Method, device and apparatus for detecting blood glucose concentration

Abstract

The application provides a blood glucose concentration detection method, device and equipment, and relates to the technical field of blood glucose detection. The controller can input the first average infrared reflection light signal data, the second average infrared reflection light signal data and the average Raman laser signal data into a pre-trained blood glucose concentration detection model to output the blood glucose concentration of the human body. Since the output blood glucose concentration of the human body considers the first average infrared reflection light signal data, the second average infrared reflection light signal data and the average Raman laser signal data, the first average infrared reflection light signal data and the average Raman laser signal data can be used to measure the blood glucose concentration. However, the first average infrared reflection light signal data is easily affected by non-blood glucose substances such as water molecules in the human skin. The Raman spectrum is not affected by water molecules, but the signal of the Raman spectrum is relatively weak. Through the coupling of the first average infrared reflection light signal data and the Raman spectrum, the influence can be reduced, more factors are considered, and the obtained blood glucose concentration is higher.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of blood glucose detection, and in particular to a blood glucose concentration detection method, device and equipment. BACKGROUND

[0002] Diabetes is one of the three major chronic diseases in the world, which is caused by insufficient secretion of insulin or inability to utilize, resulting in blood glucose deviating from normal and being at a high level. However, since the existing medical means cannot cure diabetes, and there are no obvious symptoms in the early stage of diabetes, only blood glucose concentration can be determined, therefore, safe, fast, accurate and real-time blood glucose monitoring is of great significance for controlling and treating diabetes.

[0003] The current non-invasive blood glucose detection is usually a single spectrum detection method. However, the detection accuracy of the detection method selecting a single spectrum is low. SUMMARY

[0004] The present application provides a blood glucose concentration detection method, device and equipment, which is used to solve the problem of low detection accuracy of blood glucose concentration in the prior art.

[0005] In a first aspect, the present application provides a blood glucose concentration detection method applied to a blood glucose concentration detection device, the blood glucose concentration detection device comprising a controller, a Raman laser generator, an infrared light source, N Raman laser emitters, N Raman laser receivers, M near-infrared receivers and M far-infrared receivers, wherein M and N are positive integers, the N Raman laser emitters are arranged around the outside of the infrared light source, the M near-infrared receivers are arranged around the outside of the N Raman laser emitters, the M far-infrared receivers are arranged around the outside of the M near-infrared receivers, the N Raman laser receivers are arranged around the outside of the M far-infrared receivers, and each Raman laser receiver is located on the optical path of a Raman laser emitter. The method provided by the present application comprises the following steps:

[0006] The controller controls the infrared light source to emit infrared rays of a first wavelength for detecting water and infrared rays of a second wavelength for detecting glucose to irradiate into the skin of a human body respectively, and the infrared rays of the first wavelength and the second wavelength are reflected by the skin of the human body to the M near-infrared receivers, and the infrared rays of the first wavelength and the second wavelength are reflected by the skin of the human body to the M far-infrared receivers;

[0007] The controller controls the Raman laser generator to generate laser light transmitted to the N Raman laser emitters, and the Raman laser emitted by each Raman laser emitter irradiates into the skin of a human body and is reflected by the skin of the human body to the N Raman laser receivers;

[0008] The controller acquires M first infrared reflection spectrums from the M near-infrared receivers, M second infrared reflection spectrums from the M far-infrared receivers, and a plurality of Raman laser signals from the N Raman laser receivers;

[0009] The controller determines first average infrared reflection light signal data according to the M first infrared reflection spectrums, determines second average infrared reflection light signal data according to the M second infrared reflection spectrums, and determines average Raman laser signal data according to the plurality of Raman laser signals from the N Raman laser receivers.

[0010] The controller inputs the first average infrared reflection light signal data, the second average infrared reflection light signal data, and the average Raman laser signal data into a pre-trained blood glucose concentration detection model to output the blood glucose concentration of the human body, wherein the blood glucose concentration detection model is trained by inputting a plurality of training samples into a network to be trained, each training sample including historical first average infrared reflection light signal data, historical second average infrared reflection light signal data, historical average Raman laser signal data, and corresponding historical blood glucose concentration.

[0011] In a possible implementation, determining the first average infrared reflection light signal data according to the M first infrared reflection spectrums includes:

[0012] According to the formula determining the first infrared reflection spectrum of the i-th near-infrared receiver; wherein i is the number of the near-infrared receiver, j is the time sequence of the infrared signal received by the i-th near-infrared receiver, Sn(i,j)1 is the infrared signal of the first wavelength received by the i-th near-infrared receiver at the j-th time sequence, Sn(i,j)2 is the infrared signal of the second wavelength received by the i-th near-infrared receiver at the j-th time sequence, k is the total number of time sequences, and Sn(i) is the first infrared reflection spectrum of the i-th near-infrared receiver.

[0013] According to the formula determining the first average infrared reflection light signal data, wherein M is the total number of the near-infrared receivers, and Sn is the first average infrared reflection light signal data.

