PPG signal feature-based traditional Chinese medicine deficiency and excess analysis method and device and electronic equipment

Abstract

The invention relates to the field of machine learning, in particular to a traditional Chinese medicine virtual-real analysis method and device based on PPG signal characteristics and electronic equipment. Comprising the steps of obtaining a PPG signal, analyzing the PPG signal, extracting target feature information which comprises harmonic feature information, obtaining a quantitative label of traditional Chinese medicine diagnosis information, and analyzing the target feature information according to the quantitative label to obtain a traditional Chinese medicine virtuality and reality analysis result. According to the method, the association between PPG signal characteristics and traditional Chinese medicine viscera and meridian and collateral deficiency and excess states is automatically learned through machine learning, automation and intelligentization of traditional Chinese medicine diagnosis are achieved, and personalized traditional Chinese medicine diagnosis and health management suggestions are provided for users.

Description

Technical Field

[0001] The present application relates to the field of machine learning, and in particular to a method, device and electronic device for TCM deficiency and excess analysis based on PPG signal features. Background Art

[0002] Existing PPG signal analysis methods mainly focus on monitoring basic vital signs, such as heart rate and blood oxygen saturation. These methods usually obtain data through simple waveform analysis or basic frequency domain analysis. However, there is little research on the complex information contained in PPG signals, especially the harmonic components. These harmonic components may carry rich physiological and pathological information, including hemodynamic characteristics and microcirculatory status.

[0003] Current technology fails to fully utilize this harmonic information, which is mainly reflected in the following aspects:

[0004] Lack of in-depth harmonic analysis: Most existing technologies remain at the analysis level based on DC components or fundamental frequencies (such as heart rate), and have limited ability to analyze and interpret higher-order harmonics. This limits the understanding and application of complex physiological processes in PPG signals.

[0005] No association model with TCM diagnosis has been established: Although TCM diagnosis emphasizes integrity and complexity, such as the deficiency and excess symptoms of the five internal organs, the existing PPG analysis method does not attempt to associate harmonic analysis with these TCM diagnostic indicators. The lack of a suitable mathematical model to interpret and utilize harmonic data limits the application prospects of this technology in TCM diagnosis.

[0006] Inconsistent technical standards and methods: The methods for collecting, processing and analyzing PPG signals in different studies and applications are not uniform, resulting in poor comparability and repeatability of results. This has, to a certain extent, hindered the promotion and application of new methods and models. Summary of the invention

[0007] In view of this, the present application proposes a TCM deficiency and excess analysis method based on PPG signal characteristics to solve the problems reflected by the above-mentioned background technology.

[0008] According to one aspect of the present application, a TCM deficiency-excess analysis method based on PPG signal features is provided, comprising:

[0009] Get PPG signal;

[0010] Analyzing the PPG signal to extract target feature information, wherein the target feature information includes harmonic feature information;

[0011] Obtain quantitative labels for TCM diagnostic information;

[0012] The target characteristic information is analyzed according to the quantitative labels to obtain a TCM deficiency-excess analysis result.

[0013] As an optional implementation scheme of the present application, the PPG signal is analyzed to extract target feature information, wherein the target feature information includes harmonic feature information, including:

[0014] Extracting a heart rate value from the PPG signal;

[0015] Calculating periodic characteristic information of the PPG signal according to the heart rate value;

[0016] Performing Fourier transform on the PPG signal, and extracting harmonic characteristic information from the transformation result as target characteristic information according to the periodic characteristic information.

[0017] As an optional implementation scheme of the present application, calculating the periodic characteristic information of the PPG signal according to the heart rate value includes:

[0018] Calculating the fundamental frequency of the PPG signal according to the heart rate value;

[0019] Based on the multiple relationship between the fundamental frequency and the harmonic frequency, the harmonic frequency corresponding to the harmonic order of the PPG signal is obtained.

