technologies such as big data, artificial intelligence, and fuzzy semantic computing have made remarkable progress in other fields, their application in optimizing rural human settlements is still lagging. Most existing research focuses on single design methods or traditional ecological optimization techniques, and lacks the deep integration of digital intelligence technology. In particular, the combination of bionic design and fuzzy semantic computing still lacks systematic research and effective examples of applications.

In conclusion, research in the field of rural human settlement environment optimization has gradually expanded from infrastructure construction to ecological, emotional, and other multi-dimensional aspects. As emerging design and evaluation methods, bionic design and fuzzy semantic computing are introducing innovative research pathways in this field. However, gaps and challenges in the theoretical frameworks, empirical analysis, and technical applications remain. The integration of digital intelligence technology, bionic design, and fuzzy semantic computing for optimizing rural human settlements holds important theoretical value and practical significance, making it the core innovation of this research.

Although some studies have explored the application of digital intelligence technology in rural planning, there is still a lack of systematic theoretical research and practical guidance on how to integrate bionic design and fuzzy semantic computing to develop a comprehensive optimization strategy that aligns with rural ecological characteristics and enhances the emotional resonance and ecological identity of residents. Therefore, this study aimed to address two core issues:

The specific mechanisms by which bionic design characteristics influence rural human settlement optimization.

The feasibility and effectiveness of using fuzzy semantic computing to model emotional and identity relationships.

The primary goal of this study was to develop an ecological optimization strategy that combines bionic design and fuzzy semantic computing from the perspective of digital intelligence empowerment. This approach aims to provide a scientific foundation and practical pathway for improving rural human settlements. Hopefully, this study can offer a new perspective and methodology for optimizing rural human settlement environments and promote rural ecological design and human settlement construction along a more scientific, intelligent, and sustainable development path. This study also aims to provide theoretical references and practical experiences for future research in the field of rural revitalization and green development.

This study employed a variety of research methods to systematically explore the theoretical construction and practical application of bionic design and fuzzy semantic computing in the optimization of rural human settlement environments. The research design not only focused on constructing the theoretical framework but also emphasized the analysis and verification of actual data to ensure that the optimization strategy of rural human settlement environments under digital intelligence empowerment was explored comprehensively from different dimensions. Through a combination of literature review, questionnaire surveys, fuzzy semantic computing, data analysis, and ecological benefit assessments, this study constructed a comprehensive research framework for optimizing rural human settlement environments. This paper also discusses the application value of bionic design and fuzzy semantic computing in improving rural human settlements by integrating quantitative and qualitative methods, offering a scientific basis and operational strategies for optimizing rural human settlements within the context of rural revitalization.

This study primarily used triangular fuzzy numbers to calculate membership degrees. Triangular fuzzy numbers are a common approach in fuzzy semantic computing for representing the membership degree of fuzzy sets (Lee, 2014). These numbers define a membership function in the shape of a triangle, which is used to describe the degree to which a variable belongs to a fuzzy set. To represent the membership degree of each evaluation, a triangular fuzzy number is defined by three parameters: a, b, and c, where a denotes the lower bound of the fuzzy number, b represents the peak value (i.e., the point where the membership degree equals 1), and c indicates the upper bound of the fuzzy number. These three parameters are used to determine the membership degree µ(x) of each evaluation value x calculated using the following formula:

When x<a, µ(x)=0; this indicates that when x is less than a, the membership degree is 0, meaning that $x$ does not belong to this fuzzy set. When $a\le x\le b$, $\mu \left( x \right)=\frac{x-a}{b-a}$; this indicates that when $x$ is between $a$ and $b$, the membership degree increases linearly from 0 to 1. When $~b\le x\le c$, $\mu \left( x \right)=\frac{c-x}{c-b}$; this indicates that when $x$ is between $b$ and $c$, the membership degree decreases linearly from 1 to 0. When $~x>c$, $\mu \left( x \right)=0$; this indicates that when $x$ is greater than $c$, the membership degree is 0, meaning that $x$ does not belong to this fuzzy set.

