Blood glucose detection method, device, equipment, medium and program product

Abstract

The invention relates to a blood glucose detection method and device, equipment, a medium and a program product, the blood glucose detection method comprises the steps that user behavior information and detection data are obtained, the user behavior information is used for representing the execution condition of at least one user behavior capable of influencing blood glucose changes, and the detection data can represent vital signs of a user; and determining blood glucose detection information according to the user behavior information and the detection data. The execution condition of the user behavior influencing the blood glucose change and the vital signs of the user are jointly used as the basis for determining the blood glucose detection information, multi-dimensional information can be synthesized for analysis, the accuracy of the detection result is ensured, the detection response time is shortened, the influence of the user behavior habit on the blood glucose is conveniently evaluated, and the user experience is improved. And the user experience is improved.

Description

Technical Field

[0001] This disclosure relates to the field of blood glucose testing, specifically to a blood glucose testing method, device, equipment, medium, and procedure product. Background Technology

[0002] In recent years, with the rapid development of physiological indicator detection technology and the continuous iteration of wearable devices, wearable devices with non-invasive physiological indicator detection functions have been widely used in people's daily health monitoring. Blood glucose, as a key indicator for measuring a user's health, can be indirectly detected using optical methods through the sensors of wearable devices.

[0003] However, the use of related technologies for blood glucose testing has problems such as insufficient accuracy of test results and excessively long testing time. Furthermore, it is difficult to assess the impact of user behavior on blood glucose, resulting in a poor user experience. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this disclosure provides a blood glucose detection method, device, equipment, medium, and program product.

[0005] According to a first aspect of the present disclosure, a blood glucose detection method is provided, the blood glucose detection method comprising:

[0006] Acquire user behavior information and detection data, wherein the user behavior information is used to characterize the execution of at least one user behavior that can affect blood glucose changes, and the detection data can characterize the user's vital signs;

[0007] Based on the user behavior information and the detection data, blood glucose detection information is determined.

[0008] In some embodiments of this disclosure, the blood glucose detection method further includes:

[0009] In response to a user's request for behavioral information input, display a behavioral information input interface, an image selection interface, or an image capture interface;

[0010] Receive user behavior information input by the user on the behavior information input interface, or determine the user behavior information based on a first image selected by the user on the image selection interface, or determine the user behavior information based on a second image captured by the user on the image capture interface;

[0011] And / or,

[0012] The blood glucose detection method also includes:

[0013] In response to the arrival of the preset behavior time, a behavior information recording prompt is issued;

[0014] Receive user behavior information prompted by the user in response to the behavior information record, or determine the user behavior information based on a third image prompted by the user in response to the behavior information record;

[0015] And / or,

[0016] The blood glucose detection method also includes:

[0017] In response to a corresponding action occurring in a preset application or preset platform associated with the user behavior information, the user behavior information is obtained from the preset application or preset platform.

[0018] In some embodiments of this disclosure, the user behavior information includes exercise information, and the blood glucose detection method further includes:

[0019] The motion information is determined based on acceleration and / or gyroscope signals.

[0020] In some embodiments of this disclosure, the user behavior information includes any one or any combination of the following:

[0021] Dietary information, which includes any one or any combination of eating time, food type and food quantity;

[0022] Medication information, which includes any one or any combination of medication time, type of medication, and dosage;

[0023] The exercise information includes any one or any combination of exercise mode, exercise intensity, and exercise duration.

[0024] In some embodiments of this disclosure, the detection data includes multiple different detection signals detected by the wearable device, and the different detection signals can characterize different vital signs.

[0025] In some embodiments of this disclosure, the detection signal includes a near / shortwave infrared spectral signal, which is used to determine the absorption peak of glucose molecules.

[0026] In some embodiments of this disclosure, the detection signal further includes any one or any combination of the following signals:

[0027] Photoplethysmography (PPG) signal, wherein the PPG signal is used to determine hemoglobin phase differences;

[0028] Skin temperature signal, which is used to determine metabolic intensity;

[0029] Electrocardiogram (ECG) signals, which are used to determine heart rate changes;

[0030] Electrodermal signals, used to determine the level of sympathetic nerve activity.

[0031] In some embodiments of this disclosure, the blood glucose detection method further includes:

[0032] In response to a preset detection operation performed by the user on a non-wearing hand, the electrocardiogram signal and / or the electrical skin signal are acquired.

[0033] In some embodiments of this disclosure, determining the blood glucose detection information based on user behavior information and the detection data includes:

[0034] Based on the user behavior information, the detection data, and the preset configuration information, the blood glucose detection information is determined. The preset configuration information is used to characterize the correspondence between the user behavior information, the detection data, and the blood glucose detection information. Different user behavior information and different detection data correspond to different influence weights, and the influence weights are used to characterize the degree of influence on the determination result.

[0035] In some embodiments of this disclosure, the influence weight corresponding to the user behavior information is negatively correlated with the time interval between the last execution of the user behavior.

[0036] In some embodiments of this disclosure, the blood glucose detection method further includes:

[0037] Acquire invasive blood glucose information, which is obtained through invasive or minimally invasive measurement methods;

[0038] Based on the invasive blood glucose information and the blood glucose detection information, the preset configuration information is corrected.

[0039] In some embodiments of this disclosure, the blood glucose detection method further includes:

[0040] Based on the blood glucose test information, determine whether the user's blood glucose level is abnormal;

[0041] If the user's blood sugar level is found to be abnormal, a notification message will be sent.

[0042] In some embodiments of this disclosure, determining whether a user's blood glucose level is abnormal based on the blood glucose detection information includes:

[0043] Based on the blood glucose detection information and the blood glucose standard change curve, difference information is determined, which is used to characterize the degree of difference between the blood glucose detection information and the blood glucose standard change curve;

[0044] If the degree of difference is greater than a preset degree of difference, the user's blood glucose is determined to be abnormal.

[0045] In some embodiments of this disclosure, the blood glucose standard change curve is determined in the following manner:

[0046] Obtain a sample set, which includes blood glucose detection information corresponding to multiple different times;

[0047] If the sample set meets the preset conditions, a standard blood glucose change curve is determined based on the sample set. The standard blood glucose change curve is used to characterize the correspondence between the blood glucose detection information and time.

[0048] In some embodiments of this disclosure, the preset conditions include sample quantity conditions and sample repeatability precision conditions; or,

[0049] The preset conditions include sample quantity conditions, sample repeatability precision conditions, and sample accuracy conditions.

[0050] In some embodiments of this disclosure, determining the standard blood glucose change curve based on the sample set includes:

[0051] The blood glucose detection information at each time point is averaged to obtain standard blood glucose information.

[0052] The blood glucose standard information within multiple preset time periods is fitted to obtain the fitting curve corresponding to each preset time period.

[0053] Based on the fitted curves, the standard blood glucose change curve is determined.

[0054] In some embodiments of this disclosure, issuing a prompt message when it is determined that the user's blood glucose level is abnormal includes:

[0055] If a user's blood sugar level is found to be abnormal, a user behavior prompt is issued. The user behavior prompt is used to prompt the user to perform a target user behavior or adjust the execution method of the target user behavior.

[0056] In some embodiments of this disclosure, the target user behavior is determined based on the influence weight corresponding to each user behavior information.

[0057] According to a second aspect of the present disclosure, a blood glucose detection device is provided, the blood glucose detection device comprising:

[0058] The acquisition module is used to acquire user behavior information and detection data. The user behavior information is used to characterize the execution of at least one user behavior that can affect blood glucose changes, and the detection data can characterize the user's vital signs.

[0059] The determination module is used to determine blood glucose detection information based on the user behavior information and the detection data.

[0060] According to a third aspect of the present disclosure, an electronic device is provided, the electronic device comprising:

[0061] processor;

[0062] Memory used to store processor-executable instructions;

[0063] The processor is configured to perform the blood glucose detection method as described in the first aspect.

[0064] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the blood glucose detection method as described in the first aspect.

[0065] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the blood glucose detection method as described in the first aspect.

[0066] The technical solutions provided by the embodiments of this disclosure may include the following beneficial effects: by using the execution of user behaviors that affect blood glucose changes and the user's vital signs as the basis for determining blood glucose detection information, it is possible to analyze information from multiple dimensions, which ensures the accuracy of the detection results, shortens the detection response time, facilitates the assessment of the impact of user behavior on blood glucose, and improves the user experience.

