Explanatory Ability Research Articles

Research on the correlation between different dietary habits and chronic diseases in China

Among all chronic disease risk factors, an unhealthy diet is the first and most widely affected risk factor. Although there have been many studies on eating behavior, there is a lack of quantitative studies on the association between dietary taste differences and chronic diseases in different regions of China. Therefore, this paper utilizes crowd-sourced online recipe data to extract multi-dimensional flavor information from cuisine, combined with geo-tagged restaurant-type interest points data from different regions, to quantitatively analyze the flavor preferences of different groups of people. From the perspective of spatial heterogeneity, we established the association between the 7 flavors and three chronic diseases (hemorrhagic stroke, pancreatic cancer, and upper respiratory infection), and obtained the measure of the explanation ability of dietary flavor on the spatial distribution of chronic diseases. The results show that salty is the primary flavor risk factor for hemorrhagic stroke; sweet to a certain extent is the primary flavor risk factor for pancreatic cancer, and the degree of sweetness is not simply linearly related to the risk of pancreatic cancer; spicy is the primary flavor risk factor for upper respiratory infection, and all three are statistically significant.

Measuring The Information Content Of Accounting Profits In The Iraqi Banking Sector For Banks Listed On The Iraqi Stock Exchange

The study aims to measure the information content of the accounting profits of banks listed on the Iraqi Stock Exchange, as the sample included 10 banks for a period of 4 years (2016-2019). The study concluded that banks that have a high explanatory ability reflect greater stability in the stock price, which would reassure Investors and stakeholders, thus reducing dispersion and fluctuations in the stock price, while banks with weak explanatory power show higher volatility in the stock price, which indicates additional risks that increase the fluctuation in investor returns, and the influencing factors have a major role in enhancing or reducing the information content of profits. Which explains the discrepancy between banks, and the study recommended the need to enhance the quality of financial disclosure, especially banks with weak explanatory capacity, increase transparency, and work to enhance the informational content of profits, which in turn increases investors’ confidence in accounting information, as well as encouraging banks to strengthen their internal control systems, which helps in Reducing accounting errors and the accuracy of declared profits, thus stabilizing the share price. Strengthening the administrative capabilities of executive managers contributes significantly to enhancing the informational content of profits by allocating the company’s available resources efficiently and effectively.

Research on Dynamic Flexible Performance Evaluation System of Geely Automobile under the Background of Digital Transformation

As a pillar industry of the country, the automobile manufacturing industry implements the digital transformation strategy in the era of intelligent innovation, which is not only an objective requirement for the development of the digital economy in the era of big data, but also an internal driving force for diversified consumer demand and improving the core competitiveness of products, reducing costs and increasing efficiency and improving the operating efficiency of enterprises. Under the premise of analyzing the necessity and feasibility of the construction of Geely Automobile's dynamic flexible performance evaluation system under the background of digital transformation, this paper constructs Geely Automobile's dynamic flexible performance evaluation system from four aspects: target layer, criterion layer, scheme layer and influence layer, based on the principles of dynamic flexibility and reflecting key success factors. The empirical results show that the Geely Automobile dynamic flexible performance evaluation system constructed in this paper has relevance, stability and explanatory ability.

Learning to explain is a good biomedical few-shot learner.

Significant progress has been achieved in biomedical text mining using deep learning methods, which rely heavily on large amounts of high-quality data annotated by human experts. However, the reality is that obtaining high-quality annotated data is extremely challenging due to data scarcity (e.g. rare or new diseases), data privacy and security concerns, and the high cost of data annotation. Additionally, nearly all researches focus on predicting labels without providing corresponding explanations. Therefore, in this paper, we investigate a more realistic scenario, biomedical few-shot learning, and explore the impact of interpretability on biomedical few-shot learning. We present LetEx-Learning to explain-a novel multi-task generative approach that leverages reasoning explanations from large language models (LLMs) to enhance the inductive reasoning ability of few-shot learning. Our approach includes (1) collecting high-quality explanations by devising a suite of complete workflow based on LLMs through CoT prompting and self-training strategies, (2) converting various biomedical NLP tasks into a text-to-text generation task in a unified manner, where collected explanations serve as additional supervision between text-label pairs by multi-task training. Experiments are conducted on three few-shot settings across six biomedical benchmark datasets. The results show that learning to explain improves the performances of diverse biomedical NLP tasks in low-resource scenario, outperforming strong baseline models significantly by up to 6.41%. Notably, the proposed method makes the 220M LetEx perform superior reasoning explanation ability against LLMs. Our source code and data are available at https://github.com/cpmss521/LetEx.

