Self-adaptive psychological assessment game engine construction method for teenagers and implementation strategy

Abstract

The invention relates to the technical field of psychological assessment, and discloses a teenager-oriented self-adaptive psychological assessment game engine construction method and implementation strategy for generating a game for psychological assessment based on a game generation module and different psychological assessment questionnaires. Aiming at the construction of a game generation module, the game engine construction method comprises the following steps: generating a first game architecture; generating a second game architecture and outputting the second game architecture for game generation; and generating a third game architecture, adjusting the second game architecture, generating a fourth game architecture, and outputting the fourth game architecture for game generation. The implementation strategy corresponds to the game engine construction method. According to the method, the problems of teenager resistance evaluation, high cost of traditional means and insufficient game evaluation validity are effectively solved, the participation degree and the result authenticity are improved, and the method is suitable for large-scale psychological evaluation requirements.

Description

Technical Field

[0001] The present application relates to the field of psychological assessment technology, and specifically to a method and implementation strategy for constructing an adaptive psychological assessment game engine for teenagers. Background Art

[0002] With the significant increase in the incidence of psychological problems among adolescents, traditional psychological assessment technology faces multiple challenges: The assessment format is not adaptable enough: Using adult standard questionnaires to assess adolescents will lead to distorted assessment results due to the immaturity of adolescents' cognitive abilities, and will not accurately reflect their true psychological state.

[0003] Low participation and strong resistance: Adolescents are resistant to traditional questionnaire assessments and have low willingness to cooperate. They find it particularly difficult to understand abstract questions, which can easily lead to data collection bias.

[0004] Professional methods are costly: Traditional immersive assessments such as psychological sandplay games require the guidance of professionals, which have high costs in terms of manpower, material resources and time. They are difficult to popularize on a large scale and cannot meet the screening needs of the high incidence of psychological problems among adolescents.

[0005] Gamified assessments suffer from validity flaws: Existing gamified assessment technologies generate game content solely based on static questionnaires and lack dynamic adaptation to individual differences in adolescents (such as age, cognitive level, and interests). This leads to significant user distraction and social desirability bias during the assessment process, making it difficult to ensure the validity and reliability of the results. Chinese invention patent application publication number CN119724569A discloses a multi-agent-based psychological assessment method, device, and system, but this invention performs poorly in ensuring the validity of gamified assessments.

[0006] The above problems indicate that existing technologies are unable to achieve an effective balance between participation, personalized adaptation, and data authenticity in adolescent psychological assessments. There is an urgent need for a new technical solution for adaptive psychological assessments for adolescents. Summary of the Invention

[0007] The purpose of this application is to provide a method and implementation strategy for building an adaptive psychological assessment game engine for teenagers to solve the technical problems raised in the above background technology.

[0008] To achieve the above objectives, this application discloses the following technical solutions: In a first aspect, the present application discloses a method for constructing an adaptive psychological assessment game engine for teenagers. The game engine is constructed based on a game generation module and different psychological assessment questionnaires, and is configured to use the game generation module to parse the psychological assessment questionnaire and then generate a game for psychological assessment. The method for constructing the game engine includes the following steps for constructing the game generation module: S1: Analyze the psychological assessment questionnaire using artificial intelligence generation technology to generate a first game framework; wherein the first game framework stores game materials corresponding to the psychological assessment questionnaire, and the game materials include at least text elements, visual elements, auditory elements, and interactive logic; S2: Adjusting the first game framework based on the basic data of the test subject, generating a second game framework, and outputting the second game framework for game generation; wherein the basic data is used to represent the identity information of the test subject, and the second game framework stores game materials corresponding to the basic data and the psychological assessment questionnaire; S3: Utilize artificial intelligence generation technology to analyze the new psychological assessment questionnaire, generate a third game framework, adjust the second game framework based on the physiological data of the testee, fuse the second game framework and the third game framework to generate a fourth game framework and output it for generating a game; wherein, the third game framework stores game materials corresponding to the new psychological assessment questionnaire, the physiological data is used to characterize the psychological fluctuations of the testee, and the fourth game framework stores game materials corresponding to the basic data, the physiological data and the new psychological assessment questionnaire.

[0009] Preferably, adjusting the second game architecture based on the physiological data of the person being tested specifically includes: Collecting the physiological data of the subject, the physiological data including at least eye movement trajectory and heart rate fluctuation, and performing feature extraction on the physiological data to obtain physiological features for characterizing physiological changes of the subject; A physiological mapping relationship between the physiological characteristics and the game materials is constructed, and when the generated characteristics are detected, the game materials in the corresponding game scene are automatically adjusted.

