Research on the Optimization Path of Art and Design Product Development and Creativity in Cultural Tourism Industry Based on Genetic Algorithm

Tourism industry enterprises or related departments as the main body of integration. The tourism industry sector to take advantage of its own tourism resources, in-depth penetration and development to the field of culture and art, and provide the market with tourism products containing cultural content, thus giving rise to the phenomenon of “tourism industry literature and art” [1-3]. In the case of the tourism industry or related sectors as the integration of the main body, to promote the traditional tourism products rely solely on the provision of natural resources or humanistic landscapes, the construction of humanistic scenic spots, and provide tourists with humanistic scenic spots of large-scale live performances of cultural and artistic products [4-6].

It makes tourism products literary and artistic, and also prompts cultural and artistic products to make full use of tourism resources and show their unique charm. With the development of economic globalization, cultural and creative industries are developing rapidly, and cultural and creative products with culture as the connotation and products as the carrier are increasingly favored by the public, and cultural and creative industries are gradually becoming one of the emerging industries with the most development potential [7-10]. Cultural and creative industry is a new type of industry that arises in the background of economic globalization and takes creation and innovation as its core [11-12]. It is an industrial form integrating culture, knowledge, creativity and technology elements, and has been widely concerned and highly valued both at home and abroad in recent years [13-14].

Art product design embodies creativity from the aspect of life vitality, often favoring lively and vivid, flexible and changing styles, and paying attention to evocation, charm, style, etc., all of which are signs of active life and beauty [15-16]. Designers look for design inspiration from natural life, based on the form of natural things, seize the characteristic elements of life and vitality in things, and apply them to art product design, which can better show the vivid and flexible interest [17-19].

The study designed a product development process model by combining genetic algorithm and brainstorming method. The model realizes product development through three stages: problem construction, automatic solution and decision making. Using CBD technology, the developed product styling-related design DNA elements are classified into five aspects: function, behavior, culture, emotion, and construction method. The multi-objective optimization model of product styling-related design DNA elements is constructed, and the method of genetic algorithm’s adaptive function is adopted to seek the local optimal solution first, and then the overall optimal solution for the optimization of product creativity. Practical analysis is carried out through specific cases to explore whether the method of this paper can save development time and cost as well as the convergence effect of the algorithm in the process of creative optimization.

2

Method

2.1

Development of art and design products in the cultural tourism industry

2.1.1

Brainstorming

Brainstorming (BS) is a method that allows inspiration to flow. The basic idea is to organize people with active minds in different fields to propose design themes and encourage them to come up with objective ideas or thoughts and stipulate that they are only allowed to add to the ideas of others but not to negate or criticize them, aiming to form a union of new ideas. Often through this method to get the information is the most original information and inspiration, and will be these messy information through the designers to effectively integrate and reorganize, and then use their own professional knowledge to analyze and filter, and ultimately get more innovative design ideas [20].

2.1.2

Application of Genetic Algorithm for Brainstorming Approach to Product Development

1)

Genetic Algorithm

Genetic algorithm is proposed through the study of biological evolutionary laws, which is an iterative adaptive probabilistic search algorithm. The process of genetic algorithm can be divided into several steps: first of all, the generation of the initial population, this process is the size of the population randomly generated, followed by the generation of the initial population needs to go through the screening process, through the “cross-selection”, “mutation” and other genetic operations, so that the new population will be generated, at the end of the process, the quality genes of the population, and then the new population will be generated. At the end of the process, populations with high-quality genes are retained and inherited, while populations with inferior genes are gradually eliminated.

There are three primary operators in the genetic algorithm: That is, “selection operator” (SO), “mutation operator” (MO), and “crossover operator” (CO) The three operational operators of genetic algorithms make them more efficient and faster than other conventional algorithms in solving complex solved, non-threaded problems more efficient and faster than other conventional algorithms [21].

(1)

Starting state: set up the running parameters, which include “population size”, “crossover probability”, “mutation probability”, “maximum number of genetic Maximum number of hereditary generations” and so on.

(2)

Encoding initial population: random individuals are generated by the computer to establish the corresponding starting population, and each encoded random individual is used as an alternative to the optimal population in the scheme pool.

(3)

Construct the fitness function: establish the fitness function of each individual through the formula.

(4)

Determine the termination condition: if the evolution result satisfies this termination condition (e.g., individual fitness value exceeds the set threshold, exceeds the maximum number of iterations, etc.), the computation stops and the high-quality population individual solution is obtained, and if this termination condition is not met, step 5 is repeated.

