Respiring scheme recommendation method based on traditional Chinese medicine deficiency-excess syndrome differentiation and related equipment

Abstract

The invention provides a traditional Chinese medicine deficiency-reality syndrome differentiation-based information calling scheme recommendation method and related equipment. The method comprises the following steps of: obtaining deficiency-reality syndrome differentiation associated information of a target object; obtaining mind differentiation associated information of the target object; acquiring heart rate variability parameters of the target object; inputting the virtual and actual evaluation information, the frequency evaluation information and the heart rate variability parameters into a respiring scheme recommendation model to obtain a respiring scheme; and guiding the user to call the information according to the information calling scheme. According to the method, a traditional Chinese medicine deficiency-excess syndrome differentiation scale, a traditional Chinese medicine mind state identification scale and a modern biological feedback technology are utilized, so that the system can more comprehensively evaluate the mind state of the user, the theoretical basis of an information adjusting technology is expanded through the combination, and the two state evaluation interaction scales, HRV data and the modern information technology are combined, so that the user experience is improved. By constructing the random forest model, the problem with the maximum contribution degree in the scale can be accurately selected according to the state of the user, and the accuracy of recommendation of the respiring scheme is improved.

Description

Technical Field

[0001] The present invention relates to the field of medical care information technology, and more specifically, to a method for recommending a breathing regulation program based on deficiency-excess syndrome differentiation of traditional Chinese medicine and related equipment. Background Art

[0002] In the prior art, guiding users to perform breathing training by adjusting the breathing rhythm is a relatively common technical means. By guiding users to perform deep breathing and meditation, it can effectively reduce users' stress, improve anxiety and depression symptoms, and enhance mental health.

[0003] Traditional breathing guidance simply guides users to regulate their breathing through specific proportions. It cannot recommend breathing regulation plans tailored to users' situations. Existing breathing regulation plans rely on Western mindfulness and meditation concepts, lack the guidance of traditional Chinese medicine theory, and fail to fully utilize the unique advantages of traditional Chinese medicine in regulating breathing, calming the mind and nourishing the spirit. Summary of the invention

[0004] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a method and related equipment for recommending a breathing regimen based on TCM syndrome differentiation, so as to overcome the shortcoming of the prior art that a breathing regimen cannot be recommended according to the user's mental state.

[0005] The above technical objectives of the present invention are achieved through the following technical solutions: A method for recommending a breathing regimen based on deficiency and excess syndrome differentiation in traditional Chinese medicine, comprising:

[0006] Acquire the target object's deficiency-excess syndrome differentiation association information, and determine the deficiency-excess evaluation information to which each deficiency-excess syndrome differentiation association information belongs; acquire the target object's mind syndrome differentiation association information, and determine the frequency evaluation information to which each mind syndrome differentiation association information belongs; acquire the target object's heart rate variability parameter;

[0007] Inputting the virtual-real evaluation information, the frequency evaluation information and the heart rate variability parameter into a breathing regulation scheme recommendation model to obtain a breathing regulation scheme;

[0008] The user is guided to regulate his / her breathing according to the regulating breathing plan.

[0009] In one embodiment, the method of obtaining the virtual-real syndrome differentiation association information of the target object and determining the virtual-real evaluation information to which each virtual-real syndrome differentiation association information belongs specifically includes: using a virtual-real syndrome differentiation evaluation information question scale to interactively obtain the virtual-real syndrome differentiation association information of the target object; and judging the virtual-real syndrome differentiation association information to determine the virtual-real evaluation information to which each virtual-real syndrome differentiation association information belongs, wherein the virtual-real evaluation information includes: "virtual" items, "real" items and "normal" items.

[0010] In one embodiment, the step of obtaining the target object's mind and spirit syndrome differentiation-related information and determining the frequency evaluation information to which each piece of mind and spirit syndrome differentiation-related information belongs specifically includes: using a mind and spirit syndrome differentiation-related information question scale to interactively obtain the target object's mind and spirit syndrome differentiation-related information; and judging the mind and spirit syndrome differentiation-related information to determine the frequency evaluation information to which each piece of the TCM syndrome differentiation-related information belongs; wherein the frequency evaluation information specifically includes: a first occurrence frequency, a second occurrence frequency, a third occurrence frequency, a fourth occurrence frequency, and a fifth occurrence frequency.

[0011] In one embodiment, obtaining the heart rate variability parameters of the target object specifically includes: obtaining heart rate interval data of the target object; performing time domain analysis, frequency domain analysis and nonlinear analysis on the heart rate interval data to obtain the heart rate variability parameters of the target object.

[0012] In one embodiment, the breathing regulation scheme specifically includes a breathing regulation duration and a breathing ratio; wherein the breathing regulation duration includes 8 seconds, 9 seconds and 10 seconds; the breathing ratio specifically includes: the ratio of exhalation duration to inhalation duration is 4:6; the ratio of exhalation duration to inhalation duration is 5:5; the ratio of exhalation duration to inhalation duration is 6:4.

