A non-contact physiological and mental health detection device based on AI

Abstract

The present invention proposes an AI-based non-contact physiological and psychological health detection device, comprising a cabinet, a host, a liquid crystal display, a high-precision camera, a multi-wavelength RGB camera, a fill light, an ID card swiping module, a social security card swiping module, an IC card swiping module, a printer, and a power supply; a high-precision camera is used to collect facial images of a human body, and facial parameters are obtained based on the facial images; a multi-wavelength RGB camera is used to detect subtle color changes caused by pulses on the surface of human skin, and RPPG technology is used to extract blood volume pulse signals to obtain physiological parameters, and a deep learning network is used to perform real-time analysis and processing of facial parameters and physiological parameters to evaluate the health status of a user; and the results, facial parameters, and physiological parameters output by the AI ​​analysis module are visualized and displayed on the liquid crystal display, so that the user can better understand his or her own health status.

Description

Technical Field

[0001] The present invention relates to the field of health detection technology, and in particular to an AI-based non-contact physiological and psychological health detector. Background Art

[0002] With the improvement of people's living standards and the enhancement of health awareness, the demand for physiological and mental health testing is increasing. However, the traditional contact detection method requires the use of electrodes, sensors and other equipment to directly contact the human body, which is not only cumbersome to operate, but may also cause discomfort to the user. In addition, for some special groups (such as infants and young children), the contact detection method has great limitations. Therefore, the development of a non-contact, efficient and accurate physiological and mental health detection device has important practical significance. Summary of the invention

[0003] The purpose of the present invention is to provide an AI-based non-contact physiological and psychological health detection device, which uses advanced AI technology and non-contact sensing technology to achieve real-time, non-invasive detection of human physiological and psychological health parameters, so as to improve detection efficiency and accuracy, while reducing user discomfort. In order to achieve the above purpose, the present invention adopts the following technical solutions:

[0004] A non-contact physiological and mental health detection device based on AI, characterized in that the device comprises: a cabinet, a host, a liquid crystal display, a high-precision camera, a multi-wavelength RGB camera, a fill light, an ID card swiping module, a social security card swiping module, a QR code scanning module, a printer, and a power supply;

[0005] A high-precision camera is used to collect facial images of the human body, and facial parameters are obtained based on the facial images;

[0006] A multi-wavelength RGB camera is used to detect subtle color changes caused by pulses on the human skin surface, and RPPG technology is used to extract blood volume pulse signals to obtain physiological parameters, including heart rate, respiratory rate, heart rate variability (HRV), blood oxygen content, and blood pressure parameters;

[0007] An AI analysis module is encapsulated in the host: the AI ​​analysis module uses a deep learning network to perform real-time analysis and processing of facial parameters and physiological parameters to evaluate the user's health status;

[0008] Data display module: The output results, facial parameters, and physiological parameters of the AI ​​analysis module are visualized and displayed on the LCD display so that users can better understand their own health status.

[0009] Furthermore, an identity recognition module is encapsulated in the host, and a user selects a recognition method through a liquid crystal display, and the recognition methods include an identity card recognition method, a social security card recognition method, and a QR code recognition method.

[0010] Further, when the user selects the ID card identification method or the social security card identification method, the user performs identity identification through the ID card swiping module or the social security card swiping module in the device.

[0011] Furthermore, when the user selects the QR code recognition method, the user performs identity recognition by scanning the code.

[0012] Furthermore, the device also includes an IC card swiping module.

[0013] Furthermore, the identification method includes an IC card identification method. When the user selects the IC card identification method, the user performs identity identification through an IC card swiping module in the device.

[0014] Furthermore, the facial parameters include facial expressions, eye expressions, and skin color.

[0015] Furthermore, the deep learning network includes:

[0016] The facial parameters and physiological parameters are used as inputs to a deep learning network, and a health status is output, where the health status is a score of 1 to 100, and the larger the score, the better the health status of the user;

[0017] The deep learning network includes:

[0018] The facial parameters and physiological parameters are input into the first convolution module and the second convolution module connected in sequence to obtain feature F, the feature F is input into the GN layer and the Sigmoid layer connected in sequence, the output of the Sigmoid layer is recorded as w, and features F1 and F2 are calculated; wherein, ; ;

[0019] The F1 is passed through the third convolutional module, the pooling layer, and the sigmoid layer connected in sequence to obtain ;

[0020] The F2 is passed through the fourth convolutional module, the pooling layer, and the sigmoid layer connected in sequence to obtain ;

[0021] Based on F1, F2, , , calculate the features F1' and F2', where

[0022] ; ;

[0023] The F1' and F2' are fused to obtain the feature Fout, where: ;

[0024] The Fout is input into the fully connected layer and the softmax layer to obtain a predicted value, which represents the health status.

