A terminal device for blood sugar management during pregnancy and a cloud server thereof

Abstract

The present application relates to a terminal device for blood sugar management during pregnancy and its cloud server, the terminal device collects physiological data and blood sugar data of a target user including the gestation period, the cloud server obtains a plurality of blood sugar data of reference users from a plurality of terminal devices and forms an overall reference data set in a manner associated with gestational age, the cloud server calculates basic statistical indicators for each group in the overall reference data set, combines the specific percentile position of the user's blood sugar data in its own group distribution, judges the current blood sugar state of the user by comparing the user's blood sugar data with the preset healthy blood sugar range, and generates a graded diet suggestion accordingly, the diet suggestion optimizes the diet structure of the target user by selecting food categories with different GI values; the terminal device receives and visually displays personalized diet suggestions matching the blood sugar status of the target user to the target user.

Description

[0001] The original basis for this divisional application is patent application No. 202510219226.9, filed on February 26, 2025, entitled "A Blood Glucose Management System for Pregnancy". Technical Field

[0002] This invention relates to the field of medical management technology, and in particular to a terminal device for blood glucose management during pregnancy and its cloud server. Background Technology

[0003] Gestational diabetes mellitus (GDM) refers to an abnormal condition of glucose metabolism that first appears or is diagnosed during pregnancy, and it is one of the most common perinatal complications. According to statistics from the International Diabetes Federation (IDF) in 2019, the global prevalence of GDM is approximately 13.2%, and it shows an increasing trend year by year. As a significant public health challenge, GDM poses a significant threat to maternal and infant health, not only increasing the risk of perinatal complications (such as gestational hypertension and preeclampsia) and adverse pregnancy outcomes (such as macrosomia, increased cesarean section rates, and preterm birth), but also being associated with an increased likelihood of the mother developing type 2 diabetes mellitus (T2DM) and cardiovascular disease in the future.

[0004] The pathogenesis of gestational diabetes mellitus (GDM) is closely related to changes in hormone levels in pregnant women. As pregnancy progresses into the mid-to-late stages, various hormones and cytokines secreted by the placenta (such as tumor necrosis factor-α and TNF-α) antagonize insulin, leading to a gradual increase in insulin resistance. When the pregnant woman's own pancreatic β cells cannot adequately respond to this physiological insulin resistance, or when β cell dysfunction is present, GDM may occur.

[0005] Effective blood glucose management is crucial for mitigating the risks associated with gestational diabetes mellitus (GDM). Traditional interventions emphasize controlling blood glucose levels through dietary plans tailored by healthcare professionals. These plans typically include a balanced intake of nutrients, with particular attention to the quality and quantity of carbohydrates.

[0006] When developing a diet plan, a key consideration is the impact of carbohydrates in food on blood sugar levels, which can be measured by the glycemic index (GI). The GI is an indicator used to describe how quickly and how much a carbohydrate in a particular food raises blood sugar. It is based on standards derived from testing in healthy, non-diabetic adults who have normal fasting blood glucose levels and no other conditions affecting carbohydrate metabolism. The GI helps identify which foods cause a rapid rise in blood sugar (high GI) and which foods provide a more stable and sustained release of energy (low GI).

[0007] Nevertheless, existing blood glucose management protocols generally lack the ability to be individually adjusted and dynamically monitored, making it difficult to adapt to the specific needs of different pregnant women. Furthermore, traditional dietary recommendations primarily rely on static glycemic index (GI) values, failing to adequately consider individual differences and the impact of real-time blood glucose fluctuations.

[0008] CN114743673A discloses a health management method, device, and electronic device for patients with gestational diabetes mellitus (GDM). This solution provides personalized dietary recommendations and prenatal exercise guidance through interaction with the target user, supplemented by professional dietary and exercise consultations. The aim is to promote proactive health management by the target user, thereby reducing the probability of complications in GDM patients.

[0009] However, the aforementioned technical solutions primarily rely on pre-set static data to formulate dietary plans and exercise strategies, failing to adequately consider the impact of individual differences on health management. This method, based on fixed parameters, has limited applicability and effectiveness when dealing with users of varying physical conditions, lifestyles, and health statuses. Furthermore, due to the lack of an effective feedback mechanism, the solution cannot dynamically adjust dietary and exercise plans based on real-time monitored blood glucose data. This results in the inability to update health management measures promptly even if the user's blood glucose levels change, thus affecting the overall effectiveness of blood glucose management.

[0010] In summary, there is an urgent need to develop a more intelligent and personalized blood glucose management system that can combine real-time blood glucose monitoring data, personal health records, and other relevant factors to provide GDM patients with accurate and flexible treatment recommendations, thereby more effectively controlling blood glucose levels and reducing the risk of maternal and infant complications.

[0011] Furthermore, on the one hand, there are differences in understanding among those skilled in the art; on the other hand, the applicant studied a large number of documents and patents when making this invention, but due to space limitations, not all details and contents were listed in detail. However, this does not mean that the present invention does not possess the features of these prior art. On the contrary, the present invention already possesses all the features of the prior art, and the applicant reserves the right to add relevant prior art to the background art. Summary of the Invention

[0012] To address the shortcomings of existing technologies, this invention aims to provide a blood glucose management system for pregnancy. It generates overall data through the use of CGM devices (continuous glucose monitors) by a large number of users, and provides personalized dietary recommendations based on the position of each user's blood glucose data within the overall data. At the same time, it dynamically adjusts the GI value in the dietary recommendations based on changes in CGM readings to achieve more effective blood glucose management.

[0013] This invention relates to a blood glucose management system for pregnancy, comprising terminal devices carried by a target user and a reference user, and a cloud server connected to the terminal devices. The cloud server is configured to: acquire physiological data and blood glucose data of the target user, including pregnancy data, from the terminal devices, and calculate a characteristic index for the target user; acquire various blood glucose data of the reference user from several terminal devices and form an overall reference dataset in a manner associated with gestational week; assign the target user to a predetermined characteristic index value range within the overall reference dataset based on the characteristic index; identify factors affecting the risk of gestational diabetes for the target user, so that the target user can manage the corresponding physiological parameters for these factors.

[0014] The personalized allocation mechanism of this invention makes health management recommendations more tailored to the actual situation of the target users, thus improving the effectiveness of health management. By identifying factors influencing the risk of gestational diabetes in target users, the system can promptly detect potential health risks. This risk identification mechanism provides a basis for clinical intervention, helping to reduce the incidence of gestational diabetes and improve the health of pregnant women and fetuses. Furthermore, by integrating the data of reference users into a comprehensive reference dataset, the system can leverage the advantages of big data analytics to improve the accuracy and reliability of the analysis. This integration of group data provides a broader reference basis for the calculation of characteristic indices and the generation of health recommendations.

