Evaluation of Internet Addiction Exercise Intervention Effect for Teenagers Based on Intelligent Psychological Strategy Technology

Abstract

Modern information has led to Internet addiction among some young people. Some studies have shown that Internet addiction has serious harm to young people, such as affecting young people’s learning and endangering young people’s physical health. Even more serious, it may lead to depression, suicide, and other problem appearance. At present, most of the research on Internet addiction focuses on the development of questionnaires, symptoms, and causes of Internet addiction, and there is still a lack of treatment and intervention. Therefore, in the era of rapid development of artificial intelligence, let artificial intelligence use psychological strategies. Technology to intervene adolescents’ Internet addiction is a new technology required by current intelligent psychological terminal equipment, and this technology is still in the field of data preprocessing and classification. For the intelligent psychological strategy technology that is applied and located in the terminal device, the ability to intelligently identify whether the Internet addiction is an inevitable trend of the development of modern intelligent devices. Looking back at this technology, we can often see two prominent problems with this technology during the development process, namely, accuracy and efficiency. Due to the development of 5G technology and cloud computing, the intelligent identification process can be transferred to the cloud for rapid completion, and the terminal device only needs to receive feedback to solve the efficiency problem as much as possible. The problem of relative accuracy is the difficulty that the current intelligent psychological strategy technology needs to overcome, and it is also the focus of this article. This paper introduces the related technologies in the process of intelligent psychological technology intervention, the extraction of Internet addiction problems, and the use of related technologies to intervene and explore the improvement under the current mainstream algorithm conditions. Intelligent technology improves the accuracy of psychological intervention. Through the discussion of the actual comparison experiment of the algorithm, we can understand that the influencing factors of the accuracy rate are mainly concentrated in the influence of the Internet, such as unreasonable game play and video browsing. We are committed to ensuring that the intelligent psychological strategy technology of terminal equipment can accurately intervene the Internet addiction problem of young people without changing the equipment conditions. First of all, the optimized algorithm is easier to understand and less difficult to use than ordinary algorithms, which greatly reduces the difficulty for psychoanalysts or intervention evaluators to deal with problems. Secondly, the intelligent psychological strategy technology is the product of many experiments and is gradually widely recognized and accepted by everyone. It can carry out statistics, calculation, and visual display through various data of intelligent programs and realizes automatic intervention for multiple problems, which can significantly reduce the user’s time and cost investment, reduce the burden of staff, and provide analysts and evaluators with substantial information help.

This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.

1. Introduction

Under the development of Internet+, intelligent psychological strategy technology [1–3] was born. As a very popular new cutting-edge technology, through intelligent identification, it can solve some of the problems of Internet addiction among adolescents that were difficult to solve in the past [4–6]. However, the terminal system actually recognizes relevant data and digital concepts, so the terminal system extracts information about the causes of Internet addiction and processes it [7–9]. It roughly contains the relevant characteristics and treatment methods of Internet addiction [10–12]. Collect relevant intelligent psychological strategy technical information, quickly match with the cloud database, and feed the results back to the intelligent terminal to complete the user identification. At present, there are two commonly used methods for intelligent identification of Internet addiction, one is PCA-SIFT, which is to find the key points (feature points) of Internet addiction and calculate the relevant optimization plan; the other is LLE-SIFT, which is essentially the same as PCA-SIFT algorithm is similar but has more advantages than the former [13–15].

2. Overall Design of the Steps of the Cause Identification Feature Extraction Method

Reason identification is an addition to the algorithm for computers, and the technical support behind it is mainly concentrated in artificial logic processing, similar to subjective judgment of things, and it is difficult to give full authority to the terminal equipment to judge by itself. The simple method of feature extraction for a large amount of data is the calculation result of the terminal device under the support of the intelligent psychological strategy technology algorithm. The results of different factors match the relevant statistics of the existing data. Targeted intelligent psychological intervention work Figure 1 shows the process of intervening on Internet addiction [16].

[figure(s) omitted; refer to PDF]

As shown in Figure 1, in the process of dealing with Internet addiction problems, we first collect the causes of youth Internet addiction problems, and then upload the collected data to the cloud, and then analyze the related Internet addiction problems through cloud computing, and then pass fuzzy algorithm is used to calculate to get the corresponding intervention plan for teenagers’ Internet addiction, and then the intervention plan is transmitted to the terminal through the cloud; the terminal collects and analyzes the operation results and uploads the plan and design that need to be improved to the cloud for subsequent modification.

