Respiratory training game device for assisting airway clearance of critically ill patient

Abstract

The invention discloses a respiratory training game device for assisting in clearance of the airway of a critically ill patient, and relates to the related field of respiratory training, and the respiratory training game device comprises an embedded sensing module which is used for collecting respiratory data of a user and establishing a respiratory data set; and the joint sensing module is used for acquiring basic data of the user under the authorization of the user. And the plan construction module is used for performing feature extraction and fusion on the respiration data set and the basic data and then constructing a respiration training plan. And the dynamic feedback module is used for acquiring breathing data of the user through the sensing device after the user performs training based on the breathing training plan, generating dynamic feedback based on the breathing data and a mapping threshold value of the breathing training plan and performing user training management according to the dynamic feedback, and the dynamic feedback comprises excitation feedback and adjustment feedback. The technical problems that in the prior art, breathing training equipment cannot achieve comprehensive and personalized data collection and analysis on users, so that the training effect difference is large, and the user compliance is insufficient are solved.

Description

Technical Field

[0001] The present application relates to the field of respiratory training, and in particular to a respiratory training game device for assisting in airway clearance of critically ill patients. Background Art

[0002] With the continuous development of respiratory training technology, respiratory training equipment has been widely used to improve patients' respiratory function. Existing respiratory training systems usually monitor users' basic respiratory data, such as flow, pressure, etc., through simple equipment, and provide users with corresponding training guidance. However, such traditional equipment usually lacks customized training plans for individual users, and cannot effectively combine patients' basic data such as medical history, psychological state, etc. and external environmental factors such as training scenarios and user interests to optimize training.

[0003] Therefore, in the prior art, breathing training equipment cannot achieve comprehensive and personalized data collection and analysis of users, and lacks flexible training goal adjustment and user incentive mechanisms, resulting in large differences in training effects and technical problems such as insufficient user compliance. Summary of the invention

[0004] This application provides a breathing training game device for assisting critically ill patients in airway clearance, solving the technical problems that breathing training equipment in the prior art cannot achieve comprehensive and personalized data collection and analysis of users, and lacks flexible training goal adjustment and user incentive mechanisms, resulting in large differences in training effects and insufficient user compliance. It improves the training effect and compliance of users, and can dynamically adjust goals and incentives according to the training progress of users, providing personalized and efficient training management.

[0005] The present application provides a breathing training game device for assisting critically ill patients in airway clearance, the device comprising: an embedded sensing module, for collecting breathing data of a user and establishing a breathing data set, the embedded sensing module comprising a flow sensor, a pressure sensor, and a biological collection sensor; a joint sensing module, for obtaining basic data of the user under the user's authorization, the basic data comprising medical record data, psychological characteristic data, training compliance data, and scene adaptation data; a plan construction module, for extracting and fusing features of the breathing data set and the basic data, and then constructing a breathing training plan according to the feature extraction and fusion results, the breathing training plan comprising an initial goal and an advanced goal, the breathing training plan being configured with a game scene and user incentives; a dynamic feedback module, for obtaining the user's breathing data through a sensing device after the user has trained based on the breathing training plan, generating dynamic feedback based on a mapping threshold of the breathing data and the breathing training plan, and performing user training management according to the dynamic feedback, the dynamic feedback comprising incentive feedback and adjustment feedback.

[0006] In a possible implementation, the plan construction module is also used to establish a first feature extraction result by extracting the time domain features, frequency domain features and dynamic features of the preprocessing results after preprocessing the respiratory data set; extract medical record data features, psychological features, and scene adaptation features from the basic data to establish a second feature extraction result; perform feature joint analysis on the first feature extraction result and the second feature extraction result, and perform feature fusion based on the feature joint analysis results.

