Student psychological intervention scheme processing method and device based on multi-modal model cooperation

Abstract

According to the student psychological intervention scheme processing method and device based on multi-modal model cooperation, the accurate psychological model of the student is constructed through multi-source data on the basis of the virtual test environment, the current psychological state of the student can be reflected, the future emotional change of the student and the possible response to various intervention measures can be predicted, and the student psychological intervention scheme processing method and device based on multi-modal model cooperation are provided. According to the invention, an intervention decision maker can compare and evaluate a plurality of different intervention strategy combinations before actual implementation, so that an optimal scheme is scientifically selected to be implemented to real students, the trial and error cost of psychological intervention is remarkably reduced, and the accuracy and effectiveness of intervention are effectively improved.

Description

Technical Field

[0001] This application relates to the field of mental health, specifically to a method and apparatus for processing student psychological intervention programs based on multimodal model collaboration. Background Technology

[0002] In recent years, mental health problems have shown a trend of occurring at younger ages and becoming more widespread. Academic pressure, family relationships, social barriers and other factors have led to the increasing complexity of students' mental health issues.

[0003] Existing student mental health monitoring and intervention systems mainly operate by collecting psychological assessment data, analyzing behavioral patterns, and providing standardized intervention recommendations.

[0004] However, the inventors of this application have discovered the following three significant defects:

[0005] 1) Lack of internal trial and error mechanism: The existing system cannot assess the possible effects of the intervention plan in advance before implementation, and directly applies the generated suggestions to students, resulting in unpredictable intervention risks, serious waste of resources, and high trial and error costs;

[0006] 2) Adopting a single model structure: It often uses a single prediction model or a simple linear model chain, which cannot achieve in-depth collaboration in professional fields such as psychological analysis, risk assessment and intervention management, forming information silos and limiting the overall performance of the system;

[0007] 3) Static methods cannot be dynamically updated: After the system is deployed, the model parameters are basically fixed, lacking a learning mechanism. It is impossible to dynamically update the entire module system based on the actual feedback from students, making it difficult to adapt to new data and changing environments, resulting in insufficient long-term effectiveness. Summary of the Invention

[0008] This application provides a method and device for processing student psychological intervention programs based on multimodal model collaboration. Based on a virtual testing environment, it constructs an accurate psychological model of students through multi-source data, which can not only reflect the current psychological state of students, but also predict their future emotional changes and possible responses to various intervention measures. This allows intervention decision-makers to compare and evaluate a variety of different intervention strategy combinations before actual implementation.

[0009] Firstly, this application provides a method for processing student psychological intervention programs based on multimodal model collaboration. This method is applied to a student psychological intervention system, which includes a student simulation module, a psychological analysis module, a risk assessment module, and an intervention management module. The method includes:

[0010] Based on virtual student data, the student simulation module uses a student simulation model to simulate the personality, behavior, and psychological state of the corresponding students, thereby obtaining simulation data.

[0011] Based on simulated data, the psychological analysis module uses a psychological analysis model to conduct in-depth analysis of the current psychological state and emotional change characteristics, thereby obtaining psychological features.

[0012] Based on psychological characteristics, the risk assessment module uses a risk assessment model to judge and handle potential psychological crises, and obtains corresponding psychological risk assessment results.

[0013] Based on the psychological risk assessment results, the intervention management module generates personalized intervention plans using the intervention management model. These personalized intervention plans are used to provide psychological counseling and support.

[0014] Secondly, this application provides a student psychological intervention program processing device based on multimodal model collaboration. The device is applied to a student psychological intervention system, which includes a student simulation module, a psychological analysis module, a risk assessment module, and an intervention management module. The device includes:

[0015] The simulation unit is used by the student simulation module to simulate the personality, behavior and psychological state of the corresponding students based on virtual student data and using a student simulation model to obtain simulation data.

[0016] The analysis unit is used by the psychological analysis module to conduct in-depth analysis of the current psychological state and emotional change characteristics based on the simulated data and using a psychological analysis model to obtain psychological characteristics.