Quantifying decision support level of explainable automatic classification of diagnoses in Spanish medical records

Background and Objective:In the realm of automatic Electronic Health Records (EHR) classification according to the International Classification of Diseases (ICD) there is a notable gap of non-black box approaches and more in Spanish, which is also frequently ignored in clinical language classification. An additional gap in explainability pertains to the lack of standardized metrics for evaluating the degree of explainability offered by distinct techniques. Methods:We address the classification of Spanish electronic health records, using methods to explain the predictions and improve the decision support level. We also propose Leberage a novel metric to quantify the decision support level of the explainable predictions.We aim to assess the explanatory ability derived from three model-independent methods based on different theoretical frameworks: SHapley Additive exPlanations (SHAP), Local Interpretable Model-agnostic Explanations (LIME), and Integrated Gradients (IG). We develop a system based on longformers that can process long documents and then use the explainability methods to extract the relevant segments of text in the EHR that motivated each ICD. We then measure the outcome of the different explainability methods by implementing a novel metric. Results:Our results beat those that carry out the same task by 7%. In terms of explainability degree LIME appears as a stronger technique compared to IG and SHAP. Discussion:Our research reveals that the explored techniques are useful for explaining the output of black box models as the longformer. In addition, the proposed metric emerges as a good choice to quantify the contribution of explainability techniques.

Impact of the destination image and government policy responsiveness of China on Korean travelers’ destination trust and behaviors in the post-pandemic era

The underlying mechanism of the destination trust of Korean travelers and behaviors toward China after the COVID-19 pandemic is explored in the present study, which considers the role of the destination image constituents and perceived government policy responsiveness for tourism recovery. The data was collected from Korean nationals who are currently residing in South Korea and have traveled to China in the last five years. The results revealed that the developed conceptual framework had a satisfactory level of explanatory ability in regards to predicting the travel and recommendation intentions of Korean travelers toward China, which destination trust serves as the key mediator. Moreover, the perception of Korean travelers in regards to Chinese government policy responsiveness for tourism recovery significantly strengthened the effect of image factors on destination trust. The study also discovered that the importance of image factors varies in regards to the formation of trust and destination behaviors. This research provides significant theoretical insights into the post-health crisis tourism recovery, which emphasizes changes in Korean travel patterns in the aftermath of COVID-19 as well as the wider socio-political environment that influences travel destinations. It also presents useful guidance for Chinese tourism stakeholders in regards to implementing effective recovery strategies that are aimed at the lucrative Korean outbound travel market during the post-COVID-19 pandemic period.

Advancing thyroid care: An accurate trustworthy diagnostics system with interpretable AI and hybrid machine learning techniques

The worldwide prevalence of thyroid disease is on the rise, representing a chronic condition that significantly impacts global mortality rates. Machine learning (ML) approaches have demonstrated potential superiority in mitigating the occurrence of this disease by facilitating early detection and treatment. However, there is a growing demand among stakeholders and patients for reliable and credible explanations of the generated predictions in sensitive medical domains. Hence, we propose an interpretable thyroid classification model to illustrate outcome explanations and investigate the contribution of predictive features by utilizing explainable AI. Two real-time thyroid datasets underwent various preprocessing approaches, addressing data imbalance issues using the Synthetic Minority Over-sampling Technique with Edited Nearest Neighbors (SMOTE-ENN). Subsequently, two hybrid classifiers, namely RDKVT and RDKST, were introduced to train the processed and selected features from Univariate and Information Gain feature selection techniques. Following the training phase, the Shapley Additive Explanation (SHAP) was applied to identify the influential characteristics and corresponding values contributing to the outcomes. The conducted experiments ultimately concluded that the presented RDKST classifier achieved the highest performance, demonstrating an accuracy of 98.98 % when trained on Information Gain selected features. Notably, the features T3 (triiodothyronine), TT4 (total thyroxine), TSH (thyroid-stimulating hormone), FTI (free thyroxine index), and T3_measured significantly influenced the generated outcomes. By balancing classification accuracy and outcome explanation ability, this study aims to enhance the clinical decision-making process and improve patient care.