2.1. Overview of Adolescent Internet Addiction Intervention Process

First of all, it is necessary to obtain the relevant causes of Internet addiction. Here, specific terminal system software should be used for processing, to enhance the understanding of the causes of the problem and to digitize the problem in a specific two-dimensional form, so that the relevant terminal can read and identify it. The above process can be turned into cause collection, enhanced analysis, and preliminary intervention. The specific steps are as follows.

Step 1 (reason collection).

Before intervening on adolescent Internet addiction, it is necessary to collect the causes of Internet addiction [17]. By collecting the relevant information of the user, including the user’s network itinerary and related Internet information, and then storing it in the chip of the terminal in the relevant form or in the cloud database in the form of binary, and then intervening in the Internet addiction problem, take out the relevant information from the database. The data then psychologically intervene on the user through a calculated approach.

Step 2 (augmented analysis).

Because there are too many reasons for teenagers’ Internet addiction, and the degree of addiction is also different, the intervention effect of the preliminary intervention plan for users is deviated from our hope. At this time, it is necessary to strengthen the analysis and processing technology. Let artificial intelligence better understand the problems and causes, analyze better intervention plans, make the plan more stable, and lay a better foundation for subsequent secondary analysis and follow-up processing after intervention [18, 19].

Step 3 (initial intervention).

Problems will be subject to many related interferences caused by other factors during acquisition, making it difficult to ensure accuracy when analyzing and building solutions. In most cases, it is necessary to perform multiple memory recovery on the problem data collected by the relevant users (that is, to mine the underlying data of the storage unit). Since there are unquantifiable influencing factors in the related interference situation of the acquisition problem, we use the hierarchical fuzzy algorithm to calculate, and we express the influencing factors in the form of sets, and the elements are mutually exclusive and do not interfere with each other. Each influencing factor is defined as $u_i$, and the composition of influencing factors is the set $U$ of Internet addiction intervention influencing factors, which is expressed as follows: $$\begin{array}{}\text{(1)}& U=u_{i}i=1,2,\cdots ,n,\end{array}$$

where $n$ is the Internet addiction intervention factor and $U$ is the Internet addiction intervention factor set.

In the set $U$, then, $i\ne j$$u_i$ with $u_j$. The degree of influence of the intervention results varies, that is, the degree of influence of the relative Internet addiction intervention is different. Corresponding to each factor in the set $u_i,i=1,2,\cdots ,n$$U$, the intervention degree value of $a_i,i=1,2,\cdots ,n$ the response is assigned, which is used to reflect the proportion of each factor participating in the adolescent Internet addiction intervention. The influence degree value constitutes a set $A$, which is mathematically expressed as follows: $$\begin{array}{}\text{(2)}& A=a_{i}i=1,2,\cdots ,n.\end{array}$$

where$a_i$is the normalization; nonnegativity conditions are satisfied, namely, $$\begin{array}{}\text{(3)}& a_1+a_2+\cdots +a_n=1.\end{array}$$Each intervention factor in the set $U$, if there are intervention programs with a total number of $S$, $S_{ij}$ an Internet addiction intervention result is $v_j$, where $S={\sum }_{j=1}^m{S}_{ij},i=1,2,\cdots ,n$. Based on the above, we call $u_i$ the degree of membership to the intervention outcome as $v_j$. $$\begin{array}{}\text{(4)}& r_{ij}=\frac{S_{ij}}{S},\hspace{1em}i=1,2,\cdots ,n,j=1,2,\cdots ,m.\end{array}$$

Taking the benchmark Internet addiction intervention factor set and the intervention result set as the element items of matrix $R$, the membership degree $r_{ij}$ can be expressed in matrix $R$ as follows: $$\begin{array}{}\text{(5)}& R=\begin{array}{ccc}{r}_{11}& \cdots & r_{1m}\\ ⋮& \ddots & ⋮\\ r_{n1}& \cdots & r_{nm}\end{array}.\end{array}$$

If the result of the fuzzy comprehensive Internet addiction intervention set is recorded as $B$, then $B$ is the fuzzy subset of the $A=a_{i}i=1,2,\cdots ,n$ Internet addiction intervention result set $V$, which will be multiplied with the column elements in the matrix $R$ one by one to get: $$\begin{array}{}\text{(6)}& A=a_{i}i=1,2,\cdots ,n\ast R=\begin{array}{ccc}{a}_1\cdot r_{11}& \cdots & a_1\cdot r_{1m}\\ ⋮& \ddots & ⋮\\ a_n\cdot r_{n1}& \cdots & a_n\cdot r_{nm}\end{array}.\end{array}$$

The $i$-th row represents the comprehensive intervention effect on the factor $u_i$. If each column in the matrix is added up, we get: $$\begin{array}{}\text{(7)}& B=\sum _{i=1}^n{a}_i{r}_{ij}=\max .\end{array}$$The intervention on $U$ is called as the result of $v_j$ comprehensive intervention for adolescent Internet addiction.