[0067] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0068] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0069] Figure 1 This is a flowchart illustrating a blood glucose detection method according to an exemplary embodiment.

[0070] Figure 2 This is a flowchart illustrating a blood glucose detection method according to another exemplary embodiment.

[0071] Figure 3 This is a flowchart illustrating a blood glucose detection method according to another exemplary embodiment.

[0072] Figure 4 This is a schematic diagram illustrating a preset detection operation according to an exemplary embodiment.

[0073] Figure 5This is a schematic diagram illustrating a preset detection operation according to another exemplary embodiment.

[0074] Figure 6 This is a flowchart illustrating a blood glucose detection method according to another exemplary embodiment.

[0075] Figure 7 This is a flowchart illustrating a blood glucose detection method according to another exemplary embodiment.

[0076] Figure 8 This is a flowchart illustrating, according to an exemplary embodiment, a process for determining whether a user's blood glucose level is abnormal based on blood glucose test information.

[0077] Figure 9 This is a flowchart illustrating the determination of a standard blood glucose change curve according to an exemplary embodiment.

[0078] Figure 10 This is a flowchart illustrating, according to an exemplary embodiment, the determination of a standard blood glucose variation curve based on a sample set.

[0079] Figure 11 This is a flowchart illustrating a blood glucose detection method according to another exemplary embodiment.

[0080] Figure 12 This is a block diagram of a blood glucose detection device according to an exemplary embodiment.

[0081] Figure 13 This is a block diagram of an electronic device according to an exemplary embodiment.

[0082] In the picture:

[0083] 10-Acquisition module; 20-Determination module; 101-Processing component; 102-Memory; 103-Power component; 104-Multimedia component; 105-Audio component; 106-Input / output interface; 107-Sensor component; 108-Communication component; 109-Processor. Detailed Implementation

[0084] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0085] In recent years, with the rapid development of physiological indicator detection technology and the continuous iteration of wearable devices, such as watches and wristbands, wearable devices with non-invasive physiological indicator detection functions have been widely used in people's daily health monitoring. Blood glucose, as a key indicator for measuring a user's health, can be indirectly detected by using the optical sensors of wearable devices to acquire optical signals and extracting features such as optical signal intensity, phase, and scattering coefficient.

[0086] In related technologies, the amplitude or phase changes of oxygenated and deoxygenated hemoglobin can be analyzed through photoplethysmography (PPG) signals to indirectly reflect blood glucose levels. Additionally, based on the principle of Raman spectroscopy, the deflection of glucose molecules can be analyzed through Raman spectroscopy signals to quantitatively analyze blood glucose concentration.

[0087] However, when using related technologies for blood glucose testing, the correlation between PPG signals and blood glucose is weak, resulting in a lack of direct evidence for the test results. Furthermore, it requires a long period of data acquisition to complete the output of results. On the other hand, Raman spectroscopy signals cannot be integrated into wearable devices due to the difficulty in miniaturization, leading to problems such as insufficient accuracy of test results, excessively long testing time, and difficulty in assessing the impact of user behavior on blood glucose, resulting in a poor user experience.

[0088] Based on this, an exemplary embodiment of this disclosure provides a blood glucose detection method. By acquiring user behavior information and detection data, it can determine blood glucose detection information based on the user behavior information and detection data, so as to truly reflect the user's blood glucose level through blood glucose detection information and provide a basis for user health monitoring. Using the execution of user behaviors that affect blood glucose changes and the user's vital signs as the basis for determining blood glucose detection information allows for comprehensive analysis of multi-dimensional information, ensuring the accuracy of detection results, shortening the detection response time, facilitating the assessment of the impact of user behavior habits on blood glucose, and improving the user experience.

[0089] In one exemplary embodiment, a blood glucose detection method is provided, applied to a wearable device, which may include, for example, a watch, a bracelet, or other device that can be worn on a specific part of a user's body. (Reference) Figure 1 As shown, blood glucose testing methods include:

[0090] S100. Obtain user behavior information and detection data. The user behavior information is used to characterize the execution of at least one user behavior that can affect blood glucose changes, and the detection data can characterize the user's vital signs.

[0091] In step S100, the wearable device acquires user behavior information and detection data. The user behavior information can characterize the execution of one or more user behaviors that affect blood glucose changes, and the detection data can characterize the user's vital signs. For example, a user's eating behavior, medication behavior, and exercise behavior can all affect the user's blood glucose level. Therefore, the execution of at least one of these user behaviors can be used as user behavior information, representing the user's behavioral habits. The detection data can be detection signals acquired by the wearable device in real time. The changing trends and characteristics of the detection signals can reflect the user's vital signs, such as metabolic intensity and heart rate changes.

[0092] User behavior information can be obtained through methods such as manual input by the user, automatic recognition, or cross-platform retrieval. This information can be acquired by the wearable device itself or by devices connected to it and transmitted to the wearable device. Detection data can be acquired through sensors configured in the wearable device. When a wearable device is equipped with multiple sensors, different sensors can acquire different types of detection data to characterize different vital signs.

[0093] S200: Determine blood glucose test information based on user behavior information and test data.

[0094] In step S200, since user behavior can affect blood glucose changes, user behavior information, i.e., the execution status of user behavior, can be used as the basis for determining blood glucose detection information. Because detection data can characterize a user's vital signs, and vital signs such as metabolic intensity and heart rate changes can directly or indirectly reflect blood glucose levels, detection data can also be used as the basis for determining blood glucose detection information.

[0095] In summary, blood glucose testing information can be determined simultaneously based on user behavior information and test data. This information can include, for example, blood glucose values ​​or ranges, both reflecting the user's blood glucose level. This achieves the fusion analysis of two different modalities of information—user behavior information and test data—ensuring the accuracy and efficiency of determining blood glucose testing information. For example, when determining blood glucose testing information based on user behavior information and test data, the information can be input into a pre-trained artificial intelligence model to output the corresponding blood glucose testing information. Alternatively, the blood glucose testing information can be determined based on a pre-defined correspondence between user behavior information, test data, and blood glucose testing information.

[0096] In this embodiment, by acquiring user behavior information and detection data, blood glucose detection information can be determined based on these two data points. This allows the blood glucose detection information to accurately reflect the user's blood glucose level, providing a basis for health monitoring. Using the execution of user behaviors that affect blood glucose changes and the user's vital signs as the basis for determining blood glucose detection information enables comprehensive analysis of multi-dimensional information, ensuring the accuracy of the detection results, shortening the detection response time, facilitating the assessment of the impact of user habits on blood glucose, and improving the user experience.

[0097] In some embodiments, reference Figure 2 As shown, blood glucose testing methods also include:

[0098] S310, in response to a user's request for inputting behavioral information, displays a behavioral information input interface, an image selection interface, or an image capture interface.

[0099] In step S310, when a user's behavior information input request is detected, a behavior information input interface, an image selection interface, or an image capture interface is displayed on the screen. The user can directly input user behavior information on the behavior information input interface, select a first image corresponding to the user behavior on the image selection interface, or capture a second image corresponding to the user behavior on the image capture interface. For example, for eating behavior, the first image can be an image pre-stored by the user that is related to the eating behavior and can determine the execution status of the eating behavior, and the second image can be an image captured by the user in real time that is related to the eating behavior and can determine the execution status of the eating behavior.

[0100] S320: Receive user behavior information input by the user in the behavior information input interface, or determine user behavior information based on the first image selected by the user in the image selection interface, or determine user behavior information based on the second image captured by the user in the image capture interface.

[0101] In step S320, user behavior information can be received directly from the user's behavior information input interface, or determined based on a first image selected by the user in the image selection interface, or determined based on a second image captured by the user in the image capture interface, thereby acquiring user behavior information and providing a basis for determining blood glucose detection information. For example, regarding a user's dietary behavior, the execution status of the dietary behavior can be directly received from the user's behavior information input interface, or determined based on a first image selected by the user in the image selection interface, such as one related to the type and amount of food consumed, or determined based on a second image captured by the user in the image capture interface, such as one related to the type and amount of food consumed.

