Moxibustion equipment temperature adjusting method and system controlled by intelligent chip

Abstract

The invention discloses a temperature adjusting method and system for moxibustion equipment controlled by an intelligent chip, and the method comprises the steps: firstly, collecting a heart rate sequence of a user during moxibustion through the intelligent chip, decomposing a long-term trend item and a short-term fluctuation item, and calculating the instantaneous heart rate change; thirdly, a causal model of the instant heart rate change and a temperature sensitivity variable is built according to the instant heart rate change; secondly, extracting historical moxibustion temperature setting data from the equipment database, and analyzing temperature setting preferences of a user in different temperature sensitivity states; splitting a basic preset temperature and a fluctuation temperature regulation part based on preference characteristics, and determining fluctuation temperature regulation coefficients in different heart rate reaction modes according to heart rate changes; meanwhile, the preference and change of the user to the moxibustion part are analyzed in combination with historical use records; and finally, storing the personalized temperature adjustment data of the user in the intelligent chip, and updating the personalized temperature adjustment data in real time after the personalized temperature adjustment data is used each time. The method can effectively grasp personalized demands of users and improve the moxibustion experience and effect.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for adjusting the temperature of a moxibustion device controlled by an intelligent chip. Background Technology

[0002] In traditional moxibustion treatment scenarios, the control method of moxibustion devices is extremely simple and fixed. Moxibustion is usually performed according to a preset fixed temperature and time, completely disregarding individual differences and real-time physiological states of users. Different users have different sensitivities to temperature, and the moxibustion temperature requirements of the same user also vary at different times and under different physical conditions. However, traditional devices cannot adjust according to these dynamic factors, resulting in poor moxibustion effects, failing to meet users' personalized health needs, and affecting the treatment experience and efficacy. Smart chips, with their powerful data processing and computing capabilities, can potentially overcome the shortcomings of traditional methods and achieve personalized temperature control when applied to the temperature regulation of moxibustion devices.

[0003] In the ongoing innovation of medical and health equipment, big data technology has demonstrated enormous potential for optimizing equipment control in numerous medical scenarios, becoming a crucial force driving industry development. However, the moxibustion device field has not yet fully capitalized on this technological advancement. Existing moxibustion device control methods have significant shortcomings in data utilization. They lack in-depth analysis and effective application of key user data, such as real-time heart rate changes reflecting real-time bodily states, historical temperature setting preferences reflecting individual usage habits, and preferences for different moxibustion sites. This prevents the device from accurately adjusting temperature based on the user's real-time physiological feedback and long-established usage habits, hindering personalized moxibustion services. Smart chips, with their powerful data acquisition, analysis, and processing capabilities, can precisely compensate for this deficiency, bringing a new breakthrough to temperature control in moxibustion devices. Summary of the Invention

[0004] This application provides a temperature adjustment method for moxibustion devices controlled by an intelligent chip, which accurately grasps the personalized needs of users and improves the personalization of moxibustion device use and user experience.

[0005] This application provides a method for adjusting the temperature of a moxibustion device controlled by an intelligent chip, including: S1 uses a smart chip to collect the user's heart rate sequence during the use of the moxibustion device, decomposes it into long-term trend terms and short-term fluctuation terms, and calculates the user's instantaneous heart rate changes. S2, based on the user's instantaneous heart rate changes, the smart chip uses a causal discovery algorithm to construct a causal model between the user and the temperature sensitivity variable; S3 extracts historical moxibustion temperature setting data from the device database, and the smart chip analyzes the user's temperature setting preferences under different temperature sensitivity states. S4, based on the characteristics of user temperature setting preferences, is divided into a basic preset temperature and a fluctuating temperature regulation part. The intelligent chip determines the fluctuating temperature regulation coefficient in different heart rate response modes according to the instantaneous heart rate changes. S5, based on the user's historical usage records, the smart chip analyzes the user's preference for different moxibustion sites, combines instantaneous heart rate changes with moxibustion preferences, and analyzes the changes in the user's preference for moxibustion items and sites under different heart rate response modes; S6 stores the table structure of the user's personalized temperature adjustment data into the smart chip. The smart chip updates the user's personalized temperature adjustment data in real time every time the user uses the moxibustion device.

[0006] Preferably, the analysis of the user's temperature setting preferences under different temperature sensitivity states specifically includes: filtering all historical moxibustion records of the user from the device database based on the user's unique identifier, obtaining the preset temperature corresponding to each moxibustion session and the temperature adjustment records during the moxibustion process, including the adjustment time point and the adjusted temperature value; combining the causal relationship between instantaneous heart rate changes and temperature sensitivity variables in the causal model, the smart chip sets a threshold for classifying temperature sensitivity states; analyzing the instantaneous heart rate changes corresponding to each moxibustion record, the analysis being completed by the smart chip, classifying each moxibustion record into the corresponding temperature sensitivity state; and for all moxibustion records in the same temperature sensitivity state... The system calculates the average value of the preset temperature; compares the average value of the preset temperature under different temperature sensitivity states to analyze the user's preference for the preset temperature under different states; for each moxibustion record, it calculates the temperature adjustment range, i.e., the difference between the adjusted temperature and the preset temperature; it statistically analyzes the direction and frequency of temperature adjustment under different temperature sensitivity states; and based on the analysis results of preset temperature preference and temperature adjustment preference, the smart chip determines the user's preference for setting the moxibustion temperature under different temperature sensitivity states. The causal model is constructed using a PC algorithm, where instantaneous heart rate changes and temperature sensitivity variables are used as nodes in a graph, with edges connecting any two nodes to form an undirected complete graph.

[0007] Preferably, the instantaneous heart rate change includes: the instantaneous heart rate change consists of the heart rate trend slope and the heart rate prediction deviation; setting a time window length n, using the computing power of the smart chip, using the moving average method to decompose the heart rate sequence, calculating the average value of the heart rate data in each time window, using the obtained average value sequence as the long-term trend term, and the short-term fluctuation term is obtained by subtracting the long-term trend term from the heart rate sequence; based on the data processing function of the smart chip, using the least squares method to linearly fit the long-term trend term, establishing a time series prediction model based on historical heart rate data to predict the heart rate value at the current moment, and calculating the deviation between the predicted value and the actual heart rate value.

