Gamification intelligent guiding method for hospitalized children and related device

Abstract

The invention discloses an in-hospital child gamification intelligent guiding method and a related device. The method comprises the following steps: collecting physiological index information of a child patient in real time through an intelligent bracelet; designing a personalized cognitive behavior therapy intervention scheme based on a psychological construction approach; in the cognitive reconstruction link, a Scotch bottom type question is adopted to guide the child patient to recognize and doubt negative automatic thinking and construct alternative thinking; the physiological index information is predicted through a multi-mode Warrens model, and the emotion titer and the activation degree of the child patient are obtained; dynamically adjusting the training content and duration of the intervention scheme according to the emotion titer and the activation degree; the improvement of treatment compliance is associated with the emotion titer, the activation degree and the sleep quality through a dynamic compliance and emotion feedback mapping model. Game elements are integrated into nursing activities based on known behavior therapy, an excitation theory and a lever principle psychology principle, and the participation degree and the treatment effect of patients are improved.

Description

Technical Field

[0001] The present invention relates to the fields of medical health and artificial intelligence technology, and particularly relates to a gamified intelligent guidance method and device for in-hospital children, and a computing device. Background Art

[0002] In-hospital children are prone to negative emotions such as anxiety and depression due to being in a strange medical environment for a long time, facing the pain of illness, treatment pressure, and separation from family and peers, which seriously affects the treatment effect and the rehabilitation process. Traditional psychological interventions for in-hospital children rely on the experience judgment of medical staff, making it difficult to accurately assess the emotional state and needs of children. Moreover, the degree of individuation is low, and it is difficult to make personalized adjustments according to the psychological characteristics, disease progression, and treatment stages of different children. In-hospital children have low interest in traditional intervention methods and low compliance, resulting in difficult-to-guarantee intervention effects.

[0003] To solve the above problems, the present invention proposes a gamified intelligent guidance method for in-hospital children, which integrates game elements into nursing activities based on cognitive behavioral therapy, motivation theory, and the psychological principle of the lever principle to improve the participation and treatment effect of patients. Summary of the Invention

[0004] In view of the above problems, the present invention provides a gamified intelligent guidance method and device for in-hospital children, and a computing device.

[0005] According to one aspect of the present invention, there is provided a gamified intelligent guidance method for in-hospital children, including:

[0006] Real-time collecting physiological index information of children through a smart bracelet, wherein the physiological index information includes heart rate, skin conductance, body temperature, activity level, and sleep quality;

[0007] Designing a personalized cognitive behavioral therapy intervention plan based on psychological construction approaches to relieve the anxiety and depression emotions of children; wherein the intervention plan includes a cognitive restructuring session, a behavioral activation session, and a problem-solving training session; the cognitive restructuring session uses Socratic questioning to guide children to identify and question negative automatic thoughts and construct alternative thoughts;

[0008] Predicting the physiological index information through a multimodal valence model to obtain the emotional valence and activation degree of children;

[0009] Dynamically adjusting the training content and duration of the intervention plan according to the emotional valence and activation degree;

[0010] Associate the improvement of treatment compliance with the emotional valence, activation level, and sleep quality through a dynamic compliance and emotional feedback mapping model; wherein, when the compliance of the child improves and the emotion is positive and the sleep quality is good, new game content is unlocked, otherwise the game difficulty is reduced or psychological support is provided.

[0011] In an alternative approach, the probability density function during the prediction of emotional valence and activation level by the multimodal valence model is:

[0012]

[0013] wherein; V is the emotional valence; A is the emotional activation level; Θ is the set of model parameters; C is the number of mixture components; π c is the mixing weight of the C-th component; N(.) is the probability density function of the Gaussian distribution; μ V,c and Σ V,c are respectively the mean vector and covariance matrix of the emotional valence V in the C-th component; μ A,c , ∑ A,c are respectively the mean vector and covariance matrix of the emotional activation level A in the C-th component.

[0014] In an alternative approach, the multimodal valence model estimates parameters through the expectation-maximization algorithm;

[0015] wherein, the posterior probability calculated in the E-step is:

[0016]

[0017] wherein, γ(z c,n ) is the posterior probability that the n-th data point belongs to the c-th mixture component; V n is the valence value of the n-th data point; A n is the activation level value of the n-th data point; π j is the mixing weight of the j-th mixture component; μ A,j and Σ A,j are respectively the mean and covariance matrix of the activation level in the j-th mixture component;

[0018] The parameter update formula in the M-step is:

[0019]

[0020] wherein, is the updated mean of the valence in the c-th mixture component; γ(z c,n ) is the posterior probability that the n-th data point belongs to the c-th mixture component.

