As the economy develops, the tourism ecological environment (TEE) has been gradually damaged. The ecological environment is the basis of human life, and the sustainable development of the ecological environment is of great importance to promote the stable development of society. China has rich grassland tourism resources. However, as a result of the rapid development of tourism, some scenic spots have been overdeveloped and commercialised, leading to the destruction of natural landscapes, damage to ecosystems and the gradual sanding of large tracts of grassland. The desert grassland used for tourism development is located between the grassland and the desert, and is the barrier that ensures the entire grassland ecosystem. To carry out environmental management of tourism ecology, it is necessary to construct a statistical monitoring index system for tourism ecology. However, traditional ecological environment monitoring is mainly based on manual sampling survey, which is cumbersome. The monitoring data is not accurate enough. In this paper, remote sensing technology (RST) was used to obtain remote sensing images of desert grassland, and intelligent image processing (IIP) technology was used for feature recognition. Compared with the traditional ecological environment statistical monitoring method, it showed that: In desert grassland A, the average monitoring accuracy of the traditional ecological environment statistical monitoring method and the ecological environment statistical monitoring method based on IIP were 90.12% and 94.56% respectively; in desert grassland B, the average monitoring accuracy of the traditional ecological environment statistical monitoring method and the ecological environment statistical monitoring method based on IIP were 88.20% and 92.60% respectively. Therefore, statistical monitoring of TEE based on IIP can improve the monitoring accuracy of ecological environment indicators.

In order to analyze the reading behavior and its meaning of readers in blockchain online reading platforms, this article conducted research on reading emotion recognition. This article utilized the characteristics of blockchain technology to analyze the reading mode of blockchain internet platforms. By using audio and image bimodal recognition methods, the recognition of readers’ reading emotions can be achieved. After feature extraction of speech and facial images, hidden Markov models (HMM) can be used for speech emotion recognition. Support vector machines (SVM) can be used for facial image emotion recognition, and decision level fusion can be used for bimodal emotion recognition. This article obtained the final emotion recognition results to analyze and predict user reading behavior. Analyzing the psychological state of readers based on emotional recognition results can achieve more intelligent reading information push. Experimental results on the effectiveness of reading bimodal emotion recognition showed that the accuracy of reading bimodal emotion recognition based on decision level fusion was much higher than that of single modal emotion recognition. The bimodal method has an average accuracy rate of over 85% in emotion recognition and has a high effect in emotion recognition. Reading bimodal emotion recognition based on audio and image can accurately identify readers’ emotions, adjust information push content in a timely manner, and achieve the regulation of readers’ emotions, which has high application value.

At present, there are differences in the building of information in various career institutions. The degree of implementation of management, teaching and services is uneven, and educational resources are limited and unevenly distributed. The construction of educational resources includes the overall layout, structure and quantity of resources, information mode, service impact, etc, all of which require systematic planning. Under the above background, this paper conducted research on the topic of building a model of co-construction and sharing of digital ideological and political resources for embedded courses based on artificial intelligence algorithms, and considered the insufficiency of the existing digital ideological and political resources in the allocation efficiency and insufficient system sharing, as well as creatively used artificial intelligence algorithms to improve the previous system. In the algorithm, the texture mapping of the system was carried out, and the duty cycle of each columnar area was specified. In the experiment, the number of resources in the digital resource platform was investigated, and the input of different types of colleges and universities in digital ideological and political resources was collected. The explanation of experimental data: 83% of 985/211 colleges and universities used the database designed in this paper, and 17% of them actively built the database; 57% of the general undergraduate schools used the database designed in this paper, and 20% were under construction, as well as 13% were still preparing. This showed that in general undergraduate schools, a small proportion of the digital ideological and political resource sharing model was used, and the 985/211 colleges and universities had relatively good investment in the construction of digital ideological and political resources.

