Online mental health education teaching mode and empirical research based on Artificial intelligence

Abstract

With the continuous development of society, work pressure and study pressure are increasingly becoming the key factors affecting people’s physical and mental health, especially for college students, good knowledge and skills as well as superior psychological quality are the important factors for them to become excellent talents. As an important factor affecting people’s psychological quality, mental health has been paid more and more attention by people. The effect of traditional mental health education in daily education activities is not very obvious, which cannot achieve a profound impact on people’s mental health training and development. In this paper, based on the artificial intelligence online technology, an expert system of mental health education and daily consultation is designed. The system mainly integrates four application modules: psychological knowledge learning, psychological daily evaluation, psychological expert consultation and personal personalized management. The experiment shows that the artificial intelligence online expert consultation system designed in this paper can query daily psychological problems conveniently and quickly. At the same time, the treatment of human psychological problems can be realized through the intelligent online psychological counselling and the relief of psychological symptoms. The artificial intelligence online mental health education system has obvious practical value and social significance.

Keywords

Artificial intelligence online mental health education and teaching mental health expert consultation and treatment system psychological evaluation and evaluation mental disease treatment psychological knowledge and personalized management

1 Introduction

With the development of social economy and the change of people’s life style, people are under great social pressure, which leads to a lot of mental health problems. For college students, mental health problems have risen to national strategic problems, and the mental health problems of college students are becoming increasingly serious, which has even developed into a topic of social development [1 –3]. In order to further understand and help solve the mental health problems of college students, a large number of psychological counseling centers have been established, and a large number of psychological talents have been trained [4]. The traditional teaching methods of psychological consultation and psychological education are only limited to offline face-to-face psychological consultation and psychological counseling. However, due to the shortage of funds and the shortage of professional psychological consultants and educators, a large number of students get mental health education and treatment of psychological diseases [5 –7]. Therefore, based on the above situation, it is an inevitable choice to develop and apply a mental health education approach and teaching and education mode to meet the needs of social development, as well as the only way to social development.

For the research on the teaching mode of mental health education, a large number of research institutions and corresponding social researchers have done a lot of work [8]. The routine mental health education is mainly offline teaching work, mainly including psychological consultation by psychological counselors, psychological education by psychological teachers, etc. it has obvious teaching effect and teaching quality for lower grade students, and it has obvious effect on improving students’ psychological adaptability, but it has effect on college students and even social personnel However, it is very limited and even causes serious waste of resources [9 –11]. As a modern education and training mode based on experiential teaching, psychological expansion training is mainly based on practical psychological teaching to realize the practicality and efficiency of mental health education. This mental health education mode helps to reflect the initiative spirit and free will of students, and it attaches great importance to personal development, which embodies the immersion mental health education of knowledge+experience Education, however, this new teaching mode of mental health education is too complex, and it is still in a relatively difficult exploration stage [12 –14]. In the teaching stage of mental health education, it is mainly divided into four stages: understanding, association, system and method. It pays attention to the school part of mental health education as the basic unit of teaching, and emphasizes the leading role of psychological education practitioners. It unilaterally believes that students should give priority to learning in the psychological education classroom The classroom teaching corresponding to the physical and health education should be the most effective and reasonable education and teaching mode, but such a mental health teaching mode will make students lose the ability of independent learning of mental health, thus losing the autonomy of psychological counseling, and easily form a single thinking mode, so this one-sided view is increasingly eliminated with the development of economic society [15 –18]. Artificial intelligence, as a popular computer technology in today’s era, is widely used in education and teaching. Therefore, the combination of artificial intelligence and education and teaching has increasingly become the focus of people’s attention. Relevant scholars and research institutions have combined and put it into practice. The mainstream technology of combining artificial intelligence with mental health education includes fuzzy logic artificial Intelligent online technology, fuzzy reasoning artificial intelligence technology, neural network artificial intelligence mental health consulting technology, etc. [19 –22].

Based on the above analysis and research, it can be found that the design of mental health education mode which is reasonable and effective and adapts to social development has significant social significance and practical value. Therefore, based on artificial intelligence online technology, this paper designs an expert system for mental health education teaching and daily consultation, which mainly integrates four application modules: psychological knowledge learning, psychological daily evaluation, psychological expert consultation and personal personalized management. The experiment shows that the artificial intelligence online expert consultation system designed in this paper can query daily psychological problems conveniently and quickly. At the same time, the treatment of human psychological problems can be realized through the intelligent online psychological counseling and the relief of psychological symptoms. The artificial intelligence online mental health education system has obvious practical value and social significance. Machine learning approaches are utilised for studying particulate matter and their feasibility which includes different algorithms. Analysis of symptoms and disease prediction are processed in healthcare sector based on the wearable sensors which is based on IoT based scenario. Ergonomic based routines are processed in occupational health for estimation of natural language interfaces. Medical based decisions using novel intelligence for supporting soft computing and IoT. Simulation analysis based on IoT platform for risk chain management system [23 –28].