[0021] In an alternative approach, the smart bracelet includes a multimodal sensor array;

[0022] Among them, the multimodal sensor array includes a medical-grade photoplethysmography sensor, a skin conductance sensor, a triaxial accelerometer, and an infrared body temperature sensor.

[0023] In an alternative approach, the method further includes:

[0024] In the cognitive restructuring session, intent recognition is achieved through a BERT-CNN hybrid model. When detecting that the child expresses negative thoughts, Socratic questions are automatically generated to guide the child to identify the types of cognitive distortions;

[0025] In the behavioral activation session, the daily activity target is converted into an energy value in the virtual world, which is used to unlock game scenarios or exchange virtual items;

[0026] In the problem-solving training session, a virtual scenario is presented by constructing a situation simulation engine, and the child provides real-time feedback based on the decision-making quality.

[0027] In an alternative approach, the BERT-CNN hybrid model includes:

[0028] A BERT layer for extracting context information in the child's speech or text expression and capturing the semantic features of negative thoughts;

[0029] A CNN layer for extracting negative words, emotion words, and exaggeration words from the output of the BERT layer;

[0030] A classification layer for mapping the feature representations extracted by the CNN layer to different types of cognitive distortions.

[0031] In an alternative approach, the method further includes:

[0032] Parents or guardians can view the child's physiological index data, emotional state, game progress, and treatment compliance in real time through a mobile application;

[0033] Parents or guardians share experiences and insights with the parents or guardians of other children, forming a mutually supportive community.

[0034] In an alternative approach, the dynamic adjustment of the intervention plan further includes:

[0035] Construct a comprehensive evaluation index for the child's state, which integrates emotional valence, activation level, compliance, and sleep quality;

[0036] When the comprehensive evaluation index < 0.4, reduce the game difficulty by 30% and push a 5-minute meditation guide;

[0037] When 0.4 ≤ the comprehensive evaluation index < 0.7, maintain the current difficulty but increase the frequency of immediate rewards;

[0038] When the comprehensive evaluation index ≥ 0.7, increase the difficulty by 15% and unlock the achievement system.

[0039] According to another aspect of the present invention, there is provided a gamified intelligent guidance device for hospitalized children, comprising:

[0040] A physiological index acquisition module, configured to collect the physiological index information of the child in real time through a smart bracelet, wherein the physiological index information includes heart rate, skin conductance, body temperature, activity level and sleep quality;

[0041] An intervention plan design module, configured to design a personalized cognitive behavioral therapy intervention plan based on psychological construction approaches to relieve the anxiety and depression emotions of the child; wherein, the intervention plan includes a cognitive restructuring session, a behavioral activation session and a problem-solving training session; the cognitive restructuring session uses Socratic questioning to guide the child to identify and question negative automatic thoughts and construct alternative thoughts;

[0042] An emotion prediction module, configured to predict the physiological index information through a multimodal Valence model to obtain the emotion valence and activation degree of the child;

[0043] An intervention plan adjustment module, configured to dynamically adjust the training content and duration of the intervention plan according to the emotion valence and activation degree;

[0044] A feedback mapping module, configured to associate the improvement of treatment compliance with the emotion valence, activation degree and the sleep quality through a dynamic compliance and emotion feedback mapping model; wherein, when the compliance of the child improves and the emotion is positive and the sleep quality is good, new game content is unlocked, otherwise the game difficulty is reduced or psychological support is provided.

[0045] According to still another aspect of the present invention, there is provided a computing device, comprising: a processor, a memory, a communication interface and a communication bus, and the processor, the memory and the communication interface complete communication with each other through the communication bus;

[0046] The memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the operations corresponding to the above-mentioned gamified intelligent guidance method for hospitalized children.

