A physiological state assessment method, apparatus, device, and storage medium

Abstract

The application discloses a physiological state evaluation method and device, equipment and a storage medium. The method comprises the following steps: calculating blood pressure parameters of a user for each preset physiological state scene according to historical physiological data corresponding to each preset physiological state scene; if current physiological data of the user is collected, a current physiological state scene in which the user is located is obtained; a matching degree between the current physiological data and a blood pressure parameter corresponding to the current physiological state scene is calculated; and the user is evaluated according to the current physiological state scene and the matching degree, so as to obtain a physiological state evaluation result of the user. According to the embodiment, the analysis accuracy of physiological data can be improved, so that an accurate physiological state evaluation result can be obtained.

Description

Technical Field

[0001] This application relates to the field of health monitoring technology, and in particular to a method, apparatus, device and storage medium for assessing physiological state. Background Technology

[0002] Currently, products related to physiological data management are mainly used to output physiological data collected in a single instance, display historical trend charts and statistical graphs of physiological data, and present multi-dimensional health data. Although these products can collect or display physiological data, they are essentially still at the "data presentation" stage.

[0003] In related technologies, a uniform threshold or population statistical mean is commonly used to analyze the collected physiological data to generate an assessment of the user's physiological state. However, this approach ignores individual physiological differences among users, resulting in low accuracy. Therefore, it is crucial to improve the precision of physiological data analysis to obtain accurate physiological state assessment results. Summary of the Invention

[0004] This application provides a physiological state assessment method, apparatus, device, and storage medium, which can improve the accuracy of physiological data analysis to obtain accurate physiological state assessment results.

[0005] On the one hand, embodiments of this application provide a method for assessing physiological state, including:

[0006] The system acquires the user's historical physiological data collected under each preset physiological state scenario, and calculates the user's blood pressure parameters for each preset physiological state scenario based on the historical physiological data corresponding to each preset physiological state scenario. If the user's current physiological data is collected, then the user's current physiological state scenario is obtained; Calculate the degree of matching between the current physiological data and the blood pressure parameters corresponding to the current physiological state scenario; Based on the current physiological state scenario and the matching degree, the user's state is evaluated to obtain the user's physiological state evaluation result.

[0007] Furthermore, embodiments of this application provide a physiological state assessment device, comprising: The data acquisition unit is used to acquire the user's historical physiological data collected under each preset physiological state scenario, and to calculate the user's blood pressure parameters for each preset physiological state scenario based on the historical physiological data corresponding to each preset physiological state scenario. The scene acquisition unit is used to acquire the current physiological state scene of the user if the user's current physiological data is collected. The matching degree calculation unit is used to calculate the matching degree between the current physiological data and the blood pressure parameter corresponding to the current physiological state scenario; The result generation unit is used to perform a status assessment on the user based on the current physiological state scenario and the matching degree, and obtain the physiological state assessment result of the user.

[0008] Furthermore, embodiments of this application provide an electronic device, including: A memory, wherein a computer program is stored; A processor for loading the computer program to implement the method as described in the first aspect.

[0009] In another aspect, embodiments of this application also provide a computer-readable storage medium storing a computer program adapted to be loaded by a processor and executed as described in the first aspect.

[0010] In another aspect, embodiments of this application also provide a computer program product, the computer program product including computer instructions, wherein the processor of the physiological state assessment device reads the computer instructions and executes the method as described in the first aspect.

[0011] In this embodiment, by calculating user-specific blood pressure parameters based on corresponding historical physiological data for each preset physiological state scenario, a personalized benchmark for the normal fluctuation range of a user's blood pressure can be established from the dual dimensions of physiological state scenario and individual differences. This fundamentally avoids individual bias caused by using a uniform threshold or population statistical mean. Furthermore, this embodiment matches the current physiological data collected from the user in the current physiological state scenario with the corresponding blood pressure parameters. By using the user's own longitudinal historical data as a reference, the interference of individual differences can be effectively eliminated, ensuring that the obtained matching degree accurately and truthfully reflects the degree of deviation of the current physiological data from the user's own normal benchmark.

