Blood glucose concentration analysis method, device, electronic device and storage medium

Abstract

The present application relates to a blood glucose concentration analysis method, apparatus, device, storage medium, and computer program product. The method comprises: obtaining intensity sets corresponding to multiple photoplethysmographic wave sets of a target subject within a target time period; the intensity sets include average AC intensity and average DC intensity; performing curve fitting on the multiple intensity sets to obtain fitting coefficients and fitting bias; comparing the fitting bias with the bias range corresponding to the target subject, and if it is determined that the fitting bias is not within the bias range, adjusting the fitting bias to obtain an adjusted fitting bias; based on the adjusted fitting bias, performing curve fitting on the multiple intensity sets to obtain adjusted fitting coefficients, and using the adjusted fitting coefficients as the target subject's blood glucose concentration during the target time period. This method can improve the accuracy of blood glucose concentration analysis.

Description

Technical Field

[0001] The present application relates to the field of non-invasive blood glucose concentration analysis, and in particular to a blood glucose concentration analysis method, device, electronic device, storage medium and computer program product. Background Art

[0002] With the development of sensing technology, wearable smart devices have emerged. Wearable smart devices are used to obtain the wearer's physiological characteristic parameters and continuously monitor the wearer's physical condition through analysis of the physiological characteristic parameters.

[0003] In traditional technology, wearable smart devices use near-infrared non-invasive blood glucose detection methods to continuously monitor the wearer's blood glucose concentration. However, since this method is easily interfered with by human tissue, the accuracy of blood glucose concentration is low. Summary of the Invention

[0004] Based on this, it is necessary to provide a blood glucose concentration analysis method, device, electronic device, computer-readable storage medium and computer program product that can improve accuracy in order to address the above technical problems.

[0005] In a first aspect, the present application provides a method for analyzing blood glucose concentration. The method comprises:

[0006] Obtain intensity sets corresponding to multiple photoplethysmographic sets of the target object within the target time period; the intensity sets include average AC intensity and average DC intensity

[0007] Performing curve fitting on the plurality of intensity sets to obtain fitting coefficients and fitting biases;

[0008] Comparing the fitting offset with an offset range corresponding to the target object, and if it is determined that the fitting offset is not within the offset range, adjusting the fitting offset to obtain an adjusted fitting offset;

[0009] Based on the adjusted fitting bias, curve fitting is performed on the plurality of intensity sets to obtain an adjusted fitting coefficient, and the adjusted fitting coefficient is used as the blood glucose concentration of the target subject in the target time period.

[0010] In one embodiment, the method further comprises performing curve fitting on the plurality of intensity sets based on the adjusted fitting bias to obtain an adjusted fitting coefficient, and then:

[0011] Acquiring a correction parameter value of the target object; the correction parameter value corresponds to a correction parameter, and the correction parameter includes at least one of a physiological characteristic parameter and an environmental characteristic parameter;

[0012] Acquire a plurality of correction weights corresponding to the target object; the plurality of correction weights include a correction weight corresponding to the adjustment fitting coefficient and a correction weight corresponding to each of the correction parameters;

[0013] The step of using the adjusted fitting coefficient as the blood glucose concentration of the target subject in the target time period includes:

[0014] The adjusted fitting coefficient and each of the correction parameter values are integrated with the corresponding correction weights to obtain the blood glucose concentration of the target subject in the target time period.

[0015] In one embodiment, the acquiring of the intensity sets corresponding to the plurality of photoplethysmogram sets of the target object within the target time period includes:

[0016] Acquire multiple photoplethysmogram sets of the target object within the target time period; each photoplethysmogram set corresponds to an emission intensity, and each photoplethysmogram set includes at least two photoplethysmograms;

[0017] For each photoplethysmogram, filtering the photoplethysmogram to obtain a DC signal and an AC signal, determining a DC intensity corresponding to the photoplethysmogram based on a signal strength of the DC signal, and determining an AC intensity corresponding to the photoplethysmogram based on the AC signal;

[0018] For each photoplethysmogram set, the DC intensities corresponding to the multiple photoplethysmograms are averaged to obtain an average DC intensity, and the AC intensities corresponding to the multiple photoplethysmograms are averaged to obtain an average AC intensity. Based on the average DC intensity and the average AC intensity, an intensity set corresponding to the photoplethysmogram set is obtained.

[0019] In one embodiment, for each photoplethysmogram, filtering is performed on the photoplethysmogram to obtain a DC signal and an AC signal, and the method further includes:

[0020] Performing a quality assessment on the photoplethysmography to obtain a quality assessment result of the photoplethysmography; the quality assessment result includes an assessment value corresponding to each band constituting the photoplethysmography;

[0021] removing the waveband corresponding to the evaluation value less than the evaluation threshold from the photoplethysmogram to obtain an adjusted photoplethysmogram;

[0022] The filtering process for each photoplethysmogram to obtain a DC signal and an AC signal includes:

[0023] For each of the adjusted photoplethysmograms, filtering is performed on the adjusted photoplethysmogram to obtain a direct current signal and an alternating current signal.

[0024] In one embodiment, determining the AC intensity corresponding to the photoplethysmography based on the AC signal includes:

[0025] Acquiring multiple trough coordinates in the AC signal, performing curve fitting on the multiple trough coordinates to obtain a fitting signal;

[0026] Calculating the difference between the AC signal and the fitting signal to obtain a target AC signal;

[0027] The multiple peak intensities in the target AC signal are averaged to obtain the AC intensity corresponding to the photoplethysmography.

[0028] In one embodiment, the comparing the fitting offset with the offset range corresponding to the target object further includes:

[0029] Acquire multiple historical time periods of the target object and multiple intensity sets corresponding to each of the historical time periods;

[0030] For each of the historical time periods, curve fitting is performed on multiple intensity sets corresponding to the historical time period to obtain a historical fitting bias;

[0031] Based on the multiple history matching offsets, an offset range corresponding to the target object is obtained.