(5)

Selection, crossover, mutation genetic operations: if the fitness value of an individual is relatively high, then the system will retain it as a sample for the next evolution, there will be N such individuals, and all these individuals will be subjected to genetic operations such as crossover, mutation, etc., and then subsequently return to step 4.

2)

The basic principle of BS method for product development using genetic algorithm

The application methods of genetic algorithm in the development of art design products in the cultural tourism industry mainly include conceptual design, shape optimization, data fitting, reverse engineering, institutional design, etc. The BS method is an important stage in the early stage of conceptual design, and it has three basic processes: divergence, convergence and adjustment. Divergence is a process of finding as many possibilities for a solution as possible without constraints, a process that is similar in nature to the way genetic algorithms randomly generate individuals of a population through cross recombination. The difference is that divergence is the unconstrained free conception of the human brain, while the random generation of population individuals by genetic algorithms is carried out under certain constraints, and the constraints are mainly formulated to exclude obviously unreasonable solutions beforehand, in order to reduce the generation rate of ineffective solutions and to improve the search efficiency. Convergence is an evaluation-based solution selection process, which is a typical feature of product conceptual design and one of the main ways of genetic algorithm solution. Factors considered in product design and auxiliary information can be changed into evaluation functions in a quantized form to achieve the goal of controlling the evolutionary direction of the solution population. Adjustment is a critical stage in obtaining the final conceptual solution, which in the brainstorming method is decided by all members of the design team after careful analysis and discussion. In conventional genetic algorithms, tuning is achieved through mutation. The main purpose of mutation is to increase the search range and obtain diversity of solutions rather than to determine the final solution, but the direction of mutation can be determined algorithmically by combining the nature of the evaluation function with a view to evolving the solution in the direction of optimality. In addition, genetic algorithms have the distinct advantage that the search process can be interrupted at any time and the population decoded for review by the user. If the user inputs evaluation and selection information at this point, the direction of evolution of the solution population can be artificially controlled, which is an advantage when dealing with vague, difficult-to-quantify design concepts that fall within the realm of the designer’s personal experience.

3)

Product development process model based on genetic algorithm

In this paper, the brainstorming process is divided into 4 stages, namely, divergence, convergence, improvement and finalization, which correspond to the 5 sub-processes of the genetic algorithm design process, such as random search, solution evaluation, recombination/mutation, solution decoding and interaction selection, respectively. In this paper, the genetic algorithm operation process that realizes the above 5 sub-processes is defined as a 10-tuple consisting of 10 basic functional operators: 1 $S G A = (X, C, F, Φ, Γ, Ψ, T, D, S)$

In the formula:

$X$ --Individual scheme construction operator (with individual coding).

$C$ --Constraint construction operators (with solution space expressions).

$G$ --Population maintenance operator, which handles the generation and replacement of populations.

$F$ --Individual evaluation operator that calculates the fitness value for each individual in the population.

$Φ$ --selection operator that determines the parent individual of the next generation in the population.

$Γ$ --Recombination of the first son, which determines the way in which the parent individual recombines to get the child individual.

$Ψ$ --variance operator that determines the probability and strength of the parent’s individual variance.

$T$ --The optimization-seeking control operator, which determines the search direction and termination conditions of the algorithm.

$D$ --Decoding operator that transforms the individual encoding of a scheme into a product form model.

$S$ --Interaction selection operator that handles the results of the designer’s interaction selection of the decoding scheme.

The general process of solving art design product solutions in the cultural tourism industry is divided into three phases: problem building, automatic solution and decision making. The problem building stage establishes the genotype and objective evaluation function of the design problem through user interaction and defines the effective solution space. The automatic solution phase is the process of manipulating the genotype within the solution space to evolve the design problem in the desired direction through the constraints of the evaluation function and generating a number of near-optimal solutions to be provided to the user. The decision-making phase is based on the results of the software’s work to select the final solution through user interaction with the software, or the user decides to carry out the next round of search until a satisfactory solution is obtained.

2.2

Analysis of product styling related design DNA elements

2.2.1

Classification of product styling related design DNA elements

CBD technology is used to incorporate product styling related design elements into the retrieval and reuse of cases. The analysis and application of product styling design elements based on CBD is shown in Figure 1. Product styling design DNA elements are divided into five aspects, including function, behavior, culture, emotion and construction method. The construction method is further divided into three aspects: design concept, compositional primitives and compositional rules. Under the role of the design concept of the construction method, the function, behavior, culture and emotion of the purpose are selected, and then the modeling elements corresponding to the function, behavior, culture and emotion are extracted as the compositional primitives of the construction method, and then rearranged and combined through the compositional rules of the construction method to reconstruct the overall shape of the product.

