Health prediction analysis system and method based on big data deep learning

Abstract

The invention discloses a health prediction analysis system and method based on big data deep learning. The system comprises an AI terminal and a matched wearable vital sign sensing device. The vital sign sensing equipment is used for detecting and collecting sign data of the blood oxygen level, the heart rate, the body surface temperature, the sleep index and the movement condition of the wearer; the AI terminal is used for being in data interconnection with the vital sign sensing equipment and obtaining the sign data detected and collected by the vital sign sensing equipment for data processing and AI analysis and prediction; according to the invention, deep analysis and accurate prediction of user health data can be realized; visual health score and risk factor analysis are provided for the user; the long-term effectiveness in a constantly changing health data environment is ensured; a comprehensive, personalized and dynamically updated health portrait generation platform is provided for the user, the defects in the prior art are overcome, and the method has high application value.

Description

Technical Field

[0001] The present invention relates to the technical field of data acquisition and analysis, and particularly to a health prediction and analysis system and method based on big data deep learning. Background Art

[0002] The prevention and early intervention of diseases are still the main means to reduce people's illness or relieve the pain of illness in the field of modern medicine. The intervention and prevention of diseases can be achieved by controlling various risk factors. Different diseases have different risk factors, and there are many risk factors for diseases. For example, as a cardiovascular and cerebrovascular disease, underlying diseases such as atrial fibrillation time and diabetes history, as well as some lifestyle habits such as smoking and drinking, are all risk factors for stroke.

[0003] Moreover, the influencing factors of risk factors for diseases corresponding to different age groups and genders are different. Generally, elderly patients only learn about their condition when they have a physical examination after the appearance of lesions and symptoms. And patients generally have a physical examination rarely or at a long interval. Among the factors causing diseases, bad eating and rest habits usually account for a certain proportion. For example, consuming high-oil, high-salt, and high-sugar foods is likely to cause obesity and cardiovascular and cerebrovascular diseases. And these diseases can be monitored and intervened in the changes of daily physical signs to prevent the further development of diseases and symptoms. For example, cardiovascular and cerebrovascular diseases are reflected in daily physical signs such as elevated blood pressure, increased heart rate, or irregular fluctuations, and obesity is manifested in changes in breathing frequency, blood oxygen supply and metabolism, and body fat percentage. However, these changes in physical signs occur in daily life and work, and it is difficult to effectively analyze and monitor them in real time. Therefore, a solution is needed to solve this problem. Summary of the Invention

[0004] The purpose of the present invention is to provide a health prediction and analysis system and method based on big data deep learning, so as to solve all or one of the above problems existing in the prior art.

[0005] To solve the above technical problems, the specific technical solutions of the present invention are as follows: On the one hand, the present invention provides a health prediction and analysis system based on big data deep learning, including: an AI terminal and a supporting wearable vital sign sensing device. The vital sign sensing device detects and collects the vital sign data of the wearer's blood oxygen level, heart rate, body surface temperature, sleep index, and exercise condition. The AI terminal and the vital sign sensing device perform positioning communication through a millimeter-wave radar. The AI terminal is data-interconnected with the vital sign sensing device through 4G and WI-FI data communication methods, and obtains the vital sign data detected and collected by the vital sign sensing device for data processing and AI analysis and prediction.

[0006] By adopting the above technical solution, the vital sign sensing device is used to detect and collect the vital sign data, and the AI terminal is used to process the data and perform AI analysis and prediction, so as to quantitatively evaluate the health risk by means of machine learning algorithms.

[0007] Further, the AI terminal is composed of a front cover, a rear cover, a bottom shell, a bottom plate and a main board which are sequentially arranged and connected to each other; the main board is provided with a radar module for receiving and transmitting millimeter waves and an AI module, the two sides of the bottom shell are provided with speaker units, and the front cover is provided with a MIC device.

[0008] By adopting the above technical solution, the positioning communication between the AI terminal and the vital sign sensing device is realized through the radar module, and the application of the AI algorithm is realized through the chip of the AI module.

[0009] Further, corresponding APPs are deployed for remote management of the vital sign sensing device and the AI terminal through the SaaS service mode.

[0010] By adopting the above technical solution, the hardware requirements of the AI terminal are lightened through the SaaS service mode.