[0032] In one embodiment, the comparing the fitting offset with the offset range corresponding to the target object further includes:

[0033] When it is determined that the fitting bias is within the bias range, the fitting coefficient is used as the blood glucose concentration of the target subject in the target time period.

[0034] In a second aspect, the present application also provides a blood glucose concentration analysis device. The device comprises:

[0035] An acquisition module, configured to acquire intensity sets corresponding to a plurality of photoplethysmographic sets of a target object within a target time period; the intensity sets include an average AC intensity and an average DC intensity;

[0036] A fitting module, configured to perform curve fitting on the plurality of intensity sets to obtain a fitting coefficient and a fitting bias;

[0037] a comparison module, configured to compare the fitting offset with an offset range corresponding to the target object, and if it is determined that the fitting offset is not within the offset range, adjust the fitting offset to obtain an adjusted fitting offset;

[0038] An adjustment module is configured to perform curve fitting on the plurality of intensity sets based on the adjustment fitting bias to obtain an adjustment fitting coefficient, and use the adjustment fitting coefficient as the blood glucose concentration of the target subject in the target time period.

[0039] In a third aspect, the present application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of the blood glucose concentration analysis method provided in the above aspects when executing the computer program.

[0040] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the blood glucose concentration analysis method provided in the above aspects.

[0041] In a fifth aspect, the present application further provides a computer program product, comprising a computer program that, when executed by a processor, implements the steps of the blood glucose concentration analysis method provided in the above aspects.

[0042] The above-mentioned blood glucose concentration analysis method, device, electronic device, storage medium and computer program product obtain a fitting coefficient by curve fitting multiple intensity sets. The fitting coefficient reflects the ratio between the AC signal intensity and the DC signal intensity in the target time period, that is, it reflects the blood glucose concentration of the target object in the target time period. The fitting bias is then compared with the bias range corresponding to the target object. The bias range characterizes the individual differences of the target object. Different target objects correspond to different bias ranges. If the fitting bias is not within the bias range, it means that the fitting bias does not conform to the individual differences of the target object. The fitting offset is adjusted so that the obtained adjusted fitting bias conforms to the bias range of the target object. The adjusted fitting bias and multiple intensity sets are then used to perform curve fitting again. The obtained adjusted fitting coefficient combines the individual differences of the target object. The adjusted fitting coefficient is used as the blood glucose concentration of the target object in the target time period, thereby improving the accuracy of the blood glucose concentration. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A diagram showing an application environment of a blood glucose concentration analysis method according to an embodiment;

[0044] Figure 2 1 is a flow chart of a method for analyzing blood glucose concentration in one embodiment;

[0045] Figure 3 FIG1 is a flow chart of a blood glucose concentration correction step in one embodiment;

[0046] Figure 4 A schematic flow chart of the intensity set acquisition step in one embodiment;

[0047] Figure 5 1 is a flow chart of a filtering step in one embodiment;

[0048] Figure 6 is a schematic diagram of a photoplethysmography method according to one embodiment;

[0049] Figure 7 FIG1 is a schematic diagram of a process for analyzing blood glucose concentration in one embodiment;

[0050] Figure 8 is a schematic diagram of a blood glucose concentration curve in one embodiment;

[0051] Figure 9 is a structural block diagram of a blood glucose concentration analysis device according to one embodiment;

[0052] Figure 10 FIG. 1 is a diagram showing the internal structure of an electronic device in one embodiment. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0054] The blood glucose concentration analysis method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown, device 102 communicates with server 104 via a network. A data storage system can store data that server 104 needs to process. The data storage system can be integrated with server 104, or placed on a cloud or other network server. Both the device and server can be used independently to perform the blood glucose concentration analysis method provided in the embodiments of the present application. The device and server can also be used together to perform the blood glucose concentration analysis method provided in the embodiments of the present application. For example, the device obtains intensity sets corresponding to multiple photoplethysmographic wave sets of a target subject during a target time period, performs curve fitting on the multiple intensity sets to obtain fitting coefficients and fitting biases, compares the fitting biases with the bias range corresponding to the target subject, and if it is determined that the fitting biases are not within the bias range, adjusts the fitting biases to obtain adjusted fitting biases. Based on the adjusted fitting biases, curve fitting is performed on the multiple intensity sets to obtain adjusted fitting coefficients, and the adjusted fitting coefficients are used as the target subject's blood glucose concentration during the target time period. Device 102 can be, but is not limited to, various portable wearable devices, such as smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0055] In one embodiment, Figure 2 As shown, a blood glucose concentration analysis method is provided, including steps 202 to 208, and the method is applied to a device as an example for description.

[0056] Step 202 : Acquire intensity sets corresponding to a plurality of photoplethysmographic sets of the target object within a target time period; the intensity sets include an average AC intensity and an average DC intensity.

[0057] The target subject refers to the individual whose blood glucose concentration is being monitored, for example, the individual wearing the device. The target time period refers to the period of time during which blood glucose concentration is monitored. The duration of the target time period can be set according to actual needs. Photoplethysmography (PP) refers to light waves generated by transmitting or reflecting light when light of a specific frequency is irradiated onto the skin surface. Different components in the blood absorb light of different frequencies to varying degrees. For example, blood glucose has a strong absorption capacity for light of frequency A. Changes in blood glucose concentration directly affect the absorption of light of frequency A, resulting in changes in the transmitted or reflected light and, consequently, changes in the PPP wave. A PPP set refers to a collection of multiple PPP waves corresponding to emitted light of the same frequency and intensity. This means that, given the same emitted light frequency and intensity, each received reflected or transmitted light wave of a preset duration is considered a PPP wave, and these multiple PPP waves constitute a PPP set. For example, the device emits light at frequency A and intensity B for 30 seconds and receives the reflected light waves for 30 seconds. Every 10 seconds of reflected light waves is counted as a photoplethysmogram (PPL). Three PPL waves are generated within 30 seconds, and these three PPL waves constitute a PPL set. An intensity set is the average DC intensity of multiple PPL waves and the average AC intensity of multiple PPL waves.

