Search

This study aims to examine adaptability for educational games in terms of adaptation elements, components used in creating user profiles, and decision algorithms used for adaptation. For this purpose, articles and full-text papers in Web of Science, Google Scholar, and Eric databases between 2000-2021 were searched using the keywords "educational games", "serious games", "game-based learning", "adapt*", "player modeling", "user modeling". After applying the inclusion and exclusion procedures of studies accessed in the search, 26 studies were included in the study. The studies were analyzed in line with the themes determined for the components used in the adaptation of educational games. According to the results, adaptive educational game design was made for a wide variety of fields such as programming teaching, physics, mathematics, computational thinking, and logic. As for adaptive factors; It was determined that adaptations were made for the game, educational content, interface, and non-player character (NPC) behaviors. It is understood that pre-game adaptation and in-game adaptation methods are used as adaptation types. Finally, it is seen that Bayesian networks, artificial neural networks, fuzzy logic, deep learning, item response theory, and decision tree methods are preferred as decision systems in the adaptation process. The findings of this literature review can facilitate the design process by providing a roadmap for researchers interested in adaptive educational game design.

Purpose: The purpose of this paper is to reveal the smart collaborative learning service. This concept aims to build teams of learners based on the complementarity of their skills, allowing flexible participation and offering interdisciplinary collaboration opportunities for all the learners. The success of this environment is related to predict efficient collaboration between the different teammates, allowing a smartly sharing knowledge in the Smart University environment. Design/methodology/approach: A random forest (RF) approach is proposed, which is based on semantic modelization of the learner and the problem-solving allowing multidisciplinary collaboration, and heuristic completeness processing to build complementary teams. To achieve that, this paper established a Konstanz Information Miner workflow that integrates the main steps for building and evaluating the RF classifier, this workflow is divided into: extracting knowledge from the smart collaborative learning ontology, calculating the completeness using a novel heuristic and building the RF classifier. Findings: The smart collaborative learning service enables efficient collaboration and democratized sharing of knowledge between learners, by using a semantic support decision support system. This service solves a frequent issue related to the composition of learning groups to serve pedagogical perspectives. Originality/value: The present study harmonizes the integration of ontology, a new heuristic processing and supervised machine learning algorithm aiming at building an intelligent collaborative learning service that includes a qualified classifier of complementary teams of learners.

In this paper, we review algorithmic bias in education, discussing the causes of that bias and reviewing the empirical literature on the specific ways that algorithmic bias is known to have manifested in education. While other recent work has reviewed mathematical definitions of fairness and expanded algorithmic approaches to reducing bias, our review focuses instead on solidifying the current understanding of the concrete impacts of algorithmic bias in education--which groups are known to be impacted and which stages and agents in the development and deployment of educational algorithms are implicated. We discuss theoretical and formal perspectives on algorithmic bias, connect those perspectives to the machine learning pipeline, and review metrics for assessing bias. Next, we review the evidence around algorithmic bias in education, beginning with the most heavily-studied categories of race/ethnicity, gender, and nationality, and moving to the available evidence of bias for less-studied categories, such as socioeconomic status, disability, and military-connected status. Acknowledging the gaps in what has been studied, we propose a framework for moving from unknown bias to known bias and from fairness to equity. We discuss obstacles to addressing these challenges and propose four areas of effort for mitigating and resolving the problems of algorithmic bias in AIED systems and other educational technology.

This paper discusses educating stakeholders of algorithmic systems (systems that apply Artificial Intelligence/Machine learning algorithms) in the areas of algorithmic fairness, accountability, transparency and ethics (FATE). We begin by establishing the need for such education and identifying the intended consumers of educational materials on the topic. We discuss the topics of greatest concern and in need of educational resources; we also survey the existing materials and past experiences in such education, noting the scarcity of suitable material on aspects of fairness in particular. We use an example of a college admission platform to illustrate our ideas. We conclude with recommendations for further work in the area and report on the first steps taken towards achieving this goal in the framework of an academic graduate seminar course, a graduate summer school, an embedded lecture in a software engineering course, and a workshop for high school teachers.

Although an increasing number of ethical data science and AI courses is available, with many focusing specifically on technology and computer ethics, pedagogical approaches employed in these courses rely exclusively on texts rather than on algorithmic development or data analysis. In this paper we recount a recent experience in developing and teaching a technical course focused on responsible data science, which tackles the issues of ethics in AI, legal compliance, data quality, algorithmic fairness and diversity, transparency of data and algorithms, privacy, and data protection. Interpretability of machine-assisted decision-making is an important component of responsible data science that gives a good lens through which to see other responsible data science topics, including privacy and fairness. We provide emerging pedagogical best practices for teaching technical data science and AI courses that focus on interpretability, and tie responsible data science to current learning science and learning analytics research. We focus on a novel methodological notion of the "object-to-interpret-with," a representation that helps students target metacognition involving interpretation and representation. In the context of interpreting machine learning models, we highlight the suitability of "nutritional labels"--a family of interpretability tools that are gaining popularity in responsible data science research and practice.