[0008] Preferably, determining the fluctuation temperature regulation coefficient based on instantaneous heart rate changes under different heart rate response modes specifically includes: The intelligent chip records dynamic data in real time during the user's use of the moxibustion device. When a temperature fluctuation occurs, it records the user's dynamic data characteristics and stores them in the historical database. The intelligent chip associates and stores the user's dynamic data characteristics during each temperature fluctuation with the corresponding temperature adjustment parameters, and performs retrospective analysis on the stored temperature fluctuation event data. Based on the retrospective user dynamic data characteristics, the intelligent chip uses data analysis algorithms to analyze the temperature adjustment patterns under different characteristic combinations. Based on the analysis results, it generates corresponding gradual temperature control curves for different user characteristic combinations. During a new moxibustion session, the intelligent chip matches the current user characteristics with the characteristics in the temperature fluctuation event database, calls the corresponding gradual temperature control curve, and performs advance temperature transition adjustments in the current moxibustion stage.

[0009] Preferably, the backtracking analysis of the stored fluctuating temperature control event data specifically includes: creating a unique identifier for each fluctuating temperature control event; the smart chip associating the user's dynamic data characteristics during fluctuating temperature control with the corresponding temperature control parameters in the form of key-value pairs; analyzing the patterns of temperature adjustment amplitude and instantaneous heart rate change characteristics under different combinations of user characteristics; extracting the patterns of temperature adjustment amplitude and instantaneous heart rate change characteristics with similar features from the stored fluctuating temperature control event data; the relationship between instantaneous heart rate change characteristics and temperature control direction; grouping according to the value range of instantaneous heart rate change characteristics; and statistically matching the proportion of events with different temperature control directions in each group. If the analysis objective is to find out the distribution of temperature adjustment amplitude under different moxibustion durations, the smart chip divides the moxibustion duration into different intervals and statistically analyzes the temperature adjustment amplitude within each interval.

[0010] Preferably, the step of generating corresponding progressive temperature control curves for different combinations of user characteristics based on the analysis results includes: the intelligent chip determining the parameters of the progressive temperature control curve based on the temperature adjustment patterns under different combinations of user dynamic data characteristics; during the user's current moxibustion process, the intelligent chip acquires the user's dynamic data characteristics in real time, matches the current user dynamic data characteristics with combinations of user dynamic data characteristics in the historical database, and finds the most similar feature combination; the intelligent chip generates a specific progressive temperature control curve based on the progressive temperature control curve parameters corresponding to the matched feature combination, combined with the current moxibustion duration and temperature; when the intelligent chip detects that the current user has characteristics similar to those observed during historical temperature fluctuations, it performs an advance temperature transition adjustment according to the generated progressive temperature control curve.

[0011] Preferably, the step of calling the corresponding progressive temperature control curve further includes: constructing a model of the progressive temperature control curve for the initial moxibustion site based on the temperature adjustment pattern of the user's dynamic data feature combination during the fluctuating temperature adjustment process; determining the segmentation points of the progressive temperature control curve for the initial moxibustion site based on the temperature changes during moxibustion; determining the temperature sensitivity difference between the initial moxibustion site and other moxibustion sites, and correcting the progressive temperature control curves for other moxibustion sites; when it is detected that the user's dynamic data features during moxibustion on other sites are similar to the features corresponding to historical fluctuating temperature adjustments, performing an advance temperature transition adjustment according to the generated progressive temperature control curves for other sites.

[0012] Preferably, the model for constructing the initial moxibustion site's gradual temperature control curve specifically involves: analyzing the relationship between the temperature adjustment range and the moxibustion duration, and the relationship between the temperature adjustment range and heart rate changes, to determine a comprehensive function of the temperature adjustment range, moxibustion duration, and heart rate change rate; determining the gradual temperature control curve based on the comprehensive function, and setting the initial moxibustion site's gradual temperature control curve, i.e. in It is heart rate sequence data. Indicates the base preset temperature With temperature adjustment range sum , and The coefficients are obtained by combining and fitting a function.

[0013] Preferably, the correction of the gradual temperature control curve for other moxibustion sites includes: Data related to acupoint therapy is imported into the moxibustion device to analyze the impact of temperature changes at different acupoints on other acupoints and the user's overall temperature sensitivity. A dynamic equilibrium model of acupoint temperature is established using system dynamics. Based on the purpose of moxibustion at each stage, the target temperature range for each acupoint in the acupoint group is determined for each stage. The temperature of each acupoint in the acupoint group is monitored in real time during the moxibustion process, and the acupoint therapy process is divided into different stages. Based on the progressive temperature control curve corrected by the user's dynamic data, the moxibustion device coordinates and regulates the temperature of each acupoint in the acupoint group at each stage according to real-time data and the dynamic equilibrium model.

[0014] Preferably, establishing the dynamic equilibrium model of acupoint temperature specifically includes: determining the elements in the acupoint temperature system and the causal relationships between them based on the principles of system dynamics; and assuming that the temperature of each acupoint is a flow potential variable. Where n is the number of acupoints; the rate of temperature change is the flow rate variable. Based on causal relationships and actual physical meaning, establish equations between the variables, that is... , can be established , where k is the thermal conductivity correlation coefficient, and f(u(t)) is the influence function of factors such as user temperature sensitivity on the rate of temperature change of acupoint i.

[0015] Preferably, a temperature control system for a moxibustion device controlled by an intelligent chip, the system comprising: The data acquisition module is used to collect the user's heart rate sequence during the use of the moxibustion device using a smart chip, decompose it into long-term trend terms and short-term fluctuation terms, and calculate the user's instantaneous heart rate changes. The decomposition calculation module is used to construct a causal model between the user's instantaneous heart rate change and the temperature sensitivity variable using a causal discovery algorithm. The preference analysis module is used to extract users' historical moxibustion temperature setting data from the device database, and the smart chip analyzes the user's temperature setting preferences under different temperature sensitivity states. The temperature control module is used to divide the user's temperature setting preferences into a basic preset temperature and a fluctuating temperature control part. The intelligent chip determines the fluctuating temperature control coefficient in different heart rate response modes based on the instantaneous heart rate changes. The preference analysis module is used to analyze the user's preference for different moxibustion sites based on the user's historical usage records. It combines instantaneous heart rate changes with moxibustion preferences to analyze changes in the user's preference for moxibustion items and sites under different heart rate response modes. The data storage module stores the table structure of the user's personalized temperature adjustment data into the smart chip. The smart chip updates the user's personalized temperature adjustment data in real time each time the user uses the moxibustion device.