[0020] As an optional implementation scheme of the present application, Fourier transform is performed on the PPG signal, and harmonic feature information is extracted from the transformation result as target feature information according to the periodic feature information, including:

[0021] According to the harmonic frequency corresponding to the harmonic order of the PPG signal, a harmonic amplitude corresponding to the harmonic frequency is obtained in the transformation result;

[0022] The harmonic amplitude corresponding to the harmonic frequency is extracted to obtain the harmonic characteristic information of the PPG signal.

[0023] As an optional implementation scheme of the present application, the target feature information further includes:

[0024] A DC component is extracted from the transformation result to obtain DC component characteristic information of the PPG signal as target characteristic information.

[0025] As an optional implementation scheme of the present application, obtaining the quantitative label of TCM diagnosis information includes:

[0026] Preset the quantitative value ranges of TCM diagnostic indicators in the deficiency syndrome state, excess syndrome state and peaceful state;

[0027] According to the quantitative value range, the virtual or real state diagnosis of the TCM diagnosis index item in the TCM diagnosis information is converted into a quantitative label.

[0028] As an optional implementation scheme of the present application, after analyzing the target feature information according to the quantitative label to obtain the TCM deficiency and excess analysis result, it also includes:

[0029] Obtaining actual diagnosis feedback information of the TCM diagnosis indicator items;

[0030] The TCM deficiency / excess analysis result is compared with the actual diagnosis feedback information, and the target feature information data set corresponding to the quantitative label is updated according to the comparison result.

[0031] The present application also provides a TCM deficiency and excess analysis device based on PPG signal characteristics, comprising:

[0032] A signal acquisition module is used to acquire PPG signals;

[0033] A feature extraction module, used to analyze the PPG signal and extract target feature information, wherein the target feature information includes harmonic feature information;

[0034] A module for obtaining quantitative labels, used to obtain quantitative labels of TCM diagnosis information;

[0035] The virtuality and excess analysis module is used to analyze the target feature information according to the quantitative label to obtain the virtuality and excess analysis result of traditional Chinese medicine.

[0036] As an optional implementation scheme of the present application, the feature extraction module includes:

[0037] A heart rate value extraction module, used to extract the heart rate value from the PPG signal;

[0038] A characteristic information calculation module, used for calculating the periodic characteristic information of the PPG signal according to the heart rate value;

[0039] The harmonic feature information extraction module is used to perform Fourier transform on the PPG signal, and extract the harmonic feature information from the transformation result as the target feature information according to the periodic feature information.

[0040] The present application also provides an electronic device, comprising:

[0041] processor;

[0042] a memory for storing processor-executable instructions;

[0043] Among them, the processor is configured to implement the above-mentioned Chinese medicine deficiency and excess analysis method based on PPG signal characteristics when executing the executable instructions.

[0044] Beneficial effects of this application:

[0045] The present invention acquires a PPG signal, analyzes the PPG signal, extracts target feature information, the target feature information includes harmonic feature information, acquires a quantitative label of TCM diagnostic information, analyzes the target feature information according to the quantitative label, and obtains a TCM deficiency and excess analysis result. The PPG signal features are combined with TCM diagnostic information to achieve the conversion from modern medical signals to TCM theory. The machine learning model is used to automatically learn the association between the PPG signal features and the deficiency and excess states of TCM viscera and meridians, realize the automation and intelligence of TCM diagnosis, and also provide users with a personalized application method of TCM diagnosis and health management suggestions.

[0046] Other features and aspects of the present application will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the present application and, together with the description, serve to explain the principles of the present application.

[0048] Figure 1 A flow chart showing a method for analyzing deficiency and excess in traditional Chinese medicine based on PPG signal characteristics according to an embodiment of the present application;

[0049] Figure 2 A PPG original signal diagram of a TCM deficiency-excess analysis method based on PPG signal features according to an embodiment of the present application is shown;

[0050] Figure 3 A PPG signal diagram after preprocessing of the TCM deficiency-excess analysis method based on PPG signal features according to an embodiment of the present application is shown;

[0051] Figure 4 A diagram showing the PPG signal Fourier transform result of the TCM deficiency-excess analysis method based on PPG signal characteristics according to an embodiment of the present application;

[0052] Figure 5 A block diagram of a TCM deficiency-excess analysis device based on PPG signal features according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0053] Various exemplary embodiments, features and aspects of the present application will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0054] Among them, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application or simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0055] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0056] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0057] In addition, in order to better illustrate the present application, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present application can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present application.