[0013] In one embodiment, the method further includes: in the process of guiding the user to regulate breathing according to the breathing regulation scheme, real-time monitoring of the user's heart rate variability parameters, and judging the user's breathing regulation effect based on the user's heart rate variability parameters.

[0014] In one embodiment, the breathing scheme recommendation model is specifically a random forest model.

[0015] A breathing plan recommendation device based on deficiency and excess syndrome differentiation of traditional Chinese medicine, comprising:

[0016] an acquisition unit, used to acquire the target object's deficiency-excess syndrome differentiation association information, and determine the deficiency-excess evaluation information to which each deficiency-excess syndrome differentiation association information belongs; acquire the target object's mind syndrome differentiation association information, and determine the frequency evaluation information to which each mind syndrome differentiation association information belongs; acquire the target object's heart rate variability parameter;

[0017] A recommendation unit, configured to input the virtual-real evaluation information, the frequency evaluation information, and the heart rate variability parameter into a breathing adjustment program recommendation model to obtain a breathing adjustment program;

[0018] A guiding unit is used to guide the user to regulate breathing according to the breathing regulation scheme.

[0019] A computer-readable storage medium stores a computer program, which implements the steps of the above method when executed by a processor.

[0020] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0021] In summary, the present invention has the following beneficial effects: a method for recommending a breathing regulation scheme based on deficiency and excess syndrome differentiation in traditional Chinese medicine, comprising: obtaining deficiency and excess syndrome differentiation association information of a target object, and determining deficiency and excess evaluation information to which each deficiency and excess syndrome differentiation association information belongs; obtaining mind and spirit syndrome differentiation association information of the target object, and determining frequency evaluation information to which each mind and spirit syndrome differentiation association information belongs; obtaining the heart rate variability parameters of the target object; inputting the deficiency and excess evaluation information, the frequency evaluation information and the heart rate variability parameters into a breathing regulation scheme recommendation model to obtain a breathing regulation scheme; and guiding the user to regulate his / her breathing according to the breathing regulation scheme. The present invention utilizes the Traditional Chinese Medicine mental state identification scale and modern biofeedback technology, so that the system can more comprehensively evaluate the user's mental state. This combination breaks the traditional Western meditation and mindfulness concepts, expands the theoretical basis of breathing techniques, and provides a personalized health management plan that is more in line with the traditional Chinese medicine. And through the combination of the deficiency and excess syndrome differentiation scale, HRV data and the Traditional Chinese Medicine mental state identification scale, this application combines two state evaluation interaction scales, HRV data and modern information technology. By constructing a random forest model, it can accurately select the question with the greatest contribution in the scale according to the user's state, thereby improving the accuracy of breathing plan recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of the method for recommending a breathing regulation scheme based on TCM deficiency and excess syndrome differentiation of the present invention;

[0023] Figure 2 It is a structural diagram of the breathing scheme recommendation device based on TCM deficiency and excess syndrome differentiation of the present invention;

[0024] Figure 3 is an internal structure diagram of a computer device in an embodiment of the present invention;

[0025] Figure 4 To express the intention of distinguishing between deficiency and excess;

[0026] Figure 5 It is intended to express the mind recognition quantity of traditional Chinese medicine;

[0027] Figure 6 This is a schematic diagram of the scale norm data;

[0028] Figure 7 A standard table for identifying male mental states;

[0029] Figure 8 A standard table for identifying female mental states;

[0030] Fig. 9is a schematic diagram of an additional feature set for HRV parameters;

[0031] In the figure: 1. Acquisition unit; 2. Recommendation unit; 3. Guidance unit. DETAILED DESCRIPTION

[0032] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings. Several embodiments of the present invention are shown in the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein.

[0033] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. The terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0034] In the present invention, unless otherwise clearly specified and limited, the first feature being "above" or "below" the second feature may include the first and second features being in direct contact, or may include the first and second features being in contact not directly but through another feature between them. Moreover, the first feature being "above", "above" and "above" the second feature includes the first feature being directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. The first feature being "below", "below" and "below" the second feature includes the first feature being directly below and obliquely below the second feature, or simply indicates that the first feature is lower in level than the second feature. The terms "vertical", "horizontal", "left", "right", "above", "below" and similar expressions are for illustrative purposes only, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0035] Embodiment 1

[0036] In order to solve the above problems, the present invention provides a method for recommending a breathing regimen based on TCM deficiency and excess syndrome differentiation, such as Figure 1 As shown, including:

[0037] Acquire the target object's deficiency-excess syndrome differentiation association information, and determine the deficiency-excess evaluation information to which each deficiency-excess syndrome differentiation association information belongs; acquire the target object's mind syndrome differentiation association information, and determine the frequency evaluation information to which each mind syndrome differentiation association information belongs; acquire the target object's heart rate variability parameter;

[0038] Inputting the virtual-real evaluation information, the frequency evaluation information and the heart rate variability parameter into a breathing regulation scheme recommendation model to obtain a breathing regulation scheme;

[0039] The user is guided to regulate his / her breathing according to the regulating breathing plan.