[0102] It is understandable that the display of the behavior information input interface, image selection interface, or image capture interface, as well as the execution of the corresponding operations, can be implemented not only on wearable devices, but also on other devices that communicate and connect with the wearable device.

[0103] In this embodiment, when a user's request to input behavioral information is detected, the system can directly acquire or indirectly determine user behavioral information by displaying a behavioral information input interface, an image selection interface, or an image capture interface, thereby providing a basis for determining blood glucose testing information. Users can input their behavioral information in various ways, ensuring the accuracy and convenience of the wearable device in acquiring user behavioral information and improving the user experience.

[0104] In some embodiments, reference Figure 3 As shown, blood glucose testing methods also include:

[0105] S330: In response to the arrival of the preset behavior occurrence time, issue a behavior information recording prompt.

[0106] In step S330, the user can pre-set the corresponding preset behavior occurrence time for user behavior. For example, for medication behavior, the regular medication time can be determined according to the user's medication habits or the medication method prescribed by the doctor, and this can be used as the preset behavior occurrence time for medication behavior. When the preset behavior occurrence time is reached, the wearable device will issue a behavior information recording prompt to remind the user to record the user behavior information.

[0107] S340: Receive user behavior information prompted by the user regarding the behavior information record, or determine user behavior information based on a third image prompted by the user regarding the behavior information record.

[0108] In step S340, after receiving the prompt to record behavior information, the user can input user behavior information or a third image through, for example, a behavior information input interface. The third image can be an image that is pre-stored by the user or captured in real time, related to the user's behavior and capable of determining the execution status of the user's behavior. The wearable device can receive the user's input behavior information or determine the user's behavior information based on the third image input by the user, thus realizing the acquisition of user behavior information and providing a basis for determining blood glucose detection information.

[0109] In this embodiment, when a preset behavior occurrence time is detected, a behavior information recording prompt is issued, enabling the user to perform corresponding input operations in response to the prompt. This allows for the direct acquisition or indirect determination of user behavior information, thereby providing a basis for determining blood glucose test information. Issuing a behavior information recording prompt upon reaching the preset behavior occurrence time provides guidance for recording user behavior information. The user can then input their behavior information in response to this prompt, ensuring the accuracy and timeliness of the acquired user behavior information and improving the user experience.

[0110] In some embodiments, the blood glucose detection method further includes: obtaining user behavior information from a preset application or preset platform in response to a corresponding behavioral action occurring in a preset application or preset platform associated with user behavior information.

[0111] Wearable devices have preset applications or platforms associated with user behavior information. When a preset application or platform performs a corresponding action, it means that the user has the possibility of performing the corresponding user action or has determined the method of performing the corresponding user action. At this time, user behavior information can be obtained from the preset application or platform, thus realizing the acquisition of user behavior information and providing a basis for determining blood glucose detection information.

[0112] For example, regarding eating behavior, there could be a food delivery app associated with the execution of eating behavior. When a user places an order through the food delivery app, the order information can be directly retrieved to obtain user behavior information corresponding to the eating behavior, such as the type of food consumed and the amount consumed. Similarly, regarding medication behavior, there could be a medical platform associated with the execution of medication behavior. When the medical platform receives a medical order report, it can be directly retrieved to obtain user behavior information corresponding to the medication behavior, such as the type of medication and the dosage.

[0113] In this embodiment, when a corresponding action occurs in a preset application or platform associated with user behavior information, the user behavior information is obtained from the preset application or platform. This data exchange facilitates the acquisition of user behavior information, providing a basis for determining blood glucose testing information. Obtaining user behavior information from the preset application or platform enables automatic acquisition and updating of user behavior information, ensuring the accuracy and convenience of obtaining this information and improving the user experience.

[0114] In some embodiments, user behavior information includes motion information, and the blood glucose detection method further includes: determining motion information based on acceleration and / or gyroscope signals.

[0115] If user behavior information includes exercise information, wearable devices can acquire corresponding acceleration and gyroscope signals through their configured accelerometers and gyroscopes, and determine the execution status of exercise behaviors such as exercise duration and intensity based on the acceleration and gyroscope signals. This enables the acquisition of exercise information as user behavior information, providing a basis for determining blood glucose detection information.

[0116] In this embodiment, if the user behavior information includes motion information, the motion information can be directly determined based on acceleration and gyroscope signals. This enables the acquisition of motion information as user behavior information, providing a basis for determining blood glucose detection information. Using acceleration and gyroscope signals, which can be directly measured by wearable devices, as the basis for determining motion information ensures the convenience and accuracy of acquiring motion information and improves the user experience.

[0117] It should be noted that wearable devices can not only determine motion information based on acceleration and gyroscope signals, but also acquire motion information through the aforementioned methods such as manual input, automatic recognition, or cross-platform retrieval.

[0118] In some embodiments, user behavior information includes any one or more combinations of the following: dietary information, including any one or more combinations of eating time, food type, and food quantity; medication information, including any one or more combinations of medication time, drug type, and dosage; and exercise information, including any one or more combinations of exercise pattern, exercise intensity, and exercise duration.

[0119] As mentioned earlier, user behavior information can characterize the execution of at least one user behavior that affects blood glucose changes. Since eating behavior, medication behavior, and exercise behavior can all affect blood glucose changes, any one or any combination of eating behavior information, medication behavior information, and exercise behavior information can be used as user behavior information.

[0120] Dietary information is used to characterize the execution of eating behaviors. This information can include any one or any combination of eating time, food type, and food quantity. Eating time, food type, or food quantity can all represent the execution of eating behaviors. Eating time, food type, and food quantity can all affect blood glucose monitoring information. For example, all other things being equal, the longer the interval between the eating time and the current time, the lower the user's blood glucose level. The more types of high-sugar foods consumed, the higher the user's blood glucose level. The larger the food quantity consumed, the higher the user's blood glucose level.

[0121] Medication information is used to represent the execution of medication behavior. This information can include any one or a combination of medication time, medication type, and dosage. Medication time, medication type, or dosage can represent the execution of medication behavior. Medication time, medication type, and dosage can all affect blood glucose monitoring information. For example, all other things being equal, the longer the interval between the medication time and the current time, the lower the user's blood glucose level. When the medication type includes a blood glucose-lowering drug, the user's blood glucose level will be lower. The higher the dosage of the blood glucose-lowering drug, the lower the user's blood glucose level.

[0122] Exercise information is used to characterize the execution of exercise behavior. This information can include any one or any combination of exercise mode, intensity, and duration. Exercise mode, intensity, and duration can all represent the execution of exercise behavior. Exercise mode, intensity, and duration can all affect blood glucose monitoring information. For example, all other things being equal, aerobic exercise, compared to anaerobic exercise, tends to result in lower blood glucose levels. Higher exercise intensity generally leads to lower blood glucose levels. Longer exercise duration also generally leads to lower blood glucose levels.

[0123] In this embodiment, any one or any combination of dietary information, medication information, and exercise information is used as user behavior information. This allows for the representation of the execution of dietary, medication, and exercise behaviors that affect blood glucose levels, thereby providing a basis for determining blood glucose monitoring information. Dietary information, medication information, and exercise information can all include multiple different expressions, ensuring the accuracy and applicability of each type of user behavior information, thus improving the accuracy of determining blood glucose monitoring information.

[0124] In some embodiments, the detection data includes multiple different detection signals detected by the wearable device, and the different detection signals can characterize different vital signs.

[0125] As mentioned earlier, the detection data can characterize a user's vital signs. This data can include multiple different detection signals detected by the wearable device. These signals can be acquired through different sensors on the wearable device, allowing each signal to represent a different vital sign. When determining blood glucose levels based on this data, different vital signs can reflect their corresponding blood glucose levels. Furthermore, a multi-dimensional comprehensive analysis can be performed, combining the blood glucose levels reflected by each vital sign with user behavior information, thereby improving the accuracy of the determined blood glucose information.

[0126] In this embodiment, the detection data includes multiple different detection signals detected by the wearable device. Different detection signals can characterize different vital signs, which improves the diversity of detection data. The different vital signs characterized by different detection signals can reflect the corresponding blood glucose levels, thereby improving the accuracy of determining blood glucose detection information.