The rapid expansion of tourism across the world necessitates constant innovation and development in the services offered to visitors in order to assure their comfort and happiness while on the road. Travelers’ experiences may be greatly enhanced by providing them with basic and essential conveniences such as optimal route identification and suggestion technology. In this paper, we use data mining to investigate the effect of scenic site clustering and group emotion on tourist route choosing. It is common for traditional route selection algorithms to just examine the impact of picturesque locations on route design. Many people choose the Chimp optimization algorithm (ChOA) because of its straightforward idea, simple implementation, and high level of resilience. With the goal of solving practical challenges in mind, this study uses real-world geographic data to build a discrete ChOA for the tourism route planning problem, which may be applied in practice. Simulation experiments are done, and outcomes data are studied and assessed. The assessment findings show that the ChOA is suitable for mass tourist data mining. The smart machine’s final best tour routes are directly tied to the requirements, interests, and habits of visitors and are completely connected with geospatial services to ensure accuracy. The ChOA algorithm serves as a good example of how data mining may be used in the field of mass tourism.

Due to the deepening reform of quality education, the requirements for physical education teaching in colleges and universities have become increasingly strict. In this era of rapid renewal and development of multimedia information technology, in order to make the traditional sports basketball teaching keep up with the pace of the trend and to search for the future development direction of college public sports basketball teaching, this paper studied the application of multi information data fusion technology in college public sports basketball teaching. The remote sensing technology and global positioning system in the multi information data fusion technology were used to conduct real-time detection and statistics on the sports effects of students in basketball teaching, and the relevant experimental scheme was designed. The data results recorded by manual recording and multi information data fusion technology were compared. The experimental results showed that when three student representatives and remote sensing technology simultaneously counted the times of passing and touching, the success rate of passing and the scoring rate of throwing for four sports members, the accuracy of remote sensing technology was higher; the Global Positioning System (GPS) system could effectively record the running distance, average speed and heart rate of 4 athletes. The average speed of No. 3 athlete was 9.1 m/s; the passing rate and shooting rate were both 50%, and the average speed of No. 4 athlete was 7.85 m/s. The pass success rate was 50%, and the shooting rate was only 33.3%. These data were conducive to teachers’ timely understanding of students’ personal conditions and basketball level, which could improve the efficiency of college sports basketball teaching and also increase the quality of students’ sports. At the same time, the questionnaire survey method was also used to study the results of the introduction of multi information data fusion technology. The findings shown that multi-information data fusion technology might increase students’ passion for learning basketball courses, hence improving the quality of sports, by altering their interest and attitude. In order to provide guidance for the future development of college public sports basketball instruction, this study offered a reference value for the application of multi-information data fusion.

Artificial intelligence (AI) and multimedia technology (MT) provide a new platform for college physical education (PE), which plays a positive role in promoting college PE. Combined with the actual situation, some discussions are made on the application of multimedia teaching technology in college PE teaching, in order to better serve the MT teaching of college PE teaching. The popularization and wide application of multimedia teaching technology in education and teaching have caused a series of changes in teaching concepts, teaching design, teaching methods, creative teaching, etc., preparing for the development of teaching. Starting from the teaching quality evaluation methods, the existing problems in the evaluation process were analyzed. These problems are reflected in the retrospective evaluation method, which is not scientific enough to summarize the evaluation results, and it is difficult to track and improve the teaching ideas. Teaching evaluation is a complex system that includes classroom teaching, sports facilities, sports activities, classroom teaching, physical health, supervision and management and many other aspects. Modern educational philosophy generally holds that the classroom teaching process should include formulating clear teaching objectives, selecting the most appropriate teaching methods and using scientific evaluation methods to collect information about correct answers. According to the construction of a comprehensive evaluation system of intelligent algorithm and AI technology, the quality of teaching evaluation has been improved by 21.4% after calculation.

