A non-invasive intelligent blood sugar measuring instrument
Through near-infrared image acquisition and artificial intelligence calibration, the trauma and consumables problems of traditional blood sugar measuring instruments are solved, and non-invasive, real-time, consumables-free blood sugar monitoring is achieved, and the quality of life of diabetic patients is improved.
Patent Information
- Application Number
- CN202080032405.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2019-03-21
- Filing Date
- 2020-03-18
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2040-03-18
AI Technical Summary
The existing blood glucose measuring instrument requires finger piercing during the measurement process, which causes pain and trauma, and frequently requires consumables, poor usage experience and high financial pressure. The so-called trauma-free instrument still requires traditional blood collection and modeling in the early stage, which is not considered true. No trauma.
It adopts a near-infrared image acquisition device and processor to collect near-infrared photos of fingers through a near-infrared camera and light source, and combines artificial intelligence machine learning algorithms for comparison and calibration to directly output blood sugar measurement results, without blood samples or blood stains, avoiding trauma and consumables.
It achieves trauma-free, real-time blood sugar measurements, reduces pain and financial stress, improves user experience and quality of life, and records historical data to help doctors analyze and treat.
Smart Images

Figure CN113811243B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to a blood glucose meter, in particular to a non-invasive intelligent blood glucose meter. Background Art
[0002] As we all know, there are billions of diabetics and potential diabetics worldwide. Diabetes has become a very serious problem that affects people's health and quality of life. Diabetics need to prevent chronic and acute complications of the disease from time to time, so diabetic patients need to measure blood sugar several times a day. Further, due to the particularity of diabetic pathology (blood sugar exceeds an index value and becomes a diabetic and can never be reversed), even potential diabetics need to measure their blood sugar levels frequently to prevent themselves from becoming "forever" diabetics. At present, the commonly used blood glucose meter needs to obtain blood for each test by finger puncture, which causes pain and inconvenience, and a new test strip is required for the next test, or instruments that can frequently / continuously monitor blood sugar indicators do exist, but they need to be implanted subcutaneously about every two weeks, causing trauma or pain to the user during implantation, and the user experience of these methods is poor, and financial pressure is generated because of consumables.
[0003] There are some so-called "non-invasive" blood glucose meters now. Although they do not require users to draw blood using traditional methods to test blood glucose, in the early stages of using the blood glucose meter, users are still required to draw blood using traditional methods to establish a corresponding model for their own blood glucose index values. This is not a truly "non-invasive" blood glucose meter.
[0004] Therefore, it is necessary to provide a truly non-invasive blood glucose measuring instrument. Summary of the invention
[0005] According to one main aspect of the present invention, a non-invasive intelligent blood glucose meter is provided, which includes a near infrared image acquisition device and a processor, wherein
[0006] The near-infrared image acquisition device is used to collect near-infrared photos of the human body.
[0007] The processor is used for processing, comparing and calibrating the near infrared photos, and then outputting the blood sugar measurement results of the user.
[0008] Preferably, the non-invasive intelligent blood glucose meter also includes an input and output device for user control and information display.
[0009] Preferably, the non-invasive smart blood glucose meter further comprises an external device and an interface for communicating with the external device, and the external device communicates with other components of the non-invasive smart blood glucose meter via wired and / or wireless means.
[0010] Preferably, the near-infrared picture acquisition device is a finger near-infrared picture acquisition device, which is used to acquire near-infrared pictures of the user's fingers.
[0011] Preferably, the near-infrared image acquisition device includes a near-infrared camera, a near-infrared light source component and a limb fixing device.
[0012] Preferably, the finger near-infrared image acquisition device comprises a near-infrared camera, a near-infrared light source component and a finger fixing device.
[0013] Preferably, the near-infrared light source component includes one or more groups of near-infrared lamps emitting near-infrared light of different wavelengths.
[0014] Preferably, the near-infrared light source component includes three groups of near-infrared lamps emitting near-infrared light of different wavelengths.
[0015] Preferably, the near-infrared picture acquisition device sequentially acquires three groups of near-infrared photos of different wavelengths.
[0016] Preferably, the wavelength selection range of the near-infrared light emitted by the near-infrared light source component is 700-1800nm.
[0017] Preferably, the near-infrared light emitted by the near-infrared light source component has a first wavelength selection range of 700-800 nm, a second wavelength selection range of 800-900 nm, and a third wavelength selection range of 900-1000 nm.