[0025] Furthermore, the convolution module includes: a convolution layer, a BN layer, and a ReLU layer.

[0026] Furthermore, a printing processing module is encapsulated in the host, and when the user clicks the print function through the LCD display, the facial parameters, physiological parameters and health status are typeset and printed.

[0027] The beneficial effects of the present invention are:

[0028] 1. It realizes non-contact physiological and mental health testing, avoiding the discomfort and limitations brought by traditional contact testing methods.

[0029] 2. The accuracy and efficiency of detection are improved through the application of AI technology and deep learning algorithms.

[0030] 3. It provides intuitive and easy-to-understand data display and a friendly interactive interface, enhancing the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the specific implementation of the present invention or the technical solution in the prior art, the drawings required for describing the specific implementation or the prior art will be briefly introduced below. Obviously, the drawings described below are only one implementation of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 This is a structural diagram of the AI-based non-contact physiological and mental health detection device of the present invention;

[0033] Figure 2 This is an architecture diagram of the deep learning network of the present invention. DETAILED DESCRIPTION

[0034] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the technical scheme in the specific implementation mode of the present invention is clearly and completely described below to further illustrate the present invention. Obviously, the specific implementation mode described is only a part of the implementation mode of the present invention, rather than all styles.

[0035] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0036] As attached Figure 1 As shown, the present invention discloses a non-contact physiological and psychological health detection device based on AI, characterized in that the device comprises: a cabinet, a host, a liquid crystal display, a high-precision camera, a multi-wavelength RGB camera, a fill light, an ID card swiping module, a social security card swiping module, a QR code scanning module, a printer, and a power supply;

[0037] A high-precision camera is used to collect facial images of the human body, and facial parameters are obtained based on the facial images;

[0038] A multi-wavelength RGB camera is used to detect subtle color changes caused by pulses on the human skin surface, and RPPG technology is used to extract blood volume pulse signals to obtain physiological parameters, including heart rate, respiratory rate, heart rate variability (HRV), blood oxygen content, and blood pressure parameters;

[0039] An AI analysis module is encapsulated in the host: the AI ​​analysis module uses a deep learning network to perform real-time analysis and processing of facial parameters and physiological parameters to evaluate the user's health status;

[0040] Data display module: The output results, facial parameters, and physiological parameters of the AI ​​analysis module are visualized and displayed on the LCD display so that users can better understand their own health status.

[0041] Furthermore, an identity recognition module is encapsulated in the host, and a user selects a recognition method through a liquid crystal display, and the recognition methods include an identity card recognition method, a social security card recognition method, and a QR code recognition method.

[0042] Further, when the user selects the ID card identification method or the social security card identification method, the user performs identity identification through the ID card swiping module or the social security card swiping module in the device.

[0043] Furthermore, when the user selects the QR code recognition method, the user performs identity recognition by scanning the code.

[0044] Furthermore, the device also includes an IC card swiping module.

[0045] Furthermore, the identification method includes an IC card identification method. When the user selects the IC card identification method, the user performs identity identification through an IC card swiping module in the device.

[0046] Furthermore, the facial parameters include facial expressions, eye expressions, and skin color.

[0047] Further, as attached Figure 2 As shown, the deep learning network includes:

[0048] The facial parameters and physiological parameters are used as inputs to a deep learning network, and a health status is output, where the health status is a score of 1 to 100, and the larger the score, the better the health status of the user;

[0049] The deep learning network includes:

[0050] The facial parameters and physiological parameters are input into the first convolution module and the second convolution module connected in sequence to obtain feature F, the feature F is input into the GN layer and the Sigmoid layer connected in sequence, the output of the Sigmoid layer is recorded as w, and features F1 and F2 are calculated; wherein, ; ;

[0051] The F1 is passed through the third convolutional module, the pooling layer, and the sigmoid layer connected in sequence to obtain ;

[0052] The F2 is passed through the fourth convolutional module, the pooling layer, and the sigmoid layer connected in sequence to obtain ;

[0053] Based on F1, F2, , , calculate the features F1' and F2', where

[0054] ; ;

[0055] The F1' and F2' are fused to obtain the feature Fout, where: ;

[0056] The Fout is input into the fully connected layer and the softmax layer to obtain a predicted value, which represents the health status.

[0057] Furthermore, the convolution module includes: a convolution layer, a BN layer, and a ReLU layer.

[0058] In order to improve the accuracy of prediction, the convolutional layers in the convolutional module in this embodiment include G groups of convolutional filters, and the number of input channels is M;

[0059] The convolution filter includes two identical branches, each of which includes: a first convolution part and a second convolution part, the first convolution part includes an M / G layer and a first convolution layer, and the first convolution layer includes a 3×3 convolution layer and a first 1×1 convolution layer connected in sequence;

[0060] The second convolution part includes a second 1×1 convolution layer of the MM / G layer, and the first 1×1 convolution layer is located above the second 1×1 convolution layer;

[0061] From the first group of convolution filters to the Gth group of convolution filters, the position of the first convolution part is shifted downward from the top by M / G layers in sequence until the first convolution part of the Gth group of convolution filters is located at the bottom.