Recently, machine learning (ML) has evolved and finds its application in higher education (HE) for various data analysis. Studies have shown that such an emerging field in educational technology provides meaningful insights into several dimensions of educational quality. An in-depth analysis of the application of ML could have a positive impact on the HE sector. However, there is a scarcity of a systematic review of HE literature to gain from the overarching trends and patterns discovered using ML. This paper conducts a systematic review and meta-analyses of research studies that have reported on the application of ML in HE. The differentiating factors of this study are primarily vested in the meta-analyses including a specific focus on student academic performance, at-risk, and attrition in HE. Our detailed investigation adopts an evidence-based framework called PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) for reporting the findings of our systematic review and meta-analyses of literature on the use of ML models, algorithms, evaluation metrics, and other criteria, including demographics for assessing student academic performance, at-risk and attrition in HE. After undergoing the PRISMA steps such as selection criteria and filtering, we arrive at a small-scale dataset of 89 relevant studies published from 2010 to 2020 for an in-depth analysis. The results show the outcomes of the quantitative analysis of the application of ML types, models, evaluation metrics, and other related demographics and provide quality insights of publication patterns and future trends towards predicting and monitoring student academic progress in HE.

Purpose: The purpose of this study is, First, to leverage the limitation of annotated data and to identify the cognitive level of learning objectives efficiently, this study adopts transfer learning by using word2vec and a bidirectional gated recurrent units (GRU) that can fully take into account the context and improves the classification of the model. This study adds a layer based on attention mechanism (AM), which captures the context vector and gives keywords higher weight for text classification. Second, this study explains the authors' model's results with local interpretable model-agnostic explanations (LIME). Design/methodology/approach: Bloom's taxonomy levels of cognition are commonly used as a reference standard for identifying e-learning contents. Many action verbs in Bloom's taxonomy, however, overlap at different levels of the hierarchy, causing uncertainty regarding the cognitive level expected. Some studies have looked into the cognitive classification of e-learning content but none has looked into learning objectives. On the other hand, most of these research papers just adopt classical machine learning algorithms. The main constraint of this study is the availability of annotated learning objectives data sets. This study managed to build a data set of 2,400 learning objectives, but this size remains limited. Findings: This study's experiments show that the proposed model achieves highest scores of accuracy: 90.62%, F1-score and loss. The proposed model succeeds in classifying learning objectives, which contain ambiguous verb from the Bloom's taxonomy action verbs, while the same model without the attention layer fails. This study's LIME explainer aids in visualizing the most essential features of the text, which contributes to justifying the final classification. Originality/value: In this study, the main objective is to propose a model that outperforms the baseline models for learning objectives classification based on the six cognitive levels of Bloom's taxonomy. In this sense, this study builds the bidirectional GRU (BiGRU)-attention model based on the combination of the BiGRU algorithm with the AM. This study feeds the architecture with word2vec embeddings. To prove the effectiveness of the proposed model, this study compares it with four classical machine learning algorithms that are widely used for the cognitive classification of text: Bayes naive, logistic regression, support vector machine and K-nearest neighbors and with GRU. The main constraint related to this study is the absence of annotated data; there is no annotated learning objective data set based on Bloom's taxonomy's cognitive levels. To overcome this problem, this study seemed to have no choice but to build the data set.

The student profile has become an important component of education systems. Many systems objectives, as e-recommendation, e-orientation, e-recruitment and dropout prediction are essentially based on the profile for decision support. Machine learning plays an important role in this context and several studies have been carried out either for classification, prediction or clustering purpose. In this paper, the authors present a comparative study between different boosting algorithms which have been used successfully in many fields and for many purposes. In addition, the authors applied feature selection methods Fisher Score, Information Gain combined with Recursive Feature Elimination to enhance the preprocessing task and models' performances. Using multi-label dataset predict the class of the student performance in mathematics, this article results show that the Light Gradient Boosting Machine (LightGBM) algorithm achieved the best performance when using Information gain with Recursive Feature Elimination method compared to the other boosting algorithms.

In this paper, a new evaluation method for under-graduate education quality is proposed based on Artificial Intelligence Neural Network Back-Propagation (BP) algorithm and stress testing. Using this method, a publically available indicator pool is constructed, consisting of 19 variables in 4 dimensions such as Teaching Attitude, Teaching Content, Teaching Approach, and Basic Characteristic of Teachers, which impact under-graduates' mastery of knowledge and capacity building. After the BP neural network algorithm is used to learn the optimum parameters for this evaluation model, sensitivity test is applied to identify the indicators that have significant effects on the quality of education. Furthermore, scenario analysis is utilized to explore the influence of the quality of education under pre-specified situations, which provides theoretical and empirical support for evaluating under-graduate teaching, improving education quality, and enriching teacher resources.