[0127] In some embodiments, the detection signal includes a near / shortwave infrared spectral signal, which is used to determine the absorption peak of glucose molecules.

[0128] The detection signal can include near-wave infrared (NRIR) or short-wave infrared (SWI) spectral signals, which can be acquired by NRIR and SWI sensors configured in wearable devices, respectively. Both NRIR and SWI signals can be used to determine the absorption peaks of glucose molecules. These absorption peaks represent the degree to which glucose molecules absorb light, and the concentration of glucose molecules, i.e., the blood glucose level, can be determined based on this absorption level. Therefore, NRIR and SWI signals can serve as the basis for determining blood glucose detection information.

[0129] For example, a near-infrared sensor can be used to acquire the scattering signal of a near-infrared light source, and the absorption peak of glucose molecules to near-infrared light can be determined based on the scattering signal. This absorption peak can characterize the degree of absorption of near-infrared light by glucose molecules, and can serve as a basis for determining blood glucose detection information.

[0130] In this embodiment, near-wave infrared (NWI) or short-wave infrared (SWI) spectral signals are used as detection signals. The absorption peaks of glucose molecules can be determined based on these signals, thereby determining the glucose concentration. This allows the NWI or SWI signals to be used to determine blood glucose levels. NWI or SWI signals have a strong correlation with blood glucose levels, and their characteristic vital signs directly reflect blood glucose levels, improving the accuracy of blood glucose detection.

[0131] In some embodiments, the detection signal further includes any one or a combination of the following signals: a photoplethysmography (PPG) signal used to determine hemoglobin phase differences; a skin temperature signal used to determine metabolic intensity; an electrocardiogram (ECG) signal used to determine heart rate variability; and an electrodermal signal used to determine sympathetic nerve activity.

[0132] When the detection data includes multiple detection signals, in addition to near / shortwave infrared spectral signals, the detection signals also include any one or any combination of photoplethysmography (PPG) signals, skin temperature signals, electrocardiogram (ECG) signals, and electrodermal (ED) signals. Furthermore, PPG signals, skin temperature signals, ECG signals, and EED signals can all characterize different vital signs.

[0133] The photoplethysmography (PPG) signal can be acquired by a PPG sensor. The PPG signal can determine the phase difference of hemoglobin, thus indirectly reflecting blood glucose levels through this vital sign. Therefore, the PPG signal can serve as a basis for determining blood glucose detection information. For example, the ratio of oxyhemoglobin to deoxyhemoglobin can be determined based on the PPG signal, and the phase difference of hemoglobin in medical imaging can be determined based on this ratio, thereby indirectly reflecting the user's blood glucose level through the hemoglobin phase difference.

[0134] Skin temperature signals can be acquired through skin temperature sensors. These signals are used to determine metabolic intensity, which indirectly reflects blood glucose levels through this vital sign. Therefore, skin temperature signals can serve as a basis for determining blood glucose detection information.

[0135] Electrocardiogram (ECG) signals can be acquired using an ECG sensor. ECG signals are used to determine heart rate changes, which in turn indirectly reflect blood glucose levels, making ECG signals a basis for determining blood glucose detection information.

[0136] Electrodermal signals, or EDA signals, can be acquired using EDA electrodermal sensors. These signals are used to determine the level of sympathetic nerve activity, which indirectly reflects blood glucose levels, thus enabling them to serve as a basis for determining blood glucose detection information.

[0137] In this embodiment, any one or any combination of photoplethysmography (PPG), skin temperature, electrocardiogram (ECG), and electrodermal (ED) signals, along with near-wave infrared (NRIR) or short-wave infrared (SWI) signals, are used as the detection signals included in the detection data. This allows the user's blood glucose level to be indirectly reflected through the hemoglobin phase difference, metabolic intensity, heart rate changes, and sympathetic nerve activity characterized by PPG, skin temperature, ECG, and EWI signals, respectively. This enables the detection data to serve as a basis for determining blood glucose detection information and further improves the accuracy of blood glucose detection information through different vital signs.

[0138] In some embodiments, the blood glucose detection method further includes: acquiring electrocardiogram signals and / or skin conductance signals in response to a preset detection operation performed by a user on a non-wearing hand.

[0139] Both the ECG sensor used to acquire electrocardiogram (ECG) signals and the EDA sensor used to acquire electrodermal skin (EDA) signals require close contact with the user to acquire the corresponding signals. To ensure accurate acquisition of ECG and EDA signals, the wearable device only acquires these signals when it detects a preset detection operation on the user's non-wearing hand. For example, the preset detection operation on the user's non-wearing hand is as follows: Figure 4 or Figure 5 As shown, this refers to the user's non-wearing hand touching the ECG electrocardiogram sensor or the EDA electrodermal sensor.

[0140] In this embodiment, when the wearable device detects a preset detection operation on the user's non-wearing hand, it then acquires electrocardiogram (ECG) signals or electrodermal (ED) signals. This achieves the acquisition of ECG or EDS signals and ensures the accuracy of the acquired ECG and EDS signals. It also avoids noise signals caused by poor contact from interfering with the determination of blood glucose detection information, further improving the accuracy of blood glucose detection information.

[0141] In some embodiments, determining blood glucose detection information based on user behavior information and detection data includes: determining blood glucose detection information based on user behavior information, detection data, and preset configuration information, wherein the preset configuration information is used to characterize the correspondence between user behavior information, detection data, and blood glucose detection information, wherein different user behavior information and different detection data correspond to different influence weights, and the influence weights are used to characterize the degree of influence on the determination result.

[0142] When determining blood glucose testing information based on user behavior information and test data, the determination can be made using user behavior information, test data, and preset configuration information. The preset configuration information characterizes the correspondence between user behavior information, test data, and blood glucose testing information. For example, the preset configuration information may include a pre-trained artificial intelligence model or neural network model; by inputting user behavior information and test data into the pre-trained model, the corresponding blood glucose testing information can be output. Alternatively, the preset configuration information may include a calculation formula, which can be used to calculate the corresponding blood glucose testing information based on user behavior information and test data. The preset configuration information may also include a dataset containing multiple data groups, each including user behavior information, test data, and corresponding blood glucose testing information. The blood glucose testing information corresponding to specific user behavior information and test data can be determined by searching through the data groups.

[0143] Different user behavior information and different detection data correspond to different influence weights. Influence weights characterize the degree of impact on the determined result, allowing different user behavior information and different detection data to have varying degrees of influence on the determined result. For example, if the preset configuration information is a calculation formula, and the user behavior information includes dietary information, medication information, and exercise information, and the detection signals include near-infrared spectral signals and photoplethysmography (PPG) signals, then the calculation formula includes dietary information, medication information, exercise information, near-infrared spectral signals, and PPG signals, along with coefficients corresponding to each of these information as influence weights. If the coefficients corresponding to medication information and near-infrared spectral signals are larger, they have a larger influence weight, meaning that medication information and near-infrared spectral signals have a greater impact on the determination result of blood glucose detection information. When medication information or near-infrared spectral signals change, the blood glucose detection information will change significantly accordingly.

[0144] In this embodiment, blood glucose testing information is determined based on user behavior information, test data, and preset configuration information. This ensures that the blood glucose testing information accurately reflects the user's blood glucose level, providing a basis for health monitoring. Different user behavior information and different test data are assigned different influence weights, allowing for a focus on key information that significantly impacts blood glucose levels during multi-dimensional analysis of user behavior information and test data, further improving the accuracy of determining blood glucose testing information.

[0145] In some embodiments, the influence weight of user behavior information is negatively correlated with the time interval between the last execution of the user behavior.

[0146] The influence weight of user behavior information is negatively correlated with the time interval since the last user action. That is, the longer the interval, the smaller the influence weight of the user behavior information, and the less influence it has on the determination of blood glucose test results. For example, for dietary information, as the interval since the last dietary action increases, the influence weight of the dietary information gradually decreases, and the influence of dietary information on determining blood glucose test results gradually diminishes.

[0147] In this embodiment, by setting the influence weight of user behavior information to be negatively correlated with the interval between the last execution of user behavior, the influence of user behavior information on the determination result of blood glucose test information can gradually decrease as the interval increases. This fully considers the timeliness of user behavior in determining blood glucose test information and further improves the accuracy of determining blood glucose test information.

