Search

To build a comprehensive learning resource system covering learning process, learning users, learning resources and other aspects, an intelligent learning system for innovation and entrepreneurship in universities was constructed and designed combined with knowledge visualisation theory. The system includes student information record module, system recommendation calculation module, learning material module, and knowledge visualisation module. The research focuses on the system recommendation calculation module, including the User-based Collaborative Filtering Algorithm (UCF) and the Joint Recommendation (JR) algorithm of the application content recommendation algorithm. The best neighbour number of JR is 20, and the best transmission path length is 2. The recommendation effect is optimal under this setting. The convergence iterations of the training and test set of the joint recommendation algorithm are 80 times and 100 times, respectively. For the training set and test set, the accuracy, precision, sensitivity, recall, running time, error, and other performance evaluation indicators of the joint recommendation algorithm are better than the corresponding values of other recommendation algorithms. The system has a good design effect and experience effect in the application of the online learning platform. [ABSTRACT FROM AUTHOR]

Abstract Given the challenges of inter-domain information fusion and data sparsity in collaborative filtering algorithms, this paper proposes a cross-domain information fusion matrix decomposition algorithm to enhance the accuracy of personalized recommendations in artificial intelligence recommendation systems. The study begins by collecting Douban movie rating data and social network information. To ensure data integrity, Levenshtein distance detection is employed to remove duplicate scores, while natural language processing technology is utilized to extract keywords and topic information from social texts. Additionally, graph convolutional networks are utilized to convert user relationships into feature vectors, and a unique thermal coding method is used to convert discrete user and movie information into binary matrices. To prevent overfitting, the Ridge regularization method is introduced to gradually optimize potential feature vectors. Weighted average and feature connection techniques are then applied to integrate features from different fields. Moreover, the paper combines the item-based collaborative filtering algorithm with merged user characteristics to generate personalized recommendation lists.In the experimental stage, the paper conducts cross-domain information fusion optimization on four mainstream mathematical matrix decomposition algorithms: alternating least squares method, non-negative matrix decomposition, singular value decomposition, and latent factor model (LFM). It compares these algorithms with the non-fused approach. The results indicate a significant improvement in score accuracy, with mean absolute error and root mean squared error reduced by 12.8% and 13.2% respectively across the four algorithms. Additionally, when k = 10, the average F1 score reaches 0.97, and the ranking accuracy coverage of the LFM algorithm increases by 54.2%. Overall, the mathematical matrix decomposition algorithm combined with cross-domain information fusion demonstrates clear advantages in accuracy, prediction performance, recommendation diversity, and ranking quality, and improves the accuracy and diversity of the recommendation system. By effectively addressing collaborative filtering challenges through the integration of diverse techniques, it significantly surpasses traditional models in recommendation accuracy and variety.

To address the challenge of users selecting rich tourism resources, this study proposes a model for cultural tourism attraction recommendation using an optimized weighted association rule algorithm. This model includes time and season weight for tourist attraction recommendations. This model proposes improvement methods to address some inherent issues in traditional tourism recommendation models. Firstly, it constructed a recommendation model for cultural tourism attractions, and then optimized the weighted association rule algorithm by incorporating dynamic time weights. It takes into account the user's intended time in the recommendation outcome. Moreover, it incorporated seasonal weights to optimize the weighted rule algorithm for factors such as user travel time and the attractions' peak season during the recommendation process. The experiment indicates that the F1 value of the improved algorithm model proposed in this study reaches 0.952, the accuracy reaches 0.985, the area under the curve reaches 0.955, the Recall value reaches 0.812, and the fitting degree reaches 0.971. The results suggest that the proposed cultural tourism attraction recommendation model, based on an optimized weighted association algorithm, performs well in recommending tourist destinations. This model can have a positive impact on the development of the tourism industry.