A Novel Hybrid ANFIS-NARX and NARX- ANN models to Predict the profitability of Egyptian Insurance Companies

The use of fuzzy logic models with machine learning (ML) models have become common in many areas, especially insurance field. This study aims to compare between non-hybrid models such as artificial neural network (ANN) model, adaptive neural fuzzy inference system (ANFIS) model, nonlinear auto-regressive external input (NARX) model, and the following hybrid models (ANFIS-NARX) and (NARX-ANN) to predict the profits of the insurance activity which represent the important indicator of the good performance of Egypt's 39 insurance companies in the period from 1st January 2009 to 31 December 2022 , monthly .This prediction based on the following factors (net premiums, reinsurance commissions, net income from earmarked investments, other direct income, net compensation, production cost commissions and general and administrative expenses) that help decision makers to make appropriate decisions . The results found that the (ANN) model is given good results compared with the following models (ANFIS), (NARX), hybrid (ANFIS-NARX) and (NARX-ANN) models according to the following prediction accuracy measures (RMSE, MAPE, MAE and Theil inequality). The explanatory ability (R2) was appeared (0.79, 0.61) respectively for training and testing phases in persons insurance companies. The explanatory ability also was appeared (0.83, 0.68) respectively in property insurance companies.

Spatial and Temporal Scale Effects of Landscape Pattern on Riverine Nitrogen and Phosphorus Nutrients in the Qingshan Lake Watershed

The influences of landscape pattern on water quality are dependent on spatial-temporal scales. However, the effects of landscape composition, landscape configuration, and landscape slope metrics on seasonal water quality at different spatial scales remain unclear. Based on the total nitrogen, total phosphorus, nitrate-N, and ammonium-N data from 26 sampling sites in the Qingshan Lake watershed, this study coupled landscape pattern analysis, redundancy analysis, and partial redundancy analysis to quantify the spatiotemporal scale effects of landscape pattern on riverine nitrogen （N） and phosphorus （P） concentrations. The results showed that： ① The explanatory ability of landscape pattern at the sub-watershed scale on riverine N and P concentrations was 6.8%-8.4% higher than that at the buffer scale, and this effect was more obvious in the dry season. ② At the sub-watershed scale, the percentage of forestland and the interspersion and juxtaposition degree of residential land had a greater influence on riverine N and P concentrations. At the buffer scale, the slope of farmland and residential land and the aggregation degree of forestland patches were the key factors affecting riverine N and P concentrations. ③ The contribution rate of landscape configuration to riverine N and P concentration variations （20.1%-36.5%） was the highest. The sensitivity of the effect of landscape configuration on riverine N and P concentrations to seasonal changes was the highest, and the effect of landscape slope on riverine N and P concentrations had the highest sensitivity to spatial scale changes. Therefore, landscape pattern-regulated non-point source pollution should be considered from a multi-scale perspective. These results can provide scientific basis for the formulation of landscape pattern optimization measures aiming at non-point source pollution control.

Profil Penjelasan Ilmiah Siswa SMA pada Materi Sistem Peredaran Darah Manusia

This study aims to determine the profile of scientific explanation ability of high school students, especially on the material of the human circulatory system. The type of research used is quantitative research with survey methods shared through google forms. The subjects of the study were high school students who had received human circulation system material in one of several schools in Central Java, the research sample was selected through random sampling techniques from the population. The research instrument used was adapted from McNeill, Lizotte, Krajcik, and Marx (2016) which consisted of 9 long answer questions to be able to determine the success of aspects of claim, evidence, and reasoning in scientific explanation. The instrument has been declared valid and reliable through Rasch Model testing. The research data is in the form of scores from student answers which are then processed through the Rasch Model to determine the level of difficulty and wright map person (students) to find out the profile of each student's scientific explanation ability. The results showed that 78% of students were still at the lower middle level in compiling the three aspects of scientific explanation, and only 12% of students were able to achieve maximum scores in the preparation of claims, evidence, and reasoning.

