Method and system for identifying network addiction based on Lauxia ink mark test, and storage medium

Abstract

The invention discloses a method and a system for identifying network addiction based on Lauxia ink mark test and a storage medium, and the method comprises the following steps: presenting a Lauxia ink mark test graph card to a subject, and recording the response data of the subject to the graph card; based on the reaction data, through a preset coding rule, multiple Luxia ink mark test variables are extracted, and the variables at least comprise the interpersonal interest Hum Cnt, the personalized reaction PER, the pressure tolerance related variable D score, the shape use distortion ratio X-% and the human motion active and passive ratio Ma: Mp; substituting the extracted variable values of Hum Cont, PER, D, X-% and Ma: Mp into a predetermined logistic regression model, and calculating to obtain a probability value P that the tested object is identified as the network addiction; and based on the probability value P, outputting a network addiction risk assessment result. According to the invention, the deep insight of the Lauxia ink mark test is combined with the modern data analysis and computer-aided technology, and efficient, objective and accurate identification and early warning of the college student network addiction are realized.

Description

Technical Field

[0001] This invention relates to the field of computer-aided psychological assessment and mental health early warning technology, and in particular to a method, system and storage medium for identifying internet addiction based on the Rorschach inkblot test. Background Technology

[0002] Internet addiction refers to the impulsive and uncontrolled use of the internet without the influence of addictive substances, manifested as excessive internet use that significantly impairs an individual's physical and mental health and social functioning. With the continuous increase in internet penetration, university students, as digital natives, have become a vulnerable group for internet addiction. Internet addiction not only leads to academic neglect and interpersonal alienation but also has a high comorbidity rate with various mental disorders such as anxiety and depression, making it a serious public health problem. Therefore, early and accurate identification and effective intervention for internet addiction among university students is of significant practical importance.

[0003] Currently, the initial screening and identification of internet addiction in academia and practice mainly relies on self-report scales, such as the Young's Internet Addiction Test (IAT) and the Chinese Internet Addiction Scale (CIAS). These methods have the advantages of being convenient to implement, simple to score, and easy to administer on a large scale. However, their inherent technical limitations are also quite prominent: (1) Highly subjective and susceptible to concealment: The results of self-report scales rely entirely on the subjects’ self-reports and are easily affected by factors such as social desirability, self-concealment, subjective cognitive bias, and even deliberate deception, which leads to a decrease in the signal-to-noise ratio of the data and affects the authenticity and accuracy of the identification results.

[0004] (2) High face validity: The scale items have obvious purpose, and the subjects are likely to guess the test intentions and answer according to social expectations rather than their own true situation, which greatly reduces the effectiveness of the screening tool in identifying individuals who intentionally conceal information.

[0005] (3) Limited information dimensions: Traditional scales mainly measure conscious behavior and subjective feelings, making it difficult to explore the deep psychological traits of an individual's subconscious personality structure, cognitive processing patterns and emotional regulation ability in a deep and undisturbed manner. These traits are often key factors in the formation and maintenance of internet addiction.

[0006] To overcome the limitations of self-report scales and seek a more objective assessment method that can bypass psychological defenses, projective tests have been introduced as a supplementary approach. Among them, the Rorschach Inkblot Test (RIT) is one of the most authoritative and widely used psychological projective tests internationally. By analyzing an individual's free responses to a fuzzy inkblot, it can reveal their subconscious personality traits, cognitive style, emotional state, and internal conflicts. It is less affected by the subject's concealment and can provide far richer personality information than self-report scales.

[0007] However, applying the Rorschach inkblot test to identify internet addiction, especially in practical applications, faces significant technical challenges and limitations: (1) High dependence on expert experience, low degree of standardization and computer assistance: Traditional Rorschach inkblot test analysis, from administration, questioning, response recording, coding to interpretation, relies heavily on the subjective judgment of long-trained psychological assessors. This process is difficult to standardize and is very time-consuming and labor-intensive, usually requiring several hours to analyze a single case.