[0007] In a possible implementation, the plan construction module is also used to obtain training target-related features in the feature extraction and fusion results, input the training target-related features into the plan construction channel, set the flow target, pressure target, duration target based on the plan construction channel, configure the advanced coefficient, and set the initial target and advanced target according to the flow target, pressure target, duration target and advanced coefficient; obtain scene-related features in the feature extraction and fusion results, use the scene-related features as matching data, perform scene matching in the scene database, and establish a game scene; obtain incentive-related features in the feature extraction and fusion results, perform incentive matching based on the incentive-related features and the initial target and advanced target, and establish user incentives, wherein the user incentives include incentive content and mapping thresholds; and construct a breathing training plan according to the initial target, advanced target game scene, and user incentives.

[0008] In a possible implementation, the dynamic feedback module is also used to perform trigger analysis on the respiratory data with the mapping threshold to establish a trigger analysis result; perform user incentive trigger frequency extraction on the trigger analysis result, perform incentive attention feedback analysis based on the user incentive trigger frequency extraction result, establish incentive feedback, and use the incentive feedback as dynamic feedback for user training management.

[0009] In a possible implementation, the dynamic feedback module is also used to identify trigger weaknesses based on the trigger analysis results and establish training weaknesses for the user; construct special training based on the training weaknesses and feature extraction fusion results, use the special training as adjustment feedback, and add the adjustment feedback to the dynamic feedback for user training management.

[0010] In a possible implementation, the dynamic feedback module is further used to perform an incentive trigger call according to the trigger analysis result, and establish an incentive trigger call result, wherein the incentive trigger call result includes a point incentive, an audio incentive, and a video incentive;

[0011] The incentive trigger call result is added to the incentive feedback to perform real-time training response for the user.

[0012] In a possible implementation, the device also includes: an early warning module, which is used to perform a joint analysis of respiratory data in combination with real-time physiological characteristic data, establish a joint early warning recognition result, match early warning levels according to the joint early warning recognition result, and issue a pre-alarm based on the early warning level matching result.

[0013] In a possible implementation, the device also includes: a self-optimization module, which is used to match and identify breathing data and breathing training plans, establish matching identification results, focus on self-optimization based on the matching identification results, generate optimization coefficients of advanced coefficients based on the self-optimization results, optimize the advanced coefficients with the optimization coefficients, reconstruct the advanced goals, and manage the user's training according to the reconstructed advanced goals.

[0014] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0015] The present application provides a breathing training game device for assisting the airway clearance of critically ill patients. The device is used to collect breathing data of users and establish a breathing data set through an embedded sensing module, wherein the embedded sensing module includes a flow sensor, a pressure sensor, and a biological collection sensor; a joint sensing module is used to obtain basic data of users under user authorization, wherein the basic data includes medical record data, psychological characteristic data, training compliance data, and scene adaptation data; a plan construction module is used to extract and fuse the breathing data set and basic data, and then construct a breathing training plan according to the feature extraction and fusion results, wherein the breathing training plan includes an initial goal and an advanced goal, and the breathing training plan is configured with a game scene and user incentives; a dynamic feedback module is used to obtain the breathing data of users through a sensing device after the user performs training based on the breathing training plan, generate dynamic feedback based on the mapping threshold of the breathing data and the breathing training plan, and manage user training according to the dynamic feedback, wherein the dynamic feedback includes incentive feedback and adjustment feedback. The present application solves the technical problems that the breathing training equipment in the prior art cannot realize comprehensive and personalized data collection and analysis of users, and lacks flexible training goal adjustment and user incentive mechanisms, resulting in large differences in training effects and insufficient user compliance. It improves the user's training effect and compliance, and can dynamically adjust goals and incentives according to the user's training progress, providing personalized and efficient training management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the device according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0017] Figure 1 A schematic diagram of the structure of a breathing training game device for assisting airway clearance in critically ill patients provided in an embodiment of the present application;

[0018] Figure 2 A schematic diagram of the flow of constructing a breathing training plan by a plan construction module in a breathing training game device for assisting airway clearance in critically ill patients in the present application.