[0058] Illustratively, in order to monitor the blood glucose concentration of the target subject within a target time period, the device obtains multiple intensity sets of the target subject within the target time period, and each intensity set is obtained by analyzing a photoplethysmogram set.

[0059] Step 204 : performing curve fitting on the multiple intensity sets to obtain fitting coefficients and fitting biases.

[0060] Among them, curve fitting refers to the process of selecting a suitable curve type and fitting an intensity set. It can be understood as taking the average DC intensity in the intensity set as the X-axis coordinate value, the average AC intensity as the Y-axis coordinate value, and the intensity set as a coordinate in the rectangular coordinate system, and performing curve fitting on multiple coordinates. Curve fitting includes but is not limited to partial least squares fitting and straight line fitting. The fitting coefficient refers to the coefficient of the fitting curve. The fitting bias refers to the intercept of the fitting curve. For example, the fitting curve fitted using multiple intensity sets is Y=KX+B, where K is the fitting coefficient and B is the fitting bias.

[0061] Exemplarily, the device performs curve fitting on multiple intensity sets to obtain an initial fitting curve, uses coefficients of the initial fitting curve as fitting coefficients, and uses an intercept of the initial fitting curve as a fitting bias.

[0062] Step 206 : Compare the fitting offset with the offset range corresponding to the target object. If it is determined that the fitting offset is not within the offset range, adjust the fitting offset to obtain an adjusted fitting offset.

[0063] The offset range refers to the intercept range corresponding to the target object. Different target objects have different corresponding offset ranges. The offset range represents the individual differences of the target objects.

[0064] Exemplarily, the device obtains the bias range corresponding to the target object, compares the fitting bias with the bias range, and if the fitting bias is within the bias range, uses the fitting coefficient as the blood glucose concentration of the target object in the target time period; if the fitting bias is not within the bias range, adjusts the fitting bias to obtain an adjusted fitting bias, and the adjusted fitting bias is within the bias range.

[0065] In one embodiment, adjusting the fitting bias to obtain an adjusted fitting bias includes: adjusting the fitting bias multiple times based on a bias range to obtain multiple candidate fitting biases; performing curve fitting on multiple intensity sets for each candidate fitting bias to obtain a candidate fitting curve; calculating the linearity of the candidate fitting curve; comparing the linearity of the multiple candidate fitting curves; and determining the candidate fitting bias of the candidate fitting curve corresponding to the maximum linearity as the adjusted fitting bias.

[0066] Step 208 : Based on the adjusted fitting bias, curve fitting is performed on the multiple intensity sets to obtain an adjusted fitting coefficient, and the adjusted fitting coefficient is used as the blood glucose concentration of the target subject in the target time period.

[0067] Among them, blood sugar concentration refers to the concentration of glucose in the blood.

[0068] Exemplarily, the device performs curve fitting on multiple intensity sets according to the adjusted fitting bias to obtain an adjusted fitting curve, uses the coefficients of the adjusted fitting curve as adjusted fitting coefficients, and uses the adjusted fitting coefficients as the blood glucose concentration of the target subject in the target time period.

[0069] In the above-mentioned blood glucose concentration analysis method, a fitting coefficient is obtained by performing curve fitting on multiple intensity sets. The fitting coefficient reflects the ratio between the AC signal intensity and the DC signal intensity in the target time period, that is, it reflects the blood glucose concentration of the target object in the target time period. Then, the fitting bias is compared with the bias range corresponding to the target object. The bias range characterizes the individual differences of the target object. Different target objects correspond to different bias ranges. If the fitting bias is not within the bias range, it means that the fitting bias does not conform to the individual differences of the target object. The fitting offset is adjusted so that the adjusted fitting bias conforms to the bias range of the target object. Then, the adjusted fitting bias and multiple intensity sets are used to perform curve fitting again. The obtained adjusted fitting coefficient combines the individual differences of the target object. The adjusted fitting coefficient is used as the blood glucose concentration of the target object in the target time period, thereby improving the accuracy of the blood glucose concentration.

[0070] In one embodiment, Figure 3 As shown, step 208 is to perform curve fitting on multiple intensity sets based on the adjusted fitting bias to obtain adjusted fitting coefficients, and then further includes:

[0071] Step 302: Acquire a correction parameter value of the target object; the correction parameter value corresponds to a correction parameter, and the correction parameter includes at least one of a physiological characteristic parameter and an environmental characteristic parameter.

[0072] Among them, the correction parameter refers to the parameter used to correct the blood glucose concentration. It can be understood as a parameter that affects the blood glucose concentration. The correction parameter value refers to the specific value of the correction parameter at a certain moment. Physiological characteristic parameters refer to characteristic parameters that characterize the physical condition of the target object. Physiological characteristic parameters include but are not limited to blood pressure, heart rate, blood oxygen and body mass index (BMI). Environmental characteristic parameters refer to characteristic parameters that characterize environmental conditions. Environmental characteristic parameters include but are not limited to temperature and humidity.

[0073] For example, after obtaining the adjusted fitting coefficient, to further improve the accuracy of the monitored blood glucose concentration, the adjusted fitting coefficient is corrected based on the target subject's physiological characteristic parameters and / or environmental characteristic parameters, and the corrected result is used as the target subject's blood glucose concentration during the target time period. A sensor on the device obtains the corrected parameter value for the target subject.

[0074] Step 304 , obtaining a plurality of correction weights corresponding to the target object; the plurality of correction weights include correction weights corresponding to the adjusted fitting coefficients and correction weights corresponding to the various correction parameters.

[0075] The correction weight refers to the proportion of the correction parameter. The larger the correction weight corresponding to the correction parameter, the greater the impact of the correction parameter on blood glucose concentration. Correction weights vary among individuals; the same correction parameter may have different weights for different subjects.

[0076] Exemplarily, the device obtains multiple correction weights of the target object from a database.