[0014] In a possible implementation, determining the second average infrared reflection light signal data according to the M second infrared reflection spectrums includes:

[0015] According to the formula determining a second infrared reflection spectrum of the i-th far-infrared receiver; wherein i is the number of the far-infrared receiver, j is the time sequence of the infrared signal received by the i-th far-infrared receiver, Sld(i,j)3 is the infrared signal of the first wavelength received by the i-th far-infrared receiver at the j-th time sequence, Sld(i,j)4 is the infrared signal of the second wavelength received by the i-th far-infrared receiver at the j-th time sequence, k is the total number of time sequences, and Sld(i) is the second infrared reflection spectrum of the i-th far-infrared receiver;

[0016] according to the formula determining second average infrared reflection light signal data, wherein M is the total number of far-infrared receivers, and Sld is the second average infrared reflection light signal data.

[0017] In a possible implementation, the average Raman laser signal data is determined according to a plurality of Raman laser signals of N Raman laser receivers, comprising:

[0018] according to the formula determining average Raman laser signal data, wherein R(i,j) is the Raman laser signal of the i-th Raman laser receiver at the j-th time sequence, k is the total number of time sequences, R is the average Raman laser signal data, and N is the total number of Raman laser receivers.

[0019] In a possible implementation, the N Raman laser emitters are arranged at a first angle apart from the infrared light source, and the M near-infrared receivers and the M far-infrared receivers are each arranged at a second angle apart from the infrared light source.

[0020] In a second aspect, the present application provides a blood glucose concentration detection device configured to a controller of a blood glucose concentration detection apparatus, the blood glucose concentration detection apparatus further comprising a Raman laser generator, an infrared light source, N Raman laser emitters, N Raman laser receivers, M near-infrared receivers, and M far-infrared receivers, wherein M and N are positive integers, the N Raman laser emitters are arranged outside the infrared light source, the M near-infrared receivers are arranged outside the N Raman laser emitters, the M far-infrared receivers are arranged outside the M near-infrared receivers, the N Raman laser receivers are arranged outside the M far-infrared receivers, and each Raman laser receiver is located on the light path of a Raman laser emitter. The device provided by the present application comprises:

[0021] a first control unit configured to control the infrared light source to emit infrared light of a first wavelength for detecting water and infrared light of a second wavelength for detecting glucose to irradiate into the skin of the human body, and the infrared light of the first wavelength and the infrared light of the second wavelength are reflected by the skin of the human body to M near-infrared light receivers, and the infrared light of the first wavelength and the infrared light of the second wavelength are reflected by the skin of the human body to M far-infrared light receivers;

[0022] a second control unit configured to control the Raman laser generator to generate laser light transmitted to N Raman laser emitters, and each Raman laser emitter emits Raman laser light to irradiate into the skin of the human body, and the Raman laser light is reflected by the skin of the human body to N Raman laser receivers;

[0023] a data acquisition unit configured to acquire M first infrared reflection spectra from the M near-infrared light receivers, M second infrared reflection spectra from the M far-infrared light receivers, and a plurality of Raman laser signals from the N Raman laser receivers;

[0024] an average data determination unit configured to determine first average infrared reflection light signal data according to the M first infrared reflection spectra, determine second average infrared reflection light signal data according to the M second infrared reflection spectra, and determine average Raman laser signal data according to the plurality of Raman laser signals of the N Raman laser receivers;

[0025] a blood glucose concentration determination unit configured to input the first average infrared reflection light signal data, the second average infrared reflection light signal data, and the average Raman laser signal data into a pre-trained blood glucose concentration detection model to output the blood glucose concentration of the human body, wherein the blood glucose concentration detection model is trained by inputting a plurality of training samples into a to-be-trained network, and each training sample includes historical first average infrared reflection light signal data, historical second average infrared reflection light signal data, historical average Raman laser signal data, and corresponding historical blood glucose concentration.

[0026] In a possible implementation, the average data determination unit is specifically configured to determine the first infrared reflection spectrum of the ith near-infrared light receiver according to determine the first infrared reflection spectrum of the ith near-infrared light receiver; wherein i is the number of the near-infrared light receiver, j is the time sequence of the infrared light signal received by the ith near-infrared light receiver, Sn(i,j)1 is the infrared light signal of the first wavelength received by the ith near-infrared light receiver at the jth time sequence, Sn(i,j)2 is the infrared light signal of the second wavelength received by the near-infrared light receiver at the jth time sequence, k is the total number of time sequences, and Sn(i) is the first infrared reflection spectrum of the ith near-infrared light receiver; according to the formula determining first average infrared reflection light signal data, wherein M is the total number of near-infrared receivers, and Sn is the first average infrared reflection light signal data.

[0027] In a possible implementation, the average data determining unit is specifically configured to determine the first average infrared reflection light signal data according to the formula determining the second infrared reflection spectrum of the i-th far-infrared receiver, wherein i is the number of the far-infrared receiver, j is the time sequence of the infrared signal received by the i-th far-infrared receiver, Sld(i,j)3 is the infrared signal of the first wavelength received by the i-th far-infrared receiver at the j-th time sequence, Sld(i,j)4 is the infrared signal of the second wavelength received by the i-th far-infrared receiver at the j-th time sequence, k is the total number of time sequences, and Sld(i) is the second infrared reflection spectrum of the i-th far-infrared receiver, according to the formula determining second average infrared reflection light signal data, wherein M is the total number of far-infrared receivers, and Sld is the second average infrared reflection light signal data.