[0010] Preferably, the construction of the physiological mapping relationship includes: A prediction model is trained based on historical physiological data, the prediction model input is the physiological data, and the output is game material adjustment instructions, the game material adjustment instructions at least include text complexity adjustment instructions, visual element adjustment instructions, and interaction logic adjustment instructions.

[0011] Preferably, the method for constructing a game engine for constructing a game generation module further includes: S4: Verify the validity of the fourth game architecture; wherein, the validity verification includes: synchronously collecting the selection data and behavior data of the testee, the selection data being the testee's evaluation answer, and the behavior data including operation delay and repeated operation frequency; constructing an evaluation model, which is used to output a verification report when it is detected that the correlation between the selection data and the behavior data is lower than a preset threshold, and the verification report includes a confidence index for the fourth game architecture.

[0012] Preferably, when it is detected that the correlation between the selection data and the behavior data is lower than a preset threshold, an optimization action is performed, the optimization action comprising: identifying game material that causes the correlation between the selection data and the behavior data to be below a preset threshold; The identified game materials are analyzed and reconstructed based on artificial intelligence generation technology, and the reconstructed game materials are verified. The verification is to reuse the evaluation model to detect the correlation between the selection data and the behavior data until the correlation is higher than a preset threshold.

[0013] Preferably, the integration of the second game architecture and the third game architecture specifically includes: The similarity between the game materials in the second game architecture and the third game architecture is analyzed, and based on the similarity, the differentiated game materials are reorganized to form a fused game architecture.

[0014] Preferably, adjusting the first game architecture based on the basic data of the test subject specifically includes: Based on the basic data of the test subjects, a preset group knowledge base is called to match group game materials corresponding to the basic data of the test subjects; wherein the group knowledge base stores group characteristics of different groups of test subjects, and the group characteristics are used to characterize the cognitive levels and interest preferences of different test subjects; The difficulty curve, character settings, and situational themes in the first game architecture are adjusted based on the matched group game materials.

[0015] Preferably, the method for constructing a game engine for constructing a game generation module further includes: S5: Based on the evaluation results, the game materials are continuously optimized. The optimization includes: recording the usage data of each game material and its impact on the evaluation results. When abnormal fluctuations in the impact value are detected, the material optimization process is triggered. The material optimization process includes game material replacement, parameter adjustment and structural reorganization.

[0016] Preferably, the artificial intelligence generation technology includes: The first generative model is used to generate narrative content corresponding to the psychological assessment questionnaire; A second generation model is used to generate a representation that matches the narrative content, the representation corresponding to the game material; A game architecture is generated based on the first generation model and the second generation model.

[0017] In a second aspect, the present application discloses an implementation strategy for an adaptive psychological assessment for teenagers. The implementation strategy is applicable to the aforementioned method for constructing an adaptive psychological assessment game engine for teenagers. The implementation strategy includes: A1: Analyze the psychological assessment questionnaire corresponding to the test subject using artificial intelligence generation technology to generate a first game framework; wherein the first game framework stores game materials corresponding to the psychological assessment questionnaire, and the game materials include at least text elements, visual elements, auditory elements, and interactive logic; A2: Obtaining basic data of the test subject and adjusting the first game architecture to generate a second game architecture and output it for game generation, and conducting a psychological assessment on the test subject based on the generated game; wherein the basic data is used to represent the test subject's identity information, and the second game architecture stores game materials corresponding to the basic data and the psychological assessment questionnaire; A3: Utilize artificial intelligence generation technology to parse a new psychological assessment questionnaire corresponding to the testee, generate a third game framework, collect the testee's physiological data and adjust the second game framework, fuse the second game framework and the third game framework to generate a fourth game framework and output it for generating a game, and conduct a psychological assessment on the testee based on the generated game; wherein, the third game framework stores game materials corresponding to the new psychological assessment questionnaire, the physiological data is used to characterize the testee's psychological fluctuations, and the fourth game framework stores game materials corresponding to the basic data, the physiological data, and the new psychological assessment questionnaire.

