Design of Interactive evaluation system for college students' psychological education based on improved KNN algorithm

Design of Interactive evaluation system for college students' psychological education based on improved KNN algorithm | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Design of Interactive evaluation system for college students' psychological education based on improved KNN algorithm Zhu Min This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2767590/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 27 Jun, 2023 Read the published version in Soft Computing → Version 1 posted 4 You are reading this latest preprint version Abstract Based on the research and investigation of the psycho-educational development and assessment of college students, this paper designs an interactive system for automatic evaluation of the psychoeducation of college students, which is based on the KNN data classification model and the current technical and environmental conditions. Based on the data and personal information of a college student's psychological census, screen the students' psychological evaluation data, analyzes the key information of the data, obtains the association rules of each factor, analyzes the experimental results. Aiming at the problem that KNN algorithm has low classification accuracy on unbalanced data, we proposes a weighted KNN hybrid algorithm. The harmonic weighted KNN classifier is added to the SVM-KNN classifier for fitting, and the SVM-KNN hybrid algorithm is jointly established. Combined with the principle of SVM-KNN hybrid data classifier, the improved algorithm is applied to a wider range of data value areas, and the appropriate algorithm is selected for data classification and prediction by judging the threshold size. For the data classification calculation method, the Euclidean distance calculation method is generally used to calculate the point-to-point distance in the plane coordinate system, as for hyper plane high-dimensional data, the improved algorithm uses a more suitable kernel function calculation method. According to the designed experimental step program, a series of basic performance such as the calculation rate of the algorithm and the system are tested, and the results show that it can be satisfied, which proves that the interactive automatic evaluation system of College Students' psychological education designed in this paper can effectively understand the psychological status of college students at this stage, find the students who need to focus on psychological counseling, and carry out psychological health education, so as to provide reference for the actual college students' psychological health education. Improved KNN algorithm psychological education Data mining Automatic evaluation system Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 1. Introduction College students not only need a strong physique to obtain specific scientific and cultural knowledge and skills, but also have a correct outlook on life, values and aesthetics, as well as specific ideological and moral character. Therefore, we need to understand the dynamic changes of students' ideology and pay close attention to their mental health [ 1 ]. The social environment in which college students live and their physiological age characteristics determine that the four-year university is an important period for the growth and development of college students. College students often face many common problems: emotional instability, over sensitivity, changes in education and living environment after enrollment, and lack of interpersonal coordination ability [ 2 ]. The increasing pressure from social competition has caused the mental health crisis of college students. This not only brings a heavy burden to education, but also brings great administrative risks [ 3 ]. Improving the quality of psychological education will improve the quality of professional and technical personnel, encourage business renewal, and play an important role in the sustainable development of the country. Therefore, to improve the quality of social psychology education at present, we must adhere to higher standards of specialization, diversification and humanization [ 4 ]. How to use these advanced technologies to describe individual mental health status, and use the remote evaluation services provided by the Internet to meet the evaluation needs of large groups, Keeping operating costs as low as possible on the basis of being able to meet the needs of the assessment is the main concern of this article [ 5 ].Therefore, we should not only understand the structure of mental health, but also develop more effective and reasonable mental health test questions, and evaluate them through the computer network platform, so as to use psychological measurement equipment. Software development and application must realize networking and networking [ 6 ]. This is the general trend of the development of modern psychoeducation. Data classification is an important part of data mining. At present, data mining has great research potential. As a field full of vitality and potential, the rational use of data mining technology can release the potential value of data [ 7 ]. Its technology is widely used in daily manufacturing, Internet construction, industrial production, scientific and technological research, medical diagnosis and treatment, financial investment, aviation technology and other fields. KNN classifier is an effective way to improve the accuracy of classification [ 8 ]. If the samples of manual classification algorithm have local sample imbalance, it will affect the classification accuracy of the algorithm to a certain extent. In order to improve the accuracy of KNN algorithm, many scientists have proposed various schemes to improve KNN algorithm, such as calculating the distance measurement of the algorithm, optimizing the K value selection method, preprocessing the sample data set, etc [ 9 ]. In the algorithm of data mining and its data collation classification, the support vector machine and the K-nearest neighbor algorithm have been widely used, and this paper evaluates and analyzes the advantages and disadvantages of the previous vector machine and algorithm on the basis of the research induction of the previous vector machine and algorithm, and then improves them respectively. [ 10 ]. 2. Related work The literature summarizes the concept of mental health education, that is, educators create positive factors for the psychology of educatees at all levels, and carry out specific psychological education activities. According to the literature, mental health education refers to the use of psychological knowledge and methods to improve the adaptability of the educated, maintain their mental health, and realize the educational practice of promoting psychological development [ 11 ]. The literature points out that mental health education follow the physical and mental development of educators, and provide psychological education and guidance to the actual body of educatees through scientific methods. It is implemented according to the physical and mental development, growth law and educational characteristics of the educated [ 12 ]. Therefore, it also opens a new era of psychological education. According to the literature, psychological education can maintain mental health, strengthen psychological personality and develop various psychological possibilities [ 13 ]. For example, the literature deals with the multidimensional causes of psychological problems, the separation of methods and means in psychological education, the complexity of educational objectives, and the contradiction between higher education personnel and the current work pattern [ 14 ]. The deficiency of psychological education and the lack of cognition have hindered the effective development of psychological education in the new era. According to the literature, the two main problems of modern psychological education are caused by the single method of psychological education and the gap between educational content and real life[ 15 ]. The literature adopts the matrix based data mining algorithm, embeds the processed data into the matrix, establishes the decision tree model, prunes on the basis of the initially generated decision model, obtains the classification rules, and analyzes the experimental results [ 16 ]. Starting from the objectives and requirements of current higher education students' psychological evaluation, the literature analyzes the process of psychological evaluation and counseling through the systematic management of psychological evaluation question bank, online psychological testing service, and consulting problem management, analyzes the feasibility of the system from the perspective of technology and business. Based on the design of the improved KNN algorithm with K-nearest neighbor method as the calculation logic, the classification paradigm and classification performance are improved, and the classification performance is also improved. The literature has improved the classification and clustering of KNN algorithm, which proves that the algorithm significantly improves the classification accuracy [ 17 ]. The classification form and clustering standard of KNN algorithm are improved, and the accuracy of each classification is significantly improved. The improved algorithm combining BP neural network and KNN algorithm is improved in the literature. This reduces the influence of K value on the accuracy of the algorithm and improves the accuracy of classification [ 18 ]. 