Blood pressure data monitoring processing method and device based on data model and electronic equipment

Abstract

The invention relates to a blood pressure data monitoring processing method and device based on a data model and electronic equipment, and the method comprises the steps: obtaining blood pressure data and physical condition data of a user, training a monitoring model according to the blood pressure data and the physical condition data, and obtaining a model prediction result, the user standard blood pressure of the user is calculated according to the related data, a predicted user blood pressure value is obtained by combining the model prediction result, the current user blood pressure value and the predicted user blood pressure value are compared, and whether early warning information is generated or not is judged according to the comparison result. According to the method, a personalized model and an advanced machine learning algorithm are introduced, specific data of each user are collected, individual differences such as age, gender and basic diseases are considered, a highly personalized blood pressure monitoring model is constructed, the monitoring model is continuously iterated and optimized, and the accuracy and efficiency of blood pressure monitoring and management are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing and medical health technology, and in particular to a blood pressure data monitoring and processing method, device and electronic equipment based on a data model. Background Art

[0002] There are two main common technical solutions for abnormal blood pressure monitoring. One is a judgment method based on a single blood pressure value: if the blood pressure value measured by the user at a certain time exceeds or is lower than the preset specific blood pressure value, it is considered to be abnormal blood pressure. The other is a judgment method based on the average blood pressure value within a certain period: within a predetermined period (such as 3 days or a week), the average value of the user's blood pressure is calculated. If the average value is higher or lower than the preset specific blood pressure value, it is considered to be abnormal blood pressure. These two methods have been widely used in blood pressure monitoring and management, and have provided certain help for the early detection and prevention of hypertension and related diseases.

[0003] However, the judgment method based on a single blood pressure value is easily affected by occasional blood pressure fluctuations. For example, a user's blood pressure value may be accidentally higher at a certain time, but the results of multiple measurements are all within the normal range. At this time, it is obviously unreasonable to judge the abnormality based only on a single blood pressure value. Similarly, the method based on the average blood pressure value within a cycle also has defects, because blood pressure has obvious fluctuation patterns within a day, including double peaks in blood pressure in the morning and evening and trough blood pressure at night. For example, some users have higher blood pressure in the morning and normal blood pressure at night. The average blood pressure value within the calculation cycle may mask the abnormal fluctuations in the morning, making it impossible to effectively monitor and manage blood pressure changes in these key time periods. Therefore, the existing technical solutions have significant deficiencies in dealing with individualized blood pressure fluctuations and multi-time period blood pressure management. Summary of the invention

[0004] In view of this, the present application proposes a blood pressure data monitoring and processing method based on a data model to solve the problems reflected in the above-mentioned background technology.

[0005] According to one aspect of the present application, a blood pressure data monitoring and processing method based on a data model is provided, wherein the data model in the method may be a large data model, comprising the following steps: Obtain user blood pressure data and physical condition data; Training a monitoring model according to the blood pressure data and the physical condition data, and obtaining a model prediction result; Calculate the user's standard blood pressure based on the relevant data, and obtain the predicted user blood pressure value in combination with the model prediction result; Receive the user's current blood pressure value uploaded by the user; The current blood pressure value of the user is compared with the predicted blood pressure value of the user, and whether to generate warning information is determined based on the comparison result.

[0006] As an optional implementation scheme of the present application, optionally, training a monitoring model according to the blood pressure data and the physical condition data, and obtaining a model prediction result, includes: Define the objective function and establish a monitoring model; Inputting user health status information and preset conditions into the monitoring model to obtain corresponding user nodes that pass the monitoring model; The scores of each user node that passes the monitoring model are added together to obtain the model prediction result.

[0007] As an optional implementation scheme of the present application, optionally, calculating the user's standard blood pressure according to the relevant data, and obtaining the predicted user blood pressure value in combination with the model prediction result, includes: Calculate the user's standard blood pressure based on the user's physical condition, combined with the "Hypertension Guidelines" and the user's blood pressure trend at that stage; The user's standard blood pressure and the model prediction result are added to obtain the predicted blood pressure value.

[0008] As an optional implementation scheme of the present application, optionally, comparing the current blood pressure value of the user with the predicted blood pressure value of the user, and determining whether to generate warning information according to the comparison result, includes: Calculate the result of subtracting the predicted user blood pressure value from the user's current blood pressure value to obtain a blood pressure difference; Compare the blood pressure difference with the preset value to determine whether to generate a warning message.

