Vertical health cabin intelligent voice interaction method, system, equipment and medium

Abstract

The invention relates to the technical field of vertical health cabins, in particular to a vertical health cabin intelligent voice interaction method, system and device and a medium. The personalized interaction parameters are generated by obtaining the interaction mode and the user parameters, the user voice input and physiological feedback data are collected in real time when voice interaction is executed, and the corresponding physiotherapy instruction is executed; the system continuously monitors the physiotherapy process, obtains state parameters such as user physiological data, environmental comfort data and voice feedback data, and adjusts physiotherapy parameters, voice interaction parameters and environmental parameters in real time according to the state parameters; according to the feedback and effect of the physical therapy, updating the health file of the user, and optimizing the next physical therapy scheme recommendation; according to the method, a real-time monitoring mechanism based on voice interaction and physiological feedback is established, parameter cooperative adjustment is realized through multi-dimensional data analysis, a complete personalized physiotherapy service closed loop is formed, and the physiotherapy safety and effect are improved.

Description

Technical Field

[0001] This application relates to the technical field of vertical health cabins, and in particular to intelligent voice interaction methods, systems, devices and media for vertical health cabins. Background Technology

[0002] With the aging population and the increasing number of people in a sub-healthy state, the demand for intelligent health management is growing. Vertical health cabins, as intelligent devices integrating physiotherapy, rehabilitation, and health care functions, can provide users with convenient health management services and are widely used in medical institutions, rehabilitation centers, and health facilities.

[0003] Currently, most vertical health cabins on the market use a preset program control system. Users select treatment modes and parameters via a touch panel and utilize various sensors to monitor the user's physiological indicators in real time. Some products also feature voice control, allowing for simple command operations and parameter adjustments.

[0004] However, existing technologies lack personalized adaptation mechanisms and cannot be dynamically optimized based on the user's real-time status; voice interaction remains at the level of simple command recognition, making it difficult to provide the best physiotherapy experience, and this situation needs further improvement. Summary of the Invention

[0005] To address the shortcomings of existing vertical health cabins, such as their inability to dynamically optimize based on real-time user status and their limited voice interaction capabilities (remaining at a basic command recognition level), thus failing to provide the best therapeutic experience, this application provides a vertical health cabin intelligent voice interaction method, system, device, and medium, employing the following technical solution: In a first aspect, this application provides a method for intelligent voice interaction in a vertical health cabin, comprising the following steps: Obtain the interaction mode and user parameters, and generate personalized interaction parameters based on the interaction mode and user parameters; Based on the personalized interaction parameters, voice interaction is performed, user voice input and physiological feedback data are collected, and corresponding physiotherapy instructions are executed. The voice interaction and physiotherapy process are monitored in real time to obtain status parameters, including user physiological data, environmental comfort data, and user voice feedback data; the physiotherapy parameters, voice interaction parameters, and environmental parameters are adjusted in real time based on the status parameters. Based on user feedback and the effectiveness of this physiotherapy, update the user's health record and optimize the next physiotherapy plan recommendation based on the user profile.

[0006] By adopting the above technical solution, since the user's physiological state and subjective feelings change dynamically during the physiotherapy process, relying solely on preset programs and simple voice commands is insufficient to respond to these changes in a timely manner. This application first obtains the interaction mode and user parameters, and generates personalized interaction parameters based on this information. Then, during the execution of voice interaction, the system collects the user's voice input and physiological feedback data in real time and executes corresponding physiotherapy commands. Simultaneously, the system continuously monitors the entire physiotherapy process, acquiring status parameters including user physiological data, environmental comfort data, and voice feedback data. Finally, the system adjusts the physiotherapy parameters, voice interaction parameters, and environmental parameters in real time based on the status parameters. The system updates the user's health record based on the feedback and effect of this physiotherapy session and uses this information to optimize the recommendation of the next physiotherapy plan. A real-time monitoring mechanism based on voice interaction and physiological feedback is established. Through comprehensive analysis of multi-dimensional data, the synergistic adjustment of physiotherapy parameters and environmental parameters is achieved. Through continuous data accumulation and plan optimization, a complete personalized physiotherapy service closed loop is formed, significantly improving the safety and effectiveness of physiotherapy.

[0007] Optionally, personalized interaction parameters are generated based on the interaction mode and user parameters, specifically including the following steps: Physiological state indicators are extracted from the user parameters, including heart rate, blood pressure, respiratory rate, and body surface temperature. Based on the physiological state indicators and the interaction mode, obtain the initial physiotherapy parameters, initial voice interaction parameters, and initial environmental control parameters; The personalized interaction parameters are generated based on the correlation between the physiological state indicators, initial physiotherapy parameters, initial voice interaction parameters, and initial environmental control parameters.

[0008] By adopting the above technical solution, since each user's physiological characteristics and health needs are different, it is difficult to meet personalized needs using a uniform parameter template. This application first extracts physiological state indicators, including heart rate, blood pressure, respiratory rate, and body surface temperature, from user parameters; then, based on these physiological state indicators and the current interaction mode, the system calculates the initial physiotherapy parameters, initial voice interaction parameters, and initial environmental control parameters respectively; finally, by analyzing the correlation between these parameters, the system generates the final personalized interaction parameters; thus achieving precise and personalized parameter adjustment.