3. Improvement of data mining KNN algorithm 3.1 knn algorithm basic data classification model KNN classification algorithm is one of the commonly used algorithms with the best classification effect. In KNN classification algorithm, when inputting new data with unknown category, it is necessary to judge the category of the new data with the help of the characteristics of other category data. Therefore, it is first necessary to extract the features of the new data and compare them with the original data, then select the k most adjacent data from the test set, count the main categories of the k most adjacent data, and classify the new data into this category. KNN algorithm realizes the whole data training process through simple steps, and the data classification efficiency is high. The KNN algorithm used in this paper classifies the local prior probability. First, for the given query example Xi, the calculation algorithm of prediction class YT is: $${y}_{t}=ar\text{g}\text{max} \sum E\left({y}_{t},c\right) c\in \left\{{c}_{1},{c}_{2},\dots ,{c}_{m}\right\} {x}_{i}\in N({X}_{r},k)$$ 1 At the same time: $$E(a,b)=\left\{\begin{array}{c}1 if a=b\\ 0 else\end{array}\right.$$ 2 The nearest set n of K is represented as: $$N\left(x,k\right)=\text{x}$$ 3 The probability of occurrence of class j data near query instance x i is expressed as: $${p\left({c}_{j}\right)}_{({x}_{t},k)}=\sum _{{x}_{i}\in N({x}_{t},k)}E\left({y}_{i},{c}_{j}\right)$$ 4 At this time, the calculation method of prediction class y t is expressed as: $${y}_{t}=ar\text{g}\text{max}\left\{{p\left({c}_{1}\right)}_{({x}_{t},k)},{p\left({c}_{2}\right)}_{({x}_{t},k)},\dots ,{p\left({c}_{m}\right)}_{({x}_{t},k)}\right\}$$ 5 3.2 Improved weighted KNN algorithm based on SVM There are many formulas for point-to-point distance calculation in KNN algorithm. In this paper, KNN algorithm uses the Euclidean distance calculation formula. The method for calculating the distance between points (𝑥 1 , 1 ) and points (𝑥 2 ,𝑦 2 ) in plane coordinates is: $$\rho =\sqrt{{\left({x}_{2}-{x}_{1}\right)}^{2}+{\left({y}_{2}-{y}_{1}\right)}^{2}}$$ 6 According to the above formula, we can get the distance between the sample points to be classified and each training sample point, then sort, then select the k nearest data points, calculate the number and judge the category of the samples to be classified. At the same time, in order to find the optimal hyperplane in the SVM classifier, we first need to transform the nonlinear problem, that is, solve the dual programming problem in solving the Lagrange function: $$minQ\left(\alpha \right)={\sum }_{i=1}^{n}{\alpha }_{i}+\frac{1}{2}{\sum }_{i=1}^{n}{\sum }_{j=1}^{n}{\alpha }_{i}{\alpha }_{j}{y}_{i}{y}_{j}K\left[\varnothing \left({x}_{i}\right),\varnothing \left({x}_{j}\right)\right]$$ 7 In solving the SVM binary classification problem, it is also necessary to transform the nonlinear problem into a simple linear programming problem. The calculation method is: $$minQ\left(\alpha \right)={\sum }_{i=1}^{n}{\alpha }_{i}-\frac{1}{2}{\sum }_{i=1}^{n}{\sum }_{j=1}^{n}{\alpha }_{i}{\alpha }_{j}{y}_{i}{y}_{j}K\left[\varnothing \left({x}_{i}\right),\varnothing \left({x}_{j}\right)\right]$$ 8 The calculation method of the relationship between positive and negative samples is: $${\sum }_{{y}_{i}}{\alpha }_{i}={\sum }_{y-i}{\alpha }_{I}=M$$ 9 According to the Lagrange principle, the samples in each category in the sample data conform to the following calculation formula: $${\alpha }_{i}\left[{y}_{i}\left({w}^{T}\varnothing \left({x}_{i}\right)+b\right)-1\right]=0$$ 10 When 𝑦 i = 1, the formula is: $${\sum }_{{y}_{i}}{\alpha }_{i}\left[{y}_{i}\left({w}^{T}\varnothing \left({x}_{i}\right)+b\right)-1\right]=0$$ 11 Namely: $${W}^{T}{\sum }_{{y}_{i}=1}{\alpha }_{i}\varnothing \left({x}_{i}\right)+{\sum }_{{y}_{i}=1}{\alpha }_{i}b-{\sum }_{{y}_{i}=1}{\alpha }_{i}=0$$ 12 Of which: $${\sum }_{{y}_{i}}{\alpha }_{i}=M$$ 13 In the data classification process of SVM, the vector fulcrum of each type of data represents the 1-NN classifier, and the difference of the distance between unknown samples can be calculated in the high-dimensional feature sample space. Finally, the optimal plane solution function of SVM is: $$f\left(x\right)=\text{s}\text{g}\text{n}\left\{{\sum }_{i}{\alpha }_{i}{y}_{i}⟨\varnothing \left({x}_{i}\right),\varnothing \left(x\right)⟩+b\right\}$$ 14 In the SVM algorithm, various sample vectors can be used as a fulcrum, which represents the 1-NN algorithm. According to the above derivation function, the SVM algorithm and KNN algorithm can be fitted, and the harmonic weighted KNN classifier is added to the SVM-KNN classifier to jointly establish the SVM-KNN hybrid algorithm. In order to further prove that the improved SVM-KNN algorithm in this paper has higher classification efficiency, in order to ensure the objective accuracy of data testing and reduce the accidental error of data experiments, the results of the hybrid algorithm used in this paper in data classification accuracy are shown in Fig. 2 compared with the traditional sknn algorithm: 4. Implementation of interactive automatic evaluation system for college students' Psychological Education 4.1 System infrastructure design The Interactive College Students' psychological education evaluation system designed in this paper focuses on the actual needs of college students at this stage. Considering the different needs of different students, as well as the better experience and human-computer interaction of users in using the evaluation system, the specific system infrastructure design is shown in Fig. 3 . 4.2 Testing and analysis of psychological education automatic evaluation system The functional test results of the Interactive College Students' psychological education evaluation system designed in this paper are shown in Table 1 . Among them, the system management function test mainly includes the test items of adding users, modifying and deleting information, and viewing the permissions of system users, and the test results are shown to be passed; The psychological evaluation information management module mainly includes the addition, modification and deletion of students' psychological evaluation information and students' psychological evaluation records. The test results show that they pass. Table 1 Main function test results of the system Main module Test child expected outcome Pass or not System Management User added Can add users pass User information modification User information can be modified pass User delete Can delete users pass system user permissions Show User Permissions pass Psychological evaluation information management Psychological assessment information addition, modification and deletion Possibility to add, modify and delete psychometric information pass Psychological Assessment Agency Additions, Modifications and Deletions Can add, modify and delete psychological assessment agency information pass Change of evaluation agency for psychological evaluation information Psychological evaluation agency information can be changed pass Psychological evaluation record Show Psychological Assessment Records pass psychological evaluation Demonstrate psychological assessment scores pass Browse Psychological Assessment Articles go to browse pass The system performance test mainly tests whether the Interactive College Students' psychological education evaluation system is in a relatively stable state in the operation process, and can maintain a high running speed in the process of using by multiple users, and does not occupy too much resources and energy consumption. The specific test items are shown in Table 2 . Table 2 System test performance requirements System performance characteristics Expected outcome Pass or not System efficiency Every user can strive to log in to the system pass pass System stability Continuous operation does not freeze pass Functionality of the system the longest response time is no more than 3 seconds pass pass System maintainability The maximum occupancy rate is less than 50% pass The throughput and clicks per second of the system are tested, and the results are shown in Fig. 4 . The results show that the maximum throughput of the system can reach 25000 bytes / millisecond, and all virtual users in the system can log in to the system normally and operate basic transactions. 4.3 Analysis of students' mental health evaluation results Finally, with the help of the systematic psychological evaluation system module, the psychological problems of students of different genders are counted and analyzed, and the frequent factors of psychological problems of college students at this stage are selected as the statistical factors of psychological problems, mainly including anxiety, depression, inferiority complex, social withdrawal, etc. the specific statistical results are shown in Fig. 5 . 