[0017] The judgment unit is used by the risk assessment module to judge and process potential psychological crises based on psychological characteristics and using a risk assessment model to obtain corresponding psychological risk assessment results.

[0018] The generation unit is used by the intervention management module to generate personalized intervention plans based on the results of psychological risk assessment using the intervention management model. The personalized intervention plans are used to provide psychological counseling and support.

[0019] Thirdly, this application provides a student psychological intervention system based on multimodal model collaboration, including a processor and a memory, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, it executes the method provided by the first aspect of this application or any possible implementation of the first aspect of this application.

[0020] Fourthly, this application provides a computer-readable storage medium storing a plurality of instructions adapted for loading by a processor to perform the method provided in the first aspect of this application or any possible implementation thereof.

[0021] From the above, it can be concluded that this application has the following beneficial effects:

[0022] Targeting the goals of mental health monitoring and intervention, this application uses a virtual testing environment as a foundation to construct an accurate psychological model of students through multi-source data. This model not only reflects the students' current psychological state but also predicts their future emotional changes and possible responses to various intervention measures. This allows intervention decision-makers to compare and evaluate different combinations of intervention strategies before actual implementation, thereby scientifically selecting the optimal solution for real students. This significantly reduces the trial-and-error costs of psychological intervention and effectively improves the accuracy and effectiveness of intervention. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of a scenario for the student psychological intervention system based on multimodal model collaboration, as described in this application.

[0025] Figure 2 This is a flowchart illustrating a student psychological intervention program based on a multimodal model collaboration method, as described in this application.

[0026] Figure 3 This is a schematic diagram of a student psychological intervention program processing device based on multimodal model collaboration, as described in this application.

[0027] Figure 4 This is a schematic diagram of a student psychological intervention system based on multimodal model collaboration, as described in this application. Detailed Implementation

[0028] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0029] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules is not necessarily limited to those explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or devices. The naming or numbering of steps appearing in this application does not imply that the steps in the method flow must be performed in the chronological / logical order indicated by the naming or numbering. The execution order of named or numbered process steps can be changed according to the desired technical purpose, as long as the same or similar technical effect is achieved.

[0030] The module division described in this application is a logical division. In practical applications, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the coupling or direct coupling or communication connection between modules shown or discussed may be through some interfaces, and the indirect coupling or communication connection between modules may be electrical or other similar forms, none of which are limited in this application. Furthermore, the modules or sub-modules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed in multiple circuit modules. Some or all of the modules may be selected to achieve the purpose of the solution in this application according to actual needs.

[0031] Before introducing the student psychological intervention program based on multimodal model collaboration provided in this application, we will first introduce the background content involved in this application.

[0032] The student psychological intervention program processing method, device, and computer-readable storage medium based on multimodal model collaboration provided in this application can be applied to a student psychological intervention system based on multimodal model collaboration. Based on a virtual testing environment, it constructs an accurate psychological model of students through multi-source data, which can not only reflect the current psychological state of students, but also predict their future emotional changes and possible responses to various intervention measures. This allows intervention decision-makers to compare and evaluate various combinations of intervention strategies before actual implementation, thereby scientifically selecting the optimal solution to implement for real students, significantly reducing the trial and error cost of psychological intervention, and effectively improving the accuracy and effectiveness of intervention.

[0033] The student psychological intervention program processing method based on multimodal model collaboration mentioned in this application can be implemented by a student psychological intervention program processing device based on multimodal model collaboration, or a student psychological intervention system based on multimodal model collaboration, such as a server, physical host, or user equipment (UE) integrating the student psychological intervention program processing device based on multimodal model collaboration. The student psychological intervention program processing device based on multimodal model collaboration can be implemented in hardware or software. The UE can specifically be a terminal device such as a smartphone, tablet, laptop, desktop computer, or personal digital assistant (PDA). The student psychological intervention system based on multimodal model collaboration can be configured through a device cluster.