[0040] In actual applications, based on the target object's virtual and real syndrome correlation information, the user's virtual and real situation can be judged, and based on the mind-spirit syndrome correlation relationship, the target object's mind-spirit situation can be determined and judged. Then, based on the user's HRV data (Heart Rate Variability, heart rate variability parameter), all three data are input into the pre-trained program recommendation model. Based on the user's current situation, a suitable breathing program can be recommended to the user, and finally the user can be guided to breathe according to the breathing program. The breathing guidance process can adopt a variety of guidance methods such as bracelet vibration and audio feedback, which increases the scope of application of the program and improves the user's experience.

[0041] In this application, the recommendation of breathing regimen uniquely combines the mind theory of traditional Chinese medicine, and uses the traditional Chinese medicine mind state identification scale and modern biofeedback technology to enable the system to more comprehensively evaluate the user's mind state. This combination breaks the traditional Western meditation and mindfulness concepts, expands the theoretical basis of breathing regulation technology, and provides a personalized health management plan that is more in line with the Chinese cultural background.

[0042] In one embodiment, the method of obtaining the virtual-real syndrome differentiation association information of the target object and determining the virtual-real evaluation information to which each virtual-real syndrome differentiation association information belongs specifically includes: using a virtual-real syndrome differentiation evaluation information question scale to interactively obtain the virtual-real syndrome differentiation association information of the target object; and judging the virtual-real syndrome differentiation association information to determine the virtual-real evaluation information to which each virtual-real syndrome differentiation association information belongs, wherein the virtual-real evaluation information includes: "virtual" items, "real" items and "normal" items.

[0043] In practical applications, such as Figure 4As shown, it is a scale used in this application to obtain the target object's deficiency and excess syndrome differentiation association information, wherein the deficiency and excess syndrome differentiation association information is each indicator in the scale, and the deficiency and excess evaluation information is the three categories to which the options in the scale belong, including "deficiency", "excess" and "normal". Based on the deficiency and excess syndrome differentiation scale, the deficiency and excess of the target user can be judged, and the specific judgment criteria are as follows: Each item in the deficiency and excess syndrome differentiation scale corresponds to one point, ① if the cumulative score of "deficiency" syndrome is ≥2 points and greater than the excess syndrome score, it is diagnosed as "partial deficiency"; ② if the cumulative score of "excess" syndrome is ≥2 points and greater than the deficiency syndrome score, it is diagnosed as "partial excess"; ③ if the scores of "deficiency" and "excess" are both ≥2 points and the scores are equal, it is diagnosed as "mixed deficiency and excess"; ④ if the scores of "deficiency" and "excess" are both <2 points, it is diagnosed as "normal". In addition, the criteria for identifying mild, moderate and severe degrees are as follows: ① Mild: The score for "deficiency" or "excess" is 2-4 points; ② Moderate: The score for "deficiency" or "excess" is 5-7 points; ③ Severe: The score for "deficiency" or "excess" is 8-10 points.

[0044] In one embodiment, the step of obtaining the target object's mind and spirit syndrome differentiation-related information and determining the frequency evaluation information to which each piece of mind and spirit syndrome differentiation-related information belongs specifically includes: using a mind and spirit syndrome differentiation-related information question scale to interactively obtain the target object's mind and spirit syndrome differentiation-related information; and judging the mind and spirit syndrome differentiation-related information to determine the frequency evaluation information to which each piece of the TCM syndrome differentiation-related information belongs; wherein the frequency evaluation information specifically includes: a first occurrence frequency, a second occurrence frequency, a third occurrence frequency, a fourth occurrence frequency, and a fifth occurrence frequency.

