Construction and Analysis of Employment Structure System Based on Artificial Intelligence and Its Influencing Factors

In today's era of increasingly fierce corporate competition, technology has undoubtedly become an important component of corporate competitiveness. With the development of computers, the gradual maturity of technologies such as big data and automation has led to the emergence of new technologies related to artificial intelligence. On one hand, artificial intelligence reduces replaceable positions like assembly line jobs through job displacement; on the other hand, it increases employment by creating irreplaceable positions such as data scientists and maintenance personnel. Moreover, artificial intelligence also influences people's consumption and employment concepts. Some Western countries have experienced noticeable changes in the labor force employment structure while using artificial intelligence and other technologies for industrial automation and intelligence transformation.

As one of the world's major economic powers and the largest developing country, China should actively seize opportunities and firmly grasp the dividends of the era brought by high-tech technologies such as artificial intelligence. The development and application of artificial intelligence technology can help address issues like labor shortages and rising labor costs caused by an aging population, reset industrial layouts, enhance productivity levels, and promote new economic development. However, it will also change employment methods. Like previous technological advancements, artificial intelligence technology acts as a double-edged sword, creating job opportunities while also replacing labor positions during its development, thus changing the total employment volume.

However, everything has two sides. While artificial intelligence drives socioeconomic transformation, it also exerts a certain impact on the labor employment market. Currently, China's economic focus is shifting from pursuing high-speed growth to achieving high-quality development. Therefore, with the continuous rise in corporate labor costs, "machine replacing humans" can improve the efficiency and economic benefits of enterprises, serving as an important means for companies to enhance their competitiveness. Based on this, the structure of China's labor employment will inevitably be affected.

To further seize the new opportunities brought by this technological revolution, the Party and the state have given high attention to the development of artificial intelligence, issuing a number of related policies in recent years. During the COVID-19 pandemic, enterprises and institutions with higher levels of AI technology utilization were able to resume normal operations more quickly, stabilizing the country's economic operation and development, fully demonstrating this strategy. The integration of AI technology into the real economy has improved traditional industries, promoted the development of new industries, fostered new industrial models, and strengthened both the production and consumption ends.

First, studying the employment effects of AI development can draw more attention to the advancement of AI technology. China, as a populous country, considers full employment of its citizens one of the state's responsibilities, yet the employment situation has always been relatively severe. In recent years, the phenomenon of population aging in China has continued to worsen. Meanwhile, AI technology has permeated all walks of life and has been elevated to the level of national strategic development. During its application, it will absorb a large number of highly educated, high-skilled workers and create many new positions. However, it will also replace a significant amount of medium-to-low skilled labor. Therefore, researching the impact of AI development on labor force employment and proposing targeted policy recommendations based on these impacts is of great practical significance for promoting AI development and formulating employment policies.

Secondly, the use of AI technology can both promote and inhibit employment. Studying the impact of AI development on labor force employment can clarify the relationship between AI development and labor force employment. On one hand, this helps people to positively view the active role that AI development plays in labor force employment, reducing panic about AI replacing human jobs. It also highlights the need for individuals to enhance their own knowledge and skill learning as AI replaces low-skilled labor positions. On the other hand, it assists the state in scientifically assessing the impact of AI development on labor force employment, preparing for the new round of technological revolution in advance by effectively allocating labor resources. This has important guiding significance for China's AI development to favor comprehensive economic development.