This study proposes an English online education platform centered on the English teaching resource management module and the teaching resources personalized recommendation module on how to closely integrate computer-aided technology into English teaching. In the English teaching resource management module, the fuzzy comprehensive evaluation method is utilized to evaluate teaching resources. An improved placement algorithm, ERRPA, based on the rating of educational resources, is proposed to improve the insufficiency of HDFS files and achieve allocation node modeling. In the English teaching resources personalized recommendation module, then a collaborative filtering algorithm for user clusters is proposed to filter some noisy users using the UCC algorithm, and mix the predicted ratings with the actual ratings through the rating mapping to obtain good recommendation prediction results. In the teaching application of the English online teaching platform, the passing rate of the subject students was improved by 13.79%, the average learning tasks were completed by 59.1% in the online learning behaviors, and the average learning video viewing time reached 89.2 minutes. Learning interest, learning attitude, and sense of independent learning in learning status were improved by 3.2, 4.38, and 4.28, respectively, compared with the pre-experiment, showing highly significant differences (P

The student community in colleges and universities is based on students’ common living areas, and the community service model in colleges and universities should be student-oriented and centered on students’ development. This paper proposes a one-stop community service model from a student-oriented perspective, with the service community model and service recommendation model being the main component modules. In the service community model, a context-based association relationship mining algorithm is proposed to add time and location contexts to the collaborative filtering algorithm in order to obtain a collection of similar users and services. After constructing the one-stop service community, a service recommendation algorithm based on a trusted coalition is proposed to introduce student credibility and service usage frequency to achieve personalized recommendations of services. University H’s student community implemented the one-stop community service model. After the practice, the mean value of each dimension of the community’s service mode and content evaluation was greater than 3, and the overall satisfaction evaluation value of the community was 39.49, which was extremely significant compared with the evaluation value of University C (P

Based on artificial intelligence technology, this paper builds an innovation and entrepreneurship education platform for college students with the goal of improving their innovation and entrepreneurship spirit and ability. For faculty information, competition information, and other aspects related to the collection and analysis of student portraits. The use of a collaborative filtering algorithm allows students to receive personalized test questions while also modeling innovation and entrepreneurship competitions and creating a set of team-matching methods that utilize student portraits. Using hierarchical analysis to construct the evaluation system model of graduate innovation and entrepreneurship education, it can be analyzed that in the student portrait, when the students basically have no attendance, the assessment grade is also 0. Students who have participated in the innovation and entrepreneurship education platform have received salaries of more than 11K in 4 cities, while social workers have only received salaries of more than 11K in 1 city. Basically, more than 70% of those who agree with the learning mode of innovation and entrepreneurship platform and who are very interested in it are more than 70%. Resource allocation (0.3537) has the greatest influence on the cultivation of innovative and entrepreneurial talents, and the importance of constructing innovative and entrepreneurial resource allocation should be highly emphasized.

This paper proposes a collaborative filtering-based learning resource recommendation algorithm to help learners find interesting resources in a huge amount of teaching resources and improve learning efficiency and learning interest so that the classical dance teaching content can be further enriched and expanded. By improving the K-means clustering algorithm, the article realizes the clustering of students’ classical dance teaching content preferences and further proposes a collaborative filtering algorithm based on ratings and attribute preferences of classical dance teaching resources, which takes into account the relationship between users’ needs and the attributes of the resources in order to complete the personalized recommendation of classical dance teaching resources for students. The article finally takes a dance teaching classroom as an example for empirical research. In the two groups of classical dance performance scoring a single total average score, the experimental group’s performance of dance movements is better than that of the control group, the average score of the experimental group’s pre-test is higher than the average score of the control group’s pre-test by 8±1.8 points, and the average score of the experimental group’s post-test is higher than the average score of the control group’s post-test by 9±2 points.

