RPPG-based hypertension single-factor traditional Chinese medicine constitution non-contact identification method and system

Abstract

The invention discloses a hypertension single-factor traditional Chinese medicine constitution non-contact identification method and system based on rPPG, and the method comprises the steps: obtaining a face video, and determining the hypertension data corresponding to the face video based on rPPG; the hypertension data and the corresponding data of different dimensions are input into a decision tree model, so that the decision tree model outputs traditional Chinese medicine constitution information, and the traditional Chinese medicine constitution information comprises mild constitution, yin deficiency constitution, yang deficiency constitution, phlegm-dampness constitution, blood stasis constitution, qi deficiency constitution, qi depression constitution, specific intrinsic constitution and damp-heat constitution. The purpose of predicting the hypertension constitution information in a non-contact mode is achieved, and the problem that in the related technology, the judgment efficiency needs to be improved through a manual mode is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent prediction processing, and particularly to a non-contact identification method and system for single-factor traditional Chinese medicine constitution of hypertension based on rPPG. Background Art

[0002] In recent years, research has shown that hypertension is closely related to traditional Chinese medicine constitution. The prevention and treatment of hypertension are long-term tasks. Among them, constitution conditioning is an important means and also the future direction of traditional Chinese medicine intervention in hypertension. It is of great significance to explore the correlation between hypertension and constitution types.

[0003] Therefore, correctly identifying the traditional Chinese medicine constitution type of hypertension patients and providing corresponding traditional Chinese medicine health care guidance from aspects such as emotional regulation, diet conditioning, daily life regulation, exercise health care, and acupoint health care according to different constitution types can help hypertension patients effectively regulate and control blood pressure levels.

[0004] In the related art, the determination of hypertension constitution still relies on contact-based manual determination, with relatively low efficiency. Summary of the Invention

[0005] The main purpose of the present invention is to provide a non-contact identification method for single-factor traditional Chinese medicine constitution of hypertension based on rPPG to solve the deficiencies in the related art.

[0006] To achieve the above purpose, according to the first aspect of the present invention, a non-contact identification method for single-factor traditional Chinese medicine constitution of hypertension based on rPPG is provided, including: obtaining a face video and determining hypertension data corresponding to the face video based on rPPG; inputting the hypertension data and corresponding data of different dimensions into a decision tree model for the decision tree model to output traditional Chinese medicine constitution information, where the traditional Chinese medicine constitution information includes peaceful constitution, yin deficiency constitution, yang deficiency constitution, phlegm-dampness constitution, blood stasis constitution, qi deficiency constitution, qi stagnation constitution, special endowment constitution, and damp-heat constitution.

[0007] Optionally, when determining the decision tree model, the method includes: obtaining a face video sample and determining corresponding hypertension sample data; constructing a decision tree model based on the hypertension data sample and associated features of different dimensions, where when constructing, the feature with the largest information gain is selected as the root node of the decision tree according to the hypertension sample data set, each sub-node in the decision tree represents a certain feature of the hypertension sample, and the leaf node of the decision tree represents the traditional Chinese medicine constitution category to which the hypertension sample belongs.

[0008] Optionally, when determining the decision tree model: calculating the information entropy of the hypertension sample data D: where D represents the hypertension sample data, c represents the number of traditional Chinese medicine constitution categories, p iIt represents the proportion of the number of samples belonging to category i in all samples; corresponding to D, when selecting the attribute feature A as the decision tree judgment node, the information entropy after the action of the attribute feature is Info(D), and the calculation is as follows: where k represents that the sample D is divided into k parts; calculate the information gain value Gain(A): Gain(A) = Info(D) - Info A (D); use the attribute feature with the largest information gain value Gain(A) as the root node, split the root node into child nodes, further calculate the information gain and use the one with the largest information gain as the child node, and build the decision tree in this way until all attribute feature values are less than the set threshold or there is no attribute feature to select.

[0009] Optionally, the data in different dimensions include gender, age, occupation, and body mass index.

