The study constructs a prediction model to predict the mental health status of innovative entrepreneurs. The real data of mental health assessment of innovative entrepreneurs in S province in 2023 is chosen as the data source. The recursive random forest feature elimination method is used to select the features of the mental health status prediction model. The pre-selection-elimination mechanism was used to construct the mental health state prediction model. The prediction models constructed by support vector machine algorithm, decision tree algorithm and random forest algorithm were trained and evaluated respectively. The AUC value and accuracy corresponding to the random forest algorithm are 0.9126 and 86.39%, respectively, which are better than the other two comparison models. Among the 17 mental health characteristic variables selected in this paper, emotional stress and self-acceptance degree have the greatest influence on the prediction model based on the random forest algorithm.

Social media as a new type of media has become an important channel for people to obtain information and communicate, which brings new opportunities and challenges for English education. In this study, the Markov chain model is improved by using the weighted ward system clustering method and the fuzzy set theory to improve the prediction performance of the model. Then the ARIMA model and the improved Markov chain model are combined to construct an improved time series prediction model to realize the prediction of the interaction efficiency of social media in English education. The performance of the improved prediction model is superior compared to other comparative models, providing reliability for the subsequent prediction results. The prediction results show that the interactive efficiency of social media interaction data in English education shows an upward trend over time, and the number of readings and playbacks of English courseware resources as well as video resources increases from 18477 and 18147 to 88629 and 84571 in six months. The predicted results of this study indicate that social media has good interactive efficiency in English education, which can be utilized in the future to expand the dimension of education, build an English education platform, expand the teaching space and extend educational thinking, and play a percolating role in English education.

Since the 21st century, the rapid development of artificial intelligence technology, artificial intelligence in many fields have achieved remarkable research results and applications, the integration of AI technology and music has also gradually become an emerging research field. In this paper, first of all, the generation principle of vocal interpretation AI model is studied, in order to realize the digital conversion of vocal interpretation this paper constructs a converter model so as to facilitate the application of artificial intelligence algorithm model. In this paper, in order to match the generated opera vocal music with the given opera performance background, the rhythmic relationship between opera and vocal interpretation is established, and the relationship between motion salience and note intensity is constructed. On this basis, the generator model is changed to a model with a loop structure, and the music theory is mathematically modeled to propose an adversarial network model based on improved multi-track sequence generation. Finally, for the prediction problem in the vocal interpretation AI model, this paper is optimized based on support vector regression. Through empirical analysis, the improved model in this paper has a smaller gap with the real dataset on the metrics of pitch use, pitch shift, note interval and polyphony rate within the track. Meanwhile, the TD distances of this paper’s improved model on the three datasets are 0.655, 0.784, and 0.685, respectively, which is the smallest in the experimental data, and the quality of the improved model’s vocal music generation is excellent. The pitch distribution of this paper’s improved model and the original vocal data basically match, indicating that this paper’s model has better effect on pitch adjustment. In addition, the improved model of this paper generates vocal music with better musicality effect, which has higher musicality while avoiding the generation of more invalid notes. The research work of the paper proves the feasibility of the AI model for opera vocal interpretation and provides a new solution for the current field of vocal music generation.

The application of technologies such as big data, mobile Internet, artificial intelligence and so on has triggered a major change in the field of education and promoted the classroom reform in colleges and universities. Taking deep learning theory as the research perspective, this paper constructs a college English teaching model based on deep learning, and applies the model to actual teaching practice, with a view to promoting students’ English learning level and enhancing their intercultural communication ability. Among them, the K-means algorithm improved by the whale optimization algorithm is also used to cluster and stratify the English proficiency of students in a class to illustrate the specific application of deep learning in English teaching. The results classified the sample students into four categories, A, B, C and D. The English level of students in category A is the highest and the largest, accounting for 35.56%, and teachers can design differentiated teaching based on the results of student stratification. After carrying out the experiment of the teaching model, the practicing students’ English scores improved by 4.01%, and at the same time, they gained 18.87%~28.45% and 18.82%~39.01% of competence in the personal domain and the communicative domain, respectively, which confirms the effect of the constructed English teaching model on the enhancement of the students’ English learning level and cross-cultural communicative competence.

Teaching curriculum design is centered around the three dimensions of affective attitudes and values, processes and methods, and knowledge and skills, which fit with the affective learning model composed of emotion, learning and cognition. This paper brings affective analysis into art curriculum design and proposes a learner affective model for teaching art courses driven by multiple teaching objectives. Through multi-objective optimization, we give an interactive decision-making method based on a hierarchical affective cognitive model to simulate learners’ affective decision-making under multi-objective-driven teaching. Analyze the teaching process of incorporating affective learning strategies in an art course, and examine the interrelationship between affective engagement and learners’ knowledge construction in three rounds of learning activities. To analyze the impact of affective learning strategies on students’ learning outcomes. The experimental group (affective learning strategy group) significantly outperformed the corresponding creativity abilities of students in the control group in the three components of surprise, originality and challenge after the teaching of the art course, and the affective learning strategy succeeded in stimulating students’ creativity. The combination of affective learning model and curriculum design can enhance the effectiveness of art education.