Introducing polyphonic folk songs into the choral teaching classroom in colleges and universities not only helps to carry forward the excellent traditional culture but also promotes the students’ emotional education and physical and mental health development. This paper analyzes the status quo and dilemma of the use of polyphonic folk songs in college choral teaching and puts forward the model of music choral intelligent tutoring system (ITS) and the method of spectral tone recognition as countermeasures. A collaborative filtering algorithm is used to construct the learning resource recommendation algorithm in the music chorus intelligent guided learning system model, which is based on the ITS system structure. The YIN algorithm is used to extract the audio, and the pitch template matching is accomplished with the help of the improved DTW algorithm to complete the choral ability assessment. An improved normal harmonic algorithm has been proposed to preprocess the audio signal and achieve spectral tone recognition for multi-part folk songs in the fundamental frequency extraction stage of spectral tone recognition. In a comprehensive university in Sichuan Province, China, the teaching practice of polyphonic folk song chorus was carried out. The students’ scores in the dimensions of learning interest and learning confidence increased by 0.976 and 0.698 on average after the experiment. The p-values were all less than 0.05, showing significant differences.

The rapid popularization and expansion of the Internet have catalyzed the growth of diverse e-commerce platforms. To mitigate information overload and enhance consumer shopping experiences, recommender systems have been developed. Our proposed algorithm, grounded in the Hadoop architecture, employs a refined cosine similarity method to calculate the average distance between users and rated items. This method involves the application of the Singular Value Decomposition (SVD) model to reduce the dimensionality of the user-item rating matrix, facilitating the extraction of item feature vectors. Subsequently, these vectors are clustered and segmented using the Matrix Factorization (MF) algorithm, addressing the challenge of data sparsity effectively. Experimental evaluations demonstrate that our enhanced algorithm outperforms five conventional collaborative filtering recommendation algorithms across varying matrix densities (from 0.05 to 0.25) on a public dataset. This results in a significant reduction in prediction error, thereby offering users more precise item recommendations.

This study develops a financial performance evaluation system for S Group, employing a collaborative filtering algorithm to address the limitations inherent in traditional financial performance evaluation methodologies. Improvements have been made to the similarity measure method, data imputation technique, and rating prediction approach within the model. Subsequently, the financial status of S Group is scrutinized, with a thorough exploration of the input and output indicators, leading to the calculation of the efficiency values within the financial indicator system. Through sensitivity analysis, this research investigates the impact of input and output indicators on the outcomes derived from collaborative filtering. Based on the study, recommendations are formulated in alignment with the evaluation outcomes. The findings reveal that the average comprehensive efficiency of S Group over the past decade is 0.772, with a median comprehensive efficiency of 0.788, indicative of a robust financial condition. This research provides a valuable reference for the formulation of financial performance evaluation systems and the analysis of financial performance across various industries.

The fusion of industry and education plays a pivotal role in optimizing talent training structures, facilitating the conversion of scientific and technological achievements, and driving the upgrade and high-quality growth of the economy. This study applies a clustering algorithm, a form of data mining, to categorize students based on personality traits, learning capabilities, and career preferences. This categorization aids vocational institutions in selecting suitable corporate partners for training programs. Furthermore, we introduce a collaborative filtering algorithm to establish a bipartite graph that matches the attributes of students and companies. This approach enhances the practical skills of students and supports the strategic integration of industry and education in talent development. After the experimental research, it was found that after the implementation of the senior industry-teaching integration talent cultivation measurement rate, the average score of the higher vocational education improvement status is 4.20, the average score of the industry’s satisfaction with the higher vocational is 3.35, and the average score of the higher vocational talent cultivation characteristics is 4.41, which indicates that the industry-teaching integration education model constructed in this paper can effectively promote the formation of the characteristics of the higher vocational schooling and talent cultivation. By integrating industry teaching, this paper’s parenting model can help change the vocational faculty structure and improve student employment rates.

With the deep integration of the Internet and education, the personalized development of education has become a new trend in education, and it also increasingly emphasizes the learner’s subject position in learning. In this study, a smart teaching model for learners’ individuality is developed by integrating WEB data mining technology, SOM neural network, and multiple recommendation mechanisms. The model achieves personalized recommendations for learning resources through the collection of user characteristics and then according to the recommendation algorithm. Then, using college English courses at Zhengzhou Shengda University as an example, the SOM neural network is utilized to diagnose the teaching cognition of the experiment. The experimental results show that the SOM neural network cognitive diagnosis results in a high judgment rate, with a high judgment rate of 84.842%. It has certain feasibility in teaching small sample diagnostics. In terms of efficiency, the time of cognitive diagnosis can be controlled within 1 second, which is real-time in teaching applications. The significance test of students’ performance after the experiment shows that the personalized wisdom teaching model constructed in this paper has a significant effect on improving teaching performance.