5. Research on the evaluation and promotion development strategy of College Students' Psychological Education 5.1 demand analysis of Interactive College Students' psychological education evaluation system The interactive psychological evaluation system keeps students' information confidential. The system aims to manage and solve students' psychological problems, psychological state information and psychological counseling. The system administrator first accepts students' psychological evaluation applications according to their specific psychological conditions. Then through the evaluation data analysis of students' mental health, so as to provide psychological counseling and evaluation. Finally, the appropriate solutions of psychological evaluation and psychological problems are given. In general, the system has the following characteristics: ① security. Security includes two levels: information security and work security. The so-called information security means that the psychological evaluation information of college students can be fully protected without being artificially leaked. The so-called work safety operation is mainly aimed at students, psychologists and managers. In the workplace, different people have different permissions, managers have the highest permissions, and can provide the system with a complete operation log to evaluate whether there are violations. ② Convenience. Convenience means convenience and simplicity. At the operation level, the operation object will never be destroyed because of the cumbersome process. The usability of related functions is the most basic requirement. Each function provided should make students and psychologists feel practical and easy to use. At the same time, for those who install and manage the program, it is very easy to implement on Microsoft Windows system, and will improve the user experience after startup, making the user interface richer and more intuitive. ③ Adaptability. The system integrates student psychological evaluation module, psychological quality analysis and evaluation module, online psychological education module, comprehensive counseling management module, authority management module, problem student counseling module, psychological education database module and analysis and prediction module. It is a multi-functional system and an effective student psychological evaluation and guidance system. The automatic generation of psychological evaluation data has greatly expanded and deepened the content on the premise of meeting the needs of students' daily psychological work. 5.2 Analysis of mental health characteristics of college students in the new era The social background of the new era makes modern college students often have a richer and diverse cognitive perspective. The ways to contact external information are gradually increasing, and the information they contact is also very complex and changeable. Therefore, it is very necessary for schools to provide mental health education and mental health survey. In addition, in the development environment of modern society, the expression of many individual emotions is not as implicit and convergent as in the past. Relatively speaking, the expression of individual emotions in modern society is more diverse and diverse. Many college students show their daily life and express their emotions through online games, live broadcasts, online dating platforms and other ways. 5.3 Research on the development strategy of College Students' Psychological Education in the new era Mental health education for college students is not a one-dimensional cause, but a project that requires the participation of society as a whole, whether it is for teachers, parents, or the government, education departments and schools, it needs to be involved, and it has an unshirkable responsibility for the psychological education of college students. Education departments at all levels should strengthen the leadership and management of school mental health education and formulate a specific and feasible assessment system. Schools should not only do their own work in education, but also play an important role in mental health education on this basis, so schools should actively establish a group team of psychological education, properly arrange mental health education tasks, strengthen the management and decision-making arrangements of psychological education, and evaluate the status of teachers taking psychoeducation work. At the same time, for individual teachers, it is necessary to clarify their educational tasks and responsibilities. At the same time, according to the relevant assessment system, the assessment of mental health teachers and mental health teaching ability should be included in the assessment of teachers' daily work, so as to ensure the efficient and orderly promotion of mental health education. The specific role of psychological teachers is to dominate the structure of educators, coordinate the development of mental health teaching and the whole psychological work of student management departments, and it is the support system of mental health education. In the process of education, subject teachers need to establish a good teacher-student relationship, actively respect and discover the positive aspects of students, and establish a positive teacher-student relationship on the basis of individual equality, understanding and trust, which has a positive impact on improving their mental health. Because psychological education has the principle of integrity, teachers must integrate psychological health into the whole process of education and practical activities in order to make psychological health have an overall impact on college students. Compared with other traditional and universal education models, psychoeducation itself has its own unique characteristics, but this cannot erase the necessity and importance of mental health knowledge for the psychological growth of students and teachers, and it is urgent to integrate psychological education teaching projects into the curriculum. 6. Conclusion The environment in which college students live is the key period of their life growth and development, so they usually face many problems such as study, employment and interpersonal communication at the same time. At the same time, with the increasing competitive pressure in modern society, the known and unknown pressures and risks faced by college students are increasing. The mental health problem of college students is not a small-scale situation, but an "abnormal" normal. Therefore, the educational task undertaken by modern college education needs to be extended to the psychological field, and should be placed in the educational agenda in any case. Based on the research and investigation on the development and evaluation of college students' psychological education, this paper designs an interactive system for automatic evaluation of college students' psychological education. This system is integrated with the KNN data classification model and the current technical and environmental conditions, which can better complete the evaluation task of college students' psychological health. Through the analysis of the data of College Students' mental health education evaluation, we can see that there are many kinds of College Students' psychological problems and the incidence is high. Therefore, the research on Intelligent psychological evaluation system should be deepened to ensure the smooth development of college education at this stage. Declarations Conflict of interest The authors declare that they have no conflict of interests Ethical approval This article does not contain any studies with human participants performed by any of the authors. Data Availability Data will be made available on request. References Oswalt SB, Lederer AM, Chestnut-Steich K, Day C, Halbritter A, Ortiz D (2020) Trends in college students’ mental health diagnoses and utilization of services, 2009–2015. J Am Coll Health 68(1):41–51 Selvaraj PR, Bhat CS (2018) Predicting the mental health of college students with psychological capital. J Mental Health 27(3):279–287 Kitzrow MA (2003) The mental health needs of today's college students: Challenges and recommendations. J Student Affairs Res Pract 41(1):167–181 Manigault AW, Woody A, Zoccola PM, Dickerson SS (2018) Education is associated with the magnitude of cortisol responses to psychosocial stress in college students. Int J Behav Med 25(5):532–539 Horita R, Nishio A, Yamamoto M (2021) The effect of remote learning on the mental health of first year university students in Japan. Psychiatry Res 295:113561 Zinchenko YP, Dorozhkin EM, Zeer EF (2020) Psychological and pedagogical bases for determining the future of vocational education: Vectors of development. Educ Sci J 22(3):11–35 Manguy AM, Joubert L, Bansemer L (2016) Psychosocial service needs of pediatric transport accident survivors: Using clinical data-mining to establish demographic and service usage characteristics. Soc Work Health Care 55(8):595–613 Amra IAA, Maghari AY (2017) “Students performance prediction using KNN and Naïve Bayesian,” In 2017 8th International Conference on Information Technology (ICIT), pp. 909–913, Liu S, Zhu P, Qin S (2018) “An improved weighted KNN algorithm for imbalanced data classification,” In 2018 IEEE 4th International Conference