Abstract
The opera performance market is maturing, and at the same time, new opera performance and marketing methods are being introduced on a regular basis to meet the growing spiritual needs of the audience. It is the foundation for opera to achieve its business goals by going to the market and completing commodity exchange. The success of opera performances on the market has a direct impact on whether they can achieve market success and achieve the ultimate goal of maximizing profits. An in-depth analysis and discussion of industrial data mining technology in the positioning and market selection of opera performance art is presented in this paper, and it is of great theoretical and practical importance for improving the positioning and market selection of opera performance art and promoting the development of the opera performance industry. The application of artistic orientation and market selection in industrial data mining will be developed, which will aid in the systematic development of artistic orientation and market selection in opera performance of industrial data mining systems, improve industrial data mining efficiency, and promote the application of artistic orientation and market selection in opera performance of industrial data mining systems.
1. Introduction
China’s opera performance market has grown from scratch. From initial success to brand building, the audience of opera is growing with the expansion of opera performance. The opera performance market is becoming more and more mature, and at the same time, the opera performance and marketing methods accepted by the market are constantly introduced, which meets the growing spiritual needs of the audience [1]. It is the premise for opera to achieve its business objectives by going to the market to complete commodity exchange. The market performance of opera performances directly affects whether it can achieve market success and achieve the ultimate goal of maximizing profits [2]. How to organically combine the artistic orientation of opera performance with market selection in western opera and national opera performance and realize the win-win situation of market popularization and self-development are problems that need attention. At present, the transformation of opera performance market from seller’s market to buyer’s market requires producers of opera performances to have a complete set of marketing strategies, take the initiative to attack, and win the market [3]. Among them, it is very necessary for opera performances to have an accurate market positioning. Nowadays, material civilization is highly developed, modern entertainment methods are constantly innovating, and the theme and living space of opera music have changed greatly compared with before. In order to adapt to the new environment, “reform” seems to be the mainstream at present, and some “high spring and white snow collections” keep operas away from nature, society, or original nonutilitarian purposes. Opera performance is the consumer of performing arts products, and the creation of opera performance is to do a good job of getting the audience’s pulse, knowing what they like and what they want to see in this work, and so long as it is a normal demand, they should strive to meet it [4, 5]. Opera is generally active in the “three highs” areas with a large number of senior intellectuals, developed economy, and frequent international exchanges. However, with the continuous development of the market, opera has evolved into a kind of music and dance with strong commerciality, and elegant music has gradually lost its original artistic foundation.
This paper deeply analyzes and discusses the application of industrial data mining technology in opera performance art positioning and market selection, which has important theoretical and practical significance for improving opera performance art positioning and market selection and promoting the development of opera performance industry [6]. Industrial data mining is widely used in retail, communication, finance, and medical services. Data mining can highly automate the analysis of enterprise data, make inductive reasoning, mine potential patterns, and help decision-makers adjust market strategies, reduce risks, and make correct decisions [7]. Industrial data mining is a basic process of knowledge discovery based on computer as the main tool, massive data as the analysis basis, and the comprehensive use of clustering, machine learning, classification, pattern recognition, expert system, and other methods to find the information hidden in massive data and the association rules between data. Parallel processing system and industrial data mining technology are listed as the top two of the top ten emerging technologies in the next five years. With the development of data capture, transmission, and storage technology, large system users will need to use industrial data mining technology to mine the value of data [8, 9]. In the field of opera performance, taking art positioning and market selection as an example, based on big data and through the application of industrial data mining technology, we can find the art positioning and market selection of opera performance, so that we can classify consumers on the basis of information, such as art positioning and market selection, and carry out product development according to the classification of opera performance. Provide personalized and customized products or product combinations for opera performances to realize economic benefits [10].