Based on the multidimensional situation of Internet addiction intervention factors, the above-mentioned intervention model is expanded to simplify the hierarchical problem between the intervention factors. The low-level intervention factors are comprehensively analyzed first, and then the high-level intervention factors are comprehensively analyzed until the optimal solution to the research problem is reached. To construct the higher-level formula needed to intervene in Internet addiction, the simplified steps are as follows:

Internet addiction intervention factor $U$ is composed of several related intervention subsets, and the elements are mutually exclusive. That is $U=U_1,U_2,\cdots ,U_k$, where $U_i=U_1^i,U_2^i,\cdots ,U_{ni}^i,i=1,2,\cdots ,k$ both are satisfied $U_i\cap U_j=\varnothing ,i\ne j;i,j\in 1,2,\cdots ,k$. Then we call it the first-level $U_i$ Internet addiction intervention factor, which $U_1^i,U_2^i,\cdots ,U_{ni}^i$ is the second-level intervention factor.

Assume that the adolescent Internet addiction intervention set conducts a $V=v_{i}i=1,2,\cdots ,m$ separate intervention analysis on the Internet addiction intervention elements of the adolescent Internet addiction intervention subset, and the intervention formula $U_i=U_1^i,U_2^i,\cdots ,U_{ni}^i$ obtained is $$\begin{array}{}\text{(8)}& R_i=\begin{array}{ccc}{r}_{11}^i& \cdots & r_{1m}^i\\ ⋮& \ddots & ⋮\\ r_{n_{i}1}^i& \cdots & r_{n_{i}m}^i\end{array}.\end{array}$$Impact degree of $A_i=a_1^i,a_2^i,\cdots ,a_{ni}^i$ the intervention is set as $U_i=U_1^i,U_2^i,\cdots ,U_{ni}^i$: $$\begin{array}{}\text{(9)}& U_i\cdot A_i=\begin{array}{ccc}{a}_1^i{r}_{11}^i& \cdots & a_1^i{r}_{1m}^i\\ ⋮& \ddots & ⋮\\ a_{n_i}^i{r}_{n_{i}1}^i& \cdots & a_{n_i}^i{r}_{n_{i}m}^i\end{array}.\end{array}$$

Formulas (8)–(9) are developed based on the basic fuzzy algorithm to evaluate the intervention factors by classification. The low-level Internet addiction intervention factor set is converted into an optimization operation after performing a preliminary set operation. The low-level Internet addiction intervention factor set is in the form of a comprehensive intervention factor set, and the low-level operation is used to calculate the high-level, so as to give answers to the problems of adolescent intervention factors in different situations.

i-th row of the matrix represents the comprehensive intervention of the factor $U_i^i$. If each column of the above formula is added, we can get $$\begin{array}{}\text{(10)}& \sum _{i=1}^{n_i}{a}_i^i\cdot r_{ij}=\min ,\end{array}$$where $v_j$ is called right, which is the result of the $U_i$ comprehensive intervention of the fuzzy algorithm on the Internet addiction of young people.

Assuming $U=U_1,U_2,\cdots ,U_k$ that the degree of influence is $A_i=a_1,a_2,\cdots ,a_k$, then defines: $$\begin{array}{}\text{(11)}& B_i=b_j^{i}j=1,2,\cdots ,m=\sum _{i=1}^{n_i}{a}_i^i\cdot r_{ij}j=1,2,\cdots ,m.\end{array}$$

The calculation formula defined above can be used to calculate the intervention effect under other influences on the basis of the above, so the total Internet addiction intervention formula is $$\begin{array}{}\text{(12)}& R=r_{ij}i=1,2,\cdots ,k;j=1,2,\cdots ,m=\begin{array}{c}\begin{array}{c}\begin{array}{c}{B}_1\\ B_2\end{array}\\ ⋮\end{array}\\ B_k\end{array}.\end{array}$$

According to the hierarchical fuzzy algorithm, the fuzzy calculation is performed on the following formula. In the calculation result, the maximum value obtained by $B$ corresponds to $v_j$, the fuzzy comprehensive intervention result for $U$ [20]. $$\begin{array}{}\text{(13)}& B=A_{i}R=a_1,a_2,\cdots ,a_k\begin{array}{c}\begin{array}{c}\begin{array}{c}{B}_1\\ B_2\end{array}\\ ⋮\end{array}\\ B_k\end{array}.\end{array}$$