Leveraging artificial intelligence (AI), this study revolutionizes examination management and education in universities by developing an intelligent system encompassing comprehensive management, pre-examination activities, scheduling, and preparation. The system also features a quality management component for educational outcomes. An enhanced genetic algorithm introduces an adaptation function to optimize intelligent grouping, facilitating effective exam paper distribution. Applied at Y University, our innovative approach significantly refines exam paper difficulty (ranging between 0.5016 and 0.5581) and differentiation (0.3845 to 0.4596), showcasing the intelligent algorithm’s effectiveness in exam management and contributing valuable insights to educational research.

Artificial intelligence (AI) and machine learning have become increasingly important in modern society and are poised to play an increasingly prominent role in education. This paper seeks to provide a theoretical framework for interrogating the integration of AI in education spaces. The paper argues that the eventual response of educators to recent developments in artificial intelligence is eerily like the earlier cycles of integrating ICT in education and, decades earlier, calculators into mathematics instruction. Premised on the argument that there are similarities between the calculator revolution in mathematics education and the ICT revolution in education several decades ago and the current ongoing developments in artificial intelligence, this paper offers a theoretical lens. The theoretical lens is composed of the Technology-Organization-Environment (TOE) framework, Technology Acceptance Model, Technological Pedagogical Content Knowledge, Socio-technical system theory, and Diffusion of Innovation theory. The paper concludes that despite spatial differences between the ICT revolution and the artificial intelligence revolution, there are shared similarities warranting adoption of a similar theoretical lens. Furthermore, factors that were considered pivotal in the integration of ICT are still relevant to the revolution of artificial intelligence. [ABSTRACT FROM AUTHOR]

In this paper we review selected significant developments in the use of digital technology in the teaching and learning of mathematics over the last five years. We focus on a number of important topics in this field, including the evolvement of STEAM and critical making as well as the process of redefining learning spaces in the transformation of the mathematics classroom. We also address the increasing use of computer algebra systems and dynamic geometry packages; and the issue of student collaboration online, especially using learning environments and social media. We briefly touch on artificial intelligence systems, including hyper-personalisation of learning, multimodality and videos. We include a brief discussion on the impact of COVID-19 on mathematics education, and lastly on the more theoretical perspective of the epistemology of digital technology and the construct of humans-with-media. We conclude the discussion with some possible concerns and mentioning some possible new topics for research in the field. [ABSTRACT FROM AUTHOR]

This research aims to improve the rationality and intelligence of AUTOMATICALLY HIGHER MATHEMATICALLY EXAM SYSTEM (AHMES) through some AI algorithms. AHMES is an intelligent and high-quality higher math examination solution for the Department of Computer Engineering at Pai Chai University. This research redesigned the difficulty system of AHMES and used some AI algorithms for initialization and continuous adjustment. This paper describes the multiple linear regression algorithm involved in this research and the AHMES learning (AL) algorithm improved by the Q-learning algorithm. The simulation test results of the upgraded AHMES show the effectiveness of these algorithms. [ABSTRACT FROM AUTHOR]

Currently, a large amount of information is presented graphically. However, visually impaired individuals do not have access to visual information. Instead, they depend on tactile illustrations—raised lines, textures, and elevated graphics that are felt through touch—to perceive geometric and various other objects in textbooks. Tactile graphics are considered an important factor for students in the science, technology, engineering, and mathematics fields seeking a quality education because teaching materials in these fields are frequently conveyed with diagrams and geometric figures. In this paper, we conducted a systematic literature review to identify the current state of research in the field of automatic tactile graphics generation. Over 250 original research papers were screened and the most appropriate studies on automatic tactile graphic generation over the last six years were classified. The reviewed studies explained numerous current solutions in static and dynamic tactile graphics generation using conventional computer vision and artificial intelligence algorithms, such as refreshable tactile displays for education and machine learning models for tactile graphics classification. However, the price of refreshable tactile displays is still prohibitively expensive for low- and middle-income users, and the lack of training datasets for the machine learning model remains a problem. [ABSTRACT FROM AUTHOR]

A group is nilpotent if it has a normal series of a finite length n. By this notion, every finite p-group is nilpotent. The nilpotence property is an hereditary one. Thus, every finite p-group possesses certain remarkable characteristics. In this paper, the explicit formulae is given for the number of distinct fuzzy subgroups of the Cartesian product of the dihedral group of order 2³ with a cyclic group of order of an m power of two for, which m ≥ 3. [ABSTRACT FROM AUTHOR]