Based on the view that artistic style is mainly reflected in sculpture and painting, the sculpture and painting style of Giacometti is analyzed in depth. Starting from the scope of application of big data technology, the theoretical knowledge based on information theory is proposed to explore the differences in the styles of Giacometti and his contemporaries, and the basic concepts used in the processing are defined, including Shannon entropy, conditional entropy, and interactive information. Redundancy, orderliness, and complexity are set as eigenvalues that can characterize the style of art works, and the eigenvalues of the style of Giacometti and contemporaneous artists are analyzed. The minimum, maximum, and average values of the complexity of Picasso’s works are 207, 991, and 596, respectively, while the values of the three indexes of the complexity of Giacometti’s art works are 446, 990, and 718, respectively, and on the whole, the complexity of Picasso’s works is smaller than that of Giacometti’s works. This paper comprehensively reveals the stylistic differences between Giacometti and his contemporaries through the analysis of quantitative characteristic indexes.

In the context of big data, with the accelerated development of digital technology, enterprises are facing the pressure of digital transformation, and at the same time, big data computing system provides technical support for the digital transformation of enterprises. In this paper, we propose a data analysis system based on iterative computing for the digital transformation of enterprises. In order to avoid the resource consumption caused by unnecessary repeated calculations in iterative computing, this paper proposes optimization based on Spark fault-tolerant mechanism and constructs an enterprise data analysis system based on iterative computing model, which provides technical support for enterprise digital transformation. On this basis, this paper also provides optimization strategies in terms of organizational structure and cultural coordination for enterprise transformation, which provides an effective path for realizing comprehensive digital transformation of enterprises. Through the test of this paper’s iterative computing data analysis system, the speed of Spark optimization based on this paper is increased by nearly 2 times, which illustrates the usefulness of this paper’s optimization based on Sparl fault-tolerant mechanism. Meanwhile, the cache misses of the data analytics system are in the range of 46% to 60%, which provides better performance performance in terms of cache hits and time overhead. In this paper, we provide practical and feasible transformation paths for enterprise digital transformation from three aspects, including digital technology, enterprise organizational structure and culture, and promote the development of enterprise digital transformation.

Product awareness can be spread to a wider audience through advertisements, and the introduction of social media platforms has made it easier for marketers to spread brand advertisements and fully attract consumers to generate corresponding purchasing behaviors. Based on fuzzy set theory, the article establishes a fuzzy evidence theory through evidence-weighted fusion, and calculates the utility value of social media advertisements in order to achieve the optimal evaluation of social media advertisements. Then, it explores the influence of social media advertisements on consumers’ purchasing behavior with OLS-LR model, and combines the VAR model to study the dynamic correlation between different types of social media advertising channels and consumers’ purchasing behavior. Without considering the control variables, the regression coefficient of social media advertising on consumer purchasing behavior is 0.438, which is significant at 1% level. With the fourth-order VAR model, CICs social media advertisements have a significant short-term effect on consumer purchasing behavior, while FICs advertisements show a long-term effect. Based on the fuzzy evidence theory, the utility value of social media advertisements can be calculated, and based on the sorting of the calculation results, the construction of optimization paths of social media advertisements can be realized, which provides a new research basis for improving the efficiency of corporate advertising and marketing.

This paper establishes a solution model for resource scheduling optimization in university laboratories, and sets the corresponding constraints and objective functions. The genetic algorithm under the heuristic algorithm is used to solve the resource scheduling optimization problem. On this basis, the pyramid model is constructed, the population evolution and variant strategy are proposed respectively, the model genes are labeled with scheduling cost adaptation, and the genes are generated in series. The framework of scheduling algorithm is proposed, and the dynamic scheduler is constructed to realize the scheduling of university laboratory resources. Through simulation experiments and algorithm analysis, the effectiveness of the use of the model is verified. The experimental results show that when the number of simulation is 10 times, the fitness of the population is 20, 100 and 200 respectively. After the implementation of scheduling for college laboratory resources, the utilization rate of laboratory equipment is increased by 16.3%, 34.6% and 18.4% respectively.

The aim of this paper is to improve the advertisement display effect and realize accurate placement in the market. Firstly, the convolutional neural network is used to select the advertisement keywords, and optimize the click rate, conversion rate and so on when the number of iterations reaches a certain value. Next, the established hierarchical analysis model is used to conduct a comprehensive evaluation of online advertisement release forms, and select the advertisement form that best suits the needs of the enterprise and the market environment. The weight of the webpage and the similarity between the center of mass of the webpage and the advertisement are used to calculate the final score, and the advertisements are sorted to achieve the improvement of the display effect and placement accuracy of the advertisements. The final analysis found that for short-term user behavior, the weight of text link ad clusters is as high as 0.66, which can improve the accuracy of ad placement. For long-term user behavior, the multi-objective optimization algorithm can accurately identify and assign high weights when users continue to visit specific web pages, for example, the cluster of web banner ads reaches 0.64. Meanwhile, it can be adapted to different application scenarios, and the weight of text link ads cluster is significantly increased from 0.14 to 0.758 when the freshness factor is increased from 0 to 1. The optimal F1 value of the advertisement delivery effect is 97.24, which is the highest F1 value of AIGC. The AIGC ad placement strategy provides a new method for the intelligent development of the advertising industry.