[0008] (2) High cost and difficult to apply on a large scale: Due to the extreme reliance on experts, the cost of a single assessment is very high, which cannot meet the actual needs of universities to conduct rapid and universal psychological screening for tens of thousands of students every year.

[0009] (3) Lack of a dedicated identification model for internet addiction: Although some studies abroad have suggested differences among internet addicts in certain Rorschach variables (such as PTI, DEPI, and H response), these findings are scattered and have failed to form an integrated predictive model with high discriminative power. Domestic research in this interdisciplinary field is almost non-existent, lacking the ability to transform the rich indicators of the Rorschach inkblot test into an objective technical solution that can be used to efficiently identify internet addiction.

[0010] In summary, a significant contradiction exists in existing technologies: on the one hand, while traditional self-report scales are convenient for large-scale use, they lack objectivity; on the other hand, while the Rorschach inkblot test can provide objective and in-depth insights, its encoding and interpretation processes are highly dependent on experts, inefficient, and cannot be scaled up, and it lacks a dedicated identification model for internet addiction. There is an urgent need in this field for a novel solution that combines the in-depth insights of the Rorschach inkblot test with computer-aided data processing and model computation techniques to assist in the efficient, objective, and accurate identification and early warning of internet addiction among university students. Summary of the Invention

[0011] This invention addresses the shortcomings of existing technologies by providing a method, system, and storage medium for identifying internet addiction based on the Rorschach inkblot test. It solves the technical problem of how to combine the in-depth insight of the Rorschach inkblot test with modern data analysis and computer-aided technology, thereby achieving efficient, objective, and accurate identification and early warning of internet addiction among college students.

[0012] A method for identifying internet addiction based on the Rorschach inkblot test includes the following steps: Step S1: Data collection step, presenting the Rorschach inkblot test cards to the subjects and recording the subjects' response data to the cards; Step S2: Data processing step. Based on the response data, multiple Rorschach inkblot test variables are extracted using preset coding rules. These variables include at least the interpersonal interest Hum Cont, personalized response PER, stress tolerance-related variable D score, shape usage distortion ratio X-%, and human movement active to passive ratio M. a :M p ; Step S3: Risk assessment step, extracting the HumCont, PER, D, X-%, M a :M p Substituting the variable values ​​into a predetermined logistic regression model, the probability value P of the subject being identified as having internet addiction is calculated, wherein the logistic regression model is: Logit(P) = ln(P / (1-P)) = α + β1*Hum Cont + β2*PER + β3*D + β4*X-% + β5*M a :M p , where α is the intercept term, and β1, β2, β3, β4, β5 are the regression coefficients corresponding to each variable; Output steps: Based on the probability value P, output the internet addiction risk assessment result.

[0013] In the data processing step, the Rorschach inkblot test variables are extracted based on the recorded response text. These variables are manually coded by trained personnel according to the preset coding rules of the Rorschach inkblot test system, thereby determining the values ​​of each variable. Specifically, this includes: The number of human-content responses contained in manually identified response records is used to determine the Hum Cont variable; The number of responses in manually identified response records that are corroborated by personal experience or knowledge is used to determine the PER variable; The D score is calculated by manually identifying all motion, color, non-color, and shadow reactions in the reaction record and calculating them according to the counting and calculation rules.

[0014] The proportion of reactions with poor shape quality (FQ code -) in all reactions is manually calculated to determine the X-% variable; Human motor responses in the reaction records were manually identified and differentiated into active and passive movements, and their ratio was calculated to determine M. a :M p variable.

[0015] In the predetermined logistic regression model, regression coefficients β1 and β2 are positive, β3 and β5 are negative, and β4 is positive.

[0016] The predetermined logistic regression model is specifically as follows: Logit(P)=ln(P / (1-P))=0.469*Hum Cont+0.366*PER-0.760*D+ 1.601*K*X-%-0.490*M a :M p -7.344, where K is a constant for scaling the X-% variable.

[0017] The constant K is 10.