2

Research Work

The "14th Five-Year Plan" and the 2035 Long-Range Objectives Outline proposed by the national government sets forth the long-term goal of building a strong country in education, listing the "construction of a high-quality education system" as one of the tasks for the "14th Five-Year Plan" period. Constructing a high-quality employment service system in higher education institutions is an integral part of building a high-quality education system. It is also an objective requirement for implementing the task of cultivating virtue and nurturing talent, enhancing the quality of talent cultivation, and serving high-quality development. The construction of China's high-quality employment service system has gone through important stages of development from nothing to something, and then from something to excellence. Currently, there are still practical issues such as insufficient professionalism, relevance, and effectiveness. Under the context of the new era, promoting high-quality employment requires setting construction goals of "comprehensive, professional, precise, and high-quality" and accelerating the construction of an "integrated" employment service system. The realistic significance of constructing employment guidance and service systems in higher education institutions is discussed, followed by an exposition on the practical challenges faced in constructing these systems. Finally, optimization strategies for constructing employment guidance and service systems in higher education institutions are proposed, including establishing an integrated employment service philosophy, building a specialized employment guidance team, exploring refined employment guidance methods, establishing an information-based employment service platform, creating modularized employment guidance courses, and providing empathetic employment psychological counseling. Vocational colleges should actively leverage their own advantages to improve the employment guidance service system for college students, facilitating smooth employment after graduation. This article explains the necessity of constructing an employment guidance service system in vocational colleges and summarizes a series of issues encountered during the construction process. It points out that there are problems with the current employment guidance for college students in vocational colleges, such as structural imbalance in mechanisms, short-sightedness and utilitarian tendencies in employment guidance work, and insufficient personalization and accuracy in guidance. The article also conducts a deep analysis of the causes of these problems and proposes specific strategies for the construction and improvement of the employment guidance service system for college students in vocational colleges [3]. Strengthening employment-first policies, improving employment promotion mechanisms, and promoting high-quality and adequate employment have become an important strategic task in the modernization process of China. From a national perspective, governments at all levels are actively promoting various forms of employment support and incentive policies, which undoubtedly bring benefits to the people. At the same time, addressing employment issues also requires in-depth thinking and effective responses [4].

In recent years, college students have faced a severe employment situation. Against this backdrop, constructing a precise employment guidance system based on database analysis would help improve the employment quality and competitiveness of university graduates. Based on an analysis of the current employment situation for university graduates, and according to the definition of a precise employment guidance system, strategies for building such a system include establishing a large database of student information, enriching the allocation of career guidance personnel, and promoting the systematic improvement of career courses [5]. How to fully leverage the talent resource advantages of university graduates is a challenge faced by higher education institutions in nurturing employment in the new era. This article deeply analyzes the value implications and core tasks of employment education in colleges under the new era context, proposing five principles that must be adhered to in constructing an employment education system: directionality, subjectivity, developmental nature, practicality, and collaboration; it also outlines four aspects for building an employment education system: value leadership throughout the entire training process, enhancing coordination and cooperation to form a collective educational force, multidimensional integration to promote a gradual deepening of employment from cognition to action, and strengthening investigation and tracking to form a feedback loop [6]. Employment is a significant reflection of the effectiveness of talent cultivation in higher education institutions. From the perspective of serving local economic development, this article constructs a more focused and effective, quantifiable, and comparable evaluation system for graduate employment quality based on the political theory of higher education, which serves as a beneficial supplement to existing evaluation systems. Through empirical testing, the article specifically proposes suggestions such as building a diversified dual-promotion "ideals and beliefs+" course ideological and political education model, establishing an outcome-oriented "integration+" enterprise introduction into teaching model, and drawing a "competence acquisition" oriented talent cultivation "competence map". These initiatives aim to promote a virtuous cycle of "admission-cultivation-employment-feedback", enhancing the alignment between higher education institutions' talent cultivation goals and industry needs [7]. The construction of an employment capability cultivation system for vocational colleges based on the PDCA (Plan-Do-Check-Act) cycle mode aims to enhance the employability of graduates from these institutions. This system includes four phases: planning, execution, checking, and acting. The planning phase requires in-depth research into the current employment situation of vocational college graduates, identifying employment needs and deficiencies, and formulating detailed plans for cultivating employment capabilities; the execution phase involves adjusting curriculum settings, teaching content, and methods according to the plan; the checking phase entails evaluating the effectiveness of teaching and activities, pinpointing issues; and the action phase involves implementing corresponding measures based on the results of the checks. This system can effectively improve the employability of vocational college graduates and alleviate current employment problems [8].