[0045] In practical applications, such as Figure 5As shown in the figure, it is a scale used in this application to obtain the virtual and real syndrome differentiation association information of the target object. The questions in the mental state identification scale include four dimensions, each of which contains two or three aspects. Among them, the mental state dimension specifically includes cognitive dimension, emotional dimension, physical and mental dimension and will dimension. The cognitive dimension specifically includes: attention aspect and memory aspect; the emotional dimension specifically includes: anger aspect, depression aspect and anxiety aspect; the physical and mental dimension specifically includes: sleep aspect and fatigue aspect; the will dimension specifically includes: insufficient decision aspect and insufficient resilience aspect. According to the following rules, the individual's options are converted into scores: "almost never happen" = 0; "occasionally happen" = 1; "occur in about half of the days" = 2; "frequently happen" = 3; "almost every day" = 4. And calculate the average score of each aspect. Add the rough scores of all aspects of the dimension and take the average value. For example, if the average scores (i.e., rough scores) of individual A in the three aspects of "anger", "depression" and "anxiety" are 1, 2, and 3 respectively, then its rough score in the "emotion" dimension is (1+2+3) / 3 = 2. The rough scores of the four dimensions are added together to obtain the average value to get the total rough score of the scale. Since the calculated rough score is difficult to express the user's status, it is necessary to use the status of ordinary people as a reference standard to convert the rough score into a standard score, as follows:

[0047] Among them, Z i represents the standard score of the i-th mental state dimension; A i represents the cumulative score of the i-th mental state dimension; M i represents the normative mean score of the i-th mental state dimension; SD i represents the norm standard deviation of the i-th dimension. Figure 6 As shown, the norm refers to the standard distribution data obtained in a representative sample, which provides a reference standard for interpreting individual measurement results. In the present application, the norm is a set of data that represents the composition of the standard sample, which includes the mean and standard deviation of the standard sample. We can judge the position of the individual in the standard sample based on the norm. The user's standard score is calculated based on the mean score and standard deviation in the norm, that is, the difference between the user's actual score and the mean score divided by the standard deviation. Its meaning represents a quantitative number of the relative position of the user's actual score in a group, that is, the status of the user compared to the norm. The closer the user is to the norm, the relatively normal the user is, and the farther the user is from the norm, the more serious the abnormal status of the user is. As Figure 7 , Figure 8As shown, due to the differences in the mental states of men and women, different norms need to be provided for users of different genders according to their gender. And in the subsequent score intervals, there will also be corresponding differences due to gender differences. Since the standard score has many decimal places and is not easy to interpret and compare, and does not conform to people's daily score intuition, this application further proposes a score conversion method to convert the standard score into an interpretable score, specifically including:

[0048] T i =10×Z i +50,i∈(1,4);

[0049] Among them, T i represents the interpretable score of the i-th mental state dimension, Z i Represents the standard score of the i-th mental state dimension. And based on the interpretable score, the score is converted into a percentage system, and the score is converted into a high-to-low arrangement, that is, the higher the score, the more stable the mental state, and the lower the score, the more unstable the mental state, specifically including:

[0050]

[0051] Among them, x max Indicates the upper limit of the score range, which is 100 points, x min represents the lower limit of the score range, which is 0. The final mental score corresponds to the mental score of each dimension; that is, Q i There are four in total, corresponding to the cognitive dimension, emotional dimension, physical and mental dimension, and will dimension, and a mind score is obtained in each dimension.

[0052] In one embodiment, obtaining the heart rate variability parameters of the target object specifically includes: obtaining heart rate interval data of the target object; performing time domain analysis, frequency domain analysis and nonlinear analysis on the heart rate interval data to obtain the heart rate variability parameters of the target object.

[0053] In practical applications, the target's heart rate interval data, specifically the RR interval or NN interval data of the user, is collected, and time domain analysis is performed on the heart rate interval data to obtain the target object's heart rate variability parameters such as SDNN (standard deviation of NN intervals), RMSSD (square root mean of adjacent normal RR interval differences), PNN50 (percentage of NN intervals>50ms), and NN50 (number of times the adjacent normal RR interval difference exceeds 50ms). The heart rate interval data is analyzed in the time domain. The RR interval signal is subjected to Fourier transform or wavelet transform to analyze the energy distribution of the signal in different frequency bands, mainly including: VLF (Very Low Frequency, the frequency range is usually 0.0033-0.04Hz), LF (Low Frequency, the frequency range is usually 0.04-0.15Hz), HF (High Frequency, the frequency range is usually 0.15-0.4Hz), LF / HF ratio: the ratio of low frequency to high frequency, which is often used to evaluate the balance of sympathetic and parasympathetic nerve activity. Nonlinear analysis of heart rate interval data can obtain nonlinear parameters of the heart, including: Poincaré plot (Poincaré Plot uses continuous RR intervals as two-dimensional coordinate points to reflect the dispersion characteristics of heart rhythm), DFA (Detrended Fluctuation Analysis, an algorithm for analyzing long-range correlations, which can detect the self-similarity and fractal dimension of heart rate variability), and SampEn (Sample Entropy, which is used to measure the complexity and randomness of time series).

[0054] In this application, HRV is used to monitor the user's physiological state in real time, especially the user's mental state (emotion, spirit, stress level, etc.). Through the analysis of HRV, the system can evaluate the user's current mental state, and combine it with the TCM mental state identification scale to form a more comprehensive evaluation result. This evaluation provides physiological data support for the subsequent recommendation of personalized breathing plan.