After the calculation of the fuzzy algorithm intervention formula is completed, the calculation result is normalized and defined $B^{\ast }=b_1^{\ast },b_2^{\ast },\cdots ,b_m^{\ast }$ as the normalized fuzzy comprehensive intervention set, where $$\begin{array}{}\text{(14)}& b_j^{\ast }=\frac{b_j}{{\sum }_{j=1}^m{b}_j}j=1,2,\cdots ,m.\end{array}$$

Satisfied ${\sum }_{j=1}^m{b}_j^{\ast }=1$ after comprehensive processing of normalized fuzzy criteria. It indicated that as a percentage of the corresponding adolescent Internet addiction intervention factor, the correlation status of the factor after intervention was calculated. The above calculation results constitute the relevant Internet addiction intervention matrix of the upper layer, and then fuzzy comprehensive intervention is carried out on the upper layer.

Combined with the focus of this article, under the intervention technology of intelligent psychological strategy technology, the supplementary graph of the overall effect on adolescent Internet addiction exercise problems is shown in Figure 2.

Step 4 (organize the plan and initially solve the problem).

After passing through the fuzzy algorithm, a large amount of data will be generated, and the calculated data methods will be sorted according to the relevant methods, so as to improve the accuracy of the relevant schemes and facilitate the storage of the relevant schemes. After sorting out the plan, the time required for transmission in the cloud can be reduced, and the processing time required to intervene users’ Internet addiction can also be reduced, and the relevant intervention capabilities of intelligent psychological strategies are also greatly enhanced.

When formula (10) takes the maximum value, $U_i$ is the correct fuzzy intervention result, and its correction formula is $$\begin{array}{}\text{(15)}& \sum _{i=1}^{n_i}{a}_i^i\cdot r_{ij}=\max .\end{array}$$

[figure(s) omitted; refer to PDF]

2.2. Overview of Interventions for Internet Addiction

There are several steps to intervene in adolescents’ Internet addiction problem. One is to carry out secondary question extraction and program selection during the initial intervention; it is to analyze and solve related emergencies that arise during the intervention process [21].

After preliminarily processing the adolescent Internet addiction problem, the terminal device will conduct multiple follow-up investigations and analysis, and then extract and select characteristic feedback results, and then classify and analyze the feedback results and carry out subsequent decision -making processing. According to the concept of “information entropy” proposed by Shannon, the construction calculation is carried out with half an hour as a time interval, 24 hours a day is divided into 48 - dimensional time vectors, and the follow-up behavior $v$ of Internet addict teenagers after the intervention is counted, and then calculated the frequency: $$\begin{array}{}\text{(16)}& p_{v}T=t_i=\frac{{}_{n_v{t}_i}}{{\sum }_{i=1}^n{n}_{v{t}_i}}.\end{array}$$

Then find the user’s behavior entropy as the formula: $$\begin{array}{}\text{(17)}& E_V=-\sum _{i=1}^n{p}_{v}T=t_i\log P_{V}T=t_i.\end{array}$$

Since the premise of the formula is to investigate the effect of Internet addiction intervention among adolescents, the meanings of each variable in the formula are as follows: one $t_i$ of 48 time periods, and the follow-up behavior of the investigated adolescents is represented as $V$, which $n_v{t}_i$ represents one month, the total number of subsequent actions $v$ that occurred in the time period $t_i$.

When the entropy value is larger, it proves that the behavior of the teenager is more irregular, indicating that follow-up intervention through intelligent psychological strategy technology is needed. The related process of Internet addiction intervention is shown in Figure 3.

[figure(s) omitted; refer to PDF]

As shown in Figure 3, the user data is simulated and calculated through the cloud, and then the plan is sorted out. After the simulation experiment, the optimization results are classified, and then the user’s youth Internet addiction problem is intervened. If it fails, the simulation experiment is rerun on the cloud.