[0047] According to the solution provided by the present invention, physiological index information of children is collected in real time through a smart bracelet. Among them, the physiological index information includes heart rate, skin conductance, body temperature, activity level, and sleep quality. A personalized cognitive behavioral therapy intervention plan is designed based on psychological construction approaches to relieve the anxiety and depression of children. Among them, the intervention plan includes a cognitive restructuring session, a behavioral activation session, and a problem-solving training session. The cognitive restructuring session uses Socratic questioning to guide children to identify and question negative automatic thoughts and construct alternative thoughts. The physiological index information is predicted through a multimodal Valence model to obtain the emotional valence and activation degree of children. The training content and duration of the intervention plan are dynamically adjusted according to the emotional valence and activation degree. The improvement of treatment compliance is associated with the emotional valence, activation degree, and sleep quality through a dynamic compliance and emotional feedback mapping model. Among them, when the compliance of children improves and their emotions are positive and their sleep quality is good, new game content is unlocked; otherwise, the game difficulty is reduced or psychological support is provided. The present invention integrates game elements into nursing activities based on cognitive behavioral therapy, motivation theory, and the psychological principle of leverage, improving the participation and treatment effect of patients.

[0048] The above description is only an overview of the technical solution of the present invention. In order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present invention more obvious and understandable, the following specifically describes the embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0050] Figure 1 Shows a schematic flowchart of the gamified intelligent guidance method for hospitalized children according to an embodiment of the present invention;

[0051] Figure 2 Shows a schematic framework diagram of the gamified intelligent guidance device for hospitalized children according to an embodiment of the present invention;

[0052] Figure 3 Shows a schematic structural diagram of a computing device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present invention can be more thoroughly understood and the scope of the present invention can be completely conveyed to those skilled in the art.

[0054] Figure 1 The flowchart of the gamified intelligent guidance method for hospitalized children according to an embodiment of the present invention is shown. Specifically, as Figure 1 shown, it includes the following steps:

[0055] Step S101, real-time collect the physiological index information of the child through a smart bracelet, where the physiological index information includes heart rate, skin conductance, body temperature, activity level, and sleep quality.

[0056] In this embodiment, the smart bracelet is convenient to wear and easy to operate, and will not affect the normal activities of the child. It can collect a large amount of physiological data. For example, heart rate and skin conductance reflect the degree of emotional excitement, body temperature reflects the physical condition, activity level reflects the activity level, and sleep quality reflects the rest state.

[0057] In an alternative manner, the smart bracelet includes a multimodal sensor array;

[0058] wherein, the multimodal sensor array includes a medical-grade photoplethysmography sensor, a skin conductance sensor, a triaxial accelerometer, and an infrared body temperature sensor.

[0059] In this embodiment, the medical-grade PPG sensor is used to accurately measure the heart rate and heart rate variability (HRV). The skin conductance sensor is used to measure the skin conductance level, which reflects the activity of the sympathetic nervous system and is related to the degree of emotional arousal. The triaxial accelerometer is used to measure the activity level and judge the movement state of the child (sitting still, walking, running, etc.). The infrared body temperature sensor is used to measure the body temperature and monitor the physical condition of the child.

[0060] Step S102, design a personalized cognitive behavioral therapy intervention plan based on the psychological construction approach to relieve the anxiety and depression of the child; wherein, the intervention plan includes a cognitive restructuring session, a behavioral activation session, and a problem-solving training session; the cognitive restructuring session uses Socratic questioning to guide the child to identify and question negative automatic thoughts and construct alternative thoughts.

[0061] In this embodiment, through the multimodal Valence model and the dynamic compliance and emotion feedback mapping model, the emotion and compliance of the child can be monitored in real time, and the content and duration of the intervention plan can be dynamically adjusted to ensure the effectiveness and sustainability of the intervention.

[0062] For example, child patient Xiaoming feels anxious and depressed due to long-term hospitalization. Physiological index information such as Xiaoming's heart rate, skin conductance, body temperature, activity level, and sleep quality is collected in real time through a smart bracelet. In the cognitive restructuring session, when Xiaoming interacts with the system, he expresses his worries about the future and negative thoughts. The BERT-CNN hybrid model identifies these negative thoughts and generates Socratic questions: "Do you think the future will really be as bad as you imagine? Are there any other possibilities?" In the above way, Xiaoming gradually learns to identify and question his negative thoughts and constructs more positive alternative thoughts. In the behavioral activation session, the system converts Xiaoming's daily activity level goal into an energy value in the virtual world. By increasing his activity level and accumulating energy values, Xiaoming unlocks new game scenes and virtual items, increasing his sense of participation and accomplishment. In the problem-solving training session, a virtual scenario is presented through a scenario simulation engine to let Xiaoming practice his problem-solving ability. Xiaoming makes decisions in the virtual scenario, and the system provides real-time feedback based on the quality of his decisions to help him improve the decision-making process and enhance his problem-solving ability.