[0018] In the risk assessment step, the calculated Logit(P) value is compared with a preset threshold value; If Logit(P) is greater than or equal to the threshold value, it is considered to be at high risk of internet addiction.

[0019] The preset threshold value is 1.637.

[0020] A system for identifying internet addiction based on the Rorschach inkblot test includes: The data acquisition module is configured to present Rorschach inkblot test cards to the subjects and record the subjects' response data to the cards; The data processing module is configured to extract multiple Rorschach inkblot test variables based on the response data using preset coding rules. These variables include at least the interpersonal interest Hum Cont, personalized response PER, stress tolerance-related variable D score, shape usage distortion ratio X-%, and the ratio of active to passive human movement M. a :M p This module is used to receive and input manually coded variable values.

[0021] The risk assessment module is configured to extract the HumCont, PER, D, X-%, and M values. a :M p Substituting the variable values ​​into a predetermined logistic regression model, the probability value P of the subject being identified as having internet addiction is calculated, wherein the logistic regression model is: Logit(P) = ln(P / (1-P)) = α + β1*Hum Cont + β2*PER + β3*D + β4*X-% + β5*M a :M p , where α is the intercept term, and β1, β2, β3, β4, β5 are the regression coefficients corresponding to each variable; The results output module is configured to output the internet addiction risk assessment result based on the probability value P.

[0022] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for identifying internet addiction based on the Rorschach inkblot test.

[0023] Compared with existing technologies, the scheme for identifying internet addiction based on the Rorschach inkblot test provided by this invention has the following significant technical effects: (1) Improved objectivity and resistance to interference in the identification results: This invention extracts objective Rorschach variables by analyzing the subjects' responses to standardized inkblots, replacing the method that relies entirely on self-report, and can effectively bypass the subjects' psychological defense mechanisms. This greatly reduces the interference of subjective factors such as social desirability and cover-up behavior on the evaluation results, thereby obtaining psychological data with a higher signal-to-noise ratio and greater authenticity and reliability, fundamentally overcoming the inherent defects of self-report scales, which are highly subjective and easily falsified.

[0024] (2) Optimized assessment process and improved efficiency: This invention systematically integrates the Rorschach test analysis and calculation process, which traditionally relies entirely on expert experience, by constructing a complete process that includes data collection, (manual) coded data entry, model calculation, and result output. The system can quickly complete model calculations and generate risk assessment reports in a very short time, significantly improving efficiency compared to purely manual analysis and interpretation. This reduces the reliance on high-frequency, repetitive model calculations, making it possible to assist in screening large-scale populations.

[0025] (3) Provides higher identification accuracy: This invention does not simply list Rorschach variables, but uses rigorous mathematical statistical analysis to screen out the five key variables most relevant to internet addiction (Hum Cont, PER, D, X-%, M). a :M p A binary logistic regression prediction model with specific regression coefficients was constructed. This model was validated, achieving an F1 score as high as 92.75%, demonstrating extremely high classification accuracy. This ensures that the screening results are not only objective but also accurate and reliable, providing a solid basis for subsequent precise interventions.

[0026] (4) Early warning and proactive intervention are achieved: The present invention integrates an early warning function, which can automatically trigger an early warning mechanism (such as sending an alarm to the administrator) based on the risk probability calculated by the model. This enables educators and psychological counselors to proactively and promptly identify high-risk individuals, rather than passively waiting for problems to erupt before taking action, realizing the transformation from "post-event remediation" to "pre-event prevention", and significantly improving the effectiveness of mental health work in universities.

[0027] (5) Possesses strong scalability and promotion potential: The core of this invention lies in an algorithm model and system architecture, whose underlying technical solution has high replicability. This system can not only be applied to university settings, but with slight adjustments, it can be extended to other groups that need mental health screening, such as middle schools, enterprises, medical institutions, and the military. In addition, this technical framework also lays the foundation for future integration or adaptation of identification models for other mental health problems (such as depression and anxiety), demonstrating broad application prospects.

