This study aims to construct an effective pathway for students’ career planning and innovative industry education by integrating support vector machine algorithm with big data analysis technology. By effectively integrating multi-source data and combining the improved genetic algorithm for feature selection and extraction of student data, the support vector machine algorithm is used to conduct in-depth analysis of the data related to students’ career planning and innovation and entrepreneurship education, to provide students with accurate and personalized career and entrepreneurship guidance, and based on which, the career planning and innovation and entrepreneurship education path is constructed. Experimental analysis of the classification prediction performance of the support vector machine algorithm and comparison with other classification prediction algorithms show that the support vector machine algorithm used in this paper has the highest classification accuracy in the assessment of students’ career planning and innovation and entrepreneurship ability, and the model performance is the most stable. The results of the educational experiment show that after using the educational path proposed in this paper, the students’ satisfaction with career planning and the mean value of the assessment score of innovation and entrepreneurship ability increase by 70.89% and 170.73%, respectively. The above results fully demonstrate the effectiveness of the educational path constructed in this paper, which provides a useful reference for efficient education and teaching reform.

This paper measures the international trade efficiency of developing countries based on the data envelopment analysis (DEA) model, and explores the impact of digital transformation on trade efficiency differentiation using regression analysis. Relevant data of 19 developing countries, including China, are selected, and the trade efficiency at each stage is calculated separately using the three-stage DEA model in this paper. The regression model is constructed to quantitatively analyze the impact of digital transformation in the differentiation of trade efficiency of developing countries. From 2011 to 2020, the trade efficiency of each developing country shows a wave-like upward trend, and the average value of the comprehensive average efficiency in the third stage is 0.728, but only China, Peru and Colombia have a higher than average level of trade efficiency, which intuitively demonstrates the trade efficiency differentiation of developing countries. Differentiation. The overall regression results show that the elasticity coefficient of digital transformation on the international trade efficiency gap is -0.274, indicating that digital transformation has a greater effect on narrowing the trade efficiency gap than widening it. And in the subregional regression, the elasticity coefficient of digital transformation in Asia is 1.398, and the elasticity coefficients in Africa and Latin America regions are -0.953 and -0.603 respectively, and the digital transformation has significantly different impacts on trade efficiency differentiation in different regions.

The continuous improvement of judicial construction has led to the emergence of a large amount of judicial data on the Internet, and how to make full use of judicial data to promote judicial openness, fairness and efficiency has become an important issue in the construction of judicial informatization. In the article, the word vector generation technique is used to obtain the annotation sequence of legal text, and then the BiLSTM model is combined with the CRF model to realize the recognition of legal text entities, and the Adam algorithm is used to optimize the training of the model, so as to improve the recognition effect of the model on legal text entities. The GCN model in the graph representation learning algorithm is introduced, and the legal text entity recognition results are used as inputs for the construction of sequential and semantic relationships, and the GCN-BiLSTM model for legal text entity relationship extraction is constructed by combining the graph representation attention network and the BiLSTM model. Based on the self-constructed legal text dataset, the validation analysis of the above model is carried out through simulation experiments.The accuracy of the BILSTM-CRF model in legal text entity recognition is 85.67%, which is 7.35% higher than that of the single LSTM-CRF model. The GCN-BiLSTM model improves its accuracy by 2.14 percentage points compared with the CasRel model in extracting the entity relationships of legal texts with multi-entity overlapping. Combined with the legal text entity relationship extraction results, the knowledge map of legal cases can be constructed to provide accurate knowledge relationship support for sorting out the veins of legal cases.

Under the accelerated process of economic globalization and the booming development of Internet technology, cross-border e-commerce, as a new mode of international trade, is becoming a new driving force for the transformation and upgrading of foreign trade with its high efficiency and convenience, low cost and high benefit. This study uses data cleaning and missing value filling methods to preprocess user behavior data and merchandise sales marketing data in cross-border e-commerce Wish platform, and discretizes user behavior data using rough set method. Then, we select the merchandise sales and user behavior as the dependent and independent variables to construct a multiple nonlinear regression model in order to analyze the influence of user data on sales in cross-border e-commerce Wish platform. The results of the multivariate nonlinear regression model show that user behavior in cross-border e-commerce Wish platform has a significant effect on merchandise sales (P=0.005243). It is also found that the sales strategy adjusted according to the regression results can improve the sales and promotion effect of enterprises in cross-border e-commerce platform. The research results of this paper enrich the theoretical and practical research on the optimization and adjustment of cross-border e-commerce enterprises’ sales strategies, provide theoretical basis and decision-making reference for the subsequent adjustment of cross-border e-commerce enterprises’ sales strategies, and help cross-border e-commerce enterprises to go global.

In this paper, based on the knowledge graph, word vectors and other personalized path generation related technologies, based on the graph convolutional neural network to complete the construction of the English knowledge graph model, to generate a personalized English knowledge graph, drawing on the data structure in the graph, to generate a personalized learning path, in order to make the generation of personalized learning path is more reasonable, in accordance with the difficulty value of the exercises for the exercises to be sorted. Simulation experiments are designed to evaluate the difficulty level of the generated exercises. The difficulty level of most of the English exercises generated by the personalized recommendation path is concentrated in the easy and general levels, and there are a total of 2,229 questions in these two difficulty levels, so the difficulty level of the generated questions is moderate. After a period of personalized path-generated English learning, six teaching activities were carried out, and the average score of the first post-test of the experimental group was higher than that of the control group, and the Sig values were all less than 0.05, indicating that the difference in the scores of the two groups of students was significant, which side by side reflected the accuracy of personalized path-generated English teaching.