[0009] As an optional implementation scheme of the present application, optionally, obtaining the user's blood pressure data and physical condition data includes: The user's blood pressure data can be collected from different blood pressure testing devices, or can be manually entered through a mini program.

[0010] As an optional implementation scheme of the present application, optionally, defining an objective function and establishing a monitoring model include: The model has a continuous updating mechanism. The model is updated by calculating the optimal weight for a single leaf node and then splitting it to form the optimal solution.

[0011] As an optional implementation scheme of the present application, optionally, it is characterized in that the objective function is defined and the monitoring model is established, and further includes: The model regularly receives new user physical condition and blood pressure data to update and adjust model parameters.

[0012] According to the second aspect of the present application, a blood pressure data monitoring and processing device based on a data model is provided, comprising the following modules: A module for obtaining user health status information is used to obtain user health status information to be analyzed; Construct and train a monitoring model module, which is used to construct a monitoring model and continuously optimize the model, input the user's health status data into the model, and obtain the model prediction result; A module for calculating user standard blood pressure is used to obtain the user's standard blood pressure based on the user's periodic health information; Receive the user's current blood pressure module, used to record the user's real-time blood pressure measurement value; Generate an early warning information module to determine whether to issue an early warning prompt for the user's health.

[0013] As an optional implementation scheme of the present application, optionally, constructing and training a monitoring model module includes: An update model module, used to obtain the optimal solution of the monitoring model when it is continuously updated; The training model module is used to continuously receive new user data, and continuously update and adjust model parameters based on the new data, so as to continuously improve the accuracy and efficiency of the monitoring model.

[0014] According to the third aspect of the present application, an electronic device is proposed, comprising: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement a blood pressure data monitoring and processing method based on a data model as described in any one of claims 1 to 8 when executing the executable instructions.

[0015] Beneficial effects of this application: The present invention significantly improves the accuracy and efficiency of blood pressure monitoring and management by introducing personalized models and advanced machine learning algorithms, which is mainly reflected in the following aspects. The accuracy and personalization of blood pressure abnormality judgment are improved. The model can fully consider the individual differences of users, such as age, gender, basic blood pressure level, living habits, etc., so as to make more accurate and personalized blood pressure abnormality judgment. This avoids misjudgment or missed judgment caused by ignoring individual differences. The sensitivity to blood pressure fluctuations is enhanced. By continuously adding tree structures and learning new functions to fit the residuals of the last prediction, the model can more sensitively capture the slight fluctuations and changing trends of the user's blood pressure. This helps to timely discover and warn potential blood pressure abnormalities, and provide more powerful support for the user's health management. Effective management of blood pressure in multiple time periods can be achieved. The model can comprehensively consider the blood pressure data of users in different time periods, such as blood pressure fluctuations in key time periods such as morning and evening. This helps to understand the user's blood pressure status more comprehensively and formulate more targeted health management plans. Improve the efficiency and effectiveness of chronic disease management. Through personalized blood pressure monitoring and early warning, the model can help users manage their health more scientifically and reduce the risk of chronic diseases.

[0016] Other features and aspects of the present application will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the present application and, together with the description, serve to explain the principles of the present application.

[0018] Figure 1 A flow chart showing a blood pressure data monitoring and processing method based on a data model according to an embodiment of the present application; Figure 2 A block diagram of a blood pressure data monitoring and processing device based on a data model according to an embodiment of the present application is shown; Figure 3 A tree diagram showing the input sample data and the monitoring model trained under preset conditions of the blood pressure data monitoring and processing method based on the data model according to an embodiment of the present application; DETAILED DESCRIPTION Various exemplary embodiments, features and aspects of the present application will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0019] Among them, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application or simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0020] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0021] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0022] In addition, in order to better illustrate the present application, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present application can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present application.