[0058] The analysis of deficiency and excess in TCM is an important part of TCM diagnosis. It involves two basic states in the development of diseases, namely, the strength and weakness of the righteous qi and the strength and weakness of the evil qi. In TCM theory, deficiency and excess are mutually opposed and interrelated. Deficiency and excess can exist alone or mixed with each other. For example, in the development of some diseases, patients may show symptoms of insufficient righteous qi and strong evil qi at the same time, that is, a mixture of deficiency and excess. At this time, treatment needs to take into account the overall condition of the patient, both replenishing the righteous qi and eliminating the pathogenic evil. Through deficiency and excess differentiation, TCM physicians can more accurately judge the nature, location of the disease, and the strength and weakness of the evil qi, so as to formulate corresponding treatment plans. The treatment principles and methods of deficiency and excess are completely different. Deficiency syndrome is mainly based on replenishment, while excess syndrome is mainly based on attacking the evil qi. Therefore, accurate deficiency and excess differentiation is of great significance for the clinical diagnosis and treatment of TCM.

[0059] Example 1

[0060] Figure 1The flowchart of the TCM deficiency and excess analysis method based on PPG signal characteristics according to an embodiment of the present application is shown. According to this method, the PPG signal can be linked to the TCM deficiency and excess analysis, providing a new idea for formulating a corresponding treatment plan. Figure 1 As shown, the flow chart includes:

[0061] S100, obtaining a PPG signal;

[0062] In this embodiment, a wearable device, such as a smart watch or a health monitoring bracelet, is used to collect the user's PPG signal in real time. The device uses optical technology to record the changes in blood volume under the skin through a photoelectric sensor to form pulse waveform data. The collection process should be carried out under stable conditions to minimize the interference of motion and ambient light on the signal, such as Figure 1 The acquired raw PPG signal is shown.

[0063] S200, analyzing the PPG signal to extract target feature information, where the target feature information includes harmonic feature information;

[0064] The analysis of PPG signals includes preprocessing operations, which include filtering and smoothing. Filtering includes applying a low-pass filter to remove high-frequency noise, such as high-frequency noise caused by changes in ambient light and device vibration; using a high-pass filter to remove low-frequency baseline drift, such as baseline drift caused by changes in body posture. Smoothing includes using a smoothing algorithm to reduce the high-frequency fluctuations of the signal and improve the stability and accuracy of the signal. The smoothing algorithm can use a moving average or Kalman filter, such as Figure 2 The preprocessed PPG signal is shown.

[0065] The preprocessed PPG signal is further analyzed to extract the harmonic feature information and DC component feature information of the PPG signal as target feature information.

[0066] S300, obtaining a quantitative label of TCM diagnosis information;

[0067] The diagnostic information about the TCM diagnostic index items in the user's TCM diagnostic information is quantified in advance based on the quantitative numerical range corresponding to the actual virtual-real analysis to obtain a quantitative label for the TCM diagnostic index item.

[0068] S400, analyzing the target feature information according to the quantitative label to obtain a TCM deficiency-excess analysis result.

[0069] Using the trained TCM deficiency / excess analysis model that has learned the relationship between PPG signal features and TCM diagnosis results, the PPG signal is analyzed according to the quantitative labels of the TCM diagnosis information stored in the model to output the deficiency / excess status of the user's internal organs and meridians.

[0070] Among them, when constructing the TCM deficiency and excess analysis model, the original PPG signals of multiple users are collected, and a series of preprocessing operations are performed. The heart rate value is extracted according to the PPG signal to calculate the periodic feature information, and the PPG signal is Fourier transformed. The required target feature information is extracted from the transformation result according to the periodic feature information. On the other hand, the TCM diagnosis information corresponding to multiple users is collected, the TCM diagnosis information is converted into quantitative labels, the extracted target feature information and the quantitative labels are combined with each other, a training data set is constructed, and a supervised machine learning model is used for training. The machine learning model can use a deep neural network (DNN), a support vector machine (SVM) or a random forest to train the TCM deficiency and excess analysis model.