Intervening in the youth Internet addiction movement is that various factors in the current environment, such as family and school will affect the intervention. In addition to the above factors, there are many factors such as time factors, personal hobbies, and the influence of contact groups. The cloud calculates the adolescent Internet addiction problem, filters the results, and then makes classification decisions, analyzes, evaluates, and estimates them to maximize the accuracy. [22, 23]

2.3. Improvement of the Algorithm of Intelligent Psychological Strategy for Adolescent Internet Addiction Exercise Intervention

In addition to the fuzzy algorithm for intervening in adolescent Internet addiction problems, the tracking algorithm can be used for the follow-up motion processing to deal with the relationship between the two factors and measure the correlation between the follow-up processing. We deduce the correlation, assuming that there are two Correlation functions $f$ and $g$, then the relevant formula is described as follows: $$\begin{array}{c}\text{(18)}& f\otimes gy={\int }_{\infty }^{-\infty }f\ast tgt+ydt,f\otimes gn=\sum _{-\infty }^{\infty }f\ast mgm+n.\end{array}$$

This paragraph describes the use of fuzzy algorithm for derivation. In the formula, it $f\ast$ represents $f$ the complex conjugate of yes; $g$ represents the response output of Internet $f$ addiction intervention, represents the output of adolescent user information, and represents $h$ the filtering template for Internet addiction intervention.

The complex conjugate of the expression in the $f$ formula and the tracking algorithm is applied to the target tracking field, because the target tracking is mainly to find the maximum response value of the target to be tracked in the image. $f\ast$ The simplest way to understand the formula is that the two signal values are close to each other, and the higher the correlation value [24, 25].

The tracking algorithm can read the uploaded initial question and give the relevant calculation formula, convert the candidate intervention plan, and then perform logarithmic transformation on it to enhance the contrast and intervention success rate, reduce the edge effect, and perform fast Fourier transform to improve calculation speed. Based on the diversity of its algorithm modes, we only select a few of them for the specific scenarios involved in this article.

David S. Bolme uses the filter $h$ to reduce the least squares of the error, and the MOSSE algorithm passes a correlation filter. The target is processed through the filter, and the relevant formula is $$\begin{array}{}\text{(19)}& g=f\otimes h.\end{array}$$

MOSSE algorithm first calculates the response output of $h$ and then calculates the response output $g$. When calculating larger problems, the fast Fourier transform operation is used to reduce the number of related calculations and improve efficiency. The formula is as follows: $$\begin{array}{}\text{(20)}& G=F•H\ast ,\end{array}$$where $G$ represents the response output, $F$ represents the correlation image, $H\ast$ represents the filter, and the formula to solve $H\ast$ is $$\begin{array}{}\text{(21)}& H\ast =\frac{G}{F}.\end{array}$$

The network guarantees the robustness in the tracking calculation process. Considering the influence of related factors on the results, the MOSSE algorithm adds a multitemplate reference strategy to improve the effect of the overall algorithm. The formula is $$\begin{array}{}\text{(22)}& \min H\ast =\sum _{i=1}^m{H\ast Fi-Gi}^2,\end{array}$$where $m$ represents the data, $i$ represents the template, and then derive $H$ from the above formula: $$\begin{array}{}\text{(23)}& H=\frac{{\sum }_{i}F•G_i^{\ast }}{{\sum }_{\text{i}}{F}_i•F_i^{\ast }}.\end{array}$$

In order to ensure that the current sequence is not far from the initial sequence, a new strategy formula is adopted: $$\begin{array}{}\text{(24)}& H_t=\frac{A_t}{B_t},\text{(25)}& A_t=\eta F_t•G_t^{\ast }+1-\eta A_t-1,\text{(26)}& B_t=\eta F_t•F_t^{\ast }+1-\eta B_t-1,\end{array}$$

where$\eta$is the parameter of the filter update,$A_t$is the numerator, and$B_t$is the current formula and the denominator of the current formula.

In the MOSSE algorithm, the defined expression, that is, the $d$ function, selects the weight according to the factor. The smaller the factor, the greater the proportion. This is the same as the double filter and the Gaussian filter. The $r$ function assigns weights according to the differences in related factors. If the two correlation values are closer, the proportion will be larger. It is the role of the $r$ function that enhances the accuracy of the intervention algorithm for adolescent-related Internet addiction problems with different problems.

The results and discussion may be presented separately, or in one combined section, and may optionally be divided into headed subsections.

3. Experimental Simulation

In order to ensure the compatibility of the algorithm, a large amount of data is used for experimental verification. The experimental objects are: the number of successful intervention points, the success rate of intervention, and the time spent on successful intervention. The advantages of the algorithm before and after the improvement are often determined through the above comparison angles. According to the above four considerations, after summarizing, an experimental comparison is made in terms of accuracy and time. The results of the effect analysis of Internet addiction under the intervention of intelligent psychological strategy technology are shown. The intervention effect size for Internet addiction in adolescents was 5.5%, and the Boostrap 95% confidence interval was [0.026, 0.088], excluding 0. Therefore, the effect of adolescent Internet addiction under the control of intelligent psychological strategy technology is significant.