[0063] In an alternative approach, the BERT-CNN hybrid model includes:

[0064] A BERT layer for extracting context information from the speech or text expressions of the child patient and capturing the semantic features of negative thoughts;

[0065] A CNN layer for extracting negative words, emotion words, and exaggeration words from the output of the BERT layer;

[0066] A classification layer for mapping the feature representations extracted by the CNN layer to different types of cognitive distortions.

[0067] Step S103, predicting the emotional valence and arousal of the child patient through a multimodal valence model based on the physiological index information.

[0068] In this embodiment, the emotional valence and arousal are dynamically adjusted to provide a personalized cognitive-behavioral therapy intervention plan for each child patient.

[0069] In an alternative approach, the probability density function in the process of the multimodal valence model predicting the emotional valence and arousal is:

[0070]

[0071] where; V is the emotional valence; A is the emotional arousal; Θ is the set of model parameters; C is the number of mixture components; π c is the mixture weight of the C-th component; N(.) is the probability density function of the Gaussian distribution; μ V,c and ∑ V,c are the mean vector and covariance matrix of the emotional valence V in the C-th component, respectively; μA,c , ∑ A,c They are the mean vector and covariance matrix of the emotional activation degree A in the C-th component respectively.

[0072] In this embodiment, the emotional state of the child is comprehensively evaluated through two dimensions of emotional valence (V) and activation degree (A), considering the interaction and influence among different physiological indicators. The multimodal Valence model fits the complex emotional distribution. Since the emotional expression of children may be affected by various factors and presents the characteristic of multimodal distribution, the multimodal Valence model can capture these different emotional states.

[0073] In an alternative manner, the parameters of the multimodal Valence model are estimated by the Expectation-Maximization algorithm;

[0074] Among them, the posterior probability calculated in the E step is:

[0075]

[0076] Among them, γ(z c,n ) is the posterior probability that the n-th data point belongs to the c-th mixture component; V n is the valence value of the n-th data point; A n is the activation degree value of the n-th data point; π j is the mixing weight of the j-th mixture component; μ A,j and Σ A,j are the mean and covariance matrix of the activation degree in the j-th mixture component respectively;

[0077] The formula for updating parameters in the M step is:

[0078]

[0079] Among them, is the mean of the valence in the updated c-th mixture component; γ(z c,n ) is the posterior probability that the n-th data point belongs to the c-th mixture component.

[0080] In this embodiment, in the E step and M step of the Expectation-Maximization algorithm, the posterior probability and updated parameters are calculated respectively, enabling the model to dynamically adjust to adapt to the emotional changes of different children. By dynamically adjusting the model parameters in the E step and M step, the accuracy of emotional prediction and the personalization of the intervention plan are ensured. For example, if the emotional valence and activation degree of the child remain low, the model adjusts the parameters to provide a more suitable intervention plan, such as increasing meditation guidance or reducing the game difficulty.

[0081] Step S104, dynamically adjust the training content and duration of the intervention plan according to the emotional valence and activation degree.

[0082] In this embodiment, by adjusting the training content and duration, medical resources are utilized more effectively. For example, the training intensity is increased when the child is in a good mood; the training duration is reduced when the mood is low to avoid excessive stress.

[0083] In an alternative approach, the dynamically adjusted intervention plan further includes:

[0084] Construct a comprehensive evaluation index for the child's state, which integrates emotional valence, activation level, compliance, and sleep quality;

[0085] When the comprehensive evaluation index < 0.4, the game difficulty is reduced by 30% and a 5-minute meditation guidance is pushed;

[0086] When 0.4 ≤ the comprehensive evaluation index < 0.7, the current difficulty is maintained but the frequency of immediate rewards is increased;

[0087] When the comprehensive evaluation index ≥ 0.7, the difficulty is increased by 15% and the achievement system is unlocked.

[0088] In this embodiment, different intervention strategies (reducing difficulty, pushing meditation, increasing rewards, increasing difficulty, unlocking achievements) are adopted for different state ranges, improving the intervention effect and preventing the fatigue effect of a single strategy.

[0089] Step S105, associate the improvement of treatment compliance with the emotional valence, activation level, and sleep quality through a dynamic compliance and emotion feedback mapping model; wherein, when the child's compliance improves and the emotion is positive and the sleep quality is good, new game content is unlocked, otherwise the game difficulty is reduced or psychological support is provided.