[0015] In a gestational glucose management system, "physiological parameters" refer to a set of basic indicators reflecting the individual health status and dynamic changes during pregnancy. These include BMI (body mass index), gestational age, weight gain rate, hormone levels (such as progesterone, hCG, and estradiol), and continuous glucose monitoring data. These parameters are collected in real-time via terminal devices or actively input by the user, forming the raw data basis for the system's assessment of gestational diabetes mellitus (GDM) risk. For example, an excessively high BMI may indicate an obesity-related risk of insulin resistance, while abnormal hormone levels can be directly linked to the impact of placental function on glucose metabolism. The system integrates multidimensional physiological parameters into standardized scores by calculating the Feature Index (FI), eliminating dimensional differences and enabling cross-individual comparisons, providing a unified framework for subsequent analysis.

[0016] "Key parameters" are the core factors that have the most significant impact on the risk of gestational diabetes mellitus (GDM) for a specific user, selected from physiological parameters. The system uses a dynamic grouping strategy to categorize the target user and reference users with highly similar gestational age, BMI, and weight gain into a homoprotic group, and then compares the deviation of their physiological parameters from the group mean. For example, if a user's BMI deviates from the group mean by 2 standard deviations and their weight gain exceeds the medically recommended threshold, these two are identified as key parameters. If their estradiol level is abnormally elevated by 40%, the hormonal imbalance may further exacerbate insulin resistance, thus forming a composite risk profile. This precise identification mechanism avoids the drawbacks of traditional approaches that comprehensively intervene in all parameters, instead focusing on the specific indicators that most need regulation.

[0017] The purpose of this invention is to address the pain point of "blind intervention leading to metabolic disorders" in traditional blood glucose management. The system guides users to adjust their behavior only for key parameters through data-driven dynamic analysis, rather than broadly restricting diet or exercise. For example, for those with a high BMI, it recommends adjusting their diet with low-GI foods (such as oatmeal instead of white bread) rather than simply reducing food intake, thereby avoiding cortisol spikes and blood glucose rebound caused by insufficient energy intake. For those with abnormal weight gain, it designs a daily 300kcal calorie deficit (achieved through food recording and low-intensity walking) to avoid stress responses caused by strenuous exercise. Simultaneously, the system dynamically adjusts the intervention intensity by continuously monitoring changes in key parameters: if the user's weight gain meets the target for two consecutive weeks, the GI restriction is automatically relaxed to below 65; if there is no improvement, a medical collaboration process is triggered to ensure controllable risks. This strategy optimizes blood glucose control while maintaining hormonal homeostasis and metabolic balance.

[0018] According to a preferred embodiment, the cloud server further subdivides reference users within the characteristic index value range into multiple pregnancy groups based on gestational age. The cloud server further analyzes the deviation between the target user's physiological parameters and the average value of reference users within the same pregnancy group, thereby identifying one or more key parameters among several physiological parameters that affect the target user's blood glucose level. These key parameters include BMI, weight gain rate, and hormone levels. This grouping method considers physiological changes at different stages of pregnancy, making the analysis more relevant and accurate, and helping to identify specific pregnancy risks. By analyzing the deviation between the target user's physiological parameters and the average value of reference users within the same pregnancy group, the system can identify outliers for the target user. This method effectively helps identify key parameters affecting blood glucose levels, ensuring the targeting of the analysis. Once the key parameters affecting blood glucose levels are identified, the cloud server can provide personalized health management recommendations to the target user based on these factors. For example, for users with excessively high BMI, the system can recommend adjusting their diet and increasing exercise; for users with abnormal weight gain rates, corresponding intervention measures can be developed. This personalized recommendation helps improve the effectiveness of user health management.

[0019] Based on the Feature Index (FI) value, cloud servers can group users with similar FI values ​​into the same group. This approach, which integrates multiple factors influencing gestational diabetes risk into a single comprehensive index, allows cloud servers to standardize this multi-dimensional data. This means that even if target users and reference users perform differently on individual factors, commonalities or similarities can be found through FI values, enabling effective cross-individual comparisons. This grouping method ensures high homogeneity among group members, meaning they exhibit similar trends or characteristics across multiple key health indicators. Therefore, comparing and analyzing blood glucose data within such groups is more meaningful, as it is more likely to reflect the true impact of specific factors on blood glucose control, rather than random fluctuations.

[0020] According to a preferred embodiment, the cloud server can calculate the percentile of a target user's daily trend blood glucose data within their respective pregnancy group, and identify blood glucose fluctuation patterns and potential abnormalities by comparing and analyzing this data with that of a reference user. By calculating the percentile of the target user's blood glucose data within their pregnancy group, the system can provide a relative health assessment indicator. This assessment helps users understand their blood glucose level's position among other pregnant women, thereby gaining a better understanding of their health status.

[0021] According to a preferred embodiment, the terminal device includes a data acquisition unit for acquiring continuous blood glucose data. The terminal device uploads the blood glucose data recorded by the acquisition unit to a cloud server via a configured communication unit, linked to gestational week, and receives personalized dietary recommendations from the cloud server. Using a continuous blood glucose data acquisition unit enables continuous monitoring of blood glucose levels, providing more comprehensive and accurate information on blood glucose trend changes compared to traditional spot testing methods. Linking blood glucose data to gestational week during upload allows the system to more accurately analyze blood glucose variation characteristics at different stages of pregnancy, thereby providing more personalized recommendations that align with the physiological characteristics of pregnancy. Furthermore, the terminal device's design allows users to monitor blood glucose and upload data anytime, anywhere, improving ease of use and user compliance.

[0022] According to a preferred embodiment, the terminal device integrates an interactive unit that is signal-connected to the communication unit. The interactive unit is configured to receive and display dietary suggestions from a cloud server and storage unit to the user, and to provide a platform for the user to input and update personal health information, including current gestational age, weight changes, and dietary records. The interactive unit's ability to receive and display dietary suggestions from the cloud server and storage unit provides the user with a real-time information exchange platform. This instant feedback mechanism helps users adjust their eating habits based on the latest recommendations. Furthermore, the interactive unit provides a platform for users to input and update personal health information, encouraging users to actively participate in the health management process. Users can input information such as current gestational age, weight changes, and dietary records, allowing the system to better understand their personal health status.

[0023] According to a preferred embodiment, the cloud server groups the acquired overall reference dataset based on similar gestational weeks. Specifically, the cloud server adjusts the time window range for similar gestational weeks according to the user's stage of pregnancy: a relatively narrower time window is used for early and late pregnancy, and a relatively wider time window is used for mid-pregnancy. By grouping the overall reference dataset based on similar gestational weeks, the cloud server can provide more accurate and relevant data analysis. This grouping method ensures higher relevance and comparability of the compared and analyzed data. Furthermore, adjusting the time window range for similar gestational weeks according to different stages of pregnancy reflects the system's dynamic adaptability. This flexible adjustment mechanism also better matches the physiological changes at different stages of pregnancy.