[0019] Explanation of the reference numerals: embedded perception module 11, joint perception module 12, plan construction module 13, dynamic feedback module 14. DETAILED DESCRIPTION

[0020] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0021] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0022] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, devices, products, or equipment. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0023] The present application embodiment provides a breathing training game device for assisting critically ill patients in airway clearance, such as Figure 1 As shown, the device comprises:

[0024] An embedded sensing module 11 is used to collect respiratory data of the user and establish a respiratory data set. The embedded sensing module 11 includes a flow sensor, a pressure sensor, and a biological collection sensor;

[0025] The joint perception module 12 is used to obtain the basic data of the user under the authorization of the user, and the basic data includes medical record data, psychological characteristic data, training compliance data, and scene adaptation data;

[0026] Through the flow sensor, pressure sensor, and biological collection sensor embedded in the perception module 11, the user's breathing data is collected to establish a breathing data set. Among them, the flow sensor is used to measure the gas flow inhaled and exhaled by the patient during breathing. The pressure sensor is used to measure the pressure change in the airway when the patient breathes. The biological collection sensor includes a heart rate sensor, a blood oxygen saturation sensor, etc., which are used to collect the patient's physiological characteristic data. Subsequently, through the joint perception module 12, under the user's authorization, the user's basic data is obtained, and the basic data includes medical record data, psychological characteristic data, training compliance data, and scene adaptation data. Among them, the medical record data is the patient's medical history, diagnosis information, treatment plan, etc. The psychological characteristic data is the patient's psychological state assessment, such as anxiety level, depression level, etc. Training compliance data: the patient's past completion of the training plan and attitude. The scene adaptation data is the patient's hobbies, favorite colors, age, and gender information, which is used for subsequent customization of the game scene.

[0027] A plan construction module 13 is used to extract and fuse the features of the respiratory data set and the basic data, and then construct a respiratory training plan according to the feature extraction and fusion results, wherein the respiratory training plan includes an initial goal and an advanced goal, and the respiratory training plan is configured with a game scene and a user incentive;

[0028] The dynamic feedback module 14 is used to obtain the user's breathing data through the sensing device after the user has trained based on the breathing training plan, generate dynamic feedback based on the mapping threshold of the breathing data and the breathing training plan, and manage the user's training according to the dynamic feedback, wherein the dynamic feedback includes motivational feedback and adjustment feedback.

[0029] The breathing data set and basic data are feature extracted by the plan construction module 13, and after the features are fused, a breathing training plan is constructed according to the feature extraction and fusion results. The breathing training plan includes an initial goal and an advanced goal, and the breathing training plan is configured with a game scene and a user incentive, wherein the user incentive is a reward for the user in terms of emotions and the like after the user reaches the goal, so as to improve the user's training enthusiasm. Finally, through the dynamic feedback module 14, after the user performs training based on the breathing training plan, the user's breathing data is obtained through the sensing device, and the breathing data includes training time, gas flow, and pressure in the airway. Dynamic feedback is generated based on the mapping threshold of the breathing data and the breathing training plan, and the dynamic feedback is feedback data generated by the system according to the actual breathing data of the user combined with the mapping threshold. Finally, user training management is performed according to the dynamic feedback, and the dynamic feedback includes incentive feedback and adjustment feedback.

[0030] The device also includes: an early warning module, which is used to perform a joint analysis of the respiratory data in combination with the real-time physiological characteristic data, obtain the matching results of the respiratory data and the real-time physiological characteristic data in the early warning database, and establish a joint early warning recognition result. Among them, the early warning database stores various categories that need to be warned, as well as the corresponding respiratory data and real-time physiological characteristic data. The joint early warning recognition result includes the judgment result of whether an early warning is needed and the specific early warning category. When the corresponding early warning data is matched in the early warning database, the early warning level is matched according to the joint early warning recognition result. Different early warning categories correspond to different early warning levels, and early warning is issued based on the early warning level matching result.