2.2.2

Expression of design DNA elements related to product modeling

For the expression of product styling design, it includes two aspects, on the one hand, the conceptual description of product styling, i.e. the content of the text. On the other hand, it is related to the composition of the product modeling form, i.e. the product modeling itself, which is composed of various modeling elements. The intrinsic connection of design elements related to product modeling is shown in Figure 2.

For a cultural product example, the product styling concept description set $P D$ is expressed as: $P D = (F D, B D, C D, K D, S D)$ .

1)

The product function set is denoted as $F D$ , the function-related styling elements are denoted as $f$ , and the product function set $F D$ is expressed in the form of a gene tree as: 2 $F D = t r e e (F D_{i j}), i = 1, 2, ..., n; j = 1, 2, ..., m;$

$F D_{i j}$ can represent the $j$ rd functional gene under the $i$ nd sub-function of the product of the class (sample), $n$ is the total number of primary sub-function sets in the function set, and $m$ is the total number of secondary sub-functions in the sub-function set. The product function set tree structure is shown in Figure 3.

2)

Denote the set of product usage behavior $l$ interaction patterns as $B D$ , consisting of behavior vector $V$ and object $O$ , $B D : V \to O$ . Related styling elements as $b$ , and the set of usage behaviors $B D = {B D_{1}, B D_{2}, ..., B D_{m}}$ . Set of behavior-related styling elements $b = {b_{1}, b_{2}, ..., b_{n}}$ .

3)

Record the set of cultural features as $C D$ , the set of culturally relevant styling elements as $c$ , the set of cultural features as $C D = {C D_{1}, C D_{2}, ..., C D_{m}}$ , and the set of culturally relevant styling elements as $c = {c_{1}, c_{2}, ..., c_{n}}$ .

4)

Record the set of emotional imagery as $K D$ , the emotion-related modeling elements as $k$ , the set of emotional imagery as $K D = {K D_{1}, K D_{2}, L, K D_{m}}$ , and the set of emotion-related modeling elements as $k = {k_{1}, k_{2}, L, k_{n}}$ .

5)

Denote the set of constructive methods as $S D$ , the design concept as $T$ , the compositional primitives as $E$ , and the compositional rules as $R$ , $S D = (T, E, R)$ . Design Concept $T = {T_{1}, T_{2}, ..., T_{n}}$ . Compositional Primitives $E = {E_{1}, E_{2}, ..., E_{n}}$ . Compositional Rules $R = {R_{1}, R_{2}, ..., R_{n}}$ .

2.3

Creative optimization path of art design products

2.3.1

Adaptation function design

Since this paper divides the design elements related to product styling into five aspects: function, behavior, culture, emotion and constructive method, the method of genetic algorithm’s adaptive function is used here to find the local optimal solution first and then the overall optimal solution.

1)

Initial population

The initial population is generated by the following methods: random generation, similar case retrieval, designers adding modern product cases and cultural artifact product cases. The size of the initial population is 20~100.

2)

Adaptation function setting

Since there are 5 groups of design elements related to product modeling, the weight coefficient method is used to perform multi-objective optimization on the constituent elements of product modeling, 5 groups of sub-objective functions are set and the corresponding weight coefficients are set, and finally, the values of the 5 groups of functions are added up to be the total adaptability of the product modeling.

Represent the sub-objective value of the genetic algorithm by satisfaction $M$ , which represents the mean square difference between a certain styling-related design element matrix $Y$ of a case and the user’s target demand matrix of that aspect of styling-related design element $R$ , i.e., $M = \sqrt{\sum_{k = 1}^{n} w_{k} {(Y_{k} - R_{k})}^{2}}$ , $R_{k}$ are the corresponding values in the target demand matrix of styling-related design element. The daily scale function $M$ is directly used as the fitness function of the genetic algorithm GA, and the smaller the target value is, the better the combination program is. The expression of the fitness function is: 3 $F (X_{m}) = \sqrt{\sum_{k = 1}^{n} w_{k} {(Y_{k} - R_{k})}^{2}}$ where $X_{m}$ denotes the $m$ nd individual in the population.

