Personalized dynamic blood glucose data processing method and system

Abstract

The invention relates to the technical field of blood glucose health data management, in particular to a personalized dynamic blood glucose data processing method and system, and the method comprises the steps: obtaining an effective event and a stage interval corresponding to the effective event; adding a processing task for the effective event based on the stage interval where the effective event is located; performing point processing and / or surface processing on the blood glucose data contained in the effective event based on the processing task; obtaining pre-training information and test information based on a processing result of the point processing and / or the surface processing and the stage interval, and generating a diet improvement scheme based on the pre-training information and the test information; experience information and post-training information are obtained in the corresponding stage intervals based on the diet improvement scheme and the processing result of the point processing and / or the face processing; and generating a personalized blood glucose data report according to a plurality of data acquired in different stage intervals. The method has the effect of accurately analyzing and improving the personalized living habits of the user through 24-hour dynamic blood glucose data monitoring.

Description

Technical Field

[0001] The present application relates to the technical field of blood glucose health data management, and in particular to a method and system for processing personalized dynamic blood glucose data. Background Art

[0002] Continuous blood glucose monitoring helps control blood sugar. It can provide comprehensive and continuous blood sugar information, help optimize treatment plans, timely detect and deal with abnormal blood sugar, reduce the risk of complications, and improve the quality of life of patients by reducing the number of needle sticks, improving the accuracy and convenience of monitoring. Continuous blood glucose monitoring enables patients to manage their blood sugar more easily. At the same time, personalized treatment plans and diet plans also help patients maintain a healthy lifestyle and improve their long-term quality of life.

[0003] Currently, there are many blood glucose monitoring devices such as bracelets and watches that can detect the blood glucose value of the human body. These devices often monitor blood glucose through non-invasive technologies (such as optical sensing, electrochemical sensing, data modeling, etc.). However, compared with dynamic blood glucose monitoring technology, these technologies have certain errors and cannot process blood glucose data to further evaluate and analyze each user's eating habits, lifestyle, etc., resulting in users only being able to constantly check a single value to determine whether they are currently in a state of high or low blood glucose, and cannot obtain personalized dietary recommendations and dietary analysis content after in-depth analysis of their overall blood glucose status. At the same time, they cannot process the 24-hour dynamic fluctuations of blood glucose and all-weather blood glucose monitoring and warning, and the blood glucose monitoring effect is single. Summary of the invention

[0004] In order to achieve accurate analysis and improvement of users' personalized living habits through 24-hour dynamic blood glucose data monitoring, the present application provides a personalized dynamic blood glucose data processing method and system.

[0005] In a first aspect, the present application provides a method for processing personalized dynamic blood glucose data, which adopts the following technical solution: A method for processing personalized dynamic blood glucose data, comprising the following steps: Acquire a valid event and a phase interval corresponding to the valid event, wherein the valid event is characterized by the collection of valid blood glucose data; Adding a processing task for the valid event based on the phase interval where the valid event is located; Based on the processing task, point processing and / or surface processing is performed on the blood glucose data contained in the valid event, wherein the point processing is characterized by independently processing the numerical points of the blood glucose data, and the surface processing is characterized by integrating multiple data points of the blood glucose data and processing them in combination with a preset reference line; Obtaining pre-training information and test information based on the processing results of the point processing and / or the surface processing and the stage interval, and generating a dietary improvement plan based on the pre-training information and the test information; Based on the dietary improvement plan and the processing results of the point processing and / or the surface processing, experience information and post-training information are obtained in the corresponding stage interval; A personalized and accurate lifestyle assessment report is generated based on the data obtained in the different stage intervals.

[0006] In some of the embodiments, obtaining a valid event includes the following steps: Setting a valid event time range and generating corresponding condition checks, the condition checks corresponding to a first condition check for a short time check and a second condition check for a long time check; Acquire a data set including event time and corresponding blood glucose data, taking the collected initial event point as a starting point; adding the first condition check at the starting point to determine whether there is valid blood glucose data within the valid event time range corresponding to the first condition check; adding the second condition check at the starting point to determine whether there is valid blood glucose data within the valid event time range corresponding to the second condition check; If the data set satisfies both the first condition check and the second condition check, the data set is considered to be the valid event.

[0007] In some of the embodiments, obtaining the phase interval corresponding to the valid event includes the following steps: Obtaining the total blood sugar improvement time, and dividing the total blood sugar improvement time into phase intervals of corresponding time lengths based on the time division requirements, wherein the phase intervals include a daily behavior collection phase before training, a blood sugar test phase, an intervention experience phase, and a self-monitoring phase after training; The current time corresponding to the starting point is obtained, and the current time is compared with the time lengths corresponding to the respective stage intervals to determine the stage interval in which the effective time is located.

[0008] In some embodiments, adding a processing task for the valid event based on the phase interval where the valid event is located includes the following steps: In the daily behavior collection stage before training, the processing tasks include obtaining the proportion of three major energy-producing substances, blood sugar fluctuations, dynamic blood sugar graphs, post-meal blood sugar peaks, and average blood sugar levels before and after meals; In the blood glucose testing phase, the processing tasks include obtaining a personalized blood glucose index; In the intervention experience stage, the processing tasks include blood sugar fluctuations after the dietary improvement program, dynamic blood sugar graphs, post-meal blood sugar peaks, and average blood sugar levels before and after meals; In the post-training self-monitoring stage, the processing tasks include obtaining blood sugar fluctuations, dynamic blood sugar graphs, post-meal blood sugar peaks, average blood sugar levels before and after meals, and comparing the corresponding results of the processing tasks in the pre-training daily behavior collection stage.

[0009] In some embodiments, performing point processing and / or surface processing on the blood glucose data contained in the valid event based on the processing task includes the following steps: When performing the point processing, the highest value of each blood glucose data in the valid event is obtained to obtain the post-meal blood glucose peak value, the average value of each blood glucose data in the valid event is calculated to obtain the pre- and post-meal blood glucose average value, the blood glucose fluctuation is obtained based on the change of each blood glucose data in the valid event, and the dynamic blood glucose map is drawn; When performing the surface processing, a reference instruction is generated and a personal standard blood sugar response obtained in response to the reference instruction is obtained, a test instruction is obtained and a specified food intake amount is generated in response to the acquisition instruction, a standard food test blood sugar response matching the specified food intake amount is obtained, and the personalized glycemic index is calculated based on the personal standard blood sugar response and the standard food test blood sugar response.