[0031] The device also includes: a self-optimization module, which is used to match and identify the breathing data and the breathing training plan, obtain the completion degree of the breathing data and the corresponding breathing training plan, obtain the target in which the ratio of the breathing data to the corresponding breathing training plan is greater than 1, and establish a matching recognition result. When the ratio is greater than 1, the breathing data has exceeded the corresponding training target, so it is necessary to adjust the training target to meet the training needs of the user. Focus on self-optimization according to the matching recognition result, focus on the self-optimization result contains a specific optimization target and the breathing data and the corresponding breathing training plan, based on the self-optimization result, obtain the ratio of the breathing data to the corresponding breathing training plan to generate the optimization coefficient of the advanced coefficient, obtain the product of the optimization coefficient and the advanced coefficient to complete the optimization of the advanced coefficient, based on the optimized advanced coefficient, reconstruct the advanced target, perform user training management according to the reconstructed advanced target, and obtain the corresponding training plan. The invention solves the technical problems that the breathing training equipment in the prior art cannot realize comprehensive and personalized data collection and analysis of users, and lacks flexible training target adjustment and user incentive mechanism, resulting in large differences in training effects and insufficient user compliance. It improves the user's training effect and compliance, and can dynamically adjust goals and incentives according to the user's training progress, providing personalized and efficient training management.

[0032] Furthermore, the plan construction module 13 is also used to: after preprocessing the respiratory data set, establish a first feature extraction result by extracting the time domain features, frequency domain features and dynamic features of the preprocessing results; extract medical record data features, psychological features, and scene adaptation features from the basic data to establish a second feature extraction result; perform feature joint analysis on the first feature extraction result and the second feature extraction result, and perform feature fusion based on the feature joint analysis results.

[0033] The feature extraction and fusion of the respiratory data set and the basic data also includes: preprocessing the respiratory data set, eliminating data with obvious abnormalities and performing data standardization, such as abnormal data with gas flow far exceeding the limit range of the human body. After the preprocessing is completed, the time domain features, frequency domain features and dynamic features of the preprocessing results are extracted, wherein the time domain features are statistical features directly extracted from the time series data, such as the average respiratory frequency, peak flow during breathing, respiratory cycle, etc. The frequency domain features are methods such as Fourier transform of the time series data to analyze the frequency components of the signal, such as obtaining the main frequency components, i.e., the dominant frequency in the respiratory signal. Dynamic features are features that describe the changes of the signal over time, such as trends, fluctuations, etc., such as evaluating the rising or falling trends of the respiratory frequency and depth. The rate of change of the respiratory parameters is calculated, and abnormal fluctuations are identified, thereby completing the establishment of the first feature extraction result.

[0034] Furthermore, the basic data is subjected to medical record data features, psychological features, and scene adaptation features extraction to establish a second feature extraction result, wherein the second feature extraction result includes the diagnostic data obtained from the medical record and the corresponding stage of the disease, and the features extracted from the psychological feature data that reflect the patient's psychological state, such as emotions, motivation levels, etc. The scene adaptation features include user interests and hobbies, i.e., favorite themes, colors, music types, cognitive abilities, i.e., the ability to understand and operate complex games, and user information, such as age, gender, etc. Finally, the first feature extraction results and the second feature extraction results are subjected to feature joint analysis to obtain the corresponding relationship between the first feature extraction results and the second feature extraction results, and obtain feature joint analysis results. Finally, feature fusion is performed based on the feature joint analysis results, so that each feature is fused into a set of feature data.