[0023] The present application scheme is applied in the field of automatic blood pressure monitoring for users with chronic diseases. When the present method is used, a blood pressure monitoring device is equipped on the user side, and the blood pressure monitoring device includes an automatic blood pressure monitoring device, which can automatically monitor the user's blood pressure at regular intervals, and automatically upload the monitored user's blood pressure data to the system background of the present method. The system background uses the method of the present application to analyze the user's blood pressure data. In the specific implementation process, the blood pressure monitoring device on the user side can also be a manual monitoring device, and the user can measure the blood pressure on a regular basis and upload the blood pressure measurement results in the system corresponding to the present method. For example, the user can use the WeChat applet, APP, or web page of the system corresponding to the present method to upload the blood pressure measurement results. For the blood pressure measurement data, it can be measured multiple times in one day, and the multiple measurement results can be uploaded. The specific measurement cycle and measurement time can be notified to the user in advance, or set in the automatic blood pressure monitoring device. For example, during the execution process, it can be set to measure the user's blood pressure once in the morning, afternoon, and evening.

[0024] Example 1 Figure 1 FIG. 1 is a flow chart showing a blood pressure data monitoring and processing method based on a data model according to Embodiment 1 of the present application. Figure 1 As shown, the flow chart includes: S100: Obtaining blood pressure data and physical condition data of the user.

[0025] In this embodiment, in order to solve the problem of insufficient personalized judgment in the prior art, the monitoring model is trained for each user's blood pressure, physical condition, etc. Among them, the blood pressure data is the blood pressure data automatically or manually uploaded by the user through the same or different blood pressure measurement devices for multiple times within a certain time period, such as the total blood pressure measurement data uploaded by the user in the morning, noon and evening within the month before the current date, and the physical condition data is the basic health data of the user in the time period, such as the user's age, the degree of bilateral carotid artery stenosis, whether there are basic diseases such as hypertension or hypotension, etc., which are entered by the user or added by medical staff.

[0026] S200: training a monitoring model according to the blood pressure data and the physical condition data, and obtaining a model prediction result.

[0027] In this embodiment, the model prediction result is a predicted value obtained after the user sample data passes through the trained monitoring model, which is used to calculate the predicted blood pressure value of the user using the monitoring model. In order to obtain the predicted value, it is necessary to train the monitoring model using the user blood pressure data and the physical condition data in S100 within a certain time period. The core idea of ​​the monitoring model is to continuously add tree structures. Each time a tree is added, a new function is learned to fit the residual of the last prediction. When the training is completed, k trees are obtained, and a corresponding leaf node will fall in each tree. Each leaf node corresponds to a score. Finally, you only need to add up the scores corresponding to each tree to get the predicted value, that is, the model prediction result.

[0028] S300, calculating the user's standard blood pressure according to relevant data, and obtaining a predicted user blood pressure value in combination with the model prediction result.

[0029] In this embodiment, the relevant data includes the user's physical condition data, the hypertension guide, and the user's stage blood pressure trend. The hypertension guide points out that when the user's physical condition data meets the conditions, the user's standard blood pressure value can be lowered. For example, when the user is 80 years old or older, the user's real-time blood pressure value measured at the same time every day within a certain period of time can be compared with 150 / 90, and the doctor determines whether it is tolerated. If it is tolerated, the user's standard blood pressure can be lowered to 140 / 90. After calculating the user's standard blood pressure based on the user's physical condition combined with the "hypertension guide" and the user's stage blood pressure trend, the model prediction result is added to the standard blood pressure to obtain the user's predicted blood pressure value.

[0030] S400: Receive the current blood pressure value of the user uploaded by the user.

[0031] In this embodiment, the monitoring model receives the real-time measured blood pressure value uploaded by the user using a blood pressure measuring device.

[0032] S500: Compare the current blood pressure value of the user with the predicted blood pressure value of the user, and determine whether to generate warning information based on the comparison result.

[0033] In this embodiment, the user's current blood pressure value is the blood pressure value uploaded by the user in real time using a blood pressure measuring device, and the predicted user blood pressure value is the predicted blood pressure value obtained by adding the model prediction result to the user's standard blood pressure. The user's current blood pressure value and the predicted user blood pressure value are compared. If the user's current blood pressure value is greater than the predicted user blood pressure value by a preset value (the preset value is set by expert discussion), a work order and SMS warning will be issued to the user.

[0034] As an optional implementation scheme of the present application, optionally, a monitoring model is trained according to the blood pressure data and the physical condition data, and a model prediction result is obtained, including: defining an objective function and establishing a monitoring model; inputting user health status information and preset conditions into the monitoring model to obtain corresponding user nodes that pass the monitoring model; and adding the scores of each user node that passes the monitoring model to obtain the model prediction result.