[0010] According to the second aspect of the present invention, a non-contact identification system for single-factor traditional Chinese medicine constitution of hypertension based on rPPG is provided, including: a collection unit for acquiring a face video and determining hypertension data corresponding to the face video based on rPPG; a prediction unit for inputting the hypertension data and corresponding data in different dimensions into a decision tree model for the decision tree model to output traditional Chinese medicine constitution information, where the traditional Chinese medicine constitution information includes peaceful constitution, yin deficiency constitution, yang deficiency constitution, phlegm-dampness constitution, blood stasis constitution, qi deficiency constitution, qi stagnation constitution, special endowment constitution, and damp-heat constitution.

[0011] Optionally, when determining the decision tree model: acquire a face video sample and determine the corresponding hypertension sample data; build a decision tree model based on the hypertension data sample and associated features in different dimensions, where when building, select the feature with the largest information gain as the root node of the decision tree according to the hypertension sample data set, each sub-node in the decision tree represents a certain feature of the hypertension sample, and the leaf node of the decision tree represents the traditional Chinese medicine constitution category to which the hypertension sample belongs.

[0012] Optionally, when determining the decision tree model: calculate the information entropy of the hypertension sample data D: where D represents the hypertension sample data, c represents the number of traditional Chinese medicine constitution categories, and p i It represents the proportion of the number of samples belonging to category i in all samples; corresponding to D, when selecting the attribute feature A as the decision tree judgment node, the information entropy after the action of the attribute feature is Info(D), and the calculation is as follows: where k represents that the sample D is divided into k parts; calculate the information gain value Gain(A): Gain(A) = Info(D) - Info A(D); Use the attribute feature with the maximum information gain value Gain(A) as the root node, split the root node into child nodes, further calculate the information gain, and use the one with the maximum information gain as the child node, and construct a decision tree in this way until all attribute feature values are less than the set threshold or there is no attribute feature selection left.

[0013] Optionally, the data in different dimensions include gender, age, occupation, and body mass index.

[0014] According to the third aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a computer to execute the method according to any one of the first aspect.

[0015] According to the fourth aspect of the present invention, there is provided an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to cause the at least one processor to execute the method according to any one of the implementation manners of the first aspect.

[0016] The non-contact identification method and system for single-factor traditional Chinese medicine constitution of hypertension based on rPPG in this embodiment, wherein the method includes obtaining a face video and determining hypertension data corresponding to the face video based on rPPG; inputting the hypertension data and corresponding data in different dimensions into a decision tree model for the decision tree model to output traditional Chinese medicine constitution information, wherein the traditional Chinese medicine constitution information includes peaceful constitution, yin deficiency constitution, yang deficiency constitution, phlegm-dampness constitution, blood stasis constitution, qi deficiency constitution, qi stagnation constitution, special endowment constitution, and damp-heat constitution. The purpose of predicting hypertension constitution information in a non-contact manner is achieved, and the problem that the efficiency of manual judgment in related technologies needs to be improved is overcome. Description of the Drawings

[0017] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of the non-contact identification method for single-factor traditional Chinese medicine constitution of hypertension based on rPPG in an embodiment of the present invention;

[0019] Figure 2 It is a schematic diagram of the electronic device in an embodiment of the present invention. Detailed Embodiments

[0020] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0021] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data used in appropriate cases can be interchanged so as to implement the embodiments of the present invention described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0022] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0023] According to an embodiment of the present invention, a data processing method is provided, as Figure 1 shown, including steps 101 to 103 as follows:

[0024] Step 101: Obtain a face video and determine hypertension data corresponding to the face video based on rPPG.

[0025] In this step, through the rPPG technology, using the light reflected by the human face, and then combining artificial intelligence and deep learning algorithms to calculate the change in blood flow, and finally obtain hypertension data. Perform data feature preprocessing on the blood pressure data measured by the user to obtain preprocessed blood pressure status information data. Obtain the blood pressure data measured by the user for data preprocessing, process the user information data to obtain stable user hypertension status information data; use a normalization model to perform normalization processing on the stable user hypertension status information data to obtain the preprocessed user hypertension status information data. Specifically, it includes selecting a plurality of preprocessed user hypertension status information data before the current moment to generate a prediction result, using a normalization algorithm to normalize the prediction result to a standard range, and the normalized result is used as the actual hypertension status data measurement value at the current moment.