[0028] In summary, this invention organically integrates in-depth psychological projective testing with modern data analysis and computer-aided technology, successfully creating a comprehensive technical solution that combines objectivity, efficiency, accuracy, and early warning capabilities. It effectively addresses the industry pain points of "high subjectivity" and "low efficiency" in the current field of internet addiction identification, and has significant practical application value and technological advancement significance. Attached Figure Description

[0029] Figure 1 This is a diagram of the overall system architecture of the present invention.

[0030] Figure 2 This is a flowchart of the method of the present invention.

[0031] Figure 3 This is a schematic diagram of the interface of the test terminal used by the test subject. Detailed Implementation

[0032] To clearly illustrate the technical features of this solution, the following detailed implementation method will be used to explain the solution.

[0033] See Figures 1-3 A method for identifying internet addiction based on the Rorschach inkblot test includes the following steps: Step S1: Data collection step, presenting the Rorschach inkblot test cards to the subjects and recording the subjects' response data to the cards; It should be noted that data acquisition in this embodiment was conducted in a controlled physical environment. Ten standardized paper cards from the Rorschach inkblot test were used as stimulus materials. The testing process was conducted by a trained administrator and strictly followed Exner's Rorschach Inkblot Test Integrated System specifications.

[0034] Response recording: The administering officer recorded every response of the subject using a recording device. After the test, the recording was transcribed into an accurate verbatim transcript using speech recognition software combined with manual proofreading. This transcript served as the raw data for subsequent coding.

[0035] Step S2: Data processing step. Based on the response data, multiple Rorschach inkblot test variables are extracted using preset coding rules. These variables include at least the interpersonal interest Hum Cont, personalized response PER, stress tolerance-related variable D, shape usage distortion ratio X-%, and active vs. passive human movement comparison M. a :M p ; Step S3: Risk assessment step, extracting the HumCont, PER, D, X-%, M a :M p Substituting the variable values ​​into a predetermined logistic regression model, the probability value P of the subject being identified as having internet addiction is calculated, wherein the logistic regression model is: Logit(P) = ln(P / (1-P)) = α + β1*Hum Cont + β2*PER + β3*D + β4*X-% + β5*M a :M p , where α is the intercept term, and β1, β2, β3, β4, β5 are the regression coefficients corresponding to each variable; Output steps: Based on the probability value P, output the internet addiction risk assessment result.

[0036] The five variable values ​​obtained above are input into the predetermined logistic regression model of this invention for calculation. In this embodiment, the model is: Logit(P)=ln(P / (1-P))= 0.469*Hum Cont+0.366 * PER-0.760* D+1.601* K*X-%-0.490*M a :M p -7.344, where the constant K=10.

[0037] Calculation example: Suppose a subject's coding results are: Hum Cont=3, PER=2, D=0, X-%=0.15, M a :M p = 3:1 = 2.

[0038] Substitute into the formula: Logit(P)= 0.469*3+0.366*2-0.760*0+1.601*(10*0.15)-0.490*2-7.344 =1.407+0.732-0+2.4015-0.98-7.344=-3.7835.

[0039] Then calculate the probability P: P=exp(-3.7835) / (1+exp(-3.7835))≈0.022.

[0040] The results indicate that the risk of this subject developing internet addiction is extremely low (approximately 2.2%).

[0041] In step S2, during the data processing step, the Rorschach inkblot test variables are extracted based on the recorded response text. These variables are manually coded by trained personnel according to the preset coding rules of the Rorschach inkblot test system to determine their values. Specifically, this includes: The number of human-content responses contained in manually identified response records is used to determine the Hum Cont variable; The number of responses in manually identified response records that are corroborated by personal experience or knowledge is used to determine the PER variable; The D score is calculated by manually identifying all motion, color, non-color, and shadow reactions in the reaction record and calculating them according to the counting and calculation rules.

[0042] The proportion of reactions with poor shape quality (FQ code -) in all reactions is manually calculated to determine the X-% variable; Manually identify and distinguish between active and passive movements in the reaction records, and calculate M. a Subtract M p Difference to determine M a :M p variable.