According to the shortcomings of the tracking algorithm, we need a formula for stabilizing the correlation function, so combined with the actual situation, the added formula is $$\begin{array}{}\text{(27)}& \begin{array}{c}{d_{0i}}^1=\sum _{k=1}^{n-1}{d_{0i}}^{1}k=\sum _{k=1}^{n-1}{x}_{0}k+1-x_{i}k+1-x_{0}k+x_{i}k\\ {d_{0i}}^2=\sum _{k=2}^{n-1}{d_{0i}}^{1}k\end{array}{d_{0i}}^1=\sum _{k=1}^{n-1}{d_{0i}}^{1}k=\sum _{k=1}^{n-1}{x}_{0}k+1-x_{i}k+1-x_{0}k+x_{i}k.\end{array}$$

3.1. Comparison before and after Algorithm Optimization

This part of the experiment mainly compares the experimental results of different algorithms under the different performances of the before and after optimization algorithms under the same intelligent psychological mechanism module. The effect of the terminal’s intelligent psychological strategy intervening in the youth Internet addiction movement, which $F_{IM}$ represents the harmonic mean value of accuracy and success rate, which $A_{uc}$ represents the accuracy. When the intelligent psychological strategy mechanism module is added, the accuracy rate is increased from 85.6% to 90.13%. The variance is reduced from 5.78% to 3.27%, which has good stability. After adding the optimized algorithm, the accuracy rate is increased to 93.42%, and the variance is reduced to 1.63%, and better stability is obtained after the optimization algorithm; the intervention accuracy rate is higher, and the effect is more obvious; the results are shown in Table 1.

Table 1

Comparison of before and after algorithms.

Method	Precision (%)	Variance (%)	FIM (%)	GM (%)	AUC (%)
MDNet	85.6	5.78	82.1	85.04	67.8
Smart mental template formula	90.13	3.27	83.1	87.08	67.8
Optimize formulas	93.42%	1.63	86.79	89.37	67.8

Figure 4 shows the comparison before and after the optimization algorithm. It is obvious that the optimized algorithm has higher accuracy, lower variance, and higher success rate of user intervention.

[figure(s) omitted; refer to PDF]

Further, we explored the robustness and accuracy of Internet addiction intervention data for different users and truncated the test videos with length ratios of 1, 2, 3, and 4 to form three sets of test data. We input these different data into the before and after formulas to measure the effect of postintervention on different users and get the comparison results in Table 2.

Table 2

Comparison of different user intervention results.

Algorithm	Problem processing is time-consuming (ms)	Analyzing scenario results takes time (ms)	Total time consuming (ms)
BAM	602.6	625.5	1228.1
FAM	447.9	420.2	868.1
TAM-S	356.6	367.5	724.1

Figure 5 compares the intervention results of different users. The results show that the shorter the sequence, the worse the intervention effect, and the longer the sequence, the better the intervention effect.

[figure(s) omitted; refer to PDF]

The results of the effect analysis of Internet addiction under the intervention of intelligent psychological strategy technology showed that the intervention effect size of adolescent Internet addiction was 5.5%, and the 95% confidence interval of Boostrap was 0.026 and 0.088, and the interval did not include 0. Therefore, the effect of adolescent Internet addiction under the control of intelligent psychological strategy technology is significant. It is shown in Figure 6 and Table 3.

[figure(s) omitted; refer to PDF]

Table 3

Analysis of the effect of intelligent psychological strategy technology intervention on adolescent Internet addiction movement.

	Intervention effect value	Boot effect value	Boot CI lower limit	Boot CI upper limit
Adolescent Internet addiction intervention	0.055	0.016	0.026	0.088

The intelligent psychological strategy technology calculated and compared the formula before and after the youth Internet addiction exercise and concluded that the optimized TAM-S formula had the greatest effect on the youth Internet addiction intervention. The roadmap of the intervention effect model is shown in Figure 7.

[figure(s) omitted; refer to PDF]

The intelligent psychological strategy technology analyzes the causes of Internet addiction and intervenes the Internet addiction problems of young people and can directly intervene Internet addiction for some simple Internet addiction problems.

3.2. Time-Consuming Comparison of Experimental Simulation with Different Algorithms

How much time is spent is a key indicator to measure the practicability of an algorithm. By comparing the running time of the three algorithms on the problem of intervening in youth Internet addiction movement, the algorithm with less time consuming is more practical.

Table 4 and Figure 8 are obtained by averaging the time-consuming calculations using the three algorithms using the data in the relevant libraries.

Table 4

Time-consuming comparison.