[0055] In one embodiment, the breathing regulation scheme specifically includes a breathing regulation duration and a breathing ratio; wherein the breathing regulation duration includes 8 seconds, 9 seconds and 10 seconds; the breathing ratio specifically includes: the ratio of exhalation duration to inhalation duration is 4:6; the ratio of exhalation duration to inhalation duration is 5:5; the ratio of exhalation duration to inhalation duration is 6:4.

[0056] In practice, extending the length of breathing can activate the parasympathetic nervous system, promote relaxation and recovery of the body, help reduce stress and relieve anxiety. The parasympathetic nervous system dominates the "rest and digest" response, and extending exhalation can slow the heart rate and bring a relaxing effect. The duration and proportion of exhalation are closely related to the overall breathing rhythm in breathing. A slower and controlled breathing rhythm can bring a stronger relaxation effect, especially when the exhalation time is longer, the depth of breathing will also increase, which helps to improve the efficiency of oxygen exchange in the lungs and further enhance the relaxation effect. In traditional Chinese medicine theory, the balance between exhalation and inhalation is not only a physiological regulation, but also involves the movement of qi. Adjusting the duration and proportion of exhalation is believed to help adjust the flow of qi in the body in traditional Chinese medicine breathing. Longer exhalation time can be seen as expelling "turbid qi" from the body, which helps to clear negative emotions and bad qi, thereby improving the mental state and enhancing the conditioning effect of the mind. Longer exhalation will lead to higher HRV, indicating that the body is in a more relaxed state. Higher HRV is associated with better heart health, lower stress levels and better mental state.

[0057] In one embodiment, the method further includes: in the process of guiding the user to regulate breathing according to the breathing regulation scheme, real-time monitoring of the user's heart rate variability parameters, and judging the user's breathing regulation effect based on the user's heart rate variability parameters.

[0058] In practical applications, in order to judge the effect of breathing regulation, the user's heart rate variability parameters are continuously measured during the user's breathing regulation process, and the present application further constructs a mind index so that the user can intuitively understand the effect of breathing regulation. The algorithm evaluates the user's mind state in two dimensions: breathing regulation effect evaluation and breathing regulation concentration evaluation. The specific algorithm is as follows: The steps for calculating the mind index are:

[0059] (a) Define the frequency interval for calculating the mind index: f i =0.015Hz; Specifically, in heart rate variability analysis, HRV signals are usually converted into signals in the frequency domain through fast Fourier transform (FFT) or other spectrum analysis methods. In the frequency domain, frequency intervals refer to different frequency bands and are expressed in Hertz (Hz).

[0060] (b) Find [f l ,f h ]The maximum power spectral density value within the frequency range: P m =max(F),F∈[f l ,f h ]; where f l and f h They represent the minimum frequency point and the maximum frequency point in the frequency domain respectively.

[0061] (c) Calculate the frequency range of the mind index: F L =P m -f i , F H =P m +f i The frequency range of the mind index refers to the frequency range centered on the maximum power spectrum density value and defined by the frequency interval of the mind index.

[0062] (d) Calculate the numerator and denominator of the mind index:

[0063] (e) Mind index:

[0064] The concentration of breathing is obtained by comparing the heart rate variability of the current breathing with the user's standard waveform. The standard waveform is obtained by inverse Fourier transforming the standard heart rate variability of the breathing practitioner. The calculation steps are as follows:

[0065] (a) Performing Fourier transform on the user's standard heart rate variability data to obtain a frequency vector F and a spectrum S;

[0066] (b) Extract the spectrum data in the range of 0.04-0.26 Hz: F S With S s ;

[0067] (c) Find the maximum peak value A within this range m and its frequency f m ;

[0068] (d) The frequency range of the 0.03 Hz window is selected with the maximum peak frequency as the center;

[0069] (e) Create a complex zero vector of the same size as the original spectrum and fill it with the selected window spectrum;

[0070] (f) Perform inverse Fourier transform on the spectrum to obtain the time domain signal S C ;

[0071] (g) Calculate the correlation between the current breathing HRV signal and the standard signal, i.e., the breathing concentration:

[0072] C S =0.5×(f c (s n ,s c )+1);

[0073] in:

[0074]

[0075] The final evaluation result is determined by the Mind Index I s and Pranayama Concentration Index C S Weighted, including:

[0076] Mind Index I s Logarithmic normalization is performed to avoid the mental index I s Breathing concentration index C S The order of magnitude difference between them is too large. M Is the reasonable upper limit of the mind index:

[0077]

[0078] The normalized mind index and breathing concentration are weighted to obtain the comprehensive evaluation effect I:

[0079] I=ρL s +(1-ρ)C s ;

[0080] Among them, ρ is the adjustment coefficient, ρ=0.75.