[0043] For example, the core of step S2 is the manual coding of the verbatim text by coders trained in the Rorschach inkblot testing system. The coding process follows the preset rules of the Exner synthesis system and mainly includes the following eight types of coding: (1) Response Sites (W, D, Dd, S). Participants provide the inkblot sites used in their responses. Site coding is divided into four types: Whole (W): The entire inkblot used in the response, which must include all parts of the inkblot; Common Site (D): Common areas where the inkblot was used; Uncommon Site (Dd): Uncommon areas where the inkblot was used; Blank Site (S): Blank areas where the inkblot was used, which can only be coded together with other sites, for example: WS, DS, DdS.

[0044] (2) Development Quality (DQ, e.g., +, o, v / +, v). Represents the characteristics or quality of the processing by which the subject forms a response. There are four coding types: combined response (+), ordinary response (o), fuzzy combined response (v / +), and fuzzy response (v). A combined response refers to a response in which two or more independent objects are described separately, but there is a meaningful connection between them, and at least one object has a specific shape requirement or is described with a specific shape requirement. For example: "a dog walking in a bush." ​​An ordinary response is a response in which the subject's response contains only one object, which has a natural shape requirement, such as: "a car," "a maple leaf." A fuzzy combined response requires that two or more objects be described separately in the subject's response, and that they are interconnected, but none of them have a specific shape requirement, such as: "a bay with plants on the shore." A fuzzy response is a response in which the content contains only one object and has no specific shape requirement, such as: "cloud," "sky," etc.

[0045] (3) Determinants (e.g., F, M, CF, C, etc.). What factors or characteristics of the picture card cause the subject to respond in this way? These factors or characteristics are the determinants of the subject's response. The Rorschach inkblot test has 7 categories and 24 determinants. Each category represents a way in which an individual shifts the stimulus area, reflecting certain aspects of the cognitive activities involved in and forming the response. These 7 categories of determinants are: Form, Movement, Chromatic Color, Achromatic Color, Shading, Form Dimension, and Pairs & Reflection.

[0046] (4) Shape Quality (FQ, e.g., +, o, u, -). Provides information on the "compliance" of the response, i.e., whether the inkblot area used in the response conforms to the shape requirements of the identified object. Shape quality includes four codes, three of which indicate that the shape used in the response is appropriate, and one indicates that the shape used in the response is inaccurate or distorted, namely, Common-Refinement (+), Common (o), Uncommon (u), and Distorted (-). Common-Refinement responses refer to responses that provide a very detailed description of the shape, and this description enriches the quality of the response without compromising the appropriateness of the shape use. Common responses are those that are common and can be easily identified as an object based on the usual shape characteristics. Uncommon responses are those that occur infrequently, involve basic morphological outlines that are appropriate for the response, and can be quickly and easily recognized by the observer. Distorted responses are those where the content of the response given by the subject does not conform to the inkblot shape of the corresponding part of the card used, the shape use is subjectively imposed on the inkblot, and the inkblot outline of the area used is ignored.

[0047] (5) Content (e.g., H, Bt, Id, etc.). The specific things in the content of the response given by the subject. The Rorschach Inkblot Test Integrated System provides 27 categories of content responses. For example, if the subject's response includes a description of "people", the content code is H; if the subject describes plants in the response, the content code is Bt; if the content of the response is not in the given specific category code, it is coded as uncommon content Id.

[0048] (6) Common Responses (P). Responses that appear at least once in every 3 test records, totaling 13, and that meet the criteria for common responses, are coded with P. For example, on the second card, if part D1 is identified as a bear, dog, elephant, or sheep, then the response is assigned the common response code P.