The expression for the total fitness of the product modeling is: 4 $μ (f (x)) = \sum_{i = 1}^{5} w_{i} f_{i} (x)$ $f_{i} (x)$ is the sub-objective function with weights $w_{i} \geq 0$ , respectively, of the importance $(i = 1, 2, ..., 5)$ of the five modeling-related elements, and the sum of the weights is 1: 5 $\sum_{i = 1}^{s} w_{i} = 1$

Functional fitness is the degree to which a product’s feature set satisfies the user’s functional requirements, expressed as: 6 $f (F D (x)) = \sum_{j = 1}^{n} a_{j} f_{j} (x) / n, j = 1, 2, ..., n$ $f (F D (\bar{x}))$ is the functional fitness of the feature set of the product. $f_{j} (\bar{x})$ is the functional fitness of each functional feature element. $a_{j} = [0, 1]$ indicates the presence or absence of the functional feature element, $a_{j} = 1$ indicates the presence of the functional feature element and vice versa. $\bar{x} = {[x_{1}, x_{2}, ..., x_{p}]}^{T}$ indicates the feature element that constrains the functional fitness of this product.

Behavioral fitness is the degree of satisfaction of the product behavior set to the user’s behavioral needs, which is denoted as $f (B D (\bar{x}))$ , cultural fitness is the degree of satisfaction of the product’s cultural characteristics to the user’s cultural needs, which is denoted as $f (C D (\bar{x}))$ , and affective fitness is the degree of satisfaction of the product’s affective intention to the user’s perceptual needs, which is denoted as $f (K D (\bar{x}))$ , and their mathematical expressions are the same as Equation (6).

Constructive adaptation is the degree of satisfaction of the product constructive set to the user’s needs, and its functional expression is: 7 $\begin{matrix} f (S D (\bar{x})) = \sum_{t = 1}^{n} [a_{t} d_{t} T_{t} (\bar{x}) + b_{t} d_{t} E_{t} (\bar{x}) + c_{t} d_{t} R_{t} (\bar{x})] / n \\ t = 1, 2, ..., n \end{matrix}$ $f (S D (\bar{x}))$ is the constructive method adaptation of the product constructive method set. $T_{t} (\bar{x})$ is the design concept adaptation degree. ${\bar{E}}_{t} (\bar{x})$ is the composition primitive adaptation degree. $R_{t} (\bar{x})$ is the composition rule adaptation degree. $a_{t}, b_{t}, c_{t}$ is the weight coefficient of $T_{t} (\bar{x}), E_{t} (\bar{x})$ and $R_{t} (\bar{x})$ , and $a_{t} + b_{t} + c_{t} = 1, d_{t} = [0, 1]$ indicates the existence or non-existence of the construction method feature element, $d_{t} = 1$ indicates the existence of the construction method feature element, and vice versa. $\bar{z} = {[z_{1}, z_{2}, ..., z_{q}]}^{T}$ denotes the feature element that constrains the product design concept, composition primitives and composition rule adaptation.

2.3.2

Selection operations

Evaluating the degree of satisfaction of product styling to the user’s styling needs requires a comprehensive consideration of the product’s functional, behavioral, cultural, emotional, and constructive method factors, so the total adaptability of each product styling is: 8 $\begin{matrix} G (x) = w_{1} f (F D (x)) + w_{2} f (B D (x)) + w_{3} f (C D (x)) \\ + w_{4} f (K D (x)) + w_{5} f (S D (x)); \end{matrix}$ $w_{1} + w_{2} + w_{3} + w_{4} + w_{5} = 1$ of them.

Set the initial evolution algebra $t = 0$ , set the maximum evolution algebra $T$ , $T \in [0, 100]$ , in the case library, select $N$ cases as the initial population $P (0)$ , select $N_{1}$ modern products and $N_{2}$ cultural artifacts products, which can be selected by designers based on their experience or randomly. $N = N_{1} + N_{2}, N_{1} \in [10, 50], N_{2} \in [10, 50]$ . When the evolution algebra reaches the maximum value of $T$ , then the evolution stops. Calculate the fitness of each product shape in population $P$ and apply the selection operator to the population. The optimized product styling elements are directly inherited by the selection operator, or new product styling elements are formed by cross recombination and inherited to the next generation of products.