Probabilistic rutting model using NGBoost and SHAP: Incorporating other performance indicators

This study focuses on accurately predicting rutting depth (RD) through a probabilistic prediction model, which is crucial for timely road maintenance and traffic safety. Natural Gradient Boosting (NGBoost) technology is employed to achieve this goal as it provides accurate predictions and estimates the uncertainty of predictions. Furthermore, to explain the decision-making process of the proposed prediction model, Shapley Additive Explanations (SHAP) analysis is applied to identify and quantify significant factors affecting RD. Research results show that the NGBoost model surpasses the traditional Gaussian Process and Random Forest model regarding prediction accuracy and performs better regarding certainty of prediction intervals. Meanwhile, SHAP analysis improves the transparency of model decision-making and further validates the model. Explanatory ability elucidates the impact of other characteristics on RD. The two-stage probabilistic prediction model not only enhances the reliability of predictions but also provides an in-depth understanding of the key influencing factors of pavement performance, improving the efficiency and effectiveness of maintenance measures.

Exploring the Role of Self-Adaptive Feature Words in Relation Quintuple Extraction for Scientific Literature

Extracting relation quintuple and feature words from unstructured text is a prelude to the construction of the scientific knowledge base. At present, the prior works use explicit clues between entities to study this task but ignore the use and the association of the feature words. In this work, we propose a new method to generate self-adaptive feature words from the original text for every single sample. These words can add additional correlation information to the knowledge graph. We allow the model to generate a new word representation and apply it to the original sentence to judge the relation type and locate the head and tail of the relation quintuple. Compared with the previous works, the feature words increase the flexibility of relying on information and improve the explanatory ability. Extensive experiments on scientific field datasets illustrate that the self-adaptive feature words method (SAFW) is good at ferreting out the unique feature words and obtaining the core part for the quintuple. It achieves good performance on four public datasets and obtains a markable performance improvement compared with other baselines.

Improving Driving Style in Connected Vehicles via Predicting Road Surface, Traffic, and Driving Style

This paper investigates the application of ensemble learning in improving the accuracy and reliability of predictions in connected vehicle systems, focusing on driving style, road surface quality, and traffic conditions. Our study’s central methodology is the voting classifier ensemble method, which integrates predictions from multiple machine learning models to improve overall predictive performance. Specifically, the ensemble method combines insights from random forest, decision tree, and K-nearest neighbors models, leveraging their individual strengths while compensating for their weaknesses. This approach resulted in high accuracy rates of 94.67% for driving style, 99.10% for road surface, and 98.80% for traffic predictions, demonstrating the robustness of the ensemble technique. Additionally, our research emphasizes the importance of model explanation ability, employing the tree interpreter tool to provide detailed insights into how different features influence predictions. This paper proposes a model based on the algorithm GLOSA for sharing data between connected vehicles and the algorithm CTCRA for sending road information to navigation application users. Based on prediction results using ensemble learning and similarity in driving styles, road surface conditions, and traffic conditions, an ensemble learning approach is used. This not only contributes to the predictions’ transparency and trustworthiness but also highlights the practical implications of ensemble learning in improving real-time decision-making and vehicle safety in intelligent transportation systems. The findings underscore the significant potential of advanced ensemble methods for addressing complex challenges in vehicular data analysis.

Effects of litter thickness on natural regeneration of Larix principis-rupprechtii plantations

In this study, we explored the thickness influence of undecomposed litter layer and semi-decomposed litter layer on the natural regeneration in an artificial pure forest of Larix principis-rupprechtii in the forest area of Guandi Mountain. We divided the litter into an undecomposed layer and a semi-decomposed layer, which was further divided into eight groups based on the thickness. The results showed that when the thickness of undecomposed layer was 0.32-0.83 cm, and that of semi-decomposed layer was 0.18-0.89 cm, the regeneration index was larger (≥0.15), and the regeneration was better. When the thickness of undecomposed layer was more than 1.1 cm and that of semi-decomposed layer was more than 0.5 cm, the regeneration index was smaller (≤0.07), and the rege-neration of understory was worse. Results of redundancy analysis showed that the undecomposed layer thickness of litter had a high and stable explanatory ability for natural regeneration, with a contribution rate of 38.7%, while the semi-decomposed layer thickness had no significant effect on natural regeneration. Structural equation modeling revealed that the thickness of undecomposed layer of litter increased the mechanical resistance to seed germination which had a negative direct effect on natural regeneration (-0.617), and a positive indirect effect on natural rege-neration by influencing the content of alkali-hydrolyzed nitrogen and available phosphorus (+0.178). The combined effects (-0.439) showed an inhibitory effect on the natural regeneration. In conclusion, the thickness of undecomposed layer of litter under L. principis-rupprechtii was most closely related to natural regeneration, and the thickness of semi-decomposed layer had a minimal effect on natural regeneration.