[0018] Preferably, the near-infrared light emitted by the near-infrared light source component has a first wavelength selection range of 750-800 nm, a second wavelength selection range of 850-900 nm, and a third wavelength selection range of 950-1000 nm.
[0019] Preferably, the near-infrared camera is arranged on one side of the finger fixing device, and the near-infrared light source component is arranged on the other side of the finger fixing device.
[0020] Preferably, the near-infrared camera is arranged below the finger fixing device, and the near-infrared light source component is arranged above the finger fixing device.
[0021] Preferably, the near-infrared camera and the finger fixing device are separated by transparent glass.
[0022] Preferably, the finger securing means comprises a U-shaped groove.
[0023] Preferably, a switch is provided at a position of the U-shaped groove corresponding to the fingertip, for starting the collection of the near-infrared image of the finger.
[0024] Preferably, the switch is a touch sensitive switch.
[0025] Preferably, the bottom of the U-shaped groove is hollow.
[0026] Preferably, the processor includes an image processing module and a comparison and calibration module.
[0027] Preferably, the processor further comprises a data management module.
[0028] Preferably, the image processing module processes the collected near-infrared image and transmits it to the comparison and calibration module for comparison and calibration.
[0029] Preferably, the image processing includes associating the collected near-infrared image with the near-infrared wavelength at the time of shooting.
[0030] Preferably, the comparison and calibration module is obtained by training on a computer with powerful computing power using an artificial intelligence machine learning algorithm and a large amount of training data.
[0031] Preferably, the artificial intelligence machine learning algorithm is a deep learning algorithm.
[0032] Preferably, the computer with powerful computing capability is a GPU computer.
[0033] Preferably, the training data includes the near-infrared light image of the subject's finger and the corresponding blood sugar index, and the wavelength of near-infrared light corresponding to the near-infrared light image of the finger used in the training data is the same as the wavelength of near-infrared light used in the finger near-infrared image acquisition device.
[0034] Preferably, the comparison and calibration module is configured to operate normally without a network.
[0035] Preferably, the data management module is used to manage user information and analyze historical data of blood sugar levels measured by the user.
[0036] The non-invasive intelligent blood glucose meter of the present invention can collect finger near-infrared images and send them to the comparison and calibration module, so as to obtain the user's blood glucose index directly and in real time, without blood samples or blood stains, without trauma, no stinging for the user, and no infection and cross-infection risks. Moreover, the use of the non-invasive intelligent blood glucose meter of the present invention does not require the generation of consumables, no disposables or hazardous waste, the number of times the user uses it is not limited, and the cost of use will not increase, reducing the financial pressure of diabetics and thus improving their quality of life, and can also remind potential diabetics to avoid becoming "forever" diabetics. In addition, the non-invasive intelligent blood glucose meter of the present invention is easy to carry and simple to operate. It can be used anytime and anywhere, whether at home, in the office or even in other public places, which greatly facilitates the user. Furthermore, the non-invasive intelligent blood glucose meter of the present invention can record the user's historical results, help doctors analyze and study and formulate treatment methods, and one instrument can also be used by multiple people or the whole family, and there will be no mutual infection and confusion of data results, which also greatly improves the user experience and quality of life. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] The above summary and the following detailed description will be better understood by reading in conjunction with the accompanying drawings. For ease of illustration, certain embodiments of the present disclosure are shown in the accompanying drawings. However, it should be understood that the present invention is not limited to the precise arrangements and tools shown. The accompanying drawings, which are incorporated into and constitute a part of this specification, illustrate implementations of systems and devices in accordance with the present invention and are used together with this description to illustrate the advantages and principles of the present invention.
[0038] Figure 1a The functional framework diagram of the non-invasive intelligent blood glucose meter according to one embodiment of the present invention is schematically shown;
[0039] Figure 1b Schematically shows Figure 1a The structure of the non-invasive smart blood glucose meter;
[0040] Figure 2 The flowchart of the use of the non-invasive intelligent blood glucose meter according to one embodiment of the present invention is schematically shown. DETAILED DESCRIPTION
[0041] Before describing in detail at least one embodiment of the present invention, it is to be understood that the present invention is not limited to the application of the details of its construction and the arrangement of components set forth in the following description or shown in the accompanying drawings. The accompanying drawings and written description are provided to guide those skilled in the art to make and use the present invention for which patent protection is sought. The present invention is applicable to other embodiments and can be implemented and executed in various ways. Those skilled in the art will understand that for the sake of clarity and ease of understanding, not all features of a commercial embodiment are shown. Those skilled in the art will also understand that the development of actual commercial embodiments incorporating aspects of the present invention will require many implementation-specific decisions to achieve the ultimate goal of the developer's commercial embodiment. Although these efforts will be complex and time-consuming, they are routine tasks for those skilled in the art who benefit from the present disclosure.