[0035] Further, such as Figure 2 As shown, the plan construction module 13 is also used to: obtain training target-related features in the feature extraction and fusion results, input the training target-related features into the plan construction channel, set the flow target, pressure target, and duration target based on the plan construction channel, and configure the advanced coefficient, and set the initial target and the advanced target according to the flow target, pressure target, duration target and the advanced coefficient; obtain the scene-related features in the feature extraction and fusion results, use the scene-related features as matching data, perform scene matching in the scene database, and establish a game scene; obtain the incentive-related features in the feature extraction and fusion results, perform incentive matching based on the incentive-related features and the initial target and the advanced target, and establish user incentives, wherein the user incentives include incentive content and mapping thresholds; and construct a breathing training plan according to the initial target, advanced target game scene, and user incentives.

[0036] The method of constructing a breathing training plan according to the feature extraction and fusion results also includes: obtaining training target associated features in the feature extraction and fusion results, wherein the training target associated features are preset associated features, including respiratory performance features and medical history features. The training target associated features are input into the plan construction channel, and the flow target, i.e., the gas flow target, the pressure target, i.e., the airway pressure target, and the duration target, i.e., the training duration target, are set based on the plan construction channel. These targets are specific quantitative standards for breathing training and can be preset according to the actual situation of the user. The advanced coefficient is configured, and the initial target and the advanced target are set according to the flow target, the pressure target, the duration target and the advanced coefficient. The advanced coefficient is a preset proportional parameter, such as 1.2 times the current target. When the flow, pressure, and duration detected during the actual training of the user are multiplied by the advanced coefficient to reach the set target, the training of the advanced target is entered.

[0037] Obtain scene-related features in the feature extraction and fusion results, where the scene-related features are features associated with the user's scene selection, such as age, gender, psychological characteristics, etc. Subsequently, the scene-related features are used as matching data to perform scene matching in the scene database to obtain the game scene corresponding to the scene-related features. Record the scene-related features and the corresponding game scene selection objects in the scene database. For example, for a patient with great psychological pressure, the game scene may select a virtual relaxation scene, such as breathing training in a quiet forest, to help the user relieve psychological pressure. Another example is children's games such as blowing balloons and breathing to the rhythm of music.

[0038] The incentive-related features in the feature extraction and fusion results are obtained, wherein the incentive-related features are features associated with the user's incentive selection, such as age, etc. Incentive matching is performed based on the incentive-related features and the initial goal and the advanced goal, and the user incentive is established according to the incentive-related features, wherein the user incentive includes incentive content and mapping threshold. Whenever a user reaches a goal, a user incentive is established according to the incentive-related features, wherein the user incentive includes incentive content, i.e., content displayed during the incentive process, such as audio or video of encouragement or cheering from family members recorded in advance. When the patient reaches the game goal, the game device automatically pops up and plays the audio or video of the family members to enhance the patient's confidence. The mapping threshold is a preset threshold for the user to trigger incentives or dynamically adjust the goal, such as a mapping threshold of 60% of the goal, and the user is motivated when this threshold is exceeded. In order to achieve the goal of encouraging users to complete the training goals, thereby ensuring the training effect. Finally, a breathing training plan is constructed according to the initial goal, advanced goal game scene, and user incentive.

[0039] Furthermore, the dynamic feedback module 14 is also used to: perform trigger analysis on the respiratory data with the mapping threshold to establish a trigger analysis result; perform user incentive trigger frequency extraction on the trigger analysis result, perform incentive attention feedback analysis based on the user incentive trigger frequency extraction result, establish incentive feedback, and use the incentive feedback as dynamic feedback for user training management.

[0040] The mapping threshold based on the breathing data and the breathing training plan generates dynamic feedback, and the user training management is performed according to the dynamic feedback, and also includes: triggering analysis of the breathing data with the mapping threshold, judging whether the user's breathing data is greater than or equal to the mapping threshold, and establishing a trigger analysis result according to the judgment result. When it is greater than or equal to the mapping threshold, the user's training effect is better, otherwise the training effect is not good. Wherein, the trigger analysis result contains a trigger object and a trigger frequency. Further, the user incentive trigger frequency of the trigger analysis result is extracted, and an incentive attention feedback analysis is performed based on the user incentive trigger frequency extraction result, and an incentive feedback is established, and the incentive feedback is used as dynamic feedback for user training management. The incentive feedback is an incentive trigger instruction generated when the user triggers the incentive, which is used to instruct the system to display subsequent incentives. Wherein, the incentive attention feedback analysis is to obtain the items in which the training is weak according to the trigger frequency.