[0026] Step 102: Input the hypertension data and the corresponding data of different dimensions into the decision tree model for the decision tree model to output traditional Chinese medicine constitution information, where the traditional Chinese medicine constitution information includes peaceful constitution, yin deficiency constitution, yang deficiency constitution, phlegm-dampness constitution, blood stasis constitution, qi deficiency constitution, qi stagnation constitution, special endowment constitution, and damp-heat constitution.

[0027] In this step, the hypertension of the user to be measured is obtained through rPPG technology. According to the model, the hypertension range of the user and factors such as age and gender are automatically calculated, and the possible traditional Chinese medicine constitution types are inferred, so as to intelligently generate a hypertension cognitive analysis report and a traditional Chinese medicine constitution health assessment report.

[0028] The hypertension of the user to be measured is obtained through rPPG technology. According to the model, the hypertension range of the user and factors such as age and gender are automatically calculated, and the possible traditional Chinese medicine constitution types are inferred, so as to intelligently generate a hypertension cognitive analysis report and a traditional Chinese medicine constitution health assessment report.

[0029] As an optional implementation manner of this embodiment, when determining the decision tree model, the method includes: obtaining a face video sample and determining the corresponding hypertension sample data; constructing a decision tree model based on the hypertension data sample and the associated features of different dimensions, where when constructing, the feature with the largest information gain is selected as the root node of the decision tree according to the hypertension sample data set, each sub-node in the decision tree represents a certain feature of the hypertension sample, and the leaf node of the decision tree represents the traditional Chinese medicine constitution category to which the hypertension sample belongs.

[0030] In this optional implementation manner, the feature preprocessing of the predicted hypertension data of the user is performed to obtain a cognitive staging database of the hypertension sample data (including factors such as age and gender) and the corresponding traditional Chinese medicine constitution types. That is, according to the measured values of the actual cognitive hypertension status data after normalization, the staging rules for cognition or recognition are set according to these data, and the system automatically determines the nature of these abnormal signals and data and automatically identifies the possible abnormal situations.

[0031] Generally speaking: Taking the normal reference values of systolic blood pressure (high blood pressure) for teenagers and adults as an example, if the range is between 90 - 130, the high blood pressure is generally considered normal. If it is between 130 - 139, it is generally considered borderline hypertension, that is to say, this belongs to the high-risk group of hypertension; if it is greater than or equal to 140, it is diagnosed hypertension; if it is between 140 - 159, it is mild hypertension, that is, grade 1 hypertension; if it is between 160 - 179, it is moderate hypertension, that is, grade 2 hypertension; if it is above 180, it is severe hypertension, that is, grade 3 hypertension; if it is greater than or equal to 230, it is malignant hypertension; if it is less than or equal to 130, it is decapitated hypertension and so on. In addition, the causes of different types of hypertension are different. And there are also special situations in the same population. For example, the range of gestational hypertension in pregnant women is greater than or equal to 140; it may be between 150 - 159 under the condition of taking medicine; if it is greater than or equal to 160, it is severe preeclampsia.

[0032] In addition, qi deficiency constitution, phlegm-dampness constitution, and yang deficiency constitution are the main constitutional types of essential hypertension; there is a certain correlation between the constitutional types of hypertension patients and age, body mass index, and gender.

[0033] The research results show that the incidence rates of qi deficiency constitution and yang deficiency constitution are relatively high in hypertension patients over 60 years old, and the older the age, the greater the possibility of forming qi deficiency constitution and yang deficiency constitution. Because after middle age, the primordial yang gradually declines, resulting in yang deficiency, which is prone to form qi deficiency constitution and yang deficiency constitution. Hypertension patients under 60 years old are mainly of phlegm-dampness constitution, which is related to the fact that smoking and drinking are more common in the middle and young stages, and the diet is mostly rich and greasy, resulting in the accumulation of phlegm and turbidity.