[0028] In a possible implementation, the average data determining unit is specifically configured to determine the first average infrared reflection light signal data according to the formula determining average Raman laser signal data, wherein R(i,j) is the Raman laser signal of the i-th Raman laser receiver at the j-th time sequence, k is the total number of time sequences, R is the average Raman laser signal data, and N is the total number of Raman laser receivers.

[0029] In a second aspect, the present application also provides a blood glucose concentration detection device, comprising a controller, a Raman laser generator, an infrared light source, N Raman laser emitters, N Raman laser receivers, M near-infrared receivers, and M far-infrared receivers, wherein M and N are positive integers, the N Raman laser emitters are arranged around the outside of the infrared light source, the M near-infrared receivers are arranged around the outside of the N Raman laser emitters, the M far-infrared receivers are arranged around the outside of the M near-infrared receivers, the N Raman laser receivers are arranged around the outside of the M far-infrared receivers, and each Raman laser receiver is located on the light path of a Raman laser emitter, and the controller is configured to execute the blood glucose concentration detection method provided in the first aspect of the present application.

[0030] The present application provides a blood glucose concentration detection method, device, and equipment, wherein the controller controls the infrared light source to emit infrared rays of a first wavelength for detecting water and infrared rays of a second wavelength for detecting glucose to irradiate into the skin of a human body,

[0031] And the first wavelength of infrared rays and the second wavelength of infrared rays are reflected by the skin of the human body to the M near-infrared receivers, and the first wavelength of infrared rays and the second wavelength of infrared rays are reflected by the skin of the human body to the M far-infrared receivers. The first wavelength of infrared rays is partially absorbed after entering the human skin and is reflected to the near-infrared receiver, and the reflected near-infrared receiver can be used to detect moisture; the second wavelength of infrared rays is partially absorbed after entering the human skin and is reflected to the near-infrared receiver, and the second wavelength of infrared rays reflected to the near-infrared receiver can be used to detect glucose.

[0032] The controller controls the Raman laser generator to generate laser light transmitted to the N Raman laser emitters, and each Raman laser emitter emits Raman laser light that irradiates into the skin of the human body and is reflected by the skin of the human body to the Raman laser receiver. The Raman laser light reflected to the Raman laser receiver can be used to detect a blood glucose signal.

[0033] The controller acquires M first infrared reflection spectra from the M near-infrared receivers, M second infrared reflection spectra from the M far-infrared receivers, and a plurality of Raman laser signals from the N Raman laser receivers.

[0034] The controller determines first average infrared reflection light signal data according to the M first infrared reflection spectra, and the first average infrared reflection light signal data can more accurately express the characteristics of the M first infrared reflection spectra.

[0035] According to the M second infrared reflection spectra, the second average infrared reflection light signal data is determined, which can more accurately express the characteristics of the M second infrared reflection spectra. According to the plurality of Raman laser signals of the N Raman laser receivers, the average Raman laser signal data is determined, which can more accurately express the characteristics of the N Raman laser receivers.

[0036] The controller inputs the first average infrared reflection light signal data, the second average infrared reflection light signal data, and the average Raman laser signal data into the pre-trained blood glucose concentration detection model to output the blood glucose concentration of the human body. The blood glucose concentration detection model is obtained by inputting a plurality of training samples into a to-be-trained network for training, and each training sample includes historical first average infrared reflection light signal data, historical second average infrared reflection light signal data, historical average Raman laser signal data, and corresponding historical blood glucose concentration.

[0037] Since the output blood glucose concentration of the human body considers the first average infrared reflection light signal data, the second average infrared reflection light signal data and the average Raman laser signal data, the first average infrared reflection light signal data and the average Raman laser signal data can be used to measure the blood glucose concentration, but the first average infrared reflection light signal data is easily affected by non-blood glucose substances such as water molecules in the human skin, and the Raman spectrum is not affected by water molecules, but the signal of the Raman spectrum is relatively weak. Through the coupling of the first average infrared reflection light signal data and the Raman spectrum, the influence can be reduced, more factors are considered, and the obtained blood glucose concentration is higher. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0039] Figure 1 The flow chart of the blood glucose concentration detection method provided by the embodiments of the present application;

[0040] Figure 2 The structural schematic diagram of the blood glucose concentration detection device provided by the embodiments of the present application;

[0041] Figure 3 The functional module block diagram of the blood glucose concentration detection device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical scheme and advantages of the embodiments of the present application more clear, the technical scheme in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments made by those skilled in the art according to the inspiration of the present embodiments belong to the scope of protection of the present application.

