3.1 Experimental Design
As an important carrier of human cultural heritage and scientific knowledge, museums carry various types of exhibition content such as history, culture, art, and nature. With the rapid development of digital technology, the Digital transformation of museums has become a trend. Digital transformation can not only improve the exhibition effect and audience experience of museums, but also realize the digitalization of museum internal management and operation. In recent years, the rapid development of AI technology has provided new ideas and methods for museum Digital transformation. AI interactive devices can achieve intelligent recognition, interaction, and recommendation of audiences through perception technology and intelligent algorithms. In the design of museum exhibition content, AI interactive devices can provide visitors with a more personalized, in-depth, and diverse exhibition experience through multidimensional data analysis and mining.
This paper aimed to explore the application of AI interactive device based on database management system in the design of museum display and exhibition content in multi-dimensional, so as to improve the level of Digital transformation of museums and the effect of audience experience. This article designed four experiments to explore this. 200 people were randomly selected and divided into 10 groups with 20 people in each group. Among them, 5 groups used AI interaction technology (experimental group), and the other 5 groups used traditional technology (control group).
(1) Comparing the application effects of AI interactive devices in multidimensional exhibition content design in museums
As a cultural venue, museums should constantly innovate to attract the attention of audiences, and the application of AI interactive devices can provide a more diverse and diverse exhibition experience. The experimental group used AI interactive devices to provide multi-level exhibition content presentation and personalized recommendation functions. The control group used traditional display methods to display text and image information. The purpose is to compare the differences in visitor satisfaction, stay time, and interaction frequency between using AI interactive devices and traditional exhibition methods.
Visitor satisfaction: It refers to the satisfaction of visitors to the entire exhibition content and interaction design.
Average stay time: It refers to the average stay time of visitors in the museum, and also reflects their level of interest in the exhibition content and interaction.
Interaction frequency: It refers to the number of times visitors interact with each exhibit, which can reflect the attraction of exhibits and the quality of interaction design.
(2) Comparing the improvement effect of using AI technology for voice guided tours on the quality of museum visits
Voice guided tours are one of the most common ways to visit museums, but traditional voice guided tours have problems such as being unable to meet the needs of different tourists and difficult to deeply analyze the meaning of cultural relics. By using AI technology to upgrade the voice guided system, the quality of visitors’ visits and the attractiveness of museums can be further improved. The experimental group adopted AI technology for voice navigation to provide precise explanations and interactive navigation services. The control group used traditional navigation methods (such as text navigation), which limited their experience and could not meet different needs. The purpose is to compare the differences in visit depth, visit efficiency, and visitor satisfaction between voice guided systems using AI technology and traditional voice guided systems.
Visiting depth: It refers to the depth of visitors’ understanding of the exhibits and their understanding of museum culture.
Visiting efficiency: It refers to the amount of information and understanding of exhibits that visitors have per unit of time.
Visitor satisfaction: It refers to the satisfaction level of visitors with the entire museum visiting experience.
(3) Comparing the effectiveness of AI technology prediction algorithms in managing museum visitor traffic
Museums often experience congestion and queuing during peak hours, which can affect the experience and management of visitors. By using AI technology prediction algorithms, it is possible to better manage tourist traffic and allocate museum personnel more reasonably. The experimental group used AI prediction algorithm to predict and manage visitor traffic based on historical data and real-time monitoring. The control group adopted manual allocation and management methods, which is inefficient and prone to congestion. The purpose is to compare the differences in accuracy, waiting time, and rationality of personnel allocation between prediction algorithms using AI technology and traditional management methods.
The accuracy of pedestrian flow monitoring: It refers to the accuracy of the prediction algorithm in monitoring the entry and exit of tourists.
Shortening degree of waiting time: It refers to the optimization and management of tourist traffic through predictive algorithms, which can reduce the waiting time of tourists in queues and improve the visiting experience.
Rationality of personnel allocation: It refers to optimizing tourist flow management through predictive algorithms, which can achieve a more reasonable and efficient allocation of museum personnel.
(4) Comparing the guiding effect of intelligent recommendation systems using AI technology on museum visitors
Museums usually have a large number of exhibits, and visitors are inevitably overloaded with information and unable to get started. By adopting AI technology as an intelligent recommendation system, visitors can be provided with more personalized and accurate exhibition recommendations, further enhancing their visiting experience and understanding of museum culture. The experimental group adopted an intelligent recommendation system using AI technology, which can provide personalized visiting plans and recommended exhibition selection. The control group adopted traditional exhibition layout, which can not consider the personalized needs of tourists. The purpose is to compare the differences in visit depth, visit frequency, and personalized demand satisfaction between intelligent recommendation systems using AI technology and traditional recommendation methods.
Visiting depth: It refers to the visitor’s understanding of the exhibits and their understanding of museum culture.
Visit frequency: It refers to the number of repeated visits by visitors to specific exhibits or venues, and also reflects their level of interest and desire to explore.