[0010] In some embodiments, calculating the personalized glycemic index based on the standard blood glucose response and the standard food test blood glucose response comprises the following steps: generating a reference instruction of drinking 50 g of glucose, and screening out personal standard events that respond to the reference instruction from the valid events; Draw a personal standard blood sugar change curve based on each of the blood sugar data in the personal standard event and the corresponding event time, and define a personal standard blood sugar response based on the personal standard blood sugar change curve; After obtaining the test instruction, determining the test food type in the test instruction, and generating a standard intake amount of the corresponding type of food based on the test food type; monitoring blood sugar changes after the test instruction, and screening out test events from the valid events after blood sugar changes occur; Draw a test blood glucose change curve based on each of the blood glucose data in the test event and the corresponding event time, and define a standard food test blood glucose response based on the test blood glucose change curve; calculating the area between the individual's standard blood glucose response and the standard food test blood glucose response to obtain a personalized glycemic index for the standard test food; The personalized glycemic index is calculated based on the following formula: PGI = (standard food test blood sugar response / personal standard blood sugar response) * 100%.

[0011] In some of the embodiments, when screening the personal standard events and the test events, the following steps are also included: Determine whether the personal standard event or the test event is abnormal, wherein the abnormality includes abnormal meal time and abnormal event quantity; If there is an abnormality, analyzing the credibility of the personal standard event or the test event based on the event time and the response event, and the trend of the blood glucose data; A time adjustment process or an optimal event selection process is performed based on the reliability.

[0012] In some embodiments, obtaining pre-training information and test information based on the processing results of the point processing and / or the surface processing and the stage interval, and generating a dietary improvement plan based on the pre-training information and the test information include the following steps: In the daily behavior collection stage before training, the corresponding lifestyle assessment results are obtained based on the diet registration corresponding to the user's own diet habits, and the lifestyle assessment results and the blood sugar data are integrated into the pre-training information, and the lifestyle assessment results include single types of food and food combinations corresponding to the high blood sugar impact; In the blood sugar test phase, high and low PGI foods are obtained based on the diet registration corresponding to each of the test events, and the high and low PGI foods and their corresponding glycemic indexes are integrated into the test information; High blood sugar fluctuation foods and / or high blood sugar fluctuation food combinations are screened based on the pre-training information and the test information, and dietary improvement suggestions and dietary recommendation suggestions are generated based on the high blood sugar fluctuation foods and / or the high blood sugar fluctuation food combinations.

[0013] In some embodiments, obtaining experience information and post-training information in the corresponding stage interval based on the dietary improvement plan and the processing results of the point treatment and / or the surface treatment includes the following steps: In the intervention experience stage, the diet registration uploaded by the user is collected and it is determined whether it meets the diet improvement plan; If satisfied, obtaining the experience result based on the diet registration, comparing the blood glucose data corresponding to the experience result with the blood glucose data in the pre-training daily behavior collection phase to obtain a first comparison result, and integrating the experience result, the blood glucose data and the first comparison result into an experience value; If not, the valid event corresponding to the dietary registration will not be counted in the generation of the experience result; In the post-training self-monitoring stage, the post-training result is obtained based on the diet registration, the blood glucose data corresponding to the post-training result is obtained and compared with the blood glucose data in the pre-training daily behavior collection stage to obtain a second comparison result, and the difference between the current diet registration and the dietary improvement plan is found based on the negative data in the second comparison result, and the post-training information is generated based on the post-training result, the blood glucose data, the second comparison result and the difference.

[0014] In a second aspect, the present application provides a personalized dynamic blood glucose data processing system, which adopts the following technical solution: A personalized dynamic blood glucose data processing system, comprising: Dynamic blood glucose monitoring equipment, used to monitor and obtain continuous blood glucose data; An effective event acquisition module, used to acquire effective events and phase intervals corresponding to the effective events, wherein the effective events are characterized by the collection of effective blood glucose data; A processing task generating module, used for adding a processing task to the valid event based on the phase interval where the valid event is located; a blood glucose data processing module, configured to perform point processing and / or surface processing on the blood glucose data contained in the valid event based on the processing task, wherein the point processing is characterized by independently processing the numerical points of the blood glucose data, and the surface processing is characterized by integrating a plurality of data points of the blood glucose data and processing them in combination with a preset reference line; A front-end data acquisition and analysis module, used for obtaining pre-training information and test information based on the processing results of the point processing and / or the surface processing and the stage interval; A dietary plan generating module, used for generating a dietary improvement plan based on the pre-training information and the test information; A post-stage data collection and analysis module, for obtaining experience information and post-training information in the corresponding stage interval based on the dietary improvement plan and the processing results of the point processing and / or the surface processing; The personalized and accurate lifestyle assessment report generation module is used to generate a personalized and accurate lifestyle assessment report based on a number of blood sugar data obtained in different stage intervals.

[0015] The technical solution provided by the embodiments of the present application has the following technical effects: The conventional blood sugar test in the current technology is converted into a phased personal lifestyle test and adjustment based on blood sugar data. The blood sugar fluctuation content corresponding to the previous living habits and the eating habits content are collected through the collection of blood sugar data at different stages. According to the specific blood sugar processing results, a personalized dietary improvement plan for the patient is generated, and the patient is guided to adjust his personal lifestyle through the dietary improvement plan. The blood sugar improvement effect of the dietary improvement plan is judged through continuous detection and analysis of blood sugar fluctuations, and the difference in blood sugar data before and after the dietary improvement is reflected, so as to realize the visualization of the patient's lifestyle changes and generate a personalized and accurate lifestyle assessment report, so that the patient can intuitively understand the blood sugar improvement before and after the change of living habits, as well as the changes in blood sugar fluctuations caused by eating different foods. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flowchart of the steps of a method for processing personalized dynamic blood glucose data provided in this embodiment.

[0017] Figure 2 This is a module connection diagram of a personalized dynamic blood glucose data processing system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0018] To more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. However, it should be understood by those of ordinary skill in the art that the present application can be implemented without these details. In some cases, in order to avoid unnecessary descriptions that make various aspects of the present application obscure, well-known methods, processes, systems, components and / or circuits that have been described at a higher level will not be described in detail. For those of ordinary skill in the art, it is obvious that various changes can be made to the embodiments disclosed in the present application, and without departing from the principles and scope of the present application, the general principles defined in the present application can be applied to other embodiments and application scenarios. Therefore, the present application is not limited to the embodiments shown, but conforms to the broadest scope consistent with the scope claimed for protection of the present application.

[0019] It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention. In addition, the technical features involved in each embodiment of the present invention described below can be combined with each other as long as there is no conflict between them.

[0020] In the description of this application, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed", etc. are understood to exclude the number itself, and "above", "below", "within", etc. are understood to include the number itself. If there is a description of "first" or "second", it is only used to distinguish the technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0021] In the description of the present application, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples.