Based on the OBE (Outcomes-Based Education) philosophy, a course evaluation system for college students' employment and innovation and entrepreneurship is constructed to meet the needs of new-era educational evaluation reform. Through literature reviews and case analyses, the value and specific applications of the OBE philosophy in courses related to college students' employment and innovation and entrepreneurship are thoroughly explored. By employing logical analysis, the Delphi method, and mathematical statistics, an evaluation system scheme based on the OBE philosophy is proposed. The evaluation system is further refined by analyzing survey questionnaire results, ultimately forming an OBE-based evaluation system for college students' employment and innovation and entrepreneurship courses. This aims to improve the course evaluation system, promote students' all-around development, and enhance teaching quality [9]. With the popularization of higher education reform, the number of college graduates has gradually increased, making the employment situation for graduates increasingly severe. Using the AHP (Analytic Hierarchy Process) to evaluate factors influencing employability can provide effective guidance for enhancing the employability of vocational college students. According to the analysis results, vocational colleges should adopt measures such as strengthening social practice activities to highlight practical education outcomes, reinforcing employment capability guidance, emphasizing self-learning ability and quality improvement, and building a professional faculty team. These actions guide students toward high-quality employment and provide a basis for schools to adjust their talent cultivation plans [10]. College graduates are a valuable talent resource for the country and an important group served by employment services. Leveraging big data technology to enable precise employment matching for college graduates can improve the efficiency of talent selection by employers, maximize the value of talent resources, and better provide strong talent support for the comprehensive construction of a modern socialist country. There is ample room for improvement in using big data technology to empower precise employment services for college graduates in China. By analyzing four dimensions—basic scenarios, promotional scenarios, service scenarios, and regression scenarios—it is explored how modules such as mutual understanding between supply and demand sides, promotion and guidance for both parties, caring services for both sides, and feedback collection on employment data can be organically combined. This aims to effectively promote the construction of a precise employment service system for college graduates [11]. The current international situation is complex and changing, and the values of postgraduate students are gradually becoming more diversified. Many postgraduate students focus on personal short-term interests in their job choices and overlook social values. How to inspire contemporary postgraduate students' patriotic enthusiasm and enhance their defense consciousness, thereby encouraging postgraduates to choose defense-related employment, has become an important task for ideological and political workers in higher education institutions. A method for constructing a guidance system for postgraduate defense employment based on the SECI model is proposed, which fully leverages the collaborative education function of universities to guide students to understand defense, love defense, and choose defense-related careers. Practical verification shows that adopting an "explicit + implicit" educational guidance approach can effectively help postgraduate students understand the employment situation in defense sectors and precisely achieve defense employment [12]. The application of "Internet Plus" technology in the employment and entrepreneurship service systems of higher education institutions has accelerated their development, continuously increasing students' employment and entrepreneurship rates. This article describes the characteristics of university employment and entrepreneurship service systems under the "Internet Plus" context, addresses issues that arise in the construction of an ecological system for employment and entrepreneurship services, and analyzes specific solutions for strengthening related service systems, such as training services for students' employment and entrepreneurship. It aims to establish an ecological system beneficial for student employment and entrepreneurship, providing strong support for students' career planning [13]. The era of Educational Informatization 2.0 is a time when information technology is deeply integrated into all aspects of educational systems, presenting new requirements for employment guidance work in higher education institutions. The employment guidance system of universities should focus on building intelligent employment service platforms, creating multi-dimensional employment information databases, developing employment guidance courses based on new media, and conducting employment guidance activities using VR technology. Simultaneously, it should ensure organizational, institutional, talent, and financial guarantees to achieve high-quality and adequate employment for college students [14]. In the context of collaborative education environments, guidance services for college student employment and entrepreneurship exhibit three major trends: closer alignment with market demand for talent, deeper integration into the entire process of student growth, and full utilization of Internet information technologies. Currently, some universities still face issues such as imperfect collaborative guidance mechanisms, incomplete collaborative service platforms, unreasonable allocation of collaborative resources, and inadequate collaborative education. Therefore, universities must accelerate the construction and improvement of collaborative guidance mechanisms for employment and entrepreneurship, expand collaborative service paths, optimize collaborative service connections, and perfect the collaborative education system for employment and entrepreneurship [15]. Currently, artificial intelligence (AI) methods primarily embodied by robots have been put into production applications and are driving the process of industry automation. As the country actively responds to the accumulation of AI technology and technological capital, the impact of AI on employment has shown preliminary effects. The relative surplus population or continuous expansion of industrial reserve armies can lead to changes in labor structure, which is a unique phenomenon of mismatch between supply and demand in the labor market's job positions. In the social context where AI is gradually accepted and applied in production and life, enterprises have higher requirements for the quality of labor, such as possessing higher skills and stronger creativity. Meanwhile, the emergence of new industries creates additional demands for labor skills, such as flexible employment and digital labor. From Marx's perspective, technology as a form of productive force also represents relations of production. Under specific relations of production, the application of technical means exhibits clear class characteristics. The class nature of technology can be understood as its bias, with capitalists' adoption of new technologies manifesting in different classes within capitalist society. Workers under more advantageous capitalists would experience internal class differentiation first, which then influences production throughout society from individual enterprises. As a new means of productivity, AI brings about demonstration effects from pioneering enterprises and eventually becomes a general-purpose technology across the entire industry, leading to changes in relations of production. This section will mainly discuss how the influence of AI on human labor leads to changes in labor structure and further explore the relationship between AI and employment. The replacement of positions with different job natures by AI has heterogeneity. As a form of technological progress, AI can produce polarized or even unipolar impacts on the employment structure, especially in the field of skill distribution. With the increase in popular skilled occupations in the market, it can trigger a skill-biased path. Acemoglu proposed the theory of skill-biased technological change, which refers to how technological progress leads to increased demand for high technology and high-skilled talent simultaneously within enterprises. Technology and skilled talents exhibit complementary and interdependent structural distributions, reflecting that highly skilled workers will become increasingly favored in the market, becoming sought-after human resources. Medium-skilled and low-skilled workers will gradually be completely or partially replaced by AI, making polarization phenomena more severe. Even after technology develops to a certain extent, high-skilled workers may also be affected.