[0148] In some embodiments, reference Figure 6 As shown, blood glucose testing methods also include:

[0149] S410. Obtain invasive blood glucose information. Invasive blood glucose information is obtained through invasive or minimally invasive measurement methods.

[0150] In step S410, the user can also obtain invasive blood glucose information through other measuring instruments using invasive or minimally invasive methods, and synchronize this invasive blood glucose information to the wearable device through various methods such as manual input, automatic recognition, or cross-platform retrieval, enabling the wearable device to acquire invasive blood glucose information. For example, invasive blood glucose information may include blood glucose information detected by a CGM blood glucose patch, which can be paired with the wearable device to enable the wearable device to acquire invasive blood glucose information. It is understood that because invasive blood glucose information is detected through invasive or minimally invasive methods, it has higher accuracy than blood glucose detection information.

[0151] S420: Based on invasive blood glucose information and blood glucose detection information, the preset configuration information is corrected.

[0152] In step S420, since invasive blood glucose information has higher accuracy than blood glucose detection information, the preset configuration information can be corrected based on the invasive blood glucose information and the determined blood glucose detection information acquired at the same time. This allows the blood glucose detection information determined based on the corrected preset configuration information to be closer to the invasive blood glucose information, thereby improving the accuracy of the correspondence represented by the preset configuration information. For example, if the preset configuration information includes a calculation formula, the coefficients corresponding to user behavior information and detection data in the calculation formula can be adjusted to gradually reduce the difference between the calculation result and the invasive blood glucose information.

[0153] In this embodiment, by acquiring invasive blood glucose information and correcting the preset configuration information based on the invasive blood glucose information and blood glucose detection information, synchronous calibration of the preset configuration information is achieved. This makes the blood glucose detection information determined by the corrected preset configuration information more similar to the invasive blood glucose information, thus having higher accuracy and further improving the accuracy of determining blood glucose detection information based on the preset configuration information.

[0154] In some embodiments, reference Figure 7 As shown, blood glucose testing methods also include:

[0155] S510. Based on the blood glucose test information, determine whether the user's blood glucose is abnormal.

[0156] In step S510, the user's blood glucose level can be determined to be abnormal based on the determined blood glucose test information. For example, when the blood glucose test information is a blood glucose value, it can be determined whether the blood glucose value is lower than a first preset blood glucose value or higher than a second preset blood glucose value. The first preset blood glucose value is lower than the second preset blood glucose value. The first and second preset blood glucose values ​​can be determined based on the range of blood glucose values ​​in a normal or healthy state and adjusted according to the user's individual differences. When the blood glucose test information is lower than the first preset blood glucose value or higher than the second preset blood glucose value, the user's blood glucose level can be determined to be abnormal.

[0157] S520: If the user's blood sugar is found to be abnormal, issue a prompt message.

[0158] In step S520, if the user's blood glucose level is determined to be abnormal, the wearable device can issue a prompt message to alert the user to the abnormal blood glucose state. The user can then perform actions to raise or lower blood glucose levels based on the prompt message to restore blood glucose to a normal state. The wearable device can issue prompt messages in various ways, such as displaying them on the screen, vibrating, or emitting an alarm sound.

[0159] For example, if the wearable device determines that the user is in a hypoglycemic state based on blood glucose monitoring information, it can display a prompt message on the display interface to remind the user that the blood glucose is too low. At this time, the user can improve blood glucose by performing dietary behaviors to maintain blood glucose at a normal level.

[0160] In this embodiment, based on blood glucose detection information, it is determined whether the user's blood glucose is abnormal. If the user's blood glucose is determined to be abnormal, a prompt message is issued, which realizes the prompt message to the user to change the blood glucose according to the prompt message, so as to restore the blood glucose to a normal state and avoid damage to the user's health caused by abnormal blood glucose.

[0161] In some embodiments, reference Figure 8 As shown, based on blood glucose test information, it is determined whether the user's blood glucose level is abnormal, including:

[0162] S511. Based on blood glucose detection information and blood glucose standard change curve, determine the difference information. The difference information is used to characterize the degree of difference between blood glucose detection information and blood glucose standard change curve.

[0163] In step S511, the blood glucose standard change curve describes the standard change trend of blood glucose over time, representing the user's blood glucose level under normal conditions over a period of time. The blood glucose standard change curve can be determined, for example, based on a sample set composed of blood glucose detection information. When determining whether a user's blood glucose is abnormal, difference information can be determined based on the blood glucose detection information determined at the current moment and the pre-determined blood glucose standard change curve, so as to characterize the degree of difference between the blood glucose detection information and the blood glucose standard change curve through the difference information.

[0164] S512. If the difference is greater than the preset difference, determine that the user's blood glucose is abnormal.

[0165] In step S512, if the degree of difference represented by the difference information is greater than the preset degree of difference, it means that the user's current blood glucose level is too different from the standard blood glucose level under normal circumstances, and the user is in an abnormal blood glucose state. In this case, the user's blood glucose is determined to be abnormal and a prompt message is issued.

[0166] For example, the blood glucose value represented by the blood glucose detection information determined at the current time of 12:00 can be compared with the standard blood glucose value at 12:00 corresponding to the standard change curve, and the blood glucose difference can be used as the difference information. If the blood glucose difference is greater than the preset blood glucose difference, the user's blood glucose is determined to be abnormal.

[0167] In this embodiment, based on blood glucose test information and the blood glucose standard change curve, difference information is determined. If the difference exceeds a preset difference level, the user's blood glucose is determined to be abnormal, thus realizing the judgment of whether the user's blood glucose is abnormal. Using the blood glucose standard change curve as the basis for comparison with blood glucose test information allows the trend of blood glucose standard change under normal circumstances to serve as a reference for whether blood glucose is abnormal, improving the convenience and accuracy of determining whether the user's blood glucose is abnormal, thereby ensuring the prompting function of the alert information.

[0168] In some embodiments, reference Figure 9 As shown, the standard blood glucose variation curve is determined in the following way:

[0169] S610. Obtain a sample set, which includes blood glucose test information corresponding to multiple different times.

[0170] In step S610, the wearable device can obtain a sample set by retrieving stored data. The sample set includes blood glucose detection information determined at multiple different times. It is understandable that the more times included in the sample set, the more blood glucose detection information corresponding to each time point, and the more accurate the subsequently determined blood glucose standard change curve will be.

[0171] S620. If the sample set meets the preset conditions, determine the standard blood glucose change curve based on the sample set. The standard blood glucose change curve is used to characterize the correspondence between blood glucose detection information and time.

[0172] In step S620, if the sample set meets the preset conditions, it means the sample set meets the sample requirements and can be used to determine the standard blood glucose change curve. At this point, the standard blood glucose change curve can be determined based on the sample set. The obtained standard blood glucose change curve can characterize the correspondence between blood glucose detection information and time, providing a basis for determining difference information and judging whether the user's blood glucose is abnormal. The time range described by the standard change curve can be set according to different times in the sample set and the user's needs. For example, the standard change curve can be used to characterize the correspondence between blood glucose detection information and time within the time ranges of 8:00–10:00, 12:00–14:00, and 18:00–20:00, or it can be used to characterize the correspondence between blood glucose detection information and time within the entire 24-hour period.

[0173] In this embodiment, by acquiring a sample set and determining the standard blood glucose change curve based on the sample set when it meets preset conditions, the standard blood glucose change is determined, providing a basis for determining difference information and judging whether a user's blood glucose is abnormal. By setting preset conditions for the sample set, it can be ensured that the sample set meets the sample requirements when used as the basis for determining the standard blood glucose change curve, thus ensuring the accuracy of the standard blood glucose change curve and improving the accuracy of determining whether a user's blood glucose is abnormal.

[0174] In some embodiments, the preset conditions include sample quantity conditions and sample repeatability precision conditions; or, the preset conditions include sample quantity conditions, sample repeatability precision conditions, and sample accuracy conditions.