Measurement and Spatial Difference Analysis of the Development Level of Urban Solid Waste Resource Utilization from the Perspective of "Waste-Free City"

While the domestic economy is developing rapidly, the impact of municipal solid waste on the ecological environment is increasing. The construction of "waste-free cities" has become an inevitable choice and an important tool to promote the sustainable development of cities and the sustainable management of solid waste. This paper evaluates the level of solid waste resource utilization in 27 central cities in the Yangtze River Delta region from four dimensions: technical level, economic benefit, social benefit and environmental protection benefit. Firstly, the gray correlation is used to calculate the gray correlation between the selected indicators and the green low-carbon city index, and the results show that the gray correlation of all the indicators is greater than 0.80, which has strong explanatory ability. Then, the entropy weighting method was used to calculate the weights of the indicators and the comprehensive score of the cities, and the top five cities in the comprehensive score were Shanghai, Suzhou, Hangzhou, Ningbo and Nanjing. Then, by comparing the average scores of Shanghai, Jiangsu Province, Zhejiang Province and Anhui Province, the difference analysis is carried out, and it is found that the regional economic level and industrial structure are the main factors affecting the development level of municipal solid waste resourceization. Finally, the results of the empirical analysis are combined to make suggestions for the construction of "waste-free cities" in China.

Driving forces of digital transformation in chinese enterprises based on machine learning

With advanced science and digital technology, digital transformation has become an important way to promote the sustainable development of enterprises. However, the existing research only focuses on the linear relationship between a single characteristic and digital transformation. In this study, we select the data of Chinese A-share listed companies from 2010 to 2020, innovatively use the machine learning method and explore the differences in the predictive effects of multi-dimensional features on the digital transformation of enterprises based on the Technology-Organization-Environment (TOE) theory, thus identifying the main drivers affecting digital transformation and the fitting models with stronger predictive effect. The study found that: first, by comparing machine learning and traditional linear regression models, it is found that the prediction ability of ensemble earning method is generally higher than that of tradition measurement method. For the sample data selected in this research, XGBoost and LightGBM have strong explanatory ability and high prediction accuracy. Second, compared with the technical driving force and environmental driving force, the organizational driving force has a greater impact. Third, among these characteristics, equity concentration and executives’ knowledge level in organizational dimension have the greatest impact on digital transformation. Therefore, enterprise managers should always pay attention to the decision-making role of equity concentration and executives’ knowledge level. This study further enriches the literature on digital transformation in enterprises, expands the application of machine learning in economics, and provides a theoretical basis for enterprises to enhance digital transformation.

A Systematic Review of the Single-Item Burnout Question: Its Reliability Depends on Your Purpose.

Surveillance of burnout by the gold-standard Maslach Burnout Inventory (MBI) is hindered by cost and length. The validity and benchmarking of the commonly recommended and used single-item burnout question (SIBOQ) are unknown. We sought to (1) derive an equation for predicting the gold standard MBI from the SIBOQ and (2) measure the correlation of the SIBOQ with the full MBI and its subscales. We sought studies in PubMed along with citations by and to included studies. We included studies that either correlated the SIBOQ and the MBI or reported the rates of burnout measured by both instruments. Two reviewers extracted data and CLARITY risk of bias. We used generalized linear mixed regression to separately quantify the predictive (benchmarking) and explanatory (hot-spotting) capabilities of the SIBOQ. We created a regression equation for converting SIBOQ scores to MBI scores. We meta-analyzed correlation coefficients (r) for the SIBOQ and MBI subscales. For all analyses, we considered an r of 0.7 as acceptable reliability for group-level comparisons. We included 17 studies reporting 6788 respondents. All studies had a high risk of bias, as no study had a response rate over 75% and no study was able to examine non-responders. The correlations (r) of the SIBOQ with the overall MBI were explanatory r = 0.82 and predictive r = 0.56. Regarding MBI subscales, the correlations of the SIBOQ with emotional exhaustion were adequate with r = 0.71 (95% CI 0.67-0.74; I2 = 89%), and depersonalization was r = 0.44 (95% CI 0.34-0.52; I2 = 90%). However, in 8 of 15 comparisons, the r was less than 0.70. The SIBOQ's usually adequate explanatory abilities allow "hot-spotting" to identify subgroups with high or low burnout within a single, homogenous survey fielding. However, the predictive ability of the SIBOQ indicates insufficient reliability in comparing local results to external benchmarks.