Industrial data mining often needs to analyze and judge the data in opera performance art positioning and market selection, for example, the prediction of opera performances, the analysis of artistic orientation, and the classification and clustering of market choices [11, 12]. Opera performance is the main application field of industrial data mining, and a large amount of data has also been accumulated in the opera performance industry. Industrial data mining on these data can identify the artistic orientation and market selection and discover the modes or trends of people watching opera performances, which can better improve the service quality, improve the satisfaction of users, and improve the management of opera performances. The opera performance of industrial data mining will be developed into the application of artistic positioning and market selection in industrial data mining, which will help the systematic development of artistic positioning and market selection of opera performance of industrial data mining system, improve the efficiency of industrial data mining, and promote the application of artistic positioning and market selection of opera performance of industrial data mining system in enterprises, society, and other aspects. In the process of industrial data mining, the art positioning and market selection of opera performances should use visual methods as much as possible, which makes the knowledge mining process easier for users to intuitively understand and manipulate [13]. It is also convenient for human-computer interaction [14, 15]. This will help to promote data mining as a basic tool for data analysis of opera performance art positioning and market selection.
2. Related Work
Literature [16] proposes that the development of modern media technology can convey information to more audiences in the shortest time. The dissemination and popularity of this media culture will also bring a new round of shock wave, attract the attention of artists, record companies and music lovers, stimulate their interest in opera art and promote the development of excellent opera art in China, promote the popularization and development of opera, and let people really contact, understand, and reaccept elegant art. According to literature [17], the drama concept of audience awareness and aesthetic education is not only the foundation for success and decline in the beginning, maturity, and growth of drama, but also the support point for its survival and foothold in the era context of “people-oriented” and “enriching the country and strengthening the people” advocated by current politics. In the function of drama, audience consciousness and aesthetic education are also two aspects of dialectical unity. Domestic performances cannot reach the stage of comprehensive development of the market value of opera music performances, according to a review of the literature [18], and the concept of performance promotion units remains at the level of relying on the box office, resulting in high opera performance costs and ticket prices. Literature [19] pointed out that, throughout the history of drama, there has been a phenomenon of artificially distorting and opposing the two, which has caused the drama to fall into misunderstandings on several occasions or biased the public’s low taste, excluded the educational function of the drama itself, and led the drama to the vulgar and meaningless left or held high the banner of “social responsibility,” dispelled the entertainment nature of drama, ignored racial discrimination, and led the drama to the vulgar and meaning. According to literature [20], the high ticket price accounts for 14 percent of the monthly income of ordinary visitors, which is significantly less than that of Chinese visitors. The ticket price of several hundred yuan is still prohibitively expensive for the working class, and many citizens can only “look at the drama and sigh,” resulting in the performer almost immediately giving up the potential audience. The complete, original, or museum preservation of opera music is contrary to the objective law of art development, according to literature [21]. The “audience theory” of drama is based on the “audience consciousness” in drama creation, according to literature [22]. There have been “four elements” (script, actor, audience, and theater) in drama composition theory, “three elements” (script, actor, and audience), and “two elements” (actor and audience) [23]. The performances of the world’s top opera houses in Europe generally cost 28 euros (equivalent to RMB about 280 yuan), according to the big data analysis method, and the fare only accounts for 2.8 percent of Europe’s per capita monthly income. The “audience theory” of drama is the most representative view of the French theorist F. Sasser in the discussion of the essence of drama after the 19th century, according to literature [24] research. Sa Sai believes that all drama works, no matter what kind, are for the audience, which is the necessary condition of drama and the essence of drama. When discussing how to open up the market for excellent dramas, literature [25] points out that audience awareness and aesthetic education in the drama production process, as core factors of drama creation motivation and purpose, are two factors that should not be overlooked.
Based on industrial data mining, this paper studies the positioning and market selection of opera performance art. No matter in the West or the East, they all tell the same truth: the audience is an integral part of drama. The aesthetic power contained in drama arouses the psychological activities of the audience, mobilizes the ability of perception, emotion, imagination, and understanding, understands, and observes this aesthetic experience, resulting in aesthetic feeling. This conclusion has been an indisputable fact in the theory and practice of early drama and contemporary drama.