on Computer and Communications (ICCC), pp. 1814–1819, Raikwal JS, Saxena K (2012) Performance evaluation of SVM and k-nearest neighbor algorithm over medical data set. Int J Comput Appl 50:14 Levin ME, Hayes SC, Pistorello J, Seeley JR (2016) Web-based self‐help for preventing mental health problems in universities: Comparing acceptance and commitment training to mental health education. J Clin Psychol 72(3):207–225 Happell B, Byrne L, McAllister M, Lampshire D, Roper C, Gaskin CJ, …, Hamer H (2014) Consumer involvement in the tertiary-level education of mental health professionals: A systematic review. Int J Ment Health Nurs 23(1):3–16 Cornaglia F, Crivellaro E, McNally S (2015) Mental health and education decisions. Labour Econ 33:1–12 Wu W, Qu G, Wang L, Tang X, Sun YH (2019) Meta-analysis of the mental health status of left‐behind children in China. J Paediatr Child Health 55(3):260–270 Kratt D (2018) Teachers’ perspectives on educator mental health competencies: A qualitative case study. Am J Qualitative Res 2(1):22–40 Bravo AJ, Villarosa-Hurlocker MC, Pearson MR (2018) College student mental health: An evaluation of the DSM–5 self-rated Level 1 cross-cutting symptom measure. Psychol Assess 30(10):1382 Tarmizi SSA, Mutalib S, Hamid NHA, Rahman SA (2019) A review on student attrition in higher education using big data analytics and data mining techniques. Int J Mod Educ Comput Sci 11(8):1–14 Abuzneid MA, Mahmood A (2018) Enhanced human face recognition using LBPH descriptor, multi-KNN, and back-propagation neural network. IEEE access 6:20641–20651 Cite Share Download PDF Status: Published Journal Publication published 27 Jun, 2023 Read the published version in Soft Computing → Version 1 posted Reviewers agreed at journal 19 May, 2023 Reviewers invited by journal 19 May, 2023 Editor assigned by journal 11 Apr, 2023 First submitted to journal 02 Apr, 2023 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-2767590","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":201976598,"identity":"ae5b42e4-a4d0-4078-9e60-75c84621ee85","order_by":0,"name":"Zhu Min","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5ElEQVRIiWNgGAWjYDACCSBOYLCRk+dvbDjwwcDGjlgtacaGMw43HpxRkJZMnBYGhsOJDQfSmw/zfDjE2EBIh/zsHtMND3cwMzY2HGw4bGNwgJmB/fDRDfi0MM45Y3Yj8QwbMztzY8PhHIM7fAw8aWk38GlhlsgBamnjYWME2ZJj8IyZQYLHDK8WNogWCR6GA4kNhy0MDjM2ENLCA9FiIAHWwkCMFgmJtDKglgQDwxkHGw72GKQlsxHyi/yM5G03f7b9r5/P3/74w48/Nnb87IeP4dWCxXekKR8Fo2AUjIJRgA0AADGMUeDx3FbPAAAAAElFTkSuQmCC","orcid":"","institution":"Guangzhou City Polytechnic","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Zhu","middleName":"","lastName":"Min","suffix":""}],"badges":[],"createdAt":"2023-04-02 11:56:01","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-2767590/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2767590/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00500-023-08794-6","type":"published","date":"2023-06-27T21:26:37+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":37381544,"identity":"b963a620-793d-4eff-b1ac-62d163e4a775","added_by":"auto","created_at":"2023-05-23 14:12:12","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":10747,"visible":true,"origin":"","legend":"\u003cp\u003eExample of KNN algorithm classification\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-2767590/v1/d185925a4c5bef9f6fd7cdf1.png"},{"id":37381548,"identity":"bc9c06aa-868f-4359-8f32-fd574e26eeeb","added_by":"auto","created_at":"2023-05-23 14:12:12","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":14129,"visible":true,"origin":"","legend":"\u003cp\u003eComparison diagram of average accuracy of two types of algorithms\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-2767590/v1/657082ac512c05d22728d0cf.png"},{"id":37382532,"identity":"59abfc33-56d4-442c-8f15-986b73d9a76e","added_by":"auto","created_at":"2023-05-23 14:20:12","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":48823,"visible":true,"origin":"","legend":"\u003cp\u003eSchematic diagram of system architecture design\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-2767590/v1/31aa30fbc81d6a4b06838778.png"},{"id":37381545,"identity":"5280bab6-66a7-4e13-b131-ba970ffbdeb8","added_by":"auto","created_at":"2023-05-23 14:12:12","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":37649,"visible":true,"origin":"","legend":"\u003cp\u003eSystem throughput test\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-2767590/v1/0592e5c1c2e9aba9b3cee80a.png"},{"id":37382533,"identity":"3a788d0a-8bda-476d-9119-baa2510d5230","added_by":"auto","created_at":"2023-05-23 14:20:12","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":23612,"visible":true,"origin":"","legend":"\u003cp\u003eAverage statistical results of students with psychological problems of different genders\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-2767590/v1/276526eceebcbcc1a0a38a4a.png"},{"id":44732125,"identity":"f7dbf0d7-531b-4029-9e58-2798cf674db5","added_by":"auto","created_at":"2023-10-16 21:53:15","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":549466,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2767590/v1/b24981a7-f98c-4c0a-9f8a-c2f17b45905b.pdf"}],"financialInterests":"","formattedTitle":"Design of Interactive evaluation system for college students' psychological education based on improved KNN algorithm","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eCollege students not only need a strong physique to obtain specific scientific and cultural knowledge and skills, but also have a correct outlook on life, values and aesthetics, as well as specific ideological and moral character. Therefore, we need to understand the dynamic changes of students' ideology and pay close attention to their mental health [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. The social environment in which college students live and their physiological age characteristics determine that the four-year university is an important period for the growth and development of college students. College students often face many common problems: emotional instability, over sensitivity, changes in education and living environment after enrollment, and lack of interpersonal coordination ability [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. The increasing pressure from social competition has caused the mental health crisis of college students. This not only brings a heavy burden to education, but also brings great administrative risks [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. Improving the quality of psychological education will improve the quality of professional and technical personnel, encourage business renewal, and play an important role in the sustainable development of the country. Therefore, to improve the quality of social psychology education at present, we must adhere to higher standards of specialization, diversification and humanization [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. How to use these advanced technologies to describe individual mental health status, and use the remote evaluation services provided by the Internet to meet the evaluation needs of large groups, Keeping operating costs as low as possible on the basis of being able to meet the needs of the assessment is the main concern of this article [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e].Therefore, we should not only understand the structure of mental health, but also develop more effective and reasonable mental health test questions, and evaluate them through the computer network platform, so as to use psychological measurement equipment. Software development and application must realize networking and networking [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. This is the general trend of the development of modern psychoeducation.\u003c/p\u003e \u003cp\u003eData classification is an important part of data mining. At present, data mining has great research potential. As a field full of vitality and potential, the rational use of data mining technology can release the potential value of data [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. Its technology is widely used in daily manufacturing, Internet construction, industrial production, scientific and technological research, medical diagnosis and treatment, financial investment, aviation technology and other fields. KNN classifier is an effective way to improve the accuracy of classification [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. If the samples of manual classification algorithm have local sample imbalance, it will affect the classification accuracy of the algorithm to a certain extent. In order to improve the accuracy of KNN algorithm, many scientists have proposed various schemes to improve KNN algorithm, such as calculating the distance measurement of the algorithm, optimizing the K value selection method, preprocessing the sample data set, etc [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. In the algorithm of data mining and its data collation classification, the support vector machine and the K-nearest neighbor algorithm have been widely used, and this paper evaluates and analyzes the advantages and disadvantages of the previous vector machine and algorithm on the basis of the research induction of the previous vector machine and algorithm, and then improves them respectively. [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e].