The rapid development of artificial intelligence, "Internet +," big data, 5G, and other technologies in the twenty-first century has not only brought great changes to the field of education but also brought unprecedented opportunities and challenges to the reform and innovation of mathematics teaching. The use of intelligent technology to carry out the reform of college mathematics teaching in depth and effectively improve the quality of teaching has become a hot topic discussed by the majority of mathematics teachers. This paper carefully analyzes and sorts out the problems existing in the current intelligent college mathematics teaching and systematically studies the related theories and design principles of the blended teaching mode. The ideas and approaches of the reform of college mathematics blended teaching supported by intelligent technology are deeply discussed from the aspects of improving the level of teachers, setting up a blended teaching team supported by intelligent technology, optimizing the informatization construction of teaching environment and establishing rich teaching resources, building an online and offline classroom teaching system, personalized learning under the background of microclass and cloud class, cross-university blended learning in the network environment, and mathematics precision teaching evaluation and optimization using big data. [ABSTRACT FROM AUTHOR]

It is not simple to consider the world from only one side, but analyzing all sides can cloud comprehension without reaching deep insight found at the core. In a word as a whole, there is potential for telling the whole world in one word, i.e., data, leading to interpretations as phenomena and paradigms at the core of this review. The tug of war between the two sides explains that data represent the world, or vice versa, and present a fundamental view that systems or subsystems frame the world, even though they are encoded and composed of culture, rules, or approaches such as the threshold of democracy. When the COVID-19 pandemic posed a threat, human efforts contributed to finding potentially answers to questions presented by the world: what, who, where, when, why, and how (5 wh); a calling in the form of a challenge, where facts show something. All these questions resulted in research, education, and service activities, with their respective data frameworks producing results. This paper aims to reveal the meaning of the outcomes through an observation from an outside perspective. Therefore, like COVID-19 and its vaccines, the assertion of convexity and concave contradictions in the treatment of data leads to a mutually conjugate treatment of data. In this regard, statistics and artificial intelligence play separate and complementary roles. [ABSTRACT FROM AUTHOR]

Copyright of Human Review is the property of Eagora Science and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In today’s rapid development of the economic environment, the company’s financial crisis can significantly reflect the enterprise crisis, and it has a significant impact on the development of the enterprise. Therefore, the prediction of the company’s financial crisis and the establishment of an early warning system have important practical significance. Based on the method of pattern recognition and artificial intelligence, this paper establishes a new forecasting model of corporate financial crisis, predicts its financial index data and realises the dynamic financial crisis warning. The model developed in this paper employs pattern recognition and artificial intelligence, and is thus endowed with high classification accuracy, good anti-noise ability and the ability to be sorted according to the importance of its index features.

With the rapid development of the Internet, security issues are becoming more and more prominent, and since most information is transmitted through the Internet today, Internet security is particularly important. When the Internet was designed, only mutual compatibility and interoperability between networks were considered, and security issues were not fully considered. As a result, as the Internet continues to grow, security issues are becoming more and more serious. One of the more difficult attacks is the Distributed Denial of Service (DDoS) attack, which has many forms of attacks, is harmful, and is difficult to identify and defend. Therefore, building a global Internet security protection system to achieve effective protection against DDoS attacks is the main work of this research paper. In this paper, we propose an artificial intelligence DDoS attack protection system, which implements a controller and switch auto-detection model by extending the protocol and establishing an optimization model to realize a low-load and low-latency traffic monitoring scheme; for DDoS attacks. We propose the attack inspection algorithm SCVAE based on Variational Encoder (VAE) and Spectral Clustering. in order to mitigate DDoS attack traffic, the protection system uses the QoS traffic control method, builds the application flow hierarchy model, and filters the attack traffic endured by the system by setting the application flow bandwidth limit as well as the traffic priority dual policy. Finally, a Mininet-based simulation test environment is built to evaluate the model, and different test indexes are set for different system modules to evaluate their actual performance. The results of this paper show that in the network traffic monitoring test, the artificial intelligence DDoS attack protection algorithm can respond to the attack more quickly by reducing the average 73ms per sampling compared with other algorithms; in the attack traffic identification test, the comparison accuracy (P) is improved by 15.14%, the accuracy (AC) is improved by 13.26%, the recall (R) is reduced by 9.23%, and the F1 measurement criteria improved by 23%. The test verifies that the artificial intelligence DDoS attack protection system can achieve real-time monitoring of each performance parameter and also illustrates the feasibility and practicality of the research content of this paper, which strengthens the construction of the technical means of Internet security protection and further enhances the Internet security defense capability.

The automated choreography of dance movements is a new field combining artificial intelligence and dance performance, which has important research value. In this paper, a Transformer-based cheerleading automatic choreography and real-time adjustment algorithm are proposed, which generates cheerleading movements consistent with the music rhythm by stacking multi-layer bidirectional cross-attention layers and introduces an algorithm for real-time adjustment according to the music phrases and the emotions of the dance phrases. The experimental results show that the new algorithm has a dance matching accuracy score of 4.33, which is 0.95 points higher than the accuracy score of manual matching, and 80.76% of the judges think that the overall effect of the cheerleading exercise generated by this algorithm is better than that of the choreography results of the comparison algorithm. This paper’s algorithm has good results, as evidenced by the results.