[0024] According to a preferred embodiment, the cloud server can comprehensively group the overall reference dataset based on physiological data input by the user through the interactive unit of the terminal device. This grouping method, employing multi-dimensional approaches, improves the homogeneity of members within each group. The physiological data includes the user's regularly input or updated BMI and weight gain rate. By comprehensively grouping the reference dataset based on user-input physiological data (such as BMI and weight gain rate), the homogeneity of members within each group can be significantly improved. This grouping method ensures the comparability and consistency of data within groups, particularly improving the accuracy of user-corrected characteristic indices.

[0025] According to a preferred embodiment, the cloud server calculates basic statistical indicators for each group in the overall reference dataset. Combining this with the specific percentile position of the user's blood glucose data within their group, the system compares the user's blood glucose data with a preset healthy blood glucose range to determine the user's current blood glucose status and generate tiered dietary recommendations. These recommendations optimize the target user's diet by selecting food types with different glycemic index (GI) values. By calculating the basic statistical indicators for each group, the cloud server can accurately locate the specific percentile of the user's blood glucose data within that group. This method makes blood glucose assessment more accurate and can identify the user's current blood glucose status. Comparing the user's blood glucose data with the preset healthy blood glucose range helps to personalize the assessment of the user's health status. This allows for customized health recommendations to be provided to users with different blood glucose statuses. Furthermore, by selecting food types with different GI values ​​(glycemic index), the system can help users optimize their diet. This method helps to stabilize blood glucose fluctuations and improve overall health.

[0026] According to a preferred embodiment, the cloud server is configured to divide users into different groups based on gestational age. Within each gestational age group, multiple BMI ranges are set, allowing users to be further subdivided into multiple BMI subgroups. Within the same BMI subgroup, the cloud server can further subdivide users based on their weight gain rate to identify users who are gaining weight too quickly or too slowly and assign them to a special attention group. This division into different groups and subgroups allows for the provision of personalized health guidance and advice. This guidance can be adjusted according to the user's specific gestational age and weight changes, improving the effectiveness of health management.

[0027] According to a preferred embodiment, the cloud server can periodically reassess the gestational age information of target users and adjust their group accordingly. The cloud server allows users to object to automatically assigned groups and receives gestational age information manually adjusted by users through an interactive unit. Allowing users to object to automatically assigned groups and manually adjust gestational age information helps the system correct potential errors or inaccuracies, thereby improving the overall accuracy of the data. Furthermore, it enhances users' sense of participation and control, increasing their acceptance and compliance with health management recommendations. Attached Figure Description

[0028] Figure 1 This is a preferred hardware topology diagram of a pregnancy blood glucose management system provided by the present invention;

[0029] Figure 2 This is a schematic diagram of a preferred cloud server process for obtaining a characteristic index that characterizes the risk of gestational diabetes in a user, provided by the present invention.

[0030] Figure 3This is a schematic diagram of a preferred cloud server process for dividing gestational weeks, provided by the present invention.

[0031] Figure 4 This is a schematic diagram of a preferred cloud server provided by the present invention for homogenizing the overall reference dataset by gestational age, BMI and weight gain rate;

[0032] Figure 5 This is a hardware scenario diagram of a preferred gestational blood glucose management system provided by the present invention;

[0033] Figure 6a This is an example graph showing the changes in characteristic indices of a preferred cloud server for a specific target user during early pregnancy, as provided by the present invention.

[0034] Figure 6b This is an example graph showing the changes in characteristic indices of a preferred cloud server for a specific target user during the mid-pregnancy stage, as provided by the present invention.

[0035] Figure 6c This is an example graph showing the changes of a characteristic index with gestational age in late pregnancy, plotted by a preferred cloud server for a specific target user, according to the present invention.

[0036] Figure 7 This invention provides a preferred cloud server that generates a comparison chart of blood glucose data for a target user and blood glucose data for other reference users within the same FI interval.

[0037] Figure 8 This is an example of a target user's daily trend blood glucose comparison chart provided by the present invention.

[0038] List of reference numerals

[0039] 100: Terminal device; 110: Acquisition unit; 120: Communication unit; 130: Storage unit; 140: Interaction unit; 200: Cloud server. Detailed Implementation

[0040] The following is a detailed explanation with reference to the accompanying drawings.

[0041] In this application, "target user" and "reference user" refer to two categories of pregnant women participating in a gestational glucose management system. These two terms are used to distinguish individuals who play different but interconnected roles within the same system.

[0042] The target users are pregnant women currently using the system and seeking personalized blood sugar management and dietary advice. These women typically have high blood sugar levels or a need for blood sugar management, using the system to optimize their health management, particularly for effective control of their blood sugar levels. Their data is used to generate personalized health guidance plans.

[0043] Reference users refer to other pregnant women who are also pregnant and can share their blood glucose data with the system, such as... Figure 5 As shown. The blood glucose levels of these pregnant women typically remain within the normal range. The anonymized data provided constitutes a large reference database, offering a benchmark for comparison and supporting population analysis for the target users. The data from the reference users helps establish typical blood glucose patterns for each stage of pregnancy.

[0044] The identities of target users and reference users are not fixed. If a reference user, who was originally a data contributor, begins to require personalized blood glucose management services, she can activate all the functions of the smart monitoring terminal device 100 and become a target user enjoying full services. This can happen when a reference user discovers that her blood glucose levels are elevated. Conversely, if a target user has achieved effective blood glucose control or simply wishes to continue contributing data to help others, she can choose to keep the device's basic monitoring functions enabled and continue as a provider of reference data without receiving further personalized services.

[0045] Example 1

[0046] This invention relates to an intelligent system for blood glucose management during pregnancy, such as... Figure 1 , Figure 4 As shown, the system includes multiple terminal devices 100 and a cloud server 200. The terminal devices 100 can be wearable devices such as smart bracelets and smartwatches, for use by target users and reference users, such as... Figure 5 As shown, this allows for real-time collection and viewing of blood glucose data. Simultaneously, the terminal device 100 can intuitively display personalized dietary recommendations matching the target user's blood glucose level. The cloud server 200, with its powerful computing capabilities and storage capacity, rapidly processes and deeply analyzes the massive amounts of data collected by the terminal, thereby generating optimized dietary recommendations for the target user.

[0047] Preferably, such as Figure 1As shown, the system can support the access of multiple terminal devices 100 to cover more target and reference users. Each terminal device 100 interacts with the cloud server 200 via a data connection to upload and provide feedback on data. Each terminal device 100 includes a blood glucose acquisition unit 110, which can be a continuous glucose monitor (CGM) that uses a glucose sensor to dynamically monitor changes in glucose concentration in the user's subcutaneous interstitial fluid, thereby achieving continuous and dynamic blood glucose data acquisition.