[0022] The embodiment of the present application discloses a method for processing personalized dynamic blood glucose data.

[0023] like Figure 1 As shown, a method for processing personalized dynamic blood glucose data includes the following steps: S100, obtaining valid events and phase intervals corresponding to the valid events.

[0024] In the present application, dynamic blood glucose data monitoring and dietary assessment are divided into several stages, each stage corresponds to a stage interval of the same or different time length, and each stage corresponds to different blood glucose data processing and dietary test action plans.

[0025] A valid event is characterized by the collection of valid blood sugar data. In this application, an event refers to a data change scenario corresponding to a behavior that will cause a certain degree of change in blood sugar data. In the embodiment of this application, an event mainly refers to eating.

[0026] Among them, events are divided into valid events and invalid events. When accurately analyzing blood sugar data, it is necessary to meet the requirements of the change behavior of blood sugar data matching the preset human behavior, such as breakfast, lunch and dinner, and some blood sugar data changes that do not meet the detection time requirements or are not caused by eating are defined as invalid events.

[0027] S200, adding a processing task for the valid event based on the phase interval where the valid event is located.

[0028] When a valid event occurs, it is considered that blood sugar fluctuations caused by the specified eating behavior have occurred. At this time, it is necessary to determine the stage interval in which the eating behavior is located, and generate and add different processing tasks based on the different detection needs of the stage interval. Different processing tasks differ in the way blood sugar data is processed, the content obtained after processing, the type of eating, etc.

[0029] S300: performing point processing and / or surface processing on the blood glucose data included in the valid event based on the processing task.

[0030] Point processing is characterized by independently processing the numerical points of blood glucose data, and surface processing is characterized by integrating multiple data points of blood glucose data and processing them based on preset reference lines.

[0031] Specifically, point processing refers to processing a single point when blood sugar data fluctuates, such as processing a single point of a section of blood sugar fluctuation data to obtain a processing result, or processing the result after processing multiple single points in the blood sugar fluctuation, such as obtaining the highest blood sugar, the average blood sugar, the lowest blood sugar, etc. through blood sugar data.

[0032] Surface processing means integrating all points when blood sugar fluctuates to integrate multiple points into a curve, combining the blood sugar curve and other reference lines to obtain a closed surface, and performing corresponding processing on the closed surface to obtain a processing result.

[0033] Through point processing and surface processing, a variety of processing methods for the detected blood sugar data can be obtained to obtain several different types of processing results reflecting different blood sugar responses.

[0034] S400, obtaining pre-training information and test information based on the processing results of the point processing and / or the surface processing and the stage interval, and generating a dietary improvement plan based on the pre-training information and the test information.

[0035] According to the stage interval where the detected effective event is located, the blood glucose status in the stage interval can be obtained by combining the processing results of point processing and / or surface processing. The obtained analysis results are defined as pre-training information and test information.

[0036] A dietary improvement plan is inferred and generated through these two information. The dietary improvement plan is characterized as a plan that is beneficial to improving one's own blood sugar by changing the dietary structure based on the analysis of previous blood sugar results.

[0037] Taking this plan as a node, the stage interval before generating the dietary improvement plan is considered to be the detection and summary of the patient's own personal living habits, and the stage interval after generating the dietary improvement plan is considered to be the health changes monitored and analyzed after the patient changes his or her personal eating habits through the dietary improvement plan.

[0038] S500, obtaining experience information and post-training information in a corresponding stage interval based on the dietary improvement plan and the processing results of the point processing and / or the surface processing.

[0039] After the patient changes his or her personal lifestyle habits through the dietary improvement program, the blood sugar data detected after the improved lifestyle is analyzed again through point processing and / or surface processing to obtain experience information and post-training information.

[0040] S600 generates a personalized and accurate lifestyle report based on a number of blood sugar data obtained in different stage intervals.

[0041] According to the blood sugar data obtained in different stage intervals and the different processing results after different processing of the blood sugar data, personalized blood sugar data reports for different patients are obtained, which include the blood sugar data fluctuation content corresponding to different effective events and the processing results obtained after processing the blood sugar data.

[0042] Through the above steps, the conventional blood sugar value detection in the current technology is converted into a phased personal lifestyle test and adjustment based on blood sugar data. The blood sugar fluctuation content corresponding to the previous living habits and the collection of eating habits are realized through the collection of blood sugar data at different stages. According to the specific blood sugar processing results, a personalized dietary improvement plan for the patient is generated, and the patient is guided to adjust his personal lifestyle through the dietary improvement plan. The blood sugar improvement effect of the dietary improvement plan is judged through continuous detection and analysis of blood sugar fluctuations, and the difference in blood sugar data before and after the dietary improvement is reflected, so as to realize the visualization of the patient's lifestyle change, and generate a personalized and accurate lifestyle assessment report, so that the patient can intuitively understand the blood sugar improvement before and after the change of living habits, as well as the changes in blood sugar fluctuations caused by eating different foods.

[0043] In some other embodiments, obtaining a valid event includes the following steps: S110, setting a valid event time range and generating corresponding conditional checks, the conditional checks corresponding to a first conditional check for a short-time check and a second conditional check for a long-time check.

[0044] The conditional check is based on blood sugar response and the duration of a blood sugar fluctuation is used as the judgment standard.

[0045] When screening valid events, it is mainly based on the effective collection time of blood glucose data. The continuous collection time of valid blood glucose data and the retention time of blood glucose data both play a role in determining whether the blood glucose data is valid.

[0046] Therefore, we first set the effective event time range, which represents the event range regulations that need to be met after the event is detected to be considered a valid event. Based on this regulation, we generate two conditional inspection contents with different judgment time lengths, and use these two conditional inspections to check and judge the detected blood glucose data.

[0047] The inspection time range corresponding to the first condition inspection is smaller than the inspection time range corresponding to the second condition inspection.

[0048] S111, obtaining a data set including event time and corresponding blood glucose data, with the collected initial event point as the starting point.

[0049] The event time is characterized by the corresponding collection event after each blood glucose data is collected. The collection of blood glucose data is generally performed at a certain preset interval, such as collecting blood glucose every 5 minutes.

[0050] A data set within a certain time range is obtained. The data set is generally generated with the time point of the blood sugar data at which a drastic change in blood sugar occurs as the starting point, and the event corresponding to the time point is defined as the starting point.

[0051] S112, adding a first condition check at the starting point to determine whether there is valid blood glucose data within the valid event time range corresponding to the first condition check.

[0052] First, the data set is checked based on the first condition check. The duration of the first condition check in the embodiment of the present application is 10 minutes. That is, only when there is valid blood sugar data for 10 consecutive minutes after the starting point, the starting point corresponds to a valid time point, and subsequent blood sugar data can be used as a valid event.