[0077] Step 306 , using the adjusted fitting coefficient as the blood glucose concentration of the target subject in the target time period, includes: fusing the adjusted fitting coefficient and each correction parameter value with the corresponding correction weight to obtain the blood glucose concentration of the target subject in the target time period.

[0078] Exemplarily, the device multiplies the adjusted fitting coefficient by the corresponding correction weight to obtain the corrected fitting coefficient, multiplies each correction parameter value by the corresponding correction weight to obtain corresponding multiple correction values, and adds the corrected fitting coefficient to the multiple correction values to obtain the blood glucose concentration of the target object in the target time period.

[0079] In this embodiment, the device performs curve fitting on multiple intensity sets based on the adjusted fitting bias. After obtaining the adjusted fitting coefficient, the correction parameter value affecting the blood glucose concentration and the correction weight corresponding to the target object are obtained. The same correction parameter for different target objects corresponds to different correction weights. The correction weight reflects the individual differences of the target objects. The adjusted fitting coefficient is corrected in combination with the correction parameter value affecting the blood glucose concentration and the corresponding correction weight. It can be understood that, while considering the physical characteristics of the target object and the environmental characteristics of the environment in which the target object is located, the blood glucose concentration of the target object in the target time period is comprehensively analyzed, thereby further improving the accuracy of the blood glucose concentration.

[0080] In one embodiment, Figure 4 As shown, step 202, obtaining an intensity set corresponding to a plurality of photoplethysmographic sets of the target object within a target time period, includes:

[0081] Step 402 : Acquire multiple photoplethysmogram sets of the target object within a target time period; each photoplethysmogram set corresponds to an emission intensity, and each photoplethysmogram set includes at least two photoplethysmograms.

[0082] Emission intensity refers to the intensity of the light waves emitted by the device. Emission intensity can be achieved by adjusting the peak intensity of the emitted light or by adjusting the duration of the light emission.

[0083] Exemplarily, in order to monitor the blood glucose concentration of the target object within the target time period, the device obtains multiple photoplethysmograms of the target object within the target time period, and combines the multiple photoplethysmograms corresponding to the same emission intensity into a photoplethysmogram set to obtain multiple photoplethysmogram sets.

[0084] In step 404, for each photoplethysmogram, the photoplethysmogram is filtered to obtain a DC signal and an AC signal. Based on the signal strength of the DC signal, the DC intensity corresponding to the photoplethysmogram is determined. Based on the AC signal, the AC intensity corresponding to the photoplethysmogram is determined.

[0085] Filtering involves separating the DC and AC signals in the photoplethysmography (PPE) wave based on preset rules. The AC signal, which is synchronized with the heart rate and reflects the absorption of light by arterial blood, is the AC component of the PPE wave. The DC signal, which reflects the absorption of light by non-arterial blood, venous blood, capillary blood, and muscle tissue, is the DC component of the PPE wave.

[0086] Exemplarily, for each photoplethysmogram, the device separates the DC signal and AC signal from the photoplethysmogram based on a preset frequency range, uses the signal strength of the DC signal as the DC intensity of the photoplethysmogram, and determines the AC intensity corresponding to the photoplethysmogram based on the peak intensity and trough intensity of the AC signal.

[0087] In one embodiment, based on an AC signal, determining the AC intensity corresponding to the photoplethysmography signal includes: the device obtains the peak intensity corresponding to each peak in the AC signal, and the trough intensity corresponding to each trough, adding multiple peak intensities to obtain the peak statistical intensity, adding multiple trough intensities to obtain the trough statistical intensity, counting the number of peaks or troughs to obtain a statistical value, calculating the difference between the peak statistical intensity and the trough statistical intensity, dividing the difference by the statistical value, and obtaining the AC intensity corresponding to the photoplethysmography signal.

[0088] Step 406: For each photoplethysmogram set, the DC intensities corresponding to the multiple photoplethysmograms are averaged to obtain an average DC intensity, and the AC intensities corresponding to the multiple photoplethysmograms are averaged to obtain an average AC intensity. Based on the average DC intensity and the average AC intensity, an intensity set corresponding to the photoplethysmogram set is obtained.

[0089] Exemplarily, the device averages the DC intensities corresponding to multiple photoplethysmograms in the same photoplethysmogram set to obtain an average DC intensity, and averages the AC intensities corresponding to multiple photoplethysmograms to obtain an average AC intensity, and combines the average DC intensity and the average AC intensity to form an intensity set corresponding to the photoplethysmogram set.

[0090] In this embodiment, by forming an intensity set for curve fitting with the average DC intensity and the average AC intensity, the inaccuracy of the intensity set caused by fluctuations in one of the photoplethysmography waves or measurement errors is avoided, which in turn causes inaccurate curve fitting results. The accuracy of the intensity set is improved, and accurate basic data is provided for subsequent curve fitting.

[0091] In one embodiment, Figure 5 As shown, step 404, for each photoplethysmogram, filtering is performed on the photoplethysmogram to obtain a DC signal and an AC signal, which also includes:

[0092] Step 502 : Perform a quality assessment on the photoplethysmography to obtain a quality assessment result of the photoplethysmography; the quality assessment result includes an assessment value corresponding to each waveband constituting the photoplethysmography.

[0093] Quality assessment refers to evaluating the quality of the photoplethysmography (PPE). This can be understood as evaluating the PPE waveform. The quality assessment result is a collection of evaluation values corresponding to each PPE band. Preset bands are pre-set standard bands used for band evaluation. Preset bands can be set based on experience or experimental data.

[0094] For example, in step 404, the photoplethysmography is directly filtered. This photoplethysmography may have large errors and fail to reflect the true condition of the target object. To improve the accuracy of the intensity set, the photoplethysmography needs to be preprocessed before filtering. The preprocessing step includes steps 502 and 504. The device divides the photoplethysmography into multiple bands. For each band, the similarity between the band and a preset band is calculated to obtain an evaluation value for the band. The evaluation values of the multiple bands are combined to form the photoplethysmography evaluation result.