[0090] In this embodiment, associating the emotional valence, activation level, and sleep quality with treatment compliance realizes the two-way regulation of emotion and behavior, promoting the overall rehabilitation of the child.

[0091] For example, the threshold settings for the child's compliance, emotional valence, activation level, and sleep quality are as follows:

[0092] Compliance improvement threshold: Compliance score ≥ 80

[0093] Positive emotional valence threshold: Emotional valence ≥ 0.7

[0094] Good sleep quality threshold: Sleep quality score ≥ 85

[0095] At a certain moment, the child's various indicators are as follows:

[0096] Compliance score: 85

[0097] Emotional valence: 0.8

[0098] Activation level: 0.75

[0099] Sleep quality score: 90

[0100] Due to the improved compliance, positive mood and good sleep quality of the child, new game content is unlocked. For example, new game levels or new game items are unlocked. If after a period of intervention, the various indicators of the child become:

[0101] Compliance score: 70

[0102] Emotional valence: 0.5

[0103] Activation degree: 0.4

[0104] Sleep quality score: 75

[0105] Since the compliance and emotional valence of the child do not reach the threshold, the game difficulty is reduced or psychological support is provided. For example, the requirement for the reaction speed of the game is reduced, more tips and help are added in the game, or a 5-minute meditation guidance audio is pushed.

[0106] In an alternative embodiment, the method further includes:

[0107] Parents or guardians can view the physiological index data, emotional state, game progress and treatment compliance of the child in real time through a mobile application;

[0108] Parents or guardians share experiences and insights with the parents or guardians of other children, forming a mutually supportive community.

[0109] In this embodiment, the real-time monitoring and participation of parents / guardians can actively participate in the treatment process of the child, enhance the cohesion and support of the family, and reduce the loneliness and anxiety of the child.

[0110] According to the solution provided by the present invention, physiological index information of children is collected in real time through a smart bracelet. Among them, the physiological index information includes heart rate, skin conductance, body temperature, activity level, and sleep quality. A personalized cognitive behavioral therapy intervention plan is designed based on psychological construction approaches to relieve the anxiety and depression of children. Among them, the intervention plan includes a cognitive restructuring session, a behavioral activation session, and a problem-solving training session. The cognitive restructuring session uses Socratic questioning to guide children to identify and question negative automatic thoughts and construct alternative thoughts. The physiological index information is predicted through a multimodal valence model to obtain the emotional valence and activation degree of children. The training content and duration of the intervention plan are dynamically adjusted according to the emotional valence and activation degree. The improvement of treatment compliance is associated with the emotional valence, activation degree, and sleep quality through a dynamic compliance and emotional feedback mapping model. Among them, when the compliance of children improves and their emotions are positive and their sleep quality is good, new game content is unlocked; otherwise, the game difficulty is reduced or psychological support is provided. The present invention integrates game elements into nursing activities based on cognitive behavioral therapy, incentive theory, and the psychological principle of leverage, improving the participation and treatment effect of patients.

[0111] Figure 2 The framework schematic diagram of the gamified intelligent guidance device for hospitalized children according to an embodiment of the present invention is shown. The gamified intelligent guidance device for hospitalized children includes:

[0112] A physiological index collection module 210, configured to collect the physiological index information of children in real time through a smart bracelet. Among them, the physiological index information includes heart rate, skin conductance, body temperature, activity level, and sleep quality;

[0113] An intervention plan design module 220, configured to design a personalized cognitive behavioral therapy intervention plan based on psychological construction approaches to relieve the anxiety and depression of children. Among them, the intervention plan includes a cognitive restructuring session, a behavioral activation session, and a problem-solving training session. The cognitive restructuring session uses Socratic questioning to guide children to identify and question negative automatic thoughts and construct alternative thoughts;

[0114] An emotion prediction module 230, configured to predict the physiological index information through a multimodal valence model to obtain the emotional valence and activation degree of children;

[0115] An intervention plan adjustment module 240, configured to dynamically adjust the training content and duration of the intervention plan according to the emotional valence and activation degree;

[0116] A feedback mapping module 250 is configured to associate the improvement of treatment compliance with the emotional valence, arousal, and the sleep quality through a dynamic compliance and emotional feedback mapping model. When the compliance of the child patient improves, and the emotion is positive and the sleep quality is good, new game content is unlocked; otherwise, the game difficulty is reduced or psychological support is provided.