\u003c/p\u003e"},{"header":"2. Related work","content":"\u003cp\u003eThe literature summarizes the concept of mental health education, that is, educators create positive factors for the psychology of educatees at all levels, and carry out specific psychological education activities. According to the literature, mental health education refers to the use of psychological knowledge and methods to improve the adaptability of the educated, maintain their mental health, and realize the educational practice of promoting psychological development [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. The literature points out that mental health education follow the physical and mental development of educators, and provide psychological education and guidance to the actual body of educatees through scientific methods. It is implemented according to the physical and mental development, growth law and educational characteristics of the educated [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. Therefore, it also opens a new era of psychological education. According to the literature, psychological education can maintain mental health, strengthen psychological personality and develop various psychological possibilities [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. For example, the literature deals with the multidimensional causes of psychological problems, the separation of methods and means in psychological education, the complexity of educational objectives, and the contradiction between higher education personnel and the current work pattern [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. The deficiency of psychological education and the lack of cognition have hindered the effective development of psychological education in the new era. According to the literature, the two main problems of modern psychological education are caused by the single method of psychological education and the gap between educational content and real life[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe literature adopts the matrix based data mining algorithm, embeds the processed data into the matrix, establishes the decision tree model, prunes on the basis of the initially generated decision model, obtains the classification rules, and analyzes the experimental results [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. Starting from the objectives and requirements of current higher education students' psychological evaluation, the literature analyzes the process of psychological evaluation and counseling through the systematic management of psychological evaluation question bank, online psychological testing service, and consulting problem management, analyzes the feasibility of the system from the perspective of technology and business. Based on the design of the improved KNN algorithm with K-nearest neighbor method as the calculation logic, the classification paradigm and classification performance are improved, and the classification performance is also improved. The literature has improved the classification and clustering of KNN algorithm, which proves that the algorithm significantly improves the classification accuracy [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]. The classification form and clustering standard of KNN algorithm are improved, and the accuracy of each classification is significantly improved. The improved algorithm combining BP neural network and KNN algorithm is improved in the literature. This reduces the influence of K value on the accuracy of the algorithm and improves the accuracy of classification [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e].\u003c/p\u003e"},{"header":"3. Improvement of data mining KNN algorithm","content":"\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e3.1 knn algorithm basic data classification model\u003c/h2\u003e \u003cp\u003eKNN classification algorithm is one of the commonly used algorithms with the best classification effect. In KNN classification algorithm, when inputting new data with unknown category, it is necessary to judge the category of the new data with the help of the characteristics of other category data. Therefore, it is first necessary to extract the features of the new data and compare them with the original data, then select the k most adjacent data from the test set, count the main categories of the k most adjacent data, and classify the new data into this category.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eKNN algorithm realizes the whole data training process through simple steps, and the data classification efficiency is high. The KNN algorithm used in this paper classifies the local prior probability. First, for the given query example Xi, the calculation algorithm of prediction class YT is:\u003cdiv id=\"Equ1\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ1\" name=\"EquationSource\"\u003e\n$${y}_{t}=ar\\text{g}\\text{max} \\sum E\\left({y}_{t},c\\right) c\\in \\left\\{{c}_{1},{c}_{2},\\dots ,{c}_{m}\\right\\} {x}_{i}\\in N({X}_{r},k)$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e1\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eAt the same time:\u003cdiv id=\"Equ2\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ2\" name=\"EquationSource\"\u003e\n$$E(a,b)=\\left\\{\\begin{array}{c}1 if a=b\\\\ 0 else\\end{array}\\right.$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e2\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eThe nearest set n of K is represented as:\u003cdiv id=\"Equ3\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ3\" name=\"EquationSource\"\u003e\n$$N\\left(x,k\\right)=\\text{x}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e3\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eThe probability of occurrence of class j data near query instance x\u003csub\u003ei\u003c/sub\u003e is expressed as:\u003cdiv id=\"Equ4\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ4\" name=\"EquationSource\"\u003e\n$${p\\left({c}_{j}\\right)}_{({x}_{t},k)}=\\sum _{{x}_{i}\\in N({x}_{t},k)}E\\left({y}_{i},{c}_{j}\\right)$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e4\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eAt this time, the calculation method of prediction class y\u003csub\u003et\u003c/sub\u003e is expressed as:\u003cdiv id=\"Equ5\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ5\" name=\"EquationSource\"\u003e\n$${y}_{t}=ar\\text{g}\\text{max}\\left\\{{p\\left({c}_{1}\\right)}_{({x}_{t},k)},{p\\left({c}_{2}\\right)}_{({x}_{t},k)},\\dots ,{p\\left({c}_{m}\\right)}_{({x}_{t},k)}\\right\\}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e5\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e3.2 Improved weighted KNN algorithm based on SVM\u003c/h2\u003e \u003cp\u003eThere are many formulas for point-to-point distance calculation in KNN algorithm. In this paper, KNN algorithm uses the Euclidean distance calculation formula. The method for calculating the distance between points (\u0026#119909;\u003csub\u003e1\u003c/sub\u003e,\u003csub\u003e1\u003c/sub\u003e) and points (\u0026#119909;\u003csub\u003e2\u003c/sub\u003e,\u0026#119910;\u003csub\u003e2\u003c/sub\u003e) in plane coordinates is:\u003cdiv id=\"Equ6\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ6\" name=\"EquationSource\"\u003e\n$$\\rho =\\sqrt{{\\left({x}_{2}-{x}_{1}\\right)}^{2}+{\\left({y}_{2}-{y}_{1}\\right)}^{2}}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e6\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eAccording to the above formula, we can get the distance between the sample points to be classified and each training sample point, then sort, then select the k nearest data points, calculate the number and judge the category of the samples to be classified. At the same time, in order to find the optimal hyperplane in the SVM classifier, we first need to transform the nonlinear problem, that is, solve the dual programming problem in solving the Lagrange function:\u003cdiv id=\"Equ7\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ7\" name=\"EquationSource\"\u003e\n$$minQ\\left(\\alpha \\right)={\\sum }_{i=1}^{n}{\\alpha }_{i}+\\frac{1}{2}{\\sum }_{i=1}^{n}{\\sum }_{j=1}^{n}{\\alpha }_{i}{\\alpha }_{j}{y}_{i}{y}_{j}K\\left[\\varnothing \\left({x}_{i}\\right),\\varnothing \\left({x}_{j}\\right)\\right]$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e7\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eIn solving the SVM binary classification problem, it is also necessary to transform the nonlinear problem into a simple linear programming problem. The calculation method is:\u003cdiv id=\"Equ8\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ8\" name=\"EquationSource\"\u003e\n$$minQ\\left(\\alpha \\right)={\\sum }_{i=1}^{n}{\\alpha }_{i}-\\frac{1}{2}{\\sum }_{i=1}^{n}{\\sum }_{j=1}^{n}{\\alpha }_{i}{\\alpha }_{j}{y}_{i}{y}_{j}K\\left[\\varnothing \\left({x}_{i}\\right),\\varnothing \\left({x}_{j}\\right)\\right]$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e8\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eThe calculation method of the relationship between positive and negative samples is:\u003cdiv