Education informatization is an important initiative for the country to realize education modernization, which is related to the development of China’s education. The use of a single evaluation of teaching effectiveness obviously cannot meet the assessment needs. Based on the premise of intelligent assistance through a hybrid brain-computer interface, this paper aims to study an evaluation method for teaching effectiveness using artificial intelligence. Firstly, EEG signals are collected through an EEG acquisition device, and then they are preprocessed. Second, the pre-processed signals are subjected to feature extraction, and then the features are classified using a specific pattern recognition method, and finally the classification results are used to assess the effectiveness of English teaching for college students. Based on the evaluation results, the learning system is optimized and improved. The signals collected by EEG devices carry a lot of noise, and in this paper, the processing of the original signals includes a smoothing filter, de-baseline filter, filter filter, and Kalman filter to achieve a higher signal-to-noise ratio. Multivariate evaluation results are provided by the evaluation system that is assisted by artificial intelligence. Compared with other evaluation methods to enrich the evaluation information, based on the above system effectiveness evaluation study, as far as the F1 value is concerned, this paper’s method is the highest, reaching 0.815, which is 0.048 higher than the highest F1 value of the traditional algorithm, and in the other two values, this paper’s method is also higher than other methods. This verifies the rationality and effectiveness of the teaching effectiveness evaluation system based on a hybrid brain-computer interface proposed in this paper.

Music education, as an important part of art education, can also take advantage of artificial intelligence technology to achieve more efficient personalized teaching. The direction of the application of artificial intelligence technology in music course learning is explored in this paper. Therefore, a music data technology interactive learning system is proposed. The music recognition module’s design utilizes a deep neural network model to model the complex problem of speech signal recognition. The encoder formula is obtained by representing the implicit layer feature vectors in the sample through a mathematical model. After encoding and decoding, as well as designing the activation function, the HMM algorithm is introduced to realize the application of DNN-HMM in acoustic modeling. Using a digital filter, the spectrum of the speech signal is smoothed, and the spectrogram is obtained by Fourier variation to visualize the representation of the speech frequency domain. The design of a music Internet teaching course is based on the method proposed in this paper. The melody recognition accuracy of the system is tested through simulation experiments, in which the distribution of auditory feature points of the piano ranges from 0.66 to 0.69. The distribution of rock music is above 0.7, and there is no overlap between the two audio datasets, which indicates that the system proposed in this paper has good recognition accuracy of audio features. Using the speech analysis module, the students’ music learning performance is analyzed. After the model designed in this paper to assist music learning, students’ music performance mean value is 4.397, and the control group’s performance is 3.565. The difference is 0.832. The system designed in this paper is more effective for music learning.

The rapid development of modern science and technology promotes technological innovation in education, and this paper constructs the higher education innovation model of “Artificial Intelligence+Education” to realize the goal of responding to the construction of education informatization in higher education. The intelligent education platform is created using the theoretical foundation of three-layer education to manage data integratedly. The intelligent mode includes face recognition and voice recognition, which are realized using LBP feature extraction and neural network algorithms. Their effects are verified. The model is better than the traditional education model in all dimensions of the impact of student training. The P is less than 0.05, which is a significant difference, and the effect of education management is improved by 0.02~0.09. This paper’s “Artificial Intelligence + Education” innovation model has certain advantages in higher education management and student training, and provides a practical path to the construction of informationization and intelligent development of education. It provides a pragmatic path for constructing information and the thoughtful development of education.

With the help of the dynamics model of the integration of AI and the management of college civic education, this paper investigates the integration of artificial intelligence and civic education in three directions: application specification, application design, and application practice. Using differential equations to represent the non-linear dynamics equations of the system and by means of differential solutions, the evolution mechanism of AI education application and integration is projected in this paper. The integration of AI and college civic education is explored through empirical analysis and comparative analysis. The results show that the average value of the comprehensive score of the three directions in the sample colleges and universities is 77.5828, which is in the bare integration stage, and the integration degree in the “formulation” path is the best, which is 85.698, and is in the complete integration stage. The students in the experimental class of the sample universities scored better than the control class without AI integration in civic education. There were no students with scores below 60, and there were 32 more students than the control class in the 90–100 segment.

The development of artificial intelligence technology has brought unprecedented challenges and opportunities for higher education management and student training mechanisms. The traditional education management mode and student training strategy appear to be incompetent in the face of new technology and urgently need innovation and reform. In the face of the latest trend of education informatization, higher education institutions must explore management and cultivation means that keep pace with the times, and take artificial intelligence as the driving force to create a new system of intelligent education to meet the diversified needs of education in the digital era. This paper analyzes the design and functions of the smart education platform, as well as its practical application effect in education management and student training. By introducing the intelligent education platform with artificial intelligence, the utilization efficiency of teaching resources was improved by 20%, and student satisfaction increased by 30%. Based on data analysis, this paper thoroughly discusses the effectiveness of the intelligent education platform in improving the quality of education and optimizing the allocation of educational resources. The modernization of higher education management and comprehensive improvement of students’ abilities can be effectively promoted by incorporating artificial intelligence technology in this study, which provides new ideas for building future education.