In this paper, the structure of the article is arranged as follows. The second section of this paper focuses on the analysis of the design principle of the online mental health education system based on artificial intelligence; the third section of this paper will carry out experiments based on the relevant student groups of a university and analyze the corresponding experimental data; finally, this paper will make a summary.

2 Design principle of mental health education system based on artificial intelligence online

The corresponding structure of the artificial intelligence online mental health expert system based on this paper is shown in Fig. 1. Its corresponding structure includes three main components: intelligent human-computer interaction interface and system, mental health knowledge base and Reasoning Intelligent mechanism. It can be seen from the figure that the corresponding rotation process is as follows: the mental health knowledge base system mainly interacts with the psychological consulting experts directly, focuses on collecting and sorting out the mental health knowledge of experts in related fields, and creates and maintains the knowledge base through the human-computer interaction mechanism; the mental health patients describe the corresponding mental problems through the human-computer interaction intelligent system, According to the facts provided by users, the Reasoning Intelligent mechanism system uses the background mental health knowledge base to solve the corresponding problems, and outputs the results of the problems to the patients with mental diseases through human-computer interaction.

Fig.1

The structure chart of artificial intelligence online mental health expert system.

The details of each link of the corresponding artificial intelligence online mental health expert system are shown in Table 1. It can be seen from the table that the details of the three main links of the artificial intelligence online mental health expert system designed in this paper are as follows:

Table 1

Details of each link of the artificial intelligence online mental health expert system

Component	Interface details
Intelligent human-computer interface and system	It is mainly a human-computer interface, which is essentially a bridge between artificial intelligence and the outside world. It is composed of a group of programs and corresponding hardware. Its main maintenance comes from the input, modification and maintenance of expert knowledge engineers. At the same time, it is essentially a medium and system for the system to output corresponding mental health solutions.
Mental health knowledge base	It is mainly used for knowledge reserve of system artificial intelligence expert system. Its specific operation includes operation, rule and model. It is generally realized by database. Meanwhile, it needs corresponding mental health knowledge engineer and corresponding database for maintenance and management.
Reasoning intelligence mechanism	In essence, it is the core system of the artificial intelligence online expert system in this paper. It mainly simulates the corresponding thinking process in the expert field, uses the relevant rules and control strategies already set in this paper to make the entire expert system choose reasonably, and effectively uses the knowledge in the corresponding knowledge base for analysis and discussion, and finally provides a reasoning for users The process. The whole reasoning mechanism can transform the corresponding mental health knowledge into a specific knowledge structure, and the corresponding reasoning system is mainly used for learning and training.

A. Intelligent human-computer interaction interface and system: it is mainly human-computer interaction interface, which is essentially a bridge between artificial intelligence and the outside world for communication and interaction. It is composed of a group of programs and corresponding hardware. Its main maintenance comes from the input, modification and maintenance of expert knowledge engineer, and it is also the corresponding mental health solution of system output in essence Media and system.

B. Mental health knowledge base: it is mainly used for the knowledge reserve of the system artificial intelligence expert system. Its specific operation includes operation, rules, models and other methods. It is generally realized by the database. At the same time, it needs corresponding mental health knowledge engineers and corresponding data base for maintenance and management.

C. Reasoning intelligence mechanism: in essence, it is the core system of the artificial intelligence online expert system in this paper. It mainly simulates the corresponding thinking process in the expert field, uses the relevant rules and control strategies that have been set in this paper, so that the entire expert system can be reasonably selected, and effectively uses the knowledge in the corresponding knowledge base for analysis and discussion, and finally the user provides a reasoning process. The whole reasoning mechanism can transform the corresponding mental health knowledge into a specific knowledge structure, and the corresponding reasoning system is mainly used for learning and training.