[0049] (7) Organizational Activity (Z-score). This refers to the participant's mental organization during the response, i.e., establishing connections between the objects or entities being responded to, and using different inkblot regions. When organizational activity occurs, a Z-score is assigned to the response. There are four criteria for measuring whether a response can obtain a Z-score: ①ZW, a whole response coded as +, O, v / + in DQ; ②ZA, a response that uses adjacent inkblot regions, reports two or more independent objects, and there is a meaningful connection between them; ③ZD, a response that uses non-adjacent inkblot regions, reports two or more independent objects, and there is a meaningful connection between them; ④ZS, a response that integrates blank areas of the inkblot with other areas to form a response.

[0050] (8) Special scores (such as PER, MOR, etc.). The Rorschach inkblot test has 15 special scores used to identify special characteristics in the response. Among them, 6 are used for abnormal language expression, 1 for continuous speech, 4 are related to special content, 2 are used to distinguish responses involving human figures, 1 is used for personalized responses, and the last one is used for special color responses. These special responses can indicate some special representations of the subject's behavior, language, thinking, etc. during the response process, which are of great significance for the interpretation of the subject's test results.

[0051] After all responses are coded, the data needs to be summarized, calculated, and entered into a structured table. The structured table is used to statistically analyze and score test codes according to specific requirements; it is a data organization of test results, and the interpretation of the Rorschach Inkblot Test System directly relies on the structured table. The structured table is divided into two parts. The upper part displays the raw information of the codes, including the frequency statistics of six parts of the codes: site characteristics (tissue score, site code, developmental quality), determinants, content, shape quality response site sequence, and special scores. The lower part is divided into seven data modules and six special index clusters. The seven data modules are the core part, emotion part, interpersonal part, thinking part, psychological adjustment part, information processing part, and self-perception part. The six special index clusters are the Safety-to-Life Index (S-CON), Depression Index (DEPI), High Vigilance Index (HVI), Perceptual Thinking Index (PTI), Coping Deficiency Index (CDI), and Obsessive-Compulsive Index (OBS). See Tables 1 and 2 for details. Table 1 Examples of Encoded Sequence Representations Picture Card serial number Part DQ Determinant FQ (2) content P Z Special scores I 1 WS o F o (Ad) 3.50 PER 2 W o <![CDATA[FM p ]]> o A P 1.0 II 1 D3 o <![CDATA[FC.FM p ]]> o A 2 WS o <![CDATA[FM p ]]> u Ad 4.5 III 1 WS o FC u Ad 4.5 PER IV 1 W O F - An 2.0 2 W O FY u Ad 2.0 PSV V 1 W o F o A P 1.0 VI 1 D3 o Mp o Art,H,Ay PER, GHR 2 D1 o F - Art, Fd PER 3 W o <![CDATA[FC'.FM p ]]> u A 2.5 4 W v / + Fr o Na 2.5 VII 1 W o F - (H) 2.50 PER, MOR, PHR 2 W o <![CDATA[FM a .MY]]> - A 2.5 VIII 1 W o CF - Art,Cg 4.50 PER 2 W + <![CDATA[FM a .Fr.FC]]> o A,Ls P 4.50 3 W o F u (Hd) 4.50 PER, GHR IX 1 WS o FC u Hh,Ay 5.5 2 D1 o <![CDATA[FM a ]]> o Ad X 1 W + <![CDATA[FM a ]]> o 2 A,Sc P 5.5 2 Dd21 + <![CDATA[m p .FC]]> o Bt 4.5 PER Table 2 Examples of Structured Representation

[0052] PER variable: In a specific score, count the number of all values ​​coded as PER (Personalized Response).

[0053] X-% variable: Calculates the proportion of all reactions in which shape quality (FQ) is coded as - (distorted).

[0054] D-score variable: This variable is related to situation-related stress in the core part. It is calculated by a specific formula based on motion response, color response, non-color response and shadow response. The specific calculation rules follow the Exner system.

[0055] M a :M p Variables: Among the determinants, all human motor responses M are statistically analyzed and categorized into active motor responses M. a and passive motion M pFinally, the difference in the number of active and passive human motor responses was calculated to obtain M. a :M p .

[0056] After all responses have been coded, the coders will compile the data and fill it into a standardized Rorschach inkblot test structured form.