[0043] The terms "first", "second", "third", "fourth" and the like in the description and in the claims of the present application, and above-mentioned drawings, if any, are used to distinguish between similar objects and not necessarily for describing a specific sequential or chronological order. It is to be understood that the use of these terms here does not imply that the application has to be performed in a specific sequential or chronological order, as a specific sequential or chronological order is not necessarily implied in the present application. Furthermore, the terms "comprise" and "comprising" and any variation thereof, as well as the terms "include" and "including" and any variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, product or apparatus that comprises a list of steps or units is not necessarily limited to those steps or units that are expressly listed, but can include other not expressly listed steps or units.

[0044] The embodiments of the present application provide a blood glucose concentration detection method, which is applied to a blood glucose concentration detection device. Figure 1 As shown in the figure, the blood glucose concentration detection device comprises a controller, a Raman laser generator, an infrared light source 1, N Raman laser emitters 4, N Raman laser receivers 5, M near-infrared receivers 2 and M far-infrared receivers 3, wherein M and N are positive integers. Figure 1 In the embodiment, M=12 and N=4.

[0045] The N Raman laser emitters 4 are arranged outside the infrared light source 1, the M near-infrared receivers 2 are arranged outside the N Raman laser emitters 4, and the thickness of the epidermis near the human wrist is usually 0.8mm-1.2mm. The M near-infrared receivers 2 are arranged outside the N Raman laser emitters 4 in the form of a circular ring with the infrared light source 1 as the center and a radius of D1. It can be understood that, according to Monte Carlo photon transmission path simulation, when the light is vertically incident, the photon penetration depth is half of the distance between the incident point and the receiving point, so 0.16mm≤D1≤2.4mm can be obtained, and D1 can be but is not limited to 2mm.

[0046] The M far-infrared receivers 3 are arranged outside the M near-infrared receivers 2, and the N Raman laser receivers 5 are arranged outside the M far-infrared receivers 3, and each Raman laser receiver 5 is located on the light path of a Raman laser emitter 4. The M near-infrared receivers 2 are arranged outside the M near-infrared receivers 2 in the form of a circular ring with the infrared light source 1 as the center and a radius of D1. D1 can be but is not limited to 6mm.

[0047] Optionally, the N Raman laser emitters 4 are arranged at every first angle (such as 30 degrees) with the infrared light source 1 as the center, and the M near-infrared receivers 2 and the M far-infrared receivers 3 are arranged at every second angle (such as 30 degrees) with the infrared light source 1 as the center. The angle at which the Raman laser is incident on the human skin can be but is not limited to 75 degrees. As shown in the figure, the N Raman laser emitters 4 are arranged at every 30 degrees with the infrared light source 1 as the center, and the M near-infrared receivers 2 and the M far-infrared receivers 3 are arranged at every 30 degrees with the infrared light source 1 as the center.Figure 2 As shown, the method provided by the embodiments of the present application comprises:

[0048] S201: The controller controls the infrared light source 1 to emit infrared light of a first wavelength for detecting water and infrared light of a second wavelength for detecting glucose to irradiate into the skin of the human body respectively, and the infrared light of the first wavelength and the infrared light of the second wavelength are reflected by the skin of the human body to the M near-infrared light receivers 2, and the infrared light of the first wavelength and the infrared light of the second wavelength are reflected by the skin of the human body to the M far-infrared light receivers 3.

[0049] Wherein, since water has an absorption peak at 1100nm-1600nm, the first wavelength can be but is not limited to 1410nm, and the glucose molecule has an absorption peak at 1400nm-1700nm, the second wavelength can be but is not limited to 1550nm.

[0050] S202: The controller controls the Raman laser generator to generate laser light transmitted to the N Raman laser emitters 4, and each Raman laser emitter 4 emits Raman laser light to irradiate into the skin of the human body, and the Raman laser light is reflected by the skin of the human body to the N Raman laser receivers 5.

[0051] Wherein, the Raman laser generator generates laser light transmitted to the N Raman laser emitters 4 through the incident optical fiber. Wherein, the wavelength of the Raman laser light can be but is not limited to 1125nm.

[0052] S203: The controller acquires M first infrared reflection spectra from the M near-infrared light receivers 2, M second infrared reflection spectra from the M far-infrared light receivers 3, and multiple Raman laser signals from the N Raman laser receivers 5.

[0053] Wherein, the controller can acquire M first infrared reflection spectra from the M near-infrared light receivers 2, M second infrared reflection spectra from the M far-infrared light receivers 3, and multiple Raman laser signals from the N Raman laser receivers 5 through the outgoing light rays.

[0054] S204: The controller determines first average infrared reflection light signal data according to the M first infrared reflection spectra, determines second average infrared reflection light signal data according to the M second infrared reflection spectra, and determines average Raman laser signal data according to the multiple Raman laser signals of the N Raman laser receivers 5.

[0055] Specifically, the first average infrared reflection light signal data, the second average infrared reflection light signal data, and the average Raman laser signal data can be determined by determining a first infrared reflection spectrum of the i th near-infrared receiver 2; wherein i is the number of the near-infrared receiver 2, j is the time sequence of the infrared signal received by the i th near-infrared receiver 2, Sn(i,j) 1 is the infrared signal of the first wavelength received by the i th near-infrared receiver 2 at the j th time sequence, Sn(i,j) 2 is the infrared signal of the second wavelength received by the i th near-infrared receiver 2 at the j th time sequence, k is the total number of time sequences, and Sn(i) is the first infrared reflection spectrum of the i th near-infrared receiver 2; according to the formula determining first average infrared reflection light signal data, wherein M is the total number of the near-infrared receivers 2, and Sn is the first average infrared reflection light signal data.