[0071] After constructing and training the TCM deficiency-excess model, the model is evaluated and verified through cross-validation, holdout method and other techniques to ensure its stability and robustness under different individuals and conditions. The performance of the model is optimized by continuously adjusting the hyperparameters and structure of the model, which may require the introduction of regularization techniques and data enhancement strategies to avoid overfitting of the model.

[0072] As an optional implementation scheme of the present application, the PPG signal is analyzed to extract target feature information, wherein the target feature information includes harmonic feature information, including: extracting a heart rate value from the PPG signal; calculating the periodic feature information of the PPG signal according to the heart rate value; performing Fourier transform on the PPG signal, and extracting harmonic feature information from the transform result as target feature information according to the periodic feature information.

[0073] The trained TCM deficiency and excess analysis model is used to extract target feature information from the PPG signal. The heart rate value is first used to determine the periodic feature information of the PPG signal. The periodic feature information can be used to analyze the Fourier transform result of the PPG signal. That is, after Fourier transforming the PPG signal, the target feature information required for TCM deficiency and excess analysis is extracted on the basis of determining the periodic feature information. In this embodiment, one of the target feature information is the harmonic feature information.

[0074] As an optional implementation scheme of the present application, calculating the periodic characteristic information of the PPG signal according to the heart rate value includes: calculating the fundamental frequency of the PPG signal according to the heart rate value; and obtaining the harmonic frequency corresponding to the harmonic order of the PPG signal based on a multiple relationship between the fundamental frequency and the harmonic frequency.

[0075] The heart rate value (HR) is extracted from the PPG signal. In this embodiment, the heart rate value is in units of beats per minute (BPM). The heart rate value is converted to the basic frequency f0, that is, the heart rate value is divided by 60 seconds to obtain the number of heart beats per second (Hz): f0 = HR / 60. According to the relationship that the harmonic frequency is an integer multiple of the basic frequency, the harmonic frequency of the PPG signal is determined. That is, the nth harmonic frequency fn can be expressed as fn = n*f0, where n is a positive integer representing the harmonic order. For example, if the heart rate value is 75BPM, the basic frequency f0 = 75 / 60 ​​= 1.25Hz, then the first harmonic frequency f1 = 1*1.25Hz, and the second harmonic frequency is f2 = 2*1.25Hz = 2.5Hz. In this way, the harmonic frequencies corresponding to each harmonic of the PPG signal can be obtained.

[0076] As an optional implementation scheme of the present application, Fourier transform is performed on the PPG signal, and harmonic characteristic information is extracted from the transform result as target characteristic information according to the periodic characteristic information, including: according to the harmonic frequency corresponding to the harmonic order of the PPG signal, obtaining the harmonic amplitude corresponding to the harmonic frequency in the transform result; and extracting the harmonic amplitude corresponding to the harmonic frequency to obtain the harmonic characteristic information of the PPG signal.

[0077] Perform Fourier transform on the PPG signal and convert it to the frequency domain for analysis. The harmonic frequency of the PPG signal has been calculated above, so the harmonic amplitude corresponding to the harmonic frequency can be obtained from the transformation result and extracted as the harmonic feature information of the PPG signal.

[0078] As an optional implementation scheme of the present application, the target feature information further includes: extracting a DC component from the transformation result to obtain DC component feature information of the PPG signal as the target feature information.

[0079] After Fourier transform is performed on the PPG signal, in the transformation result, the DC component reflects the average light absorption of the user's blood, and the harmonic component represents the periodic changes of the user's blood flow. The DC component (DC) can be directly extracted from the transformation result as the DC component characteristic information of the PPG signal.