[0012] In this way, subsequent user status assessments, combining the matching degree with the current physiological state scenario, can, on the one hand, accurately determine whether the user is in an abnormal or specific physiological state through the deviation represented by the matching degree; on the other hand, the current physiological state scenario can be used to impose scenario constraints on the assessment process, preventing the status assessment results from deviating from the actual situation. Therefore, the final physiological status assessment result obtained in this embodiment is generated under the constraints of the current physiological state scenario, integrating the deviation of the current physiological data from the user's own blood pressure parameters. Compared to the traditional "data presentation" mode based only on single data points or uniform thresholds, this embodiment achieves a leap towards personalized, scenario-adaptive, and accurate status assessment, significantly improving the accuracy of physiological data analysis, thereby greatly improving the accuracy and reliability of the physiological status assessment results. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a schematic diagram of the architecture of a physiological state assessment system provided in an embodiment of this application; Figure 2 This is a flowchart illustrating a physiological state assessment method provided in an embodiment of this application; Figure 3 This is a schematic diagram of a blood pressure data analysis interface provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a physiological state assessment device provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0015] It should be noted in advance that, in order to enable those skilled in the art to better understand the technical solutions proposed in the embodiments of this application, the embodiments of this application will be described clearly and completely in conjunction with one or more accompanying drawings. Furthermore, the accompanying drawings shown in the embodiments of this application are merely illustrative examples; for instance, the execution order of each step in the drawings can be adaptively adjusted according to the actual application scenario.

[0016] Furthermore, in the embodiments of this application, the block diagrams, modules, and units shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. Each module or unit can be part of a larger module or unit that includes the functionality of that module or unit. That is, the terms "module" or "unit" mentioned in the embodiments of this application refer to a computer program or part of a computer program with a predetermined function, which can work together with other related parts to achieve a predetermined goal. It can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof, or implemented in different network and / or processor devices and / or microcontroller devices. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units.

[0017] Currently, products related to physiological data management mainly fall into three categories. The first category includes products like home electronic blood pressure monitors, which collect physiological data and primarily output single-collection data (such as single systolic and diastolic blood pressure readings). The second category consists of recording products, such as health apps, which mainly display historical trend charts and statistical graphs of physiological data. The third category comprises comprehensive health products that display multi-dimensional health data, including exercise, sleep, and stress. While these products can collect or display a significant amount of data, the vast majority remain at the stage of simply "presenting data to the user."

[0018] However, what users truly care about is not isolated data, but whether the data reflects their own physiological state and whether it is normal. Related technologies commonly use uniform thresholds or population statistical means to analyze the collected physiological data, thereby generating an assessment of the user's physiological state. However, this approach ignores individual physiological differences between users, leading to low accuracy in the assessment results.

[0019] Based on this, this application provides a physiological state assessment scheme. The scheme calculates the user's blood pressure parameters for each preset physiological state scenario based on the user's historical physiological data collected in advance. Subsequently, the physiological data collected in the user's current physiological state scenario can be matched with the blood pressure parameters corresponding to the current physiological state scenario. Based on the matching degree and the current physiological state scenario, the user's state is assessed, thereby obtaining the user's physiological state assessment result.

[0020] It is clear that this solution, by calculating the user's blood pressure parameters for each preset physiological state scenario based on historical physiological data, establishes a personalized benchmark for the normal fluctuation range of a user's blood pressure from both the perspectives of the physiological state scenario and the individual, fundamentally eliminating individual bias caused by using a uniform threshold or population mean. Furthermore, this solution further leverages the user's own longitudinal historical data as a reference by matching the physiological data collected in the current physiological state scenario with the corresponding blood pressure parameters. This eliminates interference from individual differences, ensuring that the resulting matching degree accurately and truthfully reflects the user's physiological deviation relative to their normal state.