[0034] Body mass index is one of the important indicators to measure health status, and there is a certain correlation between it and hypertension. This correlation can be reflected and intervened from the distribution direction of constitutional types. The results of this group show that the constitutional types presented by the four states of low weight, normal weight, overweight, and obesity are different. Hypertension patients with phlegm-dampness constitution have a strong correlation with obesity. Qi deficiency constitution patients tend to be overweight, and yang deficiency constitution patients are not prone to overweight, suggesting that as the body mass index increases, the probabilities of qi deficiency constitution and phlegm-dampness constitution appear to increase. It is suggested that when the body mass index increases, attention should be paid to the conditioning of qi deficiency constitution and phlegm-dampness constitution, and when the body mass index decreases, attention should be paid to the conditioning of yang deficiency constitution.

[0035] Relationship between gender and constitutional types in patients with hypertension: The distribution of constitutional types in male patients with hypertension is relatively concentrated, mainly including qi deficiency constitution, phlegm-dampness constitution, and damp-heat constitution. The distribution of constitutional types in female patients with hypertension is relatively wide, and qi deficiency constitution, yang deficiency constitution, phlegm-dampness constitution, blood stasis constitution, qi stagnation constitution, and yin deficiency constitution are all relatively common. It is suggested that male patients with hypertension should focus on regulating their constitutions and pay attention to the regulation of qi deficiency constitution, phlegm-dampness constitution, and damp-heat constitution. Female patients with hypertension should pay attention to diversification and individualization in regulating their constitutions.

[0036] The study also shows that the risk factors for male hypertensive patients are phlegm-dampness constitution, and the protective factors are balanced constitution, qi deficiency constitution, and yang deficiency constitution; the risk factors for female hypertensive patients are phlegm-dampness constitution and blood stasis constitution, and the protective factors are balanced constitution, yang deficiency constitution, and qi deficiency constitution. In addition, women with phlegm-dampness constitution are more likely to develop hypertension. Phlegm-dampness constitution, yin deficiency constitution, and qi deficiency constitution are the constitutional types that are very likely to develop essential hypertension.

[0037] Based on the above hypertension sample database and the corresponding traditional Chinese medicine constitutional types, a single-factor traditional Chinese medicine constitution decision tree identification model for hypertension is established.

[0038] The decision tree analysis method is a risk-based decision-making method that uses a tree in probability theory and graph theory to compare different options in a decision-making process to obtain the optimal option. A decision tree consists of a decision graph and possible outcomes (including resource costs and risks) and is used to create a plan to reach the goal. Its basic principle is to use decision points to represent decision-making problems, use alternative branches to represent alternative options, use probability branches to represent various possible outcomes of the options, and provide a decision-making basis for decision-makers through the calculation and comparison of the profit and loss values of various options under various outcome conditions.

[0039] As an optional implementation mode of this embodiment, when determining the decision tree model: Calculate the information entropy of the hypertension sample data D: where D represents the hypertension sample data, c represents the number of traditional Chinese medicine constitutional categories, and p i represents the proportion of the number of samples belonging to category i in all samples; for D, when selecting the attribute feature A as the decision tree judgment node, the information entropy after the action of the attribute feature is Info(D), and the calculation is as follows: where k represents that the sample D is divided into k parts; calculate the information gain value Gain(A): Gain(A) = Info(D) - Info A (D). Take the attribute feature with the largest information gain value Gain(A) as the root node, split the root node into child nodes, further calculate the information gain and take the one with the largest information gain as the child node, and construct the decision tree in this way until all attribute feature values are less than the set threshold or there is no attribute feature to select.

[0040] As an alternative implementation of this embodiment, the data in different dimensions include gender, age, occupation, and body mass index.