[0080] As an optional implementation scheme of the present application, obtaining quantitative labels for TCM diagnostic information includes: presetting the quantitative numerical ranges corresponding to TCM diagnostic index items in the deficiency syndrome state, excess syndrome state and peaceful state; and converting the deficiency and excess state diagnosis conditions of the TCM diagnostic index items in the TCM diagnostic information into quantitative labels according to the quantitative numerical ranges.

[0081] In this embodiment, the TCM diagnostic index items are viscera and meridians, where the viscera include the heart, liver, spleen, lung, kidney, gallbladder, stomach, large intestine, small intestine, bladder, and triple burner. Meridians include: pericardium meridian, kidney meridian, lung meridian, stomach meridian, gallbladder meridian, bladder meridian, spleen meridian, liver meridian, etc. The "virtual" of the viscera and meridians is defined as 0 and "real" as 100, and the middle value 50 is the peaceful and healthy state of TCM. Each viscera and meridian has its own virtuality and real value, ranging from 0 to 100. Through the virtuality and real values, the deficiency and real conditions of the user's viscera and meridians can be judged.

[0082] After setting the quantitative value range of the zang-fu organs and meridians, when collecting the user's TCM diagnosis information, the diagnosis of the deficiency and excess state of the zang-fu organs and meridians is obtained from the TCM diagnosis information, and converted into quantitative labels according to the quantitative value range. Among them, the TCM diagnosis information includes the doctor's clinical diagnosis, the user's self-report, and the deficiency and excess state of the zang-fu organs and meridians obtained through the TCM scale.

[0083] After the conversion to quantitative labels, the user's PPG target feature information and quantitative labels are matched and combined to construct a training data set, and a supervised machine learning model is used to train the TCM deficiency-excess analysis model.

[0084] As an optional implementation scheme of the present application, after analyzing the target feature information according to the quantitative label to obtain the TCM deficiency / excess analysis result, it also includes: obtaining actual diagnosis feedback information of the TCM diagnostic indicator item; comparing the TCM deficiency / excess analysis result with the actual diagnosis feedback information, and updating the target feature information data set corresponding to the quantitative label according to the comparison.

[0085] The newly collected PPG signals are analyzed using the trained and verified TCM deficiency and excess analysis model. The model outputs the deficiency and excess status of the user's internal organs and meridians, providing data support for personalized TCM diagnosis and health management. The model can also be combined with other health data, such as exercise volume, eating habits, etc., to provide users with comprehensive health advice.

[0086] Furthermore, actual diagnostic feedback information of the user's internal organs and meridians can be obtained, and the actual diagnostic feedback information includes the actual health status and feedback from the Chinese medicine practitioner. The results output by the model are compared with the actual diagnostic feedback information to see whether the analysis results between the two are too different. Based on the experience guidance of the Chinese medicine practitioner, the training data set that corresponds to the target feature information and the quantitative labels is updated according to the comparison results, and used for retraining and updating of the model. The update of the training data set can also be based on user feedback, extraction of health records, etc., to continuously improve the accuracy and reliability of the diagnosis.

[0087] Through the above methods, the PPG signal features are combined with TCM diagnostic information to achieve the transformation from modern medical signals to TCM theory. The machine learning model is used to automatically learn the relationship between PPG signal features and the deficiency and excess status of TCM organs and meridians, realize the automation and intelligence of TCM diagnosis, and provide users with personalized TCM diagnosis and health management suggestions.

[0088] Example 2

[0089] In Example 1, the frequency domain features of the PPG signal are mainly used. This embodiment provides a method that uses the time domain features of the PPG signal to classify the pulse shape through a machine learning algorithm. The method has the following steps:

[0090] S10, obtaining a PPG signal;

[0091] In this embodiment, a finger-clip type or wrist-band type PPG sensor is used to collect the PPG signal.

[0092] S20, analyzing the PPG signal to extract pulse characteristic information;

[0093] The collected PPG signal is preprocessed by low-pass filtering, high-pass filtering and smoothing methods, and then the pulse feature information is extracted by using the time domain characteristics of the PPG signal. The pulse feature information includes pulse wave morphology characteristics, periodicity characteristics and amplitude characteristics. The pulse wave morphology characteristics include the rising edge time, falling edge time, peak width, etc. of the pulse wave; the periodicity characteristics include the pulse interval of the pulse wave, where the pulse interval is based on the time interval between the peaks of the PPG signal; the amplitude characteristics include the maximum amplitude and minimum amplitude of the pulse wave, etc.