The way that artificial intelligence technology is being developed is causing a progressive evolution in college and university teaching methods and systems. This paper presents the design of the English teaching mode in colleges and universities based on artificial intelligence technology. Research on strategies for English teaching reform in colleges and universities supported by artificial intelligence technology. A weighted inference model was used to design an AI expert system, based on which an intelligent assisted learning system based on a neural network was constructed using the law of knowledge forgetting. Based on information acquisition, the random Linsen method was selected as the assessment methodology for the impact of English instruction in colleges and universities. The assessment model’s performance and errors are examined through comparison tests of the teaching evaluation model. In this article, the educational effect evaluation model has an accuracy rate of 91% and a mean square error of less than 0.002. The impact of AI-assisted English instruction on teaching is evaluated based on this. Results from studies conducted both before and following the experimental group show that the overall score increases by 12.33 points and the P-value of the four dimensions’ teaching effect is less than 0.01. The experimental group using artificial intelligence technology for English instruction received an average comprehensive score of 95 points in the actual English assessment, which is 8 points higher than the control group receiving traditional English instruction. This paper’s artificial intelligence teaching mode is believed to have a significant impact on students’ English, which is confirmed by its effectiveness and rationality. It is beneficial for teaching reform and guides enhancing and advancing English instruction in colleges and institutions.

The development of artificial intelligence technology has promoted economic development and improved people’s living standards, but it will also cause many risks and uncertainties. The purpose of this paper is to create a reciprocal fairness model for artificial intelligence collaboration and explore the causal relationship and liability allocation in artificial intelligence criminal infringement cases based on Rabin’s theory. Through the Hande formula, the criteria for determining fault in the case, as well as the marginal costs and benefits of the aggressor’s use of AI to commit crimes, are calculated. Finally, based on the theory of behavioral game evolution, this paper discusses the cooperation law of the three parties under the regulation of the Criminal Procedure Law, and discusses the illegal cost of the illegal implementation of artificial intelligence from the amount of compensation. The results show that in 68,535 cases of using AI to commit crimes in 2022, the average compensation is 74,556.87 yuan, indicating that the cost of crime is much lower than the proceeds of crime. The proposed legal regulations and the prevention and control of AI technology risks can be practiced through this study’s practical relevance.

In recent years, the rapid development of artificial intelligence technology represented by knowledge graphs and deep learning has provided an opportunity for educational innovation and learning mode change. A smart music learning model for colleges and universities is developed in this paper with the help of artificial intelligence technology. Learning data analysis is achieved through the use of a community discovery algorithm based on graph data in the model. In order to construct the learning community, the AGNES hierarchical clustering algorithm is used to cluster individual samples in the dataset. Learning big data and music professional ability are correlated through the mining of learner portrait features. Personalized learning paths are generated using the improved convolutional neural network. As experimental subjects, sophomore music majors at X institution were tested and analyzed for the teaching model in the end. The results show that the maximum learning interaction coefficient of the experimental subjects can be obtained as 5.34 and the maximum learning path coefficient as 2.84 under the smart learning mode. The correlation coefficients of the use of the smart learning mode with the usual test scores and the learning effort values are between 0.318 and 0.502. Teachers can obtain precise teaching data from this paper to quantitatively characterize subject competence goals and facilitate the smooth implementation of smart learning.

S&T management data has a wide range of sources and types, and the innovation of S&T management data service model is an important way for the efficient utilization of S&T resources in the new era, so this paper creates an innovative model of S&T management data service based on Data-Information-Knowledge-Wisdom model and artificial intelligence technology. Heterogeneous data mining technology based on association rules is used to obtain the connection between S&T management data, Lagrange interpolation is used for heterogeneous data cleaning to predict the missing values of S&T management data, and data lineage resolution technology is used to solve the challenges brought by the complex and diverse S&T management data components. Experimental analyses are conducted from both S&T management data processing and data service cases to verify the effectiveness and scientificity of the S&T management data service innovation model proposed in this paper. The results show that in S&T management data processing, this paper’s method consumes less than 2.45s for associated data rule mining, which has high mining efficiency, and the duplication rate and missing rate of data are below 0.0260 and 0.0222. Through the analysis of the service quality data, it can be seen that the degree of explanation of the service process quality problems of the model proposed in this paper tends to be close to 1, which can reflect the differences in the service process quality problems, and provide accurate, intelligent and personalized services for the main body of science and technology innovation.