Using the fitness proportion method, the number of product styling elements involved in the reorganization is set to $n$ . The probability of selecting a product styling element with fitness $f_{k}$ is: 9 $p_{k} = \sum_{j = 1}^{k} f_{j}, k = 1, 2, ..., n;$

The cumulative selection probability of a particular product modeling element is then: 10 $q_{k} = \sum_{j = 1}^{k} p_{j}, k = 1, 2, ..., n$

Using the roulette wheel selection method, a roulette wheel is designed to select the styling elements of the products according to the above probabilities. The roulette wheel is rotated $n$ time, and each time a product modeling element set is selected and placed into the set of modeling elements of the products to be crossed $S$ . At the end of the selection operation, there will be $n$ styling element sets in the set of elements to be intersected, and the element set with a high selection probability will be repeatedly selected, while the element set with a low selection probability will be excluded from the set of elements to be intersected.

3

Results and discussion

3.1

Case Studies

3.1.1

Design objectives

This design practice takes Qiantang River as the main research object, takes cultural and creative products as the carrier, takes culture as the soul, takes creativity as the support, bases on the cultural resources and regional characteristics of Qiantang River, through the product development and creativity optimization based on genetic algorithms, designs the tourism cultural and creative products which are both aesthetic, functional, innovative and emotional.

3.1.2

Design orientation

1)

Audience Positioning

Through the preliminary questionnaire research, the user groups of Qiantang River tourism cultural and creative products are divided into three categories, which are literary type (18-25 years old), curiosity type (26-30 years old), and pragmatic type (41-50 years old). The data shows that the young group of 18-30 years old is the main consumer group, while the middle-aged group of 41-50 years old is the secondary consumer group. Therefore, the audience of this Qiantang River tourism cultural and creative product design is positioned as the young group of 18-30 years old, including school students and office workers entering the workplace. These groups are young and open-minded, good at accepting new things, and have a strong willingness to buy products. As a new generation of young consumers, they pay more attention to the aesthetics, innovativeness and functionality of the products, and are more inclined to cultural and creative products with a sense of design and cultural connotation. Therefore, in the process of designing cultural and creative products for Qiantang River tourism, it is necessary to further think about the aesthetic tendency and demand preference of such groups, and design cultural and creative products in line with young people’s aesthetic demand.

2)

Product Positioning

Product positioning is often affected by consumers’ age, gender and other factors. According to the research data above, the majority of consumers are generally keen on stationery and daily necessities cultural and creative products. Therefore, the positioning of Qiantang River tourism creative products mainly focuses on series and practical stationery and daily necessities, which on the one hand can show the cultural characteristics of the Qiantang River and increase the cultural added value of the products, and on the other hand closely link the Qiantang River culture with daily necessities, which increases the practicality of the products and promotes the diversified dissemination of the Qiantang River culture.

3)

Style Positioning

This project further enriches the protection and inheritance of Qiantang River culture through the design of “Qiantang Gift” tourism cultural and creative products. Therefore, in terms of style positioning, with the characteristics of youthfulness, trendiness and fun as the core, it strengthens the creative design, integrates the spiritual connotation of Qiantang River culture, and makes it the biggest highlight and selling point of the product, so that consumers can feel the charm of Qiantang River culture.

3.2

The effect of art design product development in cultural tourism industry

The product development process model based on genetic algorithm designed above is used to develop Qiantang River tourism cultural and creative products. Taking the development of 30 cultural and creative products as an example, the product development method of this paper is compared with the traditional method in terms of development time and development cost, respectively. The product development time and cost comparisons corresponding to different methods are shown in Fig. 4, with (a)~(b) indicating the comparisons of development time and development cost, respectively. The average time and cost of developing 30 cultural and creative products by traditional methods require 1036h and 1.69 million yuan, respectively. The product development process model based on genetic algorithm only needs 933h and 1.33 million yuan, which effectively saves development time and cost.

3.3

Creative optimization effect of art design products in cultural tourism industry

A genetic algorithm is used to optimize the creativity of a Qiantang River tourism cultural and creative product. The iterative trend of this cultural and creative product after creative optimization is shown in Fig. 5. (a), (b) and (c) represent the iteration process of development time, development cost and change risk, respectively. The development time, development cost and change risk are stabilized after 17, 15 and 23 iterations, respectively, indicating that the algorithm converges well.

3.4

Overall evaluation

This chapter constructs the evaluation index system of cultural and creative products, and evaluates 30 Qiantang River tourism cultural and creative products that are developed and creatively optimized under genetic algorithm. The evaluation index system is shown in Table 1. According to the process of cultural and creative product development, the elements of cultural and creative product development can be categorized into cultural elements, technological elements, creative elements, aesthetic elements, interactive elements, experiential elements, and economic elements, and their contents are expressed by applying the sense and quality of the five elements, and the 30 Qiantang River tourism cultural and creative products are evaluated in five aspects, namely, charm, aesthetics, creativity, engineering, and sophistication, respectively.