[0081] Effect feedback: Provide real-time feedback to users through wristbands or mobile devices to help users understand the effect of breathing exercises and adjust their practice plans.

[0082] In one embodiment, the breathing scheme recommendation model is specifically a random forest model.

[0083] Furthermore, the present application also provides a training method for the random forest model, so that the random forest model can recommend a breathing plan according to the input options of the deficiency-excess syndrome differentiation scale, the options of the mind identification scale, and the HRV parameters of the target object. The specific training steps are as follows:

[0084] In this application, the training of the random forest model adopts a greedy algorithm, with the age of the target object and the options in the virtual and real syndrome differentiation scale as the basic feature set. On the basis of the basic feature set, the options of the mind recognition scale and the HRV parameters are set as additional feature sets. In the first round of training, each additional feature is combined with the basic feature set on the basis of the basic feature set, and the accuracy of the scheme recommended by the group of features is judged to select a first additional feature from the additional feature set that can make the performance of the random forest model the best. In the second round of training, on the basis of the basic feature set and the first additional feature, a second additional feature that can make the performance of the random forest model better and maximize the performance parameters is selected from the remaining additional feature sets. In the third round of training, on the basis of the basic feature set, the first additional feature and the second additional feature, a third additional feature that can make the performance of the random forest model better and maximize the performance parameters is selected from the additional feature set. And so on, until the number of additional features meets the predetermined number requirements, or the number of training rounds reaches the predetermined maximum number of rounds, to avoid infinite repetition of the training process and waste of computing resources.

[0085] Based on the above training process, the present application can select several features that are most influential in recommending breathing control plans from a number of features, so that the breathing control model can be more suitable for most people and make the model more universal. In addition, based on the above training process, it can be seen that not all questions in the scale have an impact on the recommendation of breathing control plans, but only the questions in the basic feature set (that is, the questions in the virtual and real syndrome differentiation scale) and some additional features in the selected additional feature set will contribute to the recommendation of breathing control plans.

[0086] Regarding HRV parameter characteristics, such as Fig. 9 As shown, the figure lists all the additional features that may affect the recommendation of the breathing plan and the corresponding meaning of the feature.

[0087] In this embodiment, the additional effective feature screening results are as follows: ['fear of difficulty', 'poor sleep quality', 'Time Doamin-SDNNi', 'Freq Domain: peak-VLF', 'Freq Domain: peak-HF', 'Time Freq: aVLF', 'Time Freq: aLF',]. The HRV parameter features in this result correspond to Fig. 9 Features 5, 13, 15, 16 and 17.

[0088] Based on the above additional effective features, the final performance indicators of the breathing plan recommendation model are: accuracy: 88.89%, precision: 90.28, recall: 88.89, and F1 value 88.73.

[0089] Furthermore, the present application also provides a performance evaluation method for a model, and obtains a group of experimenters. The more experimenters there are, the more representative the summarized results are. First, it is necessary to determine the performance of the basic feature set, that is, to let the random forest model recommend breathing schemes for all experimenters with the support of the basic feature set, and judge whether the breathing scheme is effective for the user based on the experimenter's HRV data, and count the accuracy of the breathing schemes of all experimenters, and finally obtain the first performance of the model with the support of the basic feature set. Then in the first round of training, each additional feature is combined with the basic feature set, and based on this combination, a breathing scheme is recommended for the experimenter, and the breathing scheme is judged according to the experimenter's HRV data. Whether the breathing scheme is effective for the user, and the accuracy of the breathing schemes of all experimenters is counted, and finally the second performance of the model is obtained with the support of the basic feature set and an additional feature, and the additional feature with the best performance is selected from many additional performances. In the second round of training, each additional feature from the remaining additional feature set is combined with the basic feature set and the additional features selected in the first round to calculate the third performance. Since the greedy algorithm is used in this application, only one additional feature with the best performance is selected each time, regardless of whether the combined performance can reach the maximum. By collecting the experimenter's breathing data, the performance of the model can be evaluated. The specific evaluation parameters include the following:

[0090] Definition of accuracy: refers to the ratio of the number of samples predicted correctly by the model to the total number of samples; calculation method:

[0091]

[0092] Definition of precision: refers to the proportion of samples predicted by the model as positive examples that are actually positive examples; calculation method:

[0093]

[0094] Definition of recall rate: refers to the proportion of samples that are actually positive examples that are correctly predicted as positive examples by the model; calculation method:

[0095]

[0096] F1 value definition: the harmonic mean of precision and recall, which takes these two indicators into consideration; calculation method:

[0097]

[0098] Among them, TP (True Positive): the number of positive examples that are actually positive and correctly predicted by the model. TN (True Negative): the number of negative examples that are actually negative and correctly predicted by the model. FP (False Positive): the number of negative examples that are actually negative but are incorrectly predicted as positive by the model (false positive). FN (False Negative): the number of positive examples that are actually positive but are incorrectly predicted as negative by the model (false negative).