[0009] Optionally, based on the state parameters, real-time adjustment suggestions are obtained, specifically including the following steps: The decision tree algorithm is used to perform multi-dimensional feature analysis on heart rate, blood pressure, respiratory rate and body surface temperature. Combined with the active intervention and passive monitoring types in the interaction mode, the physical therapy intensity threshold range and duration parameters are dynamically generated. Based on the fluctuation trend of the user's physiological data, a fuzzy algorithm is used to adjust the initial voice interaction parameters, including the speech rate adjustment range, voice emotion weight, and voice recognition sensitivity. Based on the correlation between the user's physiological data and environmental parameters, the dynamic equilibrium point of temperature, humidity and light intensity is calculated, and an environmental regulation curve is generated. The physiotherapy intensity threshold range, duration of action, voice interaction parameters, and environmental control curve are input into a preset optimization model. With physiological comfort and physiotherapy effect as constraints, the optimized parameter combination is output.

[0010] By adopting the above technical solution, since the user's physiological state changes dynamically over time, traditional linear parameter calculation methods are difficult to accurately reflect this complex relationship. This application first uses a decision tree algorithm to perform multi-dimensional feature analysis on heart rate, blood pressure, respiratory rate, and body surface temperature, and combines the active intervention and passive monitoring types in the interaction mode to dynamically generate the physiotherapy intensity threshold range and duration parameters. Next, based on the fluctuation trend of the user's physiological data, the system uses a fuzzy algorithm to calculate voice interaction parameters such as speech rate adjustment amplitude, voice emotion weight, and voice recognition sensitivity. At the same time, by analyzing the correlation between the user's physiological data and environmental parameters, the system calculates the dynamic balance point of temperature, humidity, and light intensity, and generates corresponding environmental control curves. Finally, these parameters are input into a preset optimization model, with physiological comfort and physiotherapy effect as constraints, and the final optimized parameter combination is output. This significantly improves the intelligence level and service quality of the health cabin.

[0011] Optionally, dynamically generating the physiotherapy intensity threshold range and duration parameters includes the following steps: Heart rate variability, blood pressure standard deviation, and body surface temperature variability are obtained, a decision tree classification model is established, and the weights of key physiological indicators are generated through feature importance analysis. The key physiological indicator weights and interaction mode types are input into the physiotherapy parameter generation model, and combined with historical physiotherapy data, the initial threshold range of physiotherapy intensity is output. The initial threshold range and user scenario type are input into the safety parameter optimization model to calculate the redundancy-containing physiotherapy intensity range, and the final duration parameter is output based on the mean intensity and heart rate variability. The user scenario types include chronic disease management scenarios, postoperative rehabilitation scenarios, sub-health conditioning scenarios, and preventive healthcare scenarios. Each scenario type corresponds to different security redundancy strategies and methods for calculating the duration of action.

[0012] By adopting the above technical solution, this application first systematically acquires real-time data such as heart rate variability, blood pressure standard deviation, and body surface temperature fluctuation rate. It then analyzes these indicators using a decision tree classification model to generate weight values ​​reflecting the importance of each indicator. These weight values, along with the current interaction mode type, are input into the physiotherapy parameter generation model. Simultaneously, combined with the user's historical physiotherapy data, an initial physiotherapy intensity threshold range is calculated. Finally, based on the user's current scenario type, the system selects an appropriate safety redundancy strategy to optimize and adjust the initial threshold range, and calculates the final duration parameter based on the mean intensity and heart rate variability. This allows for different parameter calculation strategies for different types of users, ensuring the safety of physiotherapy while improving the rationality of parameter settings, significantly enhancing the adaptability and service level of the health cabin.

[0013] Optionally, based on the fluctuation trend of the user's physiological data, a fuzzy algorithm is used to adjust the initial voice interaction parameters, specifically including the following steps: The system acquires trends in heart rate and blood pressure, inputs them into a physiological-speech mapping model, and outputs speech rate inhibition coefficient and tone softness parameters. The heart rate variability and respiratory entropy are input into the neural fuzzy reasoning system, and the voice emotion tendency parameters are output based on the emotional state assessment results. Input users’ historical voice data into the interaction preference analysis model, calculate dialect usage preferences, and output dynamic dialect adaptation parameters.

[0014] By adopting the above technical solution, since the user's physiological and emotional state changes dynamically during the physiotherapy process, traditional fixed voice parameters are difficult to provide a natural and smooth interactive experience. For example, when the user is in a tense or tired state, if the system still uses fast and mechanical voice prompts, it may aggravate the user's discomfort. This application firstly acquires the user's heart rate and blood pressure change trends in real time, inputs this data into a specially designed physiological-voice mapping model, and automatically adjusts the speech rate inhibition coefficient and tone softness parameters according to the changes in physiological state, so that the voice prompts are more in line with the user's current physical and mental state. Secondly, the system inputs two key indicators reflecting emotional state, namely heart rate variability and respiratory entropy, into the neural fuzzy inference system. Through real-time evaluation of the user's emotional state, corresponding voice emotion tendency parameters are generated, so that the system's voice feedback can reflect appropriate emotional characteristics. Finally, the system analyzes the user's historical voice interaction data, identifies the user's language usage habits and dialect preferences, and dynamically adjusts the system's dialect adaptation parameters accordingly, so that the voice interaction is closer to the user's daily expression. This realizes the intelligence and personalization of voice interaction, and enhances the affinity of interaction through dialect adaptation, significantly improving the naturalness of the health cabin voice interaction and user experience.