3

Analysis of the Theoretical Mechanisms of Artificial Intelligence

3.1

Bayesian analysis method

Let A1, A2, ... An is a disjoint event, that is, P (Ai ∩ Aj) = 0, i ≠ j; And P (A1 ∪ A2 ∪… ∪ Am.), let the inevitable event δ = A1 ∪ A2 ∪... ∪ Am P (δ) = 1. Thus, by deriving Equation 1: (1) $P (B) = P (B ∣ δ) = \sum_{j=1}^{m} P (B ∣ A_{i}) P (A_{i})$

In this way, the inevitable event δ is divided into m disjoint sub-events, and the conditional probability of event B is the sum of the conditional probabilities of event B given each sub-event Aj (j = 1, 2..., m). Thus, given event B (P (B) > 0), the conditional probability of event Ak can be written as: (2) $P (A_{k}) | B = \frac{P (B ∣ A_{k}) P (A_{k})}{P (B)} = \frac{P (B ∣ A_{k}) P (A_{k})}{\sum_{j=1}^{m} P (B ∣ A_{j})} = \frac{P (B ∣ A_{k}) P (A_{k})}{\sum_{j=1}^{m} P (B ∣ A_{j}) P (A_{j})}$

Let's start with a simple derivation of the cubic variables: (3) $P(x ∣ y,z) = \frac{P(y ∣ x,z)P(x ∣ z)}{P(y ∣ z)} = \frac{P(z ∣ x,y)P(x ∣ y)}{P(z ∣ y)}$

If y, Z comply with the Markov property, then the following can also be derived: (4) $P(x ∣ y,z) = \frac{P(y ∣ x)P(x ∣ z)}{P(y ∣ z)} = \frac{P(y ∣ x)P(x ∣ z)}{P(y ∣ open) P (open ∣ z) + P(y ∣ \bar{open}) P (\bar{open} ∣ z)}$

Put Z 1,...., Zn are regarded as a whole, and then according to the Markov condition, when X is known, Zn is the same as {Z1,..., Zn – 1} is independent, so (5) $P (X ∣ Z_{1} \dots Z_{n}) = \frac{P (Z_{n} ∣ x, Z_{1}, \dots, Z_{n - 1}) P (x ∣ Z_{1}, \dots, Z_{n - 1})}{P (Z_{n} ∣ Z_{1}, \dots, Z_{n - 1})} = \frac{P (Z_{n} ∣ x) P (x ∣ Z_{1}, \dots, Z_{n - 1})}{P (Z_{n} ∣ Z_{1}, \dots, Z_{n - 1})}$