[0042] In addition, it is to be understood that the terms and terminology used herein are for ease of description and should not be considered as limiting. For example, the use of singular terms, such as "one", "a", "an", is not intended to limit the number of items. In addition, the use of non-restrictive relational terms such as "top", "bottom", "left", "right", "up", "down", "downward", "upward", "side" and the like is used in this description with specific reference to the accompanying drawings for clarity, and is not intended to limit the scope of the present invention or the appended claims. In addition, it should be understood that any of the features of the present invention can be used alone or in combination with other features. By reading the drawings and detailed description, those skilled in the art will clearly know other systems, methods, features and advantages of the present invention. It is expected that all such other systems, methods, features and advantages are included in this description, included in the scope of the present invention, and protected by the appended claims.
[0043] Implementation of the present invention will now be described in detail with reference to the accompanying drawings.
[0044] See also Figure 1a In one embodiment of the present invention, the non-invasive smart blood glucose meter 100 includes: a processor 1, an input-output device 2, a finger near-infrared picture acquisition device 3 and an external device 4. The finger near-infrared picture acquisition device 3 acquires near-infrared pictures of the user's fingers (pictures taken by a near-infrared camera under near-infrared light), and then these pictures are transmitted to the processor 1 for processing. After comparison and calibration are completed in the processor 1, the results are output. The results can be displayed in the input-output device 2 integrated into the non-invasive smart blood glucose meter 100, or transmitted to the external device 4.
[0045] It should be noted that in other embodiments of the present invention, the input / output device 2 and the external device 4 may not be included. In this embodiment, they are described together for the purpose of completeness, but this does not mean that these components are necessary.
[0046] like Figure 1a As shown, the finger near-infrared picture acquisition device 3 includes a near-infrared camera 31, a near-infrared light source component 32 and a finger fixing device 33. The near-infrared camera 31 is used to take near-infrared pictures of the finger, and the near-infrared light source component 32 is used to emit near-infrared light to the user's finger so that the near-infrared camera 31 can take pictures. When the user puts the finger correctly on the finger fixing device 33, the near-infrared light source component 32 emits three near-infrared lights of different wavelengths, and the near-infrared camera 31 takes three near-infrared pictures of different wavelengths in sequence. It should be understood that although near-infrared light is preferably used in this embodiment, it is also possible to use light of other frequency bands on the spectrum in other embodiments, and these alternatives should not be excluded from the scope of the present invention. It should also be understood that although it is preferred to collect photos under three different wavelengths of near-infrared light in this embodiment, it is also possible to use one, two, or four, five or even more different wavelengths of photos in other embodiments, and these alternatives should not be excluded from the scope of the present invention.
[0047] See also Figure 1b , the near-infrared light source component 32 is located above the finger fixing device 33, and the near-infrared camera 31 is located below the finger fixing device 33. A layer of transparent glass is placed between the finger fixing device 33 and the near-infrared camera 31. The transparent glass protects the near-infrared camera 31 from dust; the near-infrared camera 31 can photograph the finger through the glass. It is emphasized again that the "upper" and "lower" in this embodiment only indicate the relative positions between the components. In other embodiments, for example, the near-infrared light source component 32 can be located on the left side of the finger fixing device 33, and the near-infrared camera 31 can be located on the right side of the finger fixing device 33. Of course, the positions of one side and the other side are preferably opposite to each other, but in some embodiments, they can also be within a certain range away from the opposite position. Those skilled in the art should understand that as long as the near-infrared light source component 32 can irradiate the user's finger and the near-infrared camera 31 can take photos of the near-infrared light passing through the finger, these solutions should not be excluded from the scope of the present invention.
[0048] The finger fixing device 33 is a "U-shaped" groove, and its bottom is empty. A capacitive inductive touch switch is provided at the top of the "U-shape" (the position corresponding to the fingertip), and its inductive touch function is triggered by a capacitive inductive chip circuit installed there. It should be understood that in other embodiments, the finger fixing device 33 may not be U-shaped, but other suitable shapes; its bottom is not necessarily hollow, as long as the near-infrared camera 31 can take pictures of the near-infrared light passing through the finger; the inductive touch switch does not have to be set at the top of the U-shape, and other suitable positions are also possible. It should also be understood that although the inductive touch switch is capacitive in the present embodiment, other forms of inductive touch switches are also possible; and even other forms of switches, such as mechanical switches, photosensitive switches or voice-controlled switches are also feasible. These alternatives should not be excluded from the scope of the present invention.