Table 1.

The product evaluation index system

Evaluation dimension	Evaluation factor
Charm (A)	Cultural connotation (A1)
	Impressive (A2)
	It has the age of fashion (A3)
Aesthetic feeling (B)	Aesthetic feeling (B1)
	Aesthetic feeling (B2)
	Make a sense of pleasure (B3)
Originality (C)	Creative approach (C1)
	Feature (C2)
	Design ingenuity (C3)
Engineering (D)	Technology (D1)
	Series combination (D2)
	Utility and durability (D3)
Delicacy (E)	Experience good (E1)
	Selling multivariate (E2)
	Broad coverage (E3)

The study used semantic differential psychometrics for rating. Its determination of psychological feelings through linguistic scales is the most commonly used method for setting sensory scales in psychology. It believes that the judgment of evaluation should not be too much, and it is generally appropriate to set the evaluation scale of 5-7 levels, and it is most reasonable to take 5 levels, and according to the strength of the evaluation factor, it adopts five levels of rating scale of -2 (very little), -1 (less), 0 (general), 1 (more), 2 (very much) [22]. When evaluating, set the evaluation factors to relative adjective pairs. For example, if “cultural connotation” is set to “have cultural connotation” and “do not have cultural connotation”, five different evaluation scales are set according to the strength of their content.

The selection of evaluation subjects is chosen to be as comprehensive as possible, using a mix of professionals and non-professionals to survey the personnel. The number of evaluators is usually set at 20-50 people, and if the situation permits the sample size chosen is as large as possible. In addition, in order to reduce the impact of other factors on the evaluation activities, it is required to participate in the evaluation site will not appear biased information, in order to exclude as much as possible the influence and interference of other factors. Secondly, the evaluation process is to first introduce the object and method of evaluation to the evaluators, help the personnel to understand the meaning of the relevant indicators, the requirements of different sub-evaluation levels, explain the specific meaning of the sensory elements and evaluation factors to fill in the form, and introduce the specifics of the evaluation samples one by one, the method of experience, and other elements, and to carry out multiple rounds of scoring and evaluation of the personnel to reduce the actual error.

In this paper, 45 people were selected to evaluate 30 Qiantang River tourism cultural and creative products with 5 levels. The evaluation results are shown in Figure 6. The evaluation factors of each dimension are more in 1 (more) and 2 (very much). In the creativity dimension, the proportion of people giving “very much” grade is 49.3%, which is the highest proportion. It shows that the method of this paper can achieve the effect of product creativity optimization.

4

Conclusion

The research on the product development process model designed based on genetic algorithm and brainstorming method only requires 933h and 1.33 million yuan to develop 30 Qiantang River tourism cultural and creative products, and 1036h and 1.69 million yuan based on traditional methods. The method in this paper saves 103h and 360,000 yuan in development time and cost, respectively.

The adaptive function of genetic algorithm is used to carry out the local optimal solution for the product function, behavior, culture, emotion and construction method first, and then the overall optimal solution. After the creative optimization, the development time, development cost and change risk tend to be stable after 17, 15 and 23 iterations respectively, which indicates that the method in this paper has a good convergence effect when performing creative optimization.

The semantic difference method is used to evaluate the developed creative products in five dimensions: charm, aesthetics, creativity, engineering, and refinement. Under the creativity dimension, the percentage of people who gave the rating of “very much” reached 49.3%. The evaluation obtained after product creativity optimization under the method of this paper is more satisfactory.

Language:: English

Publication timeframe:: 1 times per year
Journal Subjects:: Life Sciences, Life Sciences, other, Mathematics, Applied Mathematics, General Mathematics, Physics, Physics, other

Journal RSS Feed

Research on the Optimization Path of Art and Design Product Development and Creativity in Cultural Tourism Industry Based on Genetic Algorithm

Qiang Fu

Published Online: Sep 24, 2025

Received: Jan 06, 2025

Accepted: Apr 29, 2025

DOI: https://doi.org/10.2478/amns-2025-0982

KeywordsGenetic algorithm, Brainstorming, Adaptive function, DNA elements, Product development

© 2025 Qiang Fu, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Keywords
Genetic algorithm, Brainstorming, Adaptive function, DNA elements, Product development