[0175] Preset conditions may include sample size and sample repeatability precision conditions, or sample size, sample repeatability precision, and sample accuracy conditions. The sample size condition determines whether the sample size in the sample set meets the requirements, i.e., whether the sample size can guarantee the accuracy of determining the blood glucose standard change curve. The sample repeatability precision condition determines whether the sample repeatability precision in the sample set meets the requirements, i.e., whether the sample precision can guarantee the accuracy of determining the blood glucose standard change curve. The sample accuracy condition determines whether the accuracy in the sample set meets the requirements, i.e., whether the sample accuracy can guarantee the accuracy of determining the blood glucose standard change curve.

[0176] For example, the sample size condition, sample repeatability precision condition, and sample accuracy condition can be determined according to the GB / T19634-2021 standard, wherein the sample size condition may include, for example:

[0177] a. For a total of seven days, user behavior information corresponding to a certain user behavior is obtained at least once a day, and the cumulative measurement data reaches a preset amount (e.g., a total of 200) during the user behavior and within the preset time before and after the behavior (e.g., from one hour before the eating behavior to two hours after the eating behavior).

[0178] b. The number of blood glucose test results for the sample in each of the following ranges (30, 50], (50, 110], (110, 150], (150, 250], and (250, 400] mg / dL is 20 or more.

[0179] c. The number of blood glucose test results for the samples in the blood glucose ranges ≤50, (50, 80], (80, 120], (120, 200], (200, 300], (300, 400], and >400 mg / dL reached 2, 8, 10, 15, 8, 5, and 2 or more, respectively.

[0180] Sample repeatability precision conditions may include, for example:

[0181] d. When the blood glucose test result is less than 100 mg / dL, the standard deviation of the blood glucose test result is less than 0.42 mmol / L.

[0182] e. When the blood glucose level is greater than or equal to 100 mg / dL, the coefficient of variation of the blood glucose level is less than 7.5%.

[0183] Sample accuracy conditions may include, for example:

[0184] f. When comparing invasive blood glucose information, at least 95% of the differences should be within ±0.83 mmol / L when the blood glucose level is less than 100 mg / dL.

[0185] g. When comparing invasive blood glucose information, at least 95% of the differences should be within ±15% when the blood glucose test result is greater than or equal to 100 mg / dL.

[0186] In this embodiment, the sample quantity condition and sample repeatability precision condition, or the sample quantity condition, sample repeatability precision condition and sample accuracy condition, are used as preset conditions. This provides a basis for whether the sample set meets the preset conditions, ensuring that the sample quantity, sample precision and sample accuracy in the sample set can meet the requirements, so as to ensure the accuracy of determining the standard blood glucose change curve, thereby improving the accuracy of determining whether the user's blood glucose is abnormal.

[0187] In some embodiments, reference Figure 10 As shown, based on the sample set, the standard blood glucose variation curve is determined, including:

[0188] S621. The blood glucose detection information at each time point is averaged to obtain the standard blood glucose information.

[0189] In step S621, for each time point in the sample set, the average of multiple blood glucose test results corresponding to that time point is calculated to obtain standard blood glucose information. This standard blood glucose information represents the standard blood glucose level under normal conditions at that time point. It can be understood that if a certain time point corresponds to only one blood glucose test result, that blood glucose test result can be directly identified as the standard blood glucose information.

[0190] S622. Fit the blood glucose standard information for multiple preset time periods to obtain the fitting curve corresponding to each preset time period.

[0191] In step S622, multiple preset time periods can be determined, and the blood glucose standard information within each preset time period can be fitted to obtain the fitting curve corresponding to each preset time period. The multiple preset time periods can be set according to different times in the sample set and the user's needs. For example, the three time periods of 8:00–10:00, 12:00–14:00, and 18:00–20:00 can be used as preset time periods.

[0192] S623. Based on each fitted curve, determine the standard change curve of blood glucose.

[0193] In step S623, a standard blood glucose variation curve can be determined based on the fitted curves corresponding to each preset time period. For example, the fitted curves can be directly combined into a standard blood glucose variation curve, so that the standard blood glucose variation curve can characterize the correspondence between blood glucose detection information and time within multiple preset time periods. Alternatively, multiple fitted curves can be subjected to difference or secondary fitting processing to obtain a standard blood glucose variation curve corresponding to the entire 24-hour period, so that the standard blood glucose variation curve can characterize the correspondence between blood glucose detection information and time within the entire 24-hour period.

[0194] In this embodiment, by averaging the blood glucose test information at each time point, standard blood glucose information is obtained. Then, the standard blood glucose information within multiple preset time periods is fitted to obtain fitting curves for each preset time period. Based on these fitting curves, the standard blood glucose change curve can be determined, providing a basis for identifying discrepancies and judging whether a user's blood glucose is abnormal. By averaging the blood glucose test information and fitting the standard blood glucose information, it is ensured that the fitted curves can describe the correspondence between blood glucose test information and time within the corresponding preset time period, thus guaranteeing the accuracy of determining the standard blood glucose change curve.

[0195] In some embodiments, when it is determined that a user's blood glucose level is abnormal, a prompt message is issued, including: when it is determined that a user's blood glucose level is abnormal, a user behavior prompt is issued, which is used to prompt the user to perform a target user behavior or adjust the execution method of the target user behavior.

[0196] When a user's blood glucose level is determined to be abnormal, the alert message may include a user behavior prompt in addition to informing the user of the abnormal blood glucose state. This prompt prompts the user to perform a target user action among various options, or to adjust the execution method of the target user action. Upon receiving the user behavior prompt, the user can then perform the corresponding target user action or adjust its execution method accordingly.

[0197] For example, if a user's blood glucose level is determined to be abnormally low, a user behavior prompt is issued. This prompt advises the user to perform a dietary action, or adjust the type or amount of food consumed, to raise their blood glucose level and restore it to normal. Conversely, if a user's blood glucose level is determined to be abnormally high, a user behavior prompt is issued. This prompt advises the user to take medication, or adjust the type and dosage of medication consumed, to lower their blood glucose level and restore it to normal.

[0198] In this embodiment, when it is determined that a user's blood sugar is abnormal, a user behavior prompt can be issued to prompt the user to perform a target user behavior among various user behaviors, or to adjust the execution method of the target user behavior. This allows the user to adjust their blood sugar by performing the target user behavior or adjusting the execution method of the target user behavior after receiving the user behavior prompt, so as to restore the blood sugar to a normal state. This facilitates the user's timely control of blood sugar and improves the user experience.

[0199] In some embodiments, the target user behavior is determined based on the influence weight corresponding to each user behavior information.

[0200] Among various user behaviors, the target user behavior corresponding to the user behavior prompt is determined based on the influence weight of each user behavior information. As mentioned earlier, the influence weight is used to characterize the degree of influence of the corresponding user behavior information on the determination result of blood glucose test information. Therefore, the user behavior corresponding to the user behavior information with the largest influence weight, that is, the user behavior information with the greatest influence on the determination result of blood glucose test information, can be determined as the target user behavior.

[0201] For example, when a user's blood sugar is in an abnormally low state, if the dietary information has the greatest influence weight among dietary information, medication information, and exercise information, that is, the dietary information has the greatest influence on blood sugar detection information, then the dietary behavior corresponding to the dietary information can be identified as the target user behavior. The issued user behavior prompt can prompt the user to perform the dietary behavior or change the type and amount of food consumed, so as to encourage the user to raise their blood sugar to a normal level by performing the dietary behavior or changing the type and amount of food consumed.

[0202] In this embodiment, the target user behavior is determined according to the influence weight corresponding to each user behavior information, so that the target user behavior can have the greatest impact on blood glucose level. This makes the user behavior prompts have a targeted prompting effect on changing abnormal blood glucose, ensuring that users can adjust their blood glucose in the most effective way according to the user behavior prompts, thereby ensuring the timeliness of blood glucose control and improving the user experience.

[0203] In one exemplary embodiment, a blood glucose detection method is provided, applied to a wearable device, with reference to... Figure 11 As shown, blood glucose testing methods include:

[0204] S1. In response to the user's request for inputting behavioral information, display the behavioral information input interface, image selection interface, or image capture interface;

[0205] S2. Receive user behavior information input by the user in the behavior information input interface, or determine user behavior information based on the first image selected by the user in the image selection interface, or determine user behavior information based on the second image captured by the user in the image capture interface.