So the recursive Bayes formula can be obtained (6) $\begin{matrix} P (X ∣ Z_{1} \dots Z_{n}) = \frac{P (Z_{n} ∣ x) P (x ∣ Z_{1}, \dots, Z_{n - 1})}{P (Z_{n} ∣ Z_{1}, \dots, Z_{n - 1})} = ηnP (Z_{n} ∣ x) P (x ∣ Z_{1}, \dots, Z_{n - 1}) \\ = ηnP (Z_{n} ∣ x) P (Z_{n - 1} ∣ X) P (x ∣ Z 1, \dots, Zn - 2) = η_{1} \dots η_{n} \prod_{i = 1 \dots n} P (Z_{i} ∣ x) P (x) \end{matrix}$

The Bayesian filter is derived as follows: (7) $\begin{matrix} \begin{matrix} \begin{matrix} Bel (x_{1}) = P (x_{t} ∣ u_{1} {,z}_{1} {…,u}_{t} {,z}_{t}) \\ = ηP (z_{t} ∣ x_{t} {,u}_{1} {,z}_{1} {…,u}_{t}) P (x_{t} ∣ u_{1} {,z}_{1} {…,u}_{t}) \leftarrow Bayes \end{matrix} \\ = ηP (z_{t} ∣ x_{t}) P (x_{t} ∣ u_{1} {,z}_{1} {…,u}_{t}) \leftarrow Markov \end{matrix} \\ = ηP (z_{t} ∣ x_{t}) \int P (x_{t} ∣ u_{1} {,z}_{1} {…,u}_{t} {,x}_{t - 1}) P (x_{t - 1} ∣ u_{1} {,z}_{1} {…,u}_{t}) {dx}_{t - 1} \end{matrix}$ (8) $\begin{matrix} Bel (x_{1}) = ηP (z_{t} ∣ x_{t}) \int P (x_{t} ∣ u_{t} {,x}_{t - 1}) P (x_{t - 1} ∣ u_{1} {,z}_{1} {…,u}_{t}) {dx}_{t - 1} \\ = ηP (z_{t} ∣ x_{t}) \int P (x_{t} ∣ u_{t} {,x}_{t - 1}) P (x_{t - 1} ∣ u_{1} {,z}_{1} {…,z}_{t - 1}) {dx}_{t - 1} \\ = ηP (z_{t} ∣ x_{t}) \int P (x_{t} ∣ u_{t} {,x}_{t - 1}) Bel (x_{t - 1}) {dx}_{t - 1} \end{matrix}$

3.2

Genetic algorithm

Genetic algorithm can optimize the evaluation method of different impact indicators in the employment structure system, and never choose different ones. Improve the competition mechanism in combination and other operations. In the employment index system, it is necessary to update the weight of the evaluation index constantly to find an adaptive value to objectively evaluate the employment index system. Considering that genetic algorithm mutates different input indexes, mutation operation is beneficial to genetic algorithm in evaluating the diversity of employment structure system. In the whole evaluation process, it is necessary to change each employment index adaptively, so as to find an optimal value of global evaluation. The probability of variation of employment indicators is described by the following formula: (9) $P = (P_{1} + P_{2}) / 2 + (P_{0} - (P_{0} - P_{\min}) / m / M + P_{0} * maxF (X_{K}) / \bar{F}) / 2$ Where M is the maximum number of iterations, m is the current number of iterations, P₁ is inversely proportional to the number of evolution generations, P₂is inversely proportional to the average fitness value, and P₀ is the starting value of mutation probability. P_min is the minimum value of the range of mutation probability, $\bar{F}$ is the average fitness of the current population, and maxF(X_K) is the maximum fitness of the current population.

The basic flow of the adaptive genetic algorithm is as follows:

Step 1: Coding

Continuously coding a value can achieve better efficiency for the global optimal solution. The coding in this paper is shown in Figure 1:

Step 2: Determine the initial population

The size of the initial population has an important impact on the training efficiency. If the population is too large, the probability of getting the global optimal solution will be greater, but it will require more training time and computing resources, and the solving efficiency will be lower. If the population is too small, the probability of global optimal solution is small, and it is easy to train into the local optimal process. The population chosen in this paper is between [25, 45]. The minimum error is 0.251 and the convergence time is small when the population is 30 by continuous training. The error training results are shown in Figure 2.