The triangular fuzzy number is used to define the membership degree of elements in a fuzzy set, and to describe the membership degree of variables within the set using parameters $a$, $b$, and $c$ (Pedrycz, 1994). Fuzzy semantic computing employs these membership functions to process and analyze fuzzy information (Zadeh, 1971). In fuzzy semantic computing, the membership function plays a key role in fuzzy reasoning and decision-making (Dubois and Prade, 1997). For example, fuzzy inference can be performed by calculating the membership function of an input variable and combining it with fuzzy rules to yield an inference result (Guillaume, 2001). In fuzzy decision-making, the membership degrees of different options are calculated by defining the membership functions of decision variables. The triangular fuzzy number is commonly used to represent the uncertainty of various decision options, as illustrated in Figures 1 and 2, which show the membership degree and fuzzy semantic relationship diagrams. Triangular fuzzy numbers are widely applied in fields such as fuzzy logic, fuzzy control, decision analysis, and other areas that deal with uncertainty and fuzziness.

To ensure the comprehensiveness and accuracy of this research, a mixed research method combining questionnaire surveys with fuzzy semantic analysis was used. This study was divided into three main stages: first, data on the residents’ responses to the living environment was collected through a questionnaire survey; second, fuzzy semantic computing was applied to process the questionnaire data; and finally, fuzzy semantic computing methods were used for quantitative analysis to reveal the role of bionic design in optimizing rural human settlement environments and its ecological benefits.

To quantify and analyze the impact of bionic design features on the emotional resonance and ecological identity of rural residents, a relational model based on fuzzy semantic computing was developed. This model was designed to handle complex and multi-dimensional evaluation factors and reveal the relationship between bionic design features and the emotional experiences and ecological identity of residents through fuzzy logic reasoning. The fuzzy semantic relation model in this study was built using Fuzzy Comprehensive Evaluation (FCE) and Fuzzy Inference System (FIS). By the fuzzy processing of multi-dimensional evaluation factors, this model reflects the impact of bionic design features—such as morphological differences, material integration, and interactive functions—on the emotional resonance and ecological identity of residents, and it quantifies the relationship, as shown in Figure 3. In this model, bionic design features serve as independent variables, which are used for subsequent reasoning and evaluation through fuzzy semantic computing models (including fuzzy processing, fuzzy reasoning, and defuzzification). The output layer mainly includes the emotional resonance and ecological identity of residents. Through fuzzy reasoning, the model analyzes how bionic design features influence these two outcomes, ultimately assisting in the optimization of rural human settlements.

The model uses fuzzy semantic computing to analyze how bionic design features influence the emotional resonance and ecological identity of rural human settlements. Through fuzzy reasoning, the model processes complex, multidimensional data to determine the specific impact of the emotional responses of residents to the environment and their ecological identity, providing a scientific basis for environmental optimization in rural revitalization.

This study investigated the impact of bionic design features on the optimization of rural human settlements and quantified their effects on the emotional resonance and ecological identity of residents through fuzzy semantic computation. To ensure the scientific validity and representativeness of the findings, the selected samples encompassed rural areas in China's eastern, central, western, and northeastern regions, and covered diverse economic and geographical contexts, including plains, hills, and mountainous areas, in order to reflect the environmental characteristics of different localities.

When selecting villages in each region, priority was given to sites that varied in population size, economic development level, cultural traditions, and architectural styles, thereby ensuring that the survey results captured a wide range of rural contexts. In total, 600 questionnaires were distributed, with 576 returned and 560 deemed valid, resulting in an effective response rate of 93.3%. Approximately 80-100 rural residents were surveyed in each region, representing a balanced distribution across gender, age, educational background, and occupational categories, in order to maintain demographic representativeness. The questionnaire primarily focused on the residents’ emotional evaluations of the rural living environment, perceptions of ecological identity, and subjective impressions of bionic design features, thereby providing a robust data foundation for subsequent quantitative analysis.

In this study, a questionnaire survey and fuzzy theory were employed to collect feedback from rural residents on the optimization of the human settlement environment, with a focus on the impact of bionic design features on emotional resonance and ecological identity. To ensure the scientific validity and reliability of the data, the questionnaire design and execution process included the steps of construction, pre-testing, formal survey execution, and data collection and processing.