[0206] S3. In response to the arrival of the preset behavior occurrence time, issue a behavior information recording prompt;

[0207] S4. Receive user behavior information input by the user in response to the prompt for behavior information recording, or determine user behavior information based on the third image input by the user in response to the prompt for behavior information recording;

[0208] S5. In response to a corresponding action occurring in a preset application or preset platform associated with user behavior information, obtain user behavior information from the preset application or preset platform.

[0209] S6. Determine motion information based on acceleration and / or gyroscope signals;

[0210] S7. Acquire any one or any combination of near / shortwave infrared spectral signals, photoplethysmography pulse wave signals, skin temperature signals, electrocardiogram signals, and electrodermal signals as detection data;

[0211] S8. Determine blood glucose detection information based on user behavior information, detection data, and preset configuration information;

[0212] S9. Obtain invasive blood glucose information. Invasive blood glucose information is obtained through invasive or minimally invasive measurement methods.

[0213] S10. Based on invasive blood glucose information and blood glucose detection information, the preset configuration information is corrected;

[0214] S11. Based on blood glucose detection information and blood glucose standard change curve, determine the difference information. The difference information is used to characterize the degree of difference between blood glucose detection information and blood glucose standard change curve.

[0215] S12. If the difference is greater than the preset difference, the user's blood glucose is determined to be abnormal.

[0216] S13. If the user's blood sugar is found to be abnormal, issue a prompt message.

[0217] In this embodiment, by acquiring user behavior information and detection data, blood glucose detection information can be determined based on these two data points. This allows the blood glucose detection information to accurately reflect the user's blood glucose level, providing a basis for health monitoring. Using the execution of user behaviors that affect blood glucose changes and the user's vital signs as the basis for determining blood glucose detection information allows for comprehensive analysis of multi-dimensional information, ensuring the accuracy of the detection results, shortening the detection response time, and facilitating the assessment of the impact of user habits on blood glucose, thus improving the user experience. Using the blood glucose standard change curve as a basis for comparison with blood glucose detection information allows the trend of blood glucose standard changes under normal conditions to serve as a reference for whether blood glucose is abnormal, improving the convenience and accuracy of determining whether a user's blood glucose is abnormal, thereby ensuring the effectiveness of the alert information.

[0218] In one exemplary embodiment, a blood glucose detection device is provided for use in a wearable device, referenced to... Figure 12 As shown, the blood glucose testing device includes an acquisition module 10 and a determination module 20. The acquisition module 10 is used to acquire user behavior information and test data. The user behavior information is used to characterize the execution of at least one user behavior that can affect blood glucose changes, and the test data can characterize the user's vital signs. The determination module 20 is used to determine blood glucose test information based on the user behavior information and the test data.

[0219] In this embodiment, the acquisition module 10 acquires user behavior information and detection data, and the determination module 20 determines blood glucose detection information based on the user behavior information and detection data. This allows the blood glucose detection information to accurately reflect the user's blood glucose level, providing a basis for user health monitoring. Using the execution of user behaviors that affect blood glucose changes and the user's vital signs as the basis for determining blood glucose detection information allows for comprehensive analysis of multi-dimensional information, ensuring the accuracy of the detection results, shortening the detection response time, facilitating the assessment of the impact of user behavior habits on blood glucose, and improving the user experience.

[0220] In one embodiment, the acquisition module 10 is further configured to: display a behavior information input interface, an image selection interface, or an image capture interface in response to a user's behavior information input request; receive user behavior information input by the user on the behavior information input interface, or determine user behavior information based on a first image selected by the user on the image selection interface, or determine user behavior information based on a second image captured by the user on the image capture interface; and / or, issue a behavior information recording prompt in response to the arrival of a preset behavior occurrence time; receive user behavior information input by the user in response to the behavior information recording prompt, or determine user behavior information based on a third image input by the user in response to the behavior information recording prompt; and / or, acquire user behavior information from a preset application or preset platform in response to a corresponding behavior action occurring in a preset application or preset platform associated with the user behavior information.

[0221] In one embodiment, the user behavior information includes motion information, and the acquisition module 10 is further configured to: determine the motion information based on acceleration and / or gyroscope signals.

[0222] In one embodiment, user behavior information includes any one or any combination of the following: dietary information, which includes any one or any combination of eating time, food type, and food quantity; medication information, which includes any one or any combination of medication time, drug type, and dosage; and exercise information, which includes any one or any combination of exercise pattern, exercise intensity, and exercise duration.

[0223] In one embodiment, the detection data includes multiple different detection signals detected by the wearable device, and the different detection signals can characterize different vital signs.

[0224] In one embodiment, the detection signal includes a near / shortwave infrared spectral signal, which is used to determine the absorption peak of glucose molecules.

[0225] In one embodiment, the detection signal further includes any one or any combination of the following signals: photoplethysmography (PPG) signal, used to determine hemoglobin phase difference; skin temperature signal, used to determine metabolic intensity; electrocardiogram (ECG) signal, used to determine heart rate changes; and electrodermal signal, used to determine sympathetic nerve activity.

[0226] In one embodiment, the acquisition module 10 is further configured to: acquire electrocardiogram signals and / or electrodermal signals in response to a preset detection operation performed by the user on a non-wearing hand.

[0227] In one embodiment, the determining module 20 is further configured to: determine blood glucose detection information based on user behavior information, detection data and preset configuration information, wherein the preset configuration information is used to characterize the correspondence between user behavior information, detection data and blood glucose detection information, wherein different user behavior information and different detection data correspond to different influence weights, and the influence weights are used to characterize the degree of influence on the determination result.

[0228] In one embodiment, the influence weight of user behavior information is negatively correlated with the time interval between the last execution of the user behavior.

[0229] In one embodiment, the blood glucose detection device further includes a calibration module, which is used to: acquire invasive blood glucose information, which is acquired through invasive or minimally invasive measurement methods; and calibrate preset configuration information based on the invasive blood glucose information and the blood glucose detection information.

[0230] In one embodiment, the blood glucose detection device further includes a prompting module, which is used to: determine whether the user's blood glucose is abnormal based on the blood glucose detection information; and issue a prompting message if the user's blood glucose is determined to be abnormal.

[0231] In one embodiment, the prompting module is further configured to: determine difference information based on blood glucose detection information and blood glucose standard change curve, wherein the difference information is used to characterize the degree of difference between blood glucose detection information and blood glucose standard change curve; if the degree of difference is greater than a preset degree of difference, determine that the user's blood glucose is abnormal.

[0232] In one embodiment, the prompting module is further configured to: acquire a sample set, the sample set including blood glucose detection information corresponding to multiple different times; if the sample set meets preset conditions, determine a blood glucose standard change curve based on the sample set, the blood glucose standard change curve being used to characterize the correspondence between blood glucose detection information and time.

[0233] In one embodiment, the preset conditions include sample quantity conditions and sample repeatability precision conditions; or, the preset conditions include sample quantity conditions, sample repeatability precision conditions, and sample accuracy conditions.

[0234] In one embodiment, the prompting module is further configured to: perform mean processing on the blood glucose detection information corresponding to each time point to obtain blood glucose standard information; perform fitting processing on the blood glucose standard information in multiple preset time periods to obtain fitting curves corresponding to each preset time period; and determine the blood glucose standard change curve based on each fitting curve.

[0235] In one embodiment, the prompting module is further configured to: issue a user behavior prompt when it is determined that the user's blood sugar is abnormal, the user behavior prompt being used to prompt the user to perform a target user behavior or adjust the execution method of the target user behavior.

[0236] In one embodiment, the target user behavior is determined based on the influence weight corresponding to each user behavior information.

[0237] In one exemplary embodiment, an electronic device is provided, which may include, for example, a watch, a bracelet, or other wearable device that can be worn on a specific part of a user's body.

[0238] refer to Figure 13 As shown, the electronic device may include one or more of the following components: processing component 101, memory 102, power component 103, multimedia component 104, audio component 105, input / output (I / O) interface 106, sensor component 107, and communication component 108.

[0239] Processing component 101 typically controls the overall operation of an electronic device, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 101 may include one or more processors 109 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 101 may include one or more modules to facilitate interaction between processing component 101 and other components. For example, processing component 101 may include a multimedia module to facilitate interaction between multimedia component 104 and processing component 101.