[0018] Beneficial effects: The method and implementation strategy of the adaptive psychological assessment game engine for teenagers in this application uses artificial intelligence generation technology to analyze psychological assessment questionnaires to generate game architecture, combines the basic data of the subjects to call the group knowledge base to match personalized game materials, dynamically adjusts the difficulty, role and situation, and solves the problem of mismatch between traditional questionnaires and adolescent cognition; introduces physiological data collection and feature extraction, and generates material adjustment instructions through historical data training prediction models to achieve real-time optimization of game scenes with psychological fluctuations, and accurately capture real states such as attention distraction; dynamically repairs data inconsistencies and improves assessment validity by calculating the correlation between selected data and behavioral data and reconstructing low-correlation materials; integrates differentiated materials from multiple game architectures to reduce redundancy and ensure dimensional integrity; establishes a continuous optimization mechanism for game materials, and updates them in real time as the research objects expand, breaking through the rigid limitations of materials; adopts multi-agent technology to drive the dual generation model to achieve multimodal alignment of narrative and expression forms, and enhance immersion; thereby effectively solving the problems of teenagers' resistance to assessment, the high cost of traditional means and the insufficient validity of gamified assessment, improving participation and authenticity of results, and adapting to the needs of large-scale psychological assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 A flowchart of a method for constructing an adaptive psychological assessment game engine for teenagers provided in an embodiment of the present application; Figure 2 This is a flowchart of the implementation strategy of the adaptive psychological assessment for teenagers provided in the embodiment of the present application. DETAILED DESCRIPTION

[0021] The following is a clear and complete description of the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0022] In this document, the term "comprising" is intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0023] With the passage of time, the incidence of psychological problems among adolescents is increasing. Unlike adults, adolescents' cognitive abilities are not yet fully developed. Therefore, using the same questionnaires as adults will result in poor assessment results. Furthermore, even if psychological assessment questionnaires for adolescents exist, adolescents may resist psychological assessments due to their cognitive immaturity. To address this issue, psychological sandbox games exist in the field of psychological research. However, these games require significant manpower, material resources, and time, and are not suitable for the high prevalence of psychological problems among adolescents. Therefore, gamifying psychological assessment questionnaires is an effective technical means to address this issue. With the development of artificial intelligence generation technology, it is possible to quickly generate psychological assessment questionnaires through gamification. However, in actual applications, it has been found that the effectiveness of psychological assessment results cannot be guaranteed due to the gamification approach used. Therefore, this example, based on an existing children's depression scale, uses 150 adolescents visiting a hospital for treatment as research subjects. By analyzing the data collected during and after the study subjects' completion of a pre-set game, an adaptive psychological assessment game engine for adolescents is constructed. Based on this game engine, a real-time adaptive psychological assessment strategy for adolescents is also constructed.

[0024] The first aspect of this embodiment discloses Figure 1 A method for constructing an adaptive psychological assessment game engine for teenagers is shown. The game engine is constructed based on a game generation module and different psychological assessment questionnaires. The game engine is configured to use the game generation module to parse the psychological assessment questionnaire and then generate a game for psychological assessment. The method for constructing the game engine includes the following steps for constructing the game generation module: S1: Analyzing a psychological assessment questionnaire using artificial intelligence generation technology to generate a first game framework; wherein the first game framework stores game materials corresponding to the psychological assessment questionnaire, and the game materials include at least text elements, visual elements, auditory elements, and interaction logic; S2: Adjusting the first game framework based on the basic data of the test subject, generating a second game framework, and outputting the framework for game generation; wherein the basic data is used to represent the identity information of the test subject, and the second game framework stores game materials corresponding to the basic data and the psychological assessment questionnaire; S3: Use artificial intelligence generation technology to parse the new psychological assessment questionnaire, generate a third game framework, adjust the second game framework based on the physiological data of the test subject, integrate the second game framework and the third game framework to generate a fourth game framework and output it for generating the game; wherein, the third game framework stores game materials corresponding to the new psychological assessment questionnaire, the physiological data is used to characterize the psychological fluctuations of the test subject, and the fourth game framework stores game materials corresponding to the basic data, physiological data and the new psychological assessment questionnaire.

[0025] By leveraging AI-generated technology to analyze psychological assessment questionnaires and dynamically adjust the generated game framework based on subject baseline and physiological data, this approach addresses adolescent resistance to traditional assessments and the ineffectiveness of existing assessments, improving participation and validating results without requiring significant human and material resources, adapting to the current high prevalence of adolescent psychological problems. Furthermore, traditional depression diagnostic tools based on text-based scales suffer from limitations such as a strong reliance on reading ability, a tendency to trigger defensiveness, and test results distorted by practice effects, making them incapable of accurately capturing adolescents' true psychological states. This approach, centered on the concept of gamified assessment, breaks through the constraints of traditional text-based tests and leverages the inherent immersiveness, fun, and interactivity of games to integrate psychological assessments into virtual scenarios and interactive tasks. By concealing the purpose of the test and reducing test anxiety, this approach enables a naturalistic and dynamic assessment of adolescent depressive tendencies, providing a more scientific and effective solution for adolescent mental health screening and intervention.