[0015] Optionally, based on the correlation between the user's physiological data and environmental parameters, the dynamic equilibrium point of temperature, humidity, and light intensity is calculated to generate an environmental regulation curve, specifically including the following steps: Acquire body surface temperature, carbon dioxide concentration, and humidity data, input them into an environmental coupling model, calculate the environmental sensitivity coefficient, and output the temperature equilibrium point. The heart rate and body surface temperature changes are input into the adaptive control model, and the light intensity adjustment strategy is output based on the thermal comfort index. The temperature equilibrium point and light regulation strategy are input into the environmental parameter optimization model, and combined with the user status type, the final environmental control command is output.

[0016] By adopting the above technical solution, since the user's physiological state changes with the environment during physiotherapy, traditional fixed environmental parameter settings are difficult to adapt to such dynamic changes. For example, when the user's body surface temperature rises or heart rate increases, if the ambient temperature and light intensity are not adjusted in time, it may affect the user's comfort and the physiotherapy effect. This application firstly collects the user's body surface temperature, carbon dioxide concentration and humidity data in the environment in real time, inputs these data into an environmental coupling model, and calculates the environmental sensitivity coefficient to obtain the most suitable temperature balance point. Secondly, the system inputs the user's heart rate and body surface temperature change data into an adaptive control model, uses the human thermal comfort index as the evaluation standard, and generates a corresponding light intensity adjustment strategy to ensure that the light environment matches the user's physiological state. Finally, the system inputs the calculated temperature balance point and light adjustment strategy into an environmental parameter optimization model, combines the user's current state type, and comprehensively generates the final environmental control command. It can automatically adjust environmental parameters according to the user's real-time physiological state, and ensure the comfort of the physiotherapy environment through multi-dimensional collaborative optimization, significantly improving the service quality and user experience of the health cabin.

[0017] Secondly, this application provides a vertical health cabin intelligent voice interaction system, including: A personalized interaction parameter generation module is used to obtain interaction modes and user parameters, and generate personalized interaction parameters based on the interaction modes and user parameters. The physiotherapy instruction execution module is used to perform voice interaction according to the personalized interaction parameters, collect user voice input and physiological feedback data, and execute corresponding physiotherapy instructions. The real-time adjustment suggestion generation module is used to monitor the executed voice interaction and physiotherapy process in real time, and obtain status parameters, including user physiological data, environmental comfort data and user voice feedback data; and adjust physiotherapy parameters, voice interaction parameters and environmental parameters in real time based on the status parameters. The user health record update module is used to update the user's health record based on user feedback and the effect of this physiotherapy, and to optimize the recommendation of the next physiotherapy plan based on the user profile.

[0018] Thirdly, this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described intelligent voice interaction method for a vertical health cabin.

[0019] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-described intelligent voice interaction method for a vertical health cabin.

[0020] In summary, this application includes at least one of the following beneficial technical effects: 1. This application generates personalized interaction parameters by acquiring interaction modes and user parameters. During voice interaction, it collects user voice input and physiological feedback data in real time and executes corresponding physiotherapy instructions. The system continuously monitors the physiotherapy process, acquiring status parameters such as user physiological data, environmental comfort data, and voice feedback data, and adjusts physiotherapy parameters, voice interaction parameters, and environmental parameters in real time accordingly. Based on the feedback and effect of this physiotherapy, the system updates the user's health record and optimizes the recommendation of the next physiotherapy plan. This application establishes a real-time monitoring mechanism based on voice interaction and physiological feedback, and achieves coordinated parameter adjustment through multi-dimensional data analysis, forming a complete closed loop of personalized physiotherapy service, thereby improving the safety and effectiveness of physiotherapy. 2. Since each user's physiological characteristics and health needs differ, using a uniform parameter template is insufficient to meet personalized requirements. This application first extracts physiological state indicators, including heart rate, blood pressure, respiratory rate, and body surface temperature, from user parameters. Then, based on these physiological state indicators and the current interaction mode, the system calculates initial physiotherapy parameters, initial voice interaction parameters, and initial environmental control parameters. Finally, by analyzing the correlation between these parameters, the system generates the final personalized interaction parameters, thus achieving precise and personalized parameter adjustment. 3. Because users' physiological states change dynamically over time, traditional linear parameter calculation methods cannot accurately reflect this complex relationship. This application utilizes a decision tree algorithm to perform multi-dimensional feature analysis on heart rate, blood pressure, respiratory rate, and body surface temperature. Combined with active intervention and passive monitoring types, it dynamically generates physiotherapy intensity threshold ranges and duration parameters. Based on the fluctuation trend of physiological data, the system uses a fuzzy algorithm to adjust voice interaction parameters and calculates the dynamic equilibrium point of temperature, humidity, and light intensity by analyzing the correlation between physiological data and environmental parameters, generating an environmental control curve. Finally, the parameters are input into an optimization model, with physiological comfort and physiotherapy effect as constraints, to output an optimized parameter combination, thereby improving the intelligence level of the health cabin. Attached Figure Description

[0021] Figure 1 This is a flowchart illustrating an intelligent voice interaction method for a vertical health cabin according to an embodiment of this application; Figure 2 This is a flowchart illustrating step S100 in a vertical health cabin intelligent voice interaction method according to an embodiment of this application. Figure 3 This is a flowchart illustrating step S300 in a vertical health cabin intelligent voice interaction method according to an embodiment of this application. Figure 4 This is a flowchart illustrating step S310 in a vertical health cabin intelligent voice interaction method according to an embodiment of this application. Figure 5 This is a flowchart illustrating step S320 in a vertical health cabin intelligent voice interaction method according to an embodiment of this application. Figure 6 This is a flowchart illustrating step S330 in a vertical health cabin intelligent voice interaction method according to an embodiment of this application. Figure 7 This is a schematic diagram of a vertical health cabin intelligent voice interaction system according to an embodiment of this application; Figure 8 This is an internal structural diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0022] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0023] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0024] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0025] Firstly, this application provides a vertical health cabin intelligent voice interaction method, referring to... Figure 1 It includes the following steps: S100: Obtain the interaction mode and user parameters, and generate personalized interaction parameters based on the interaction mode and user parameters.