[0021] This solution, by combining matching degree and the current physiological state scenario to assess the user's state, can accurately determine whether the user is in an abnormal or specific physiological state based on the deviation of the current physiological data (represented by the matching degree) from the user's own blood pressure parameters. Furthermore, it can use the current physiological state scenario to constrain the state assessment process, preventing deviations in the assessment direction. Therefore, the physiological state assessment results in this solution are obtained by integrating the deviation of the current physiological data from the user's own blood pressure parameters under the constraints of the current physiological state scenario. Compared to traditional solutions, this solution represents a leap from traditional "data presentation" to personalized, scenario-adaptive, and precise state assessment, significantly improving the accuracy of physiological data analysis and thus enhancing the accuracy and reliability of the physiological state assessment results.

[0022] Based on the above-described physiological state assessment method, this application provides a physiological state assessment system, which can be found in [reference needed]. Figure 1 , Figure 1 The physiological state assessment system shown may include terminal device 101 and server 102. The number of terminal devices 101 may include at least one, and the number of servers 102 may include at least one. A communication connection is established between any terminal device and any server.

[0023] like Figure 1 As shown, terminal device 101 may include any one or more electronic devices such as smartphones, tablets, laptops, desktop computers, smart in-vehicle devices, and smart wearable devices. Various applications (APPs) can run within terminal device 101, such as payment clients, game clients, virtual interaction clients, multimedia playback clients, social clients, information streaming clients, etc., which are not limited herein.

[0024] Server 102 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. Terminal device 101 and server 102 can communicate directly or indirectly via wired or wireless communication; this application does not impose any restrictions on this.

[0025] In some embodiments, the above-described physiological state assessment method may be solely determined by... Figure 1 The terminal device 101 in the physiological state assessment system described above executes the following process: The terminal device 101 can acquire the user's historical physiological data collected under each preset physiological state scenario, and calculate the user's blood pressure parameters for each preset physiological state scenario based on the historical physiological data. If the user's current physiological data is collected, the terminal device 101 can acquire the user's current physiological state scenario. Then, the terminal device 101 can calculate the matching degree between the current physiological data and the blood pressure parameters corresponding to the current physiological state scenario. In this way, the terminal device 101 can assess the user's state based on the current physiological state scenario and the matching degree, and obtain the user's physiological state assessment result.

[0026] Optionally, the above-mentioned physiological state assessment methods can also be used solely by... Figure 1 The server 102 in the physiological state assessment system shown executes the process, and the specific execution process can be found in the specific execution process of the terminal device 101 mentioned above. This application will not repeat the details here.

[0027] In other embodiments, the above-described physiological state assessment method may be solely determined by... Figure 1 The terminal device 101 and server 102 in the physiological state assessment system are executed as follows: Server 102 can acquire the user's historical physiological data collected under each preset physiological state scenario, and calculate the user's blood pressure parameters for each preset physiological state scenario based on the historical physiological data. Each time terminal device 101 collects the user's current physiological data, it can send the current physiological data to server 102. Upon receiving the current physiological data, server 102 can obtain the user's current physiological state scenario. Then, server 102 can calculate the matching degree between the current physiological data and the blood pressure parameters corresponding to the current physiological state scenario, and perform a status assessment on the user based on the current physiological state scenario and the matching degree to obtain the user's physiological state assessment result.

[0028] Optionally, the server 102 may also send the user's physiological state assessment results to the terminal device 101, so that the terminal device 101 outputs the physiological state assessment results.

[0029] It should be noted that in the specific implementation of this application, if physiological data, physiological state scenarios, or other data or information involve objects, when the embodiments of this application are applied to specific products or technologies, permission or consent from the objects is required, and the collection, use, and processing of related data or information must comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0030] Based on the implementation principle of the above technical solution, this application also provides a method for assessing physiological state. A flowchart of this method can be found here. Figure 2 And this method can be derived from the aforementioned Figure 1 The physiological state assessment system mentioned above can be executed by either a terminal device or a server, or jointly by both. Specifically, the method will be explained using an example of execution by a terminal device. Figure 2 As shown, the method may specifically include the following steps S201 to S204: S201. Obtain the user's historical physiological data collected under each preset physiological state scenario, and calculate the user's blood pressure parameters for each preset physiological state scenario based on the historical physiological data corresponding to each preset physiological state scenario.