3. Principle and Model of Industrial Data Mining
Nowadays, with the wide application of industrial database warehouse system and the rapid development of information technology, the amount of data accumulated by people has increased dramatically, and the data scale of the system has reached the level of trillions of bytes. Industrial data mining technology is the data processing technology developed to meet this need, and it shows great vitality. The value of industrial data mining method for the artistic positioning and market selection of opera performances is mainly reflected in that the market positioning and artistic positioning of opera performances can be realized through data mining. Industrial data mining is a process of extracting hidden and unknown information and knowledge from a large number of incomplete, noisy, fuzzy, and random practical application data. Industrial data mining query conditions or tasks provide attention information and search functions. In addition, this module also allows users to access databases and data warehouses, browse data structures, evaluate patterns of knowledge mining, and visualize knowledge output patterns through different forms, as shown in Figure 1.
At present, opera performance corresponds to different artistic positioning and market choice. Therefore, the rational positioning of opera performance and the formulation of targeted strategies are of great significance for the positioning of opera performance art and the development of market choice. A key research direction of industrial data mining is opera performance art positioning and market selection. At present, although some research has been done on the mining of multimedia data, time series data, and spatial geographic data, it is still far from the requirements of practical application. Therefore, this field will be one of the frontier fields of industrial data mining in the future.
The tasks of industrial data mining mainly include the following six aspects: association analysis, cluster analysis, classification, valuation, prediction, and deviation analysis.
① Correlation analysis
Association rules are a kind of important knowledge that can be found in array library. If there is some regularity between the values of two or more variables, it is called correlation. Association can be divided into simple association, time series association, and causal association.
② Cluster analysis
Clustering is to divide data into several categories according to similarity. The data in the same category are similar to each other, and the data in different categories are different. The purpose of clustering analysis is to collect data for classification on the basis of similarity.
③ Classification
Classification is to find out the conceptual description of a class, which represents the overall information of this kind of data, that is, the feature description of this class, and use these features to construct the model. The process of classification is generally divided into two steps. First, select the training set that has been classified from the data, then use the technology of data mining classification on the training set to establish a classification model, and finally classify the unclassified data.
④ Valuation
The comparison of valuation is similar to that of classification, but the difference is that classification describes the output of discrete variables, while the value of data processed by valuation is continuous. The category of classification is a definite number, and the quantity of valuation is uncertain. Therefore, valuation can be used as the previous step of classification. Given some input data, the unknown values of continuous variables can be obtained by estimation and then classified according to preset boundary values.
Visual technology or other knowledge representation technology is used to provide users with the knowledge mined from data, so that users can more intuitively see the mining results and understand the mined knowledge more easily, as shown in Figure 2.
Each step in the process of industrial data mining is closely linked, and according to the preliminary mining results or interaction with users, the mining process needs to add the results or user feedback to the mining conditions, so as to further dig out meaningful information. Therefore, industrial data mining is a process that needs repeated iteration and revision. The purpose of industrial data mining is to find out all the rules that meet the minimum support and confidence from the transaction database. Its mining process mainly includes two steps: finding all large itemsets from the database, that is, finding all itemsets that meet the minimum support. Generate all industrial data mining according to frequent itemsets and minimum confidence. The basic model of industrial data mining is shown in Figure 3.
The main system overhead in the process of industrial data mining is concentrated in the first step. Therefore, various algorithms are also aimed at mining frequent itemsets. Due to the huge amount of data, it poses a high challenge to the efficiency and scalability of the algorithm. Based on the idea of vertical distribution, the industrial data mining algorithm first converts the transaction data in database into a matrix and then makes statistics. The basic concepts are as follows:
is a transaction record in database , and is specific project data.
Therefore, the support count of item is expressed as a formula.
The vector corresponding to each item is defined as
The cross product of item set is defined as
where ∧ is a logical AND operation, so the support count of 2-itemset is expressed as a formula.
The cross product of item set is defined as
Therefore, the support count of -itemset is expressed as a formula.
The sum of items of item for vectors can be calculated using the formula when calculating the support count of item . Instead of scanning all transaction records in the database again, it is only necessary to calculate the product of each vector according to the formula when calculating the support count of -itemset . The amount of calculation required for statistical support can be greatly reduced in this way, and the AND operation can be easily implemented in a high-speed computer.