[0057] The five key variables used in this invention (Hum Cont, PER, D, X-%, M) a :M p The values ​​of all can be obtained directly from this structured table.

[0058] In the predetermined logistic regression model, regression coefficients β1 and β2 are positive, β3 and β5 are negative, and β4 is positive.

[0059] The predetermined logistic regression model is specifically as follows: Logit(P)=ln(P / (1-P))=0.469*Hum Cont+0.366*PER-0.760*D+ 1.601*K*X-%-0.490*M a :M p -7.344, where K is a constant for scaling the X-% variable.

[0060] The constant K is 10.

[0061] In step S3, during the risk assessment step, the calculated Logit(P) value is compared with a preset threshold value. If Logit(P) is greater than or equal to the threshold value, it is considered to be at high risk of internet addiction.

[0062] The preset threshold value is 1.637.

[0063] The system compares the calculated Logit(P) value with the preset critical value of 1.637.

[0064] If Logit(P) >= 1.637 (i.e., P >= 0.837), then the subject is considered to be at high risk of internet addiction.

[0065] At this point, the system can generate a high-risk warning signal and send the warning information (including the subject ID and risk level) to the management terminal of the designated psychological counselor or mentor via email or internal messaging system for timely intervention.

[0066] If Logit(P) < 1.637, then output the assessment result of low risk or normal risk. A system for identifying internet addiction based on the Rorschach inkblot test includes: The data acquisition module is configured to present Rorschach inkblot test cards to the subjects and record the subjects' response data to the cards; The data processing module is configured to extract multiple Rorschach inkblot test variables based on the response data using preset coding rules. These variables include at least the interpersonal interest Hum Cont, personalized response PER, stress tolerance-related variable D score, shape usage distortion ratio X-%, and the ratio of active to passive human movement M. a :M p ; The risk assessment module is configured to extract the HumCont, PER, D, X-%, and M values. a :M p Substituting the variable values ​​into a predetermined logistic regression model, the probability value P of the subject being identified as having internet addiction is calculated, wherein the logistic regression model is: Logit(P) = ln(P / (1-P)) = α + β1*Hum Cont + β2*PER + β3*D + β4*X-% + β5*M a :M p , where α is the intercept term, and β1, β2, β3, β4, β5 are the regression coefficients corresponding to each variable; The results output module is configured to output the internet addiction risk assessment result based on the probability value P.

[0067] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for identifying internet addiction based on the Rorschach inkblot test.

[0068] The system implementation process of this invention is as follows: Although the data encoding process relies on manual labor, the data processing, model calculation, result comparison, and early warning transmission stages of this invention can be entirely implemented by a computer system. For example, a B / S architecture system can be constructed, including: Front-end interface: This is part of the system's data processing module, where coders can enter the values ​​of five key variables obtained from structured tables.

[0069] Backend service: Receives variable values ​​submitted by the frontend, calls the stored regression model (such as the specific formulas and coefficients mentioned above) to perform calculations, and compares the results with the thresholds in the database.

[0070] Early warning module: When the conditions are met, it automatically calls the email or SMS interface to send an early warning.

[0071] Database: Stores subject information, coded data, model coefficients, calculation results, and warning records.

[0072] This invention combines complex Rorschach coding with efficient computer model calculations to achieve rapid and objective auxiliary judgment of internet addiction risk while ensuring the depth of psychological assessment.

[0073] The technical details not described in this solution are all based on the conventional understanding and operation of those skilled in the art and can be accomplished using existing technologies, and will not be elaborated here.

[0074] The technical features of this invention not described can be implemented by or using existing technology, and will not be repeated here. Of course, the above description is not a limitation of this invention, and this invention is not limited to the examples above. Any changes, modifications, additions or substitutions made by those skilled in the art within the scope of this invention should also be within the protection scope of this invention.