[0048] Preferably, such as Figure 1 As shown, the terminal device 100 is also equipped with a communication unit 120 for uploading and receiving data. On the one hand, the communication unit 120 can upload the blood glucose data recorded by the acquisition unit 110 to the cloud server 200 in a gestational week-related manner; on the other hand, it can also receive personalized dietary suggestions generated by the cloud server 200 for the target user. The communication unit 120 can be composed of various wireless communication modules (such as Bluetooth Low Energy (BLE), Wi-Fi, Zigbee, etc.) to ensure the security, reliability, and real-time performance of data transmission.

[0049] Preferably, such as Figure 1 As shown, the terminal device 100 also includes a storage unit 130, which is equipped with a large storage capacity. On the one hand, it can store personalized dietary recommendations fed back by the cloud server 200; on the other hand, it can store the blood glucose change data of the target user since wearing the terminal device 100, so as to meet the user's need to view it at any time.

[0050] Preferably, such as Figure 1 As shown, the terminal device 100 also integrates an interaction unit 140, which can exist in the form of a mobile application interface. The interaction unit 140 is connected to the communication unit 120 and can interact directly with the target user. It is not only responsible for providing users with personalized health advice, reminders, and historical trend charts, but also supports users to input and update key personal information, such as current gestational age, weight changes, and dietary records.

[0051] Preferably, the cloud server 200, with its superior computing power and storage capacity compared to the terminal device 100, undertakes the core data processing tasks in the system. The cloud server 200 not only stores the blood glucose data and related information of all target users and reference users, but also deploys analytical models to perform in-depth analysis of complex blood glucose data and generate scientific and accurate personalized dietary recommendations, thereby effectively assisting the target users in managing their blood glucose during pregnancy.

[0052] Preferably, such as Figure 1As shown, the cloud server 200 can be configured to acquire four physiological data points from the target user's terminal device 100: gestational age, BMI, weight gain rate, and hormone levels. These data are then fed into a built-in calculation model to initially calculate the characteristic index FI. The characteristic index FI is a comprehensive quantitative indicator calculated by the cloud server 200 based on various physiological parameters of the target user. It aims to unify pregnant women with different gestational ages, BMIs, weight gain rates, and hormone levels into a standardized comparative framework, allowing target users to be assigned to groups with similar or comparable FI values ​​for research. By comparing the differences in blood glucose data between the target user and the reference user within these groups, the specific factors with the greatest impact on the risk of gestational diabetes can be identified, and personalized health management recommendations can be provided to the target user.

[0053] Preferably, the cloud server 200 can calculate the characteristic index FI using the following formula:

[0054]

[0055] Because each pregnant woman's physiological condition is different, directly comparing their blood glucose data may not accurately reflect their individual health status. Therefore, the system uses a Feature Index (FI) to comprehensively calculate multiple key health indicators for pregnant women (such as body mass index, gestational age, weight gain rate, and hormone levels), adjusting the importance weights of different indicators to ultimately generate a unified score. This process eliminates the influence of unit differences and magnitudes among different indicators, allowing for fair comparison of the complex health data of all pregnant women under the same standard. For example, the system assigns pregnant women with excessively rapid weight gain or abnormal hormone levels to specific scoring intervals and matches their blood glucose data with that of other pregnant women within the same interval. In this way, each pregnant woman can intuitively understand her own health status relative to similar groups and identify key health areas requiring attention (such as controlling weight gain or monitoring hormone changes). This standardized scoring and grouping mechanism simplifies the complexity of data processing and helps users manage health risks more effectively.

[0056] In the formula,

[0057] B represents Body Mass Index (BMI), calculated by dividing weight (P) by height (H). s Squared 1 / 2, we get:

[0058] Body mass index (BMI) has a significant impact on the risk of gestational diabetes mellitus (GDM). A higher BMI is often associated with insulin resistance; obesity leads to decreased insulin sensitivity, resulting in elevated blood sugar levels and thus increasing the risk of GDM. Furthermore, obesity can trigger chronic low-grade inflammation, which can further affect insulin function and glucose metabolism. During pregnancy, the body needs to adapt to various metabolic changes, and a high BMI may complicate this adaptation process, increasing the risk of abnormal glucose metabolism.

[0059] W represents gestational week, which refers to the number of weeks of pregnancy calculated from the first day of the last menstrual cycle.

[0060] W=D c -LMP.

[0061] D c The current date is shown, and LMP is the date of the last menstrual period. Increased gestational age may be associated with an increased risk of gestational diabetes, especially in late pregnancy.

[0062] Current date D c The system time of the target user's terminal device (100) can be automatically obtained to ensure real-time accuracy. The last menstrual date (LMP) can be entered by the user, with specific format requirements provided (such as YYYY-MM-DD or other standard date formats).

[0063] G represents the rate of weight gain, which indicates the weekly weight gain (G) during pregnancy, expressed in kilograms per week.

[0064]

[0065] T c T represents current weight (kg). pThe previous weight measurement (kg) is represented by Δt, and the time interval (weeks) is represented by Δt. Both the current and previous weight measurements can be uploaded by the user periodically (either manually entered or automatically synchronized to the terminal device 100 via Bluetooth). If the user's data upload time is not fixed, Δt can be dynamically calculated based on the upload timestamp information to ensure data accuracy. For users with low upload frequency, the cloud server 200 can be configured with a reminder mechanism to prompt the user to upload physiological data periodically via the terminal device 100 to ensure the accuracy of the assessment results. The rate of weight gain has a significant impact on the risk of gestational diabetes. Rapid weight gain may lead to increased insulin resistance, making it more challenging for the body to regulate blood sugar levels. Furthermore, rapid weight gain during pregnancy increases the metabolic burden, especially in late pregnancy, which may make blood sugar control more difficult. At the same time, rapid weight gain is often associated with unhealthy diets and lack of exercise, and these lifestyle factors further increase the risk of gestational diabetes.

[0066] H represents hormone level, and a comprehensive hormone level index is used to reflect the combined effects of multiple hormones. H = h1·H1 + h2·H2 + h3·H3.

[0067] Where: H1, H2, H3 represent the concentration values ​​of different hormones (e.g., progesterone, human chorionic gonadotropin (hCG), estradiol); h1, h2, h3 represent the corresponding weighting coefficients.