[0049] When the top of the finger touches the switch at the top, the process of taking a near-infrared picture will be started. The near-infrared light source component 32 includes three groups of near-infrared lamps, each of which includes one or more near-infrared lamps, and preferably each group includes 8-12 near-infrared lamps. Each group of near-infrared lamps can emit near-infrared light of the wavelength of the group when turned on. When the near-infrared camera 31 starts the shooting process, each group of near-infrared lamps of wavelengths is turned on in sequence, and the near-infrared picture of the finger under the wavelength is taken accordingly. Specifically, the near-infrared light source component 32 will turn on the near-infrared light of the first wavelength, and the near-infrared camera 31 will take the near-infrared light photo of the finger under the first wavelength, and then the near-infrared light source component 32 will turn on the near-infrared light of the second wavelength, and the near-infrared camera 31 will take the near-infrared light photo of the finger under the second wavelength, and then the near-infrared light source component 32 will turn on the near-infrared light of the third wavelength, and the near-infrared camera 31 will take the near-infrared light photo of the finger under the third wavelength. In a preferred embodiment, the entire photo-taking process takes less than 1 second. After the photo-taking is finished, the user can remove the finger from the finger fixing device 33 by himself. It should be understood that in some embodiments, the aforementioned light emission and photo taking process can be completed automatically once it is started, while in other embodiments, the process can also be controlled by the user, for example, by the aforementioned switch or another switch. It should also be understood that in some embodiments, after the photo taking is completed, a prompt can be issued to the user in the form of light or sound, for example, a prompt can be issued on the input / output device 2 or the external device 4 of the non-invasive smart blood glucose meter 100; of course, a prompt light or a speaker can also be provided for prompting. These alternatives should not be excluded from the scope of the present invention.
[0050] The three different wavelengths of the near infrared light source component 32 are all between 700 and 1800 nm. In a preferred embodiment, the first wavelength is set between 700-800 nm, the second wavelength is set between 800-900 nm, and the third wavelength is set between 900-1000 nm. In a more preferred embodiment, the first wavelength is set between 750-800 nm, the second wavelength is set between 850-900 nm, and the third wavelength is set between 950-1000 nm.
[0051] like Figure 1a As shown, the processor 1 is preferably a CPU processor, which includes an image processing module 11, a comparison and calibration module 12 and a data management module 13. The image processing module 11 processes the near infrared image collected by the finger near infrared image collection device 3 and transmits it to the comparison and calibration module 12 for comparison and calibration, and the result of the comparison and calibration module 12 is output to the data management module 13, in which the data is analyzed and output to the input and output device 2 or the external device 4 for the user.
[0052] In the image processing module 11, the collected near-infrared image is associated with the near-infrared wavelength at the time of shooting, and the image is compared and calibrated based on the specific wavelength information in the comparison and calibration module 12. In a preferred embodiment, the comparison and calibration module 12 reflects the corresponding blood sugar index through three near-infrared images of different wavelengths, and obtains the final blood sugar index through comparison and calibration. In some embodiments, the program for controlling the finger near-infrared image acquisition device 3 to take pictures can also be integrated into the image processing module 11. Of course, the function of the image processing module 11 can also be integrated into the comparison and calibration module 12, or directly integrated into the finger near-infrared image acquisition device 3.
[0053] In a preferred embodiment, the comparison and calibration module 12 is obtained by training using an artificial intelligence machine learning algorithm, such as a deep learning algorithm, and the processed near-infrared image is sent to the comparison and calibration module 12 to obtain the corresponding user's blood sugar value. Specifically, the comparison and calibration module 12 is based on a large amount of raw data collected specifically and accurately sorted and matched as basic training data, and then trained by applying a deep learning algorithm on a computer with powerful computing power, such as a GPU computer. The raw data includes the near-infrared light image of the finger of the person being collected and the corresponding blood sugar index. The wavelength of the near-infrared light corresponding to the finger near-infrared light image used in the training data is the same as the wavelength of the near-infrared light used in the finger near-infrared image acquisition device 3. For example, the finger near-infrared image in the training data is also collected using three different wavelengths between 700 and 1800nm. Preferably, three different wavelengths between 700-800nm, between 800-900nm and between 900-1000nm are used for collection. More preferably, three different wavelengths are used for acquisition, between 750-800 nm, between 850-900 nm and between 950-1000 nm.
