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.

In order to study the role of digital economy on the transformation of regional economic structure, firstly, the mechanism of the role of datatized economy on the change of regional economic form is elaborated, and on the basis of the analysis of theoretical model, the structure of the distribution of capital factors in each industry and the ideal factor are determined. Determine the index system and weights of regional economic structure transformation through the selection of weight indicators, and complete the measurement of the data-based economic situation under the construction of the index system of data-based economic situation. Two hypotheses are proposed that digital industrialization can have an ideal effect on the structural transformation of local development but the shape of the effect is inverted U-shape, and that industrial digitalization can have an ideal effect on the structural transformation of local development. The empirical analysis finds that the Moran’s I index of structural transformation of local development from 2008 to 2020 is prominent in the 1% case, and the FP and UE within, central, eastern, western regions of China and the level of structural transformation of local economy is prominent in the 1% case. It is concluded that there is a prominent spatial isotropic relationship between the datadriven economy on regional economic structural change resilience in the whole region, and the constructed research model has a good robustness.

With the development of Internet of Things (IoT) technology, improving the interactivity of IoT communication teaching has become an important research content. This paper firstly constructs the IOT communication teaching system on the basis of service layer, network layer and teaching layer, through which the teaching information is ensured to be delivered timely and accurately. Secondly, the group intelligence algorithm teaching interactivity is optimized and designed to optimize the teaching environment, network, and teaching layer to get the optimized server resource allocation scheme to achieve the optimization of different levels in the teaching of Internet of Things communication. When the number of iterations reaches 20 and 45, the adaptability of this paper’s algorithm is maintained between 100-10-1, and the optimization of the algorithm improves the student participation, the depth of understanding of knowledge, the accuracy of data, the speed of transmission, the efficiency of management, and the teaching effect by 28.6%, 41.7%, 4%, 100%, 18.8%, and 20%, respectively. In the delay analysis, when the number of terminals is 10, 20, and 30 respectively, the delay of the teaching system in this paper is the lowest among all the compared systems, which is 10ms, 40ms, and 230ms respectively.This study can lay the foundation for improving the quality and effect of IoT communication teaching and promote the cultivation of teaching interactivity between teachers and students.

In order to satisfy consumers’ needs, enterprises must conduct in-depth research on consumers’ purchasing behaviours and design and develop marketing strategies based on the characteristics of consumers’ needs. The article takes 4P marketing theory and SOR model as the guide, and establishes a consumer purchase intention model in combination with the consumer behaviour model. The questionnaire is designed from the product value, price range, channel optimisation, and promotional efforts of the enterprise marketing strategy, and the validity of the questionnaire is tested by principal component analysis. Then meta-analysis method was used to explore the correlation of each variable, and the SEM model was combined to explore the influence path of corporate marketing strategy on consumer purchase intention. The Q-value of the hypothesised relationship of consumer purchase intention ranges from 446.137 to 814.535 and is significant at 1% level, and the correlation coefficients of each variable in the model with consumer purchase intention are more than 0.35. The indicators of model fit, CMIN/DF and RMSEA, are 1.076 and 0.015 respectively, and the path coefficient of the value of the product in the marketing strategy on the purchase intention is the largest at 0.076. The path coefficient of product value on consumers’ purchase intention in marketing strategy is 0.369, and the development of enterprise marketing strategy needs to actively expand marketing channels and design differentiated product and service programmes, so as to enhance consumers’ recognition of the enterprise brand to stimulate their purchase intention.

With the proposal of sustainable development of energy, countries begin to develop from fuel vehicles to new energy vehicle market. Firstly, we construct a consumer purchase behavior recognition model based on XG Boost algorithm, simulate the gradient enhancement process of purchase behavior recognition, obtain the approximation value based on function calculation to become the learning target of the overflow value, and at the same time, give higher learning weight to the samples with unsatisfactory accuracy in the last round, and after continuous iteration, gradually correct the purchase behavior recognition bias. According to the number of purchase behavior features identified correctly, the number of features that do not have purchase behavior features, and the number of features that are not identified, invalid users are eliminated to improve the accuracy of the algorithm. The Cronbach’s alpha coefficients of the four factors are found to be 0.891, 0.895, 0.813, and 0.800, all of which are greater than or equal to 0.800, indicating that the factors are internally consistent. And the relationship values between the factors and purchase intention are 0.439, 0.406, 0.430, 0.387, which are all greater than 0. Therefore, there is a prominent relationship between all four dimensions of consumer purchase behavior factors and consumption impulse, and the identification of purchase behavior patterns has a guiding role in electric energy vehicle marketing strategy.

In order to be able to accurately identify user behavior and emotional tendency, this paper firstly adopts the neural network structure to build the emotion analysis model, and divides the model into four parts to analyze the text and emotion in social media, and obtains the information of semantics and emotion-related content in social media text. Secondly, from the semantic and emotional symbol content of the text in social media, the public emotional tendency model is built, and the sharing content and behavior of a large number of users in social media are analyzed. Finally, the association rule mining algorithm is used to extract the text and emotional symbols in social media, to improve the accuracy of the user’s emotional tendency analysis model, and to be able to accurately derive the user’s behavioral habits. In order to verify the analytical effect of the model, the model was tested, and the training speed of the BLSTM model was fast, and the training time was 1.5 hours in the first iteration of the test with a data set of 1 million. The model is more accurate in analyzing the user’s positive emotions, with accuracy and precision around 85% and 90% respectively, and the results obtained are more accurate, meet the user’s needs, and enhance the user’s experience.