[0016] One or more technical solutions provided in this application have at least the following technical effects or advantages: By accurately collecting and analyzing users' heart rate data through intelligent chips, and combining it with historical data to build a predictive model, a causal model is intelligently constructed based on heart rate changes to analyze temperature sensitivity, thereby accurately grasping users' personalized preferences for moxibustion temperature and location.

[0017] By using a smart chip to record dynamic data of moxibustion in real time and link and store information related to temperature fluctuations, a gradual temperature control curve is generated after backtracking analysis and pattern mining. This enables precise matching and advance temperature adjustment based on the user's real-time characteristics, effectively avoiding discomfort caused by sudden temperature changes. It significantly improves the personalization and intelligence of temperature control during moxibustion, bringing users a more comfortable moxibustion experience that is more in line with their own condition.

[0018] By deeply analyzing the differences in temperature sensitivity between the initial treatment site and other sites during moxibustion, and combining this with dynamic user data, a progressive temperature control curve is precisely constructed and corrected. This solution can personalize and optimize temperature adjustments based on the physiological differences of different sites, making moxibustion temperature control more closely match the actual needs of users. This effectively improves the comfort and accuracy of moxibustion treatment, bringing users a higher quality and more scientific moxibustion experience.

[0019] By importing acupoint treatment data, constructing a dynamic balance model, dividing treatment stages, and coordinating the temperature adjustment of each acupoint based on real-time data, this approach fully considers the mutual influence of temperature changes between acupoints and the differences in needs at different treatment stages. This solution can accurately adapt the appropriate temperature for each acupoint at different stages, effectively improving the targeting and synergy of moxibustion treatment, making the treatment process more in line with human physiological rhythms, thereby enhancing treatment efficacy and providing users with a more efficient and comfortable moxibustion experience. Attached Figure Description

[0020] Figure 1 This is a schematic flowchart of a temperature adjustment method for a smart chip-controlled moxibustion device according to an embodiment of the present invention. Figure 2 This is a structural block diagram of a temperature control system for a moxibustion device controlled by an intelligent chip, according to an embodiment of the present invention. Detailed Implementation

[0021] To facilitate understanding of the present invention, a more complete description of this application will be given below with reference to the accompanying drawings, which illustrate preferred embodiments of the invention. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to enable a more thorough and complete understanding of the disclosure of the present invention.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains; the terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to limit the invention; the term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0023] Example 1: Figure 1 This is a flowchart illustrating a method for adjusting the temperature of a moxibustion device controlled by an intelligent chip, according to an embodiment of the present invention.

[0024] like Figure 1 As shown, a method for adjusting the temperature of a moxibustion device controlled by a smart chip includes the following steps: S1 uses a smart chip to collect the user's heart rate sequence during the use of the moxibustion device, decomposes it into long-term trend terms and short-term fluctuation terms, and calculates the user's instantaneous heart rate changes.

[0025] The instantaneous heart rate change consists of the heart rate trend slope and the heart rate prediction deviation.

[0026] Specifically, 1a, leveraging the computing power of the intelligent chip, a moving average method is used to decompose the heart rate sequence. A suitable time window length n is set (in this application, n is 10 minutes, which can be adjusted appropriately according to data characteristics and needs). The average value of the heart rate data in each time window is calculated, and the resulting average value sequence is used as the long-term trend term T(t). The short-term fluctuation term F(t) is obtained by subtracting the long-term trend term T(t) from the heart rate sequence H(t). For time point t, the corresponding long-term trend term is decomposed as follows: (Here, it is assumed that the time window is symmetrical about t; if limited by the length of the time series, the calculation method can be adjusted appropriately).

[0027]

[0028] Where t is a time point and i is a time index in the time series, and it is assumed that the time window is symmetric about t. If the calculation method is limited by the length of the time series, it can be adjusted appropriately.

[0029] The short-term fluctuation term is calculated as F(t) = H(t) - T(t).

[0030] 1b. Based on the data processing capabilities of the intelligent chip, the long-term trend term T(t) is linearly fitted using the least squares method. The fitted straight line equation is T(t) = kt + b, where k is the slope of the heart rate trend, reflecting the rate of change of the long-term heart rate trend. The values ​​of k and b are then determined by calculating partial derivatives to minimize the sum of squared fitting errors:

[0031]

[0032] 1c, relying on the model-building capabilities of intelligent chips, a simple time series prediction model (such as the autoregressive model AR(p)) is established based on historical heart rate data to predict the heart rate value at the current moment and calculate the deviation between the predicted value and the actual heart rate value. Taking the AR(1) model as an example, the expression for establishing the AR(1) model is as follows: ,in H(t-1) is the predicted heart rate at time t, and H(t-1) is the actual heart rate at time t-1. Parameters α and β are estimated using the least squares method based on historical data. Assume there are N pairs of historical data. To make To minimize this, take the partial derivatives of α and β with respect to 0, and solve the system of equations to obtain estimates of α and β. α is the autoregressive coefficient, reflecting the predicted heart rate at the current moment based on the actual heart rate H(t-1) from the previous moment. The degree of influence, typically ranging from -1 to 1. β is a constant, representing the baseline level of the current heart rate in the absence of influence from the previous heart rate value. It is an index variable used to iterate through all the samples. j=1,2,…,N means there are a total of N samples.

[0033] 1d, for the current time t, its heart rate prediction bias is ,in Here is the predicted heart rate at time t.

[0034] S2, based on the user's instantaneous heart rate changes, the smart chip uses a causal discovery algorithm to construct a causal model between the user and the temperature sensitivity variable.

[0035] The causal model is constructed by using the PC algorithm to treat instantaneous heart rate changes and temperature sensitivity variables as nodes in the graph, with edges connecting any two nodes to form an undirected complete graph.

[0036] S3 extracts historical moxibustion temperature setting data from the device database, and the smart chip analyzes the user's temperature setting preferences under different temperature sensitivity states.

[0037] The temperature setting data includes the preset temperature for each moxibustion session and the temperature adjustment records during the moxibustion process.

[0038] Specifically, 3a, from the device database, the smart chip filters out all the user's historical moxibustion records based on the user's unique identifier, obtains the preset temperature corresponding to each moxibustion and the temperature adjustment record during the moxibustion process, including the adjustment time point and the adjusted temperature value.

[0039] 3b. Combining the causal relationship between instantaneous heart rate changes and temperature sensitivity variables in the causal model, the smart chip sets a threshold for classifying temperature sensitivity states.