In the corresponding intelligent reasoning mechanism system, the most important algorithm mechanism is the algorithm mechanism used. The algorithm mechanism used in this paper is the weighted fuzzy logic reasoning mechanism, and the details of the corresponding reasoning mechanism are shown in Fig. 2. From the figure, we can see that the core formula of the weighted fuzzy reasoning mechanism used in this paper is shown in Formula 1 and formula 2, and the corresponding formula 1 represents the truth calculation formula In the corresponding formula, m1, m2, m3... xn represent the weighted proposition formula of the whole intelligent reasoning mechanism system. $T (S) = (\sum_{S = 1 - m} T (m_{ij}) * W^{n} (m_{ij})) / \sum_{j = 1}^{m} W^{n} (m_{j})$ (1) $W (S) = (\sum_{j = 1}^{m} m^{n} (m_{Ij})) / \sum_{j = 1}^{m} W^{n} (m_{j}) K$ (2)

Fig.2

Details of core algorithm of reasoning mechanism of artificial intelligence online expert system.

At the design level of corresponding mental health knowledge base, it mainly stores the relevant parameters required for the operation of all systems, and the corresponding mental health knowledge base system is shown in Fig. 3. From the figure, it can be seen that the corresponding knowledge base contains mental state, mental problems related symptoms and corresponding mental health problems countermeasures. In the actual knowledge base design, the corresponding design tables need to be divided into two kinds, the corresponding ones are mainly fact tables and corresponding noun tables. The corresponding fact table mainly includes the corresponding mental health name, the corresponding mental health problem fact type, the corresponding mental health fact classification, etc. the details of the corresponding classification table correspond to Table 2–4. In actual operation, it also needs to include the patient’s basic information table, the corresponding mental health problem patient fact table and the corresponding conclusion result table.

Fig.3

Mental health knowledge base system diagram.

Table 2

Facts of artificial intelligence online mental health expert system

Mental health fact name	Fact type	Weight
Fact 1	Type 1	Weight 1
Fact 2	Type 2	Weight 2
Fact 3	Type 3	Weight 3
Fact 1	Type 1	Weight 1
Fact 2	Type 2	Weight 2
Fact 3	Type 3	Weight 3
Fact 2	Type 1	Weight 1
Fact 3	Type 2	Weight 2
....	....	....

Table 3

Terms of online mental health expert system of artificial intelligence

Proper noun	Explain	Weight
Proper noun 1	Interpretation 1	Weight 1
Proper noun 2	Interpretation 2	Weight 2
Proper noun 3	Interpretation 3	Weight 3
Proper noun 4	Interpretation 4	Weight 4
Proper noun 5	Interpretation 5	Weight 5
Proper noun 6	Interpretation 6	Weight 6
Proper noun 7	Interpretation 7	Weight 7
Proper noun 8	Interpretation 8	Weight 8

Table 4

Conclusion of artificial intelligence online mental health expert system

Mental health fact name	Fact type	Truth of fact
Fact 1	Type 1	Truth of fact 1
Fact 2	Type 2	Truth of fact 2
Fact 3	Type 3	Truth of fact 3
Fact 1	Type 1	Truth of fact 1
Fact 2	Type 2	Truth of fact 2
Fact 3	Type 3	Truth of fact 3
Fact 1	Type 1	Truth of fact 1
Fact 2	Type 2	Truth of fact 2
Fact 3	Type 3	Truth of fact 3
Fact 4	Type 4	Truth of fact 4
...	...	...

At the knowledge acquisition level corresponding to the knowledge base, the main technology means of knowledge acquisition adopted in this paper is automatic acquisition technology, and the corresponding detailed schematic diagram of automatic acquisition is shown in Fig. 4. It can be seen from the figure that the main function of automatic acquisition technology is to continuously acquire the experience in the operation process of the system, constantly modify and expand the knowledge base of the system. At the same time, the system also needs to constantly summarize experience in practice, constantly summarize new knowledge, and constantly find and correct its own errors. Through continuous improvement of self, the knowledge base will eventually tend to gradually improve and be consistent. The technology involved in the whole process includes automatic pattern recognition technology, natural language understanding technology, machine learning technology, and so on. At the same time, it also has greater requirements for hardware.

Fig.4

Schematic diagram of automatic acquisition of mental health knowledge base.

The design detail schematic diagram of the corresponding reasoning mechanism design level is shown in Fig. 5. It can be seen from the figure that the main forward reasoning detail processing algorithm used in this paper is that the reasoning is relatively direct, and the relevant mental health patients are allowed to actively provide health facts.

Fig.5

Design detail schematic diagram of reasoning mechanism design level.

Based on the above design, the whole architecture of the artificial intelligence online expert consultation system is constructed, and the core algorithm and mechanism of the corresponding part are also presented.

3 Experiment and analysis

In order to verify the superiority of the artificial intelligence online expert consultation system designed in this paper, it is compared with the traditional mental health education mode. In this paper, the participants in the experiment are 200 students in a university, including 120 male students and 80 female students. The main method used in this paper is questionnaire survey.