[0026] In this embodiment, the interaction mode refers to the way the user interacts with the health cabin, which is divided into active intervention mode and passive monitoring mode. In active intervention mode, the user actively controls the physiotherapy process through voice commands, while in passive monitoring mode, the system automatically collects data and makes adjustments. User parameters include basic physiological parameters, past medical history, and physiotherapy goals. Personalized interaction parameters refer to physiotherapy control parameters customized according to user characteristics, including physiotherapy mode selection, intensity range setting, and initial values ​​of environmental parameters.

[0027] Specifically, the system selects appropriate physiotherapy modes through a pre-established user characteristic-parameter mapping table. Users are categorized according to age group and disease type, and corresponding physiotherapy modes and intensity ranges are configured for each category. Simultaneously, the system establishes a database of correspondences between basic physiological parameters and environmental parameters, setting initial combinations of environmental parameters such as temperature, humidity, and light intensity based on the user's physiological characteristics.

[0028] S200: Performs voice interaction based on personalized interaction parameters, collects user voice input and physiological feedback data, and executes corresponding physiotherapy instructions.

[0029] In this embodiment, the physiotherapy commands include start commands, stop commands, intensity adjustment commands, and mode switching commands. Physiological feedback data is collected through sensors built into the health cabin, including four basic indicators: heart rate, blood pressure, respiratory rate, and body surface temperature.

[0030] Specifically, the system pre-builds a vocabulary list for voice command recognition, standardizing commonly used physiotherapy commands. It also sets warning threshold ranges for physiological indicators, triggering an alert mechanism when an indicator exceeds a safe range. These warning thresholds are personalized based on the user's baseline physiological state.

[0031] S300 monitors the voice interaction and physiotherapy process in real time and acquires status parameters, including user physiological data, environmental comfort data, and user voice feedback data; based on the status parameters, it adjusts the physiotherapy parameters, voice interaction parameters, and environmental parameters in real time.

[0032] In this embodiment, the status parameters reflect the user's real-time status changes during the physiotherapy process. Environmental comfort data includes cabin temperature, humidity, light intensity, and carbon dioxide concentration. User voice feedback data includes voice commands, tone characteristics, and emotional tendencies in the voice.

[0033] Specifically, the system establishes a parameter adjustment rule base and adjusts parameters based on changes in status parameters. When physiological indicators approach the warning threshold, the intensity of physical therapy is automatically reduced; when discomfort is detected in voice feedback, physical therapy is immediately paused and the status is confirmed; when environmental indicators exceed the comfort range, environmental parameter adjustments are triggered.

[0034] S400: Based on user feedback and the effectiveness of this physiotherapy, update the user's health record and optimize the recommendation of the next physiotherapy plan based on the user profile.

[0035] In this embodiment, the user's health record includes basic user information, historical physiotherapy records, adverse reaction records, and physiotherapy effect evaluation. The user profile includes user habits and preferences, physiotherapy sensitivity, and environmental adaptation characteristics.

[0036] Specifically, the system uses a rating scale to record the effects of physical therapy, scoring it from three dimensions: pain improvement, functional recovery, and subjective comfort. A user profile tagging system is established, categorizing users into three types: therapy-sensitive, environment-sensitive, and stable-tolerance. Different parameter adjustment strategies are adopted for different user types. A gradual enhancement strategy is used for therapy-sensitive users, while standard physical therapy protocols can be used directly for stable-tolerance users.

[0037] In one embodiment, refer to Figure 2 In step S100, personalized interaction parameters are generated based on the interaction mode and user parameters, specifically including the following steps: S110. Extract physiological state indicators from user parameters, including heart rate, blood pressure, respiratory rate and body surface temperature.

[0038] In this embodiment, physiological state indicators refer to key physiological parameters that reflect the user's current physical condition. These indicators are collected in real time by multiple medical-grade sensors built into the health cabin, including a heart rate sensor, blood pressure monitor, respiration monitor, and infrared thermometer. The data collected by these sensors is processed to form a standardized physiological state indicator data stream.

[0039] Specifically, the system first performs noise reduction and smoothing on the collected raw physiological data, and then converts indicators of different dimensions into standard values ​​within a unified range using preset data standardization rules. The system establishes a physiological indicator evaluation table, dividing the four indicators of heart rate, blood pressure, respiratory rate, and body surface temperature into low-value, normal, and high-value ranges, respectively, for subsequent parameter matching.

[0040] S120. Based on physiological state indicators and interaction modes, obtain initial physiotherapy parameters, initial voice interaction parameters, and initial environmental control parameters.

[0041] In this embodiment, the initial parameters refer to the combination of basic parameters preset by the system based on the user's state before the start of physiotherapy. Initial physiotherapy parameters include physiotherapy mode selection, intensity level, and duration of action; initial voice interaction parameters include voice prompt frequency, speech rate setting, and volume. Specifically, the initial voice interaction parameters include dual-frequency voice modulation, which superimposes a specific frequency modulation wave onto the basic voice signal. By adjusting the frequency and amplitude of the modulation wave, fine-tuning of the voice signal is achieved. When the user is in a tense state (judged by analyzing heart rate variability and blood pressure trends), the system will activate a soothing modulation wave to provide a better calming effect for the voice prompts; initial environmental control parameters include temperature setting, humidity setting, and light intensity setting.