With the popularization of higher education, the competition in the employment market of college students is becoming increasingly intense. To enhance the employment efficiency and satisfaction of college students. The study first analyzes college students’ employment unit selection, attribute preference, and location preference through an employment recommendation algorithm. The collaborative filtering algorithm is utilized to complete personalized modeling and output the final recommendation results based on the acquired employment preferences and relevant data collection. Finally, the gradient descent method is used to evaluate the accuracy of college students’ employment recommendations. The results show that the overall educational requirements of enterprises for the three significant positions of short video production, account operation and anchor are not high, and the percentage of those with education of high school or below or master’s degree or above is meager, neither exceeding 3.5%. The personalized employment recommendation algorithm can provide scientific and reasonable guidance for graduates’ employment, with an accuracy rate of up to 50% and a recommendation list length of N=30. When α=0.75, the personalized employment recommendation algorithm can obtain better recommendation performance with smaller recommendation list length. This paper provides new solutions for college students’ employment and valuable references and lessons for research in related fields.

The article first discusses the categorization and difficulty of learning resources and proposes a method to quantify the difficulty of teaching resources. Then, the article recommends appropriate learning resources through similarity matching and student knowledge level diagnosis. This includes analyzing students’ test answers and modeling students’ knowledge level based on this. Data analysis and model building were employed to propose four key indicators: knowledge point density, knowledge point depth, evaluation index and correctness rate. In addition, cosine distance was employed to measure the similarity between resources and Hidden Markov Models were used to predict students’ knowledge point mastery. Four key indicators were effectively applied to construct a vector of resource difficulty indicators in quantifying learning resource difficulty. A vector representation of students’ knowledge mastery was successfully built in diagnosing students’ knowledge level. In addition, the article discusses the construction of a personalized learner preference model and a personalized English teaching model based on collaborative filtering algorithms. The effect of college English teaching can be effectively improved through the detailed Analysis of learning resources and the application of personalized recommendation model.

Tea culture is an excellent traditional culture in China, and its integration into higher vocational aesthetic education can promote the overall development of students. This paper takes the higher vocational colleges and universities in H city as an example, constructs the correlation index of the integration and development of tea culture and aesthetic education, and explores the key factors of the integration and development of tea culture and aesthetic education by combining the gray correlation method. At the same time, the students’ portraits are constructed, the constructed user portraits are clustered using the K-mean algorithm, combined with the improved collaborative filtering algorithm, and the resources related to tea culture and aesthetic education in higher vocational colleges and universities are accurately recommended. The improved model is also applied to the city to analyze the resource recommendation effect of tea culture and aesthetic education and explore the development path of integration of tea culture and aesthetic education in higher vocational colleges. The results show that the gray correlation between the integration of tea culture and aesthetic education in higher vocational colleges and universities, and the educational foundation, educational level, student ability, and educational needs are within (0.642, 0.808). The similarity between the users recommending aesthetic education resources is above 0.7, the similarity between the users recommending tea culture and aesthetic education resources and the users recommending tea culture resources is above 0.8, and the content recommended by each user achieves the desired effect (100%). The effective promotion of tea culture and aesthetic education in higher vocational colleges and universities is achieved through the accurate recommendation of relevant resources for students’ needs.