[0068] Hormone levels (H1, H2, H3) can be measured through laboratory tests at medical institutions during regular prenatal checkups. The types of hormones tested include progesterone, human chorionic gonadotropin (hCG), and estradiol. Users can upload test reports to terminal device 100, which collects data via OCR (image recognition) or manual input by the user. In the formula, h1, h2, and h3 can be set based on initial weight values ​​from medical research. By reviewing authoritative medical literature and clinical studies, the strength and correlation of the effects of progesterone (H1), hCG (H2), and estradiol (H3) on the risk of gestational diabetes mellitus (GDM) are analyzed. Initial weights are assigned to each hormone based on the reported effect size in the studies (such as regression coefficients, correlation coefficients, etc.). When the hormone test values ​​received by communication unit 120 exceed the safety threshold pre-stored in storage unit 130, the corresponding sub-weights are automatically increased to 1.5 to 2.0 times the original value. Furthermore, the weight coefficients can be adjusted based on statistical analysis. For example, a large amount of real-life data on pregnant women can be collected, including progesterone (H1), hCG (H2), estradiol (H3) concentrations, and gestational diabetes mellitus (GDM) diagnoses. Then, Pearson correlation coefficients, multiple linear regression analysis, or generalized linear models can be used to assess the independent contribution or correlation of each hormone to the risk of GDM.

[0069] Hormonal changes during pregnancy have a significant impact on the risk of developing gestational diabetes mellitus (GDM). As pregnancy progresses, the increase in levels of hormones such as progesterone, human chorionic gonadotropin (hCG), and estradiol gradually affects insulin sensitivity and glucose metabolism, leading to increased insulin resistance. Consequently, the risk of GDM varies at different gestational weeks.

[0070] w1, w2, w3, and w4 are all weighting coefficients, representing the relative importance of each factor in risk assessment. By setting weights, the different degrees of influence of each factor on the risk of gestational diabetes can be reflected. The weighting coefficients can be set based on large-scale medical statistical data, and the weight values ​​can be optimized through data analysis and other methods. For example, the initial values ​​of weighting coefficients w1 to w4 are linked to a pre-stored clinical standard database in storage unit 130 of terminal device 100. This database includes the "Guidelines for Health Management During Pregnancy" module, which is regularly updated by cooperating medical institutions. BMI and gestational age use the weight-gestational age correlation weight recommended in the guidelines. The "Clinical Pathway for Weight Management During Pregnancy," as a sub-module of the database, is developed by endocrinology experts and includes differentiated weight gain thresholds for early, mid, and late pregnancy. The system automatically calls the w3 coefficient calculation logic for the corresponding stage based on the current gestational age value, while the dynamic adjustment range of the hormone level weight w4 can be constrained by gestational age grouping rules. In addition, historical data is used to train linear regression or logistic regression models to optimize the weights of each parameter. An adaptive weight adjustment mechanism can be provided for different populations. For example, based on the basic information input by the user, a corresponding weight set is loaded, and the weights are dynamically adjusted to reflect the actual risk of different groups of people.

[0071] K represents the exponential constant of the rate of weight gain, used to adjust the strength of the impact of the rate of weight gain on risk. By changing the value of k, the nonlinear effect of the rate of weight gain on risk indicators can be controlled. The value of the exponential constant K can be based on historical medical data, and an initial range suitable for most pregnant women can be obtained by fitting a nonlinear regression model. Furthermore, dynamic adjustment techniques can be used, that is, adjusting the value of K according to each user's actual weight gain. For example, if the rate of weight gain is rapid, the value of K can be increased to better reflect the risk.

[0072] Z is the standardization factor, used to normalize the results, avoiding bias caused by variables of different dimensions and ranges, thus making FI more comparable. Its calculation formula is as follows:

[0073] Z=σ(B)+σ(W)+σ(G)+σ(H).

[0074] The calculation of the standardized factor Z can be based on a large-scale sample dataset. This dataset may include, but is not limited to, data acquired by the cloud server 200 using a large number of reference users' terminal devices 100, and may contain historical statistical data from different population groups (e.g., women of childbearing age). The calculation parameters of the standardized factor are regularly updated using the latest user data to maintain the accuracy and timeliness of the model. If user data is insufficient, the cloud server 200 can combine publicly available medical big data or perform estimations based on statistical models.

[0075] σ(B), σ(W), σ(G), and σ(H) represent the standard deviations of BMI, gestational age, weight gain rate, and overall hormone levels, respectively.

[0076]

[0077] In the formula, B i Let BMI be the value of the i-th user (target user).

[0078] The average BMI for all users (reference user);

[0079] N is the total number of samples.

[0080] Similarly, the formulas for calculating other standard deviations are as follows:

[0081]

[0082] In the formula, W i G i and H i These represent the gestational age, weight gain rate, and overall hormone level of the i-th user (target user). These are the average gestational age, weight gain rate, and overall hormone levels for all users (reference users).

[0083] In summary, the cloud server 200, based on its built-in computing model, can obtain the characteristic index FI for assessing the risk of gestational diabetes in the target user. Preferably, such as... Figure 1As shown, the cloud server 200 can be configured to collect various blood glucose data from the terminal devices 100 of various reference users, encompassing different stages of pregnancy, to form a comprehensive overall reference dataset. Based on this, after calculating the FI value of the target user, the cloud server 200 can include it in a pre-determined FI value interval corresponding to that FI value. These FI value intervals are derived by the cloud server 200 through homogeneous grouping optimization using statistical analysis algorithms based on large-scale reference user data, aiming to ensure that users within each interval have highly similar risk characteristics. The purpose of this step is to narrow the comparison range from a massive number of reference users, enabling the target user to undergo more accurate comparative analysis with other reference users with similar FI values.

[0084] Within the same FI value range, the cloud server 200 first further subdivides reference users into multiple pregnancy groups based on gestational age. This stratification strategy takes into account the unique physiological changes at different gestational stages, ensuring comparisons are made under the same or similar gestational age conditions, thus improving the relevance and reliability of the analysis results.

[0085] In conclusion, the Feature Index (FI) is not only a crucial bridge connecting individual and group health information, but also an indispensable technical means to achieve intelligent and personalized gestational blood glucose management. Through mathematical models, it transforms complex physiological variables into easily understood and applicable numerical values, contributing to improving users' blood glucose status.

[0086] Preferably, to improve the homogeneity of the groups, such as Figure 3 As shown, the cloud server 200 can first group data based on gestational age to improve the accuracy of data analysis. Specifically, the cloud server 200 automatically assigns the target user to the corresponding gestational age group based on the latest gestational age information reported by the target user. To maintain the timeliness and accuracy of the data, the cloud server 200 can reassess the gestational age of the target user at certain intervals and adjust their group accordingly. Considering the continuity of gestational age, the cloud server 200 can set a reasonable range to define "close" gestational ages, such as ±2 weeks. For example, if a target pregnant woman is in her 20th week, her blood glucose data will be compared with other reference pregnant women between 18 and 22 weeks.

[0087] Preferably, the cloud server 200 can adjust the definition of "similar" gestational week based on key events at different stages of pregnancy. These key events may include fetal developmental milestones and maternal physiological changes.