Questionnaire design was a critical step in the entire research process. Its purpose was to accurately gather feedback from rural residents regarding the optimization of the human settlement environment through a well-structured and relevant questionnaire. In addition, 16 questionnaires were pre-tested, after which the questionnaires were modified and adjusted accordingly. According to the criteria proposed by some researchers (Nunnally, 1995; Tiku and Pecht, 2010), when Cronbach's α is greater than 0.7, the reliability and validity of the questionnaire are considered satisfactory. The questionnaire was divided into three main sections. The first section gathered basic information about the residents, including gender, age, education level, and income level. The second section focused on bionic design features, such as morphological differences, material integration, and functional interaction. The third section assessed the emotional resonance and ecological identity of the respondents, including their emotional responses and ecological identity perceptions. The questionnaire used a five-point Likert scale for scoring, with five response options for each question: “Strongly Agree,” “Agree,” “Neutral”, “Disagree,” and “Strongly Disagree,” corresponding to 5, 4, 3, 2, and 1 points, respectively. The specific questionnaire items are shown in Tables 1 and 2.

In this study, feedback data were collected from rural residents regarding the impact of bionic design features (such as morphological differences, material integration, and interactive functions) on their emotional resonance and ecological identity through a questionnaire survey. However, the evaluations provided by residents are often fuzzy and uncertain, making it difficult for traditional statistical methods to analyze these data accurately. To address this issue, fuzzy semantic computing was introduced to process and analyze the fuzzy evaluation data. In this study, the collected data were first processed, followed by fuzzy semantic statistical analysis to obtain the fuzzy evaluation results from rural residents on bionic design features. Using descriptive statistics, correlation analysis, and regression analysis, the defuzzified data were analyzed in detail to reveal the specific impacts of bionic design features on the emotional resonance and ecological identity of residents.

In this study, 560 participants from various regions of China were surveyed, and the descriptive statistics are presented in Table 3. Among them, males and females each accounted for 45.71% of the sample. Most of the respondents (74.29%) were aged between 31 and 40, while only 0.89% was over 60. In terms of educational background, nearly half (49.11%) held a bachelor's degree, whereas only 4.46% had earned a doctoral degree. Regarding annual income, 53.75% of the participants reported earning between 20000 and 50000 yuan, and only 7.50% earned more than 100000 yuan.

Note that the sample in this study shows a significant age distribution bias, with a dominant proportion (over 74%) consisting of “new-generation rural residents” aged between 31 and 40. This demographic structure reflects the active involvement of young and middle-aged groups in current rural development, and it is closely related to the phenomenon of “youth returning to the countryside” observed in the broader context of rural digitalization, tourism development, and ecological renewal. However, the representation of the traditional elderly population (aged 60 and above) is extremely limited, accounting for only 0.36% of the sample, so it is difficult to capture their cognitive and emotional distinctions comprehensively. Therefore, when interpreting the results and evaluating the applicability of the model, it is important to acknowledge the limitations in representativeness and to consider potential intergenerational differences in ecological identity, emotional resonance, and related cognitive dimensions.

Reliability analysis is used to assess whether sample responses are consistent and dependable. In this study, the second part of the questionnaire focused on the residents’ views and evaluations of bionic design features, including morphological differences, material integration, and functional interaction. As shown in Table 4, the Cronbach's α coefficient is 0.957. The third part of the questionnaire assessed the emotional resonance and ecological identity of residents, with a Cronbach's α of 0.963. The reliability coefficients for both the second and third parts of the questionnaire exceed 0.8, indicating excellent reliability of the test and trustworthy results.

The second part of the questionnaire focused on the impact of bionic design features, such as size, appearance, and color, on the fuzzy semantics of residents, as shown in Table 5. For Question 2-6, which states, “The design in the rural environment extensively uses eco-friendly and sustainable materials (e.g., recycled wood, green building materials),” the fuzzy semantic value is the highest at 4.32. In contrast, for Question 2-9, “Interactive elements in rural design (e.g., smart guides, shared spaces) enhance the residents’ living experience,” the fuzzy semantic value is the lowest at 2.87.

The third section of the questionnaire focused on the impact of bionic design features on the emotional resonance and ecological identity of residents, specifically examining morphological differences, material integration, and functional interaction. As shown in Table 6, Q3-8, “The green spaces in the rural environment make you feel relaxed and comfortable,” received a score of 4.29. The corresponding membership function is µ(x)=(5-4.29)/(5-4)=0.71, which indicates that the value of 4.29 is close to “Strongly Agree,” as shown in Figure 4. However, Q3-10, “Rural design makes you feel like part of the community, enhancing your sense of belonging,” shows a fuzzy semantic value of 2.84. The corresponding membership function is µ(x)= (2.74-2)/ (3-2)=0.74, which indicates that the value is closer to “Neutral,” as shown in Figure 5.