Based on the two teaching methods for two months of course test, the corresponding survey results of mental health course teaching objectives after the test are shown in Fig. 6. It can be seen from the figure that the mental health education method used in this paper is more representative and effective.

Fig.6

Investigation of the effect of mental health education.

The corresponding Fig. 7 shows the corresponding satisfaction survey of two kinds of mental health education. The corresponding survey results show that the mental health education method used in this paper is more popular with students, and the corresponding satisfaction is about 20% higher than the traditional teaching method.

Fig.7

Pie chart of satisfaction survey of mental health education.

At the corresponding teaching effect level, it mainly evaluates and analyzes from the aspects of personality attitude improvement, psychological theory level, psychological adjustment ability, physical and mental quality and thinking mode transformation. The corresponding analysis results are shown in Fig. 8. It can be seen from Fig. 8 that the corresponding mental health teaching method designed in this paper is more effective.

Fig.8

Pie chart of investigation on teaching effect of mental health education.

In the corresponding level of teaching achievement testing, it mainly analyzes from four levels: written examination, practical application, practice+examination and corresponding psychological counseling. It can be seen from the Fig. 9 that the new teaching mode of mental health education designed in this paper has the characteristics of the form of mental health education that students want, and has achieved some teaching results.

Fig.9

Pie chart of investigation on teaching results of mental health education.

Based on the above experimental results and the results of investigation and analysis, it can be concluded that the artificial intelligence online expert consultation system designed in this paper has obvious advantages over the traditional teaching mode of mental health education, and has obvious practical significance and social benefits as a whole.

4 Conclusion

This paper mainly analyzes the problems existing in the current mental health education and the advantages and disadvantages of the current mainstream mental health education mode. Based on this background, it draws the following conclusions: with the continuous development of society, work pressure and learning pressure are increasingly becoming the key factors affecting people’s physical and mental health, especially for college students, good knowledge, skills and advantages The psychological quality of Yue is an important factor for him to become an excellent talent. As an important factor affecting people’s psychological quality, mental health has been paid more and more attention by people. The effect of traditional mental health education in daily education activities is not very obvious, which can not achieve a profound impact on people’s mental health training and development. In this context, this paper applies artificial intelligence to the teaching design of mental health education. Based on the online technology of artificial intelligence, an expert system of mental health education teaching and daily consultation is designed. The system mainly integrates four application modules: psychological knowledge learning, psychological daily evaluation, psychological expert consultation and personal personalized management. The experiment shows that the artificial intelligence online expert consultation system designed in this paper can query daily psychological problems conveniently and quickly. At the same time, the treatment of human psychological problems can be realized through the intelligent online psychological counseling and the relief of psychological symptoms. The artificial intelligence online mental health education system has obvious practical value and social significance. The follow-up research of this paper will focus on the research of psychotherapy technology under artificial intelligence technology.

References

Ertel

A.-M.

, Lupo

and Scheifhacken

, Heavy load and high potential: anthropogenic pressures and their impacts on the water quality along a lowland river (Western Bug, Ukraine)[J], Environmental Earth Sciences 18(1/2) (2012), 34–41.

Abdel-Basset

, Manogaran

, Gamal

and Chang

, A Novel Intelligent Medical Decision Support Model Based on Soft Computing and IoT, IEEE Internet of Things Journal, 2019.

Aziz

, Haque

M.M.

, Rahman

, et al., Flood estimation in ungauged catchments: application of artificial intelligence based methods for Eastern Australia[J], Stochastic Environmental Research and Risk Assessment 99(1) (2016), 113–119.

Muthu

B.A.

, Sivaparthipan

C.B.

, Manogaran

, Sundarasekar

, Kadry

, Shanthini

and Dasel

, IOT based wearable sensor for diseases prediction and symptom analysis in healthcare sector, Peer-to-Peer Networking and Applications, Pages 1–12.

McLean

C.A.

and Llewellyn

H.R.H.

, Towards and evidence base for online MBBS pathology education – a threshold effect is noted between the numbers of online pathology case submissions and the quality of online student work[J], Pathology 46 (2014), 74–84.

Connan

, Marcon

M.A.

, Mahmud

F.H.

, et al., Online education for gluten-free diet teaching: Development and usability testing of an e-learning module for children with concurrent celiac disease and type 1 diabetes[J], Pediatric Diabetes 124(8) (2019), 22–31.

Conway

M.A.

, Cabrera

O.A.

, Clarke-Walper

, et al., Sleep disturbance mediates the association of adverse childhood experiences with mental health symptoms and functional impairment in US soldiers[J], Journal of Sleep Research 45(3) (2020), 11–23.