Step 3: Determine fitness

The confirmation process of fitness is generally calculated by taking the maximum value of the fitness function, using the following formula: (10) $E = \frac{\sum_{k=1}^{p} \sum_{j=1}^{l} (y_{j}^{k} - o_{j}^{k})}{2}$ (11) $fitness = \frac{1}{E}$

Step4: Select operation

The selection operation is to calculate the proportion of the fitness value of an individual to the total fitness value, which is regarded as the probability of an individual being selected in the whole variation process. The formula is as follows: (12) $z (s_{i}) = \frac{f (s_{i})}{\sum_{j = 1}^{d} f (s_{i})}$

After determining the selection probability of each individual, it is necessary to determine whether the cumulative probability of each individual can evolve in the next generation. The selection process is as follows: (13) $q (s_{i}) = \sum_{i = 1}^{k} z (s_{i})$

The above process is continuously executed to finally obtain a stable fitness value, and at this time, the population is based on a stable state.

Step5: Cross operation

Crossover operation is to let the population enter a faster training, which can get a better gene probability. In this paper, the crossover probability ranges from 0.6 to 1.

4

The Development of Artificial Intelligence in China and the Evolution of Employment Structure

4.1

Development trend of artificial intelligence

Figure 1 and Figure 2 show the size of the global and Chinese AI market in 2017-2024, respectively.

Figure 3 and Figure 4 show that the scale of global AI economy is relatively large, which has an important role in promoting the development of emerging economic industries. The fastest growth in the world is in 2019, with a growth rate of 33.29%, while the slowest is in 2024, with a growth rate of 14.1%, indicating that AI is now slowing down and is in a mature period of saturation compared with other industrial economies. The scale of AI economic development in China is still in a stage of development, especially the integration with other industries, such as vocational education, social employment, agriculture and other traditional industries.

Artificial intelligence is in a large growth rate in 2018, and is in a slow decline after 2018. Artificial intelligence patents are in a period of rapid growth before 2018. Figure 5 shows the growth of AI patent licensing in China from 2000 to 2017. From 2014 to 2017, the number of patents authorized in the field of artificial intelligence is in the stage of adjustment and growth, rising from 3753 to 17477. The growth rate almost reached more than 90%, indicating that the increase in the scale of AI economic growth in 2018 has important intellectual property support.

4.2

Analysis of China's Employment Scale and Structure

Table 1 shows the output value of China's three industries and the proportion of employees from 2001 to 2017.

Table 1.

Output Value and Employment Proportion of Primary, Secondary and Tertiary Industries in China from 2001 to 2017 (Unit%)

Year	An industry		The secondary industry		The third industry
2017	7.6	27.0	40.5	28.1	51.9	44.9
2018	7.2	26.1	40.7	27.6	52.1	46.3
2019	7.1	25.1	38.6	27.5	54.3	47.4
2020	7.7	23.6	37.8	28.7	54.5	47.7
2021	7.2	22.9	39.3	29.1	53.5	48.0
2022	7.3	24.1	39.3	28.8	53.4	47.1
2023	7.1	22.8	38.3	29.1	54.6	48.1

Figure 6 is a more intuitive representation of the proportion of output value of different industries in China from 2017 to 2023:

Figure 7 is a more intuitive representation of the proportion of employees in different industries in China from 2017 to 2023:

5

Impact and Analysis of Artificial Intelligence on Employment Structure System

5.1

Analysis of factors affecting employment

Through the investigation of marking papers and interviews with employees, this paper analyzes the main effects on the employment structure to understand the current employment environment, employment pressure and social security system. The evaluation system of employment structure is shown in Table 2: Table 2.

The factors affecting employment and the weights of different factors.