[0034] It is understandable that this application is usually based on existing data processing. Therefore, the student psychological intervention scheme processing method based on multimodal model collaboration of this application, or the student psychological intervention system based on multimodal model collaboration that carries the corresponding application service of the student psychological intervention scheme processing method based on multimodal model collaboration of this application, usually only needs to meet the required data processing capabilities. The specific equipment type and equipment deployment form are quite flexible.

[0035] If the direct collection of existing data mentioned above is involved, or if there are application requirements such as result display, then it is clear that further adaptive configuration of the software and hardware of the student psychological intervention system based on multimodal model collaboration is needed.

[0036] For example, a student psychological intervention system based on multimodal model collaboration can be divided into a first equipment part responsible for data collection, a second equipment part responsible for processing student psychological intervention plans based on multimodal model collaboration, and a third equipment part responsible for displaying results.

[0037] Furthermore, it is understood that this application involves a multimodal model collaboration processing mechanism, or in other words, the application of a fusion model that integrates processing models of different modalities. Therefore, the solution in this application may also involve the early model training stage before the model application stage.

[0038] Correspondingly, the student psychological intervention system based on multimodal model collaboration can be divided into a first equipment part responsible for model training, a second equipment part responsible for processing intervention plans based on multimodal model collaboration (fusion model), and a third equipment part responsible for displaying results.

[0039] The following section introduces the student psychological intervention program based on multimodal model collaboration provided in this application.

[0040] First, it is understood that the student psychological intervention program processing method based on multimodal model collaboration provided in this application is applied to a student psychological intervention system based on multimodal model collaboration. This system includes four main modules: a student simulation module, a psychological analysis module, a risk assessment module, and an intervention management module, corresponding to the system's four-layer processing architecture, which can be referenced here. Figure 1 The following is a schematic diagram of a scenario for a student psychological intervention system based on a multimodal model collaboration, as shown in this application, to provide a more vivid understanding.

[0041] As can be seen, the core of this application lies in building a closed-loop system for multi-model collaboration, which is configured with four specialized modules for processing corresponding models, each performing its own function while working closely together. These modules include:

[0042] 1) The student simulation module serves as the "digital twin core" of the system, providing a verifiable feedback mechanism;

[0043] 2) The psychological analysis module is responsible for in-depth analysis of students' psychological state, providing a professional psychological perspective;

[0044] 3) The risk assessment module quantifies risks and predicts development trends, providing data support for decision-making;

[0045] 4) The intervention management module translates analysis into action and verifies the optimization plan through simulation.

[0046] Unlike traditional methods, this system's unique "simulation-verification-optimization" loop transforms the entire process from linear to iterative, achieving truly precise intervention. The system's data flow and workflow can be described as a closed-loop process, from multi-source data collection to student simulation, psychological analysis, risk assessment, and intervention management. Finally, each module is continuously optimized through simulation verification and real-world feedback. A simplified data flow can be summarized as follows:

[0047]

[0048] It should be noted that the Large Language Model (LLM) configured for each of the four professional modules mentioned above can be configured according to actual needs in practice, therefore this application does not impose specific limitations.

[0049] As an example, the large language models involved in this application can specifically refer to large language models of types such as GPT, DeepSeek, Claude, and Qwen Chat.

[0050] Furthermore, for the four major professional modules mentioned above, in terms of details, the same large language model can be used for all or part of them, or different large language models can be used. This can be flexibly configured according to the actual situation.

[0051] Next, please refer to... Figure 2 , Figure 2 This paper illustrates a flowchart of a student psychological intervention program processing method based on multimodal model collaboration, as described in this application. The student psychological intervention program processing method based on multimodal model collaboration provided in this application may specifically include the following steps S201 to S204:

[0052] Step S201: Based on the virtual student data, the student simulation module uses a student simulation model to simulate the personality, behavior, and psychological state of the corresponding students to obtain simulation data.

[0053] Understandably, this application uses a virtual approach and a four-layer processing analysis to predict students' future emotional changes and possible responses to various interventions under different circumstances, thereby providing strong data support.