[0099] Embodiment 2

[0100] See also Figure 2 , a breathing scheme recommendation device based on TCM deficiency and excess differentiation, the breathing scheme recommendation device based on TCM deficiency and excess differentiation comprising:

[0101] an acquisition unit, used to acquire the target object's deficiency-excess syndrome differentiation association information, and determine the deficiency-excess evaluation information to which each deficiency-excess syndrome differentiation association information belongs; acquire the target object's mind syndrome differentiation association information, and determine the frequency evaluation information to which each mind syndrome differentiation association information belongs; acquire the target object's heart rate variability parameter;

[0102] A recommendation unit, configured to input the virtual-real evaluation information, the frequency evaluation information, and the heart rate variability parameter into a breathing adjustment program recommendation model to obtain a breathing adjustment program;

[0103] A guiding unit is used to guide the user to regulate breathing according to the breathing regulation scheme.

[0104] Regarding the specific limitations of the breathing regulation scheme recommendation device based on TCM deficiency and excess differentiation, please refer to the limitations of the breathing regulation scheme recommendation method based on TCM deficiency and excess differentiation in the above text, which will not be repeated here. Each module in the above-mentioned breathing regulation scheme recommendation device based on TCM deficiency and excess differentiation can be fully or partially implemented by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0105] Those skilled in the art will understand that Figure 2 The structure shown in the figure is only a block diagram of a part of the structure related to the present application scheme, and does not constitute a limitation of the present application scheme. The specific breathing scheme recommendation device based on TCM deficiency and excess syndrome differentiation may include more or less components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0106] Embodiment 3

[0107] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method for recommending a breathing regimen based on TCM deficiency-excess syndrome differentiation as described in Example 1.

[0108] Embodiment 4

[0109] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. When the computer program is executed by the processor, a method for recommending a breathing plan based on TCM deficiency and excess syndrome differentiation is implemented.

[0110] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0111] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0112] Acquire the target object's deficiency-excess syndrome differentiation association information, and determine the deficiency-excess evaluation information to which each deficiency-excess syndrome differentiation association information belongs; acquire the target object's mind syndrome differentiation association information, and determine the frequency evaluation information to which each mind syndrome differentiation association information belongs; acquire the target object's heart rate variability parameter;

[0113] Inputting the virtual-real evaluation information, the frequency evaluation information and the heart rate variability parameter into a breathing regulation scheme recommendation model to obtain a breathing regulation scheme;

[0114] The user is guided to regulate his / her breathing according to the regulating breathing plan.

[0115] In one embodiment, the method of obtaining the virtual-real syndrome differentiation association information of the target object and determining the virtual-real evaluation information to which each virtual-real syndrome differentiation association information belongs specifically includes: using a virtual-real syndrome differentiation evaluation information question scale to interactively obtain the virtual-real syndrome differentiation association information of the target object; and judging the virtual-real syndrome differentiation association information to determine the virtual-real evaluation information to which each virtual-real syndrome differentiation association information belongs, wherein the virtual-real evaluation information includes: "virtual" items, "real" items and "normal" items.

[0116] In one embodiment, the step of obtaining the target object's mind and spirit syndrome differentiation-related information and determining the frequency evaluation information to which each piece of mind and spirit syndrome differentiation-related information belongs specifically includes: using a mind and spirit syndrome differentiation-related information question scale to interactively obtain the target object's mind and spirit syndrome differentiation-related information; and judging the mind and spirit syndrome differentiation-related information to determine the frequency evaluation information to which each piece of the TCM syndrome differentiation-related information belongs; wherein the frequency evaluation information specifically includes: a first occurrence frequency, a second occurrence frequency, a third occurrence frequency, a fourth occurrence frequency, and a fifth occurrence frequency.

[0117] In one embodiment, obtaining the heart rate variability parameters of the target object specifically includes: obtaining heart rate interval data of the target object; performing time domain analysis, frequency domain analysis and nonlinear analysis on the heart rate interval data to obtain the heart rate variability parameters of the target object.

[0118] In one embodiment, the breathing regulation scheme specifically includes a breathing regulation duration and a breathing ratio; wherein the breathing regulation duration includes 8 seconds, 9 seconds and 10 seconds; the breathing ratio specifically includes: the ratio of exhalation duration to inhalation duration is 4:6; the ratio of exhalation duration to inhalation duration is 5:5; the ratio of exhalation duration to inhalation duration is 6:4.

[0119] In one embodiment, the method further includes: in the process of guiding the user to regulate breathing according to the breathing regulation scheme, real-time monitoring of the user's heart rate variability parameters, and judging the user's breathing regulation effect based on the user's heart rate variability parameters.