With the development and improvement of artificial intelligence technology, the teaching innovation mode of combining college sports courses with artificial intelligence has gradually received widespread attention. This paper is based on artificial intelligence technology for the design of intelligent sports detection wearable devices, through which students’ sports data are collected, low-pass filters are used to reduce the noise of the collected data, normalization is carried out, and the AlphaPose algorithm is combined with the assessment and extraction of the human movement posture of college sports. The artificial intelligence sports teaching framework is built to innovate college sports teaching based on artificial intelligence. Finally, the impact of sports recognition is examined, and a comparison experiment is carried out to examine the practical implications of this teaching method. The four experimental targets had sports recognition errors that were less than 10% on average according to the results. The two classes under the experimental control have a P-value of less than 0.05 in the comparison of physical skills and physical fitness test data, and there is an improvement of 5-20 in all scores, which indicates that the experimental class has a higher teaching effect and is significantly helpful in performance improvement. Based on the above, this paper researches the practice of artificial intelligence technology in college sports teaching to provide an innovative path for the transformation of traditional sports teaching to artificial intelligence sports teaching.

In this paper, relevant cultural materials were first collected and extracted using knowledge mapping and retrieval tools, and the co-occurrence analysis method was used to construct the co-occurrence relationship matrix between keywords. Combined with the method of graphic vectorization, the traditional cultural and creative product design patterns and motifs are directly scanned to extract the design prototype’s outer contour and polygonal path. Next, the recommendation process of cultural and creative products was realized by combining collaborative filtering and the TransD-CF algorithm. Finally, the influence of cognitive attitude and purchase behavior indicators on cultural and creative products was analyzed through correlation. The results show that the difference between genders using essay on hobby collection of cultural and creative products is 0.203, and the practicality requirement of cultural and creative products decreases by 0.09 for every 100 yuan increase in price. This paper presents a fresh perspective on cultural and creative promotion and plays a guiding role in design practice with the aid of artificial intelligence.

This paper first deconstructs the core of the college English precision education model, combines relevant theoretical knowledge, and constructs a college English precision education model based on artificial intelligence. Secondly, the convolutional neural network technology is integrated into the joint probability matrix decomposition model, and the resource recommendation list is generated through the cognitive ability level of students and their individualized needs so as to realize the precise, intelligent recommendation of English education resources. Finally, the performance of the recommendation for teaching English educational resources and the practical effect of the educational model are explored through comparative experiments. The results show that the precision rate and recall rate of the recommendation with a test set of 10% are 0.871 and 0.866, respectively, and the F1 value is 0.88. After the teaching practice, students’ listening ability improved by 0.132, expression ability improved by 0.13, reading ability improved by 0.132, writing ability improved by 0.130, and translation ability improved by 0.128. Based on the paper, the educational model has a positive impact on improving the level of English education in colleges and universities.

To solve the problems of low completeness of data collection and poor accuracy of evaluation of traditional sports training movement completion, this paper proposes an artificial intelligence-based DTW pose matching algorithm. Firstly, the sports postures are matched and evaluated for movements. Then define the limb angle deviation factor and calculate the deviation degree of each limb angle, output the limbs with a deviation degrees greater than the set standard, identify the deviated limbs that affect the overall movement standard, and realize the evaluation and result in the feedback of basic movements in sports training. Under the three feature extraction methods, the accuracy of the statistical value feature extraction algorithm, LR feature extraction algorithm and integrated feature extraction algorithm of the DTW poses matching algorithm were 91.12%, 96.84% and 96.54%, respectively. The accuracy rates of LDA, KNN, NB, CART and DTW algorithms were 25%, 43%, 32%, 33%, and 72%, respectively, when the other four models were used to compare the accuracy rates with the DTW pose matching algorithm. Among them, the accuracy of the DTW algorithm is significantly higher than the other four algorithms. Therefore, the artificial intelligence-based sports training management model proposed in this paper can significantly improve the current problems, such as difficulty in assessing the accuracy of sports movement training, inefficient supervision of teachers’ guidance to students, and difficulty for students to improve their movements directly, which has strong practical significance and application value.

In the context of the development tendency of artificial intelligence, the paper describes the opportunities and challenges artificial intelligence brings to business English talent training, innovates and reforms innovative business negotiation talent training methods, and develops independent innovation according to the future development trend of artificial intelligence. The paper discusses the practical activities of training business English talents using artificial intelligence. It mainly focuses on the indicators of building the entity model of business English talents training through artificial intelligence technical RBF ne ural network, grasping the genetic algorithm from four aspects such as the number of gender chromosomes, integral function formula calculation, genetic algorithm, RBF neural network parameters to optimize the entity model and genetic algorithm, and optimizing the limitation of RBF neural network according to the genetic algorithm. The RBF neural network entity model with the genetic algorithm is used to implement detailed analysis and scientific research exploration of the business English talent training evaluation system. The database deviation index and precision index values under the two entity models were implemented for comparison operation. The experimental results show that under the deviation index, the RBF neural network entity model, according to the genetic algorithm, converges quickly and longer than the RBF entity model. Regarding the precision index, the genetic algorithm RBF neural network has a higher precision than 0.94 for every 60 teams, while the RBF model has a precision of 0.84. This research allows for a more accurate analysis of the strengths and weaknesses of school students in business English. Teachers need to improve their academic performance and quality based on their strengths and weaknesses to facilitate the shaping of more excellent business English talents for China. It is important to explore the way of training business English talents under artificial intelligence to accelerate the innovative development of English education and training in China and the trend of English development.