[0054] In response, this application can configure corresponding virtual student data for virtual / fictional student objects as data input for student simulation processing here, and drive the data processing and analysis of the subsequent three layers.

[0055] In addition, it should be noted that this application scheme can also be used for groups other than students. The processing logic of the scheme is the same, so it can also be called user object, virtual user, etc.

[0056] As an exemplary embodiment, the student data involved herein can be denoted as student data x, which may specifically include psychological assessment data x. psych Academic performance data x academic Student behavior data x behavior Student social data x social Environmental factors x env And personalized intervention plan P (tentative or already implemented intervention plan).

[0057] As can be seen, this section provides a specific and feasible implementation plan for the student data that this application may involve.

[0058] It is important to understand that the data mentioned above is usually directly virtual / constructed data, or it can be real data after removing personal privacy, or data processed based on real data.

[0059] Meanwhile, regarding the configuration of the student simulation model, as an exemplary embodiment, the student simulation model can be denoted as f. sim The simulated data output by the model can be denoted as p. sim And simulated data p sim Specifically, this can include predictions of language expression patterns (E), behavioral response simulations (B), emotional fluctuations (F), and potential psychological needs (N), and the following probabilistic relationships may exist:

[0060] p sim (E,B,F,N|X)=p sim (E∣X)·p sim (B∣X,E)·p sim (F∣X,E,B)·p sim (N|X,E,B,F).

[0061] Understandably, the student simulation model involved here, and several subsequent models, can be denoted as different models θ. In the design of this application, each of these different models θ will use a corresponding modal pre-trained encoder (such as a Transformer text encoder, a ViT visual encoder, or a dedicated sequence encoder) to map the original model input x into a vector representation v. This vector representation v is then fed into the same language model to generate unnormalized output logits (a raw prediction value, or the output of the last layer of the model before the output layer, which needs to be further processed by the output layer or activation function for final model output). Finally, the output logits are subjected to a softmax operation by a softmax layer to obtain the probability distribution of each candidate output y, corresponding to the following expression:

[0062] v x =Encoder modality,φ (x),

[0063] p θ (y|x)=Softmax(LM) θ (v x )) y .

[0064] The simulated data p that the student simulation model needs to output here corresponds to... sim (In single probability form), it can be seen that it also involves the joint probability setting of language expression pattern prediction E, behavioral response simulation B, emotional fluctuation prediction F and potential psychological needs N. That is, it needs to be calculated by the above joint probability formula.

[0065] Similarly, subsequent psychoanalysis models, risk assessment models, and intervention management models also involve joint probability settings.

[0066] Understandably, this section provides specific implementation schemes for the student situation initially simulated or predicted by the student simulation model in this application, such as possible psychological fluctuations and needs. From the perspective of probability expression, further scheme configurations are given, which helps the student simulation model to better complete the processing of simulation data and provide high-quality data input for subsequent scheme processing.

[0067] Step S202: Based on the simulated data, the psychological analysis module uses a psychological analysis model to conduct an in-depth analysis of the current psychological state and emotional change characteristics to obtain psychological characteristics.

[0068] After obtaining the corresponding simulation data through the student simulation model in the first layer of the model, the psychological analysis model in the second layer of the model can continue to perform further in-depth analysis and more refined predictive processing to obtain the specific psychological characteristics of the current virtual student.

[0069] Specifically, as an exemplary embodiment herein, the method of this application may further include:

[0070] Obtain students' authentic multimodal expression data (D) and historical mental health records (H);

[0071] It is understandable that the additional student real multimodal expression data D and historical mental health records H involved here are processed in the same way as the virtual student data mentioned above.

[0072] Furthermore, in some cases, the student's real multimodal expression data D and historical mental health records H, which are additionally involved here, may themselves be part of the virtual student data, but are not used as data inputs for the student simulation model.