[0120] In one embodiment, the breathing scheme recommendation model is specifically a random forest model.

[0121] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0122] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0123] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A method for recommending a breathing regimen based on TCM deficiency and excess syndrome differentiation, characterized in that: include: Obtaining the virtual-real syndrome differentiation association information of the target object, and determining the virtual-real syndrome differentiation association information to which each virtual-real syndrome differentiation association information belongs; Obtaining the target object's mind syndrome differentiation-related information, and determining the frequency evaluation information to which each mind syndrome differentiation-related information belongs; obtaining the target object's heart rate variability parameter; Inputting the virtual-real evaluation information, the frequency evaluation information and the heart rate variability parameter into a breathing regulation scheme recommendation model to obtain a breathing regulation scheme; The user is guided to regulate his / her breathing according to the regulating breathing plan.

2. The method for recommending a breathing regimen based on TCM deficiency and excess syndrome differentiation according to claim 1, characterized in that: The method of obtaining the virtual-real syndrome differentiation association information of the target object and determining the virtual-real syndrome differentiation association information to which each virtual-real syndrome differentiation association information belongs specifically includes: using a virtual-real syndrome differentiation evaluation information question scale to interactively obtain the virtual-real syndrome differentiation association information of the target object; and judging the virtual-real syndrome differentiation association information to determine the virtual-real syndrome differentiation association information to which each virtual-real syndrome differentiation association information belongs, wherein the virtual-real syndrome differentiation association information includes: "virtual" items, "real" items and "normal" items.

3. The method for recommending a breathing regimen based on TCM deficiency and excess syndrome differentiation according to claim 1, characterized in that: The method of obtaining the target object's mind and spirit syndrome differentiation-related information and determining the frequency evaluation information to which each piece of mind and spirit syndrome differentiation-related information belongs specifically includes: using a mind and spirit syndrome differentiation-related information question scale to interactively obtain the target object's mind and spirit syndrome differentiation-related information; and judging the mind and spirit syndrome differentiation-related information to determine the frequency evaluation information to which each piece of the TCM syndrome differentiation-related information belongs; wherein the frequency evaluation information specifically includes: a first occurrence frequency, a second occurrence frequency, a third occurrence frequency, a fourth occurrence frequency, and a fifth occurrence frequency.

4. The method for recommending a breathing regimen based on TCM deficiency and excess syndrome differentiation according to claim 1, characterized in that: The step of obtaining the heart rate variability parameter of the target object specifically includes: Get the heartbeat interval data of the target object; The heart rate variability parameters of the target object are obtained by performing time domain analysis, frequency domain analysis and nonlinear analysis on the heart rate interval data.

5. The method for recommending a breathing regimen based on TCM deficiency and excess syndrome differentiation according to claim 1, characterized in that: The breathing regulation scheme specifically includes a breathing regulation duration and a breathing ratio; wherein the breathing regulation duration includes 8 seconds, 9 seconds and 10 seconds; the breathing ratio specifically includes: the ratio of exhalation duration to inhalation duration is 4:6; the ratio of exhalation duration to inhalation duration is 5:5; the ratio of exhalation duration to inhalation duration is 6:

4.

6. The method for recommending a breathing regimen based on TCM deficiency and excess syndrome differentiation according to claim 1, characterized in that: The method further includes: in the process of guiding the user to regulate breathing according to the breathing regulation scheme, real-time monitoring of the user's heart rate variability parameters, and judging the user's breathing regulation effect based on the user's heart rate variability parameters.

7. The method for recommending a breathing regimen based on TCM deficiency and excess syndrome differentiation according to claim 1, characterized in that: The breathing scheme recommendation model is specifically a random forest model.

8. A breathing plan recommendation device based on TCM deficiency and excess differentiation, characterized in that: The breathing regulation scheme recommendation device based on TCM deficiency and excess syndrome differentiation comprises: an acquisition unit, used to acquire the target object's deficiency-excess syndrome differentiation association information, and determine the deficiency-excess evaluation information to which each deficiency-excess syndrome differentiation association information belongs; acquire the target object's mind syndrome differentiation association information, and determine the frequency evaluation information to which each mind syndrome differentiation association information belongs; acquire the target object's heart rate variability parameter; A recommendation unit, configured to input the virtual-real evaluation information, the frequency evaluation information, and the heart rate variability parameter into a breathing adjustment program recommendation model to obtain a breathing adjustment program; A guiding unit is used to guide the user to regulate breathing according to the breathing regulation scheme.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for recommending a breathing plan based on deficiency-excess syndrome differentiation in traditional Chinese medicine as described in any one of claims 1 to 7 is implemented.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the method for recommending a breathing plan based on TCM deficiency-excess syndrome differentiation as described in any one of claims 1 to 7 is implemented.

Images