Exploring the Drivers of Soil Conservation Variation in the Source of Yellow River under Diverse Development Scenarios from a Geospatial Perspective

Soil conservation (SC) plays a vital role in preventing soil erosion and ensuring ecological security. While current research on SC primarily focuses on historical spatiotemporal variations, there remains a dearth of sufficient simulation research exploring future development scenarios. In this study, simulations were applied to the source of Yellow River (SYR), a representative ecologically fragile area. Satellite remote sensing and product data, including precipitation, soil, land use/cover, DEM, and SPOT/VEGETATION NDVI, were utilized. The historical and future evolutionary trends of SC in the SYR were quantitatively assessed using the Revised Universal Soil Loss Equation (RUSLE) and trend analysis method, and the geographical detector was employed to explore the forces driving spatial differentiations in SC. The results demonstrated that: (1) 2000–2020, the spatial heterogeneity of SC in the SYR was characterized by the distribution of “gradually decreasing from Southeast to Northwest”, demonstrated a trend of “increasing, decreasing, and then increasing”. (2) Under the diverse development scenarios, the trend of SC change in the SYR was predominantly rising, and the natural change scenario (NCS) > ecological conservation scenario (ECS) > economic expansion scenario (EES). (3) Slope was the most important single driver affecting the spatiotemporal differentiation of SC, and the interaction of slope with average annual precipitation, and NDVI on the spatiotemporal heterogeneity of SC had the strongest explanatory ability. The results can serve as a scientific basis for regional SC and ecological protection and construction of the SYR.

Evaluation of impact of land use and landscape metrics on surface water quality in the northeastern part along Lake Tanganyika, Africa.

As the second deepest lake in Africa, Lake Tanganyika plays an important role in supplying fish protein for the catchment's residents and is irreplaceable in global biodiversity. However, the lake's water environment is threatened by socioeconomic development and rapid population growth along the lake. This study analyzed the spatial scale effects and seasonal dependence of land use types and landscape metrics on water quality in 16 sub-basins along northeastern Lake Tanganyika at different levels of urbanization. The results revealed that land use types had a higher influence on water quality in urban areas than that in rural areas; the explanatory variance in the urban area was 0.78-0.96, while it was 0.21-0.70 in the rural area. The explanatory ability of land use types on water quality was better at the buffer scale than at the sub-watershed scale, and the 500m buffer scale had the highest explanatory ability in the urban area and rural area both in the rainy season and dry season, and artificial surface and arable land were the main contributing factors. And this phenomenon was more obvious in dry season than in rainy season. We identified that CONTAG was the key landscape metric in urban area and was positively correlated with nutrient variables, indicating that water quality degraded in less fragmented landscapes. The sub-watershed scale had the highest explained ability, while in rural area, the 1500m buffer scale had the highest explained ability and IJI had the highest explanatory variance, which had a negative effect on water quality. Research on the relationship between land use and water quality would help assess the water quality in the unmonitored watershed as monitoring is expensive and time-consuming in low-income area. This knowledge would provide guideline to watershed managers and policymakers to prioritize the future land use development within Lake Tanganyika basin.

Traditional Woodworking Techniques and Digital Restoration Technology in the Perspective of Intangible Cultural Heritage

Abstract Based on the theoretical knowledge of woodworking skills and digital restoration, this paper designs a questionnaire on traditional woodworking skills and digital restoration technology, conducts a reliability test on the questionnaire, adopts online and offline methods to distribute the questionnaire and obtains research data. Pearson’s coefficient and multiple linear regression model were used to explore the relationship between traditional woodworking skills and digital restoration technology from the perspective of non-heritage. The results show that the regression equation of the historical value of woodworking skills = 0.428+0.176*Efficiency Improvement+0.208*Quality Optimization+0.235*Talent Cultivation, and the explanatory ability of Efficiency Improvement, Quality Optimization (X2), and Talent Cultivation (X3) for the historical value of the skills is 76.6%, and there is no problem of multicollinearity. The mechanism of interaction between traditional woodworking techniques and digital restoration technology is analyzed from the perspective of non-heritage, which is important for the preservation and dissemination of non-heritage.