With the rapid development of informatization technology, the security of network data is more and more emphasized. In this study, ECDSA digital signature algorithm and PBET consensus algorithm are adopted to construct a network data security model based on blockchain technology. The system in this paper consists of three functional modules: application interaction client, federation chain Fabric module and data storage module DHT, which are further logically divided into ϐive parts: initialization, identity registration, uploading data, querying data and permission revocation. The average CPU occupation of each component of the system ranges from 0.02% to 39.96%, which consumes low resources, and the maximum value of the time used by the system for data encryption and decryption and signature authentication is no more than 41ms, which is a relatively fast operation speed, and it can support the operation of the network data security system, and the designed system has relatively high security in resisting the attack of the authentication process, and it utilizes the decentralized characteristics of blockchain to resist the attacks of the distribution process, and it utilizes the blockchain to resist the attacks of the distribution process. Centrality to resist distributed denial of service (DDoS) attacks and replay attacks. This study provides lessons and references for the application of blockchain technology in network data security.

With the accelerating process of urbanization development, it is urgent to optimize the national land spatial planning to promote the coordinated development of urbanization. Based on the image recognition technology, this study uses the kernel density gradient algorithm to segment the image samples of the national spatial layout and the GWO-SVM classiϐication model to classify the land use types of the national spatial layout, and ϐinally combines the Markov-FLUS model to predict the future planning of the existing national spatial layout. The research analysis found that the segmentation and classiϐication accuracy of the kernel density gradient algorithm and the GWO-SVM classiϐication model for the homeland spatial layout samples both reached more than 90%. The classiϐication accuracy using the GWO-SVM classiϐication model is improved to a greater extent than that of SVM, GA-SVM, etc. The Markov-FLUS model also maintains an accuracy of more than 80% for the prediction of future territorial spatial planning. In terms of land use types, the Markov-FLUS model shows that the proportion of residential land and industrial land will decrease after 10 years compared with 5 years, while the proportion of public facilities land will increase by about 8% after 10 years compared with 5 years. The optimization of national spatial layout is of great signiϐicance to the development of urbanization in China, and the research in this paper will promote the development of national spatial layout planning in a more reasonable direction.

With the development of sharing economy, educational resource sharing has become the focus of experts and scholars to explore and practice. In this paper, from the perspective of resource sharing, a smart teaching management platform is successfully designed by combining artiϐicial intelligence technology. This research adopts YOLOv5s algorithm for face recognition and prediction in the design process, which is convenient for teaching management. Relying on the Hadoop cloud resource base, the teaching resource sharing database is designed, and the system computing logic is optimized by the distributed ϐile system HDFS. It is analyzed that the maximum number of interactions per second of the intelligent teaching management platform designed in this paper can reach 207, and the maximum interaction response time is about 68ms, and the load performance is completely better than that of the traditional teaching resource platform. At the same time, the intelligent teaching management platform can accommodate nearly 300 people to study online at the same time, which is far more than the previous mode of learning in the classroom. With the use of the intelligent platform, the development of “Internet + education” is greatly promoted.

Artiϐicial intelligence plays an increasingly important role in contemporary education, and it provides new possibilities for the innovation of physical education teaching mode. This paper constructs a college sports teaching integration model based on artiϐicial intelligence from ϐive aspects: educators, learners, teaching methods, educational resources and teaching feedback and evaluation. It focuses on designing a precise teaching model PLRSM based on personalized learning resource recommendation by combining learner portrait and learning resource portrait, and takes the recommendation of physical education teaching resources for physical education students as a case study to verify the effectiveness of the proposed algorithm. The results show that compared with the traditional baseline algorithm, the PLRSM algorithm still maintains a better recommendation performance when the data set co-occurrence matrix is extremely sparse, and its correct rate of physical education teaching resources recommendation is 0.80. In addition, compared with the traditional teaching model, the AIbased college physical education teaching fusion model can signiϐicantly improve the learners’ knowledge of physical education subject and course teaching, and its post-test score is higher than the pre-test score 11.525 to 15.436 points. The study provides theoretical support and practical guidance for the application of artiϐicial intelligence in physical education teaching, and provides a useful reference for promoting the innovation of physical education teaching mode.

The modernization and development of industrial chain supply chain in the era of digital economy is an important content to cultivate new quality productivity, maintain industrial competitiveness and realize industrial modernization. After the promotion effect of digital economy on the modernization and development of industrial chain supply chain, this paper takes China’s digital economy data from 2012 to 2022 as the research object, designs the evaluation index system of the development level of digital economy, and measures the development level of digital economy by using entropy value method and Kernel density estimation method. The overall situation of China’s digital economy development level is analyzed, and the dynamic evolution trend of digital economy development level is explored. Then, based on the threshold regression model, the benchmark regression and threshold effect analysis of the relevant inϐluencing factors of the digital economy-enabled industrial chain supply chain modernization and development are carried out. 2012-2022 China’s digital economy shows a steady upward trend, and its average annual growth rate reaches 1.8%, and the Kernel Density value decreases from 0.0474 in 2012 to 0.0425 in 2022, with the digital economy of each region level gap decreases. For every 1% increase in the level of digital economy development, the level of industry chain supply chain modernization and development is increased by 1.407%, and there are two threshold effects of economic double cycle and digital technology level for digital economy-enabled industry chain supply chain modernization and development. Enhancing the level of digital technology promotes the enhancement of the level of international and domestic economic double cycle, which in turn improves the level of modernization and development of industrial chain supply chain.