[0094] S30, analyzing the pulse characteristic information, and outputting the pulse shape category and pulse pattern description information.

[0095] In this embodiment, a pulse shape classification model is used to analyze the pulse feature information, wherein the pulse shape classification model includes the following training: the classifier selects a machine learning algorithm such as support vector machine (SVM), decision tree, random forest or neural network, performs an importance assessment on the pulse feature information, selects the feature subset that has the greatest influence on the pulse shape classification, and uses the corresponding labeled PPG signal data set for model training, and evaluates the model performance through methods such as cross-validation.

[0096] After the pulse shape classification model is trained and verified, when receiving a new PPG signal, it can analyze the pulse feature information and output the recognized pulse shape category, such as floating pulse, sinking pulse, slow pulse, rapid pulse, etc. On the other hand, it can also provide descriptive text of the pulse shape to help users better understand the characteristics of the pulse.

[0097] Example 3

[0098] Based on the same principle as the above method, a TCM deficiency and excess analysis device based on PPG signal characteristics is also proposed, see Figure 5 , a TCM deficiency and excess analysis device 100 based on PPG signal characteristics of an embodiment of the present disclosure includes:

[0099] A signal acquisition module 110 is used to acquire a PPG signal;

[0100] A feature extraction module 120 is used to analyze the PPG signal and extract target feature information, wherein the target feature information includes harmonic feature information;

[0101] A quantitative label acquisition module 130 is used to acquire quantitative labels of TCM diagnosis information;

[0102] The virtual-real analysis module 140 is used to analyze the target feature information according to the quantitative labels to obtain the virtual-real analysis results of traditional Chinese medicine.

[0103] As an optional implementation scheme of the present application, the feature extraction module includes:

[0104] A heart rate value extraction module 121 is used to extract the heart rate value from the PPG signal;

[0105] A characteristic information calculation module, used to calculate the periodic characteristic information 122 of the PPG signal according to the heart rate value;

[0106] The harmonic feature information extraction module 123 is used to perform Fourier transform on the PPG signal, and extract the harmonic feature information from the transformation result as the target feature information according to the periodic feature information.

[0107] Obviously, those skilled in the art should understand that all or part of the processes in the above-mentioned embodiment method can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned control methods. The modules or steps of the present invention can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by program codes executable by computing devices, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules respectively, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the present invention is not limited to any specific combination of hardware and software.

[0108] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment method can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned control methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated as: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0109] Example 4

[0110] Furthermore, an electronic device is proposed, comprising:

[0111] processor;

[0112] a memory for storing processor-executable instructions;

[0113] Among them, the processor is configured to implement the Chinese medicine deficiency and excess analysis method based on PPG signal characteristics described in Example 1 when executing the executable instructions.

[0114] The electronic device of the embodiment of the present disclosure includes a processor and a memory for storing processor executable instructions. The processor is configured to implement any of the above-mentioned TCM deficiency and excess analysis methods based on PPG signal features when executing the executable instructions.

[0115] It should be noted that the number of processors may be one or more. At the same time, the electronic device of the embodiment of the present disclosure may also include an input device and an output device. The processor, memory, input device, and output device may be connected via a bus or in other ways, which are not specifically limited here.

[0116] The memory, as a computer-readable storage medium of the TCM deficiency and excess analysis method based on PPG signal features, can be used to store software programs, computer executable programs and various modules, such as: the program or module corresponding to the TCM deficiency and excess analysis method based on PPG signal features of the embodiment of the present disclosure. The processor executes various functional applications and data processing of the electronic device by running the software programs or modules stored in the memory.

[0117] The input device can be used to receive input numbers or signals. The signal can be a key signal related to user settings and function control of the device / terminal / server. The output device can include a display device such as a display screen.