[0095] In one embodiment, step 502, performing quality assessment on the photoplethysmography to obtain a quality assessment result of the photoplethysmography includes: performing normalization processing on the photoplethysmography to obtain a photoplethysmography to be assessed, such as Figure 6As shown in the collected data in , the photoplethysmography to be evaluated is divided into multiple bands. For each band, the similarity between the band and the preset band is calculated to obtain the initial evaluation value of the band. The initial evaluation value is normalized to obtain the evaluation value of the band. The evaluation values of multiple bands are combined to form the evaluation result of the photoplethysmography, as shown in Figure 6 The quality assessment is shown in .

[0096] Step 504 : remove the waveband corresponding to the evaluation value less than the evaluation threshold from the photoplethysmogram to obtain an adjusted photoplethysmogram.

[0097] The evaluation threshold refers to the minimum evaluation value of the retained band. The evaluation threshold can be set according to actual needs.

[0098] Exemplarily, the device compares each evaluation value with the evaluation threshold value, removes the band corresponding to the evaluation value less than the evaluation threshold value from the photoplethysmogram, and obtains an adjusted photoplethysmogram. In one embodiment, step 504 removes the band corresponding to the evaluation value less than the evaluation threshold value from the photoplethysmogram to obtain an adjusted photoplethysmogram, which also includes: the device compares each evaluation value in the photoplethysmogram with the evaluation threshold value, and counts the proportion of evaluation values less than the evaluation threshold value in the quality evaluation result. If the proportion is greater than the preset threshold value, it is determined that the quality of the photoplethysmogram is poor, and the photoplethysmogram is deleted; if the proportion is less than or equal to the preset threshold value, it is determined that the quality of the photoplethysmogram is good, and the band corresponding to the evaluation value less than the evaluation threshold value is removed from the photoplethysmogram to obtain an adjusted photoplethysmogram. For example, Figure 6 If the quality of the photoplethysmogram in (a) is good, the band corresponding to the evaluation value less than the evaluation threshold is removed from the photoplethysmogram to obtain the adjusted photoplethysmogram. Figure 6 If the quality of the PPG in (b) is poor, it will be deleted from the PPG set.

[0099] Step 506 , filtering each photoplethysmogram to obtain a DC signal and an AC signal, includes filtering each adjusted photoplethysmogram to obtain a DC signal and an AC signal.

[0100] Exemplarily, after the device obtains the adjusted photoplethysmogram, for each adjusted photoplethysmogram, the device separates a direct current signal and an alternating current signal from the adjusted photoplethysmogram according to a preset frequency range.

[0101] In this embodiment, the quality of the photoplethysmography is evaluated, and the band corresponding to the evaluation value less than the evaluation threshold is removed from the photoplethysmography. If the evaluation value is less than the evaluation threshold, it means that the band corresponding to the evaluation value is a mutation band, which is significantly different from other bands. The mutation band cannot accurately reflect the normal changes of reflected light or transmitted light. Removing this band from the photoplethysmography can be understood as removing the mutation band from the photoplethysmography. Adjusting the photoplethysmography can more accurately reflect the changes in reflected light or transmitted light, thereby improving the accuracy of adjusting the photoplethysmography, thereby improving the accuracy of the separated DC signal and AC signal.

[0102] In one embodiment, in step 404, determining the AC intensity corresponding to the photoplethysmography based on the AC signal includes:

[0103] Acquire multiple trough coordinates in the AC signal, perform curve fitting on the multiple trough coordinates to obtain a fitting signal; calculate the difference between the AC signal and the fitting signal to obtain a target AC signal; average the multiple peak intensities in the target AC signal to obtain the AC intensity corresponding to the photoplethysmogram.

[0104] The trough coordinates refer to the coordinates of the lowest point in the trough of the AC signal. One dimension of the trough coordinates is the time dimension, and the other dimension is the intensity dimension. For example, Figure 6 As shown in (a), the coordinates of the first trough are (0, 0.45). The fitted signal refers to the fitting curve obtained by fitting multiple trough coordinates. The peak intensity refers to the intensity of the highest point of the target AC signal peak.

[0105] Exemplarily, after obtaining the AC signal of the photoplethysmography, the device obtains the trough coordinates of each trough in the AC signal, performs curve fitting on the above multiple trough coordinates to obtain a fitting signal, subtracts the fitting signal from the AC signal to obtain the target AC signal, obtains the peak intensity of each peak in the target AC signal, averages the above multiple peak intensities, and obtains the AC intensity corresponding to the photoplethysmography.

[0106] In this embodiment, compared with directly using the peak intensity to subtract the trough intensity to obtain the peak intensity to be averaged, the peak intensity value to be averaged is affected by time, that is, the subtracted peak intensity and trough intensity are not at the same time, and the peak intensity to be averaged includes the influence of the time factor. The accuracy of the peak intensity to be averaged is low. The AC signal is subtracted from the fitting signal to obtain the target AC signal. The target AC signal reflects the amplitude of the change of the AC signal. The peak intensity to be averaged is obtained from the target AC signal. The peak intensity is not affected by the time factor, which improves the accuracy of the peak intensity to be averaged, thereby improving the accuracy of the AC intensity.

[0107] In one embodiment, step 206, comparing the fitted offset with the offset range corresponding to the target object, may also include:

[0108] Acquire multiple historical time periods of the target object and multiple intensity sets corresponding to each historical time period; for each historical time period, perform curve fitting on the multiple intensity sets corresponding to the historical time period to obtain a historical fitting bias; and obtain a bias range corresponding to the target object based on the multiple historical fitting biases.

[0109] The historical time period refers to the time period before the current time period.