[0042] Specifically, the system establishes a mapping database between physiological indicators and initial parameters. Through a lookup table, it selects the corresponding parameter combination based on the user's physiological state indicator range. Simultaneously, it fine-tunes parameters based on the interaction mode type, increasing the frequency of voice prompts in active intervention mode and decreasing the frequency in passive monitoring mode. The system also maintains a parameter combination recommendation table, recording the optimal parameter configurations for different physiological states.

[0043] Furthermore, by analyzing the user's heart rate variability cycle characteristics, this application synchronizes the rhythm of change in physiotherapy parameters with the user's physiological rhythm. For example, when the system detects a significant low-frequency component of the user's heart rate variability, it will adjust the cycle of change in physiotherapy intensity accordingly, so that the physiotherapy process conforms to the body's natural regulatory laws.

[0044] Furthermore, the system is equipped with an adjustable LED light source array, capable of outputting a combination of near-infrared and red light. By analyzing the user's body surface temperature distribution characteristics and blood pressure change patterns in real time, the system dynamically adjusts the spectral composition of the illumination. When uneven body surface temperature distribution is detected, the system increases the output proportion of near-infrared light. Near-infrared light has strong tissue penetration capabilities, which can promote local blood circulation and help balance body surface temperature distribution. The system dynamically adjusts the output power of near-infrared light according to the coefficient of variation of body surface temperature; the higher the coefficient of variation, the higher the proportion of near-infrared light.

[0045] When the system detects that a user's blood pressure is too high, it increases the output of red light. Red light has a mild physiological regulatory effect, helping to relax blood vessels and regulate blood pressure. The system adjusts the output intensity of the red light based on the degree of deviation of the blood pressure value from the standard range; the greater the deviation, the longer the red light exposure time.

[0046] S130. Generate personalized interaction parameters based on the correlation between physiological state indicators, initial physiotherapy parameters, initial voice interaction parameters, and initial environmental control parameters.

[0047] In this embodiment, the correlation refers to the mutual influence between physiological state indicators and various initial parameters. By analyzing these correlations, the system ensures that the settings of various parameters are coordinated to create the optimal therapeutic environment.

[0048] Specifically, the system pre-establishes a parameter association rule base, defining the constraints between different parameters. For example, when the heart rate is in a high range, the system will reduce the intensity of the physical therapy, adjust to a gentler voice prompt, and set soothing environmental parameters. The system inputs the initial parameters into the association rule base for analysis and outputs the final personalized interaction parameter combination. For parameter settings that may conflict, the system adjusts them according to preset priority rules to ensure the rationality of the parameter combination.

[0049] In one embodiment, refer to Figure 3 In step S300, real-time adjustment suggestions are obtained based on the status parameters, specifically including the following steps: S310. The decision tree algorithm is used to perform multi-dimensional feature analysis on heart rate, blood pressure, respiratory rate and body surface temperature. Combined with the active intervention and passive monitoring types in the interaction mode, the physical therapy intensity threshold range and duration parameters are dynamically generated.

[0050] In this embodiment, multi-dimensional feature analysis refers to a comprehensive analysis process of physiological data. The decision tree algorithm forms a decision path for adjusting physical therapy parameters by performing hierarchical judgments on data from four dimensions: heart rate, blood pressure, respiratory rate, and body surface temperature. The interaction mode type, as an important branch condition of the decision tree, affects the sensitivity of parameter adjustment. This application determines the sensitivity of parameter adjustment based on the interaction mode type.

[0051] Specifically, the system constructs a three-layer decision tree structure: the first layer divides the system into active intervention and passive monitoring branches based on the interaction mode; the second layer classifies the system based on the combined states of four physiological indicators; and the third layer determines the adjustment strategy for physical therapy parameters based on the classification results. The system pre-establishes a table of physiological indicator combinations, establishing a correspondence between common indicator combinations and physical therapy parameter adjustment strategies. For example, when an elevated heart rate and fluctuating blood pressure are detected, the system will lower the upper limit of the physical therapy intensity threshold and shorten the duration of the treatment.

[0052] S320: Based on the fluctuation trend of user physiological data, a fuzzy algorithm is used to adjust the initial voice interaction parameters, including the speech rate adjustment range, voice emotion weight, and voice recognition sensitivity.

[0053] In this embodiment, fluctuation trend analysis refers to the monitoring of the rate and direction of change in physiological data. Voice interaction parameters include three key dimensions: speech rate adjustment reflects the rhythmic changes of voice prompts, emotion weight controls the tone characteristics of the speech, and recognition sensitivity determines the system's response speed to user commands.

[0054] Specifically, the system establishes a mapping table between physiological fluctuations and voice parameters, selecting appropriate combinations of voice parameters based on the changing characteristics of physiological indicators. A fuzzy rule base defines the correspondence between physiological fluctuations and voice parameters, enabling dynamic adjustment of voice interaction.

[0055] S330. Based on the correlation between user physiological data and environmental parameters, calculate the dynamic equilibrium point of temperature, humidity and light intensity, and generate an environmental regulation curve.

[0056] In this embodiment, the dynamic equilibrium point refers to the combination of environmental parameters that is most conducive to the therapeutic effect under the current physiological state. The environmental regulation curve describes the trajectory of environmental parameters over time, ensuring a smooth transition of environmental parameters.