Precision marketing is an intrinsic motivation for enterprises as a strategic consideration and guiding principle. In this paper, we first constructed a cross-border e-commerce precision marketing and management strategy based on big data technology. We mined user data and analyzed user behavior and characteristics. Moreover, the initial group division of users is carried out to realize the construction of user segmentation and user portrait, followed by the prediction of user purchasing behavior based on the Stacking algorithm and the use of a collaborative filtering algorithm to carry out accurate recommendations for different user groups. The effectiveness of the marketing management strategy is evaluated based on the level of customer value perception of Enterprise H. By using regression modeling, the impact of the marketing management method on customer loyalty and user purchase intention is investigated. The results show that the perceived level of each dimension of precision marketing is between (4,5.6), and the perceived risk is 3.657. The degree of explanation of the precision marketing model on the customer’s willingness to buy is 78.8%, and the t-value significance is 0.005, which reaches a significant level, indicating that the marketing management model is effective. The purpose of this study is to provide practical marketing management suggestions for enterprises that can obtain and maintain competitive advantages in fierce market competition, which will promote enterprise performance improvement and stable growth.

Innovative English teaching resources will inevitably result from the use of media technology in the classroom. This article will examine the new approach to teaching English in college from the standpoint of teaching resources. In order to establish a new mode of English teaching in higher education institutions based on personalized recommendation of teaching resources, this paper proposes two recommendation algorithms: one is content-based, and the other is collaborative filtering. The algorithm is enhanced by combining it with the design of multimedia English teaching resources. The influence of hit rate and MAE values prior to and following the cooperative filtering recommendation method is examined. The distinction between the pre-and post-test results of the experimental and control courses is analyzed and compared to conclude the examination of the impact of the novel model of teaching college English. The analysis indicates that the improved recommendation algorithm has a 4.85% higher hit rate than the traditional collaborative filtering algorithm. The improved recommendation algorithm is more accurate than the traditional recommendation algorithm, as suggested by this.

In order to improve the ideological and political education of college students, this paper constructs a cloud technology education platform based on big data analysis and collection technology. Firstly, the collaborative filtering algorithm is used to filter and collect student information; secondly, the Pearson correlation formula is used for pre-processing, MAE (mean absolute error value) is used as an evaluation index; and finally, the data is combined with FCM (fuzzy C-mean) algorithm to filter and analyze as needed. Its application performance is examined to verify the rationality and practicality of the construction of the cloud technology education platform. The analysis results show that, compared with the three-tier neural network education platform and MOOC (Massive Open Online Course) education platform, the educational resource transmission time of the cloud technology education platform constructed in this paper is reduced by 1/3, and the load balancing deviation is reduced by 1/4. Among four different servers, the average error value of the platform constructed in this paper is as low as 0.35% and can reach as high as 0.65%. The detection rate reaches 97.64%, the false alarm rate is only 2.93%, and the leakage rate is only 1.13%. It can be seen that the cloud technology education platform constructed in this paper can improve the utilization rate of educational resources and realize the sharing of educational resources.

In the context of big data development, one of the reasons for the ineffectiveness of Chinese cultural translation research is the lack of attention to the “system construction”, this paper focuses on the construction of the cultural translation research system under the big data technology, based on the MOOC recommendation system using the recommendation engine group for the hybrid recommendation, the recommendation engine group integrated the use of the mainstream collaborative filtering algorithm based on foreign translation literature in the recommendation algorithm. Through the experimental analysis, the model performance reaches the maximum when the number of cultural literature is 7, and the F_1 of the traditional method is improved by about 2.6%. Compared with the original recommendation algorithm, the improved recommendation algorithm of the MOOC implicit scoring model can get more accurate recommendation results to promote the construction of a Chinese cultural foreign translation discourse system. It is expected to promote the construction of Chinese cultural foreign translation discourse system, show the vitality, staying power, and influence of China’s excellent culture to the world, enhance the international discourse power and cultural soft power of Chinese culture in the new era, and contribute Chinese wisdom to global cultural exchange and governance.