Algorithm	Problem processing is time-consuming (ms)	Analyzing scenario results takes time (ms)	Total time consuming (ms)
BAM	602.6	625.5	1228.1
FAM	447.9	420.2	868.1
TAM-S	356.6	367.5	724.1

[figure(s) omitted; refer to PDF]

In Figure 8, by comparing the running time of the three algorithms on the problem of intervening in adolescent Internet addiction movement, the algorithm with less time consumption is more practical. It shows that the TAM-S algorithm has the highest practicability.

3.3. The Experimental Comparison of the before and after Optimization Formulas of Intelligent Psychological Strategy Technology under Different Circumstances

After the intervention of two different psychological strategies and the exclusion of special reasons such as low contrast, the optimized algorithm can still maintain a high matching success rate. Compared with the direct experimental data, it can also be seen that the optimized algorithm performs better, as shown in Table 5 and Figure 9.

Table 5

Experimental comparison of before and after optimization formulas under different circumstances.

Compute $C$	IMT	IMST	ISR (%)	T/s
BAM	435	320	73.5	7.46
FAM	411	325	79.2	5.88
TAM-S	329	360	92.2	3.48

[figure(s) omitted; refer to PDF]

By comparing the formulas before and after optimization in different situations, it is found that the TAM-S algorithm has the best performance and the highest accuracy and can more obviously intervene in the problem of Internet addiction.

Comparative performance of the three psychological strategies and techniques to intervene in the youth Internet addiction movement is mentioned above, and low contrast is the fatal point for calculating the success rate of the intervention, which is a common problem of commonly used algorithms. Whether it is the traditional BAM algorithm or the improved FAM algorithm, it lacks processing ability for some problems. The TAM-S algorithm is better than the related traditional algorithms. The results are shown in Table 6 and Figure 10.

Table 6

Experimental comparison of three formulas under low contrast conditions.

Compute $C$	$\sigma =10$				$\sigma =20$
	IMT	IMST	ISR (%)	T/s	IMT	IMST	ISR (%)	T/s
BAM	773	578	74.9	11.58	630	393	62.4	9.73
FAM	657	494	75.2	7.31	587	379	64.6	6.52
TAM-S	588	476	81.1	5.95	483	359	74.5	4.94

[figure(s) omitted; refer to PDF]

Through the simulation calculation of the experimental data under the condition of ground comparison of the three experimental formulas, it is found that the optimized TAM-S algorithm is significantly better than the traditional BAM algorithm and is more suitable for adolescent Internet addiction intervention.

4. Conclusion

The intelligent psychological strategy technology facing the problem of adolescent Internet addiction is a hot field of intelligent psychology and plays a key role in the Internet addiction problem of this group of adolescents. Whether it is now or in the future, online psychological technology intervention will be a trend and also a development direction. This article mainly introduces the FAM algorithm and the similar TAM-S algorithm about its specific calculation method, interference factors, and improvement effect. Both traditional BAM and FAM can intervene in adolescents’ Internet addiction movement problems. The biggest disadvantage of the FAM algorithm is that it cannot guarantee the successful intervention of adolescents with special problems, which in turn leads to a decrease in the success rate of intervention, but this does not mean that the algorithm cannot be applied to related intelligent mental techniques, as other advantages of the algorithm are also visible. In view of the above experimental situation, it is not difficult to find from the comparison between FAM and TAM-S algorithm that TAM-S algorithm has more advantages in intervening in adolescent Internet addiction movement.

References

[1] C. Chou, M. C. Hsiao, "Internet addiction, usage, gratification, and pleasure experience: the Taiwan college students' case," Computers & Education, vol. 35 no. 1, pp. 65-80, DOI: 10.1016/S0360-1315(00)00019-1, 2000.

[2] M. Shaw, D. W. Black, "Internet addiction," CNS Drugs, vol. 22 no. 5, pp. 353-365, DOI: 10.2165/00023210-200822050-00001, 2008.

[3] K. Kambatla, G. Kollias, V. Kumar, A. Grama, "Trends in big data analytics," Journal of Parallel and Distributed Computing, vol. 74 no. 7, pp. 2561-2573, DOI: 10.1016/j.jpdc.2014.01.003, 2014.

[4] N. J. Nilsson, "Artificial intelligence: a modern approach," Applied Mechanics & Materials, vol. 263 no. 5, pp. 2829-2833, 2003.

[5] C. Wang, Q. Wang, K. Ren, N. Cao, W. Lou, "Toward secure and dependable storage services in cloud computing," IEEE Transactions on Services Computing, vol. 5 no. 2, pp. 220-232, DOI: 10.1109/TSC.2011.24, 2012.