[0056] Specifically, the first average infrared reflection light signal data Sn can be determined according to the formula determining a second infrared reflection spectrum of the i th far-infrared receiver 3; wherein i is the number of the far-infrared receiver 3, j is the time sequence of the infrared signal received by the i th far-infrared receiver 3, Sld(i,j) 3 is the infrared signal of the first wavelength received by the i th far-infrared receiver 3 at the j th time sequence, Sld(i,j) 4 is the infrared signal of the second wavelength received by the i th far-infrared receiver 3 at the j th time sequence, k is the total number of time sequences, and Sld(i) is the second infrared reflection spectrum of the i th far-infrared receiver 3; according to the formula determining second average infrared reflection light signal data, wherein M is the total number of the far-infrared receivers 3, and Sld is the second average infrared reflection light signal data.

[0057] Specifically, the second average infrared reflection light signal data Sld can be determined according to the formula determining average Raman laser signal data; wherein R(i,j) is the Raman laser signal of the i th Raman laser receiver 5 at the j th time sequence, k is the total number of time sequences, R is the average Raman laser signal data, and N is the total number of the Raman laser receivers 5.

[0058] S205: The controller inputs the first average infrared reflection light signal data, the second average infrared reflection light signal data, and the average Raman laser signal data into the pre-trained blood glucose concentration detection model to output the blood glucose concentration of the human body.

[0059] The blood glucose concentration detection model is trained by inputting a plurality of training samples into a to-be-trained network, each training sample comprising historical first average infrared reflection light signal data, historical second average infrared reflection light signal data, historical average Raman laser signal data, and corresponding historical blood glucose concentration. Exemplarily, the to-be-trained network can be, but is not limited to, a PSL regression network and a deep learning network.

[0060] The function of the blood glucose concentration detection model can be simulated as BG = μ * f1(Sld) + φ * f2(R) - σ * f3(Sn) + Δε1, where BG is the blood glucose concentration of the human body, Sld is the second average infrared reflection light signal data, Sn is the first average infrared reflection light signal data, R is the average Raman laser signal data, μ, φ, and σ are weighting coefficients, and Δε1 is a bias coefficient.

[0061] In summary, the present application provides a blood glucose concentration detection method, a controller controls an infrared light source 1 to emit infrared light of a first wavelength for detecting water and infrared light of a second wavelength for detecting glucose to irradiate into the skin of a human body,

[0062] and the infrared light of the first wavelength and the infrared light of the second wavelength are reflected by the skin of the human body to M near-infrared receivers 2, and the infrared light of the first wavelength and the infrared light of the second wavelength are reflected by the skin of the human body to M far-infrared receivers 3. The infrared light of the first wavelength is partially absorbed after entering the human skin and is reflected to the near-infrared receiver 2, which can be used for detecting water; the infrared light of the second wavelength is partially absorbed after entering the human skin and is reflected to the near-infrared receiver 2, and the infrared light of the second wavelength reflected to the near-infrared receiver 2 can be used for detecting glucose.

[0063] The controller controls a Raman laser generator to generate laser light transmitted to N Raman laser emitters 4, and each Raman laser emitter 4 emits Raman laser light to irradiate into the skin of the human body, and the Raman laser light is reflected by the skin of the human body to a Raman laser receiver 5, and the Raman laser light reflected to the Raman laser receiver 5 can be used for detecting a blood glucose signal.

[0064] The controller acquires M first infrared reflection spectra from the M near-infrared receivers 2, M second infrared reflection spectra from the M far-infrared receivers 3, and multiple Raman laser signals from the N Raman laser receivers 5.

[0065] The controller determines first average infrared reflection light signal data according to the M first infrared reflection spectra, which can more accurately express the characteristics of the M first infrared reflection spectra.

[0066] According to the M second infrared reflection spectra, the second average infrared reflection light signal data is determined, which can more accurately express the characteristics of the M second infrared reflection spectra. According to the multiple Raman laser signals of the N Raman laser receivers 5, the average Raman laser signal data is determined, which can more accurately express the characteristics of the N Raman laser receivers 5.

[0067] The controller inputs the first average infrared reflection light signal data, the second average infrared reflection light signal data, and the average Raman laser signal data into the pre-trained blood glucose concentration detection model to output the blood glucose concentration of the human body. The blood glucose concentration detection model is trained by inputting a plurality of training samples into a network to be trained, each of the training samples including historical first average infrared reflection light signal data, historical second average infrared reflection light signal data, historical average Raman laser signal data, and corresponding historical blood glucose concentration.