[0041] In this alternative implementation, the influencing factor data index values such as the hypertension sample data (which also includes factors such as age, gender, occupation, etc.). Here, the attribute feature with the largest information gain is selected from the hypertension sample dataset as the root node of the decision tree. Each sub-node in the decision tree represents a certain attribute feature data of the hypertension sample, and the leaf node of the decision tree represents the traditional Chinese medicine constitution category to which the hypertension sample belongs. The method for constructing the decision tree model is as follows:

[0042] Calculate the information entropy of the sample dataset D:

[0043]

[0044] where D represents the hypertension sample dataset, c represents the number of traditional Chinese medicine constitution categories, and p i represents the proportion of the number of samples belonging to category i in all samples.

[0045] For the dataset D, when selecting the attribute feature A as the decision tree judgment node, the information entropy after the action of the attribute feature is I nfo(D), and the calculation is as follows:

[0046]

[0047] where k represents that the sample D is divided into k parts;

[0048] Calculate the information gain value Gai n(A):

[0049] Gain(A)=Info(D)-Info A (D)

[0050] Use the attribute feature with the largest information gain value Gai n(A) as the root node, split the root node into sub-nodes, further calculate the information gain and use the one with the largest information gain as the sub-node, and construct the decision tree in this way until all attribute feature values are less than the set threshold or there is no attribute feature to select. After the decision tree model is established, it is verified through the test set, and the decision tree model is evaluated through evaluation indicators, and the evaluation indicators include classification accuracy, recall rate, false alarm rate, and precision, etc.

[0051] The non-contact identification method and system for single-factor traditional Chinese medicine constitution of hypertension based on rPPG technology involve an important research direction in the field of human physiological health, with profound and multi-dimensional significance. First of all, this technology provides a new, non-invasive and non-contact method for the identification of single-factor traditional Chinese medicine constitution of hypertension. Traditional methods rely on cuff-type or wrist-type sphygmomanometers for measurement, and these methods have certain limitations in continuous monitoring. However, the technology based on face video signals overcomes the limitations of traditional methods and provides a more convenient option for blood pressure monitoring. At the same time, combining the single factor of hypertension with traditional Chinese medicine constitution based on rPPG technology for non-contact and non-invasive intelligent identification is expected to achieve an important breakthrough in the field of constitution identification in the future.

[0052] Secondly, this technology can predict blood pressure sample data through rPPG technology and achieve the identification of traditional Chinese medicine constitution, providing a more quantitative and personalized analysis for individual health. This means that it is no longer necessary to rely on professionals or medical equipment to obtain individual blood pressure data and constitution judgment and recognition, making personalized health management more convenient. For those who need to regularly monitor blood pressure, especially patients with diseases such as hypertension, there will be a more accurate and scientific solution for their health management.

[0053] In addition, establishing a non-contact identification model for single-factor traditional Chinese medicine constitution of hypertension based on rPPG technology not only quantitatively evaluates the health status, but more importantly provides a new analysis idea for related health problems. This correlation model is expected to help medical professionals more accurately evaluate the overall health status of patients and provide them with more personalized treatment plans and health management suggestions. For individual users, this quantitative evaluation model can also be used as an early warning system to provide timely health risk warnings and promote personal self-health management.

[0054] What is more worthy of attention is the intelligent application brought by this technology. By intelligently generating traditional Chinese medicine constitution cognitive analysis reports and health assessment reports, it provides users with detailed and visual health information, which helps individuals better understand their own health status, promotes the improvement of health awareness, and stimulates individuals to participate more actively in health management.

[0055] In the long run, the significance of this technology lies not only in blood pressure detection and analysis and the identification of traditional Chinese medicine constitution, but more importantly in its representation of the deep integration of technology and medical health. This integration will bring more innovations to the future medical and health field, may give rise to more personalized and precise health management methods, and is expected to improve the overall medical service level and public health awareness.

[0056] Therefore, this method for blood pressure cognitive staging and health assessment based on face video signals is not only a technological innovation but also an important breakthrough in the field of medical and health management, and is expected to have a profound impact on aspects such as health management, disease prevention, and medical diagnosis in the future.

[0057] Reference Figure 2 , which shows the application schematic diagram of the above method. Users can select any material, such as a picture material, and then click "Download", and all files will be packaged and downloaded synchronously with one click.