Based on the fuzzy semantic values from the second part of the questionnaire, a correlation analysis was conducted between these values and the emotional responses of residents in the third part of the questionnaire. Pearson's Chi-square test (X²), degrees of freedom (df), and significance analysis (P) were primarily applied using SPSS software. Pearson's Chi-square tests are used to assess the independence or association between two categorical variables by comparing the difference between observed and expected frequencies. This helps to determine whether there is a statistically significant association between variables. In this study, the relationship between the residents’ perceptions of bionic design features and their emotional resonance and ecological identity was examined.

The degrees of freedom represent the independent pieces of information used to calculate statistics in a statistical model. It reflects the extent to which the sample data can vary without affecting the statistical parameters. The degrees of freedom provide a better interpretation of the Chi-square test results to ensure the reliability and validity of the conclusions. Significance analysis determines whether the observed statistical results are statistically significant by calculating the P-value. The P-value represents the probability of obtaining the current result, or one more extreme, assuming the null hypothesis is true. Generally, a significant association is indicated when P<0.05.

As shown in Table 7, the Chi-square statistics for most questions demonstrate a high level of significance (P<0.05), suggesting that “bionic design features (morphological differences)” are significantly correlated with “the emotional resonance and ecological identity of residents”. This indicates that the morphological differences in bionic design features have a significant impact on the emotional resonance and ecological identity of residents.

The Chi-square test between the material integration of bionic design features and their impact on the emotional resonance and ecological identity of residents (Q3-1 to Q3-10) revealed that the Chi-square statistics for all questions are statistically significant (P<0.05). This indicates that the bionic design feature “material integration” has a significant impact on the emotional resonance and ecological identity of residents. Therefore, in the optimization of human settlements, integrated design is a crucial factor in enhancing the living comfort of residents.

The Chi-square test of bionic design features (functional interaction) and their impact on the emotional resonance and ecological identity of residents (Q3-1 to Q3-10) revealed that the Chi-square statistics for all questions are statistically significant (P<0.05). This suggests that the “functional interaction” aspect of design also has a significant impact on the emotional resonance and ecological identity of residents. Thus, in the optimization of rural living environments, “functional interaction” is a crucial factor. Designers should focus on this aspect to enhance the satisfaction and comfort of residents.

This study used a linear regression model to assess how three design features—“morphological difference,” “material integration,” and “functional interaction”—affect the emotional resonance and ecological identity of residents.

The model summary (Table 8) shows that the correlations of all independent variables are highly significant. Among them, material integration has the strongest impact on emotional resonance and ecological identity, followed by morphological difference, and finally functional interaction. The adjusted R² values demonstrate the strong explanatory power of these independent variables in relation to the dependent variables. Notably, in the “material integration” model, higher R² values and lower standard errors indicate that this independent variable has a strong ability to explain emotional resonance and ecological identity. At the same time, the analysis further revealed the standardized regression coefficient (Beta value) for each independent variable and its impact on the dependent variable. The results show that morphological difference and material integration significantly affect emotional resonance and ecological identity, with Beta values of 0.117 and 0.122, respectively, and P-values less than 0.05. This demonstrates that both have significant positive effects on the dependent variables. Although the Beta value of functional interaction is 0.149, its high P-value (P=0.340) suggests that its effect in this model is not significant. Therefore, future research could explore ways to enhance the effect of functional interaction on emotional resonance and ecological identity, or consider supplementing it with other variables.

ANOVA was used to evaluate the impacts of independent variables on emotional resonance and ecological identity (Table 9). Based on the F-value and P-value results, morphological difference and material integration had statistically significant effects on emotional resonance and ecological identity (P<0.05). This suggests that these two design features have a significant positive effect on improving the emotional experience and ecological satisfaction of residents. The P-value for functional interaction (0.083) is slightly above 0.05, indicating that its effect on emotional resonance and ecological identity is not significant. This may be due to either other influencing factors or its relatively weak effect in the current data sample.