[0040] The criterion for this division could be that the slope of the heart rate trend shown by the causal model is greater than a certain value. And the absolute value of the heart rate prediction deviation is greater than a certain value. At that time, the user was in a state of high temperature sensitivity; the slope of the heart rate trend was less than ( < And the absolute value of the heart rate prediction deviation is less than ( < When the temperature is low, the user is in a low temperature sensitivity state; otherwise, the user is in a medium temperature sensitivity state. and Standard thresholds used to classify the magnitude of the slope of heart rate trends This represents the lower limit of the slope of the heart rate trend under high temperature sensitivity conditions. This represents the upper limit of the slope of the heart rate trend under low temperature sensitivity conditions. and Standard thresholds used to classify the magnitude of the absolute value of heart rate prediction bias. This represents the upper limit of the absolute value of heart rate prediction deviation under high temperature sensitivity conditions. This represents the lower limit of the absolute value of the heart rate prediction deviation under low temperature sensitivity conditions.

[0041] 3c: The system analyzes the instantaneous heart rate changes corresponding to each moxibustion record. The analysis is performed by the smart chip, which categorizes each moxibustion record into a corresponding temperature sensitivity state.

[0042] For 3 days, calculate the average value of the preset temperature for all moxibustion records under the same temperature sensitivity state.

[0043] 3e, compare the average value of the preset temperature under different temperature sensitivity states, and analyze the differences in user preference for the preset temperature under different states.

[0044] 3f, For each moxibustion record, calculate the temperature adjustment range, that is, the difference between the adjusted temperature and the preset temperature.

[0045] For example, suppose the preset temperature for a certain moxibustion recording is... The adjusted temperature is The adjustment range For all moxibustion records under the same temperature sensitivity state, calculate the average adjustment range. Taking a high temperature sensitivity state as an example, suppose there are m temperature adjustment records under this state, and the adjustment range for each instance is... The average adjustment range under high temperature sensitivity conditions 'm' represents the number of moxibustion records under the same temperature sensitivity state, used to calculate the average value of adjustment amplitude or heart rate trend slope, etc., under that state. Similarly, the average temperature sensitivity state can be calculated. and low temperature sensitivity state The average adjustment range.

[0046] 3g, statistically analyze the direction (increase or decrease) of temperature adjustment and the frequency of adjustment (the proportion of adjustment times to the total number of moxibustion times) under different temperature sensitivity states.

[0047] After 3 hours, based on the analysis results of the preset temperature preference and the temperature adjustment preference, the smart chip determines the user's preference for setting the moxibustion temperature under different temperature sensitivity states.

[0048] Among them, it is necessary to determine the user's preference for setting the moxibustion temperature under different temperature sensitivity states. That is, when the user is in a high temperature sensitivity state, they tend to set a lower preset temperature and frequently adjust the temperature. When the user is in a low temperature sensitivity state, they tend to set a higher preset temperature and make fewer temperature adjustments.

[0049] Based on the user's temperature setting preferences, S4 is divided into a basic preset temperature and a fluctuating temperature control part. The intelligent chip determines the fluctuating temperature control coefficient in different heart rate response modes according to the instantaneous heart rate changes.

[0050] The basic preset temperature is the temperature that is tended to be set under the user's physical condition and average temperature sensitivity, while the fluctuation temperature adjustment reflects the temperature adjustment caused by instantaneous heart rate changes.

[0051] Specifically, 4a establishes a mapping relationship between physical condition, average temperature sensitivity, and temperature preference based on a large amount of user data statistics and human physiological models.

[0052] 4b. Based on the user's physical condition and average temperature sensitivity, the smart chip determines the basic preset temperature through a mapping relationship. .

[0053] 4c, different heart rate response modes are divided according to different heart rate changes. The smart chip sets a corresponding range of characteristic parameters for each heart rate response mode to determine the current heart rate mode.

[0054] 4d. For different heart rate response modes, the intelligent chip establishes a mathematical model of heart rate change and fluctuation temperature regulation coefficient.

[0055] The heart rate change is the difference between the base preset temperature and the average heart rate over a period of time (defined as 3 minutes in this application, but the specific time can be set according to the actual situation).

[0056] 4e, based on the established mathematical model and the amount of heart rate change, calculate the fluctuation temperature regulation coefficient under the current heart rate response mode.

[0057] Based on the user's historical usage records, the S5 intelligent chip analyzes the user's preference for different moxibustion sites, combines instantaneous heart rate changes with moxibustion preferences, and analyzes the changes in the user's preference for moxibustion items and sites under different heart rate response modes.

[0058] The analysis of user preferences for moxibustion items and sites under different heart rate response modes involves statistically analyzing the frequency of each moxibustion site in historical records, acquiring real-time heart rate changes during moxibustion, and classifying the user's heart rate state into different response modes. For each heart rate response mode, the frequency of user selection of each site under that mode is statistically analyzed. The differences in the frequency of user selection of the same moxibustion site under different heart rate response modes are compared. If, under a certain heart rate response mode, the user's selection frequency for a particular moxibustion item or site is significantly higher than in other modes, it indicates an increased preference for that item or site under that heart rate response mode; conversely, a decreased preference indicates a weakened preference.

[0059] For example, suppose there are k heart rate response patterns, and at the kth... Under the heart rate response mode, the number of times the i-th moxibustion item is selected is In this mode, the total number of times all moxibustion items were selected was [number missing]. Then the i-th moxibustion item is in the th... Preference ratio under heart rate response pattern Calculate the change in the preference ratio for the i-th moxibustion item under different heart rate response modes, for example, compared to the low heart rate stable mode (denoted as mode 1), the... Variation under the model Similarly, for the moxibustion site, in the first... Under the heart rate response pattern, the j-th moxibustion site is treated with moxibustion the number of times. In this mode, the total number of moxibustion treatments on all moxibustion sites is [number]. Then the j-th moxibustion site is at the th Preference ratio under heart rate response pattern And calculate the change in the proportion of preference under different heart rate response patterns. .

[0060] S6 stores the table structure of the user's personalized temperature adjustment data into the smart chip. The smart chip updates the user's personalized temperature adjustment data in real time every time the user uses the moxibustion device.

[0061] The technical solutions described in the embodiments of this application have at least the following technical effects or advantages: By accurately collecting and analyzing users' heart rate data through intelligent chips, and combining it with historical data to build a predictive model, a causal model is intelligently constructed based on heart rate changes to analyze temperature sensitivity, thereby accurately grasping users' personalized preferences for moxibustion temperature and location.