[0058] The non-contact identification method and system for single-factor traditional Chinese medicine constitution of hypertension based on rPPG technology in this embodiment mainly collect the facial video of a person through a camera, and infer the change in blood flow based on the color change caused by the absorption and reflection of external light by the facial skin, and use this to measure the corresponding hypertension indicators. According to the hypertension sample data and the corresponding cognitive staging results of traditional Chinese medicine constitution types, a decision tree evaluation and identification model is established to infer possible traditional Chinese medicine constitutions or health problems, and thus an intelligent hypertension cognitive analysis report and a traditional Chinese medicine constitution health assessment report are generated.

[0059] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0060] According to an embodiment of the present invention, there is also provided a non-contact identification system for single-factor traditional Chinese medicine constitution of hypertension based on rPPG, including: a collection unit for acquiring a facial video and determining hypertension data corresponding to the facial video based on rPPG; a prediction unit for inputting the hypertension data and corresponding data of different dimensions into a decision tree model for the decision tree model to output traditional Chinese medicine constitution information, where the traditional Chinese medicine constitution information includes peaceful constitution, yin deficiency constitution, yang deficiency constitution, phlegm-dampness constitution, blood stasis constitution, qi deficiency constitution, qi stagnation constitution, special endowment constitution, and damp-heat constitution.

[0061] As an optional implementation manner of this embodiment, when determining the decision tree model: acquiring a facial video sample and determining corresponding hypertension sample data; constructing a decision tree model based on the hypertension data sample and associated features of different dimensions, where when constructing, the feature with the largest information gain is selected as the root node of the decision tree according to the hypertension sample data set, each sub-node in the decision tree represents a certain feature of the hypertension sample, and the leaf node of the decision tree represents the traditional Chinese medicine constitution category to which the hypertension sample belongs.

[0062] As an optional implementation manner of this embodiment, when determining the decision tree model: calculating the information entropy of the hypertension sample data D: Where D represents the sample data of hypertension, c represents the number of traditional Chinese medicine constitution categories, and p i represents the proportion of the number of samples belonging to category i in all samples; corresponding to D, when selecting the attribute feature A as the decision tree judgment node, the information entropy after the action of the attribute feature is Info(D), and the calculation is as follows: Where k represents that the sample D is divided into k parts; calculate the information gain value Gain(A): Gain(A) = Info(D) - Info A (D) Use the attribute feature with the largest information gain value Gain(A) as the root node, split the root node into child nodes, further calculate the information gain and use the one with the largest information gain as the child node, and construct the decision tree in this way until all attribute feature values are less than the set threshold or there is no attribute feature to select.

[0063] As an optional implementation manner of this embodiment, the data in different dimensions includes gender, age, occupation, and body mass index.

[0064] According to an embodiment of the present invention, the present invention also provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor can implement the method described in any of the above embodiments.

[0065] According to an embodiment of the present invention, the present invention also provides a readable storage medium, which stores computer instructions, and when the computer instructions are executed, the computer can implement the method described in any of the above embodiments.

[0066] According to an embodiment of the present invention, the present invention also provides a computer program product, and when the computer program is executed by a processor, it can implement the method described in any of the above embodiments.

[0067] Figure 2 FIG. shows a schematic block diagram of an exemplary electronic device 300 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices.

[0068] As Figure 2As shown, the electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to computer programs stored in a read-only memory (ROM) 302 or computer programs loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0069] Multiple components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a magnetic disk, an optical disc, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0070] The computing unit 301 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 301 executes the various methods and processes described above, such as the object matching method. For example, in some embodiments, the object matching method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the methods described above can be executed.

[0071] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0072] The program code for implementing the methods of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing device so that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0073] In the context of the present invention, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Claims

1. A non-contact identification method of single-factor TCM constitution of hypertension based on rPPG, characterized in that: include: Obtain a face video, and determine the hypertension data corresponding to the face video based on rPPG; The hypertension data and corresponding data of different dimensions are input into a decision tree model, so that the decision tree model outputs TCM constitution information, wherein the TCM constitution information includes balanced constitution, yin deficiency constitution, yang deficiency constitution, phlegm-damp constitution, blood stasis constitution, qi deficiency constitution, qi stagnation constitution, special constitution, and damp-heat constitution.