[0035] In this embodiment, the objective function defined in the model , is used to measure the gap between the model prediction value and the true value, which helps to establish a monitoring model so that the prediction of the tree group is as close to the true value (accuracy) as possible. The objective function is obtained as follows: Among them, i represents the i-th sample, The loss function represents the prediction error of the i-th sample, is the predicted value of sample i, is the true value, A function that represents the complexity of the tree. The smaller the function, the lower the complexity and the stronger the generalization ability.

[0036] The user nodes that pass the monitoring model correspond to the leaf nodes in the monitoring model. For leaf node j, its score It can be calculated by the following formula: in, is the sum of the first-order gradients of all samples on the leaf nodes, is the sum of the second-order gradients of all samples on leaf node j, and λ is a manually set parameter.

[0037] The monitoring model is set with preset conditions such as the depth of the tree and the number of trees. After inputting the user's age, the degree of bilateral carotid artery stenosis and other user health status information into the monitoring model, the tree group of the monitoring model can be obtained. The leaf nodes of the tree group are the users after the monitoring model. The calculation formula can be used to obtain the score of the leaf node, i.e. the user node. The scores of all leaf nodes with the same user whose scores have been calculated are added together to obtain the prediction result of the model. For example, assuming that the depth of the tree is set to 3, the number of trees is set to 2, the root node of the first tree uses age as the splitting condition, and the root node of the second tree is the degree of bilateral carotid artery stenosis. Assuming that there are 6 groups of user samples, the preset value is 6, and the samples are: Sample 1: Age 54, bilateral carotid artery stenosis ≥ 75, standard blood pressure 135 / 85, blood pressure value 148 / 93 Sample 2: Age 60, bilateral carotid artery stenosis <75, standard blood pressure 135 / 85, blood pressure value 136 / 82 Sample 3: Age 69, bilateral carotid artery stenosis ≥ 75, standard blood pressure 140 / 80, blood pressure value 143 / 84 Sample 4: Age 72, bilateral carotid artery stenosis <75, standard blood pressure 140 / 80, blood pressure value 148 / 96 Sample 5: Age 84, bilateral carotid artery stenosis ≥ 75, standard blood pressure 145 / 85, blood pressure value 151 / 93 Sample 6: Age 85, bilateral carotid artery stenosis <75, standard blood pressure 145 / 85, blood pressure value 163 / 100 Then the tree structure after the sample passes through the model and the node scores are calculated is Figure 3 , and finally add up the scores of the same sample to get the model prediction result of the sample.

[0038] As an optional implementation scheme of the present application, optionally, the user's standard blood pressure is calculated based on relevant data, and the predicted user blood pressure value is obtained in combination with the model prediction result, including: calculating the user's standard blood pressure based on the user's physical condition combined with the "Hypertension Guidelines" and the user's stage blood pressure trend; the user's standard blood pressure and the model prediction result are added to obtain the predicted blood pressure value.

[0039] In this embodiment, the method of calculating the standard blood pressure according to the user's physical condition combined with the "Hypertension Guidelines" and the user's stage blood pressure trend can calculate the user's own standard blood pressure while taking into account the individual differences of the user, rather than the unified standard blood pressure of the general public. Then, the blood pressure value predicted by the model is obtained by adding the user's standard blood pressure to the model prediction result, thereby realizing highly personalized blood pressure monitoring.

[0040] As an optional implementation scheme of the present application, optionally, the user's current blood pressure value and the predicted user blood pressure value are compared, and it is determined whether to generate a warning message based on the comparison result, including: calculating the result of subtracting the predicted user blood pressure value from the user's current blood pressure value to obtain a blood pressure difference; comparing the blood pressure difference with a preset value to determine whether to generate a warning message.