[0110] Exemplarily, before the device begins monitoring the target subject's blood glucose concentration, it needs to determine the target subject's corresponding bias range. After the target subject wears the device for a period of time, the device can obtain multiple historical time periods from the wear period, determine a bias range that meets the target subject's individual differences based on the intensity sets corresponding to the multiple historical time periods, and then save the bias range with the target subject's target subject identifier. This bias range is then used during subsequent monitoring of the target subject's blood glucose concentration. Alternatively, before each monitoring of the target subject's blood glucose concentration, the device obtains intensity sets corresponding to multiple historical times preceding the target time period and determines the bias range based on the multiple intensity sets. The device obtains multiple historical time periods for the target subject, then obtains multiple intensity sets corresponding to each historical time period. For each historical time period, the device performs curve fitting on the multiple intensity sets to obtain a historical fitting bias. The multiple historical fitting biases are averaged to obtain an average bias. Based on the average bias and a preset floating range, the bias range corresponding to the target subject is obtained. For example, if the average bias is M and the preset floating range is plus or minus 10%, the bias range is [M*(1+10%), M*(1-10%)].

[0111] In this embodiment, multiple intensity sets corresponding to each historical time period of the target object are fitted to obtain multiple fitting biases, and the bias range corresponding to the target object is determined based on the multiple fitting biases. The bias range corresponds to the target object one-to-one, and the bias range has individual differences, which can more accurately characterize the individual differences of the target object.

[0112] In one embodiment, step 206, comparing the fitting offset with the offset range corresponding to the target object, further includes:

[0113] When it is determined that the fitting bias is within the bias range, the fitting coefficient is used as the blood glucose concentration of the target subject in the target time period.

[0114] Illustratively, in step 206 , the device compares the fitting offset with the offset range corresponding to the target subject. If the fitting offset is within the offset range, the fitting coefficient is used as the blood glucose concentration of the target subject in the target time period.

[0115] In this embodiment, if the fitting bias is within the bias range, it means that the fitting bias obtained by curve fitting is consistent with the individual differences of the target subject, the accuracy of the fitting coefficient is high, and the blood glucose concentration of the target subject in the target time period can be accurately reflected.

[0116] In an exemplary embodiment, the process of analyzing blood glucose concentration is as follows Figure 7 As shown, the device emits light of frequency A and first intensity, receives a photoplethysmogram (PPL) of a preset duration, normalizes the PPL to obtain a PPL to be evaluated, divides the PPL to be evaluated into multiple bands, calculates the similarity between each band and a preset band, obtains an initial evaluation value for the band, normalizes the initial evaluation value to obtain an evaluation value for the band, and combines the evaluation values of the multiple bands into an evaluation result of the PPL. Based on the evaluation result, the quality of the PPL is determined. If the quality of the PPL is poor, the PPL is deleted. If the quality of the PPL is good, the bands corresponding to the evaluation values less than the evaluation threshold are removed from the PPL to obtain an adjusted PPL. The above process is repeated to obtain a preset number of PPLs, which are then combined into a first PPL set. The device adjusts the intensity of the emitted light to a second intensity, emits light at frequency A and the second intensity, repeats the above process, obtains a preset number of photoplethysmograms, and combines the preset number of photoplethysmograms into a second photoplethysmogram set. The device adjusts the intensity of the emitted light to a third intensity, emits light at frequency A and the third intensity, repeats the above process, obtains a preset number of photoplethysmograms, and combines the preset number of photoplethysmograms into a third photoplethysmogram set.

[0117] For each photoplethysmogram in each photoplethysmogram set, filtering is performed on the photoplethysmogram based on a preset frequency range to separate a direct current signal and an alternating current signal from the photoplethysmogram.

[0118] The signal strength of the DC signal is used as the DC intensity of the photoplethysmography. The trough coordinates of each trough in the AC signal are obtained, and a curve fit is performed on the multiple trough coordinates to obtain a fitted signal. The fitted signal is subtracted from the AC signal to obtain a target AC signal. The peak intensity of each peak in the target AC signal is obtained, and the multiple peak intensities are averaged to obtain the AC intensity corresponding to the photoplethysmography. For each photoplethysmography set, the DC intensities corresponding to the multiple photoplethysmography waves are averaged to obtain an average DC intensity. The AC intensities corresponding to the multiple photoplethysmography waves are averaged to obtain an average AC intensity. Based on the average DC intensity and the average AC intensity, an intensity set corresponding to the photoplethysmography set is obtained, and the average DC intensity and the average AC intensity are combined to form an intensity set corresponding to the photoplethysmography set.

[0119] Perform curve fitting on multiple intensity sets to obtain an initial fitting curve, use the coefficient of the initial fitting curve as the fitting coefficient, use the intercept of the initial fitting curve as the fitting bias, obtain the bias range corresponding to the target object, compare the fitting bias with the bias range, if the fitting bias is within the bias range, use the fitting coefficient as the blood glucose concentration of the target object in the target time period; if the fitting bias is not within the bias range, adjust the fitting bias to obtain an adjusted fitting bias, adjust the fitting bias within the bias range, perform curve fitting on multiple intensity sets according to the adjusted fitting bias, obtain an adjusted fitting curve, use the coefficient of the adjusted fitting curve as the adjusted fitting coefficient, use the adjusted fitting coefficient as the blood glucose concentration of the target object in the target time period, connect multiple initial blood glucose concentrations in consecutive time periods into a curve, so as to achieve continuous monitoring of changes in the blood glucose concentration of the target object. Figure 8 As shown in the middle left figure, the units of the estimated blood glucose value and the standard blood glucose value are both mg / dL (concentration unit, milligrams per deciliter). Each point in the estimated blood glucose value curve represents the blood glucose concentration of the target object in the target time period. It is obtained using the above-mentioned blood glucose concentration analysis method. The estimated blood glucose value represents the change in the target object's blood glucose concentration, and the standard blood glucose value represents the target object's actual blood glucose concentration change. Based on the preset correction parameters, the device obtains the correction parameter value corresponding to the target object and the correction weight corresponding to the target object, multiplies the adjusted fitting coefficient with the corresponding correction weight to obtain the corrected fitting coefficient, multiplies each correction parameter value with the corresponding correction weight to obtain the corresponding multiple correction values, and adds the corrected fitting coefficient to the multiple correction values to obtain the target object's blood glucose concentration in the target time period. As shown Figure 8As shown in the middle right figure, each point in the estimated blood glucose value curve represents the blood glucose concentration of the target subject during the target time period. The blood glucose concentration is obtained by combining the physiological characteristics and environmental characteristics of the target subject using the above-mentioned blood glucose concentration analysis method. The estimated blood glucose value represents the change in the blood glucose concentration of the target subject, and the standard blood glucose value represents the actual change in the blood glucose concentration of the target subject.