[0011] On the other hand, the present invention also provides a method for health analysis and prediction based on big data deep learning, including: collecting vital sign data based on the vital sign sensing device; obtaining corresponding key health index data from the physical examination center platform based on the AI terminal through the SaaS service mode; calculating the personal health index by comparing and analyzing the key health index data and the collected vital sign data based on the AI terminal, specifically as follows: S1, data collection and preprocessing, performing desensitization processing on the corresponding key health index data obtained from the physical examination center platform; S2, feature selection, selecting key health indicators as features based on professional health knowledge and the feature importance scoring system f(x)=Σ(w_i* f_i(x)); S3, establishing a scoring model, using machine learning algorithms of XGboost and random forest, and establishing a health scoring model in combination with the selected features; S4, weight adjustment, adjusting the weights of the key health indicators by combining expert rules and machine learning; S5, generating health suggestions, constructing a recommendation system based on the knowledge graph, and providing health warnings and diet suggestions.

[0012] By adopting the above technical solution, by collecting the basic information of users, such as age, gender, height, weight, disease history and living habits, etc., a health data file of users is constructed, and by applying a variety of AI algorithms, in-depth analysis and accurate prediction of users' health data are realized.

[0013] Further, the mechanism of millimeter-wave positioning communication between the AI terminal and the vital sign sensing device is as follows: M1. The AI terminal emits a transmission signal to the vital sign sensing device in the form of a continuous frequency modulation pulse through the radar module, and receives the echo signal reflected by the vital sign sensing device. The radar module performs frequency modulation on the transmission signal and the echo signal to obtain a difference value, that is, an intermediate frequency signal IF with a specific frequency; M2. After being sampled by the ADC module, the intermediate frequency signal IF is converted into a digital signal, and then the spectral peak fc is obtained through Fourier transform. Then, the target distance R is calculated by using the frequency modulation slope S and the round-trip time T of the radar module receiving the transmission signal and the echo signal.

[0014] By adopting the above technical solution, the position information of the user can be obtained in real time indoors through millimeter-wave positioning communication, so as to draw the user's activity trajectory and rules.

[0015] Further, in M1, the vital sign sensing device enhances the echo signal through a signal enhancement structure.

[0016] By adopting the above technical solution, the signal of the echo signal is enhanced by means of the signal enhancement structure, so that the position information of the user is more accurate.

[0017] The beneficial effects of the technical solution of the present invention are as follows: The present invention comprehensively applies a variety of AI algorithms to realize in-depth analysis and accurate prediction of user health data; the establishment of the scoring model provides users with intuitive health scores and risk factor analysis; in addition, the adjustability and continuous optimization mechanism ensure its long-term effectiveness in a changing health data environment; it provides a comprehensive, personalized and dynamically updated health portrait generation platform for users, making up for the defects of the existing technology and having high application value. Description of the Drawings

[0018] 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, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 It is the external view of the AI terminal in the health prediction and analysis system based on big data deep learning described in Embodiment 1 of the present invention; Figure 2 It is the exploded view of the AI terminal in the health prediction and analysis system based on big data deep learning described in Embodiment 1 of the present invention; Figure 3Schematic diagram of the process of calculating the personal health index by comparing and analyzing the physical sign data collected by the AI terminal through the vital sign sensing device in the health prediction and analysis method based on big data deep learning described in Embodiment 2 of the present invention; Figure 4 Schematic diagram of the process of millimeter-wave positioning communication between the AI terminal and the vital sign sensing device in Embodiment 3 of the present invention; The reference numerals in the drawings are explained as follows: 1. Front cover; 2. MIC device; 3. Radar module; 4. Bottom case; 5. Speaker unit; 6. Main board; 7. Rear cover; 8. Bottom plate. Detailed implementation manners

[0020] The following elaborates on the preferred embodiments of the present invention in conjunction with the drawings, so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making the protection scope of the present invention more clearly defined.

[0021] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be understood as a limitation of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the protection scope of the present invention.

[0022] In the description of the present invention, it should be noted that the embodiments described in the present invention are a part of the embodiments of the present invention, rather than all the embodiments; all other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the protection scope of the present invention.

[0023] In the description, claims and drawings of this document, terms such as "first", "second", etc. are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of this document described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment that includes 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 equipment.