Personalized demand satisfaction: It refers to the satisfaction of visitors with personalized recommendation schemes and also reflects the effectiveness of intelligent recommendation systems.
For four different experimental purposes, each experimental index was different, but all were related to the museum’s visiting experience and management efficiency. The four experimental designs using AI technology discusd the application effect of AI technology in the museum’s Digital transformation from different perspectives.
3.2 Application of AI Interactive Devices in Museum Exhibitions
Figure 2 shows the application effect of AI interactive devices in the multi-dimensional exhibition content design of museums. Figure 2 (a) shows the experimental group using AI interactive devices, while Fig. 2 (b) shows the control group using traditional display methods. In the experimental group, the visitor satisfaction score was 8.92, the average stay time was 2.12 hours, and the interaction frequency was 8 times. In the control group, the visitor satisfaction score was 6.38, the average stay time was 1.34 hours, and the interaction frequency was 2.8 times. This indicated that in the design of multi-dimensional exhibition content, the use of AI interactive devices can better improve visitor satisfaction, average stay time, and interaction frequency, resulting in a more diverse and diverse exhibition experience. Compared to traditional exhibition methods, AI interactive devices based on database management systems can provide a more personalized, in-depth, and diverse exhibition experience.
Figure 3 shows the improvement effect of using AI technology for voice guided tours on the quality of museum visits. Figure 3 (a) shows the experimental group using AI technology for voice navigation, while Fig. 3 (b) shows the control group using traditional navigation methods. In the experimental group, the depth of visits increased by 32.24%, the efficiency of visits increased by 21.8%, and visitor satisfaction reached 91.98%. In the control group, the depth of visits increased by 13.22%, the efficiency of visits increased by 9.88%, and visitor satisfaction was 74.64%. This indicated that in terms of voice navigation, upgrading with AI technology can further enhance the depth, efficiency, and satisfaction of visitors. Traditional voice guided tours cannot meet the needs of different tourists and are difficult to deeply analyze the meaning of cultural relics. However, through the use of AI technology for upgrading, precise explanations and interactive guided services can be provided to visitors, thereby improving the quality of their visits.
Figure 4 shows the effectiveness of the AI technology prediction algorithm in managing museum visitor traffic. Figure 4 (a) shows the experimental group using AI prediction algorithm, while Fig. 4 (b) shows the control group using manual allocation and management methods. Table 1 shows the average comparison of the effectiveness of museum visitor flow management. In the experimental group, the accuracy of abortion monitoring was 92.94%, the waiting time was shortened by 22.04%, and the rationality score of personnel allocation was 93. The accuracy rate of abortion monitoring in the control group was 65.18%, the waiting time increased by 37.1%, and the rationality score of personnel allocation was 72.96. This indicated that in terms of tourist flow management, the prediction algorithm using AI technology can better predict tourist flow and allocate museum personnel more reasonably. Traditional management methods are prone to congestion, but prediction algorithms based on AI technology in database management systems can optimize visitor traffic management and reduce the time spent waiting in queues, thereby improving the visiting experience.
Table 1
Comparison of the mean effects of museum visitor flow management
| Experimental group | Control group |
Accuracy rate of human flow monitoring (%) | 92.94 | 65.18 |
Reduction in waiting time (%) | -22.04 | 37.1 |
Personnel allocation rationality rating | 93 | 72.96 |
Figure 5 shows the guiding effect of an intelligent recommendation system using AI technology on museum visitors. Figure 5 (a) shows the experimental group with an intelligent recommendation system using AI technology, while Fig. 5 (b) shows the control group with traditional exhibition layout. Table 2 shows the mean analysis of the guiding effects of different technologies on museum visitors. In the experimental group, the depth of visits increased by 26.78%, the frequency of visits increased by 11.26%, and the satisfaction of personalized needs reached 86.62%. In the control group, the depth of visits increased by 10.66%, the frequency of visits increased by 4.74%, and the satisfaction rate of personalized needs was 58.62%. This indicated that in terms of intelligent recommendation systems, AI technology can provide visitors with more personalized and accurate exhibition recommendations, further enhancing their visiting experience and understanding of the cultural value of museums. Traditional exhibition recommendation is often based on simple rules such as region and category, which is difficult to truly meet the personalized needs of visitors. However, intelligent recommendation systems using AI technology can comprehensively analyze visitors’ historical browsing records, visitor portraits, and other aspects, thereby providing more targeted, personalized, and in-depth exhibition recommendation services.
Table 2
Mean analysis of the guiding effect of different technologies on museum visitors
| Experimental group | Control group |
Visit depth (%) | 26.78 | 10.66 |
Access frequency (%) | 11.26 | 4.74 |
Personalized demand satisfaction (%) | 86.62 | 58.62 |
To sum up, the four groups of comparative experiments showed that the use of AI technology can significantly improve the experience and management efficiency of museum visitors in all aspects, providing new ideas and solutions for the Digital transformation of museums.