[0120] In order to evaluate the accuracy of the above blood glucose concentration analysis method, formula (1) was used to calculate Figure 8 The mean absolute relative difference (mARD) between the estimated blood glucose value and the standard blood glucose value shown in is calculated using formula (2) Figure 8 The root mean square error (RMSE) between the estimated blood glucose value and the standard blood glucose value shown in is calculated using formula (3) Figure 8 The mean absolute difference (MAD) between the estimated blood glucose value and the standard blood glucose value shown in:

[0121]

[0122]

[0123]

[0124] Among them, g(t) is the standard blood glucose value, is the estimated blood glucose value, t represents the time point, and N represents the number of time points included.

[0125] right Figure 8 By comparing the results of the three indicators in the middle left and right figures, it can be seen that the estimated blood glucose value obtained by combining the physiological characteristics and environmental characteristics of the target object is more accurate and closer to the standard blood glucose value than the estimated blood glucose value obtained without combining the physiological characteristics and environmental characteristics of the target object.

[0126] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0127] Based on the same inventive concept, embodiments of the present application also provide a blood glucose concentration analysis device for implementing the aforementioned blood glucose concentration analysis method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more blood glucose concentration analysis device embodiments provided below can be found in the above-described limitations of the blood glucose concentration analysis method and will not be further elaborated here.

[0128] In one embodiment, Figure 9 As shown, a blood glucose concentration analysis device is provided, including: an acquisition module 902, a fitting module 904, a comparison module 906 and an adjustment module 908, wherein:

[0129] The acquisition module 902 is used to acquire intensity sets corresponding to multiple photoplethysmographic sets of the target object within a target time period; the intensity sets include average AC intensity and average DC intensity.

[0130] The fitting module 904 is used to perform curve fitting on multiple intensity sets to obtain fitting coefficients and fitting biases.

[0131] The comparison module 906 is configured to compare the fitting offset with the offset range corresponding to the target object, and if it is determined that the fitting offset is not within the offset range, adjust the fitting offset to obtain an adjusted fitting offset.

[0132] The adjustment module 908 is configured to perform curve fitting on the multiple intensity sets based on the adjusted fitting bias to obtain an adjusted fitting coefficient, and use the adjusted fitting coefficient as the blood glucose concentration of the target subject in the target time period.

[0133] In one embodiment, the blood glucose concentration analysis device also includes a correction module, which is used to: obtain a correction parameter value of the target object; the correction parameter value corresponds to the correction parameter, and the correction parameter includes at least one of a physiological characteristic parameter and an environmental characteristic parameter; obtain multiple correction weights corresponding to the target object; the multiple correction weights include a correction weight corresponding to the adjusted fitting coefficient, and a correction weight corresponding to each correction parameter; using the adjusted fitting coefficient as the blood glucose concentration of the target object in the target time period includes: fusing the adjusted fitting coefficient and each correction parameter value with the corresponding correction weight to obtain the blood glucose concentration of the target object in the target time period.

[0134] In one embodiment, the acquisition module 902 is further used to: acquire multiple photoplethysmogram sets of the target object within a target time period; each photoplethysmogram set corresponds to an emission intensity, and each photoplethysmogram set includes at least two photoplethysmograms; for each photoplethysmogram, filter the photoplethysmogram to obtain a DC signal and an AC signal, determine the DC intensity corresponding to the photoplethysmogram based on the signal intensity of the DC signal, and determine the AC intensity corresponding to the photoplethysmogram based on the AC signal; for each photoplethysmogram set, average the DC intensities corresponding to the multiple photoplethysmograms to obtain an average DC intensity, average the AC intensities corresponding to the multiple photoplethysmograms to obtain an average AC intensity, and obtain an intensity set corresponding to the photoplethysmogram set based on the average DC intensity and the average AC intensity.

[0135] In one embodiment, the blood glucose concentration analysis device further includes an evaluation module, which is used to: perform quality evaluation on the photoelectric volumetric pulse wave to obtain a quality evaluation result of the photoelectric volumetric pulse wave; the quality evaluation result includes evaluation values corresponding to each band constituting the photoelectric volumetric pulse wave; remove the band corresponding to the evaluation value less than the evaluation threshold from the photoelectric volumetric pulse wave to obtain an adjusted photoelectric volumetric pulse wave; for each photoelectric volumetric pulse wave, filter the photoelectric volumetric pulse wave to obtain a DC signal and an AC signal, including: for each adjusted photoelectric volumetric pulse wave, filter the adjusted photoelectric volumetric pulse wave to obtain a DC signal and an AC signal.

[0136] In one embodiment, the acquisition module 902 is further used to: obtain multiple trough coordinates in the AC signal, perform curve fitting on the multiple trough coordinates to obtain a fitting signal; calculate the difference between the AC signal and the fitting signal to obtain a target AC signal; and average the multiple peak intensities in the target AC signal to obtain the AC intensity corresponding to the photoelectric volume pulse wave.

[0137] In one embodiment, the blood glucose concentration analysis device further includes an analysis module, which is used to: obtain multiple historical time periods of the target object and multiple intensity sets corresponding to each historical time period; for each historical time period, perform curve fitting on the multiple intensity sets corresponding to the historical time period to obtain a historical fitting bias; and based on the multiple historical fitting biases, obtain a bias range corresponding to the target object.