Level 1 indicator	Weights	Secondary indicators	Weights	Logo
Nature of employment	0.21	Position of employment	0.42	A1
		Nature of the unit	0.35	A2
		Enterprise scale	0.23	A3
Conditions of employment	0.31	Employment environment	0.31	A4
		Salary level	0.29	A5
		Working hours	0.25	A6
		Work pressure	0.15	A7
Employment Security	0.28	Labour regulations	0.37	A8
		Insurance system	0.28	A9
		Employee relations	0.1	A10
		Lead the affinity	0.25	A11
Employment prospects	0.2	Industry prospects	0.45	A12
		Promotion mechanism	0.34	A13
		Refresher training mechanism	0.21	A14

Table 2 analyzes the factors affecting employment and calculates the weights of different factors. Artificial intelligence algorithm can be used to further analyze the relationship between different indicators of employment structure system. Describe the correlation between different indicators to see the corresponding correlation, as shown in Table 3.

Table 3.

Correlation degree of different indicators

	A1	A2	A3	A4	A5	A6	A7	A8	A9	A10	A11	A12	A13	A14
A1	1
A2	0.91	1
A3	0.74	0.64	1
A4	0.88	0.78	0.68	1
A5	0.86	0.81	0.84	0.78	1
A6	0.82	0.76	0.67	0.71	0.81	1
A7	0.75	0.78	0.45	0.85	0.67	0.76	1
A8	0.35	0.37	0.84	0.34	0.41	0.81	0.62	1
A9	0.51	0.28	0.82	0.42	0.57	0.38	0.42	0.86	1
A10	0.38	0.68	0.75	0.53	0.41	0.41	0.53	0.65	0.84	1
A11	0.42	0.71	0.69	0.61	0.26	0.68	0.64	0.67	0.71	0.86	1
A12	0.65	0.67	0.72	0.35	0.35	0.21	0.38	0.51	0.32	0.27	0.27	1
A13	0.43	0.47	0.65	0.26	0.26	0.36	0.34	0.71	0.39	0.33	0.21	0.68	1
A14	0.35	0.35	0.62	0.31	0.37	0.42	0.31	0.73	0.34	0.28	0.19	0.54	0.82	1

The correlation between different indicators can reflect the degree of dependence between different indicators. There is a high correlation between employment location and the nature of the unit, indicating that the relationship between employment location and the nature of the unit is relatively close.

5.2

Optimization analysis of employment indicators

The artificial intelligence algorithm is used to evaluate and apply the employment structure, and the weights of different indicators are adjusted and optimized. The weights of employment structure are optimized by artificial intelligence algorithm, which objectively reflects the influence of different weights. The first-level index optimization is shown in Figure 8.

Only by optimizing the secondary indicators, can whole index system be optimized. The secondary indicators are optimized as shown in Figure 9-12.

It can be seen that the weights before and after artificial intelligence optimization are optimized, and the evaluation of employment structure can be objective and fair.

6

Conclusion

The basic principles for the establishment of the evaluation system of employment structure include the principles of comprehensiveness, directionality, incentive and improvement, objectivity and subjectivity. Secondly, the basic methods for the evaluation of employment quality in theory and practice in recent years are sorted out; Then, it explains the relevant influencing factors of employment structure evaluation, and analyzes the problems existing in the current employment structure evaluation system according to the research results, and explains them one by one; Finally, in order to avoid some problems in the process of establishing the current employment structure evaluation system and solve the shortcomings of the current employment structure evaluation system, the mutation probability is improved to enhance the diversity of the population and improve the convergence speed. Realize the objectivity of the weight evaluation in the employment structure evaluation system, and make the employment structure evaluation system more scientific, reasonable and effective.

Język:: Angielski

Częstotliwość wydawania:: 1 razy w roku
Dziedziny czasopisma:: Nauki biologiczne, Nauki biologiczne, inne, Matematyka, Matematyka stosowana, Matematyka ogólna, Fizyka, Fizyka, inne

Kanał RSS czasopisma

Construction and Analysis of Employment Structure System Based on Artificial Intelligence and Its Influencing Factors

Nan Lu

Pengli Wang

Xiaoting Zhu

Data publikacji: 27 lut 2025

Otrzymano: 10 wrz 2024

Przyjęty: 08 sty 2025

DOI: https://doi.org/10.2478/amns-2025-0131

Słowa kluczoweemployment structure, system evaluation, genetic algorithm, mutation operation

© 2025 Nan Lu et al., published by Sciendo

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

Słowa kluczowe
employment structure, system evaluation, genetic algorithm, mutation operation