Claims

1. A method for identifying internet addiction based on the Rorschach inkblot test, characterized in that, Includes the following steps: Step S1: Data collection step, present the Rorschach inkblot test cards to the subjects and record the subjects' response data to all cards; Step S2: Data processing step. Based on the participants' response data, multiple Rorschach inkblot test variables are extracted using preset coding rules. These variables include at least the interpersonal interest Hum Cont, personalized response PER, stress tolerance-related variable D score, shape use distortion ratio X-%, and human movement active to passive ratio M. a :M p ; Step S3: Risk assessment step, extracting HumCont, PER, D, X-%, M a :M p Substituting the variable values ​​into a predetermined logistic regression model, the probability value P of the subject identifying as having internet addiction is calculated, wherein the logistic regression model is: Logit(P) = ln(P / (1-P)) = α + β1*Hum Cont + β2*PER + β3*D + β4*X-% + β5*M a :M p , where α is the intercept term, and β1, β2, β3, β4, β5 are the regression coefficients corresponding to each variable; Output steps: Based on the probability value P, output the internet addiction risk assessment result.

2. The method for identifying internet addiction based on the Rorschach inkblot test according to claim 1, characterized in that, In step S2, during the data processing step, the Rorschach inkblot test variables are extracted based on the recorded response text. These variables are manually coded by trained personnel according to the preset coding rules of the Rorschach inkblot test system to determine their values. Specifically, this includes: The number of responses containing human content in manually identified response records was used to determine the Hum Cont variable; The number of responses in manually identified response records that are corroborated by personal experience or knowledge is used to determine the PER variable; The D score is calculated based on the counting and calculation rules of all motion, color, non-color, and shadow reactions recorded by the human identification reaction record. The proportion of reactions with poor shape quality (FQ code -) in all reactions is manually calculated to determine the X-% variable; The system manually identifies and distinguishes between active and passive movements in human motor responses recorded in response logs, and calculates the difference between active and passive movements to determine M. a :M p variable.

3. The method for identifying internet addiction based on the Rorschach inkblot test according to claim 1, characterized in that, In the predetermined logistic regression model, regression coefficients β1 and β2 are positive, β3 and β5 are negative, and β4 is positive.

4. The method for identifying internet addiction based on the Rorschach inkblot test according to claim 1, characterized in that, The predetermined logistic regression model is specifically as follows: Logit(P)=ln(P / (1-P))=0.469*Hum Cont+0.366*PER-0.760*D+ 1.601*K*X-%-0.490*M a :M p -7.344, where K is a constant for scaling the X-% variable.

5. The method for identifying internet addiction based on the Rorschach inkblot test according to claim 4, characterized in that, The constant K is 10.

6. The method for identifying internet addiction based on the Rorschach inkblot test according to claim 1, characterized in that, In step S3, during the risk assessment step, the calculated Logit(P) value is compared with a preset critical value. If Logit(P) is greater than or equal to the threshold value, it is considered to be at high risk of internet addiction.

7. The method for identifying internet addiction based on the Rorschach inkblot test according to claim 6, characterized in that, The preset threshold value is 1.

637.

8. A system for identifying internet addiction based on the Rorschach inkblot test, characterized in that, include: The data acquisition module is configured to present Rorschach inkblot test cards to the subjects and record the subjects' response data to the cards; The data processing module is configured to extract multiple Rorschach inkblot test variables based on the response data using preset coding rules. These variables include at least the interpersonal interest Hum Cont, personalized response PER, stress tolerance-related variable D score, shape usage distortion ratio X-%, and active vs. passive human movement comparison M. a :M p ; The risk assessment module is configured to extract the HumCont, PER, D, X-%, and M values. a :M p Substituting the variable values ​​into a predetermined logistic regression model, the probability value P of the subject being identified as having internet addiction is calculated, wherein the logistic regression model is: Logit(P) = ln(P / (1-P)) = α + β1*Hum Cont + β2*PER + β3*D + β4*X-% + β5*M a :M p , where α is the intercept term, and β1, β2, β3, β4, β5 are the regression coefficients corresponding to each variable; The results output module is configured to output the internet addiction risk assessment result based on the probability value P.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images