[0068] Since the output blood glucose concentration of the human body considers the first average infrared reflection light signal data, the second average infrared reflection light signal data, and the average Raman laser signal data, the first average infrared reflection light signal data and the average Raman laser signal data can be used to measure the blood glucose concentration. However, the first average infrared reflection light signal data is easily affected by non-blood glucose substances such as water molecules in the human skin, and the Raman spectrum is not affected by water molecules, but the signal of the Raman spectrum is relatively weak. By coupling the first average infrared reflection light signal data and the Raman spectrum, the influence can be reduced, more factors are considered, and the obtained blood glucose concentration is higher.

[0069] Please refer to Figure 3 The application also provides a blood glucose concentration detection device, which is configured to a controller of a blood glucose concentration detection apparatus. The blood glucose concentration detection apparatus further includes a Raman laser generator, an infrared light source 1, N Raman laser emitters 4, N Raman laser receivers 5, M near-infrared receivers 2, and M far-infrared receivers 3. M and N are positive integers. The N Raman laser emitters 4 are arranged around the outside of the infrared light source 1. The M near-infrared receivers 2 are arranged around the outside of the N Raman laser emitters 4. The M far-infrared receivers 3 are arranged around the outside of the M near-infrared receivers 2. The N Raman laser receivers 5 are arranged around the outside of the M far-infrared receivers 3. Each Raman laser receiver 5 is located on the light path of one Raman laser emitter 4. The device provided by the application includes a first control unit, a second control unit, a data acquisition unit, an average data determination unit, and a blood glucose concentration determination unit.

[0070] The first control unit is configured to control the infrared light source 1 to emit infrared light of a first wavelength for detecting water and infrared light of a second wavelength for detecting glucose to irradiate into the skin of the human body. The infrared light of the first wavelength and the infrared light of the second wavelength are reflected by the skin of the human body to the M near-infrared receivers 2, and the infrared light of the first wavelength and the infrared light of the second wavelength are reflected by the skin of the human body to the M far-infrared receivers 3.

[0071] a second control unit configured to control the Raman laser generator to generate laser light transmitted to the N Raman laser emitters 4, each of which emits Raman laser light that irradiates into the skin of the human body and is reflected by the skin of the human body to the N Raman laser receivers 5.

[0072] a data acquisition unit configured to acquire M first infrared reflection spectra from the M near-infrared receivers 2, M second infrared reflection spectra from the M far-infrared receivers 3, and a plurality of Raman laser signals from the N Raman laser receivers 5.

[0073] an average data determination unit configured to determine first average infrared reflection light signal data according to the M first infrared reflection spectra, determine second average infrared reflection light signal data according to the M second infrared reflection spectra, and determine average Raman laser signal data according to the plurality of Raman laser signals from the N Raman laser receivers 5.

[0074] a blood glucose concentration determination unit configured to input the first average infrared reflection light signal data, the second average infrared reflection light signal data, and the average Raman laser signal data into a pre-trained blood glucose concentration detection model to output a blood glucose concentration of the human body, wherein the blood glucose concentration detection model is trained by inputting a plurality of training samples into a network to be trained, each of the training samples including historical first average infrared reflection light signal data, historical second average infrared reflection light signal data, historical average Raman laser signal data, and a corresponding historical blood glucose concentration.

[0075] In a possible implementation, the average data determination unit is specifically configured to determine the first infrared reflection spectrum of the ith near-infrared receiver 2 according to the formula determine the first infrared reflection spectrum of the ith near-infrared receiver 2; wherein i is the number of the near-infrared receiver 2, j is the time sequence of the infrared signal received by the ith near-infrared receiver 2, Sn(i,j)1 is the infrared signal of the first wavelength received by the ith near-infrared receiver 2 at the jth time sequence, Sn(i,j)2 is the infrared signal of the second wavelength received by the ith near-infrared receiver 2 at the jth time sequence, k is the total number of time sequences, and Sn(i) is the first infrared reflection spectrum of the ith near-infrared receiver 2; and determine the first average infrared reflection light signal data according to the formula determine the first average infrared reflection light signal data, wherein M is the total number of the near-infrared receivers 2, Sn is the first average infrared reflection light signal data, and the data range is 38500000-39000000.

[0076] In a possible implementation, the average data determination unit is specifically configured to determine the first infrared reflection spectrum of the ith near-infrared receiver 2 according to the formula determining a second infrared reflection spectrum of the i-th far infrared receiver 3; wherein i is the number of the far infrared receiver 3, j is the time sequence of the infrared signal received by the i-th far infrared receiver 3, Sld(i,j)3 is the infrared signal of the first wavelength received by the i-th far infrared receiver 3 at the j-th time sequence, Sld(i,j)4 is the infrared signal of the second wavelength received by the i-th far infrared receiver 3 at the j-th time sequence, k is the total number of the time sequences, Sld(i) is the second infrared reflection spectrum of the i-th far infrared receiver 3; according to the formula determining second average infrared reflection light signal data, wherein M is the total number of the far infrared receivers 3, Sld is the second average infrared reflection light signal data, the data range is 750000-1250000.