[0118] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for analyzing deficiency and excess in traditional Chinese medicine based on PPG signal characteristics, characterized in that: include: Get PPG signal; Analyzing the PPG signal to extract target feature information, wherein the target feature information includes harmonic feature information; Obtain quantitative labels for TCM diagnostic information; The target characteristic information is analyzed according to the quantitative labels to obtain a TCM deficiency-excess analysis result.

2. The TCM deficiency-excess analysis method based on PPG signal characteristics according to claim 1, characterized in that: Analyze the PPG signal to extract target feature information, wherein the target feature information includes harmonic feature information, including: Extracting a heart rate value from the PPG signal; Calculating periodic characteristic information of the PPG signal according to the heart rate value; Performing Fourier transform on the PPG signal, and extracting harmonic characteristic information from the transformation result as target characteristic information according to the periodic characteristic information.

3. The TCM deficiency-excess analysis method based on PPG signal characteristics according to claim 2, characterized in that: The calculating the periodic characteristic information of the PPG signal according to the heart rate value includes: Calculating the fundamental frequency of the PPG signal according to the heart rate value; Based on the multiple relationship between the fundamental frequency and the harmonic frequency, the harmonic frequency corresponding to the harmonic order of the PPG signal is obtained.

4. The TCM deficiency-excess analysis method based on PPG signal characteristics according to claim 3 is characterized in that: Performing Fourier transform on the PPG signal, and extracting harmonic characteristic information from the transform result as target characteristic information according to the periodic characteristic information, comprising: According to the harmonic frequency corresponding to the harmonic order of the PPG signal, a harmonic amplitude corresponding to the harmonic frequency is obtained in the transformation result; The harmonic amplitude corresponding to the harmonic frequency is extracted to obtain the harmonic characteristic information of the PPG signal.

5. The TCM deficiency-excess analysis method based on PPG signal characteristics according to claim 4, characterized in that: Target feature information also includes: A DC component is extracted from the transformation result to obtain DC component characteristic information of the PPG signal as target characteristic information.

6. The TCM deficiency-excess analysis method based on PPG signal characteristics according to claim 1, characterized in that: Obtain quantitative labels for TCM diagnostic information, including: Preset the quantitative value ranges of TCM diagnostic indicators corresponding to the deficiency syndrome state, excess syndrome state and peaceful state; According to the quantitative value range, the virtual or real state diagnosis of the TCM diagnosis index item in the TCM diagnosis information is converted into a quantitative label.

7. The TCM deficiency-excess analysis method based on PPG signal characteristics according to claim 6, characterized in that: After analyzing the target feature information according to the quantitative label to obtain the TCM deficiency and excess analysis result, the method further includes: Obtaining actual diagnosis feedback information of the TCM diagnosis indicator items; The TCM deficiency / excess analysis result is compared with the actual diagnosis feedback information, and the target feature information data set corresponding to the quantitative label is updated according to the comparison result.

8. A TCM deficiency and excess analysis device based on PPG signal characteristics, characterized in that: include: A signal acquisition module is used to acquire PPG signals; A feature extraction module, used to analyze the PPG signal and extract target feature information, wherein the target feature information includes harmonic feature information; A module for obtaining quantitative labels, used to obtain quantitative labels of TCM diagnosis information; The virtuality and excess analysis module is used to analyze the target feature information according to the quantitative label to obtain the virtuality and excess analysis result of traditional Chinese medicine.

9. The TCM deficiency and excess analysis device based on PPG signal characteristics according to claim 8, characterized in that: The feature extraction module comprises: A heart rate value extraction module, used to extract the heart rate value from the PPG signal; A characteristic information calculation module, used for calculating the periodic characteristic information of the PPG signal according to the heart rate value; The harmonic feature information extraction module is used to perform Fourier transform on the PPG signal, and extract the harmonic feature information from the transformation result as the target feature information according to the periodic feature information.

10. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the TCM deficiency-excess analysis method based on PPG signal features as described in any one of claims 1-7 when executing the executable instructions.

Images