[6] D. E. O'Leary, "Artificial intelligence and big data," Intelligent Systems, IEEE, vol. 28 no. 2, pp. 96-99, DOI: 10.1109/MIS.2013.39, 2013.

[7] J. L. Jin, Y. M. Wei, J. Ding, "Fuzzy comprehensive evaluation model based on improved analytic hierarchy process," Journal of Hydraulic Engineering, vol. 2, pp. 144-147, 2004.

[8] Z. Qi, C. Lu, R. Boutaba, "Cloud computing: state-of-the-art and research challenges," Journal of Internet Services and Applications, vol. 1 no. 1,DOI: 10.1007/s13174-010-0007-6, 2010.

[9] M. A. Vouk, "Cloud computing–issues, research and implementations," Journal of Computing & Information Technology, vol. 16 no. 4,DOI: 10.2498/cit.1001391, 2008.

[10] A. Iosup, S. Ostermann, M. N. Yigitbasi, R. Prodan, T. Fahringer, D. H. J. Epema, "Performance analysis of cloud computing services for many-tasks scientific computing," IEEE Transactions on Parallel & Distributed Systems, vol. 22 no. 6, pp. 931-945, DOI: 10.1109/TPDS.2011.66, 2011.

[11] K. E. Siomos, E. D. Dafouli, D. A. Braimiotis, O. D. Mouzas, N. V. Angelopoulos, "Internet addiction among Greek adolescent students," Cyberpsychology & Behavior, vol. 11 no. 6, pp. 653-657, DOI: 10.1089/cpb.2008.0088, 2008.

[12] H. Tinmaz, H. L. Jin, "A gender comparative study on south Korean youth internet addiction," Asia Pacific Journal of Information Systems, vol. 30 no. 3, pp. 590-613, DOI: 10.14329/apjis.2020.30.3.590, 2020.

[13] J. Y. Ha, S. M. Shin, "The effectiveness of youth internet addiction group counseling programs: a meta-analysis," The Korean Journal of Psychology: General, vol. 35 no. 1, pp. 191-216, 2016.

[14] J. Tang, Y. Yu, Y. Du, "Prevalence of internet addiction and its association with stressful life events and psychological symptoms among adolescent internet users," Addictive Behaviors, vol. 39 no. 3, pp. 744-747, DOI: 10.1016/j.addbeh.2013.12.010, 2014.

[15] S. Krishnan, D. Raviv, "2D feature tracking algorithm for motion analysis," Pattern Recognition, vol. 28 no. 8, pp. 1103-1126, DOI: 10.1016/0031-3203(95)00006-L, 1995.

[16] G. Wenbin, C. Zhiyan, "Research on the pathological psychological mechanism and comprehensive psychological intervention of internet addiction," Advances in Psychological Science, vol. 14 no. 4, pp. 596-603, 2006.

[17] Y. Bi, S. Wenliang, S. Yafeng, "An online study on the psychological and behavioral characteristics of college students with internet addiction," Chinese Journal of Clinical Psychology, vol. 13 no. 2, 2005.

[18] W. Zhu Kejing, T. S. Hanrong, "Causes and interventions of internet addiction in college students," Chinese Journal of Social Medicine, vol. 20 no. 1, pp. 15-19, 2003.

[19] D. Shengfu, "On the causes and countermeasures of internet addiction," Science and Technology and Dialectics, vol. 20 no. 6, pp. 50-53, 2003.

[20] J. Chengxin, Z. Yongsheng, "A fuzzy algorithm for maneuvering target tracking," Modern Radar, vol. 24 no. 6, 2002.

[21] J. Xinyue, L. Yue, L. Qinxue, "Psychological control and adolescent smartphone addiction: the role of network satisfaction of psychological needs and environmental sensitivity," Psychological Development and Education, vol. 38 no. 2, 2022.

[22] H. Wan, P. Hao, "A new attempt of dominance perspective theory in the psychological intervention of teenagers' internet addiction in the post-epidemic period," Journal of Hubei University of Science and Technology, vol. 41 no. 6, 2021.

[23] D. Yixian, T. Qihua, "Fuzzy comprehensive evaluation method based on neural network," Systems Engineering and Electronic Technology, vol. 27 no. 9, 2005.

[24] X. Yong, "Artificial intelligence and psychology," Popular Psychology, vol. 5, 2017.

[25] L. Xingyun, L. Xiaoqian, X. Yuanyuan, T. S. Zhu, "Artificial intelligence big data in psychology," Science and Technology Herald, vol. 37 no. 21, 2019.