id=\"Equ9\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ9\" name=\"EquationSource\"\u003e\n$${\\sum }_{{y}_{i}}{\\alpha }_{i}={\\sum }_{y-i}{\\alpha }_{I}=M$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e9\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eAccording to the Lagrange principle, the samples in each category in the sample data conform to the following calculation formula:\u003cdiv id=\"Equ10\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ10\" name=\"EquationSource\"\u003e\n$${\\alpha }_{i}\\left[{y}_{i}\\left({w}^{T}\\varnothing \\left({x}_{i}\\right)+b\\right)-1\\right]=0$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e10\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eWhen \u0026#119910;\u003csub\u003ei\u003c/sub\u003e\u0026thinsp;=\u0026thinsp;1, the formula is:\u003cdiv id=\"Equ11\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ11\" name=\"EquationSource\"\u003e\n$${\\sum }_{{y}_{i}}{\\alpha }_{i}\\left[{y}_{i}\\left({w}^{T}\\varnothing \\left({x}_{i}\\right)+b\\right)-1\\right]=0$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e11\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eNamely:\u003cdiv id=\"Equ12\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ12\" name=\"EquationSource\"\u003e\n$${W}^{T}{\\sum }_{{y}_{i}=1}{\\alpha }_{i}\\varnothing \\left({x}_{i}\\right)+{\\sum }_{{y}_{i}=1}{\\alpha }_{i}b-{\\sum }_{{y}_{i}=1}{\\alpha }_{i}=0$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e12\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eOf which:\u003cdiv id=\"Equ13\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ13\" name=\"EquationSource\"\u003e\n$${\\sum }_{{y}_{i}}{\\alpha }_{i}=M$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e13\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eIn the data classification process of SVM, the vector fulcrum of each type of data represents the 1-NN classifier, and the difference of the distance between unknown samples can be calculated in the high-dimensional feature sample space. Finally, the optimal plane solution function of SVM is:\u003cdiv id=\"Equ14\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ14\" name=\"EquationSource\"\u003e\n$$f\\left(x\\right)=\\text{s}\\text{g}\\text{n}\\left\\{{\\sum }_{i}{\\alpha }_{i}{y}_{i}\u0026lang;\\varnothing \\left({x}_{i}\\right),\\varnothing \\left(x\\right)\u0026rang;+b\\right\\}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e14\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e \u003cp\u003eIn the SVM algorithm, various sample vectors can be used as a fulcrum, which represents the 1-NN algorithm. According to the above derivation function, the SVM algorithm and KNN algorithm can be fitted, and the harmonic weighted KNN classifier is added to the SVM-KNN classifier to jointly establish the SVM-KNN hybrid algorithm.\u003c/p\u003e \u003cp\u003eIn order to further prove that the improved SVM-KNN algorithm in this paper has higher classification efficiency, in order to ensure the objective accuracy of data testing and reduce the accidental error of data experiments, the results of the hybrid algorithm used in this paper in data classification accuracy are shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e compared with the traditional sknn algorithm:\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"4. Implementation of interactive automatic evaluation system for college students' Psychological Education","content":"\u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e4.1 System infrastructure design\u003c/h2\u003e \u003cp\u003eThe Interactive College Students' psychological education evaluation system designed in this paper focuses on the actual needs of college students at this stage. Considering the different needs of different students, as well as the better experience and human-computer interaction of users in using the evaluation system, the specific system infrastructure design is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e4.2 Testing and analysis of psychological education automatic evaluation system\u003c/h2\u003e \u003cp\u003eThe functional test results of the Interactive College Students' psychological education evaluation system designed in this paper are shown in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. Among them, the system management function test mainly includes the test items of adding users, modifying and deleting information, and viewing the permissions of system users, and the test results are shown to be passed; The psychological evaluation information management module mainly includes the addition, modification and deletion of students' psychological evaluation information and students' psychological evaluation records. The test results show that they pass.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eMain function test results of the system\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMain module\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTest child\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eexpected outcome\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003ePass or not\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e \u003cp\u003eSystem Management\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eUser added\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eCan add users\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003epass\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eUser information modification\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eUser information can be modified\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003epass\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eUser delete\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eCan delete users\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003epass\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003esystem user permissions\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eShow User Permissions\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003epass\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"5\" rowspan=\"6\"\u003e \u003cp\u003ePsychological evaluation information management\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePsychological assessment information addition, modification and deletion\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePossibility to add, modify and delete psychometric information\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003epass\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePsychological Assessment Agency Additions, Modifications and Deletions\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eCan add, modify and delete psychological assessment agency information\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003epass\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eChange of evaluation agency for psychological evaluation information\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePsychological evaluation agency information can be changed\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003epass\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePsychological evaluation record\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eShow Psychological Assessment Records\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003epass\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003epsychological evaluation\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eDemonstrate psychological assessment scores\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003epass\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eBrowse Psychological Assessment Articles\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003ego to browse\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003epass\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eThe system performance test mainly tests whether the Interactive College Students' psychological education evaluation system is in a relatively stable state in the operation process, and can maintain a high running speed in the process of using by multiple users, and does not occupy too much resources and energy consumption. The specific test items are shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eSystem test performance requirements\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSystem performance characteristics\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eExpected outcome\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePass or not\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eSystem efficiency\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eEvery user can strive to log in to the system\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003epass\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003epass\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSystem stability\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eContinuous operation does not freeze\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003epass\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eFunctionality of the system\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003ethe longest response time is no more than 3 seconds\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003epass\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003epass\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSystem maintainability\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eThe maximum occupancy rate is less than 50%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003epass\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eThe throughput and clicks per second of the system are tested, and the results are shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe results show that the maximum throughput of the system can reach 25000 bytes / millisecond, and all virtual users in the system can log in to the system normally and operate basic transactions.