Under the background of the development of digital economy industry, more and more enterprises begin to make attempts of digital change. After constructing the financial performance index system of pharmaceutical enterprises, the study selects 30 pharmaceutical listed companies as the research samples, and evaluates their financial performance by using the principal component analysis method and the collected relevant data. On this basis, the study selects indicators of digitalization degree and puts forward research hypotheses, explores the influence of digitalization degree on the financial performance of pharmaceutical enterprises through correlation analysis, multiple regression analysis and time lag effect analysis, and then puts forward the path of digitalization development of pharmaceutical enterprises in combination with the results of the analysis. The results show that the financial performance of the sample pharmaceutical enterprises is at a medium level, with an average composite score of 0.520, among which pharmaceutical enterprises E10, E6 and E22 have the best performance, with scores above 0.9. The degree of digitization has a negative impact on the financial performance of enterprises at the 1% level, but the coefficient of digital capital investment turns from negative to positive after the lag two period, and there is a time-lag effect of digitization on the financial performance of pharmaceutical enterprises. It is recommended to promote the digitalization of pharmaceutical enterprises by encouraging the cultivation of digital talents, improving the law and cultivating thinking, and building a digital platform.

With the rapid development of technology and online social networking, the popularization of smartphones has promoted the research and development of sentiment analysis of contemporary literary texts. In this paper, the CBOW model based on Hierarchical Softmax algorithm is used to extract text sentiment features. The classification mechanism of sentiment lexicon, machine learning, and deep learning methods supported by sentiment features is discussed. According to the discussion results, a 5-layer sentiment analysis model based on CNN-BiLSTM-ATT is built based on text preprocessing, and the model design of different layering is proposed. Meanwhile, the analysis method of text themes is proposed based on LDA. In the long story dataset, the model recall rate of this paper is 83.91% and the precision rate is 83.86%, the values are higher than the other six models; the MacroF1 mean value is 83.16%, which proves that the fused and improved CNN-BiLSTM-ATT model of this paper possesses excellent performance in the sentiment analysis task. In the short story dataset, the accuracy, precision and recall are not less than 98%, and the loss rate is the lowest 34.11%, which are lower than the other six models. The model in this paper can be applied to text analysis systems and has superiority in parsing the sentiment of contemporary literature.

With the booming development of large-scale open online courses, blended teaching, which combines traditional closed teaching and online open teaching, is increasingly favored by colleges and universities. In this paper, from the perspective of blended teaching of English in colleges and universities, based on the LSTM model to predict the relevant learning data in English teaching in colleges and universities, and based on the density optimization K-mean algorithm to cluster the student subjects with different learning behaviors, and then use the Apriori algorithm to study the correlation rules of the learning effectiveness and behaviors, to provide ideas for English teaching in colleges and universities. The clustering results show that the average learning scores of the first, second and third categories of learners are 92.35, 83.57 and 64.96 respectively. The results of association rule analysis show that routinely, the more active learners are in each learning session, the greater the possibility of getting better learning outcomes. The LSTM learning prediction model Precision, Recall and F1 assessment indexes trained with 4-month behavioral data are 0.899, 0.785 and 0.833 respectively, which are all greater than the corresponding index values of SVM, MLP and RF models, and have a significant advantage in prediction effect. This study provides lessons and references for improving the effectiveness of English teaching in colleges and universities.

With the rapid development of science and technology, in the face of the needs of social development, colleges and universities undoubtedly need to shoulder the important task of talent training and education reform in innovation and entrepreneurship. In this paper, an intelligent learning model is constructed by using artificial intelligence technology. The model takes the subject knowledge graph as the core support, and combines the learning path recommendation algorithm to provide digital and intelligent support for innovation and entrepreneurship education. On this basis, the objectives of innovation and entrepreneurship education are formulated, and the framework of innovation and entrepreneurship education system is established based on the intelligent learning model in this paper, and the cycle model of innovation and entrepreneurship education based on the intelligent learning model is proposed, and the model is experimentally studied. The AUC values and F1 values of the proposed algorithm in the three datasets are higher than 0.85 and 0.80. Compared with the traditional model, the average value of recommendation bias decreased by 8.56, and the evaluation satisfaction increased by 0.126. In the teaching experiment, the overall average score of the innovation and entrepreneurship education model based on this paper was 4.364, which was 1.129 higher than before. Compared with the traditional innovation and entrepreneurship education, it is increased by 0.693, indicating that the innovation and entrepreneurship education model in this paper can promote the all-round development of students’ ability level and play a positive guiding role in the development and reform of innovation and entrepreneurship education.

In the field of artificial intelligence education, teaching emotion, as the main assessment basis for teaching evaluation, profoundly affects the teaching method, classroom atmosphere and teaching effect of teachers. This thesis proposes a combined network structure, CRNN, by taking advantage of CNN for speech emotion feature extraction and RNN for sequence modeling, and realizes emotion recognition of classroom discourse through DenseNet neural network to realize the crosstalk between each layer and other layers, and LSTM neural network to complete the task of speech emotion classification. On this basis, the open classroom video of the sixth grade of an elementary school is analyzed for sentiment, and the teaching practice of the application of speech emotion recognition model is carried out to study the optimization effect of the model application on the classroom atmosphere of the elementary school. The overall sentiment value of the classroom interaction video floats in the range of 0~1.9, showing a trend of first increasing and then decreasing, reflecting the feasibility of applying the speech emotion recognition model of this paper to classroom sentiment analysis. Through the teaching experiment, the positive emotional performance of the experimental group is more obvious than that of the control group, and 95.46% of the students agree that the application of the model can improve classroom interaction and the overall atmosphere. The speech emotion recognition model studied here can mobilize the classroom atmosphere, and has more important classroom guidance and application significance.