[0054] In a preferred embodiment, the corresponding blood glucose index values of the collected training data are distributed between 3.6 and 22.0, with a span of 0.1, and at least 40 pictures are collected at each wavelength for each blood glucose value. Of course, it should be understood that other value range distributions and spans, as well as the number of collected photos, can be adjusted. These alternatives should not be excluded from the scope of the present invention.
[0055] In a preferred embodiment, the trained model (engine) is embedded in the comparison and calibration module 12, and after the user's near-infrared image is input, the user's blood sugar value can be directly calculated. This eliminates the need for the user to draw blood using traditional methods to test blood sugar, nor does it require the user to draw blood using traditional methods in the initial stage to establish a corresponding model for the user's own blood sugar index value, as is done with other blood sugar meters that are not purely "non-invasive". At the same time, the trained model also ensures that the blood sugar meter of the present invention can work without a network, that is, all measurements, calculations, and storage can be completed locally in the blood sugar meter without the need for cloud intervention (such as cloud storage, cloud computing, etc.); of course, the blood sugar meter of the present invention does not exclude cooperation with cloud devices.
[0056] The data management module 13 is used to manage the relevant information of the user and to perform relevant analysis on the historical data of the blood glucose level measured by the user. In the data management module 13, a user information registration submodule may be included, which is used to register the basic information of the user, and these basic information include the user's name, age, gender, home address and other additional instructions. Preferably, multiple users can be registered through the user information registration submodule. In the data management module 13, a historical data analysis submodule may also be included, through which a historical database of blood glucose level measurement can be established for each user, and can be output to the input and output device 2 and / or the external device 4 in the form of appropriate charts to feed back to the user. At the same time, targeted health care suggestions can also be given for the current measurement data of the user and the changes in historical data, and these suggestions can also be output to the input and output device 2 and / or the external device 4 to feed back to the user.
[0057] It should be understood that in other embodiments of the present invention, part or all of the data management module 13 may not be included. In this embodiment, they are described together for the purpose of completeness, but this does not mean that these modules are necessary.
[0058] like Figure 1b As shown, the input-output device 2 is a touch screen, which, together with the processor 1 and the finger near-infrared image acquisition device 3, are installed on the main body of the non-invasive intelligent blood glucose meter 100. The input-output device 2 is used to input, edit and present each user's personal information and the situation of their blood glucose measurement, historical data, analysis results and nursing suggestions. When there are measurement results, the input-output device 2 can directly output the results according to the user's settings, or output them together with historical data and / or nursing suggestions. If there are no measurement results, the input-output device 2 can give a prompt to let the user measure again. It should be understood that the input-output device 2 can be, for example, a capacitive or resistive touch screen. In other embodiments, it can also be a traditional form of a non-touch screen plus physical buttons, or an input-output form using voice. These alternatives should not be excluded from the scope of the present invention.
[0059] The external device 4 can be the user's own mobile phone, Pad computer or PC computer. In a preferred embodiment, it communicates with the processor 1 by wired or wireless means, and a corresponding interface or communication module will be set on the non-invasive smart blood glucose meter 100 to communicate with it; if necessary, a corresponding APP program or API program will also be used. Wireless methods include, for example, WiFi, Bluetooth, Zigbee, etc., and also include, for example, 3G, 4G, 5G, etc. Of course, the external device 4 can also be a component produced and sold together with other components of the non-invasive smart blood glucose meter 100, but it is independent of the main body of the non-invasive smart blood glucose meter 100. It should be understood by those of ordinary skill in the art that if the aforementioned input and output device 2 is also set outside the main body of the non-invasive smart blood glucose meter 100, then in a sense, the input and output device 2 can also be regarded as an external device. It should also be understood by those of ordinary skill in the art that the input and output device 2 and the external device 4 are not mutually exclusive, and they can be used at the same time. These alternatives should not be excluded from the scope of the present invention.