[0062] Preferably, the computational complexity of the dual convolutional layer is for:

[0063]

[0064] in, Do represents the width and height dimensions of the output features, M represents the number of input feature channels, where represents the convolution kernel size, N represents the number of convolution filters, G Indicates the number of convolution groups.

[0065] Furthermore, a printing processing module is encapsulated in the host, and when the user clicks the print function through the LCD display, the facial parameters, physiological parameters and health status are typeset and printed.

[0066] Furthermore, some suggestions can be provided based on the user's facial parameters, physiological parameters and health status.

[0067] Furthermore, the device also includes a database module, in which facial parameters, physiological parameters, health status and corresponding suggestions are stored. When the user needs relevant suggestions, the database can be queried and prompted to the user.

[0068] The above describes the main technical features and basic principles of the present invention and the related advantages. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the concept or basic features of the present invention. Therefore, no matter from which point of view, the above specific embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the present invention.

[0069] In addition, it should be understood that although the present specification is described according to various implementation methods, not every implementation method contains only one independent technical solution. This narrative method of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each implementation method may also be appropriately combined to form other implementation methods that can be understood by those skilled in the art.

Claims

1. A non-contact physiological and mental health detection device based on AI, characterized in that: The device includes: a cabinet, a host, a liquid crystal display, a high-precision camera, a multi-wavelength RGB camera, a fill light, an ID card swiping module, a social security card swiping module, a QR code scanning module, an IC card swiping module, a printer, and a power supply; A high-precision camera is used to collect facial images of the human body, and facial parameters are obtained based on the facial images; A multi-wavelength RGB camera is used to detect subtle color changes caused by pulses on the human skin surface, and RPPG technology is used to extract blood volume pulse signals to obtain physiological parameters, including heart rate, respiratory rate, heart rate variability (HRV), blood oxygen content, and blood pressure parameters; An AI analysis module is encapsulated in the host: the AI ​​analysis module uses a deep learning network to perform real-time analysis and processing of facial parameters and physiological parameters to evaluate the user's health status; Data display module: visualize the output results, facial parameters, and physiological parameters of the AI ​​analysis module and display them on the LCD; The deep learning network includes: The facial parameters and physiological parameters are used as inputs to a deep learning network, and a health status is output, where the health status is a score of 1 to 100, and the larger the score, the better the health status of the user; The deep learning network includes: The facial parameters and physiological parameters are input into the first convolution module and the second convolution module connected in sequence to obtain feature F, the feature F is input into the GN layer and the Sigmoid layer connected in sequence, the output of the Sigmoid layer is recorded as w, and features F1 and F2 are calculated; wherein, ; ; The F1 is passed through the third convolutional module, the pooling layer, and the sigmoid layer connected in sequence to obtain ; The F2 is passed through the fourth convolutional module, the pooling layer, and the sigmoid layer connected in sequence to obtain ; Based on F1, F2, , , calculate the features F1' and F2', where ； ; The F1' and F2' are fused to obtain the feature Fout, where: ; The Fout is input into the fully connected layer and the softmax layer to obtain a predicted value, which represents the health status.

2. The AI-based non-contact physiological and psychological health detection device according to claim 1 is characterized in that: The host is encapsulated with an identity recognition module, and the user selects an identification method through a liquid crystal display, and the identification methods include an identity card identification method, a social security card identification method, and a QR code identification method.

3. The AI-based non-contact physiological and psychological health detection device according to claim 2 is characterized in that: When the user selects the ID card identification method or the social security card identification method, the user performs identity identification through the ID card swiping module or the social security card swiping module in the device.

4. The AI-based non-contact physiological and psychological health detection device according to claim 2 is characterized in that: When the user selects the QR code recognition method, the user identifies himself by scanning the code.

5. The AI-based non-contact physiological and psychological health detection device according to claim 2 is characterized in that: The identification method includes an IC card identification method. When the user selects the IC card identification method, identity identification is performed through an IC card swiping module in the device.

6. The AI-based non-contact physiological and psychological health detection device according to claim 1 is characterized in that: The facial parameters include facial expression, eye expression, and skin color.

7. The AI-based non-contact physiological and psychological health detection device according to claim 1 is characterized in that: The convolution module includes: a convolution layer, a BN layer, and a ReLU layer.

8. The AI-based non-contact physiological and psychological health detection device according to claim 1 is characterized in that: A printing processing module is encapsulated in the host. When the user clicks the print function through the LCD display, the facial parameters, physiological parameters and health status are typeset and printed.

Images