[0024] Embodiment 1, a health prediction and analysis system based on big data deep learning, as Figure 1 and Figure 2 shown, includes: An AI terminal and a supporting wearable vital sign sensing device. The vital sign sensing device can detect and collect the vital sign data of the wearer's blood oxygen level, heart rate, body surface temperature, sleep index and exercise condition. The AI terminal and the vital sign sensing device perform positioning communication through a millimeter-wave radar. The AI terminal can be data-interconnected with the vital sign sensing device through 4G and WI-FI data communication methods, and obtain the vital sign data detected and collected by the vital sign sensing device for data processing and AI analysis and prediction.

[0025] In a specific embodiment, the AI terminal includes a front cover 1, a rear cover 7, a bottom shell 4, a bottom plate 8 and a main board 6. The main board 6 is provided with a radar module 3 for transmitting and receiving millimeter waves and an AI module. The two sides of the bottom shell 4 are provided with speaker units 5, and the front cover 1 is provided with a MIC device 2.

[0026] In a specific embodiment, the vital sign sensing device and the AI terminal are deployed with corresponding APPs through the SaaS service model for remote management.

[0027] In a specific embodiment, the supporting wearable vital sign sensing device can adopt wearable devices such as smart rings, health watches, temperature stickers or continuous blood glucose monitors.

[0028] In a specific embodiment, when the user is in an indoor environment (such as at home, in community elderly care, or in the center of an elderly care institution), the AI terminal can be installed and placed at the area point with the largest radiation coverage. The AI terminal is interconnected with the vital sign sensing device through WI-FI data communication. The vital sign sensing device can monitor the user's vital sign data without feeling all day long. The vital sign sensing device uploads the detected and collected vital sign data to the AI terminal for data processing and AI analysis and prediction. And the AI terminal obtains the operation management logic of the corresponding vital sign sensing device through the SaaS service mode of the remote platform, and the user's relatives can obtain the user's vital sign data and manage the corresponding vital sign sensing device in real time through the corresponding APP. And the AI terminal will monitor the change of vital sign data in real time, and set intelligent voice reminders, two-way calls and warning records personalized, such as setting reminder thresholds according to the user's normal breathing and heart rate, and sending intelligent voice reminders to the user to pay attention when the user's breathing and heart rate are not within the normal thresholds. And it supports two-way calls between the user and the user's relatives, and will record the time period and duration when the user's vital sign data is not within the normal threshold.

[0029] Embodiment 2. This embodiment is based on the same inventive concept as the health prediction and analysis system based on big data deep learning described in Embodiment 1, and provides a health prediction and analysis method based on big data deep learning, as Figure 3 shown, including: Collecting vital sign data based on a vital sign sensing device; obtaining corresponding key health index data from a physical examination center platform by the AI terminal through the SaaS service mode; calculating a personal health index by the AI terminal according to the key health index data and the collected vital sign data. The specific steps of the above method are as follows: S1. Data collection and preprocessing, desensitizing the corresponding key health index data obtained from the physical examination center platform; In a specific embodiment, the AI terminal will first collect the user's basic information, such as age, gender, height, weight, medical history, and living habits, etc., construct a user's health data file, obtain the corresponding key health index data such as blood pressure and blood sugar from the physical examination center platform for desensitization processing. The preprocessing of key health index data includes cleaning and sorting, and uses algorithms such as isolation forest and one-class SVM for anomaly detection to ensure the quality of key health index data; S2. Feature selection, selecting key health indicators as features based on professional health knowledge and a feature importance scoring system f(x)=Σ(w_i* f_i(x)); In a specific embodiment, a Gaussian mixture model is adopted. With the help of a mixture model composed of multiple Gaussian distributions, each Gaussian distribution corresponds to a clustering cluster, which is used to represent different categories or aggregation degrees of key health indicators as features. Among them, w_i is the weight of the i-th Gaussian distribution, and f_i(x) is the probability density function of the i-th Gaussian distribution.

[0030] S3. Establish a scoring model. Use the machine learning algorithms of XGboost and random forest, and combine the selected features to establish a health scoring model. In a specific embodiment, XGboost, that is, Extreme Gradient Boosting Tree, is one of the Boosting algorithms. The idea of the Boosting algorithm is to integrate many weak classifiers together to form a strong classifier. The basic component element of XGboost is the "decision tree", and the decision tree is the "weak learner". There is a sequential order among the decision trees: the generation of the subsequent decision tree will consider the prediction results of the previous decision tree, that is, take into account the deviation of the previous decision tree, so that the training samples misjudged by the previous decision tree will receive more attention subsequently, and then train the next decision tree based on the adjusted sample distribution.