[0060] See also Figure 2 , which schematically shows a flowchart of the use of a non-invasive intelligent blood glucose meter in an embodiment of the present invention. As shown in the figure, the user first places a finger on the finger fixing device 33 of the finger near-infrared image acquisition device 3, triggers the switch to start collecting finger near-infrared images, and the collected images are transmitted to the CPU processor 1, where they are processed and the near-infrared image spectrum is compared and calibrated to obtain the user's blood glucose value. If the CPU processor 1 cannot obtain the user's blood glucose value after processing, the user is asked to place the finger again for collection and analysis. After obtaining the user's blood glucose value, the user can also select a time period to query the historical data of the blood glucose value during this period and its analysis results.
[0061] It should be understood that although in the above embodiments, the present invention is explained by taking the example of collecting and analyzing near-infrared images of fingers, the present invention is not limited to being performed only based on the user's fingers. Other suitable methods, such as taking pictures of collecting and analyzing palms or other limbs of the human body, are also feasible. These alternatives should not be excluded from the scope of the present invention.
[0062] In addition, those skilled in the art should understand that due to the diversity of software and hardware (including firmware) combinations, a software function is not necessarily implemented by only one hardware, and multiple software functions can be integrated into one hardware or implemented in multiple hardware. Unless otherwise specified, the separation or integration of hardware does not limit the functions of the software. In particular, due to the development of cloud storage and cloud computing technologies, some functions can be implemented locally, on the "cloud", or both. Unless otherwise specified, these alternatives should not be excluded from the scope of the present invention.
[0063] Those skilled in the art will appreciate that the above embodiments may be modified without departing from the broad invention overview. It is therefore to be understood that the invention disclosed herein is not limited to the specific embodiments disclosed, but is intended to cover all variations within the spirit and scope of the invention as defined by the appended claims. In addition, even if the spirit and scope of the invention as defined by the appended claims are interpreted in accordance with the embodiments disclosed in the present invention, unless the applicant makes a special statement, the principle of contribution should not be applied to select and reject the spirit and scope of the invention of the present invention.
Claims
1. A non-invasive intelligent blood glucose meter, comprising a near infrared image acquisition device and a processor, wherein: The near infrared image acquisition device is used to acquire near infrared images of the human body. The processor is used for processing, comparing and calibrating the near infrared image, and then outputting the blood sugar measurement result of the user; The processor includes an image processing module and a comparison and calibration module, wherein The image processing module processes the collected near-infrared image and transmits it to the comparison and calibration module for comparison and calibration; The image processing includes associating the collected near-infrared image with the near-infrared wavelength at the time of shooting; The near-infrared image acquisition device is a finger near-infrared image acquisition device, which is used to acquire near-infrared images of the user's fingers; The finger near-infrared image acquisition device comprises a near-infrared camera, a near-infrared light source component and a finger fixing device; The finger securing device comprises a U-shaped groove; and A switch is provided at a position of the U-shaped groove corresponding to the fingertip, for starting the collection of a near-infrared image of the finger; The near-infrared light source component includes three groups of near-infrared lamps that emit near-infrared light of different wavelengths; the first wavelength selection range of the near-infrared light emitted by the near-infrared light source component is between 750-800nm, the second wavelength selection range is between 850-900nm, and the third wavelength selection range is between 950-1000nm; the near-infrared light source components of each group of wavelengths are turned on in sequence, and the near-infrared image acquisition device collects three groups of near-infrared images of different wavelengths in sequence.
2. The non-invasive intelligent blood glucose meter according to claim 1, characterized in that: It also includes input and output devices for user control and information display.
3. The non-invasive intelligent blood glucose meter according to claim 1, characterized in that: It also includes an external device and an interface for communicating with the external device. The external device communicates with other components of the non-invasive intelligent blood glucose meter in a wired and / or wireless manner.
4. The non-invasive intelligent blood glucose meter according to claim 1, characterized in that: The near infrared camera is arranged on one side of the finger fixing device, and the near infrared light source component is arranged on the other side of the finger fixing device.
5. The non-invasive intelligent blood glucose meter according to claim 1, characterized in that: The near-infrared camera and the finger fixing device are separated by transparent glass.
6. The non-invasive intelligent blood glucose meter according to claim 1, characterized in that: The comparison and calibration module is obtained by training on a computer with powerful computing power using an artificial intelligence machine learning algorithm and a large amount of training data; The training data includes the near-infrared light image of the subject's finger and the corresponding blood sugar index, and the wavelength of the near-infrared light corresponding to the near-infrared light image of the finger used in the training data is the same as the wavelength of the near-infrared light used in the finger near-infrared image acquisition device.
7. The non-invasive intelligent blood glucose meter according to claim 6, characterized in that: The comparison and calibration module is configured to operate normally without a network.