Knowing two anchor points and with radio direction finding function and measuring the included angle and between the target node and , then
. The coordinates of the target node can be obtained by solving this equation.
4. The Development of Opera Performance Art Orientation and Market Choice
4.1. Art Orientation and Market Choice of Opera Performance Based on Industrial Data Mining
The most difficult aspect of developing opera art is figuring out how to get everyone to accept it as an art form. The media, as a new cultural communication force, now allows for the rebirth of opera art. To provide a decision-making basis, industrial data mining must extract potential opera performance art positioning and market selection valuable information or knowledge from a large number of noisy, incomplete, and fuzzy data. Business analysts must be familiar with business knowledge, data structure, mining algorithms, and analysis methods in order to effectively use data mining technology to achieve the final expected goal. A famous international tenor singer’s 2009 Beijing concert ticket price is divided into six grades in China, ranging from 380 yuan to 2000 yuan, with an average ticket price of nearly 1000 yuan. Similarly, industrial data mining is a continuous and repeated training process for opera performance art positioning and market selection. The final completion of the analysis task is inextricably linked to the use of intelligent, standardized, and process methods. Furthermore, it is difficult to sponsor; there are many complimentary tickets; only big brands and the number of performances per year are considered. The prices of tickets continue to rise, excluding those who truly want to see the show.
In practical application, aiming at different opera performance application fields and different opera performance mining projects, it is necessary to carry out correct artistic positioning and market selection and effective model setting and method implementation according to actual needs. 5A model and SEMMA model mainly emphasize the key links needed to realize the data mining process, but there is no clear and standardized process for the data mining process. The cultivation of the opera market should first be supported by the government. Love, love, hate, and even die for it. Lenin once said, “Without people’s feelings, there will never be and cannot be anyone’s pursuit of truth.” Of course, Lenin’s emotion is in a general sense, but this idea is also applicable to the aesthetic field. The existence of drama aesthetics is to meet people’s emotional needs, and the function of drama is also to act on people’s emotions. At present, the state’s encouraging policies for the cultivation of opera music market, especially the support for private companies, are insufficient.
Explain this process using industrial data mining: in the industrial data mining data warehouse, extract the valuable artistic positioning of opera performance and market selection of patterns and rules that can support decision-makers’ business decisions, such as which customers’ consumption behavior is similar, what is the offline because the audience for opera music in China is small, and production units rely on their personal experience and artistic understanding to make market judgments and blind investments; the risk of rehearsing a play is high. The degree of marketization of opera music is symbolized by the prosperity of private performance institutions. Therefore, we need to increase government support for private performance institutions. In the era of information explosion, industrial data mining, as a new research field, has a huge application space in the organic combination of artistic positioning and market selection and decision support in opera performance and customer relationship management in various industries. According to the function of industrial data mining, data mining technology can be applied to different fields and stages of opera performance art positioning and market selection of customer-centered enterprise decision analysis and management, so as to improve the customer relationship management ability of enterprises.
4.2. Experimental Results and Analysis
Three experiments were conducted on three opera houses, respectively. From 2014 to 2021, when opera house A was in 2011, the overall performance of this opera house still needed to rely on itself, but through exploration, it finally made alliance exchanges and cooperation with ten opera houses of the same type. There are nearly 300 outlets in the southwest area of the opera house B. At present, the art positioning and market selection have achieved effective coverage in Sichuan and Guizhou provinces. In the case of users’ needs, the opera house C and the related partners can achieve effective correspondence, which means that the art positioning and market selection of the opera house A are extensive, as shown in Figures 4–6.