[0057] Specifically, the system analyzes the correlation between physiological data and environmental parameters using linear regression to establish formulas for calculating environmental parameters. Based on the correlation analysis results, the system generates a stepped environmental regulation curve to avoid abrupt changes in environmental parameters. The system maintains an environmental parameter optimization table, recording the optimal environmental configuration under different physiological states.

[0058] S340: Input the physiotherapy intensity threshold range, duration parameters, voice interaction parameters, and environmental control curve into the preset optimization model, and output the optimized parameter combination with physiological comfort and physiotherapy effect as constraints.

[0059] In this embodiment, the optimization model is a rule-based parameter comprehensive evaluation system used to coordinate the relationships between various parameters. Physiological comfort and therapeutic effect serve as core constraints to ensure the rationality of parameter adjustments.

[0060] Specifically, the system establishes a parameter optimization rule base, defining the constraints and priorities between different parameters. Through rule matching, the system coordinates various parameters to generate the final parameter combination scheme.

[0061] In one embodiment, refer to Figure 4 In step S310, the dynamic generation of the physiotherapy intensity threshold range and duration parameters specifically includes the following steps: S311. Obtain heart rate variability, blood pressure standard deviation, and body surface temperature fluctuation rate, establish a decision tree classification model, and generate key physiological indicator weights through feature importance analysis.

[0062] In this embodiment, physiological variability refers to statistical indicators that reflect fluctuations in physiological data. Heart rate variability is obtained by calculating the standard deviation of adjacent heartbeat intervals, blood pressure standard deviation reflects blood pressure stability, and body surface temperature variability represents the severity of temperature changes. A decision tree classification model is used to identify the risk level corresponding to different combinations of variability features.

[0063] Specifically, the system first establishes a database of physiological indicator variability features, recording reference values ​​for features at different risk levels. A decision tree classifier then categorizes the current combination of variability features into the corresponding risk level. The system pre-defines rules for calculating feature importance, calculating corresponding weight coefficients based on the degree of influence of each indicator on the risk level. For example, heart rate variability has a significant impact on the safety of physical therapy and is therefore assigned a higher weight.

[0064] S312. Input the weights of key physiological indicators and the interaction mode type into the physiotherapy parameter generation model, and combine it with historical physiotherapy data to output the initial threshold range of physiotherapy intensity.

[0065] In this embodiment, the physiotherapy parameter generation model is a rule-based parameter calculation system that comprehensively considers physiological indicator weights, interaction pattern characteristics, and historical physiotherapy records to calculate the appropriate range of physiotherapy intensity for the current state. Historical physiotherapy data includes records of past physiotherapy intensity settings and effect evaluation information.

[0066] Specifically, the system constructs a physiotherapy parameter recommendation table, establishing a mapping relationship between different weight combinations and physiotherapy intensity ranges. The initial physiotherapy intensity range is obtained through a table lookup. The system also maintains a historical physiotherapy database, recording users' experience with physiotherapy parameter settings under different conditions, which is used to correct the initial range.

[0067] S313. Input the initial threshold range and user scenario type into the safety parameter optimization model, calculate the redundancy-containing physiotherapy intensity range, and output the final duration parameter based on the mean intensity and heart rate variability.

[0068] The user scenario types include chronic disease management, postoperative rehabilitation, sub-health conditioning, and preventive healthcare. Each scenario type corresponds to different safety redundancy strategies and methods for calculating duration of action.

[0069] In this embodiment, the safety parameter optimization model is a parameter adjustment mechanism to ensure the safety of physiotherapy. Different safety strategies are selected according to the user scenario type, and the risks of physiotherapy are reduced by adding intensity redundancy and adjusting the duration of action. Each scenario type corresponds to specific safety requirements and adjustment methods.

[0070] Specifically, the system establishes a scenario-based safety policy library, defining corresponding parameter adjustment rules for four typical scenarios. The chronic disease management scenario adopts a conservative strategy, increasing intensity redundancy; the postoperative rehabilitation scenario emphasizes gradual progression and dynamically adjusts the duration of action; the sub-health conditioning and preventative healthcare scenarios employ standard strategies. The system selects the corresponding adjustment rule based on the current scenario type and calculates the final duration of action by combining heart rate variability data.

[0071] In one embodiment, refer to Figure 5 In step S320, based on the fluctuation trend of the user's physiological data, a fuzzy algorithm is used to adjust the initial voice interaction parameters, specifically including the following steps: S321. Obtain the trends of heart rate and blood pressure changes, input the physiological-speech mapping model, and output the speech rate inhibition coefficient and tone softness parameters.

[0072] In this embodiment, the physiological-speech mapping model is a parameter transformation system based on a lookup table. The trend of change is obtained by calculating the rate of change of heart rate and blood pressure within a fixed time window, used to characterize the dynamic changes in the user's state. The speech rate suppression coefficient is used to control the rhythm of the voice prompts, while the intonation softness parameter determines the pitch characteristics of the speech.

[0073] Specifically, the system establishes a physiological change trend classification table, dividing the rate of change of heart rate and blood pressure into three levels: stable, gradually changing, and rapidly changing. Simultaneously, it constructs a voice parameter mapping table, defining combinations of voice parameters for different change levels. When a rapidly changing physiological indicator is detected, the system increases the speech rate suppression coefficient and improves the tone of voice, making the voice prompts smoother and more comfortable. The system periodically updates the parameter configurations in the mapping table to optimize the voice interaction effect.

[0074] S322. Input heart rate variability and respiratory entropy into the neural fuzzy reasoning system, and output voice emotion tendency parameters based on the emotional state assessment results.