[0240] Memory 102 is configured to store various types of data to support the operation of the electronic device. Examples of such data include instructions for any application or method used to operate on the electronic device, contact data, phonebook data, messages, pictures, videos, etc. Memory 102 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0241] Power component 103 provides power to various components of the electronic device. Power component 103 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device.

[0242] Multimedia component 104 includes a screen that provides an output interface between the electronic device and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 104 includes a front-facing camera and / or a rear-facing camera. When the electronic device is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0243] Audio component 105 is configured to output and / or input audio signals. For example, audio component 105 includes a microphone (MIC) configured to receive external audio signals when the electronic device is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 102 or transmitted via communication component 108. In some embodiments, audio component 105 also includes a speaker for outputting audio signals.

[0244] I / O interface 106 provides an interface between processing component 101 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0245] Sensor assembly 107 includes one or more sensors for providing state assessments of various aspects of the electronic device. For example, sensor assembly 107 can detect the on / off state of the electronic device, the relative positioning of components such as the display and keypad of the electronic device, changes in the position of the electronic device or a component of the electronic device, the presence or absence of user contact with the electronic device, the orientation or acceleration / deceleration of the electronic device, and temperature changes of the electronic device. Sensor assembly 107 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 107 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 107 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0246] Communication component 108 is configured to facilitate wired or wireless communication between electronic devices and other devices. Devices can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 108 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 108 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0247] In an exemplary embodiment, the electronic device may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described blood glucose detection method applied to the electronic device.

[0248] In one exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 102 including instructions, which can be executed by a processor 109 of an electronic device to perform the blood glucose detection method applied to the electronic device described above. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc. When the instructions in the storage medium are executed by the processor 109 of the electronic device, the electronic device is able to perform the blood glucose detection method shown in the above embodiment.

[0249] In one exemplary embodiment, a computer program product is also provided, including a computer program that, when executed by processor 109, implements the blood glucose detection method shown in the above embodiments.

[0250] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0251] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A blood glucose detection method, characterized in that, The blood glucose detection method includes: Acquire user behavior information and detection data, wherein the user behavior information is used to characterize the execution of at least one user behavior that can affect blood glucose changes, and the detection data can characterize the user's vital signs; Based on the user behavior information and the detection data, blood glucose detection information is determined.

2. The blood glucose detection method according to claim 1, characterized in that, The blood glucose detection method also includes: In response to a user's request for behavioral information input, display a behavioral information input interface, an image selection interface, or an image capture interface; Receive user behavior information input by the user on the behavior information input interface, or determine the user behavior information based on a first image selected by the user on the image selection interface, or determine the user behavior information based on a second image captured by the user on the image capture interface; And / or, The blood glucose detection method also includes: In response to the arrival of the preset behavior time, a prompt for behavior information recording is issued; Receive user behavior information prompted by the user in response to the behavior information record, or determine the user behavior information based on a third image prompted by the user in response to the behavior information record; And / or, The blood glucose detection method also includes: In response to a corresponding action occurring in a preset application or preset platform associated with the user behavior information, the user behavior information is obtained from the preset application or preset platform.

3. The blood glucose detection method according to claim 1, characterized in that, The user behavior information includes exercise information, and the blood glucose detection method further includes: The motion information is determined based on acceleration and / or gyroscope signals.

4. The blood glucose detection method according to claim 1, characterized in that, The user behavior information includes any one or any combination of the following: Dietary information, which includes any one or any combination of eating time, food type and food quantity; Medication information, which includes any one or any combination of medication time, type of medication, and dosage; The exercise information includes any one or any combination of exercise mode, exercise intensity, and exercise duration.

5. The blood glucose detection method according to claim 1, characterized in that, The detection data includes multiple different detection signals detected by the wearable device, and different detection signals can characterize different vital signs.

6. The blood glucose detection method according to claim 5, characterized in that, The detection signal includes near / shortwave infrared spectral signals, which are used to determine the absorption peaks of glucose molecules.

7. The blood glucose detection method according to claim 6, characterized in that, The detection signal also includes any one or any combination of the following signals: Photoplethysmography (PPG) signal, wherein the PPG signal is used to determine hemoglobin phase differences; Skin temperature signal, which is used to determine metabolic intensity; Electrocardiogram (ECG) signals, which are used to determine heart rate changes; Electrodermal signals, used to determine the level of sympathetic nerve activity.

8. The blood glucose detection method according to claim 7, characterized in that, The blood glucose detection method also includes: In response to a preset detection operation performed by the user on a non-wearing hand, the electrocardiogram signal and / or the electrical skin signal are acquired.

9. The blood glucose detection method according to claim 1, characterized in that, The step of determining blood glucose detection information based on user behavior information and the detection data includes: Based on the user behavior information, the detection data, and the preset configuration information, the blood glucose detection information is determined. The preset configuration information is used to characterize the correspondence between the user behavior information, the detection data, and the blood glucose detection information. Different user behavior information and different detection data correspond to different influence weights, and the influence weights are used to characterize the degree of influence on the determination result.

10. The blood glucose detection method according to claim 9, characterized in that, The influence weight corresponding to the user behavior information is negatively correlated with the time interval between the last execution of the user behavior.

11. The blood glucose detection method according to claim 9, characterized in that, The blood glucose detection method also includes: Acquire invasive blood glucose information, which is obtained through invasive or minimally invasive measurement methods; Based on the invasive blood glucose information and the blood glucose detection information, the preset configuration information is corrected.

12. The blood glucose detection method according to any one of claims 1 to 11, characterized in that, The blood glucose detection method also includes: Based on the blood glucose test information, determine whether the user's blood glucose level is abnormal; If the user's blood sugar level is found to be abnormal, a notification message will be sent.

13. The blood glucose detection method according to claim 12, characterized in that, The step of determining whether a user's blood glucose level is abnormal based on the blood glucose test information includes: Based on the blood glucose detection information and the blood glucose standard change curve, difference information is determined, which is used to characterize the degree of difference between the blood glucose detection information and the blood glucose standard change curve; If the degree of difference is greater than a preset degree of difference, the user's blood glucose is determined to be abnormal.

14. The blood glucose detection method according to claim 13, characterized in that, The standard blood glucose variation curve was determined in the following manner: Obtain a sample set, which includes blood glucose detection information corresponding to multiple different times; If the sample set meets the preset conditions, a standard blood glucose change curve is determined based on the sample set. The standard blood glucose change curve is used to characterize the correspondence between the blood glucose detection information and time.

15. The blood glucose detection method according to claim 14, characterized in that, The preset conditions include sample quantity conditions and sample repeatability precision conditions; or, The preset conditions include sample quantity conditions, sample repeatability precision conditions, and sample accuracy conditions.

16. The blood glucose detection method according to claim 14, characterized in that, The determination of the standard blood glucose variation curve based on the sample set includes: The blood glucose detection information at each time point is averaged to obtain standard blood glucose information. The blood glucose standard information within multiple preset time periods is fitted to obtain the fitting curve corresponding to each preset time period. Based on the fitted curves, the standard blood glucose change curve is determined.

17. The blood glucose detection method according to claim 12, characterized in that, The step of issuing a notification message when a user's blood glucose level is determined to be abnormal includes: If a user's blood sugar level is found to be abnormal, a user behavior prompt is issued. The user behavior prompt is used to prompt the user to perform a target user behavior or adjust the execution method of the target user behavior.

18. The blood glucose detection method according to claim 17, characterized in that, The target user behavior is determined based on the influence weight corresponding to each user behavior information.

19. A blood glucose detection device, characterized in that, The blood glucose detection device includes: The acquisition module is used to acquire user behavior information and detection data. The user behavior information is used to characterize the execution of at least one user behavior that can affect blood glucose changes, and the detection data can characterize the user's vital signs. The determination module is used to determine blood glucose detection information based on the user behavior information and the detection data.

20. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store processor-executable instructions; The processor is configured to perform the blood glucose detection method as described in any one of claims 1 to 18.

21. A non-transitory computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the blood glucose detection method as described in any one of claims 1 to 18.

22. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the blood glucose detection method as described in any one of claims 1 to 18.

Images