[0088] During early pregnancy, hormone levels rise rapidly, particularly changes in human chorionic gonadotropin (hCG), estrogen, and progesterone, which significantly impact metabolic function. This period is crucial for embryonic organogenesis. As the placenta begins to form and secrete various hormones, maternal insulin sensitivity changes, potentially leading to unstable blood sugar levels. Any external factor (such as blood sugar levels) can have long-term effects on fetal health. In late pregnancy, rapid fetal growth increases the maternal metabolic burden, especially the demand for glucose. As the placenta secretes more hormones that antagonize insulin, maternal insulin resistance gradually increases, and physiological changes become more pronounced, making blood sugar control more difficult. Therefore, in early pregnancy (0–12 weeks) and late pregnancy (after 28 weeks), cloud server 200 uses finer-grained time windows (such as ±1 week or specific days).

[0089] Compared to early pregnancy, hormonal fluctuations in the second trimester (12-28 weeks) tend to be more stable. Fetal growth accelerates but has not yet reached the highly active state seen in late pregnancy. During this stage, the pregnant woman's weight gain gradually accelerates, but physiological changes are relatively stable, making it suitable for large-scale group comparisons. The cloud server 200 uses a ±2-week time window, which covers a sufficient number of comparison subjects without compromising comparability due to excessively large time spans. This setting helps improve the effectiveness and reliability of statistical analysis.

[0090] After assigning pregnancy groups, the cloud server 200 will conduct a detailed comparative analysis of the target user's blood glucose data with the blood glucose data of reference users within the same pregnancy group. The specific steps are as follows: First, the percentile of the target user's blood glucose data within their respective pregnancy group is calculated to quantify their relative position compared to other reference users. The blood glucose data referred to here preferably refers to daily trend blood glucose, that is, the blood glucose changes at different times of the day obtained using a continuous glucose monitor, used to show the trend of blood glucose levels changing with time and daily activities throughout the day. This can be represented by a continuously changing blood glucose line. For example... Figure 7 The graph displays daily trend blood glucose levels for both the reference and target users. This method provides a more comprehensive understanding of the target user's blood glucose fluctuation patterns, rather than just a snapshot at a single point in time.

[0091] If a target user's daily trend blood glucose data exceeds a set threshold (e.g., exceeding 75% of reference users), an anomaly is considered to exist. This anomaly may indicate an increased risk of gestational diabetes or other health problems. For target users marked as abnormal, the cloud server 200 will further analyze which key physiological parameters (including hormone levels, BMI, and weight gain rate) show significant differences compared to other reference users. This step aims to identify specific factors that may be causing the blood glucose abnormality and provide a basis for subsequent health management. The 75th percentile threshold is dynamically linked to a blood glucose control benchmark library stored in the cloud server 200. When the 75th percentile blood glucose value of the target user's group exceeds the safe threshold for the corresponding gestational week in the benchmark library, the system automatically issues a warning for the blood glucose range. This benchmark library data is periodically updated via the communication unit 120 through a data interface from collaborating medical institutions to ensure compliance with clinical practice requirements.

[0092] To achieve this, the cloud server 200 will compare the target user's various physiological parameters with the mean or median of reference users within the same pregnancy group, identifying parameters with significant deviations. This method can quickly pinpoint factors that are significantly different from the group average, thus initially determining potential influencing factors.

[0093] Preferably, such as Figure 1 , Figure 4 As shown, in addition to gestational age, the cloud server 200 can also perform comprehensive grouping based on other physiological data input by the user through the interaction unit 140 of the terminal device 100. In this embodiment, the physiological data can be the user's BMI and weight gain rate, which are input or updated regularly (e.g., weekly).

[0094] Preferably, the BMI and weight gain rate are manually input by the user through the interaction unit 140 of the terminal device 100. This information can also be automatically synchronized by obtaining data from devices such as smart scales using the communication unit 120 of the terminal device 100. The cloud server 200 can send prompts to users who are using the terminal device 100 for the first time so that the users can provide complete height and weight information through the interaction unit 140. Based on this, the cloud server 200 can calculate the initial BMI and record the pre-pregnancy weight as a baseline.

[0095] Preferably, the cloud server 200 can convert the BMI data collected by each terminal device 100 into a standard range (e.g., 18.5–24.9 kg / m²). 2The rate of weight gain is expressed as a weekly average. BMI can be categorized according to the National Health Commission's "Recommended Values ​​for Weight Gain in Pregnant Women" (WS / T 801—2022), for example: a BMI range of ≤18.5 kg / m² for underweight women. 2 The normal BMI range is 18.5–24.9 kg / m². 2 Obese individuals with a BMI ≥ 25 kg / m² 2 Regarding the weight gain rate threshold, the cloud server 200 can set a reasonable threshold based on the latest pregnancy health guidelines and divide users into at least three groups accordingly. For example, the first weight gain rate threshold can be ≤0.2 kg / week, the second can be 0.2–0.5 kg / week, and the third can be ≥0.5 kg / week. Furthermore, the cloud server 200 can apply statistical methods such as box plots and Z-scores to identify potential outliers, preventing these extreme values ​​from affecting the accuracy of the overall statistical data. Preferably, the cloud server 200 can automatically optimize the grouping strategy based on actual user feedback and the system's internal learning process. For example, if significant differences are found between users within a group, the system will automatically adjust the threshold range for BMI or weight gain rate to ensure the rationality of the grouping.

[0096] Preferably, the cloud server 200 can employ multi-dimensional grouping logic to ensure higher homogeneity among reference users within each group, thereby enhancing the relevance and guiding significance of the comparison results for the target users. Specifically, the cloud server 200 can combine gestational age and BMI, first dividing users into different groups based on gestational age, and then further subdividing each gestational age group based on BMI. Within the same BMI subgroup, the cloud server 200 can further subdivide the user group into smaller subgroups based on the user's weight gain rate. For example, for users whose weight gain is too fast or too slow, the system will assign them to a special attention group, providing more personalized dietary advice and support, including but not limited to regularly sending reminders to the user's terminal device 100 to pay attention to dietary habits and suggesting contacting a nutritionist or doctor.

[0097] Preferably, the cloud server 200 can set a reasonable gestational age information update cycle, such as once a week or once every two weeks, and remind users to update their personal information in a timely manner through an interactive interface. Simultaneously, it allows users to manually trigger instant updates at any time, especially after experiencing significant life events or medical examinations. Furthermore, the cloud server 200 allows users to object to automatically assigned groups and provides simplified manual adjustment options. This not only enhances the user experience but also collects valuable user feedback for further optimization of the grouping algorithm.

[0098] According to one example implementation, the target user is a pregnant woman at 24 weeks of gestation with a BMI of 28.5 (obesity category) and a weight gain rate of 0.6 kg / week (exceeding the medical guideline recommended upper limit of 0.5 kg / week). The terminal device 100 worn by the target user integrates a data acquisition unit 110, which synchronizes physiological parameters including gestational age, BMI, and blood glucose data to a cloud server 200 in real time via a communication unit 120. The cloud server 200, based on the target user's gestational age, BMI, and weight gain rate, combines the aforementioned preset isoproton grouping rules (such as...) Figure 4 As shown in the figure, it is dynamically assigned to the subgroup of "22-26 weeks of gestation + obesity BMI + rapid weight gain", and the division of homogeneous subgroups is based on the population homogeneity optimization algorithm of multidimensional parameter correlation.