[0075] In this embodiment, emotional state assessment infers user emotional changes by analyzing the fluctuation characteristics of physiological indicators. Heart rate variability reflects the regulatory state of the autonomic nervous system, and respiratory entropy characterizes respiratory regularity. The neurofuzzy inference system transforms these characteristics into emotional state judgment results.

[0076] Specifically, the system pre-establishes a rule base for judging emotional states, defining the emotional state types corresponding to different combinations of physiological characteristics. Simple fuzzy rules are used for reasoning, such as "if heart rate variability decreases and respiratory entropy increases, then it is judged as a state of tension." Based on the reasoning results, appropriate voice emotion parameters are selected to adjust the emotional tone of the voice prompts.

[0077] S323. Input the user's historical voice data into the interaction preference analysis model, calculate the dialect usage preference, and output dynamic dialect adaptation parameters.

[0078] In this embodiment, dialect adaptation refers to adjusting the system's voice interaction method according to the user's language usage habits. The interaction preference analysis model identifies the user's dialect usage characteristics by statistically analyzing the user's historical voice data.

[0079] Specifically, the system maintains a user voice feature database, recording the frequency and specific scenarios of dialect usage in users' historical voice interactions. Through frequency statistics, it calculates the usage ratio of different dialect expressions to determine the user's primary language preferences. Based on the statistical results, the system dynamically adjusts the dialect configuration for voice interactions, using familiar dialects in appropriate scenarios to enhance the user's affinity for the interaction.

[0080] In one embodiment, refer to Figure 6 In step S330, based on the correlation between user physiological data and environmental parameters, the dynamic equilibrium point of temperature, humidity, and light intensity is calculated to generate an environmental regulation curve, specifically including the following steps: S331. Acquire body surface temperature, carbon dioxide concentration, and humidity data, input them into the environmental coupling model, calculate the environmental sensitivity coefficient, and output the temperature equilibrium point.

[0081] In this embodiment, the environmental coupling model is a mathematical model describing the interaction between human physiological state and environmental parameters. The environmental sensitivity coefficient reflects the user's sensitivity to environmental changes and is determined by three factors: body surface temperature, carbon dioxide concentration, and humidity. The temperature equilibrium point refers to the most suitable temperature setting value under the current conditions.

[0082] Specifically, the system establishes an environmental parameter association table to record reference values ​​of environmental sensitivity coefficients under different combinations of physiological indicators. The environmental sensitivity coefficient for the current state is calculated using a linear weighted method, with weighting coefficients pre-set according to the importance of each indicator. The system maintains a temperature equilibrium point calculation rule base and calculates the optimal temperature setpoint based on the environmental sensitivity coefficient and current environmental parameters. For example, when body surface temperature rises and carbon dioxide concentration is high, the system will correspondingly lower the temperature equilibrium point.

[0083] S332. Input the heart rate and body surface temperature changes into the adaptive control model, and output the light intensity adjustment strategy based on the thermal comfort index.

[0084] In this embodiment, the thermal comfort index is a comprehensive indicator for evaluating the level of environmental comfort. The adaptive control model dynamically adjusts the illumination parameters based on the user's physiological responses. The illumination intensity adjustment strategy includes two key elements: the range of illumination intensity variation and the adjustment rate.

[0085] Specifically, the system pre-establishes a thermal comfort assessment table, mapping changes in heart rate and body surface temperature to comfort levels. The current comfort level is determined by looking up the table, and corresponding adjustment strategies are generated based on preset lighting adjustment rules. The system also establishes a lighting parameter database, recording optimal lighting configurations for different comfort levels.

[0086] S333: Input the temperature equilibrium point and light regulation strategy into the environmental parameter optimization model, and combine it with the user status type to output the final environmental control command.

[0087] In this embodiment, the environmental parameter optimization model is a rule-based environmental control system. This system comprehensively considers temperature balance requirements, illumination regulation requirements, and user state characteristics to generate the final environmental control instructions. User state types reflect the user's tolerance to environmental changes.

[0088] Specifically, the system constructs an environmental control rule base, defining coordinated adjustment strategies for temperature and light parameters. Through rule matching, the system selects an appropriate control scheme and makes suitable adjustments based on the user's status. The system maintains an environmental parameter control experience database, recording the control effects under different conditions for optimizing the control strategy.

[0089] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0090] Secondly, this application provides a vertical health cabin intelligent voice interaction system. The vertical health cabin intelligent voice interaction system of this application will be described below in conjunction with the above-mentioned vertical health cabin intelligent voice interaction method.

[0091] Reference Figure 7 A vertical health cabin intelligent voice interaction system includes: The personalized interaction parameter generation module is used to obtain the interaction mode and user parameters, and generate personalized interaction parameters based on the interaction mode and user parameters. The physiotherapy instruction execution module is used to perform voice interaction based on personalized interaction parameters, collect user voice input and physiological feedback data, and execute corresponding physiotherapy instructions. The real-time adjustment suggestion generation module is used to monitor the executed voice interaction and physiotherapy process in real time, and obtain status parameters, including user physiological data, environmental comfort data and user voice feedback data; based on the status parameters, the physiotherapy parameters, voice interaction parameters and environmental parameters are adjusted in real time. The user health record update module is used to update the user's health record based on user feedback and the effect of this physiotherapy, and to optimize the recommendation of the next physiotherapy plan based on the user profile.

[0092] In one embodiment, this application provides an electronic device, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, the electronic device includes a processor, memory, and network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a vertical health cabin intelligent voice interaction method.