[0026] In a specific application of this embodiment, the psychological assessment of the subject is not completed in a single round. That is, after the psychological assessment based on the initial generated game, multiple rounds of psychological assessments are performed as the treatment progresses. In this case, if the game generation is based solely on the psychological assessment questionnaire and basic data, the assessment effect will be greatly reduced. To address this issue, this embodiment incorporates the subject's physiological data for optimization.

[0027] Specifically, adjusting the second game structure based on the physiological data of the test subject includes: Collecting physiological data of the subject, the physiological data including at least eye movement trajectory and heart rate fluctuation, and performing feature extraction on the physiological data to obtain physiological features used to characterize physiological changes of the subject; Construct a physiological mapping relationship between physiological features and game materials. When the generated features are detected, the game materials in the corresponding game scene are automatically adjusted.

[0028] It should be noted that this embodiment utilizes existing eye movement acquisition technology and heart rate monitoring technology to realize the collection of physiological data, and extracts physiological features for characterizing the physiological changes of the subject based on existing feature extraction technology. In a simple example, the physiological changes of the subject may be distraction of attention.

[0029] This right collects physiological data such as eye movement trajectory and heart rate fluctuation of the subject and extracts features, constructs a mapping relationship between physiological features and game materials, and can automatically adjust game scene materials based on real-time physiological changes, accurately capture the psychological fluctuations of teenagers, and solve the problem that existing game generation only relies on questionnaires. It effectively improves the immersion of the evaluation process and the authenticity and validity of the results.

[0030] Through the above, by collecting the subjects' eye movement trajectories, heart rate fluctuations and other physiological data and extracting features, a physiological mapping relationship is constructed, and the game materials in the game scene are automatically adjusted based on real-time physiological changes. The psychological fluctuations of teenagers are accurately captured, and the problem of existing game generation relying on a single source is solved, which effectively improves the immersion of the evaluation process and the authenticity and effectiveness of the results.

[0031] As a preferred implementation of this embodiment, specifically, the construction of the physiological mapping relationship includes: A prediction model is trained based on historical physiological data. The prediction model inputs physiological data and outputs game material adjustment instructions. The game material adjustment instructions at least include text complexity adjustment instructions, visual element adjustment instructions, and interaction logic adjustment instructions.

[0032] It should be noted that the prediction model of this embodiment is constructed based on existing machine learning technologies, such as deep learning models. In this embodiment, the prediction model is trained using the historical physiological data of the research subject to implement game material adjustment instructions, thereby achieving accurate mapping between physiological data and game materials.

[0033] Through the above, the prediction model is trained through historical physiological data, and the physiological data is converted into game material adjustment instructions to achieve automatic optimization of game scenes according to the real-time psychological state of adolescents, which is different from traditional static evaluation. It significantly improves the adaptability of the evaluation process and the validity of the results, and provides technical support for personalized psychological evaluation.

[0034] In a specific application of this embodiment, analysis of the evaluation results of research subjects revealed that the fourth game architecture, derived from optimization of basic and physiological data, still exhibited poor evaluation effectiveness after game generation. To address this issue, this embodiment introduces validation of the fourth game architecture.

[0035] Specifically, the game engine construction method is aimed at constructing the game generation module and also includes: S4: Verify the validity of the fourth game architecture; wherein, the validity verification includes: synchronously collecting the selection data and behavior data of the testee, the selection data is the testee's evaluation answer, and the behavior data includes operation delay and repeated operation frequency; constructing an evaluation model, which is used to output a verification report when it is detected that the correlation between the selection data and the behavior data is lower than a preset threshold, and the verification report includes a confidence index for the fourth game architecture.

[0036] It should be noted that this embodiment is based on the construction of the evaluation model based on existing machine learning technology, for example, knowledge graph technology. In this embodiment, the selection data ( ) to behavioral data ( ) of the first mapping atlas and behavioral data ( ) to select data ( ), the correlation between the selection data and the behavior data is calculated using a correlation calculation formula, which is: in: and is the preset weight parameter; Indicates the number of entities in the first mapping graph that are mapped to the behavioral data based on the prediction of the selected data. Indicates the number of entities of behavioral data actually mapped to the selected data in the first mapping graph; Indicates the number of entities in the second mapping graph that are mapped to the selected data based on the behavioral data prediction, Indicates the number of entities of the selected data actually mapped to the behavior data in the second mapping graph; The correlation between the calculated choice data and behavior data.