[0077] In a possible implementation, the average data determining unit is specifically configured to determine the second average infrared reflection light signal data according to the formula determining average Raman laser signal data, wherein R(i,j) is the Raman laser signal of the i-th Raman laser receiver 5 at the j-th time sequence, k is the total number of the time sequences, R is the average Raman laser signal data, the value range is 8000-10000, N is the total number of the Raman laser receivers 5, and the number of the embodiment is 4.

[0078] In addition, as shown in Figure 1 the embodiment of the present application further provides a blood glucose concentration detection device, which comprises a controller, a Raman laser generator, an infrared light source 1, N Raman laser emitters 4, N Raman laser receivers 5, M near infrared receivers 2 and M far infrared receivers 3, wherein M and N are positive integers, the N Raman laser emitters 4 are arranged outside the infrared light source 1, the M near infrared receivers 2 are arranged outside the N Raman laser emitters 4, the M far infrared receivers 3 are arranged outside the M near infrared receivers 2, the N Raman laser receivers 5 are arranged outside the M far infrared receivers 3, and each Raman laser receiver 5 is located on the light path of one Raman laser emitter 4, and the controller is configured to execute the blood glucose concentration detection method provided in the above embodiment.

[0079] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A blood glucose concentration detecting method characterized by comprising: The application is applied to a blood glucose concentration detection device, which comprises a controller, a Raman laser generator, an infrared light source, N Raman laser emitters, N Raman laser receivers, M near-infrared receivers, and M far-infrared receivers, wherein M and N are positive integers, the N Raman laser emitters are arranged around the infrared light source, the M near-infrared receivers are arranged around the N Raman laser emitters, the M far-infrared receivers are arranged around the M near-infrared receivers, the N Raman laser receivers are arranged around the M far-infrared receivers, and each Raman laser receiver is located on the light path of one Raman laser emitter, and the method comprises the following steps: The controller controls the infrared light source to emit infrared rays of a first wavelength for detecting moisture and infrared rays of a second wavelength for detecting glucose to irradiate into the skin of a human body, and the infrared rays of the first wavelength and the second wavelength are reflected by the skin of the human body to the M near-infrared receivers and the M far-infrared receivers; The controller controls the Raman laser generator to generate laser transmission to the N Raman laser emitters, each Raman laser emitter emits Raman laser to irradiate into the skin of a human body, and the Raman laser is reflected by the skin of the human body to the N Raman laser receivers; The controller acquires M first infrared reflection spectra from the M near-infrared receivers, M second infrared reflection spectra from the M far-infrared receivers, and multiple Raman laser signals from the N Raman laser receivers; The controller determines first average infrared reflection light signal data according to the M first infrared reflection spectra, determines second average infrared reflection light signal data according to the M second infrared reflection spectra, and determines average Raman laser signal data according to the multiple Raman laser signals of the N Raman laser receivers; The controller inputs the first average infrared reflection light signal data, the second average infrared reflection light signal data, and the average Raman laser signal data into a pre-trained blood glucose concentration detection model to output the blood glucose concentration of the human body, wherein the blood glucose concentration detection model is obtained by inputting multiple training samples into a network to be trained, and each training sample comprises historical first average infrared reflection light signal data, historical second average infrared reflection light signal data, historical average Raman laser signal data, and corresponding historical blood glucose concentration.

2. The method of claim 1, wherein, The determination of the first average infrared reflection light signal data according to the M first infrared reflection spectra comprises the following steps: According to determining a first infrared reflection spectrum of the ith near-infrared receiver; wherein i is the number of the near-infrared receiver, j is the time sequence of the infrared signal received by the ith near-infrared receiver, Sn(i,j)1 is the infrared signal of the first wavelength received by the ith near-infrared receiver at the jth time sequence, Sn(i,j)2 is the infrared signal of the second wavelength received by the near-infrared receiver at the jth time sequence, k is the total number of time sequences, and Sn(i) is the first infrared reflection spectrum of the ith near-infrared receiver. According to the formula determining first average infrared reflected light signal data, wherein M is the total number of the near infrared receivers, and Sn is the first average infrared reflected light signal data.

3. The method of claim 1, wherein, The determination of the second average infrared reflection light signal data according to the M second infrared reflection spectra comprises the following steps: According to the formula determining a second infrared reflection spectrum of the i-th far infrared receiver; wherein i is the number of the far infrared receiver, j is the time sequence of the infrared signal received by the i-th far infrared receiver, Sld(i,j)3 is the infrared signal of the first wavelength received by the i-th far infrared receiver at the j-th time sequence; Sld(i,j)4) is the infrared signal of the second wavelength received by the i-th far infrared receiver at the j-th time sequence, k is the total number of time sequences, Sld(i) is the second infrared reflection spectrum of the i-th far infrared receiver; According to the formula determining second average infrared reflected light signal data, where M is the total number of the far infrared receivers, and Sld is the second average infrared reflected light signal data.

4. The method of claim 1, wherein, The determination of the average Raman laser signal data according to the multiple Raman laser signals of the N Raman laser receivers comprises the following steps: According to the formula determining average Raman laser signal data, wherein R(i,j) is a Raman laser signal of an i-th Raman laser receiver at a j-th time sequence, K is a total number of time sequences, R is the average Raman laser signal data, and N is a total number of the Raman laser receivers.