[0053] The first condition check is mainly used to detect whether the time for continuous event collection meets the requirements. When behaviors such as just waking up, abnormal detection, and sudden standing after sitting for a long time occur, the blood sugar data will show abnormal changes, but generally the blood sugar will return to normal within a few minutes. Such behaviors do not belong to valid events in the embodiments of the present application. Therefore, in order to remove the abnormal effects of such behaviors on blood sugar detection, such events can be screened and removed through the first condition check.

[0054] S113, adding a second condition check at the starting point to determine whether there is valid blood glucose data within the valid event time range corresponding to the second condition check.

[0055] After passing the first condition check, the data set is subjected to a second condition check. The duration of the second condition check is 4 hours in the embodiment of the present application, that is, only when valid blood sugar fluctuation data can be collected within 4 hours after the starting point, the event is considered a valid event, and valid blood sugar data less than 4 hours after the event cannot be counted as a valid event. 4 hours refers to the time range of blood sugar fluctuations caused by a meal, and less than 4 hours is generally not considered to be a blood sugar fluctuation caused by eating behavior, such as eating twice in a row within 4 hours, or eating continuously within 4 hours.

[0056] S114: If the data set satisfies both the first condition check and the second condition check, the data set is considered to be a valid event.

[0057] In some other embodiments, obtaining the phase interval corresponding to the valid event includes the following steps: S120, obtaining the total blood sugar improvement time, and dividing the total blood sugar improvement time into stage intervals of corresponding time lengths based on the time division requirement.

[0058] The total blood sugar improvement time is characterized by the total time of an overall lifestyle improvement task for the patient, which is 14 days in the embodiment of the present application. Among them, these 14 days are divided into different stage intervals based on different blood sugar analysis contents and processing methods.

[0059] The phase intervals include the daily behavior collection phase before training, the blood glucose testing phase, the intervention experience phase, and the self-monitoring phase after training.

[0060] The daily behavior collection stage before training is characterized by patients eating according to their past or usual lifestyle and recording blood sugar data corresponding to their daily diet.

[0061] The blood sugar testing phase is characterized by calculating the glycemic index of some foods by comparing the blood sugar response after eating prescribed standard foods and combining them with the test foods selected by the patient.

[0062] The above two stages mainly involve blood sugar analysis of the patient's daily behavior and diet before a dietary improvement plan is proposed, which serves as the basis for the subsequent generation and push of a dietary improvement plan.

[0063] The intervention experience stage is characterized by the patients adjusting their diet according to the content of the dietary improvement plan after receiving it, and experiencing the impact of the new dietary adjustment on blood sugar response.

[0064] The post-training self-monitoring stage is characterized by the patient's self-arranging of meals based on the blood sugar data corresponding to the diet of the previous few days after adjusting the diet through the dietary improvement plan, and dynamically adjusting the content of the dietary improvement plan according to the blood sugar response, and monitoring the blood sugar data of this stage again to achieve the purpose of dynamic adjustment and monitoring.

[0065] The above two stages mainly involve the generation of a dietary improvement plan, in which the patient adjusts his or her diet according to the recommended dietary content, and arranges his or her own meals and generates new blood sugar analysis results based on the test experience and changes in blood sugar data over a certain period of time. This allows the patient to clearly see the improvements in blood sugar health brought about by changes in lifestyle.

[0066] Specifically, in the embodiment of the present application, the daily behavior collection stage before training is 1-3 days, the blood glucose testing stage is 4-7 days, the intervention experience stage is 8-10 days, and the self-monitoring stage after training is 11-14 days. According to the specific circumstances of different patients, the total number of days and the number of days for each stage can be appropriately modified.

[0067] In other embodiments, in order to improve the accuracy of the entire blood glucose analysis, a preparation day is set before the first day. During the preparation day, the patient needs to wear a dynamic blood glucose monitoring device as required, download the corresponding app, and complete a basic questionnaire. In the basic questionnaire, the patient can enter his or her basic information, health information, disease information, usual diet information, stress information, etc.

[0068] S121, obtaining the current time corresponding to the starting point, and comparing the current time with the time lengths corresponding to each stage interval to determine the stage interval in which the valid event is located.

[0069] After each stage interval is divided, the corresponding time points at both ends of the interval are obtained through the corresponding days and the current time when the task starts.

[0070] After obtaining the valid event, determine the current time corresponding to the starting point of the valid event, and determine the phase interval in which the valid event is located based on the time interval of the phase interval in which the current time is located.

[0071] In some other embodiments, adding a processing task for a valid event based on the phase interval in which the valid event is located includes the following steps: S210, during the daily behavior collection phase before training, the processing tasks include obtaining the proportion of the three major energy-producing substances, blood sugar fluctuations, dynamic blood sugar maps, post-meal blood sugar peaks, and average blood sugar levels before and after meals.

[0072] In the stage of daily behavior collection before training, the specific contents that need to be analyzed through blood glucose data are: The proportion of the three major energy-producing substances is obtained through the information uploaded by the patient every time he eats, and the food and food weight corresponding to the meal are obtained. Based on the food library resources connected to the port, the amount of protein, carbohydrates, and fat corresponding to each food is obtained and the ratio of the three major energy-producing substances is calculated.

[0073] Blood sugar fluctuations are characterized by changes in blood sugar data within a preset time, such as a day. The blood sugar values ​​collected every 5 minutes are used to draw a corresponding blood sugar graph. The horizontal axis of the blood sugar graph is time, and the vertical axis is the blood sugar value. The blood sugar fluctuations are determined by the curve in the blood sugar graph.

[0074] The dynamic blood glucose map reflects the overall distribution of blood glucose values ​​during the monitoring period. A dynamic blood glucose map is drawn for each patient based on the blood glucose values ​​collected each time to display the continuous blood glucose test data. It includes the median glucose curve, the glucose range of 50% of the time at any time point, and the glucose range of 90% of the time.

[0075] Postprandial blood glucose peak is characterized by the highest blood glucose value in the effective event corresponding to each meal.

[0076] The average blood sugar level before and after a meal is represented by the average blood sugar level within a certain period of time before and after the effective event corresponding to the meal.

[0077] It is also possible to analyze data such as the overall blood sugar response and blood sugar fluctuation range (PPGE) corresponding to each effective event.

[0078] At the same time, you can also set preset values ​​for high and low blood sugar, collect the start, end and maintenance time of all high and low blood sugar times, calculate the number of high and low blood sugar times per day, draw icons showing changes in blood sugar levels over time, represented by red lines and shadows, and process detailed information and summary results of high and low blood sugar times.