[0093] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0094] In one embodiment, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0095] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0096] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A method for intelligent voice interaction in a vertical health cabin, characterized in that, Includes the following steps: Obtain the interaction mode and user parameters, and generate personalized interaction parameters based on the interaction mode and user parameters; Based on the personalized interaction parameters, voice interaction is performed, user voice input and physiological feedback data are collected, and corresponding physiotherapy instructions are executed. The voice interaction and physiotherapy process are monitored in real time to obtain status parameters, including user physiological data, environmental comfort data, and user voice feedback data; the physiotherapy parameters, voice interaction parameters, and environmental parameters are adjusted in real time based on the status parameters. Based on user feedback and the effectiveness of this physiotherapy, update the user's health record and optimize the next physiotherapy plan recommendation based on the user profile.

2. The intelligent voice interaction method for the vertical health cabin according to claim 1, characterized in that, Based on the interaction mode and user parameters, personalized interaction parameters are generated, specifically including the following steps: Physiological state indicators are extracted from the user parameters, including heart rate, blood pressure, respiratory rate, and body surface temperature. Based on the physiological state indicators and the interaction mode, obtain the initial physiotherapy parameters, initial voice interaction parameters, and initial environmental control parameters; The personalized interaction parameters are generated based on the correlation between the physiological state indicators, initial physiotherapy parameters, initial voice interaction parameters, and initial environmental control parameters.

3. The intelligent voice interaction method for the vertical health cabin according to claim 2, characterized in that, Based on the state parameters, real-time adjustment suggestions are obtained, specifically including the following steps: The decision tree algorithm is used to perform multi-dimensional feature analysis on heart rate, blood pressure, respiratory rate and body surface temperature. Combined with the active intervention and passive monitoring types in the interaction mode, the physical therapy intensity threshold range and duration parameters are dynamically generated. Based on the fluctuation trend of the user's physiological data, a fuzzy algorithm is used to adjust the initial voice interaction parameters, including the speech rate adjustment range, voice emotion weight, and voice recognition sensitivity. Based on the correlation between the user's physiological data and environmental parameters, the dynamic equilibrium point of temperature, humidity and light intensity is calculated, and an environmental regulation curve is generated. The physiotherapy intensity threshold range, duration of action, voice interaction parameters, and environmental control curve are input into a preset optimization model. With physiological comfort and physiotherapy effect as constraints, the optimized parameter combination is output.

4. The intelligent voice interaction method for the vertical health cabin according to claim 3, characterized in that, Dynamically generating physical therapy intensity threshold ranges and duration parameters includes the following steps: Heart rate variability, blood pressure standard deviation, and body surface temperature variability are obtained, a decision tree classification model is established, and the weights of key physiological indicators are generated through feature importance analysis. The key physiological indicator weights and interaction mode types are input into the physiotherapy parameter generation model, and combined with historical physiotherapy data, the initial threshold range of physiotherapy intensity is output. The initial threshold range and user scenario type are input into the safety parameter optimization model to calculate the redundancy-containing physiotherapy intensity range, and the final duration parameter is output based on the mean intensity and heart rate variability. The user scenario types include chronic disease management scenarios, postoperative rehabilitation scenarios, sub-health conditioning scenarios, and preventive healthcare scenarios. Each scenario type corresponds to different security redundancy strategies and methods for calculating the duration of action.

5. The intelligent voice interaction method for the vertical health cabin according to claim 4, characterized in that, Based on the fluctuation trend of the user's physiological data, a fuzzy algorithm is used to adjust the initial voice interaction parameters, specifically including the following steps: The system acquires trends in heart rate and blood pressure, inputs them into a physiological-speech mapping model, and outputs speech rate inhibition coefficient and tone softness parameters. The heart rate variability and respiratory entropy are input into the neural fuzzy reasoning system, and the voice emotion tendency parameters are output based on the emotional state assessment results. Input users’ historical voice data into the interaction preference analysis model, calculate dialect usage preferences, and output dynamic dialect adaptation parameters.

6. The intelligent voice interaction method for the vertical health cabin according to claim 3, characterized in that, Based on the correlation between the user's physiological data and environmental parameters, the dynamic equilibrium point of temperature, humidity, and light intensity is calculated to generate an environmental regulation curve, specifically including the following steps: Acquire body surface temperature, carbon dioxide concentration, and humidity data, input them into an environmental coupling model, calculate the environmental sensitivity coefficient, and output the temperature equilibrium point. The heart rate and body surface temperature changes are input into the adaptive control model, and the light intensity adjustment strategy is output based on the thermal comfort index. The temperature equilibrium point and light regulation strategy are input into the environmental parameter optimization model, and combined with the user status type, the final environmental control command is output.

7. A vertical health cabin intelligent voice interaction system, characterized in that, include: A personalized interaction parameter generation module is used to obtain interaction modes and user parameters, and generate personalized interaction parameters based on the interaction modes and user parameters. The physiotherapy instruction execution module is used to perform voice interaction according to the personalized interaction parameters, collect user voice input and physiological feedback data, and execute corresponding physiotherapy instructions. The real-time adjustment suggestion generation module is used to monitor the executed voice interaction and physiotherapy process in real time, and obtain status parameters, including user physiological data, environmental comfort data and user voice feedback data; and adjust physiotherapy parameters, voice interaction parameters and environmental parameters in real time based on the status parameters. The user health record update module is used to update the user's health record based on user feedback and the effect of this physiotherapy, and to optimize the recommendation of the next physiotherapy plan based on the user profile.

8. An electronic device, characterized in that, The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the intelligent voice interaction method for the vertical health cabin as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent voice interaction method for the vertical health cabin as described in any one of claims 1-6.

Images