[0031] In a specific embodiment, a random forest is a classifier that uses multiple decision trees to train and predict samples. Randomly select the number of features and randomly select the training data. For the same prediction data, take the prediction label that appears most frequently as the final prediction label. Use the bootstrap method to generate m training sets. Then, for each training set, construct a decision tree. When finding features for splitting at a node, it does not find the one that can maximize the index (such as information gain) for all features, but randomly extracts a part of the features from the features and finds the optimal solution among the extracted features and applies it to the node for splitting. Due to the existence of bagging in the random forest method, that is, the idea of integration, it is actually equivalent to sampling both the samples and the features (if the training data is regarded as a matrix, as is common in practice, then it is a process of sampling both rows and columns), so overfitting can be avoided. The method in the prediction stage is the bagging strategy, voting for classification and taking the mean for regression.

[0032] S4. Adjust the weights. Combine expert rules and machine learning to adjust the weights of key health indicators. In a specific embodiment, experts will set corresponding rules for weight ratio for the health scoring model based on experience and professional knowledge, and then adjust the weights through machine learning to cluster the user's health status in order to better understand the health trends of the user group. S5. Generate health suggestions. Build a recommendation system based on the knowledge graph to provide health warnings and diet suggestions. In a specific implementation, a deep neural network model is used to perform feature learning and transformation on the collected data to form a high-dimensional feature representation vector. Users can obtain corresponding exercise ability reports and cardiopulmonary function through exercise assessment in a physical examination center. When the user enters the exercise state, the AI terminal will conduct real-time monitoring to ensure that the exercise amount is within a safe range, track the exercise effect, be interconnected with an electronic weighing scale, etc., record changes in weight and exercise amount, reasonably plan an exercise plan, and give diet suggestions and health warnings to the user based on a knowledge graph of the user's eating habits, health status, and nutritional intake standards.

[0033] Example 3. This example is based on the same inventive concept as the health prediction and analysis method based on big data deep learning described in Example 2. As Figure 4 shown, a communication mechanism for millimeter-wave positioning communication between an AI terminal and a vital sign sensing device is provided as follows: M1. The AI terminal can transmit a transmission signal to the vital sign sensing device in the form of a continuous frequency modulation pulse through the radar module 3, and receive the echo signal reflected by the vital sign sensing device. The radar module 3 can perform frequency modulation on the transmission signal and the echo signal to obtain a difference, that is, an intermediate frequency signal IF of a specific frequency. When the radar emits a transmission signal in the form of an electromagnetic wave, the frequency of the transmission signal changes linearly, and the frequency of its echo signal also changes linearly. By measuring the difference between the transmission frequency of the current transmission signal and the reception frequency of the echo signal, the distance to the detected object can be obtained, and the frequency of the intermediate frequency signal IF is proportional to the target distance R.

[0034] M2. After the intermediate frequency signal IF is sampled by the ADC module and converted into a digital signal, the spectral peak fc is obtained through Fourier transform, and then the target distance R is calculated through the frequency modulation slope S and the round-trip time T of the radar module 3 receiving the transmission signal and the echo signal. The specific formula is as follows: R = c·T / 2, where c is the speed of light; fc = S·T = S·2R / c = 2BR / (c·Tc); S = B / Tc (signal bandwidth B, signal duration Tc); R = fc·c·Tc / 2B.

[0035] In a specific implementation, in M1, the vital sign sensing device can enhance the echo signal through a signal enhancement structure. The signal enhancement structure is a spherical multi-faceted refractive lens. When an electromagnetic wave irradiates in, it can refract the electromagnetic wave multiple times, gather it at a certain point, and then refract it back and form a scattered electromagnetic wave, so as to achieve the function of enhancing the echo signal.

[0036] Different from the prior art, by adopting a health prediction and analysis system and method based on big data deep learning in this application, various AI algorithms can be comprehensively utilized to achieve in-depth analysis and accurate prediction of user health data; the establishment of the scoring model provides users with intuitive health scores and risk factor analysis; in addition, the adjustability and continuous optimization mechanism ensure its long-term effectiveness in a constantly changing health data environment; and it provides users with a comprehensive, personalized and dynamically updated health portrait generation platform.

[0037] It should be understood that in various embodiments of this article, the magnitude of the serial numbers of the above processes does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of this article.

[0038] It should also be understood that in the embodiments of this article, the term "and / or" is only a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after.

[0039] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights.

[0040] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this article.