[0062] Example 2: When controlling the temperature adjustment of moxibustion devices using conventional methods, fixed preset rules are mainly used to handle fluctuating temperature settings. However, the dynamic data characteristics of different users during the use of moxibustion devices vary significantly, making it difficult for a uniform temperature control strategy to accurately adapt to actual situations, resulting in insufficient accuracy and personalization in temperature adjustment. Given the historically large differences in the dynamic data characteristics and temperature adjustment effects of fluctuating temperature adjustments by different users, and the varying requirements for judging the temperature adjustment range, the following optimizations and improvements are made to refine the differentiation of moxibustion device temperature adjustments and obtain more accurate and personalized temperature adjustment effects.

[0063] In some embodiments, the fluctuation temperature regulation coefficient is determined based on the instantaneous heart rate change under different heart rate response modes. Step S4 further includes: The S41 smart chip records dynamic data in real time during the user's use of the moxibustion device. When a temperature fluctuation occurs, it records the user's dynamic data characteristics and stores them in the historical database.

[0064] The dynamic data includes moxibustion duration, preset temperature, current fluctuating temperature, and the user's heart rate sequence data.

[0065] The S42 intelligent chip associates and stores the dynamic data characteristics of the user during each temperature fluctuation adjustment with the corresponding temperature adjustment parameters, and performs retrospective analysis on the stored temperature fluctuation adjustment event data.

[0066] Specifically, 42a creates a unique identifier for each fluctuating temperature control event. The smart chip associates the user's dynamic data characteristics during fluctuating temperature control with the corresponding temperature control parameters in the form of key-value pairs.

[0067] 42b, Analyze the patterns of temperature adjustment amplitude and instantaneous heart rate changes under different combinations of user characteristics.

[0068] 42c, extract the temperature adjustment amplitude pattern and instantaneous heart rate change characteristics with similar features from the stored fluctuating temperature adjustment event data.

[0069] 42 days, the relationship between instantaneous heart rate change characteristics and temperature regulation direction, grouping according to the value range of instantaneous heart rate change characteristics, and statistically analyzing the proportion of events with different temperature regulation directions in each group for backtracking matching.

[0070] 42e, if the analysis goal is to find out the distribution of temperature adjustment range under different moxibustion durations, the smart chip divides the moxibustion duration into different intervals and statistically analyzes the temperature adjustment range within each interval.

[0071] The S43 intelligent chip uses data analysis algorithms to analyze the temperature adjustment patterns under different combinations of features based on the user dynamic data characteristics obtained from backtracking.

[0072] S44 generates corresponding progressive temperature control curves for different combinations of user characteristics based on the analysis results.

[0073] Specifically, 44a, the intelligent chip determines the parameters of the gradual temperature control curve based on the temperature adjustment pattern under different combinations of user dynamic data characteristics.

[0074] For example, if analysis reveals that when the moxibustion duration is within a certain range and the heart rate trend slope is positive, the temperature adjustment amplitude is linearly related to the moxibustion duration, then the gradual temperature control curve can be set as a linear function, and its slope and intercept parameters can be determined according to specific patterns. For different combinations of features, the corresponding curve parameters are determined in a similar manner.

[0075] 44b. During the user's current moxibustion process, the smart chip acquires the user's dynamic data features in real time, matches the current user dynamic data features with the user dynamic data features in the historical database, and finds the most similar feature combination.

[0076] 44c, the intelligent chip generates a specific gradual temperature control curve based on the gradual temperature control curve parameters corresponding to the matched feature combination, combined with the current moxibustion duration and temperature.

[0077] 44d, when the system detects that the current user has characteristics similar to those observed during historical temperature fluctuations, the smart chip performs an advance temperature transition adjustment according to the generated progressive temperature control curve.

[0078] S45, during the new moxibustion process, the smart chip matches the current user characteristics with the characteristics in the fluctuating temperature control event database, calls the corresponding gradual temperature control curve, and makes advance temperature transition adjustments in the current moxibustion stage.

[0079] The technical solutions described in the embodiments of this application have at least the following technical effects or advantages: By using a smart chip to record dynamic data of moxibustion in real time and link and store information related to temperature fluctuations, a gradual temperature control curve is generated after backtracking analysis and pattern mining. This enables precise matching and advance temperature adjustment based on the user's real-time characteristics, effectively avoiding discomfort caused by sudden temperature changes. It significantly improves the personalization and intelligence of temperature control during moxibustion, bringing users a more comfortable moxibustion experience that is more in line with their own condition.

[0080] Example 3: In Example 2, although a progressive temperature control curve could be constructed based on user dynamic data characteristics to control the temperature of the moxibustion device, this scheme treated different moxibustion sites as having the same temperature response characteristics and generated the temperature control curve in a relatively uniform way. However, different parts of the human body have significant differences in physiological structure and tissue characteristics, and their sensitivity and response to moxibustion temperature are also different. Since the temperature change characteristics and user feedback of different moxibustion sites during moxibustion have historically varied significantly, the requirements for temperature adjustment will inevitably differ. In order to make more detailed distinctions in moxibustion temperature control and obtain more accurate and personalized temperature control effects, it is necessary to consider the characteristic differences of different moxibustion sites and make targeted optimizations and improvements to the progressive temperature control curve. Therefore, Example 3 is proposed.

[0081] In some embodiments, step S45, which involves calling the corresponding progressive temperature control curve, further includes: S451, based on the temperature adjustment pattern of the initial moxibustion site under the combination of user dynamic data characteristics during the fluctuating temperature adjustment process, a model of the gradual temperature control curve of the initial moxibustion site is constructed.

[0082] The relationship between the temperature adjustment range and the moxibustion duration is as follows: assuming a linear relationship between the temperature adjustment range and the moxibustion duration t, i.e. ,in and These are coefficients to be determined. The intelligent chip collects temperature adjustment data under multiple sets of different moxibustion durations and uses the least squares method to fit the result. and The value of .

[0083] The relationship between temperature adjustment amplitude and heart rate variability is as follows: Analyze the impact of heart rate variability on temperature adjustment amplitude. Assume the heart rate variability rate... (This can be approximated by calculating the ratio of the heart rate difference between adjacent moments to the time interval.) (Heart rate sequence data) and temperature adjustment range The functional relationship is also fitted by the smart chip through data collection. and The value of .

[0084] Assuming the temperature adjustment range is a combined function of moxibustion duration and heart rate variability, i.e. To simplify the model, assume... (Here, the linear relationships obtained from the separate analyses of the relationship between temperature adjustment range and moxibustion duration and the relationship between temperature adjustment range and heart rate changes have been simply combined, and b is the constant term after the combination).