To solve the conflicts between the transparency of capital and current restrictive regulations and regulations regarding consumers’ right to claim information and safety, this paper studies the legal risk and prevention path of the transparency of capital due to artificial intelligence. Firstly, the legal risk ways and means of the transparency of capital are constructed by the combined algorithm of SVR, BP, and RNN under the artificial intelligence algorithm, focusing on data tracking before and after the rectification of sharing enterprises with the combined algorithm of BP neural network and RNN to test whether the preventive measures are effectively implemented in place, and then the legal risk prevention path based on the government and enterprise levels is derived. The study concludes that shared travel legal disputes are rising between 2018 and 2022. Among the 10 types of violations sampled for investigation, age information was accessed in violation of the law the most, reaching 53,607,900, and the least in comparison, precise location information was accessed in violation of the law, 1,029,000. After warnings by government departments, the overall violations by enterprises after rectification were on a downward trend, with the incidence of violations controlled between 28.1% and 43.2%. The research on the legal risks of sharing economy in this paper has realistic value and reference significance to the legislation of transparency of capital.

In recent years, the development of artificial intelligence has led to the growing influence of new media on society. The creators of digital images no longer play the role of exporters of art and culture but gradually delegate power to the audience, who are no longer passive recipients of information but are more involved in the interactive experience of video works, better engaged in the background of artworks and the emotional exchange of art and culture that occurs with artworks. Dunhuang murals, as a representative of the excellent traditional Chinese culture, have formed a wide range of cultural expressions with the help of new media technologies with different characteristics, effectively attracting audiences to participate in dissemination activities such as knowledge learning, cultural experience, and artistic exchange of Dunhuang culture. This paper provides an overview of interactive perceptual video design methods, the impact of interactive perceptual design on the narrative line of the video, and the features of the interactive perceptual invention, such as immersion, immersion, and fun. Firstly, a comparative analysis of interactive perceptual image design cases is conducted to summarize the differences between interactive perceptual image design and traditional images and outline the advantages of the former. Finally, a complete augmented reality display work is formed through the organic combination of the interactive perceptual design in three dimensions: user experience, visual guidance, and content narrative. The results of this paper show that 80% of the 120 people believe that the interactive perceptual presentation has made Dunhuang murals more vivid and exciting; 91% believe that the production of Dunhuang murals with perceptual machine technology gives visitors an immersive experience; among them, it is found through the research that visitors are 85% satisfied with this design, which exceeds the expected guesses. This paper, as a new exploration of future cases of digital communication of cultural heritage based on enhanced interactive perception technology, also argues the feasibility and effectiveness of its design in terms of results and provides new ideas for the communication of traditional culture.

With the change of the fourth generation of information technology represented by artificial intelligence, higher education is gradually stepping into the stage of intelligent development, and leisure sports majors as one of the majors that are booming, which puts forward higher requirements on the teaching power of teachers of leisure sports majors. Therefore, studying the current situation of talent cultivation of leisure sports majors under artificial intelligence plays a good role in promoting the overall improvement of the teaching quality of leisure sports majors. In this paper, the current situation of talent training and classroom teaching of leisure sports majors is studied based on a convolutional neural network in the artificial intelligence perspective, and the framework of artificial intelligence technology for leisure sports education is constructed. It can be seen that the attitude of leisure sports students towards theory class is better; 40.93% think theory class is very important, 38.13% think theory class is more important, and 19.27% think the importance of theory class is average. Students’ attitudes toward practical classes were better than those toward theoretical classes, with 63.71% considering practical classes very important and 26.85% considering them more important. From the analysis results, we can see that there are still problems of weak basic theory research, confusion of cultivation goals, lack of science in curriculum setting, and lack of teachers in cultivating talents in leisure sports majors. In summary, this paper argues that colleges and universities and college teachers should take the initiative to apply the technical framework of artificial intelligence in leisure sports education, strengthen theoretical research, make up for the shortcomings of teaching materials, as well as integrate training objectives, improve curriculum settings, enhance faculty strength, investigate the talent specification needs of the market in-depth, proactively meet the arrival of the era of artificial intelligence, and contribute to the cultivation of talents in leisure sports majors.