[0041] In this embodiment, the predicted user blood pressure value and the user's current blood pressure value are calculated, that is, the user's current blood pressure value is subtracted from the predicted user blood pressure value to obtain a blood pressure difference result, and the blood pressure difference is compared with a preset value used by the model to measure whether to issue an early warning. If the blood pressure difference is greater than the preset value, a work order and SMS warning are issued. Figure 3 , assuming the preset value is 6, the user's predicted blood pressure value is combined with the user's blood pressure measurement value in the user sample information mentioned above, and the final result of the user sample can be obtained: Sample 1: 136 / 86, alarm Sample 2: 133 / 83, no alarm Sample 3: 141 / 81, no alarm Sample 4: 140 / 80, alarm Sample 5: 149 / 89, no alarm Sample 6: 146 / 86, Alarm As an optional implementation scheme of the present application, optionally, the user's blood pressure data and physical condition data are obtained, including: the user's blood pressure data can be collected from different blood pressure checking devices, and can also be manually entered through a mini program.

[0042] In this embodiment, the model needs to obtain the blood pressure data measured by the user. When obtaining the blood pressure data measured by the user, the user's blood pressure data can be collected through various different blood pressure measuring devices, or the user can manually enter the data through a mini program.

[0043] As an optional implementation scheme of the present application, optionally, an objective function is defined and a monitoring model is established, including: the model has a continuous updating mechanism, and the updating of the model is to calculate the optimal weight for a single leaf node, and then split it to form an optimal solution.

[0044] In this embodiment, the model can be updated according to the input data. The update scheme of the model (new tree) is to calculate the optimal weight for a single leaf node and then split it to form the optimal solution. The gain definition formula for splitting is: Among them, L and R represent the sample sets of the left subtree and the right subtree after the split. G and H are the first-order derivative and the second-order derivative of the loss function respectively. γ is the complexity cost of adding a new leaf node, which is a manually set parameter. The larger the value of Gain, the greater the gain. Therefore, the Gain corresponding to all candidate leaf nodes should be calculated, and the one with the largest Gain should be selected for splitting. When the tree reaches the maximum depth, stop building the tree, because the depth of the tree is too deep and overfitting is prone to occur.

[0045] As an optional implementation scheme of the present application, it is optionally characterized in that the objective function is defined, the monitoring model is established, and it also includes: the model regularly receives new user physical condition and blood pressure data to update and adjust the model parameters.

[0046] In this embodiment, since the user's physical condition and blood pressure data will change over time, the model needs to regularly receive new data inputs, and update and adjust the model parameters based on these data, and continuously iterate and optimize the monitoring model mechanism. By regularly receiving specific data information such as the user's new physical condition and blood pressure data, the model's predicted data can be more closely aligned with the individual user, and highly personalized blood pressure monitoring and early warning can be performed, helping the user to fully understand their own blood pressure status, and accordingly develop more targeted health management plans, improve the efficiency and effectiveness of chronic disease management, and reduce the risk of chronic diseases.

[0047] Example 2 Based on the same principle as the above method, a blood pressure data monitoring and processing device based on a data model is also proposed, see Figure 2 , a blood pressure data monitoring and processing device 100 based on a data model according to an embodiment of the present disclosure includes: A user health status information acquisition module 110 is used to acquire the user health status information to be analyzed; Construct and train a monitoring model module 120, which is used to construct a monitoring model and continuously optimize the model. The monitoring model constructed in the present application can be a model or a large model. The user health status data is input into the monitoring model or the monitoring large model to obtain the prediction result of the monitoring model or the monitoring large model; The user standard blood pressure calculation module 130 is used to calculate the user's standard blood pressure according to the user's periodic health information; A module 140 for receiving the current blood pressure of the user, for recording the blood pressure measurement value of the user in real time; The warning information generating module 150 is used to determine whether to issue a warning prompt for the user's health.

[0048] Obviously, those skilled in the art should understand that all or part of the processes in the above-mentioned embodiment method can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned control methods. The modules or steps of the present invention can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by program codes executable by computing devices, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules respectively, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the present invention is not limited to any specific combination of hardware and software.

[0049] Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned control methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated as: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0050] Example 3 Furthermore, an electronic device is proposed, comprising: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the blood pressure data monitoring and processing method based on the data model described in Example 1 when executing the executable instructions.

[0051] The electronic device of the embodiment of the present disclosure includes a processor and a memory for storing processor executable instructions, wherein the processor is configured to implement any of the above-mentioned blood pressure data monitoring and processing methods based on a data model when executing the executable instructions.

[0052] It should be noted that the number of processors may be one or more. At the same time, the electronic device of the embodiment of the present disclosure may also include an input device and an output device. The processor, memory, input device, and output device may be connected via a bus or in other ways, which are not specifically limited here.