[0079] It should be noted that before processing blood glucose data, it is necessary to convert the units of blood glucose data and add the definition and calculation method of fasting blood glucose.

[0080] S220, in the blood glucose testing phase, the processing task includes obtaining a personalized blood glucose index.

[0081] The personalized glycemic index represents the specific blood sugar impact of different foods on different patients.

[0082] S230, in the intervention experience stage, the processing tasks include blood sugar fluctuations after the dietary improvement plan, dynamic blood sugar graphs, post-meal blood sugar peaks, and average blood sugar levels before and after meals.

[0083] The treatment of blood sugar in the intervention experience phase is the same as that in the daily behavior collection phase before training, but the difference is that the blood sugar data needs to be data corresponding to the food or food combination that matches the dietary improvement plan.

[0084] Every time they eat, patients need to upload the type and weight of food they eat. At this stage, only the uploaded food is considered a valid event if it matches the dietary improvement plan.

[0085] S240, in the post-training self-monitoring stage, the processing tasks include obtaining blood sugar fluctuations, dynamic blood sugar graphs, post-meal blood sugar peaks, pre- and post-meal blood sugar averages, and comparisons with the corresponding results of the processing tasks in the pre-training daily behavior collection stage.

[0086] In this stage, the processing method of blood sugar data is the same as that in the intervention experience stage, but there is one more item: the data collected in this stage needs to be compared with the data collected in the daily behavior collection stage before training, and the comparison content is obtained, such as the comparison results of the average blood sugar before and after each meal, the comparison results of the peak blood sugar after each meal, etc., to make patients clearly aware of the changes in their blood sugar after implementing the above-mentioned dietary improvement plan.

[0087] In some other embodiments, point processing and / or surface processing is performed on the blood glucose data contained in the valid event based on the processing task, including the following steps: S310, when performing point processing, obtain the highest value of each blood glucose data in the valid event to obtain the postprandial blood glucose peak value, calculate the average value of each blood glucose data in the valid event and the average value of the blood glucose data in the preset time period before the starting point corresponding to the valid event to obtain the average blood glucose value before and after the meal, and draw a dynamic blood glucose graph based on the blood glucose fluctuation situation obtained based on the changes in each blood glucose data in the valid event.

[0088] When performing point processing, corresponding processing is performed based on the different blood glucose data points of each valid event, such as obtaining the highest blood glucose value, calculating the average blood glucose value through multiple points, and drawing various blood glucose images based on each blood glucose data point.

[0089] S320, when performing surface processing, generates a reference instruction and obtains a personal standard blood sugar response obtained in response to the reference instruction, obtains a test instruction and obtains an instruction to specify a food intake amount, obtains a standard food test blood sugar response that matches the specified food intake amount, and calculates a personalized glycemic index based on the personal standard blood sugar response and the standard food test blood sugar response.

[0090] When performing face processing, it is necessary to connect the various blood glucose value points to obtain a blood glucose curve, which represents the patient's personal standard food test blood glucose response corresponding to a certain food.

[0091] At the same time, by referring to the instructions, the patient is asked to eat a standard base of reference food before testing each food to obtain the patient's own corresponding personal standard blood sugar parameter line, and the personal standard blood sugar parameter line serves as the standard blood sugar benchmark corresponding to the patient himself.

[0092] A closed surface is obtained by the line corresponding to the individual's standard blood sugar response and the curve corresponding to the individual's standard food test blood sugar response, and the personalized glycemic index corresponding to different patients is calculated based on the closed surface.

[0093] In other embodiments, calculating a personalized glycemic index based on a standard blood glucose response and a standard food test blood glucose response comprises the following steps: S330, generating a reference instruction of drinking 50 g of glucose, and screening out personal standard events that respond to the reference instruction from valid events.

[0094] During the blood sugar testing phase, you first need to drink 50g of glucose before calculating the personalized glycemic index of each standard food, and filter out the personal standard events corresponding to this behavior from the valid events.

[0095] S331, drawing a personal standard blood sugar change curve based on each blood sugar data in the personal standard event and its corresponding event time, and defining a personal standard blood sugar response based on the personal standard blood sugar change curve.

[0096] The line segment corresponding to the blood sugar change after drinking 50g of glucose serves as the patient's own blood sugar level benchmark. Due to different basal metabolism of the body, different disease patients, different ages, etc., the blood sugar increase impact benchmark caused by the same food is also different. Therefore, before each patient enters the blood sugar testing stage, the corresponding blood sugar impact basis of different patients is obtained by having them drink 50g of standard amount of glucose.

[0097] Among them, the event time is selected as two hours, and the personal standard blood sugar change curve is drawn according to the blood sugar value detected two hours after drinking glucose.

[0098] The corresponding value is calculated based on the area between the personal standard blood sugar change curve and the fasting blood sugar reference line and used as the personal standard blood sugar response.

[0099] S332, after obtaining the test instruction, determine the test food type in the test instruction, and generate a standard intake amount of the corresponding type of food based on the test food type.

[0100] The patient chooses the food he wants to test and selects the corresponding food type in the system. The system generates a standard food intake of 50g of carbohydrates based on the selected test food type.

[0101] S333, monitor the blood sugar changes after the test instruction, and screen out the test events from the valid events after the blood sugar changes occur.

[0102] The patient eats the food according to the standard intake amount and tests the blood sugar data at the same time. When the blood sugar data changes, it is considered that the test phase has started, and the blood sugar data within two hours after the starting point is regarded as the test event.

[0103] S334, drawing a test blood glucose change curve based on each blood glucose data in the test event and its corresponding event time, and defining a standard food test blood glucose response based on the test blood glucose change curve.

[0104] The test blood glucose change curve is drawn through the test events, which is used to characterize the blood glucose changes that occur in patients within two hours after eating a certain test food. At the same time, the test blood glucose response of the standard food is calculated based on the area between the test blood glucose change curve and the fasting blood glucose reference line.

[0105] S335 , calculating the area between the individual's standard blood sugar response and the standard food test blood sugar response to obtain a personalized glycemic index (PGI) of the standard test food.

[0106] S336, calculating the personalized glycemic index based on the following formula: PGI = (standard food test blood sugar response / personal standard blood sugar response) * 100%.

[0107] In current technology, there is a concept of GI value for food. GI is also called glycemic index, which is represented by the ratio of the blood sugar-raising effect of a certain food to the blood sugar-raising effect of a standard food (usually glucose). It represents the degree of blood sugar response caused by the human body after eating a certain amount of food.