Under the wave of big data technology development, the traditional experimental teaching methods in colleges and universities are difficult to meet the requirements of the educational objectives of the times, and teaching innovation is the focus of teaching research in many colleges and universities, which has attracted the attention of the majority of educational researchers. This paper focuses on the innovation of the construction of experimental teaching platforms of economic management in colleges and universities based on the background of big data. This paper explains the necessity of innovation of economic management experimental teaching platform, proposes the basic framework of innovation of economic management experimental teaching platform (Kube storage cloud data, front-end design, collaborative filtering algorithm), and researches and discusses the innovation mode and operation mechanism of economic management experimental teaching platform based on experimental teaching construction, based on the similarity between the specified time point and other time points The impact of the time factor on the recommendation results of experimental resources is analyzed. The results of experimental teaching resources recommendation reflect the resource recommendation ability of this platform and compare with H5 technology experimental teaching platform and content analysis method experimental platform to analyze the changing trend of MAE of teaching resources recommendation; analyze the number of concurrent connections and clicks of this platform to verify the performance of this platform. The research results show that this paper platform’s experimental teaching resources recommendation effect with MAE value of 0.51 is better than other platforms. The reason is that this paper platform’s experimental teaching resources recommendation fully takes into account the time factor and co-rated experimental teaching resources, so the accuracy of experimental teaching resources recommendation is significantly improved. This study can improve the quality and teaching efficiency of universities and train more excellent economic management talents for the country, which is of great historical significance to the development of China’s economy and education.

The purpose of exploring the development mode of online teaching resources in colleges and universities is to enhance the utilization rate of online teaching resources to promote the diversification of teaching methods. In this paper, based on big data technology, a cloud education platform integrating online teaching resources in colleges and universities is constructed under the perspective of integrating industry and education, and the architecture and functions of the cloud education platform are explained. Then the collaborative filtering algorithm is used to filter and collect the information on online teaching resources, and the Pearson correlation formula is used to pre-process the data and help users to recommend teaching resources. Finally, the pre-processed data are filtered and analyzed using the multilayer perceptron technology under the deep learning model. To verify the practicality of the cloud education platform proposed in this paper, the platform’s performance is evaluated by combining MAE metrics with RMSE metrics. In terms of load capacity, the platform has the best load capacity when the number of users is 200. From the performance test, the average transmission rate of the cloud education platform is 8.1% and 0.93% higher than that of NetEase Cloud Classroom and Tencent Classroom, and the average transmission time is 7.09 s. From the practicality analysis, the average value of the MAE index is 0.317%, and the average value of the RMSE index is 0.232%. This shows that the cloud education platform can effectively integrate university online teaching resources and help universities achieve diversified development of teaching methods.

E-learning is a very popular learning method at this stage, and Internet learners need to invest much time to retrieve the required e-learning network resources. In building the existing e-learning resources, the cognitive level, thinking ability, learning style, and other factors of learners are not considered. For this challenge, the paper gives the recommendation methods of the collaborative filtering algorithm model and learner model, compares the advantages and disadvantages of these models and traditional recommendation methods using the data of mean square error, response time, and accuracy, and examines the students’ suggestions for this recommendation method in the field. The collaborative filtering recommendation technique had the highest completion rate, above 0.7 for 5-20 recommendations and above 0.75 and 0.8 for 20-35. The rate of the learner model is stable between 0.7 and 0.8.

With the advent of the information era of smart libraries, cloud computing technology provides a new service model and an effective guarantee system for smart libraries. In this paper, we propose a personalized recommendation method and construct a personalized service recommendation model based on collaborative content filtering for the traditional information service model and low service efficiency of university libraries. To improve the accuracy, improvements are made to the VIRE positioning algorithm on the re-districting of virtual labels, the application of the non-linear interpolation method, and the value of K-neighborhood. Optimization strategies are proposed based on the change in the Chinese smart library system, and three aspects are studied: deep change in the legal system, deep change in institutional relationships, and deep change in institutional implementation. Simulation experiments on collaborative filtering recommendation algorithm based on users and items using the Hadoop cloud computing platform show that the accuracy rate remains between 75% and 88% and increases with the smaller MAE value, the more accurate the user recommends books. This study improves the efficiency of library staff and thus is important for the change and development of smart library systems in China.