[0037] In a simple example of this embodiment: , ; In the first mapping graph, , ; In the second mapping graph, , ; The calculated .

[0038] When the actual mapping ratio is higher and the correlation is closer to 1, it indicates that the mapping consistency between the selection data and the behavior data is better, that is, the validity of the psychological assessment based on the game is higher. In another simple example, This reflects that the mapping consistency is poor, that is, the effectiveness of the psychological assessment conducted by the test subject based on the game is low. In this embodiment, the preset threshold for the correlation can be obtained by fitting the data distribution of the historical correlation. In this embodiment, the preset threshold .

[0039] Through the above, the correlation calculation formula is used to quantify the correlation between selection data and behavior data, and provides a technical means for verifying the effectiveness of the fourth game architecture.

[0040] As a preferred implementation of this embodiment, specifically, when it is detected that the correlation between the selection data and the behavior data is lower than a preset threshold, an optimization action is performed, and the optimization action includes: Identify game assets that cause the correlation between selection data and behavior data to fall below a pre-set threshold; The game materials identified by artificial intelligence generation technology are analyzed and reconstructed, and the reconstructed game materials are verified. The verification is to reuse the evaluation model to detect the correlation between selection data and behavior data until the correlation is higher than a preset threshold.

[0041] Through the above, through dynamic detection of the correlation between selection data and behavioral data, low-correlation game materials are automatically identified and reconstructed, and iterative verification is carried out to ensure that the data correlation meets the standards, thus forming a self-optimization closed loop, and dynamically repairing the problem of inconsistent evaluation data, significantly improving the validity and reliability of gamified psychological assessment, and effectively solving the result distortion caused by material design defects in gamified assessment of adolescents, providing continuously evolving technical support for personalized psychological assessment, adapting to the cognitive characteristics of adolescents, and ensuring that the evaluation results are true and valid.

[0042] In a specific application of this embodiment, in order to optimize the second game architecture based on basic data, a third game architecture based on physiological data is introduced. Specifically, the second game architecture and the third game architecture are integrated, including: The similarity between the game materials in the second game architecture and the third game architecture is analyzed, and based on the similarity, the differentiated game materials are reorganized to form a fused game architecture.

[0043] It should be noted that the method for analyzing the similarity of game materials in the second game architecture and the third game architecture in this embodiment can be any existing method for similarity calculation. For example, the game materials in the second game architecture and the third game architecture are converted into corresponding feature vectors for representation, and the feature vectors are used to represent the dimensions corresponding to semantics, emotion and cognitive complexity; by calculating the similarity between vectors, differentiated game materials are screened and reorganized based on the similarity to form a fused game architecture, thereby maintaining the integrity of the evaluation dimensions while reducing redundancy.

[0044] In a specific application of this embodiment, after determining a psychological assessment questionnaire based on the patient's medical history, if the game is generated based solely on the psychological assessment questionnaire, the game effect will not be suitable for the patient. To address the above problem, this embodiment introduces the patient's basic data for optimization.

[0045] Specifically, adjusting the first game structure based on the basic data of the test subjects includes: Based on the basic data of the test subjects, a preset group knowledge base is called to match group game materials corresponding to the basic data of the test subjects; wherein the group knowledge base stores group characteristics of different groups of test subjects, and the group characteristics are used to characterize the cognitive levels and interest preferences of different test subjects; Adjust the difficulty curve, character settings, and situational themes in the first game architecture based on the matched group game materials.

[0046] It should be noted that the group knowledge base of this embodiment is constructed based on existing database technology, using the research subjects as the initial data source. The cognitive levels and interests of adolescents of different ages and genders are collected to match corresponding game materials for game generation. During this matching process, existing machine learning techniques can be used to improve the matching quality, such as the K-nearest neighbor algorithm. After expansion, based on the expanded research subjects, further basic data such as regional characteristics (the interests and preferences of adolescents in different regions vary) and growth characteristics (different adolescents enter different growth periods at different ages, and their growth periods, such as the rebellious period, can be obtained in advance through questionnaires) can be collected.