5. The method of claim 1, wherein, The N Raman laser emitters are arranged at a first angle apart from the infrared light source as a center; and the M near-infrared receivers and the M far-infrared receivers are arranged at a second angle apart from the infrared light source as a center.

6. A blood glucose concentration detecting apparatus characterized by comprising: The controller is configured to be arranged in a blood glucose concentration detection device, the blood glucose concentration detection device further comprising a Raman laser generator, an infrared light source, N Raman laser emitters, N Raman laser receivers, M near-infrared receivers, and M far-infrared receivers, wherein M and N are positive integers, the N Raman laser emitters are arranged outside the infrared light source, the M near-infrared receivers are arranged outside the N Raman laser emitters, the M far-infrared receivers are arranged outside the M near-infrared receivers, the N Raman laser receivers are arranged outside the M far-infrared receivers, and each of the Raman laser receivers is located on an optical path of one of the Raman laser emitters. The first control unit is configured to control the infrared light source to emit infrared light of a first wavelength for detecting water and infrared light of a second wavelength for detecting glucose to irradiate into the skin of a human body, and the infrared light of the first wavelength and the infrared light of the second wavelength are reflected by the skin of the human body to the M near-infrared receivers and the M far-infrared receivers. The second control unit is configured to control the Raman laser generator to generate laser light transmitted to the N Raman laser emitters, and each of the Raman laser emitters emits Raman laser light to irradiate into the skin of the human body and is reflected by the skin of the human body to the N Raman laser receivers. The data acquisition unit is configured to acquire M first infrared reflection spectra from the M near-infrared receivers, M second infrared reflection spectra from the M far-infrared receivers, and a plurality of Raman laser signals from the N Raman laser receivers. The average data determination unit is configured to determine first average infrared reflection light signal data according to the M first infrared reflection spectra, determine second average infrared reflection light signal data according to the M second infrared reflection spectra, and determine average Raman laser signal data according to the plurality of Raman laser signals of the N Raman laser receivers. The blood glucose concentration determination unit is configured to input the first average infrared reflection light signal data, the second average infrared reflection light signal data, and the average Raman laser signal data into a pre-trained blood glucose concentration detection model to output the blood glucose concentration of the human body, wherein the blood glucose concentration detection model is obtained by inputting a plurality of training samples into a network to be trained, and each of the training samples comprises historical first average infrared reflection light signal data, historical second average infrared reflection light signal data, historical average Raman laser signal data, and corresponding historical blood glucose concentration.

7. The apparatus of claim 6, wherein, The average data determination unit is specifically configured to determine the first infrared reflection spectrum of the ith near-infrared receiver according to Sn(i,j)1 is the infrared signal of the first wavelength received by the jth time sequence of the ith near-infrared receiver; Sn(i,j)2 is the infrared signal of the second wavelength received by the jth time sequence of the near-infrared receiver; k is the total number of time sequences; and Sn(i) is the first infrared reflection spectrum of the ith near-infrared receiver; according to the formula determine the first average infrared reflection light signal data, wherein M is the total number of the near-infrared receivers, and Sn is the first average infrared reflection light signal data.

8. The apparatus of claim 6, wherein, The average data determination unit is specifically configured to determine the second infrared reflection spectrum of the i-th far infrared receiver according to an algorithm determining the second infrared reflection spectrum of the i-th far infrared receiver; wherein i is the number of the far infrared receiver, j is the time sequence of the infrared signal received by the i-th far infrared receiver, Sld(i,j)3 is the infrared signal of the first wavelength received by the i-th far infrared receiver at the j-th time sequence, Sld(i,j)4 is the infrared signal of the second wavelength received by the i-th far infrared receiver at the j-th time sequence, k is the total number of time sequences, and Sld(i) is the second infrared reflection spectrum of the i-th far infrared receiver; and determining the second average infrared reflection spectrum data according to an algorithm determining the second average infrared reflection spectrum data, wherein M is the total number of the far infrared receivers, and Sld is the second average infrared reflection spectrum data.

9. The apparatus of claim 6, wherein, The average data determination unit is specifically configured to determine the average Raman laser signal data according to an algorithm determining average Raman laser signal data, wherein R(i,j) is a Raman laser signal of an i-th Raman laser receiver at a j-th time sequence, K is a total number of time sequences, R is the average Raman laser signal data, and N is a total number of the Raman laser receivers.

10. A blood glucose concentration detecting apparatus characterized by comprising: The application relates to a blood glucose concentration detection device, which comprises a controller, a Raman laser generator, an infrared light source, N Raman laser emitters, N Raman laser receivers, M near-infrared receivers and M far-infrared receivers, wherein M and N are positive integers, the N Raman laser emitters are arranged around the infrared light source, the M near-infrared receivers are arranged around the N Raman laser emitters, the M far-infrared receivers are arranged around the M near-infrared receivers, the N Raman laser receivers are arranged around the M far-infrared receivers, and each Raman laser receiver is located on the light path of one Raman laser emitter, wherein the controller is used for executing the blood glucose concentration detection method in any one of claims 1-5.

Images