In the era of digital economy, the digital transformation of enterprise financial management has become an important topic that needs to be studied and solved at present. In this paper, based on analyzing the internal and external drivers on the digital transformation of enterprise financial management, the financial data of 3,498 Shanghai and Shenzhen A-share listed enterprises were obtained using Python technology. Then a fixed effect model was constructed by combining the multiple linear regression model to analyze the degree of influence of internal and external drivers on the level of digital transformation of enterprise financial management. Policy support, digital technology environment, leadership support, team awareness, and digital technology investment all have a significant effect at the 1% level on the level of digital transformation of enterprise financial management. Among them, the influence of digital technology investment is the largest, that is, every 1 percentage point increase in the enterprise’s digital technology investment in financial management, the level of digital transformation of enterprise financial management will increase by 0.204 percentage points. And there is significant regional and equity heterogeneity in the level of digital transformation of enterprise financial management, and the effect of digital transformation of financial management is stronger in the eastern region and state-owned enterprises. Therefore, in the era of digital economy, enterprises need to build a digital financial management system, strengthen cross-departmental collaboration and communication, and combine composite talents to realize the digital transformation of financial management.

In this paper, the financial structure is defined as two parts, asset structure and capital structure, with respect to the mechanism of enterprise financial management on the economic performance of enterprises. The multivariate regression model of asset structure and business performance is constructed with the dimensions of asset turnover efficiency and asset structure ratio. In order to represent the operating performance, total return on assets and return on net assets are chosen as the measures of operating performance and as the explanatory variables. It is proposed that there is a linear correlation between capital structure and corporate profitability, and the linear model between capital structure and corporate operating profitability is constructed. Combined with empirical tests to verify the relationship between asset structure or capital structure on business operations. The curve estimation method of the regression model is used to analyze the effects of inventory ratio, money fund ratio and fixed asset ratio in asset structure and capital structure on the total return on assets and return on net assets. The coefficients of fixed asset turnover on performance are 0.033 and 0.025 respectively, i.e., for every increase of 1 in fixed assets, total return on assets and return on net assets increase by 0.033 and 0.025. Similarly, the fixed asset turnover, inventory turnover, and the ratio of long term financial assets are positively correlated with the performance of the enterprise. The correlation coefficients of equity ratio and state-owned ratio of enterprise capital structure are positive, which bring positive impact on enterprise operating profitability.

Six historical building clusters in the main city of Changchun, namely People’s Street, Xinmin Street, the Palace of the Forged Manchus, the South Square, the First Automobile Manufacturing Plant, and the Kuanchengzi Station of the Middle East Railway, with a total of 2,501 historical building sites, are taken as the research objects. Using ArcGIS software, the morphology and spatial distribution pattern of the historic building clusters in the main city are discussed based on the perspective of spatial layout by invoking spatial measurement methods such as kernel density, standard deviation ellipse, algebraic geometry, and spatial correlation, etc. The results are summarized in the following table. The results show that the spatial distribution of historic buildings in the main city of Changchun is dominated by a “single center (People’s Square)” agglomeration, with a maximum kernel density of 0.9950. At the same time, the periphery also appeared to diffuse re-agglomeration, hierarchically showing a “two-axis” diffusion pattern. Among them, the main axis resides in the center of the city and extends infinitely from north to south. The secondary axis is the administrative office and center of the pseudo-Manchukuo State, which is the pseudo-Manchu Imperial Palace and Xinmin Street respectively. Finally, from the perspective of planning and design, it tries to put forward the strategy of protection and utilization, including environment, function, and culture, etc., to provide methods and bases for the holistic protection and utilization of Changchun’s historical buildings.

Students’ mental health problems are increasingly becoming an important part of the educational and teaching process in colleges and universities. In this paper, we collect students’ psychological data through the students’ mental health early warning system and preprocess the data through data cleaning and other data. The features of the processed mental health data are extracted using Global Chaos Bat Based Algorithm (GCBA). Construct a mental health early warning system for college students and build a decision tree model into the system for categorizing students’ mental health status. The performance of the decision tree model in this paper is verified by evaluating the finger with other models and comparing the actual classification prediction results, constructing the decision tree model with the psychological condition of interpersonal relationship of college students as an example, and conducting the visualization analysis of the decision tree. Independent sample t-test is conducted on three measures such as using the mental health early warning system constructed in this paper, and according to the results, the application of the system in this paper highlights the role of the enhancement of the level of students’ mental health and the significant improvement of depression and other psychological conditions.

This paper points out that dance movements can be regarded as the carrier of the fusion of traditional cultural elements and styles, and ethnic folk dance movements are used as the dynamic expression of inheriting traditional cultural elements and styles. Analyze the characteristics of non-negative matrix decomposition algorithm, and use the non-negative matrix decomposition algorithm to reduce the dimensionality of dance action images. In order to optimize the classification effect of the classifier on the data after dimensionality reduction, SVM algorithm is selected to form a dance movement recognition method based on matrix decomposition technology and SVM classifier. By adjusting the values of penalty factor and kernel parameter , the effectiveness of matrix decomposition algorithm for image dimensionality reduction is verified. Analyze the feasibility of the dance movement recognition method based on matrix decomposition technique and SVM classifier by selecting different data sets. Establish the dance movement evaluation model based on matrix decomposition technology, compare the evaluation model scores with the dance expert scores, and test the effect of matrix decomposition technology on the classification of dance movement styles. The Spearman’s correlation coefficient between the expert’s score and the model’s score remains above 90% in the evaluation of different dance movements. Combined with the evaluation guidance of dance experts, the dance style movement evaluation model proposed in this paper can effectively evaluate and analyze dance movement styles.