De Choudhury

and Kiciman

, Integrating Artificial and Human Intelligence in Complex, Sensitive Problem Domains: Experiences from Mental Health[J], AI Magazine 39(3) (2018), 69–80.

Di Fabbrizio

, Aker

and Gaizauskas

, Summarizing Online Reviews Using Aspect Rating Distributions and Language Modeling[J], IEEE Intelligent Systems 28(3) (2013), 28–37.

10.

Dolan

, Teaching Online A Guide to Theory, Research, and Practice[J], Science 348(6242) (2015), 1436–1436.

11.

Grastien

and Anbulagan

, Diagnosis of Discrete Event Systems Using Satisfiability Algorithms: A Theoretical and Empirical Study[J], IEEE Transactions on Automatic Control 58(12) (2013), 3070–3083.

12.

Hunter

, Internet of instruments: Connectivity of research instruments and artificial intelligence could drastically advance experimental science[J], Embo Reports 19(12) (2018), 47267–47274.

13.

Karan, Saraf, Paul, Non-vitamin K antagonist oral anticoagulants (NOACs): clinical evidence and therapeutic considerations[J], Postgraduate Medical Journal 25(2) (2014), 56–65.

14.

Keating

and Nourbakhsh

, Viewpoint Teaching Artificial Intelligence and Humanity[J], Communications of the Acm 61(2) (2018), 29–32.

15.

Kleib

M.I.

, Integration of Health Informatics in Baccalaureate Nursing Education: Effectiveness of Face-to-Face vs. Online Teaching Methods[J], Mathematische Zeitschrift 263(4) (2012), 1279–1296.

16.

Kress

, Amos

, Flieg

, et al., Teaching Management and Research Competencies in Graduate Education through Student Participation in Hospital Quality Assurance reporting for Malnutrition Prevalence and Reimbursement[J], Journal of the Academy of Nutrition and Dietetics, 2018.

17.

Mooney

C.J.

and Kingsford

M.J.

, Sources and movements of Chironex fleckeri medusae using statolith elemental chemistry[J], Hydrobiologia 690(1) (2012), 269–277.

18.

Natural language interface model for the evaluation of ergonomic routines in occupational health (ILENA), Moya Jutinico Carlos Julio, Montenegro-Marin Carlos Enrique, Burgos Daniel, González Crespo Ruben, Journal of Ambient Intelligence and Humanized Computing (2019), 1611–1619.

19.

Prathik

, Uma

and Anuradha

, Particulate Matter on Human Health and their Feasibility Study Using Machine Learning Algorithms, Journal of Chemical and Pharmaceutical Research 8(9) (2016), 260–264.

20.

Gao

, Guo

, Liu

, Manogaran

, Chilamkurti

and Kadry

, Simulation analysis of supply chain risk management system based on IoT information platform, Enterprise Information Systems, Pages 1–25.

21.

Viktor, Hangy, Richárd, et al., A comparative empirical study on social media sentiment analysis over various genres and languages[J], Artificial Intelligence Review 5(3) (2016), 439–459.

22.

Vliet

L.M.V.

, Wall

E.V.D.

, Albada

, et al., The Validity of Using Analogue Patients in Practitioner–Patient Communication Research: Systematic Review and Meta-Analysis[J], Journal of General Internal Medicine 13(3) (2012), 217–228.

23.

Wedel

V.L.

, Bodies in Formation: An Ehy of Anatomy and Surgery Education. Edited by Rachel Prentice. Weehawken, NJ: Duke University Press. 312 pp. ISBN 978-0—3. $24.95 (paper)[J], American Journal of Physical Anthropology 154(1) (2014), 165–168.

24.

Wendt

, Pathak

, Lencz

, et al., Education and Socioeconomic Status Mask the Identification of Brain Cell Types in GWAS of Mental Health and Disease[J], Biological Psychiatry 87(9) (2020), 110–117.

25.

Wenjuan, Fan, Jingnan, et al., Investigating the impacting factors for the healthcare professionals to adopt artificial intelligence-based medical diagnosis support system (AIMDSS)[J], Annals of Operations Research 78(1) (2018), 22–31.

26.

Lei

, Krupinski

E.A.

and Jing

, Artificial intelligence will soon change the landscape of medical physics research and practice[J], Medical Physics 29(3) (2018), 69–80.

27.

Zollman

, Oersted Lecture: Physics education research and teaching modern Modern Physics[J], American Journal of Physics 84(8) (2016), 573–580.

28.

Zollman

, Oersted Lecture: Physics education research and teaching modern Modern Physics.[J], American Journal of Physics 16(1) (2016), 47–59.