[0073] On the other hand, the psychoanalytic model can be denoted as f psych The psychological features output by the model can be denoted as p. psych And this psychological characteristic p psych Specifically, this can include a multidimensional psychological feature map M, a prediction of psychological state change trends T, identification of key psychological needs K, and early signal identification results W of potential psychological problems, and the following probabilistic relationships may exist:

[0074]

[0075] Similar to the preceding exemplary embodiments, this embodiment provides a specific implementation scheme for the student's current psychological state and emotional change characteristics predicted by the psychological analysis model of this application, and gives further scheme configuration from the perspective of probability expression. This helps the psychological analysis model to better complete the processing of psychological characteristics and provide high-quality data input for subsequent scheme processing.

[0076] Step S203: Based on psychological characteristics, the risk assessment module uses a risk assessment model to judge and handle potential psychological crises, and obtains the corresponding psychological risk assessment results.

[0077] After the psychological analysis model provides the corresponding specific psychological characteristics, the risk assessment module at the third level of the model can then be used to make further psychological crisis judgments or psychological risk assessments, corresponding to various situations that may arise in actual operation.

[0078] As an exemplary embodiment herein, the risk assessment model can be denoted as f risk The output of the model can be denoted as p. risk The psychological risk assessment result p risk Specifically, this can include multi-dimensional risk scoring (R) and risk evolution path prediction (E). risk Key intervention time window T int Analysis of risk triggering factors and protective factors Γ, and the following probabilistic relationships may exist:

[0079]

[0080] Similar to the exemplary embodiments above, this embodiment provides a specific implementation scheme for the psychological crisis and psychological risk predicted by the risk assessment model of this application, and gives further scheme configuration from the perspective of probability expression. This helps the risk assessment model to better complete the processing of psychological risk assessment results and provide high-quality data input for subsequent scheme processing.

[0081] Step S204: Based on the psychological risk assessment results, the intervention management module generates a personalized intervention plan using the intervention management model. The personalized intervention plan is used to provide psychological counseling and support.

[0082] Understandably, after the first three layers of processing have deeply and accurately captured the psychological crisis and risks faced by the current virtual students, the intervention management model at the fourth layer of the model can then generate a final personalized intervention plan based on the corresponding psychological risk assessment results. This personalized intervention plan is an important component that provides relevant decision-makers with convenient and visualized data references. If adopted, it will obviously provide effective psychological guidance and support to the corresponding students during the implementation of the specific intervention plan.

[0083] Specifically, as an exemplary embodiment herein, the intervention management model can be denoted as f int The personalized intervention plan output by the model can be denoted as p. intThis personalized intervention plan p int The following probability relationships may exist:

[0084]

[0085] Where, π i For personalized intervention programs p int The i-th character in the text, π <i For personalized intervention programs p int The i-1 characters preceding the i-th character.

[0086] Similar to the preceding exemplary embodiments, this embodiment provides a specific implementation scheme for the personalized intervention plan predicted by the intervention management model of this application, and gives further scheme configuration from the perspective of probability expression. This helps the intervention management model to better complete the processing of personalized intervention plans and give better processing results to the output of the overall model.

[0087] Meanwhile, the personalized intervention plan obtained through the intervention management model here, as an exemplary embodiment, can specifically be the optimal intervention plan determined among different intervention plans, and the following deterministic relationship can be established:

[0088] S * =arg max P U(E,B,F,N),

[0089] Among them, S * Let U be the optimal intervention plan output, U be the utility function, and p be the probability of all different intervention plans output by the intervention management module.

[0090] It is important to understand that the specific utility function used can be flexibly configured according to actual needs during actual operation.

[0091] Furthermore, the above content mainly explains the model application stage. In practical applications, it is easy to understand that this application may also involve the prior model training stage.

[0092] For model training, the model is trained based on training samples. For testing, it is necessary to obtain sample virtual student data and configure corresponding annotations, i.e., the personalized intervention plan output by the model. Then, based on the annotated sample virtual student data, specific model training is performed to train the four models in the fusion model based on multimodal model collaboration designed in this application.