[0047] By leveraging the aforementioned data, the group knowledge base is accessed through the test subject's basic data, matching game materials to group characteristics such as cognitive level and interest preferences, and dynamically adjusting game difficulty, roles, and context. Unlike traditional single questionnaire generation, this approach precisely adapts to the differences among youth groups (such as age, region, and developmental characteristics), addressing the incompatibility between the game and the test subject, enhancing immersion and engagement during the assessment process. Simultaneously, the game structure is optimized based on cognition and interests, enhancing the fit between assessment content and adolescent psychology, significantly improving the validity of gamified psychological assessments, and providing technical support for personalized, scenario-based youth psychological assessments.

[0048] In a specific application of this embodiment, as the research object expands, if the game materials are not optimized, the use of the game engine in this embodiment will be limited, further affecting the effectiveness of the psychological assessment. To address this problem, this embodiment introduces continuous optimization of game materials.

[0049] Specifically, the game engine construction method is aimed at constructing the game generation module and also includes: S5: Based on the evaluation results, continuously optimize the game materials. This optimization includes: recording the usage data of each game material and its impact on the evaluation results. When abnormal fluctuations in the impact value are detected, the material optimization process is triggered. The material optimization process includes game material replacement, parameter adjustment, and structural reorganization.

[0050] It should be noted that the usage data of game materials in this embodiment and their impact on the evaluation effect are based on existing data analysis technology, aiming to monitor the different impacts of different game materials. In fact, abnormal fluctuations are determined based on the fitting of data statistics of the impact values, and this text does not impose any restrictions on this.

[0051] By continuously recording game asset usage data and assessment impact, a dynamic optimization mechanism is established to automatically trigger asset replacement, parameter adjustment, or structural reorganization when asset performance deviates. This mechanism can update assets in real time as the scale of research subjects expands (e.g., to cover more youth groups), breaking through the rigid limitations of traditional game assets and ensuring that the game engine remains consistently adapted to the changing cognitive development and psychological characteristics of adolescents. Through dynamic optimization, the adaptability of gamified assessments to diverse scenarios and populations is effectively enhanced, continuously ensuring assessment validity. This provides long-term, stable technical support for large-scale adolescent psychological assessments, enhances the system's robustness in complex data environments, and addresses the issue of diminished assessment effectiveness caused by unoptimized assets.

[0052] In a specific application of this embodiment, existing artificial intelligence generation technology is used to analyze psychological assessment questionnaires, for example, multi-agent technology. Based on multi-agent technology, this embodiment adapts the artificial intelligence generation technology to a first generation model and a second generation model.

[0053] Specifically, artificial intelligence generation technology includes: The first generative model is used to generate narrative content corresponding to the psychological assessment questionnaire; The second generative model is used to generate a representation that matches the narrative content, and the representation corresponds to the game material; The game architecture is generated based on the first generation model and the second generation model.

[0054] Based on the above, this embodiment uses the first generative model to generate narrative content corresponding to the psychological assessment questionnaire, while the second generative model generates matching game presentation (such as visual and auditory materials). These two models collaborate based on multi-agent technology to achieve multimodal alignment of narrative and presentation. This provides the data foundation for the generation of the first, second, third, and fourth game structures.

[0055] The second aspect of this embodiment discloses Figure 2 The following is an implementation strategy for an adaptive psychological assessment for teenagers, which is applicable to the above-mentioned method for building an adaptive psychological assessment game engine for teenagers. The implementation strategy includes: A1: Utilizing artificial intelligence generation technology to analyze the psychological assessment questionnaire corresponding to the testee and generate a first game framework; wherein the first game framework stores game materials corresponding to the psychological assessment questionnaire, and the game materials include at least text elements, visual elements, auditory elements, and interactive logic; A2: Obtain the subject's basic data and adjust the first game framework to generate a second game framework and output it for game generation. A psychological assessment is then conducted on the subject based on the generated game. The basic data represents the subject's identity information, and the second game framework stores game materials corresponding to the basic data and the psychological assessment questionnaire. A3: Utilize artificial intelligence generation technology to parse a new psychological assessment questionnaire corresponding to the testee, generate a third game framework, collect the testee's physiological data and adjust the second game framework, fuse the second game framework and the third game framework to generate a fourth game framework and output it for generating a game, and conduct a psychological assessment on the testee based on the generated game; wherein, the third game framework stores game materials corresponding to the new psychological assessment questionnaire, the physiological data is used to characterize the testee's psychological fluctuations, and the fourth game framework stores game materials corresponding to the basic data, physiological data, and the new psychological assessment questionnaire.