[0053] The memory is a computer-readable storage medium for the blood pressure data monitoring and processing method based on a data model, and can be used to store software programs, computer executable programs, and various modules, such as: the program or module corresponding to the blood pressure data monitoring and processing method based on a data model in the embodiment of the present disclosure. The processor executes various functional applications and data processing of the electronic device by running the software programs or modules stored in the memory.

[0054] The input device can be used to receive input numbers or signals. The signal can be a key signal related to user settings and function control of the device / terminal / server. The output device can include a display device such as a display screen.

[0055] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A blood pressure data monitoring and processing method based on a data model, characterized in that: The method is used to perform personalized blood pressure data monitoring and management on a user, and the method comprises the following steps: Obtain user blood pressure data and physical condition data; Training a monitoring model according to the blood pressure data and the physical condition data, and obtaining a model prediction result; Calculate the user's standard blood pressure based on the relevant data, and obtain the predicted user blood pressure value in combination with the model prediction result; Receive the user's current blood pressure value uploaded by the user; The current blood pressure value of the user is compared with the predicted blood pressure value of the user, and whether to generate warning information is determined based on the comparison result.

2. A blood pressure data monitoring and processing method based on a data model as claimed in claim 1, characterized in that: The monitoring model is trained according to the blood pressure data and the physical condition data, and the model prediction results are obtained, including: Define the objective function and establish a monitoring model; Inputting user health status information and preset conditions into the monitoring model to obtain corresponding user nodes that pass the monitoring model; The scores of each user node that passes the monitoring model are added together to obtain the model prediction result.

3. The blood pressure data monitoring and processing method based on a data model as claimed in claim 1, characterized in that: Calculating the user's standard blood pressure according to the relevant data, and obtaining the predicted user blood pressure value in combination with the model prediction result, including: Calculate the user's standard blood pressure based on the user's physical condition, combined with the "Hypertension Guidelines" and the user's blood pressure trend at that stage; The user's standard blood pressure and the model prediction result are added to obtain the predicted blood pressure value.

4. The blood pressure data monitoring and processing method based on a data model as claimed in claim 1, characterized in that: Comparing the current blood pressure value of the user with the predicted blood pressure value of the user, and determining whether to generate warning information according to the comparison result, including: Calculate the result of subtracting the predicted user blood pressure value from the user's current blood pressure value to obtain a blood pressure difference; Compare the blood pressure difference with the preset value to determine whether to generate a warning message.

5. The blood pressure data monitoring and processing method based on a data model as claimed in claim 1, characterized in that: Obtain user blood pressure data and physical condition data, including: The user's blood pressure data can be collected from different blood pressure testing devices, or can be manually entered through a mini program.

6. A blood pressure data monitoring and processing method based on a data model as claimed in claim 2, characterized in that: Define the objective function and establish a monitoring model, including: The model has a continuous updating mechanism. The model is updated by calculating the optimal weight for a single leaf node and then splitting it to form the optimal solution.

7. A blood pressure data monitoring and processing method based on a data model as claimed in claim 2, characterized in that: Define the objective function and establish a monitoring model, including: The model regularly receives new user physical condition and blood pressure data to update and adjust model parameters.

8. A blood pressure data monitoring and processing device based on a data model, characterized in that: The monitoring model is trained based on user personalized data to obtain early warning information, including: A module for obtaining user health status information is used to obtain user health status information to be analyzed; Construct and train a monitoring model module, which is used to construct a monitoring model and continuously optimize the model, input the user's health status data into the model, and obtain the model prediction result; A module for calculating user standard blood pressure is used to obtain the user's standard blood pressure based on the user's periodic health information; Receive the user's current blood pressure module, used to record the user's real-time blood pressure measurement value; Generate an early warning information module to determine whether to issue an early warning prompt for the user's health.

9. A blood pressure data monitoring and processing device based on a data model as claimed in claim 8, characterized in that: Build and train monitoring model modules, including: An update model module, used to obtain the optimal solution of the monitoring model when it is continuously updated; The training model module is used to continuously receive new user data, and continuously update and adjust model parameters based on the new data, so as to continuously improve the accuracy and efficiency of the monitoring model.

10. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement a blood pressure data monitoring and processing method based on a data model as described in any one of claims 1 to 8 when executing the executable instructions.

Images