[0099] Cloud server 200 extracts the daily trend blood glucose curve of the target user (e.g.) Figure 8 (As shown by the red broken line in the middle), and compares it with the blood glucose data of reference users within the same proton group at each time point. Specifically, the cloud server 200 calculates the 25% to 75% percentile interval of the reference user's daily trend blood glucose data at each time point within 24 hours (e.g., ...). Figure 8 (light blue filled area) and median (e.g.) Figure 8 (Dark blue dashed line). Analysis results show that the target user's blood glucose peak was 7.2 mmol / L (8:00) during the post-breakfast period (7:00–9:00), exceeding the 75th percentile threshold (6.8 mmol / L) for the isoproton group; and 7.5 mmol / L (12:30) during the post-lunch period (12:00–14:00), exceeding the 75th percentile threshold (7.0 mmol / L). The system determined that the target user's cumulative abnormal period throughout the day was 4.5 hours, and generated a "high-risk for gestational diabetes" warning signal based on the risk characteristics of their subgroup (obesity BMI and rapid weight gain).

[0100] The cloud server 200 further analyzed the physiological parameter deviations between the target user and the reference users in the same subgroup: the target user's BMI (28.5) deviated by +2.3 standard deviations (Z-score) from the group mean (26.2), placing it at the 95th percentile of the subgroup; the weight gain (0.6 kg / week) exceeded the group median (0.35 kg / week) by 71%, and deviated from the medically recommended range (0.28–0.50 kg / week) by 20%. Furthermore, the target user's estradiol concentration (450 pg / mL) was 40% higher than the group mean (320 pg / mL), while the progesterone level (18 ng / mL) was lower than the mean (22 ng / mL). Based on the association model between hormone levels and insulin resistance, the system determined that hormonal imbalance may lead to an increased risk of insulin resistance.

[0101] Based on the above analysis results, the cloud server 200 can generate the following dynamic hierarchical health management plan for the target user:

[0102] 1. Dietary adjustments: Replace high-GI foods (such as white bread, GI=75) with low-GI alternatives (such as oatmeal, GI=55), which is expected to reduce the peak blood glucose level 1 hour after a meal by 15% to 20%; increase the proportion of non-starchy vegetables to 60% and pair them with low-GI staple foods (such as quinoa, GI=53) to slow down the rate of glucose absorption.

[0103] 2. Weight control strategy: Daily dietary calories are recorded through interactive unit 140, and a daily calorie deficit of approximately 300 kcal is created by combining low-intensity walking.

[0104] 3. Dynamic feedback mechanism: If the target user's weight gain decreases to less than 0.4 kg / week for two consecutive weeks, the system automatically relaxes the GI limit to below 65; if the target is not met, the doctor's collaborative intervention process is triggered, and an early warning notification is sent to the designated medical terminal through the communication unit 120.

[0105] Preferably, the cloud server 200 of the present invention does not simply rely on the fixed reference threshold for blood glucose levels preset in existing medical guidelines (such as the "Guidelines for the Joint Management of Gestational Diabetes Mellitus in China") to set a uniform control recommendation level for target users. Instead, the system conducts in-depth analysis of the distribution characteristics of the target user's blood glucose data in a larger overall reference dataset, and dynamically adjusts the recommendation parameters by combining reference user data that is highly similar to the target user's physiological state. Through this dynamic analysis and adjustment mechanism, individual differences can be more accurately reflected, thereby providing users with personalized dietary management recommendations. Compared with schemes based on fixed reference values, this method is more in line with the actual needs of users and helps to improve users' trust and compliance with the system's recommendations.

[0106] Furthermore, the cloud server 200 continuously optimizes the overall reference dataset through real-time analysis and dynamic updates of massive amounts of user data, ensuring that the generated control recommendations maintain high timeliness and scientific rigor. This data-driven personalized recommendation generation model, compared to traditional methods based on static medical guidelines, offers greater flexibility and adaptability. It not only reflects the latest medical research findings and clinical experience but also effectively adapts to users' dynamic health status, providing more scientific and practical management solutions and ultimately improving the overall effectiveness of health management.

[0107] Preferably, such as Figure 2As shown, after receiving blood glucose data from several reference users, the cloud server 200 sorts the reference users' blood glucose data in ascending order and then determines the percentile P of the target user's blood glucose data within its group. Simultaneously, the cloud server 200 obtains several pre-divided percentage intervals. Based on the percentage interval in which the target user's blood glucose data falls and its percentile P within its group, the server 200 obtains the correction coefficient corresponding to that interval. The cloud server 200 adjusts the original feature index FI to the corrected feature index FI′.

[0108] Example 2

[0109] This embodiment is a supplement to the foregoing embodiment, and repeated content will not be described again.

[0110] Preferably, the cloud server 200 can also use a piecewise function model to describe the characteristic index FI based on different stages of pregnancy:

[0111]

[0112] In the early pregnancy stage f1(W), a nonlinear regression model was used, focusing on the impact of hormone levels on insulin sensitivity; in the mid-pregnancy stage f2(W), a linear regression model was used, which is suitable for relatively stable trends; and in the late pregnancy stage f3(W), a nonlinear regression or logistic regression model was used, focusing on the impact of insulin resistance.

[0113] Preferably, in this embodiment, the calculation of the characteristic index FI weakens the influence of gestational age, and instead sets different calculation models for the early, middle and late stages of pregnancy, giving more consideration to changes in BMI, weight gain rate and / or hormone levels, which have a significant impact on blood glucose in gestational diabetes.

[0114] Specifically,

[0115] f1(W)=w1·(e k·G(W) -1)+w2·ln(B+1).

[0116] Exponential term e k·G(W) To represent the increased risk caused by hormonal changes, several ln(B+1) terms are used to adjust for the impact of BMI on early risk, avoiding excessively large values ​​that could lead to model instability. G(W) is a function of the rate of weight gain; k is a parameter adjusting for the rate of hormonal change; B is the BMI value; w1 and w2 are weighting coefficients. Preferably, Figure 6a An example plot shows how characteristic indices change with gestational week in early pregnancy for a specific target user.

[0117] f2(W)=w3·G(W)+w4·B+w5·H(W).

[0118] The linear terms G(W) and B primarily reflect the impact of pregnant women's weight gain and BMI on the risk of GDM. The hormone level term H(W) is kept with a low weight because hormone fluctuations are relatively stable. H(W) is a function of hormone levels (where changes are smaller). w3, w4, and w5 are weighting coefficients. Preferably, Figure 6b An example plot shows the variation of characteristic indices with gestational week during the mid-pregnancy stage, plotted for a specific target user.