Although human motion form capture is widely used in multiple fields, it often requires a significant amount of time and cost to learn how to operate the device during use. Therefore, this article attempted to apply computer vision (CV) technology and image segmentation algorithms to human motion form capture technology, simplifying the operation scheme and improving recognition accuracy and efficiency. This article provided an in-depth analysis of human motion form capture technology. Firstly, it identified several parts of the current human motion form capture technology that can be optimized, and introduced the effects of these optimized parts on human motion form capture in sports training. This article took the form capture of aerobics athletes as a sample and extracted 50 keyframe images containing aerobics scoring actions from 100 aerobics activity videos. The extraction interval for these keyframe images was at least 10 seconds. Next, this article used histogram equalization to enhance the image, while segmenting and recognizing the human motion forms of the five types of actions in the keyframe images, highlighting the level of action standards of athletes in aerobics. Finally, this article selected 6 key frame images containing different movements of aerobics athletes for comparative experimental analysis. In this experiment, both commonly used optical unlabeled capture techniques and motion morphology capture techniques combining CV and image segmentation algorithms were used to capture the human body in the image. The addition of CV technology and image segmentation has improved the overall performance of human motion morphology capture technology by approximately 26.02%. The integration of CV technology and image segmentation algorithms into human motion form capture technology has greatly improved image processing efficiency. At the same time, CV technology and image segmentation algorithms have also enabled better image processing accuracy in human motion form capture.

Image hiding is a technique for transmitting secret information under the cover of a digital image. It usually conceals sensitive information into images for the purpose of encryption. Currently, high embedding capacity and information security remain important research aspects of the image hiding. In this study, a secret image sharing scheme based on a reference matrix is proposed to enhance embedding capacity and verify data integrity. In the proposed scheme, a hill matrix is designed as a reference matrix and a location table is generated. Moreover, a location pair table is generated to ensure the uniqueness of data hiding locations. Then, leveraging the processing of the location pair table, as well as the mapping of the reference matrix and the location table, each pixel pair is exploited to conceal eight secret bits. Furthermore, based on the special construction of the hill matrix, a deception recognition mechanism is designed. This mechanism can detect deceptive behavior and identify tampered images by means of data hiding locations. The experimental results indicate that the proposed scheme achieves a higher embedding capacity and better deception recognition performance than that of most of existing schemes.

Upon the arrival of the sharing consumption model, guaranteeing the authenticity of products and the transparency of transactions has emerged as fundamental challenges hindering the industry’s progression. This paper explores the selection and optimization of blockchain technology implementation methods within the shared supply chain. Through a comparative analysis of non-blockchain, private blockchain, and distributed application models, our findings reveal that distributed application generates higher profits when consumers exhibit high sensitivity to blockchain performance and when such performance adheres to specific standards. Conversely, the private blockchain is more suited to customized requirements. Blockchain technology not only increases prices and transparency but also enhances consumer trust, particularly within the distributed application framework. Performance plays a crucial role in decision-making, with the private blockchain relying on corporate investment for optimization and distributed application being constrained by the limitations of the public chain. Based on these findings, it is recommended that enterprises adopt a flexible approach in selecting the most appropriate mode according to their unique needs. Additionally, they should prioritize technological innovation, strive to improve blockchain performance, consider fostering consumer trust, and promote collaborative development throughout the supply chain. These strategies will collectively contribute to the healthy and sustainable growth of the industry.

“Internet + medical health” service is an important direction of current medical development. The high interactivity between doctors and patients in online medical services and the massive and dynamic nature of recommended information have brought new challenges to the platform’s analysis of patient perceived trust. It is difficult for the trust transfer model to process massive information in real time. Clustering massive recommended trust is an effective solution, but data clustering is difficult to process simultaneously with the perceived recommendation trust tendency, which brings about the problem of perceived recommendation trust clustering. How to measure the trust tendency reflected in the clustering of patient perceived recommendation trust is a difficult problem faced by the trust transfer model in the context of Internet medical health services. This paper proposes a two-stage research idea of ” conversion first, clustering later”. Intuitive fuzzy sets are used to measure the fuzziness of patient perceived recommendation trust, and combined with sentiment dictionary, density clustering method and other methods to cross and penetrate each other, a patient perceived recommendation trust clustering method is constructed in the context of Internet medical health services. Finally, data experiments were conducted using the real data of the top 17 doctors on the Haodafu online platform to verify the effectiveness of the method. This method can reflect the subjectivity and ambiguity of patients’ perceived trust, provide a solution for the processing of massive recommendation information, contribute to the research on the improvement of trust transfer method system, and provide method support for predicting and analyzing the trust measurement of patients in the context of Internet medical health services. The model proposed in this paper can be used as the core of the trust-based recommendation system in Internet medical care, and help Internet medical platforms formulate precise strategies for doctors.