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003e4.3 Analysis of students' mental health evaluation results\u003c/h2\u003e \u003cp\u003eFinally, with the help of the systematic psychological evaluation system module, the psychological problems of students of different genders are counted and analyzed, and the frequent factors of psychological problems of college students at this stage are selected as the statistical factors of psychological problems, mainly including anxiety, depression, inferiority complex, social withdrawal, etc. the specific statistical results are shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"5. Research on the evaluation and promotion development strategy of College Students' Psychological Education","content":"\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003e5.1 demand analysis of Interactive College Students' psychological education evaluation system\u003c/h2\u003e \u003cp\u003eThe interactive psychological evaluation system keeps students' information confidential. The system aims to manage and solve students' psychological problems, psychological state information and psychological counseling. The system administrator first accepts students' psychological evaluation applications according to their specific psychological conditions. Then through the evaluation data analysis of students' mental health, so as to provide psychological counseling and evaluation. Finally, the appropriate solutions of psychological evaluation and psychological problems are given.\u003c/p\u003e \u003cp\u003eIn general, the system has the following characteristics: ① security. Security includes two levels: information security and work security. The so-called information security means that the psychological evaluation information of college students can be fully protected without being artificially leaked. The so-called work safety operation is mainly aimed at students, psychologists and managers. In the workplace, different people have different permissions, managers have the highest permissions, and can provide the system with a complete operation log to evaluate whether there are violations. ② Convenience. Convenience means convenience and simplicity. At the operation level, the operation object will never be destroyed because of the cumbersome process. The usability of related functions is the most basic requirement. Each function provided should make students and psychologists feel practical and easy to use. At the same time, for those who install and manage the program, it is very easy to implement on Microsoft Windows system, and will improve the user experience after startup, making the user interface richer and more intuitive. ③ Adaptability. The system integrates student psychological evaluation module, psychological quality analysis and evaluation module, online psychological education module, comprehensive counseling management module, authority management module, problem student counseling module, psychological education database module and analysis and prediction module. It is a multi-functional system and an effective student psychological evaluation and guidance system. The automatic generation of psychological evaluation data has greatly expanded and deepened the content on the premise of meeting the needs of students' daily psychological work.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003e5.2 Analysis of mental health characteristics of college students in the new era\u003c/h2\u003e \u003cp\u003eThe social background of the new era makes modern college students often have a richer and diverse cognitive perspective. The ways to contact external information are gradually increasing, and the information they contact is also very complex and changeable. Therefore, it is very necessary for schools to provide mental health education and mental health survey. In addition, in the development environment of modern society, the expression of many individual emotions is not as implicit and convergent as in the past. Relatively speaking, the expression of individual emotions in modern society is more diverse and diverse. Many college students show their daily life and express their emotions through online games, live broadcasts, online dating platforms and other ways.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec13\" class=\"Section2\"\u003e \u003ch2\u003e5.3 Research on the development strategy of College Students' Psychological Education in the new era\u003c/h2\u003e \u003cp\u003eMental health education for college students is not a one-dimensional cause, but a project that requires the participation of society as a whole, whether it is for teachers, parents, or the government, education departments and schools, it needs to be involved, and it has an unshirkable responsibility for the psychological education of college students. Education departments at all levels should strengthen the leadership and management of school mental health education and formulate a specific and feasible assessment system. Schools should not only do their own work in education, but also play an important role in mental health education on this basis, so schools should actively establish a group team of psychological education, properly arrange mental health education tasks, strengthen the management and decision-making arrangements of psychological education, and evaluate the status of teachers taking psychoeducation work. At the same time, for individual teachers, it is necessary to clarify their educational tasks and responsibilities. At the same time, according to the relevant assessment system, the assessment of mental health teachers and mental health teaching ability should be included in the assessment of teachers' daily work, so as to ensure the efficient and orderly promotion of mental health education. The specific role of psychological teachers is to dominate the structure of educators, coordinate the development of mental health teaching and the whole psychological work of student management departments, and it is the support system of mental health education. In the process of education, subject teachers need to establish a good teacher-student relationship, actively respect and discover the positive aspects of students, and establish a positive teacher-student relationship on the basis of individual equality, understanding and trust, which has a positive impact on improving their mental health. Because psychological education has the principle of integrity, teachers must integrate psychological health into the whole process of education and practical activities in order to make psychological health have an overall impact on college students. Compared with other traditional and universal education models, psychoeducation itself has its own unique characteristics, but this cannot erase the necessity and importance of mental health knowledge for the psychological growth of students and teachers, and it is urgent to integrate psychological education teaching projects into the curriculum.\u003c/p\u003e \u003c/div\u003e"},{"header":"6. Conclusion","content":"\u003cp\u003eThe environment in which college students live is the key period of their life growth and development, so they usually face many problems such as study, employment and interpersonal communication at the same time. At the same time, with the increasing competitive pressure in modern society, the known and unknown pressures and risks faced by college students are increasing. The mental health problem of college students is not a small-scale situation, but an \"abnormal\" normal. Therefore, the educational task undertaken by modern college education needs to be extended to the psychological field, and should be placed in the educational agenda in any case. Based on the research and investigation on the development and evaluation of college students' psychological education, this paper designs an interactive system for automatic evaluation of college students' psychological education. This system is integrated with the KNN data classification model and the current technical and environmental conditions, which can better complete the evaluation task of college students' psychological health. Through the analysis of the data of College Students' mental health education evaluation, we can see that there are many kinds of College Students' psychological problems and the incidence is high. Therefore, the research on Intelligent psychological evaluation system should be deepened to ensure the smooth development of college education at this stage.