[0108] However, the current calculation of the GI value of human food all uses the universal standard GI value calculated through big data. It is generally the average GI value obtained by a large number of testers. However, due to the differences among individual patients, some patients have a smaller impact on their blood sugar after eating noodles, which may be 40, while some patients have a greater impact on the change in blood sugar after eating noodles, which may be 60. Therefore, the standardized and popular GI standard cannot accurately detect and guide the improvement of patients' personalized lifestyles.

[0109] Therefore, the concept of personalized glycemic index (PGI) is proposed in this application. Before calculating the glycemic index of food for each patient, the user is first asked to drink 50g of glucose to obtain and determine the patient's standard blood sugar response basis, and then different foods are tested. In this way, the personalized glycemic index of different foods for different individual patients can be accurately calculated. Improve the pertinence and accuracy of subsequent dietary screening and personalized report generation.

[0110] In some other embodiments, when screening personal standard events and test events, the following steps are also included: S340, determining whether there is an abnormality in the personal standard event or the test event.

[0111] Abnormalities include abnormal meal times and abnormal number of events.

[0112] Abnormal meal times are mainly characterized by a mismatch between the meal time registered by the user and the start time of blood sugar fluctuations detected by the wearable blood sugar monitoring device.

[0113] The abnormal number of events is characterized by the detection of multiple glucose data, that is, multiple personal standard blood glucose change curves.

[0114] S341, if there is an abnormality, the credibility of the personal standard event or test event is analyzed based on the event time and the response event and the trend of the blood glucose data.

[0115] If abnormal data is detected, a comprehensive comparison is made based on the event time corresponding to the pre-meal blood sugar, maximum post-meal blood sugar, 2-hour post-meal blood sugar, blood sugar fluctuation events, and the meal time uploaded by the user to analyze the credibility of the corresponding personal standard time or test time.

[0116] S342, performing event adjustment processing or optimal event selection processing based on credibility.

[0117] The data with the highest credibility is selected as the correct data, and the user's meal time is adjusted based on the credibility, or the glucose data with the highest credibility is selected as the correct data to draw a personal standard blood sugar change curve.

[0118] In other embodiments, obtaining pre-training information and test information based on the processing results of the point processing and / or the surface processing and the stage interval, and generating a dietary improvement plan based on the pre-training information and the test information include the following steps: S410, in the daily behavior collection stage before training, corresponding lifestyle assessment results are obtained based on the diet registration corresponding to the user's own diet habits, and the lifestyle assessment results and blood sugar data are integrated into pre-training information.

[0119] Lifestyle assessment outcomes included single food groups and food combinations that corresponded to high glycemic responses.

[0120] Because the daily behavior collection stage before training is based on the user's own eating habits, the blood sugar detection at this stage is based on the user's past living habits. After monitoring and analyzing the blood sugar data at this time, the patient's blood sugar changes, maximum blood sugar, average blood sugar and other information corresponding to each meal can be obtained. These results are used as lifestyle assessment results, and combined with specific blood sugar data to integrate pre-training information.

[0121] The pre-training information includes the type, amount, and blood sugar data for each meal, of the food or food combination consumed.

[0122] S420, in the blood sugar test phase, high and low PGI foods are obtained based on the dietary registration corresponding to each test event, and the high and low PGI foods and their corresponding personalized glycemic index are integrated into test information.

[0123] During the blood sugar testing stage, the patient calculates the PGI values ​​of multiple foods based on the testing process, and analyzes them together with the corresponding food types to determine foods with high PGI values, and integrates these high PGI foods with the corresponding GI values ​​to obtain test information.

[0124] Among them, low PGI foods can also be screened and displayed through the above steps.

[0125] In addition, during the blood sugar testing phase, patients can still perform the same blood sugar analysis and calculation on their daily meals as in the daily behavior collection phase before training and obtain corresponding processing results. The processing results at this time are still considered to be part of the pre-training information.

[0126] S430, screening high blood sugar fluctuation foods and / or high blood sugar fluctuation food combinations based on the pre-training information and the test information, and generating dietary improvement suggestions and dietary recommendation suggestions based on the high blood sugar fluctuation foods and / or high blood sugar fluctuation food combinations.

[0127] Based on the pre-training information and test information, high blood sugar fluctuation foods and / or high blood sugar fluctuation food types are obtained, wherein high PGI foods must be high blood sugar fluctuation foods. When the foods or food combinations eaten by the patient in the pre-training stage do not contain high PGI foods and their corresponding blood sugar fluctuations and / or maximum blood sugar and / or average blood sugar reflect higher blood sugar fluctuations, these foods or food combinations are also regarded as high blood sugar fluctuation foods or high blood sugar fluctuation food combinations.

[0128] When generating a dietary improvement plan, a recipe combination corresponding to the patient's specific population is first generated based on the patient's pre-uploaded height, weight, blood sugar, blood lipids, blood pressure, pregnancy status, disease status, etc. The recipe can be generated by first making intelligent recommendations based on pre-stored health documents and other content.

[0129] At the same time, foods based on high blood sugar fluctuations or food combinations based on high blood sugar fluctuations are filtered out again in the preset generated recipe combinations.

[0130] A personalized recommended recipe is generated based on the remaining recipe combinations, wherein the filtered out foods and the remaining high blood sugar fluctuation foods or high blood sugar fluctuation food combinations that do not appear in the recommended recipes are used as dietary improvement suggestions, which are used to inform and advise patients not to eat such foods that may cause higher blood sugar fluctuations.

[0131] The remaining foods are used as dietary recommendations to inform patients that they can eat more of these foods that have a good glycemic response.

[0132] In other embodiments, obtaining experience information and post-training information in a corresponding stage interval based on the dietary improvement plan and the results of the point treatment and / or surface treatment includes the following steps: S510, in the intervention experience stage, collecting the diet registration uploaded by the user and determining whether it meets the diet improvement plan.

[0133] During the intervention experience phase, the dietary registration uploaded by the user is obtained, and based on the content of the dietary registration, it is determined whether the patient has followed the dietary improvement plan.

[0134] S520: If the conditions are met, the experience result is obtained based on the diet registration, the blood glucose data corresponding to the experience result is compared with the blood glucose data in the daily behavior collection phase before training to obtain a first comparison result, and the experience result, blood glucose data and the first comparison result are integrated into an experience value.

[0135] If followed, the experience results are obtained based on the diet registration. The experience results include the specific food types and quantities of the diet registration, and the blood sugar data collected in the effective events are compared with the blood sugar data in the pre-training stage to obtain the comparison results. Finally, the comparison results, experience results and blood sugar data are output.

[0136] In this way, users can intuitively see the improved blood sugar values ​​and whether their blood sugar has increased or decreased after the dietary improvement compared with the blood sugar data before training, as well as the specific improvement situation.