[0117] Figure 3 FIG. shows a schematic structural diagram of an embodiment of the computing device of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the computing device.

[0118] As Figure 3 shown, the computing device may include: a processor 302, a communications interface 304, a memory 306, and a communication bus 308.

[0119] Among them: The processor 302, the communications interface 304, and the memory 306 communicate with each other through the communication bus 308. The communications interface 304 is used to communicate with network elements of other devices such as clients or other servers. The processor 302 is configured to execute a program 310, and specifically may execute relevant steps in the embodiment of the above-mentioned gamification intelligent guidance method for hospitalized children.

[0120] Specifically, the program 310 may include program code, and the program code includes computer operation instructions.

[0121] The processor 302 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present invention. One or more processors included in the computing device may be of the same type of processor, such as one or more CPUs; or may be different types of processors, such as one or more CPUs and one or more ASICs.

[0122] The memory 306 is used to store the program 310. The memory 306 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

[0123] According to the solution provided by the present invention, physiological index information of children is collected in real time through a smart bracelet, wherein the physiological index information includes heart rate, skin conductance, body temperature, activity level, and sleep quality; a personalized cognitive behavioral therapy intervention plan is designed based on psychological construction approaches to relieve the anxiety and depression emotions of children; wherein, the intervention plan includes a cognitive restructuring session, a behavioral activation session, and a problem-solving training session; the cognitive restructuring session uses Socratic questioning to guide children to identify and question negative automatic thoughts and construct alternative thoughts; the physiological index information is predicted through a multimodal Valence model to obtain the emotional valence and activation degree of children; the training content and duration of the intervention plan are dynamically adjusted according to the emotional valence and activation degree; the improvement of treatment compliance is associated with the emotional valence, activation degree, and the sleep quality through a dynamic compliance and emotional feedback mapping model; wherein, when the compliance of children improves and their emotions are positive and the sleep quality is good, new game content is unlocked, otherwise the game difficulty is reduced or psychological support is provided. The present invention integrates game elements into nursing activities based on cognitive behavioral therapy, motivation theory, and the psychological principle of leverage, improving the participation and treatment effect of patients.

[0124] Those skilled in the art can understand that the modules in the devices in the embodiments can be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all the features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise explicitly stated, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) can be replaced by an alternative feature that provides the same, equivalent, or similar purpose. In addition, those skilled in the art can understand that although some of the embodiments herein include certain features included in other embodiments but not other features, the combination of the features of different embodiments means that it is within the scope of the present invention and forms different embodiments. For example, in the following claims, any one of the claimed embodiments can be used in any combination. The present invention can be implemented by means of hardware including several different elements and by means of a properly programmed computer. In the unit claims listing several devices, several of these devices can be specifically embodied by the same hardware item. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the execution order.

Claims

1. Collect the physiological index information of children in real time through an intelligent bracelet, where, The physiological index information includes heart rate, skin conductance, body temperature, activity level, and sleep quality; Design a personalized cognitive behavioral therapy intervention program based on psychological construction approaches to relieve the anxiety and depressive emotions of children; wherein, the intervention program includes a cognitive restructuring session, a behavioral activation session, and a problem-solving training session; the cognitive restructuring session uses Socratic questioning to guide children to identify and question negative automatic thoughts and construct alternative thoughts; Predict the physiological index information through a multimodal Valence model to obtain the emotional valence and arousal level of the child; Dynamically adjust the training content and duration of the intervention program according to the emotional valence and arousal level; Associate the improvement of treatment compliance with the emotional valence, arousal level, and sleep quality through a dynamic compliance and emotional feedback mapping model; wherein, when the child's compliance improves and the emotion is positive and the sleep quality is good, new game content is unlocked, otherwise the game difficulty is reduced or psychological support is provided.

2. The gamification intelligent guidance method for hospitalized children according to claim 1, wherein The probability density function in the process of the multimodal Valence model predicting the emotional valence and arousal level is: Among them, V is the emotional valence; A is the emotional arousal; Θ is the set of model parameters; C is the number of mixture components; π c is the mixing weight of the C-th component; N(.) is the probability density function of the Gaussian distribution; μ V,c and Σ V,c are respectively the mean vector and covariance matrix of the emotional valence V in the C-th component; μ A,c ,∑ A,c are respectively the mean vector and covariance matrix of the emotional arousal A in the C-th component.