2. The non-contact identification method of single-factor TCM constitution of hypertension based on rPPG according to claim 1 is characterized in that: When determining a decision tree model, methods include: Obtain face video samples and determine corresponding hypertension sample data; A decision tree model is constructed based on hypertension data samples and associated features of different dimensions, wherein during construction, the feature with the maximum information gain is selected as the root node of the decision tree according to the hypertension sample data set, each child node in the decision tree represents a certain feature of the hypertension sample, and the leaf node of the decision tree represents the TCM constitution category to which the hypertension sample belongs.

3. The non-contact identification method of single-factor TCM constitution of hypertension based on rPPG according to claim 2 is characterized in that: When determining the decision tree model: Calculate the information entropy of hypertension sample data D: Where D represents the sample data of hypertension, c represents the number of TCM constitution categories, and p i Indicates the proportion of samples belonging to category i to all samples; Corresponding to D, when attribute feature A is selected as the decision tree judgment node, the information entropy after the attribute feature is applied is Info(D), which is calculated as follows: Where k means that the sample D is divided into k parts; calculate the information gain value Gain(A): Gain(A)=Info(D)-Info A (D) The attribute feature with the largest information gain value Gain(A) is used as the root node, and the child nodes are split from the root node. The information gain is further calculated and the child node with the largest information gain is used as the child node to construct a decision tree until all attribute feature values ​​are less than the set threshold or no attribute feature is selected.

4. The non-contact identification method of single-factor TCM constitution of hypertension based on rPPG according to claim 1, characterized in that: Data of different dimensions include gender, age, occupation, and body mass index.

5. A non-contact identification system of hypertension single factor TCM constitution based on rPPG, characterized in that: include: An acquisition unit, used for acquiring a face video and determining hypertension data corresponding to the face video based on rPPG; A prediction unit is used to input the hypertension data and corresponding data of different dimensions into a decision tree model, so that the decision tree model outputs TCM constitution information, wherein the TCM constitution information includes balanced constitution, yin deficiency constitution, yang deficiency constitution, phlegm-damp constitution, blood stasis constitution, qi deficiency constitution, qi stagnation constitution, special constitution, and damp-heat constitution.

6. The rPPG-based non-contact identification system for hypertension single factor TCM constitution according to claim 5 is characterized in that: When determining the decision tree model: Obtain face video samples and determine corresponding hypertension sample data; A decision tree model is constructed based on hypertension data samples and associated features of different dimensions, wherein during construction, the feature with the maximum information gain is selected as the root node of the decision tree according to the hypertension sample data set, each child node in the decision tree represents a certain feature of the hypertension sample, and the leaf node of the decision tree represents the TCM constitution category to which the hypertension sample belongs.

7. The rPPG-based non-contact identification system for hypertension in traditional Chinese medicine according to claim 6, characterized in that: When determining the decision tree model: Calculate the information entropy of hypertension sample data D: Where D represents the sample data of hypertension, c represents the number of TCM constitution categories, and p i Indicates the proportion of samples belonging to category i to all samples; Corresponding to D, when attribute feature A is selected as the decision tree judgment node, the information entropy after the attribute feature is applied is Info(D), which is calculated as follows: Where k means that the sample D is divided into k parts; calculate the information gain value Gain(A): Gain(A)=Info(D)-Info A (D) The attribute feature with the largest information gain value Gain(A) is used as the root node, and the child nodes are split from the root node. The information gain is further calculated and the child node with the largest information gain is used as the child node to construct a decision tree until all attribute feature values ​​are less than the set threshold or no attribute feature is selected.

8. The rPPG-based non-contact identification system for hypertension in traditional Chinese medicine according to claim 5, characterized in that: Data of different dimensions include gender, age, occupation, and body mass index.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 4.

10. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor executes the method described in any one of claims 1 to 4.

Images