[0137] S530: If not satisfied, the valid event corresponding to the meal registration will not be counted in the generation of the experience result.

[0138] If not met, the valid event will be deleted and will not be included in the generation of experience results. During the intervention experience phase, the user will experience the changes in blood sugar brought about by dietary improvement. If the user does not comply with the dietary improvement plan, the blood sugar data analysis will not be functional.

[0139] S540, in the post-training self-monitoring stage, obtain the post-training results based on the diet registration, obtain the blood sugar data corresponding to the post-training results and compare them with the blood sugar data in the daily behavior collection stage before training to obtain a second comparison result, find the difference between the current diet registration and the dietary improvement plan based on the negative data in the second comparison result, and generate post-training information based on the post-training results, blood sugar data, the second comparison result and the difference.

[0140] In the self-monitoring stage after training, patients are no longer required to follow the dietary improvement plan. Instead, the data from the previous three stages are used to enable patients to make their own dietary arrangements. At this time, users may still abide by the food types in the dietary improvement plan, or they may add or reduce certain food types on this basis. At this time, their dietary registration is obtained to obtain the post-training results, and the corresponding blood sugar data is combined with the blood sugar data in the daily behavior collection stage before training to obtain a second comparison result.

[0141] At the same time, based on the second comparison result, it is judged whether negative data has appeared. Negative data is characterized by the increase or decrease of food types corresponding to the high blood sugar fluctuation compared with the blood sugar data in the intervention experience stage. This type of food is characterized by the user not following the dietary improvement plan and adding certain food types by himself, which leads to high blood sugar fluctuations. This type of food will be marked and displayed to remind users to be vigilant about this type of food.

[0142] Corresponding post-training information is generated through the above-mentioned difference content, post-training results, blood sugar data, second comparison results, etc.

[0143] Finally, the information generated at each stage is used to generate a personalized blood sugar data report for different patients, which includes all the blood sugar data detected in each link, blood sugar processing results, various charts, blood sugar comparison results at different stages, etc.

[0144] like Figure 2 As shown, the present application also discloses a personalized dynamic blood glucose data processing system, including: Dynamic blood glucose monitoring equipment is used to monitor and obtain continuous blood glucose data.

[0145] The effective event acquisition module is used to obtain effective events and the phase intervals corresponding to the effective events. The effective events are characterized by the collection of effective blood sugar data.

[0146] The processing task generation module is used to add processing tasks for valid events based on the stage interval in which the valid events are located.

[0147] The blood glucose data processing module is used to perform point processing and / or surface processing on the blood glucose data contained in the valid event based on the processing task, wherein the point processing is characterized by independent processing of the numerical points of the blood glucose data, and the surface processing is characterized by integrating the data points of multiple blood glucose data and processing them in combination with the preset reference line.

[0148] The front-end data collection and analysis module is used to obtain pre-training information and test information based on the processing results of point processing and / or surface processing and the stage interval.

[0149] A dietary plan generation module is used to generate a dietary improvement plan based on pre-training information and test information.

[0150] The post-stage data collection and analysis module is used to obtain experience information and post-training information in the corresponding stage interval based on the dietary improvement plan and the processing results of point processing and / or surface processing.

[0151] The personalized and accurate lifestyle assessment report generation module is used to generate a personalized and accurate lifestyle blood sugar data report based on a number of blood sugar data obtained in different stage intervals.

[0152] The implementation principle is: The conventional blood sugar test in the current technology is converted into a phased personal lifestyle test and adjustment based on blood sugar data. The blood sugar fluctuation content corresponding to the previous living habits and the eating habits content are collected through the collection of blood sugar data at different stages. According to the specific blood sugar processing results, a personalized dietary improvement plan for the patient is generated, and the patient is guided to adjust his personal lifestyle through the dietary improvement plan. The blood sugar improvement effect of the dietary improvement plan is judged through continuous detection and analysis of blood sugar fluctuations, and the difference in blood sugar data before and after the dietary improvement is reflected, so as to realize the visualization of the patient's lifestyle changes and generate a personalized and accurate lifestyle assessment report, so that the patient can intuitively understand the blood sugar improvement before and after the change of living habits, as well as the changes in blood sugar fluctuations caused by eating different foods.

[0153] It should be understood that although the steps in the flowchart of the accompanying drawings are shown in sequence according to the instructions of the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise clearly stated in this document, the execution of these steps is not strictly limited in order and can be performed in other orders.

[0154] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for processing personalized dynamic blood glucose data, characterized in that: The following steps are involved: Acquire a valid event and a phase interval corresponding to the valid event, wherein the valid event is characterized by the collection of valid blood glucose data; Adding a processing task for the valid event based on the phase interval where the valid event is located; Based on the processing task, point processing and / or surface processing is performed on the blood glucose data contained in the valid event, wherein the point processing is characterized by independently processing the numerical points of the blood glucose data, and the surface processing is characterized by integrating multiple data points of the blood glucose data and processing them in combination with a preset reference line; Obtaining pre-training information and test information based on the processing results of the point processing and / or the surface processing and the stage interval, and generating a dietary improvement plan based on the pre-training information and the test information; Based on the dietary improvement plan and the processing results of the point processing and / or the surface processing, experience information and post-training information are obtained in the corresponding stage interval; A personalized and accurate lifestyle assessment report is generated based on the data obtained in the different stage intervals.

2. The method for processing personalized dynamic blood glucose data according to claim 1, characterized in that: Obtaining valid events includes the following steps: Setting a valid event time range and generating corresponding condition checks, the condition checks corresponding to a first condition check for a short time check and a second condition check for a long time check; Acquire a data set including event time and corresponding blood glucose data, taking the collected initial event point as a starting point; adding the first condition check at the starting point to determine whether there is valid blood glucose data within the valid event time range corresponding to the first condition check; adding the second condition check at the starting point to determine whether there is valid blood glucose data within the valid event time range corresponding to the second condition check; If the data set satisfies both the first condition check and the second condition check, the data set is considered to be the valid event.

3. The method for processing personalized dynamic blood glucose data according to claim 1, characterized in that: Obtaining the phase interval corresponding to the valid event includes the following steps: Obtaining the total blood sugar improvement time, and dividing the total blood sugar improvement time into phase intervals of corresponding time lengths based on the time division requirements, wherein the phase intervals include a daily behavior collection phase before training, a blood sugar test phase, an intervention experience phase, and a self-monitoring phase after training; The current time corresponding to the starting point is obtained, and the current time is compared with the time lengths corresponding to the respective stage intervals to determine the stage interval in which the effective time is located.