The experimental results show that in the first experiment, the choice of the first opera house performance market aided the overall upward trend, peaking in 2018. Through market capacity analysis, which is the study of specific market segments joined by relevant enterprises in order to assess their strategic impact in a specific market, relevant resources and capabilities can meet the basic needs of market segments. The C opera house had the lowest trend in 2014. The foundation of supporting analysis is market segmentation. In the second experiment, the C opera house as a whole showed an upward trend, peaking in 2019. In 2015, the C opera house reached its lowest point. Opera house A generally showed an upward trend in the third experiment, while opera house C continued to show the lowest peak trend in 2015. The B opera house was in the midst of all three experiments. The rise and fall are not in sync. To conduct a supporting capability analysis, we must examine relevant segmentation elements and investigate the competitive situation of businesses in specific market segments. It can effectively determine whether the enterprise’s resources and capabilities can meet the basic needs of the market segment using such statistical data.
In order to reflect the improvement effect of industrial data mining in opera performance art positioning and market selection, this paper comprehensively compares industrial data mining based on vertical distribution algorithm, decision tree algorithm, and machine learning algorithm. Because the new algorithm uses interactive mining in the rule generation stage, and the mining rules are all strong association rules, the new algorithm will get fewer rules than the original algorithm, so the efficiency comparison with the old algorithm mainly focuses on the mining of frequent itemsets in the first step. In this paper, four experiments have been conducted, and 3000, 5000, 7000, 9000, and 11000 records have been extracted from the database, respectively. When the support degree is 30%, the comparison of the generation time of frequent itemsets between the old and new algorithms is shown in Figures 7–10.
As shown in Figure 7, the experimental results show that opera music is highly professional and belongs in the category of serious music. Because opera music is performed at a distance from the general public, the majority of those who attend are people who want to “understand” the music. The execution time of the industrial data mining algorithm is faster than that of the vertical distribution algorithm, decision tree algorithm, and machine learning algorithm when the support is the same and the number of markets is different. The performance of industrial data mining algorithms is improving as the data scale grows. Figure 8 shows that industrial data mining takes less time to execute than vertically distributed algorithms, decision tree algorithms, and machine learning algorithms when the data scale is the same and the support is different. Hoping for the “original” and “uncontaminated” added value of opera music will only hasten the loss of the original regeneration function and existence value. The basic connotation of opera music is a combination of openness and integration. It should be allowed to adapt to industrialization and urbanization and allow transformation, so that opera music can obtain a broad living space. The smaller the support, the greater the time difference between the two mining. As can be seen from Figure 9, under the conditions of the same data scale and different support, the execution time of industrial data mining is shorter than that of vertically distributed algorithms, decision tree algorithms, and machine learning algorithms. The smaller the support, the greater the time difference between the two mining. As can be seen from Figure 10, under the conditions of the same support and different market numbers, the execution time of industrial data mining algorithm is shorter than that of vertical distribution algorithm, decision tree algorithm, and machine learning algorithm. With the growth of data scale, the performance of industrial data mining algorithm is better. If we want opera music to adapt to the aesthetic taste of society and people, we must break the closed and semiclosed state, go out of the narrow world, and find a new development direction in the collision and intersection of eastern and western cultures.
5. Conclusions
The most difficult aspect of developing opera art is finding a way for everyone to accept opera as an artistic form. Today, the media, as a new form of cultural communication, allows for the revival of opera. Dramatic times in the new period are characterized by audience awareness and aesthetic education. It avoids randomness and rigidity in the drama growth process, intentionally strengthens and fully releases drama’s noumenon energy, and propels drama into the virtuous circle area. The differentiation of aesthetic needs of consumers is the result of market positioning of opera performance products based on industrial data mining in this paper, and it is a comprehensive concept that includes cultural level positioning, artistic style positioning, and artistic expression positioning. Only by accurately positioning opera performance products on the market can we make full preparations for future targeted publicity and marketing, as well as achieve market success for opera performance products. Only in this way will industrial data mining dramas be able to accurately position themselves in the market. In practical application, it is necessary to carry out correct artistic positioning and market selection, as well as effective model setting and method implementation according to actual needs, in order to target different opera performance application fields and different opera performance mining projects.
Data Availability
The data used to support the findings of this study are included within the article.
Conflicts of Interest
All the authors do not have any possible conflicts of interest.