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eConflict of interest\u003c/strong\u003e\u003c/p\u003e\u003cp\u003eThe authors declare that they have no conflict of interests\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eEthical approval\u003c/strong\u003e\u003c/p\u003e\u003cp\u003eThis article does not contain any studies with human participants performed by any of the authors.\u003c/p\u003e\u003cp\u003e\u003cstrong\u003eData Availability\u003c/strong\u003e\u003c/p\u003e\u003cp\u003eData will be made available on request.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eOswalt SB, Lederer AM, Chestnut-Steich K, Day C, Halbritter A, Ortiz D (2020) Trends in college students\u0026rsquo; mental health diagnoses and utilization of services, 2009\u0026ndash;2015. J Am Coll Health 68(1):41\u0026ndash;51\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSelvaraj PR, Bhat CS (2018) Predicting the mental health of college students with psychological capital. J Mental Health 27(3):279\u0026ndash;287\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKitzrow MA (2003) The mental health needs of today's college students: Challenges and recommendations. J Student Affairs Res Pract 41(1):167\u0026ndash;181\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eManigault AW, Woody A, Zoccola PM, Dickerson SS (2018) Education is associated with the magnitude of cortisol responses to psychosocial stress in college students. Int J Behav Med 25(5):532\u0026ndash;539\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHorita R, Nishio A, Yamamoto M (2021) The effect of remote learning on the mental health of first year university students in Japan. Psychiatry Res 295:113561\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZinchenko YP, Dorozhkin EM, Zeer EF (2020) Psychological and pedagogical bases for determining the future of vocational education: Vectors of development. Educ Sci J 22(3):11\u0026ndash;35\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eManguy AM, Joubert L, Bansemer L (2016) Psychosocial service needs of pediatric transport accident survivors: Using clinical data-mining to establish demographic and service usage characteristics. Soc Work Health Care 55(8):595\u0026ndash;613\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAmra IAA, Maghari AY (2017) \u0026ldquo;Students performance prediction using KNN and Na\u0026iuml;ve Bayesian,\u0026rdquo; In 2017 8th International Conference on Information Technology (ICIT), pp.\u0026nbsp;909\u0026ndash;913,\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu S, Zhu P, Qin S (2018) \u0026ldquo;An improved weighted KNN algorithm for imbalanced data classification,\u0026rdquo; In 2018 IEEE 4th International Conference on Computer and Communications (ICCC), pp.\u0026nbsp;1814\u0026ndash;1819,\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRaikwal JS, Saxena K (2012) Performance evaluation of SVM and k-nearest neighbor algorithm over medical data set. Int J Comput Appl 50:14\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLevin ME, Hayes SC, Pistorello J, Seeley JR (2016) Web-based self‐help for preventing mental health problems in universities: Comparing acceptance and commitment training to mental health education. J Clin Psychol 72(3):207\u0026ndash;225\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHappell B, Byrne L, McAllister M, Lampshire D, Roper C, Gaskin CJ, \u0026hellip;, Hamer H (2014) Consumer involvement in the tertiary-level education of mental health professionals: A systematic review. Int J Ment Health Nurs 23(1):3\u0026ndash;16\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCornaglia F, Crivellaro E, McNally S (2015) Mental health and education decisions. Labour Econ 33:1\u0026ndash;12\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWu W, Qu G, Wang L, Tang X, Sun YH (2019) Meta-analysis of the mental health status of left‐behind children in China. J Paediatr Child Health 55(3):260\u0026ndash;270\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKratt D (2018) Teachers\u0026rsquo; perspectives on educator mental health competencies: A qualitative case study. Am J Qualitative Res 2(1):22\u0026ndash;40\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBravo AJ, Villarosa-Hurlocker MC, Pearson MR (2018) College student mental health: An evaluation of the DSM\u0026ndash;5 self-rated Level 1 cross-cutting symptom measure. Psychol Assess 30(10):1382\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTarmizi SSA, Mutalib S, Hamid NHA, Rahman SA (2019) A review on student attrition in higher education using big data analytics and data mining techniques. Int J Mod Educ Comput Sci 11(8):1\u0026ndash;14\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAbuzneid MA, Mahmood A (2018) Enhanced human face recognition using LBPH descriptor, multi-KNN, and back-propagation neural network. IEEE access 6:20641\u0026ndash;20651\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"soft-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"soco","sideBox":"Learn more about [Soft Computing](https://www.springer.com/journal/500)","snPcode":"500","submissionUrl":"https://submission.nature.com/new-submission/500/3","title":"Soft Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Improved KNN algorithm, psychological education, Data mining, Automatic evaluation system","lastPublishedDoi":"10.21203/rs.3.rs-2767590/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2767590/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBased on the research and investigation of the psycho-educational development and assessment of college students, this paper designs an interactive system for automatic evaluation of the psychoeducation of college students, which is based on the KNN data classification model and the current technical and environmental conditions. Based on the data and personal information of a college student's psychological census, screen the students' psychological evaluation data, analyzes the key information of the data, obtains the association rules of each factor, analyzes the experimental results. Aiming at the problem that KNN algorithm has low classification accuracy on unbalanced data, we proposes a weighted KNN hybrid algorithm. The harmonic weighted KNN classifier is added to the SVM-KNN classifier for fitting, and the SVM-KNN hybrid algorithm is jointly established. Combined with the principle of SVM-KNN hybrid data classifier, the improved algorithm is applied to a wider range of data value areas, and the appropriate algorithm is selected for data classification and prediction by judging the threshold size. For the data classification calculation method, the Euclidean distance calculation method is generally used to calculate the point-to-point distance in the plane coordinate system, as for hyper plane high-dimensional data, the improved algorithm uses a more suitable kernel function calculation method. According to the designed experimental step program, a series of basic performance such as the calculation rate of the algorithm and the system are tested, and the results show that it can be satisfied, which proves that the interactive automatic evaluation system of College Students' psychological education designed in this paper can effectively understand the psychological status of college students at this stage, find the students who need to focus on psychological counseling, and carry out psychological health education, so as to provide reference for the actual college students' psychological health education.\u003c/p\u003e","manuscriptTitle":"Design of Interactive evaluation system for college students' psychological education based on improved KNN algorithm","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-05-23 14:12:08","doi":"10.21203/rs.3.rs-2767590/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"","date":"2023-05-20T03:17:57+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2023-05-19T09:36:04+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2023-04-11T10:21:50+00:00","index":"","fulltext":""},{"type":"submitted","content":"Soft Computing","date":"2023-04-02T07:55:51+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"soft-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"soco","sideBox":"Learn more about [Soft Computing](https://www.springer.com/journal/500)","snPcode":"500","submissionUrl":"https://submission.nature.com/new-submission/500/3","title":"Soft Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"2bd607c4-8fe9-4251-98ae-f5fbe2de99bc","owner":[],"postedDate":"May 23rd, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2023-10-16T21:37:12+00:00","versionOfRecord":{"articleIdentity":"rs-2767590","link":"https://doi.org/10.1007/s00500-023-08794-6","journal":{"identity":"soft-computing","isVorOnly":false,"title":"Soft Computing"},"publishedOn":"2023-06-27 21:26:37","publishedOnDateReadable":"June 27th, 2023"},"versionCreatedAt":"2023-05-23 14:12:08","video":"","vorDoi":"10.1007/s00500-023-08794-6","vorDoiUrl":"https://doi.org/10.1007/s00500-023-08794-6","workflowStages":[]},"version":"v1","identity":"rs-2767590","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2767590","identity":"rs-2767590","version":["v1"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}