[0031] In this embodiment of the application, a physiological state scenario refers to a scenario used to characterize a user's specific physiological or behavioral state. A preset physiological state scenario refers to a pre-set physiological state scenario. For example, a preset physiological state scenario may include at least one of the following scenarios: morning scenario, bedtime scenario, daytime rest scenario, post-exercise recovery scenario, high-pressure work scenario, and emotionally stressful scenario.

[0032] Specifically, the morning scenario can include the time period after a user wakes up from sleep and before engaging in significant activity; the bedtime scenario can include the quiet time before a user prepares to fall asleep, reflecting a state of rest at night; the daytime rest scenario can include a short period of rest during the day when there is no activity, no eating, and the user's emotions are stable; the post-exercise recovery period scenario can include the time window after a user completes exercise (e.g., within 6 hours), during which physiological data (e.g., blood pressure, heart rate) are in the process of recovering from exercise stress; the high-pressure work scenario can include the time period when a user is under high-intensity workload or cognitive stress; and the emotional stress scenario can include the time period when a user experiences emotional fluctuations such as anxiety and tension, which can be determined with the help of physiological data (e.g., heart rate variability, skin conductance activity).

[0033] Furthermore, in the embodiments of this application, physiological data may specifically include blood pressure data. In addition, physiological data may also include at least one of the following: heart rate data, body temperature data, and other physiologically related data of the human body or object. This application does not impose any limitations on these data. Optionally, physiological data may also include at least one of the following: the time of collection of physiological data, the physiological state of the user at the time of collection, etc. This application does not impose any limitations on these data.

[0034] Historical physiological data can specifically include physiological data of users collected in the past. More specifically, historical physiological data can include physiological data of users collected within a first preset time period from the current time, corresponding to each preset physiological state scenario. The first preset time period can be manually set, or it can be set by the server or terminal device in the aforementioned system; this application does not limit this setting.

[0035] For example, the first preset time period may include 7 to 30 days; then, the acquired historical physiological data may include: physiological data collected within the past 7 to 30 days when the user was in each preset physiological state scenario. Preferably, the first preset time period may include 14 days; then, the acquired historical physiological data may include: physiological data collected within the past 14 days when the user was in each preset physiological state scenario.

[0036] Each time physiological data is collected from a user, the user's physiological state scenario can be obtained, and the collected physiological data and the obtained physiological state scenario are stored accordingly. Therefore, there is a correspondence between the preset physiological state scenario and historical physiological data.

[0037] Furthermore, in this embodiment, the blood pressure parameters of the user for each preset physiological state scenario are used to characterize the blood pressure reference value or blood pressure reference range of the user in each preset physiological state scenario.

[0038] Specifically, the smaller the difference between the physiological data collected under each preset physiological state scenario and the blood pressure parameter under each preset physiological state scenario, the closer the user's physiological state under each preset physiological state scenario is to the user's normal physiological state. Therefore, the blood pressure parameter serves as a benchmark for assessing whether the collected physiological data deviates from the user's normal physiological state.

[0039] In a specific embodiment, the specific calculation process of the user's blood pressure parameters for each preset physiological state scenario may include: for each preset physiological state scenario, obtaining the historical physiological data collected when the user was in that preset physiological state scenario within a first preset time period from the current time; and performing statistical processing based on the obtained historical physiological data to obtain the user's blood pressure parameters for each preset physiological state scenario.

[0040] Optionally, the statistical processing may include calculating at least one of the values ​​that can characterize the average level of the historical physiological data, such as the mean and standard deviation, and using the calculation results as the user's blood pressure parameter for each preset physiological state scenario.