[0041] Furthermore, the dynamic feedback module 14 is also used to: use the trigger analysis results to identify trigger weaknesses and establish user training weaknesses; construct special training based on training weaknesses and feature extraction fusion results, use the special training as adjustment feedback, and add the adjustment feedback to the dynamic feedback to manage user training.

[0042] After establishing the trigger analysis result, it also includes: using the trigger analysis result to identify trigger weaknesses, identifying and obtaining trigger objects in which the trigger efficiency is much lower than the average trigger frequency, and establishing the user's training weaknesses according to the trigger objects. Special training is constructed based on the training weaknesses and the feature extraction fusion results. When conducting the weaknesses, the target difficulty of the weaknesses can be appropriately increased to achieve special training for the weaknesses. Finally, the special training is used as adjustment feedback, and the adjustment feedback is added to the dynamic feedback, so that the user can perform subsequent training management according to the adjustment feedback.

[0043] Furthermore, the dynamic feedback module 14 is also used to: perform an incentive trigger call according to the trigger analysis result, establish an incentive trigger call result, and the incentive trigger call result includes point incentive, audio incentive, and video incentive; add the incentive trigger call result to the incentive feedback for real-time user training response.

[0044] The establishment of incentive feedback also includes: when the user triggers the incentive, the incentive trigger call is performed according to the trigger analysis result, and the incentive trigger call result is established. The incentive trigger call result includes point incentive, audio incentive, and video incentive. The incentive trigger call result is added to the incentive feedback for the user's real-time training response, so that the system can display the incentive.

[0045] The embodiment of the present application uses an embedded perception module to collect the user's respiratory data and establish a respiratory data set, and the embedded perception module includes a flow sensor, a pressure sensor, and a biological collection sensor; a joint perception module is used to obtain the user's basic data under the user's authorization, and the basic data includes medical record data, psychological characteristic data, training compliance data, and scene adaptation data; a plan construction module is used to extract and fuse the respiratory data set and basic data, and then construct a respiratory training plan according to the feature extraction fusion result, and the respiratory training plan includes an initial goal and an advanced goal, and the respiratory training plan is configured with a game scene and user incentives; a dynamic feedback module is used to obtain the user's respiratory data through a sensing device after the user trains based on the respiratory training plan, generate dynamic feedback based on the mapping threshold of the respiratory data and the respiratory training plan, and manage the user training according to the dynamic feedback, and the dynamic feedback includes incentive feedback and adjustment feedback. The technical problem that the respiratory training equipment in the prior art cannot realize comprehensive and personalized data collection and analysis of users, and lacks flexible training target adjustment and user incentive mechanism, resulting in large differences in training effects and insufficient user compliance is solved. It improves the user's training effect and compliance, and can dynamically adjust goals and incentives according to the user's training progress, providing personalized and efficient training management.

[0046] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A breathing training game device for assisting critically ill patients in airway clearance, characterized in that: The device comprises: An embedded sensing module is used to collect respiratory data of the user and establish a respiratory data set. The embedded sensing module includes a flow sensor, a pressure sensor, and a biological collection sensor; A joint perception module is used to obtain the user's basic data under the user's authorization, and the basic data includes medical record data, psychological characteristic data, training compliance data, and scene adaptation data; A plan building module is used to extract and fuse the features of the respiratory data set and the basic data, and then build a respiratory training plan according to the feature extraction and fusion results, wherein the respiratory training plan includes an initial goal and an advanced goal, and the respiratory training plan is configured with a game scenario and user incentives; The dynamic feedback module is used to obtain the user's breathing data through a sensing device after the user has trained based on the breathing training plan, generate dynamic feedback based on the mapping threshold of the breathing data and the breathing training plan, and manage the user's training based on the dynamic feedback, and the dynamic feedback includes motivational feedback and adjustment feedback.