4. The method for processing personalized dynamic blood glucose data according to claim 3, characterized in that: Adding a processing task for the valid event based on the phase interval where the valid event is located includes the following steps: In the daily behavior collection stage before training, the processing tasks include obtaining the proportion of three major energy-producing substances, blood sugar fluctuations, dynamic blood sugar graphs, post-meal blood sugar peaks, and average blood sugar levels before and after meals; In the blood glucose testing phase, the processing tasks include obtaining a personalized blood glucose index; In the intervention experience stage, the processing tasks include blood sugar fluctuations after the dietary improvement program, dynamic blood sugar graphs, post-meal blood sugar peaks, and average blood sugar levels before and after meals; In the post-training self-monitoring stage, the processing tasks include obtaining blood sugar fluctuations, dynamic blood sugar graphs, post-meal blood sugar peaks, average blood sugar levels before and after meals, and comparing the corresponding results of the processing tasks in the pre-training daily behavior collection stage.

5. The method for processing personalized dynamic blood glucose data according to claim 1, characterized in that: Performing point processing and / or surface processing on the blood glucose data contained in the valid event based on the processing task includes the following steps: When performing the point processing, the highest value of each blood glucose data in the valid event is obtained to obtain the post-meal blood glucose peak value, the average value of each blood glucose data in the valid event is calculated to obtain the pre- and post-meal blood glucose average value, the blood glucose fluctuation is obtained based on the change of each blood glucose data in the valid event, and the dynamic blood glucose map is drawn; When performing the surface processing, a reference instruction is generated and a personal standard blood sugar response obtained in response to the reference instruction is obtained, a test instruction is obtained and a specified food intake amount is generated in response to the acquisition instruction, a standard food test blood sugar response matching the specified food intake amount is obtained, and the personalized glycemic index is calculated based on the personal standard blood sugar response and the standard food test blood sugar response.

6. The method for processing personalized dynamic blood glucose data according to claim 5, characterized in that: Calculating the personalized glycemic index based on the standard blood glucose response and the standard food test blood glucose response comprises the following steps: generating a reference instruction of drinking 50 g of glucose, and screening out personal standard events that respond to the reference instruction from the valid events; Draw a personal standard blood sugar change curve based on each of the blood sugar data in the personal standard event and the corresponding event time, and define a personal standard blood sugar response based on the personal standard blood sugar change curve; After obtaining the test instruction, determining the test food type in the test instruction, and generating a standard intake amount of the corresponding type of food based on the test food type; monitoring blood sugar changes after the test instruction, and screening out test events from the valid events after blood sugar changes occur; Draw a test blood glucose change curve based on each of the blood glucose data in the test event and the corresponding event time, and define a standard food test blood glucose response based on the test blood glucose change curve; calculating the area between the individual's standard blood glucose response and the standard food test blood glucose response to obtain a personalized glycemic index for the standard test food; The personalized glycemic index is calculated based on the following formula: PGI=(standard food test blood sugar response / personal standard blood sugar response)*100%.

7. The method for processing personalized dynamic blood glucose data according to claim 6, characterized in that: When screening the personal standard event and the test event, the following steps are also included: Determine whether the personal standard event or the test event is abnormal, wherein the abnormality includes abnormal meal time and abnormal event quantity; If there is an abnormality, analyzing the credibility of the personal standard event or the test event based on the event time and the response event, and the trend of the blood glucose data; A time adjustment process or an optimal event selection process is performed based on the reliability.

8. The method for processing personalized dynamic blood glucose data according to claim 3, characterized in that: Based on the processing results of the point processing and / or the surface processing and the stage interval, pre-training information and test information are obtained, and a dietary improvement plan is generated based on the pre-training information and the test information, including the following steps: In the daily behavior collection stage before training, the corresponding lifestyle assessment results are obtained based on the diet registration corresponding to the user's own diet habits, and the lifestyle assessment results and the blood sugar data are integrated into the pre-training information, and the lifestyle assessment results include single types of food and food combinations corresponding to the high blood sugar impact; In the blood sugar test phase, high and low PGI foods are obtained based on the dietary registration corresponding to each of the test events, and the high and low PGI foods and their corresponding personalized glycemic indexes are integrated into the test information; High blood sugar fluctuation foods and / or high blood sugar fluctuation food combinations are screened based on the pre-training information and the test information, and dietary improvement suggestions and dietary recommendation suggestions are generated based on the high blood sugar fluctuation foods and / or the high blood sugar fluctuation food combinations.

9. The method for processing personalized dynamic blood glucose data according to claim 8, characterized in that: Based on the dietary improvement plan and the processing results of the point processing and / or the surface processing, the experience information and the post-training information are obtained in the corresponding stage interval, including the following steps: In the intervention experience stage, the diet registration uploaded by the user is collected and it is determined whether it meets the diet improvement plan; If satisfied, obtaining the experience result based on the diet registration, comparing the blood glucose data corresponding to the experience result with the blood glucose data in the pre-training daily behavior collection phase to obtain a first comparison result, and integrating the experience result, the blood glucose data and the first comparison result into an experience value; If not, the valid event corresponding to the dietary registration will not be counted in the generation of the experience result; In the post-training self-monitoring stage, the post-training result is obtained based on the diet registration, the blood glucose data corresponding to the post-training result is obtained and compared with the blood glucose data in the pre-training daily behavior collection stage to obtain a second comparison result, and the difference between the current diet registration and the dietary improvement plan is found based on the negative data in the second comparison result, and the post-training information is generated based on the post-training result, the blood glucose data, the second comparison result and the difference.

10. A personalized dynamic blood glucose data processing system, characterized in that: include: Dynamic blood glucose monitoring equipment, used to monitor and obtain continuous blood glucose data; An effective event acquisition module, used to acquire effective events and phase intervals corresponding to the effective events, wherein the effective events are characterized by the collection of effective blood glucose data; A processing task generating module, used for adding a processing task to the valid event based on the phase interval where the valid event is located; a blood glucose data processing module, configured to perform point processing and / or surface processing on the blood glucose data contained in the valid event based on the processing task, wherein the point processing is characterized by independently processing the numerical points of the blood glucose data, and the surface processing is characterized by integrating a plurality of data points of the blood glucose data and processing them in combination with a preset reference line; A front-end data acquisition and analysis module, used for obtaining pre-training information and test information based on the processing results of the point processing and / or the surface processing and the stage interval; A dietary plan generating module, used for generating a dietary improvement plan based on the pre-training information and the test information; A post-stage data collection and analysis module, for obtaining experience information and post-training information in the corresponding stage interval based on the dietary improvement plan and the processing results of the point processing and / or the surface processing; The personalized and accurate lifestyle assessment report generation module is used to generate a personalized and accurate lifestyle assessment report based on a number of data obtained in different stage intervals.

Images