Empowering precision innovation through big data to improve the effectiveness of ideological and political education in colleges and universities can effectively promote cultivating the new generation of the times. Based on learners’ learning behaviors and quantified learning behavior indicators, this paper proposes a three-branch division model based on a cognitive level to reduce the “Matthew effect” of collaborative filtering algorithms in path recommendation and improve the cognitive level of online learners. Based on the three-branch decision theory, we select the decision with the highest expected utility as the final decision and recommend the learning content suitable for the learners’ development. The analysis of the functional requirements of the personalized learning recommendation system based on knowledge mapping, the overall structure diagram of the system, and the construction process of each component module are proposed. By analyzing the influence of ideological and political education on college students, about 80% of college students generally think that ideological and political education has improved political character, strengthened ideals and beliefs, enhanced national sentiment, standardized speech and behavior, improved comprehensive literacy, and enriched after-school knowledge. More than 80% of students, teachers, and leaders are satisfied with the personalized recommendation model proposed in this paper, and less than 10% are dissatisfied. Therefore, big data technology can help improve students’ Civics learning effect and has strong applicability.

Addressing the issues of a single form, insufficient targeting, a lack of synergy, and the inability to create a customized collaborative education process in the current college Civic Education curriculum setting, This paper develops a recommendation system for a college Civic Education curriculum based on enhanced collaborative filtering technology. It adopts an enhanced algorithm of cooperative filtering based on the combination, and by having to introduce a gradual forgetting curve relying on the time-sensitive change of user interest, it more effectively resolves. The standard algorithm is outdated, inefficient, and not very adaptable. A similar classification method for college Civics courses is then constructed after data mining is performed to filter out the data noise present in the data set. Via empirical validation, it is discovered that the optimization method obtains an average accuracy of 78.83% when the amount of cycles is 40. When the number of cycles is 40, the recall rate of the optimized algorithm is the highest, and the recall rate is 78%. In terms of recommendation popularity comparison, the optimization algorithm popularity starts to be higher than the traditional algorithm when the number of cycles exceeds 80. Therefore, the system has excellent practicality and resilience, and it operates steadily, which is of positive significance for creating an atmosphere of collaborative and win-win university thinking and political education for teachers and students with various forms and individual innovation.

In this paper, firstly, a collaborative filtering algorithm based on users is used to mine the past behaviors of the target users. Items are glanced and composed to gain insight into the user’s preferred items and to mine preference information, followed by searching for users with similar preferences to the user in the system and calculating the similarity between users and users using cosine similarity and pearson similarity, and predicting the target user’s rating of an element based on the rating value of an item given by a nearby user. Then the personalized teaching system is designed by the actual situation of the online teacher teaching courses on the platform and the course demands of the platform students, and the path of high-quality improvement of teacher training and teaching is studied, mainly focusing on three aspects: clear value orientation, good personalized system teaching planning, and implementation of multiple evaluations. When analyzing the student-teacher ratio of teacher education institutions, the student-teacher ratio of Central China Normal University has the largest value, 24.79%, while the values of East China Normal University and Nanjing Normal University are relatively small, 15.97% and 15.39%, respectively. Either based on theory or based on practice, any institution of higher education with an excessive student-teacher ratio. This study helps teachers grow professionally and provides a good foundation for eventual individualized student development.

The teaching reform of law courses is to further enhance the development speed of the law education business. In this paper, a practical teaching platform for law courses is constructed based on Internet technology, and context-aware class case matching is performed by using word embedding of the BERT network and contextual information extraction of the Bi-LSTM model. Then the local semantic feature extraction by CNN network and collaborative filtering algorithm based on user preferences are used to achieve intelligent recommendation analysis of law course cases, and experimental simulation analysis is conducted for the teaching platform and recommendation algorithm. In terms of platform performance, the average response time is 24.5ms, which is 12.67% and 26.99% less than that of the Mucuo platform and Tencent Classroom, respectively. From the recommendation algorithm, the accuracy of recommendation based on students’ preferences is 68%. This shows that the practical teaching platform of law courses can be the implementation path of law teaching reform in the Internet era.