[0093] Specifically, as an example, the model training process that this application may involve may include the following:

[0094] The student simulation model is continuously updated based on real feedback (Δ), forming a closed-loop adaptive optimization:

[0095]

[0096] Where, θ new For the updated student simulation model f sim The parameters,

[0097] Throughout the process, the psychoanalysis model, risk assessment model, and intervention management model were optimized sequentially based on feedback from the previous student simulation model. The optimization methods were as follows:

[0098]

[0099] in, For the updated psychoanalytic model f psych The parameters, For the updated risk assessment model f risk The parameters, For the updated intervention management model f int The parameters.

[0100] Finally, regarding the above-mentioned proposal, it can be seen that, for the goal of mental health monitoring and intervention, this application, based on a virtual testing environment, constructs an accurate psychological model of students through multi-source data. This model not only reflects the students' current psychological state but also predicts their future emotional changes and possible responses to various intervention measures. This allows intervention decision-makers to compare and evaluate various combinations of intervention strategies before actual implementation, thereby scientifically selecting the optimal solution for real students. This significantly reduces the trial-and-error costs of psychological intervention and effectively improves the accuracy and effectiveness of the intervention.

[0101] The above is an introduction to the student psychological intervention scheme processing method based on multimodal model collaboration provided in this application. To facilitate better implementation of the student psychological intervention scheme processing method based on multimodal model collaboration provided in this application, this application also provides a student psychological intervention scheme processing device based on multimodal model collaboration from the perspective of functional modules. The student psychological intervention scheme processing device based on multimodal model collaboration is applied to a student psychological intervention system, which includes a student simulation module, a psychological analysis module, a risk assessment module, and an intervention management module.

[0102] See Figure 3 , Figure 3 This is a schematic diagram of a student psychological intervention program processing device based on multimodal model collaboration, as described in this application. Specifically, the student psychological intervention program processing device 300 based on multimodal model collaboration may include the following structure:

[0103] The simulation unit 301 is used by the student simulation module to simulate the personality, behavior and psychological state of the corresponding students based on the virtual student data and using the student simulation model to obtain simulation data.

[0104] Analysis unit 302 is used by the psychological analysis module to conduct in-depth analysis of the current psychological state and emotional change characteristics based on the simulated data and using a psychological analysis model to obtain psychological characteristics;

[0105] The judgment unit 303 is used by the risk assessment module to judge and process the possible psychological crisis based on the psychological characteristics and the risk assessment model, and obtain the corresponding psychological risk assessment result.

[0106] The generation unit 304 is used by the intervention management module to generate personalized intervention plans based on the psychological risk assessment results using the intervention management model. The personalized intervention plans are used to provide psychological counseling and support.

[0107] In one exemplary embodiment, student data x includes psychological assessment data x. psych Academic performance data x academic Student behavior data x behavior Student social data x social Environmental factors x env And personalized intervention plans (P).

[0108] In yet another exemplary embodiment, the simulated data p sim These include predictions of language expression patterns (E), behavioral response simulations (B), emotional fluctuations (F), and potential psychological needs (N), and the following probabilistic relationships exist:

[0109] p sim (E,B,F,N|X)=p sim (E∣X)·p sim (B∣X,E)·p sim (F∣X,E,B)·p sim (N|X,E,B,F).

[0110] In yet another exemplary embodiment, the apparatus further includes an acquisition unit 305 for acquiring students’ real multimodal expression data D and historical mental health records H;

[0111] Psychological characteristics p psych It includes a multidimensional psychological feature map M, a prediction of psychological state change trends T, identification of key psychological needs K, and identification results of early signals of potential psychological problems W, and the following probabilistic relationships exist:

[0112]

[0113] In yet another exemplary embodiment, the psychological risk assessment result p risk Including multi-dimensional risk score R and risk evolution path prediction E risk Key intervention time window T int Analysis of risk triggering factors and protective factors reveals the following probabilistic relationships:

[0114]

[0115] In yet another exemplary embodiment, the personalized intervention plan p int The following probability relationship exists:

[0116]

[0117] Where, π i For personalized intervention programs p int The i-th character in the text, π <i For personalized intervention programs p int The i-1 characters preceding the i-th character.