[0085] Initial moxibustion site gradual temperature control curve This can be represented as the basic preset temperature. With temperature adjustment range The sum of in , and These are coefficients obtained by the intelligent chip through data collection and fitting, reflecting the temperature adjustment pattern under the combination of user dynamic data characteristics.

[0086] S452 determines the segmentation points of the gradual temperature control curve of the initial moxibustion site based on temperature changes during moxibustion.

[0087] Specifically, 452a determines the rate of temperature change by calculating the ratio of the temperature difference between adjacent moments to the time interval.

[0088] Let T(t) be the temperature at time t, and T(t+Δt) be the temperature at time t+Δt. Then the rate of temperature change... .

[0089] 452b, the segmentation points in the moxibustion process are determined based on the temperature change rate, and each update of the temperature change rate is used as a segmentation point.

[0090] S453, determine the temperature sensitivity difference between the initial moxibustion site and other moxibustion sites, and correct the gradual temperature control curves of other moxibustion sites.

[0091] The difference in temperature sensitivity was determined by recording the time required for the skin at different locations to reach a specific temperature change during moxibustion heating. This difference in temperature sensitivity is reflected in the rate of temperature increase; if the initial temperature increase rate is... Let the rate of temperature rise in other parts after correction be... Based on the difference in temperature sensitivity, .right Integrating the data yields the corrected asymptotic temperature control curves for other components. .

[0092] S454: When it is detected that the user's dynamic data characteristics during moxibustion on other parts of the body are similar to the characteristics corresponding to historical temperature fluctuations, the temperature transition adjustment is performed in advance according to the generated gradual temperature control curve for other parts of the body.

[0093] The technical solutions described in the embodiments of this application have at least the following technical effects or advantages: By deeply analyzing the differences in temperature sensitivity between the initial treatment site and other sites during moxibustion, and combining this with dynamic user data, a progressive temperature control curve is precisely constructed and corrected. This solution can personalize and optimize temperature adjustments based on the physiological differences of different sites, making moxibustion temperature control more closely match the actual needs of users. This effectively improves the comfort and accuracy of moxibustion treatment, bringing users a higher quality and more scientific moxibustion experience.

[0094] Example 4: While Example 3 can adjust and coordinate the temperature of individual and multiple acupoints to a certain extent based on user dynamic data and site differences, this approach has limitations when dealing with group acupoint treatment. Example 3 mainly focuses on correcting the temperature curve based on real-time user dynamic data and simply considering the mutual influence of temperatures between acupoints. However, in the process of multi-acupoint synergistic treatment, the differences in the role and temperature requirements of different acupoints at different treatment stages are not fully considered, and there is a lack of systematic modeling for the dynamic balance of group acupoint temperatures. Since the temperature change patterns of each acupoint and its impact on the overall treatment effect have varied in different group acupoint treatments throughout history, the control requirements for the temperature of each acupoint will inevitably differ. In order to achieve more precise synergistic control of group acupoint temperatures and improve the effect of moxibustion treatment, it is necessary to comprehensively consider group acupoint treatment data, establish a dynamic balance model, divide treatment stages, and carry out synergistic regulation. Therefore, Example 4 is proposed.

[0095] In some embodiments, step S453, which modifies the gradual temperature control curve for other moxibustion sites, further includes: S4531 imports relevant data on acupoint treatment into the moxibustion device and analyzes the impact of temperature changes at different acupoints on other acupoints and the user's overall temperature sensitivity.

[0096] Among them, importing treatment data between acupoint groups into the moxibustion device involves importing relevant data on acupoint groups (two or more acupoints) from traditional Chinese medicine theory into the storage module of the moxibustion device. The relevant data includes user dynamic data characteristics of different moxibustion acupoints, progressive temperature control curves corrected based on user data, temperature change records, and corresponding temperature sensitivity feedback.

[0097] S4532, using system dynamics methods, establishes a dynamic equilibrium model of acupoint temperature.

[0098] Specifically, based on the principles of system dynamics, the elements (temperature of each acupoint, user temperature sensitivity, and other relevant data) and the causal relationships between these elements in the acupoint temperature system are determined. For example, an increase in the temperature of acupoint 1 may lead to an increase in the user's heart rate, thereby affecting the user's overall temperature sensitivity and thus influencing the temperature perception of other acupoints.

[0099] Construct a system dynamics model, assuming the temperature of each acupoint as a flow potential variable. (n is the number of acupoints), and the rate of temperature change is the flow rate variable. Based on causal relationships and practical physical meaning, equations are established between the variables. For example, considering heat conduction between acupoints, let u(t) be a function that includes the user's heart rate HR(t) and body surface temperature. A comprehensive vector of physiological indicators, namely , can be established , where k is the thermal conductivity correlation coefficient, and f(u(t)) is the influence function of factors such as user temperature sensitivity on the rate of temperature change of acupoint i.

[0100] S4533, based on the purpose of moxibustion at each stage, determines the target temperature range for each acupoint in the group of acupoints for each stage.

[0101] The determination of the target temperature range for each acupoint in the group is based on traditional Chinese medicine theory and rich clinical experience, clarifying the purpose of moxibustion in the preheating, treatment enhancement, and consolidation stages. The target temperature range for each acupoint in the group is determined for each stage based on its characteristics and purpose, combined with the user's individual constitution and needs.

[0102] S4534 monitors the temperature of each acupoint in the moxibustion group in real time during the moxibustion process, dividing the moxibustion treatment process into different stages.

[0103] The control system of the moxibustion device includes a stage division module that divides the moxibustion acupoint treatment process into different stages based on preset time nodes or user physiological index change thresholds.

[0104] S4535, based on the progressive temperature control curve corrected by user dynamic data, the moxibustion device coordinates the temperature of each acupoint in the group of acupoints according to real-time data and dynamic balance model at each stage.

[0105] Specifically, in conjunction with the progressive temperature control curve corrected based on user dynamic data in Example 3, at each stage, the temperature of each acupoint is monitored in real time. And a dynamic temperature balance model for acupoints is used to calculate the temperature adjustment amount for each acupoint. For example, based on the dynamic balance model and the progressive temperature control curve, if the actual temperature of a certain acupoint... If the temperature is below the lower limit of the target temperature range for this stage, calculate the required increase in temperature. Adjust the heating power of the moxibustion device to ensure the temperature of the acupoint rises at a certain rate. Considering the mutual influence between acupoints, adjust the temperature settings of other related acupoints in a coordinated manner based on a dynamic balance model. For example, when the temperature of a key acupoint is increased, adjust the temperature settings of other acupoints appropriately based on the model's calculation of the impact on their temperatures, ensuring that the overall temperature of the acupoint group is in a coordinated and effective state.