[0041] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific logical processes of the above-described methods can refer to the corresponding working processes of the systems, devices, and units in the foregoing method embodiments, and will not be elaborated herein.

[0042] In several embodiments provided in this document, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Additionally, the displayed or discussed couplings or direct couplings or communication connections to each other can be indirect couplings or communication connections through some interfaces, devices, or units, and can also be in the form of electrical, mechanical, or other connections.

[0043] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the objectives of the embodiments of this document.

[0044] In addition, in each embodiment of this document, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0045] If the above-mentioned integrated units are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution in this document, or the part that contributes to the prior art, or all or part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of this document. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, etc., which can store program codes.

[0046] The above are only the embodiments of the present invention and do not limit the patent scope of the present invention. All equivalent structural or equivalent process transformations made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, are equally included in the patent protection scope of the present invention.

Claims

1. A health prediction and analysis system based on big data deep learning, characterized in that: include: AI terminals and matching wearable vital signs sensing devices; The vital sign sensing device is used to detect and collect vital sign data of the wearer's blood oxygen level, heart rate, body surface temperature, sleep index and exercise status; The AI ​​terminal is used to interconnect with the vital sign sensing device data and obtain the vital sign data collected by the vital sign sensing device for data processing and AI analysis and prediction.

2. The health prediction and analysis system based on big data deep learning according to claim 1 is characterized by: The AI ​​terminal and the vital sign sensing device perform positioning communication via millimeter wave radar.

3. The health prediction and analysis system based on big data deep learning according to claim 1 is characterized by: The AI ​​terminal is used to interconnect data with the vital sign sensing device through 4G and WI-FI data communication methods.

4. The health prediction and analysis system based on big data deep learning according to claim 1 is characterized by: The AI ​​terminal is composed of a front cover, a rear cover, a bottom shell, a bottom plate and a main board which are arranged in sequence and connected to each other; a radar module and an AI module for transmitting and receiving millimeter waves are provided on the main board, speaker units are provided on both sides of the bottom shell, and a MIC device is provided on the front cover.

5. The health prediction and analysis system based on big data deep learning according to claim 1 is characterized by: The vital sign sensing device and the AI ​​terminal are also used to deploy corresponding APPs for remote management through the SaaS service model.

6. The health prediction and analysis method based on big data deep learning based on the health prediction and analysis system based on big data deep learning according to any one of claims 1 to 5, characterized in that: The method comprises the following steps: Collect vital sign data based on vital sign sensing equipment; Based on AI terminals, the corresponding key health indicator data is obtained from the physical examination center platform through the SaaS service model; The personal health index is calculated based on the AI ​​terminal by comparing and analyzing the key health indicator data and the collected vital sign data.

7. The health prediction and analysis method based on big data deep learning according to claim 6 is characterized by: The health prediction and analysis method based on big data deep learning further includes: Data collection and preprocessing: Desensitize the corresponding key health indicator data obtained from the physical examination center platform; Feature selection: Select key health indicators as features based on professional health knowledge and feature importance scoring system f(x)=Σ(w_i* f_i(x)); Scoring model establishment: Use XGboost and random forest machine learning algorithms and combine selected features to establish a health scoring model; Weight adjustment: Combining expert rules and machine learning to adjust the weights of key health indicators; Health advice generation: Build a recommendation system based on the knowledge graph to provide health warnings and dietary advice.

8. The health prediction and analysis method based on big data deep learning according to claim 7 is characterized by: Millimeter wave positioning communication is set between the AI ​​terminal and the vital sign sensing device.

9. The health prediction and analysis method based on big data deep learning according to claim 8 is characterized by: The millimeter wave positioning communication mechanism includes: Step M1: The AI ​​terminal transmits a transmission signal to the vital sign sensor device in the form of a continuous frequency modulated pulse through the radar module, and receives an echo signal reflected by the vital sign sensor device. The radar module modulates the transmission signal and the echo signal to obtain a difference, that is, an intermediate frequency signal IF of a specific frequency; Step M2: The intermediate frequency signal IF is sampled by the ADC module and converted into a digital signal, and then the spectrum peak fc is obtained through Fourier transform. The target distance R is then calculated by the frequency modulation slope S and the round-trip time T of the radar module receiving the transmitted signal and the echo signal.

10. The health prediction and analysis method based on big data deep learning according to claim 9 is characterized by: In the step M1, the vital sign sensing device enhances the echo signal through a signal enhancement structure.

Images