[0118] In yet another exemplary embodiment, the personalized intervention plan is the optimal intervention plan determined among different intervention plans, corresponding to the following determining relationship:

[0119] S * =arg max P U(E,B,F,N),

[0120] Among them, S * Let U be the optimal intervention plan output, U be the utility function, and p be the probability of all different intervention plans output by the intervention management module.

[0121] This application also provides a student psychological intervention system based on a multimodal model collaboration from a hardware architecture perspective. This system can be understood as a processing device (including the case of a device cluster). See [link / reference]. Figure 4 , Figure 4 This diagram illustrates a structural schematic of a student psychological intervention system based on a multimodal model collaboration according to this application. Specifically, the student psychological intervention system based on a multimodal model collaboration according to this application may include a processor 401, a memory 402, and an input / output device 403. The processor 401 is used to execute the computer program stored in the memory 402 to implement, for example... Figure 2 The corresponding embodiments describe the steps of the student psychological intervention program processing method based on multimodal model collaboration; or, when the processor 401 executes the computer program stored in the memory 402, it implements the following: Figure 3 Corresponding to the functions of each unit in the embodiment, the memory 402 is used to store the functions executed by the processor 401 as described above. Figure 2The computer program required for the student psychological intervention program processing method based on multimodal model collaboration in the corresponding embodiment.

[0122] For example, a computer program may be divided into one or more modules / units, one or more of which are stored in memory 402 and executed by processor 401 to complete this application. One or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in a computer device.

[0123] A student psychological intervention system based on multimodal model collaboration may include, but is not limited to, processor 401, memory 402, and input / output device 403. Those skilled in the art will understand that the illustrations are merely examples of a student psychological intervention system based on multimodal model collaboration and do not constitute a limitation on such a system. It may include more or fewer components than illustrated, or combine certain components, or use different components. For example, a student psychological intervention system based on multimodal model collaboration may also include network access devices, buses, etc., with processor 401, memory 402, input / output device 403, etc., connected via a bus.

[0124] Processor 401 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the student psychological intervention system based on a multimodal model collaboration, connecting various parts of the entire device through various interfaces and lines.

[0125] The memory 402 can be used to store computer programs and / or modules. The processor 401 implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 402 and by calling the data stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created based on the use of a student psychological intervention system based on a multimodal model collaboration, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0126] When processor 401 executes a computer program stored in memory 402, it can specifically perform the following functions:

[0127] Based on virtual student data, the student simulation module uses a student simulation model to simulate the personality, behavior, and psychological state of the corresponding students, thereby obtaining simulation data.

[0128] Based on simulated data, the psychological analysis module uses a psychological analysis model to conduct in-depth analysis of the current psychological state and emotional change characteristics, thereby obtaining psychological features.

[0129] Based on psychological characteristics, the risk assessment module uses a risk assessment model to judge and handle potential psychological crises, and obtains corresponding psychological risk assessment results.

[0130] Based on the psychological risk assessment results, the intervention management module generates personalized intervention plans using the intervention management model. These personalized intervention plans are used to provide psychological counseling and support.

[0131] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the student psychological intervention program processing device based on multimodal model collaboration, the student psychological intervention system based on multimodal model collaboration, and their corresponding units described above can be found in the following references: Figure 2 The specific details of the student psychological intervention scheme based on multimodal model collaboration in the corresponding embodiments will not be repeated here.

[0132] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0133] Therefore, this application provides a computer-readable storage medium storing a plurality of instructions that can be loaded by a processor to execute the present application. Figure 2 The steps of the student psychological intervention program based on multimodal model collaboration in the corresponding embodiment can be found in the following examples. Figure 2 The description of the student psychological intervention scheme based on multimodal model collaboration in the corresponding embodiments will not be repeated here.

[0134] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0135] Because of the instructions stored in the computer-readable storage medium, the present application can be executed as described above. Figure 2 The steps of the student psychological intervention program based on multimodal model collaboration in the corresponding embodiment can therefore achieve the results of this application. Figure 2 The beneficial effects of the student psychological intervention scheme based on multimodal model collaboration in the corresponding embodiments are detailed in the preceding description and will not be repeated here.