This paper uses a user-based collaborative filtering algorithm to predict the ratings of items by target users and to recommend items that target users have not interacted with. The red music and cultural resources were ranked according to their values, and the Bartholomew coefficient was introduced to calculate the similarity of items from the perspective of a probability distribution, and the content recommendation algorithm was used to construct a model of ecological civilization education concept. It is found that more than 50% of undergraduate college students pay regular attention to ecological environment information, and 30.56% of them will actively learn ecological civilization knowledge, which is not thorough and comprehensive enough for ecological civilization concept establishment and cultivation. It is suggested that universities should integrate red music culture into ecological civilization education to create an ecological civilization cultivation atmosphere.

In this paper, intelligent information retrieval of relevant literary content through collaborative filtering algorithms in Internet technology is used to analyze the similarity between users and, thus, to select similar items in a weighted ranking. The Jacobian formula is used to calculate the common feature values and thus predict the user’s unrated item ratings. Word normalization is performed through information extraction of text keywords to effectively abstract the dimensionality of text features. The results showed that the influence of learning based on language literacy was 0.697, the preference for the literary genre of prose was as high as 49.4%, and students could accept infiltration teaching. It indicates that making full use of Internet technology means can break the time and space limitations in the traditional teaching of literature, provide effective support for students’ interactive communication, expand students’ cultural horizons, and improve their humanistic literacy.

This paper proposes to introduce OBE theory in the curriculum map so as to build a curriculum master map based on the concept of engineering education accreditation-oriented and professional training objectives. In order to provide personalized services to students in the curriculum map, this paper applies the user-based collaborative filtering recommendation algorithm to the curriculum map and uses a similarity calculation based on Barclay’s coefficient improved similarity (BCCF) to finally implement the curriculum recommendation algorithm. The results show that the AUC of the recommendation algorithm constructed in this paper reaches 0.867. After the teaching reform, the mean values of students in the course reform class are 0.68, 0.61, and 1.31 higher than those in the non-course reform class at the level, of course, affect perception, teacher teaching, and student learning. Therefore, the OBE-based teaching method in this paper can develop personalized learning paths for students, which helps students learn better and plan the overall learning paths and make the most of educational resources.

This paper constructs a collection of effective teaching methods based on the improved K-Means clustering algorithm for clustering and dividing effective components of music teaching in colleges and universities. By analyzing the personalized content recommendation system, we can construct a recommendation system based on teaching content using information retrieval and filtering techniques. The collaborative filtering recommendation algorithm is used to ensure the accurate placement of teaching content. The Kruskal algorithm is used to find the minimum spanning tree of teaching effective components, and the K-means clustering principle is applied to the division of music teaching effective components, and the cluster of effective teaching components is divided by the clustering algorithm. According to the findings, mind-body integration and the teaching goal of valuing creativity were classified as effective teaching components in music. Personal aesthetics had a 0.6 influence on musical creativity, and a free environment had a 0.3 influence.

Drama education activities carried out by traditional culture comply with, guide and stimulate children’s dramatic nature so that each child can find a suitable place for himself in drama education activities and promote the growth of children with individuality. This paper builds a flipped classroom teaching model for kindergarten drama education activities based on the microblogging public platform. Teachers in the flipped classroom of drama education activities need to collect traditional cultural drama resources before class, and the basic framework of a personalized drama resource recommendation system is proposed on the WeChat public platform. The optimization of drama resource recommendation results is carried out using the preference score of drama resources using the collaborative filtering recommendation algorithm of multi-featured users. The performance test is conducted for the personalized drama resource recommendation system constructed in this paper to provide drama resources for the development of kindergarten drama education activities in the flipped classroom. The results show that when the preference recommendation of multi-featured users’ drama resources has a certain number of users, its accuracy is about 4.5% higher than that of the traditional method, the F-score value is about 0.05 higher than that of the traditional recommendation method, and the real-time updating delay of the personalized recommendation system fluctuates between 1.18s~1.65s. The personalized recommendation system can help teachers to obtain the update and download of traditional culture drama resources in time, make a good guarantee of drama teaching resources for kindergartens to carry out drama education activities with traditional culture as the carrier, and cultivate young children’s awareness of the protection of traditional culture.