[0138] In one embodiment, the comparison module 906 is further configured to: when it is determined that the fitting bias is within the bias range, use the fitting coefficient as the blood glucose concentration of the target subject in the target time period.

[0139] Each module in the blood glucose analysis device described above may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor within an electronic device in hardware form, or may be stored in a memory within the electronic device in software form, allowing the processor to call and execute the corresponding operations of each module.

[0140] In one embodiment, an electronic device is provided. The electronic device may be a terminal, and its internal structure diagram may be as follows: Figure 10 As shown. The electronic device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the electronic device is used to exchange information between the processor and an external device. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a blood glucose concentration analysis method is implemented. The display unit of the electronic device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the electronic device casing, or an external keyboard, touchpad or mouse.

[0141] Those skilled in the art will understand that Figure 10The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0142] In one embodiment, an electronic device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0143] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0144] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0145] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0146] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0147] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0148] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for analyzing blood glucose concentration, characterized in that: The method comprises: Acquire intensity sets corresponding to a plurality of photoplethysmographic sets of a target object within a target time period; the intensity sets include an average AC intensity and an average DC intensity; Performing curve fitting on the plurality of intensity sets to obtain fitting coefficients and fitting biases; Comparing the fitting offset with an offset range corresponding to the target object, and if it is determined that the fitting offset is not within the offset range, adjusting the fitting offset to obtain an adjusted fitting offset; Based on the adjusted fitting bias, curve fitting is performed on the plurality of intensity sets to obtain an adjusted fitting coefficient, and the adjusted fitting coefficient is used as the blood glucose concentration of the target subject in the target time period.

2. The method according to claim 1, characterized in that The method further comprises: performing curve fitting on the plurality of intensity sets based on the adjusted fitting bias to obtain an adjusted fitting coefficient; and then: Acquiring a correction parameter value of the target object; the correction parameter value corresponds to a correction parameter, and the correction parameter includes at least one of a physiological characteristic parameter and an environmental characteristic parameter; Acquire a plurality of correction weights corresponding to the target object; the plurality of correction weights include a correction weight corresponding to the adjustment fitting coefficient and a correction weight corresponding to each of the correction parameters; The step of using the adjusted fitting coefficient as the blood glucose concentration of the target subject in the target time period includes: The adjusted fitting coefficient and each of the correction parameter values are integrated with the corresponding correction weights to obtain the blood glucose concentration of the target subject in the target time period.

3. The method according to claim 1, characterized in that The step of obtaining an intensity set corresponding to a plurality of photoplethysmogram sets of a target object within a target time period includes: Acquire multiple photoplethysmogram sets of the target object within the target time period; each photoplethysmogram set corresponds to an emission intensity, and each photoplethysmogram set includes at least two photoplethysmograms; For each photoplethysmogram, filtering the photoplethysmogram to obtain a DC signal and an AC signal, determining a DC intensity corresponding to the photoplethysmogram based on a signal strength of the DC signal, and determining an AC intensity corresponding to the photoplethysmogram based on the AC signal; For each photoplethysmogram set, the DC intensities corresponding to the multiple photoplethysmograms are averaged to obtain an average DC intensity, and the AC intensities corresponding to the multiple photoplethysmograms are averaged to obtain an average AC intensity. Based on the average DC intensity and the average AC intensity, an intensity set corresponding to the photoplethysmogram set is obtained.

4. The method according to claim 3, characterized in that For each of the photoplethysmograms, filtering is performed on the photoplethysmogram to obtain a DC signal and an AC signal, which also includes: Performing a quality assessment on the photoplethysmography to obtain a quality assessment result of the photoplethysmography; the quality assessment result includes an assessment value corresponding to each band constituting the photoplethysmography; removing the waveband corresponding to the evaluation value less than the evaluation threshold from the photoplethysmogram to obtain an adjusted photoplethysmogram; The filtering process for each photoplethysmogram to obtain a DC signal and an AC signal includes: For each of the adjusted photoplethysmograms, filtering is performed on the adjusted photoplethysmogram to obtain a direct current signal and an alternating current signal.

5. The method according to claim 3, characterized in that The determining, based on the AC signal, the AC intensity corresponding to the photoplethysmography comprises: Acquiring multiple trough coordinates in the AC signal, performing curve fitting on the multiple trough coordinates to obtain a fitting signal; Calculating the difference between the AC signal and the fitting signal to obtain a target AC signal; The multiple peak intensities in the target AC signal are averaged to obtain the AC intensity corresponding to the photoplethysmography.

6. The method according to claim 1, characterized in that The step of comparing the fitting offset with the offset range corresponding to the target object further includes: Acquire multiple historical time periods of the target object and multiple intensity sets corresponding to each of the historical time periods; For each of the historical time periods, curve fitting is performed on multiple intensity sets corresponding to the historical time period to obtain a historical fitting bias; Based on the multiple history matching offsets, an offset range corresponding to the target object is obtained.

7. The method according to claim 1, characterized in that The step of comparing the fitting offset with the offset range corresponding to the target object further includes: When it is determined that the fitting bias is within the bias range, the fitting coefficient is used as the blood glucose concentration of the target subject in the target time period.

8. A blood glucose concentration analysis device, characterized in that: The device comprises: An acquisition module, configured to acquire intensity sets corresponding to a plurality of photoplethysmographic sets of a target object within a target time period; the intensity sets include an average AC intensity and an average DC intensity; A fitting module, configured to perform curve fitting on the plurality of intensity sets to obtain a fitting coefficient and a fitting bias; a comparison module, configured to compare the fitting offset with an offset range corresponding to the target object, and if it is determined that the fitting offset is not within the offset range, adjust the fitting offset to obtain an adjusted fitting offset; An adjustment module is configured to perform curve fitting on the plurality of intensity sets based on the adjustment fitting bias to obtain an adjustment fitting coefficient, and use the adjustment fitting coefficient as the blood glucose concentration of the target subject in the target time period.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images