[0136] The foregoing has provided a detailed description of the student psychological intervention scheme processing method, the student psychological intervention scheme processing device, the student psychological intervention system, and the computer-readable storage medium based on multimodal model collaboration provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A student psychological intervention program based on multimodal model collaboration, characterized in that, The method is applied to a student psychological intervention system, which includes a student simulation module, a psychological analysis module, a risk assessment module, and an intervention management module. The method includes: Based on virtual student data, the student simulation module uses a student simulation model to simulate the personality, behavior, and psychological state of the corresponding students, thereby obtaining simulation data. Based on the simulated data, the psychological analysis module uses a psychological analysis model to conduct in-depth analysis of the current psychological state and emotional change characteristics, thereby obtaining psychological characteristics. Based on the psychological characteristics, the risk assessment module uses a risk assessment model to judge and process potential psychological crises, and obtains corresponding psychological risk assessment results. Based on the psychological risk assessment results, the intervention management module generates a personalized intervention plan using the intervention management model, wherein the personalized intervention plan is used to provide psychological counseling and support.

2. The method according to claim 1, characterized in that, Student data x includes psychological assessment data x psych Academic performance data x academic Student behavior data x behavior Student social data x social Environmental factors x env And personalized intervention plans (P).

3. The method according to claim 2, characterized in that, Simulated data p sim These include predictions of language expression patterns (E), behavioral response simulations (B), emotional fluctuations (F), and potential psychological needs (N), and the following probabilistic relationships exist: p sim (E,B,F,N∣X)=p sim (E∣X)·p sim (B∣X,E)·p sim (F∣X,E,B)·p sim (N∣X,E,B,F)。 4. The method according to claim 3, characterized in that, The method further includes: Obtain students' authentic multimodal expression data (D) and historical mental health records (H); Psychological characteristics p psych It includes a multidimensional psychological feature map M, a prediction of psychological state change trends T, identification of key psychological needs K, and identification results of early signals of potential psychological problems W, and the following probabilistic relationships exist:

5. The method according to claim 4, characterized in that, Psychological risk assessment results p risk Including multi-dimensional risk score R and risk evolution path prediction E risk Key intervention time window T int Analysis of risk triggering factors and protective factors reveals the following probabilistic relationships:

6. The method according to claim 5, characterized in that, Personalized intervention plan p int The following probability relationship exists: Where, π i For the personalized intervention plan p int The i-th character in the text, π <i For the personalized intervention plan p int The i-1 characters preceding the i-th character mentioned above.

7. The method according to claim 5, characterized in that, The personalized intervention plan is the optimal intervention plan determined among different intervention plans, and the following definite relationship exists: S * =arg max P U(E,B,F,N), Among them, S * The optimal intervention plan is output, where U is the utility function and the subscript p represents the probability of all different intervention plans output by the intervention management module.

8. A student psychological intervention program processing device based on multimodal model collaboration, characterized in that, The device is applied to a student psychological intervention system, which includes a student simulation module, a psychological analysis module, a risk assessment module, and an intervention management module. The method includes: Based on virtual student data, the student simulation module uses a student simulation model to simulate the personality, behavior, and psychological state of the corresponding students, thereby obtaining simulation data. Based on the simulated data, the psychological analysis module uses a psychological analysis model to conduct in-depth analysis of the current psychological state and emotional change characteristics, thereby obtaining psychological characteristics. Based on the psychological characteristics, the risk assessment module uses a risk assessment model to judge and process potential psychological crises, and obtains corresponding psychological risk assessment results. Based on the psychological risk assessment results, the intervention management module generates a personalized intervention plan using the intervention management model, wherein the personalized intervention plan is used to provide psychological counseling and support.

9. A student psychological intervention system based on multimodal model collaboration, characterized in that, The method includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the method as described in any one of claims 1 to 7 when it invokes the computer program in the memory.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a plurality of instructions adapted for loading by a processor to perform the method of any one of claims 1 to 7.

Images