[0056] It should be noted that the implementation strategy for the adaptive psychological assessment for teenagers in this embodiment corresponds to the aforementioned method for building an adaptive psychological assessment game engine for teenagers. Therefore, any details not specifically described in the implementation strategy for the adaptive psychological assessment for teenagers in this embodiment, including but not limited to functional definitions, operating principles, and background technology, can be referenced in the aforementioned method for building an adaptive psychological assessment game engine for teenagers, and are not further elaborated in this document.

[0057] In summary, the method and implementation strategy for constructing an adaptive psychological assessment game engine for teenagers in this embodiment uses artificial intelligence generation technology to analyze psychological assessment questionnaires to generate game architectures, combines the basic data of the subjects to call the group knowledge base to match personalized game materials, dynamically adjusts the difficulty, roles and situations, and solves the problem of mismatch between traditional questionnaires and adolescent cognition; introduces physiological data collection and feature extraction, and generates material adjustment instructions through historical data training prediction models to achieve real-time optimization of game scenes with psychological fluctuations, accurately capturing real states such as attention distraction; dynamically repairs data inconsistencies and improves assessment validity by calculating the correlation between selected data and behavioral data and reconstructing low-correlation materials; integrates differentiated materials from multiple game architectures to reduce redundancy and ensure dimensional integrity; establishes a continuous optimization mechanism for game materials, and updates them in real time as the research objects expand, breaking through the rigid limitations of materials; adopts multi-agent technology to drive the dual generation model to achieve multimodal alignment of narrative and expression forms, and enhances immersion; thereby effectively solving the problems of teenagers' resistance to assessment, the high cost of traditional methods and the insufficient validity of gamified assessment, improving participation and the authenticity of results, and adapting to the needs of large-scale psychological assessment.

[0058] In the embodiments provided herein, it should be understood that the embodiments described herein can be implemented using hardware, software, firmware, middleware, code, or any appropriate combination thereof. For hardware implementation, the processor may be implemented in one or more of the following: an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field-programmable gate array (FPGA), a processor, a controller, a microcontroller, a microprocessor, or other electronic units designed to implement the functionality described herein, or any combination thereof. For software implementation, some or all of the processes of the embodiments may be performed by a computer program instructing the relevant hardware. During implementation, the program may be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein communication media includes any medium that facilitates the transmission of a computer program from one location to another. The storage medium may be any available medium that can be accessed by a computer. Computer-readable storage media may include, but are not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing the desired program code in the form of instructions or data structures and accessible by a computer.

[0059] Finally, it should be noted that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or make equivalent replacements for some of the technical features therein. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method for constructing an adaptive psychological assessment game engine for teenagers, wherein the game engine is constructed based on a game generation module and different psychological assessment questionnaires, and is configured to generate a game for psychological assessment after parsing the psychological assessment questionnaire using the game generation module, characterized in that: The construction method of the game engine includes the following steps for constructing the game generation module: S1: Analyze the psychological assessment questionnaire using artificial intelligence generation technology to generate a first game framework; wherein the first game framework stores game materials corresponding to the psychological assessment questionnaire, and the game materials include at least text elements, visual elements, auditory elements, and interactive logic; S2: Adjusting the first game framework based on the basic data of the test subject, generating a second game framework, and outputting the second game framework for game generation; wherein the basic data is used to represent the identity information of the test subject, and the second game framework stores game materials corresponding to the basic data and the psychological assessment questionnaire; S3: Utilize artificial intelligence generation technology to analyze the new psychological assessment questionnaire, generate a third game framework, adjust the second game framework based on the physiological data of the testee, fuse the second game framework and the third game framework to generate a fourth game framework and output it for generating a game; wherein, the third game framework stores game materials corresponding to the new psychological assessment questionnaire, the physiological data is used to characterize the psychological fluctuations of the testee, and the fourth game framework stores game materials corresponding to the basic data, the physiological data and the new psychological assessment questionnaire.

2. The method for constructing an adaptive psychological assessment game engine according to claim 1, wherein: The adjusting the second game architecture based on the physiological data of the test subject specifically includes: Collecting the physiological data of the subject, the physiological data including at least eye movement trajectory and heart rate fluctuation, and performing feature extraction on the physiological data to obtain physiological features for characterizing physiological changes of the subject; A physiological mapping relationship between the physiological characteristics and the game materials is constructed, and when the generated characteristics are detected, the game materials in the corresponding game scene are automatically adjusted.