[0106] The technical solutions described in the embodiments of this application have at least the following technical effects or advantages: By importing acupoint treatment data, constructing a dynamic balance model, dividing treatment stages, and coordinating the temperature adjustment of each acupoint based on real-time data, this approach fully considers the mutual influence of temperature changes between acupoints and the differences in needs at different treatment stages. This solution can accurately adapt the appropriate temperature for each acupoint at different stages, effectively improving the targeting and synergy of moxibustion treatment, making the treatment process more in line with human physiological rhythms, thereby enhancing treatment efficacy and providing users with a more efficient and comfortable moxibustion experience.

[0107] Furthermore, this embodiment of the invention also provides a temperature control system for moxibustion devices controlled by an intelligent chip.

[0108] Figure 2 This is a schematic diagram of the structure of a temperature regulation system for a moxibustion device controlled by an intelligent chip, according to an embodiment of the present invention.

[0109] like Figure 2 As shown, a temperature control system for a moxibustion device controlled by an intelligent chip includes: a data acquisition module, a decomposition and calculation module, a preference analysis module, a temperature control module, a preference analysis module, and a data storage module.

[0110] The data acquisition module is used to collect the user's heart rate sequence during the use of the moxibustion device using a smart chip, decompose it into long-term trend terms and short-term fluctuation terms, and calculate the user's instantaneous heart rate changes. The decomposition calculation module is used to construct a causal model between the user's instantaneous heart rate change and the temperature sensitivity variable using a causal discovery algorithm. The preference analysis module is used to extract users' historical moxibustion temperature setting data from the device database, and the smart chip analyzes the user's temperature setting preferences under different temperature sensitivity states. The temperature control module is used to divide the user's temperature setting preferences into a basic preset temperature and a fluctuating temperature control part. The intelligent chip determines the fluctuating temperature control coefficient in different heart rate response modes based on the instantaneous heart rate changes. The preference analysis module is used to analyze the user's preference for different moxibustion sites based on the user's historical usage records. It combines instantaneous heart rate changes with moxibustion preferences to analyze changes in the user's preference for moxibustion items and sites under different heart rate response modes. The data storage module stores the table structure of the user's personalized temperature adjustment data into the smart chip. The smart chip updates the user's personalized temperature adjustment data in real time each time the user uses the moxibustion device.

[0111] It should be noted that other specific implementation details of the temperature adjustment system for a moxibustion device controlled by an intelligent chip according to an embodiment of the present invention can refer to the above-described method for temperature adjustment of a moxibustion device controlled by an intelligent chip.

[0112] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. For those skilled in the art, the present invention can have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for adjusting the temperature of a moxibustion device controlled by an intelligent chip, characterized in that, include: S1 uses a smart chip to collect the user's heart rate sequence during the use of the moxibustion device, decomposes it into long-term trend terms and short-term fluctuation terms, and calculates the user's instantaneous heart rate changes. S2, based on the user's instantaneous heart rate changes, the smart chip uses a causal discovery algorithm to construct a causal model between the user and the temperature sensitivity variable; S3 extracts historical moxibustion temperature setting data from the device database, and the smart chip analyzes the user's temperature setting preferences under different temperature sensitivity states. S4, based on the characteristics of user temperature setting preferences, is divided into a basic preset temperature and a fluctuating temperature regulation part. The intelligent chip determines the fluctuating temperature regulation coefficient in different heart rate response modes according to the instantaneous heart rate changes. S5, based on the user's historical usage records, the smart chip analyzes the user's preference for different moxibustion sites, combines instantaneous heart rate changes with moxibustion preferences, and analyzes the changes in the user's preference for moxibustion items and sites under different heart rate response modes; S6 stores the table structure of the user's personalized temperature adjustment data into the smart chip. The smart chip updates the user's personalized temperature adjustment data in real time every time the user uses the moxibustion device.

2. The temperature adjustment method for a moxibustion device controlled by a smart chip as described in claim 1, characterized in that, The analysis of user temperature setting preferences under different temperature sensitivity states specifically includes: From the device database, the smart chip filters all historical moxibustion records for the user based on their unique identifier, obtaining the preset temperature for each moxibustion session and temperature adjustment records during the moxibustion process, including the adjustment time and the adjusted temperature value; combining the causal relationship between instantaneous heart rate changes and temperature sensitivity variables in the causal model, the smart chip sets a threshold for classifying temperature sensitivity states; analyzing the instantaneous heart rate changes corresponding to each moxibustion record (the analysis is performed by the smart chip), classifying each moxibustion record into the corresponding temperature sensitivity state; and for all moxibustion records in the same temperature sensitivity state... The system calculates the average value of the preset temperature; compares the average value of the preset temperature under different temperature sensitivity states to analyze the user's preference for the preset temperature under different states; for each moxibustion record, it calculates the temperature adjustment range, i.e., the difference between the adjusted temperature and the preset temperature; it statistically analyzes the direction and frequency of temperature adjustment under different temperature sensitivity states; and based on the analysis results of preset temperature preference and temperature adjustment preference, the smart chip determines the user's preference for setting the moxibustion temperature under different temperature sensitivity states. The causal model is constructed using a PC algorithm, where instantaneous heart rate changes and temperature sensitivity variables are used as nodes in a graph, with edges connecting any two nodes to form an undirected complete graph.

3. The temperature adjustment method for a moxibustion device controlled by a smart chip as described in claim 2, characterized in that, The instantaneous heart rate change includes: the instantaneous heart rate change consists of the heart rate trend slope and the heart rate prediction deviation; a time window length n is set, and with the help of the computing power of the smart chip, the moving average method is used to decompose the heart rate sequence, calculate the average value of the heart rate data in each time window, and use the obtained average value sequence as the long-term trend term, while the short-term fluctuation term is obtained by subtracting the long-term trend term from the heart rate sequence; based on the data processing function of the smart chip, the least squares method is used to linearly fit the long-term trend term, and a time series prediction model is established based on historical heart rate data to predict the heart rate value at the current moment, and the deviation between the predicted value and the actual heart rate value is calculated.