3. The gamified intelligent guidance method for hospitalized children according to claim 2, wherein, The multimodal Valence model performs parameter estimation through the expectation maximization algorithm; Among them, the posterior probability calculated in the E step is: where, γ(z c,n ) is the posterior probability that the n-th data point belongs to the c-th mixture component; V n is the valence value of the n-th data point; A n is the activation value of the n-th data point; π j is the mixing weight of the j-th mixture component; μ A,j and Σ A,j are respectively the mean and covariance matrix of the activation degree in the j-th mixture component; The formula for updating parameters in the M step is: wherein, is the mean titer in the updated c-th mixture component; γ(z c,n ) is the posterior probability that the n-th data point belongs to the c-th mixture component.

4. The gamification intelligent guidance method for hospitalized children according to claim 1, wherein, The smart bracelet includes a multimodal sensor array; Among them, the multimodal sensor array includes a medical-grade photoplethysmography sensor, a skin conductance sensor, a three-axis accelerometer, and an infrared body temperature sensor.

5. The gamification intelligent guidance method for in-hospital children according to claim 1, characterized in that, The method further includes: In the cognitive restructuring session, intention recognition is realized through a BERT-CNN hybrid model. When it is detected that the child expresses negative thoughts, Socratic questions are automatically generated to guide the child to identify the type of cognitive distortion; In the behavioral activation session, the daily activity level target is converted into an energy value in the virtual world, which is used to unlock game scenes or exchange virtual items; In the problem-solving training session, a virtual scene is presented by constructing a scenario simulation engine, and the child provides real-time feedback according to the decision-making quality.

6. The gamification intelligent guidance method for hospitalized children according to claim 5, wherein, The BERT-CNN hybrid model includes: A BERT layer for extracting context information in the child's speech or text expression and capturing the semantic features of negative thoughts; A CNN layer for extracting negative words, emotion words, and exaggeration words from the output of the BERT layer; A classification layer for mapping the feature representations extracted by the CNN layer to different types of cognitive distortions.

7. The gamification intelligent guidance method for hospitalized children according to claim 1, wherein The method further includes: Parents or guardians can view the child's physiological index data, emotional state, game progress, and treatment compliance in real time through a mobile application; Parents or guardians share experiences and insights with the parents or guardians of other children to form a mutually supportive community.

8. The gamified intelligent guidance method for hospitalized children according to claim 1, wherein The dynamic adjustment of the intervention program further includes: Construct a comprehensive evaluation index of the child's state, which integrates emotional valence, arousal level, compliance, and sleep quality; When the comprehensive evaluation index < 0.4, reduce the game difficulty by 30% and push a 5-minute meditation guide; When 0.4 ≤ the comprehensive evaluation index < 0.7, maintain the current difficulty but increase the frequency of immediate rewards; When the comprehensive evaluation index ≥ 0.7, increase the difficulty by 15% and unlock the achievement system.

9. A gamification intelligent guidance device for hospitalized children, characterized in that, Include: A physiological index collection module, which is used to collect the physiological index information of children in real time through a smart bracelet. Among them, the physiological index information includes heart rate, skin conductance, body temperature, activity level, and sleep quality; An intervention plan design module, which is used to design a personalized cognitive behavioral therapy intervention plan based on psychological construction approaches to relieve the anxiety and depression of children. Among them, the intervention plan includes a cognitive restructuring session, a behavioral activation session, and a problem-solving training session. The cognitive restructuring session uses Socratic questioning to guide children to identify and question negative automatic thoughts and construct alternative thoughts; An emotion prediction module, which is used to predict the physiological index information through a multimodal Valence model to obtain the emotion valence and activation degree of children; An intervention plan adjustment module, which is used to dynamically adjust the training content and duration of the intervention plan according to the emotion valence and activation degree; A feedback mapping module, which is used to associate the improvement of treatment compliance with the emotion valence, activation degree, and sleep quality through a dynamic compliance and emotion feedback mapping model. Among them, when the child's compliance improves and the emotion is positive and the sleep quality is good, new game content is unlocked; otherwise, the game difficulty is reduced or psychological support is provided.

10. A computing device, comprising: A processor, a memory, a communication interface, and a communication bus. The processor, the memory, and the communication interface complete communication with each other through the communication bus; The memory is used to store at least one executable instruction, and the executable instruction causes the processor to execute the operations corresponding to the above-mentioned game-based intelligent guidance method for hospitalized children.

Images