3. The method for constructing an adaptive psychological assessment game engine according to claim 2, wherein: The construction of the physiological mapping relationship includes: A prediction model is trained based on historical physiological data, the prediction model input is the physiological data, and the output is game material adjustment instructions, the game material adjustment instructions at least include text complexity adjustment instructions, visual element adjustment instructions, and interaction logic adjustment instructions.

4. The method for constructing an adaptive psychological assessment game engine according to claim 1, wherein: The game engine construction method is directed to the construction of a game generation module and further includes: S4: Verify the validity of the fourth game architecture; wherein, the validity verification includes: synchronously collecting the selection data and behavior data of the testee, the selection data being the testee's evaluation answer, and the behavior data including operation delay and repeated operation frequency; constructing an evaluation model, which is used to output a verification report when it is detected that the correlation between the selection data and the behavior data is lower than a preset threshold, and the verification report includes a confidence index for the fourth game architecture.

5. The method for constructing an adaptive psychological assessment game engine according to claim 4, wherein: When it is detected that the correlation between the selection data and the behavior data is lower than a preset threshold, an optimization action is performed, the optimization action including: identifying game material that causes the correlation between the selection data and the behavior data to be below a preset threshold; The identified game materials are analyzed and reconstructed based on artificial intelligence generation technology, and the reconstructed game materials are verified. The verification is to reuse the evaluation model to detect the correlation between the selection data and the behavior data until the correlation is higher than a preset threshold.

6. The method for constructing an adaptive psychological assessment game engine according to claim 1, wherein: The integration of the second game architecture and the third game architecture specifically includes: The similarity between the game materials in the second game architecture and the third game architecture is analyzed, and based on the similarity, the differentiated game materials are reorganized to form a fused game architecture.

7. The method for constructing an adaptive psychological assessment game engine according to claim 1, wherein: The adjusting of the first game architecture based on the basic data of the test subject specifically includes: Based on the basic data of the test subjects, a preset group knowledge base is called to match group game materials corresponding to the basic data of the test subjects; wherein the group knowledge base stores group characteristics of different groups of test subjects, and the group characteristics are used to characterize the cognitive levels and interest preferences of different test subjects; The difficulty curve, character settings, and situational themes in the first game architecture are adjusted based on the matched group game materials.

8. The method for constructing an adaptive psychological assessment game engine according to claim 1, wherein: The game engine construction method is directed to the construction of a game generation module and further includes: S5: Based on the evaluation results, the game materials are continuously optimized. The optimization includes: recording the usage data of each game material and its impact on the evaluation results. When abnormal fluctuations in the impact value are detected, the material optimization process is triggered. The material optimization process includes game material replacement, parameter adjustment and structural reorganization.

9. The method for constructing an adaptive psychological assessment game engine according to claim 1, wherein: The artificial intelligence generation technology includes: The first generative model is used to generate narrative content corresponding to the psychological assessment questionnaire; A second generation model is used to generate a representation that matches the narrative content, the representation corresponding to the game material; A game architecture is generated based on the first generation model and the second generation model.

10. An implementation strategy for an adaptive psychological assessment for teenagers, the implementation strategy being applicable to the method for constructing an adaptive psychological assessment game engine for teenagers as described in any one of claims 1 to 9, characterized in that: The implementation strategy includes: A1: Analyze the psychological assessment questionnaire corresponding to the test subject using artificial intelligence generation technology to generate a first game framework; wherein the first game framework stores game materials corresponding to the psychological assessment questionnaire, and the game materials include at least text elements, visual elements, auditory elements, and interactive logic; A2: Obtaining basic data of the test subject and adjusting the first game architecture to generate a second game architecture and output it for game generation, and conducting a psychological assessment on the test subject based on the generated game; wherein the basic data is used to represent the test subject's identity information, and the second game architecture stores game materials corresponding to the basic data and the psychological assessment questionnaire; A3: Utilize artificial intelligence generation technology to parse a new psychological assessment questionnaire corresponding to the testee, generate a third game framework, collect the testee's physiological data and adjust the second game framework, fuse the second game framework and the third game framework to generate a fourth game framework and output it for generating a game, and conduct a psychological assessment on the testee based on the generated game; wherein, the third game framework stores game materials corresponding to the new psychological assessment questionnaire, the physiological data is used to characterize the testee's psychological fluctuations, and the fourth game framework stores game materials corresponding to the basic data, the physiological data, and the new psychological assessment questionnaire.

Images