4. The temperature adjustment method for a moxibustion device controlled by a smart chip as described in claim 1, characterized in that, The determination of the fluctuation temperature regulation coefficient based on instantaneous heart rate changes under different heart rate response modes specifically includes: The intelligent chip records dynamic data in real time during the user's use of the moxibustion device. When a temperature fluctuation occurs, it records the user's dynamic data characteristics and stores them in the historical database. The intelligent chip associates and stores the user's dynamic data characteristics during each temperature fluctuation with the corresponding temperature adjustment parameters, and performs retrospective analysis on the stored temperature fluctuation event data. Based on the retrospective user dynamic data characteristics, the intelligent chip uses data analysis algorithms to analyze the temperature adjustment patterns under different characteristic combinations. Based on the analysis results, it generates corresponding gradual temperature control curves for different user characteristic combinations. During a new moxibustion session, the intelligent chip matches the current user characteristics with the characteristics in the temperature fluctuation event database, calls the corresponding gradual temperature control curve, and performs advance temperature transition adjustments in the current moxibustion stage.

5. The temperature adjustment method for a moxibustion device controlled by a smart chip as described in claim 4, characterized in that, The backtracking analysis of the stored fluctuating temperature control event data specifically includes: creating a unique identifier for each fluctuating temperature control event; the smart chip associating the user's dynamic data characteristics during fluctuating temperature control with the corresponding temperature control parameters in the form of key-value pairs; analyzing the patterns of temperature adjustment amplitude and instantaneous heart rate change characteristics under different combinations of user characteristics; extracting the patterns of temperature adjustment amplitude and instantaneous heart rate change characteristics with similar features from the stored fluctuating temperature control event data; the relationship between instantaneous heart rate change characteristics and temperature control direction; grouping according to the value range of instantaneous heart rate change characteristics; and statistically matching the proportion of events with different temperature control directions in each group. If the analysis objective is to find out the distribution of temperature adjustment amplitude under different moxibustion durations, the smart chip divides the moxibustion duration into different intervals and statistically analyzes the temperature adjustment amplitude within each interval.

6. The temperature adjustment method for a moxibustion device controlled by a smart chip as described in claim 4, characterized in that, The process of generating corresponding progressive temperature control curves for different combinations of user characteristics based on the analysis results includes: the intelligent chip determining the parameters of the progressive temperature control curve based on the temperature adjustment patterns under different combinations of user dynamic data characteristics; during the user's current moxibustion process, the intelligent chip acquires the user's dynamic data characteristics in real time, matches the current user dynamic data characteristics with combinations of user dynamic data characteristics in the historical database, and finds the most similar feature combination; the intelligent chip generates a specific progressive temperature control curve based on the progressive temperature control curve parameters corresponding to the matched feature combination, combined with the current moxibustion duration and temperature; when the intelligent chip detects that the current user has characteristics similar to those observed during historical temperature fluctuations, it performs an advance temperature transition adjustment according to the generated progressive temperature control curve.

7. The temperature adjustment method for a moxibustion device controlled by a smart chip as described in claim 4, characterized in that, The process of calling the corresponding progressive temperature control curve further includes: constructing a model of the progressive temperature control curve for the initial moxibustion site based on the temperature adjustment pattern of the user's dynamic data feature combination during the fluctuating temperature adjustment process; determining the segmentation points of the progressive temperature control curve for the initial moxibustion site based on the temperature changes during moxibustion; determining the temperature sensitivity difference between the initial moxibustion site and other moxibustion sites, and correcting the progressive temperature control curves for other moxibustion sites; and when it is detected that the user's dynamic data features during moxibustion on other sites are similar to the features corresponding to historical fluctuating temperature adjustments, performing an advance temperature transition adjustment according to the generated progressive temperature control curves for other sites.

8. The temperature adjustment method for a moxibustion device controlled by a smart chip as described in claim 7, characterized in that, The model for constructing the initial moxibustion site's gradual temperature control curve specifically involves: analyzing the relationship between temperature adjustment amplitude and moxibustion duration, and the relationship between temperature adjustment amplitude and heart rate changes; determining a comprehensive function of temperature adjustment amplitude, moxibustion duration, and heart rate change rate; and determining the gradual temperature control curve based on the comprehensive function, thus setting the initial moxibustion site's gradual temperature control curve. in It is heart rate sequence data. Indicates the base preset temperature With temperature adjustment range sum , and The coefficients are obtained by combining and fitting a function.

9. The temperature adjustment method for a moxibustion device controlled by a smart chip as described in claim 7, characterized in that, The correction of the gradual temperature control curve for other moxibustion sites includes: Data related to acupoint therapy is imported into the moxibustion device to analyze the impact of temperature changes at different acupoints on other acupoints and the user's overall temperature sensitivity. A dynamic equilibrium model of acupoint temperature is established using system dynamics. Based on the purpose of moxibustion at each stage, the target temperature range for each acupoint in the acupoint group is determined for each stage. The temperature of each acupoint in the acupoint group is monitored in real time during the moxibustion process, and the acupoint therapy process is divided into different stages. Based on the progressive temperature control curve corrected by the user's dynamic data, the moxibustion device coordinates and regulates the temperature of each acupoint in the acupoint group at each stage according to real-time data and the dynamic equilibrium model.

10. A temperature control system for a moxibustion device controlled by an intelligent chip, applied to a temperature control method for a moxibustion device controlled by an intelligent chip as described in any one of claims 1 to 9, characterized in that, The system includes: The data acquisition module is used to collect the user's heart rate sequence during the use of the moxibustion device using a smart chip, decompose it into long-term trend terms and short-term fluctuation terms, and calculate the user's instantaneous heart rate changes. The decomposition calculation module is used to construct a causal model between the user's instantaneous heart rate change and the temperature sensitivity variable using a causal discovery algorithm. The preference analysis module is used to extract users' historical moxibustion temperature setting data from the device database, and the smart chip analyzes the user's temperature setting preferences under different temperature sensitivity states. The temperature control module is used to divide the user's temperature setting preferences into a basic preset temperature and a fluctuating temperature control part. The intelligent chip determines the fluctuating temperature control coefficient in different heart rate response modes based on the instantaneous heart rate changes. The preference analysis module is used to analyze the user's preference for different moxibustion sites based on the user's historical usage records. It combines instantaneous heart rate changes with moxibustion preferences to analyze changes in the user's preference for moxibustion items and sites under different heart rate response modes. The data storage module stores the table structure of the user's personalized temperature adjustment data into the smart chip. The smart chip updates the user's personalized temperature adjustment data in real time each time the user uses the moxibustion device.

Images