2. A breathing training game device for assisting airway clearance in critically ill patients as claimed in claim 1, characterized in that: The feature extraction and fusion of the respiratory data set and the basic data also includes: After preprocessing the respiratory data set, a first feature extraction result is established by extracting time domain features, frequency domain features, and dynamic features of the preprocessing result; Extract medical record data features, psychological features, and scene adaptation features from the basic data, and establish the second feature extraction result; Performing feature joint analysis on the first feature extraction result and the second feature extraction result, and performing feature fusion based on the feature joint analysis result.

3. A breathing training game device for assisting airway clearance in critically ill patients as claimed in claim 2, characterized in that: The step of constructing a breathing training plan based on the feature extraction and fusion results also includes: Acquire training target associated features in the feature extraction and fusion results, input the training target associated features into the plan construction channel, set the flow target, pressure target, and duration target based on the plan construction channel, configure the advanced coefficient, and set the initial target and advanced target according to the flow target, pressure target, duration target, and advanced coefficient; Acquire scene-related features in the feature extraction and fusion results, use the scene-related features as matching data, perform scene matching in the scene database, and establish a game scene; Acquire incentive-related features in the feature extraction and fusion results, perform incentive matching based on the incentive-related features and the initial goal and the advanced goal, and establish user incentives, wherein the user incentives include incentive content and a mapping threshold; A breathing training plan is constructed based on the initial goal, advanced target game scenarios, and user incentives.

4. A breathing training game device for assisting airway clearance in critically ill patients as claimed in claim 1, characterized in that: The mapping threshold based on the breathing data and the breathing training plan generates dynamic feedback, and the user training management is performed according to the dynamic feedback, and further includes: Performing trigger analysis on the respiratory data using the mapping threshold to establish a trigger analysis result; Execute user incentive trigger frequency extraction based on the trigger analysis results, perform incentive attention feedback analysis based on the user incentive trigger frequency extraction results, establish incentive feedback, and use the incentive feedback as dynamic feedback for user training management.

5. A breathing training game device for assisting airway clearance in critically ill patients as claimed in claim 4, characterized in that: After the trigger analysis result is established, the following step is also included: Using the trigger analysis results to identify trigger weaknesses, and establish training weaknesses for the user; Specialized training is constructed based on training weaknesses and feature extraction fusion results, the specialized training is used as adjustment feedback, and the adjustment feedback is added to the dynamic feedback to perform user training management.

6. A breathing training game device for assisting airway clearance in critically ill patients as claimed in claim 4, characterized in that: The establishing of incentive feedback further includes: Perform incentive trigger call according to the trigger analysis result, and establish incentive trigger call result, wherein the incentive trigger call result includes point incentive, audio incentive, and video incentive; The incentive trigger call result is added to the incentive feedback to perform real-time training response for the user.

7. A breathing training game device for assisting airway clearance in critically ill patients as claimed in claim 1, characterized in that: The device also includes: The early warning module is used to conduct a joint analysis of respiratory data combined with real-time physiological characteristic data, establish a joint early warning recognition result, match the early warning level according to the joint early warning recognition result, and issue a early warning based on the early warning level matching result.

8. A breathing training game device for assisting airway clearance in critically ill patients as claimed in claim 1, characterized in that: The device also includes: The self-optimization module is used to match and identify the breathing data and the breathing training plan, establish the matching identification results, focus on self-optimization based on the matching identification results, generate optimization coefficients of the advanced coefficients based on the self-optimization results, optimize the advanced coefficients with the optimization coefficients, reconstruct the advanced goals, and manage the user's training according to the reconstructed advanced goals.

Images