[0119] f3(W) = w6·(W-28) 2 +w7·G(W)+w8·H(W).

[0120] Quadratic term (W-28) 2 The study emphasizes the increased non-linear risk during late pregnancy. The combined effect of the weight gain rate (G(W)) and hormone level (H(W)) on GDM risk is significant. w6, w7, and w8 are weighting coefficients. Preferably, Figure 6c An example plot shows how the characteristic index changes with gestational week in late pregnancy for a specific target user.

[0121] It should be noted that the specific embodiments described above are exemplary. Those skilled in the art can devise various solutions inspired by the disclosure of this invention, and these solutions all fall within the scope of this invention and its protection. Those skilled in the art should understand that this specification and its accompanying drawings are illustrative and do not constitute a limitation on the claims. The scope of protection of this invention is defined by the claims and their equivalents. This specification contains multiple inventive concepts; phrases such as "preferredly" or "according to a preferred embodiment" indicate that the corresponding paragraph discloses an independent concept. The applicant reserves the right to file divisional applications based on each inventive concept. Throughout the text, the feature introduced by "preferredly" is only an optional mode and should not be construed as mandatory. Therefore, the applicant reserves the right to abandon or delete relevant preferred features at any time.

Claims

1. A terminal device for blood glucose management during pregnancy, wherein the terminal device (100) is carried by a target user and a reference user, and the terminal device (100) interacts with a cloud server (200) via a data connection to achieve data uploading and feedback; characterized in that, The terminal device (100) collects physiological data and blood glucose data of the target user, including pregnancy data. The cloud server (200) obtains various blood glucose data of the reference user from several terminal devices (100) and forms an overall reference dataset according to the correlation with gestational week. The cloud server (200) calculates basic statistical indicators for each group in the overall reference dataset, and combines the user's blood glucose data with the specific percentile position of the distribution within its group. By comparing the user's blood glucose data with the preset healthy blood glucose range, it determines the user's current blood glucose status and generates graded dietary recommendations accordingly. The dietary recommendations optimize the target user's diet by selecting food types with different GI values. The terminal device (100) receives and visually displays personalized dietary recommendations that match the target user's blood sugar level.

2. The terminal device according to claim 1, characterized in that, The terminal device (100) sends four physiological data points of the target user—gestational age, BMI, weight gain rate, and hormone levels—to the cloud server (200). The cloud server (200) substitutes the four into the built-in computing model to initially calculate the feature index.

3. The terminal device according to claim 1 or 2, characterized in that, The cloud server (200) calculates the characteristic index (FI) using the following formula: In the formula, B is the body mass index (BMI), W is the gestational age, G is the rate of weight gain, H is the hormone level, w1, w2, w3, and w4 are all weighting coefficients, K is the exponential constant of the rate of weight gain, and Z is the standardization factor.

4. The terminal device according to any one of claims 1 to 3, characterized in that, When the user uploads the test report to the terminal device (100), the terminal device (100) collects hormone level data through OCR or manual input by the user; For users who upload their weight data infrequently, the cloud server (200) sets up a reminder mechanism to prompt users to upload their physiological data regularly through the terminal device (100) to ensure the accuracy of the assessment results; The current date of the gestational age data is automatically obtained from the system time of the target user's terminal device (100) to ensure the time is real-time and accurate.

5. The terminal device according to any one of claims 1 to 4, characterized in that, After calculating the characteristic index of the target user, the cloud server (200) incorporates the characteristic index into a pre-determined range of characteristic index values ​​corresponding to the characteristic index. Within the same characteristic index value range, the cloud server (200) further subdivides the reference user into multiple pregnancy groups based on gestational age; After assigning the pregnancy groups, the cloud server (200) performs a detailed comparative analysis of the target user's blood glucose data with the blood glucose data of the reference users in the same pregnancy group to identify the target user's blood glucose fluctuation patterns and potential abnormalities.

6. The terminal device according to any one of claims 1 to 5, characterized in that, The cloud server (200) is configured to divide users into different groups based on gestational age. Within each gestational age group, multiple BMI ranges are set so that users can be subdivided into multiple BMI subgroups. Within the same BMI subgroup, the cloud server (200) can further subdivide users based on their weight gain rate to identify users who gain weight too quickly or too slowly and assign them to a special attention group.

7. The terminal device according to any one of claims 1 to 6, characterized in that, The cloud server (200) groups the acquired overall reference dataset based on similar gestational weeks. The cloud server (200) adjusts the time window range of similar gestational weeks according to the user's stage of pregnancy: for the mid-pregnancy stage, the time window is wider than that for the early and late pregnancy stages.

8. The terminal device according to any one of claims 1 to 7, characterized in that, The cloud server (200) can calculate the percentile of the target user's relative position in the daily trend blood glucose data based on the target user's daily trend blood glucose data in their respective pregnancy group, and identify the target user's blood glucose fluctuation patterns and potential abnormalities by comparing and analyzing the blood glucose data with that of the reference user.

9. A cloud server for blood glucose management during pregnancy, wherein the cloud server (200) interacts with terminal devices (100) carried by a target user and a reference user via a data connection to realize data uploading and feedback; Its features are, The cloud server (200) is configured to: obtain physiological data and blood glucose data of the target user, including pregnancy, from the terminal device (100), and obtain various blood glucose data of the reference user from several terminal devices (100) and form an overall reference dataset in a manner associated with gestational week; For each group in the overall reference dataset, basic statistical indicators are calculated. Combined with the specific percentile position of the user's blood glucose data in its group, the user's current blood glucose status is determined by comparing the user's blood glucose data with the preset healthy blood glucose range. Based on this, graded dietary recommendations are generated. The dietary recommendations optimize the target user's diet by selecting food types with different GI values. Thus, the terminal device (100) receives and intuitively displays personalized dietary recommendations that match the target user's blood glucose status.

10. The cloud server according to claim 9, characterized in that, The cloud server (200) calculates the characteristic index (FI) using the following formula: In the formula, B is the body mass index (BMI), W is the gestational age, G is the rate of weight gain, H is the hormone level, w1, w2, w3, and w4 are all weighting coefficients, K is the exponential constant of the rate of weight gain, and Z is the standardization factor. After calculating the characteristic index of the target user, the cloud server (200) incorporates the characteristic index into a pre-determined range of characteristic index values ​​corresponding to the characteristic index; Within the same characteristic index value range, the cloud server further subdivides the reference users into multiple pregnancy groups based on gestational age; After assigning the pregnancy groups, the cloud server (200) performs a detailed comparative analysis of the target user's blood glucose data with the blood glucose data of the reference users in the same pregnancy group to identify the target user's blood glucose fluctuation patterns and potential abnormalities.

Images