[0041] Optionally, the specific process of statistically processing the acquired historical physiological data may also include: deleting invalid data from the acquired historical physiological data to obtain updated historical physiological data; and then performing statistical processing on the updated historical physiological data to obtain the user's blood pressure parameters for each preset physiological state scenario.

[0042] Invalid data refers to data whose quality is below a preset quality threshold. The quantity and quality of each historical physiological data point can be evaluated from at least one dimension, such as data completeness, data rationality, and signal-to-noise ratio, which will not be elaborated here.

[0043] Optionally, since the user's physiological data is continuously collected, in this embodiment of the application, step S201 can be triggered periodically or irregularly to update the blood pressure parameters for each preset physiological state scenario in a timely manner, so that the blood pressure parameters can be updated accordingly to adapt to changes in the user's physiological state.

[0044] For example, taking physiological data including blood pressure data as an example; for each preset physiological state scenario, the terminal device can read blood pressure data collected from the user within the past 7 to 30 days when the user is in each preset physiological state scenario. Preferably, the terminal device can read blood pressure data collected from the user within the past 14 days when the user is in each preset physiological state scenario, and delete invalid data from the read blood pressure data, thereby obtaining N valid blood pressure data collected within the past 14 days; where N is a positive integer.

[0045] A single blood pressure reading can specifically include one systolic pressure and one diastolic pressure; therefore, N blood pressure readings can contain N systolic pressures and N diastolic pressures.

[0046] In practice, the blood pressure parameter for systolic pressure can be called baseline systolic pressure, and the calculation formula for baseline systolic pressure BaseSYS can be shown in the following formula (1):

[0047] in, The i-th systolic pressure is represented by the positive integer i, which is less than or equal to N.

[0048] Furthermore, the blood pressure parameter for diastolic pressure can be called baseline diastolic pressure, and the specific formula for calculating baseline diastolic pressure (BaseDIA) is as follows (2):

[0049] in, The j-th diastolic pressure is represented by the positive integer j, which is less than or equal to N.

[0050] S202. If the user's current physiological data is collected, then the user's current physiological state scenario is obtained.

[0051] In the embodiments of this application, the terminal device or server in the above system may trigger the collection of the user's current physiological data periodically or irregularly, or the user may trigger the collection of their own current physiological data. This application does not limit this.

[0052] In a specific embodiment, the process of obtaining the user's current physiological state scenario may include: obtaining the collection time of the current physiological data and obtaining the user's behavioral state data; then, determining the user's current physiological state scenario based on the current physiological data, the collection time of the current physiological data, and the obtained behavioral state data.

[0053] Specifically, as can be seen from the physiological state scenarios mentioned in step S201 above, each physiological state scenario is related to the user's behavioral state (such as whether they have been sleeping recently, whether they have been exercising recently, etc.), and each physiological state scenario is also closely related to time; therefore, based on the current physiological data and its collection time, as well as the acquired behavioral state data, it is possible to accurately determine the user's current physiological state scenario.

[0054] The acquired behavioral state data may include: the user's behavioral state data collected at the current physiological data collection time. Optionally, the acquired behavioral state data may include: the user's behavioral state data collected within a second preset time interval from the current time.

[0055] Specifically, user behavior status data can include user behavior status data under preset attribute dimensions. These preset attribute dimensions can include at least one of the following dimensions used to characterize a user's behavior or status: activity dimension, sleep dimension, physiological stress dimension, etc.

[0056] Specifically, user behavior data in the dimension of movement can be simply referred to as movement data; and movement data can include at least one of the following: movement time, movement duration, movement intensity level, number of steps, and amount of movement.

[0057] User behavior data in the sleep dimension can be simply referred to as sleep data; and sleep data can specifically include at least one of the following data used to describe sleep status: sleep duration, sleep efficiency, deep sleep status, light sleep status, sleep onset time, wake-up time, etc.

[0058] User behavior data under physiological stress can be referred to as stress data; and stress data can specifically include at least one of the following: stress index measured and output by smart wearable devices, heart rate variability inference results, stress level, and duration of high stress.

[0059] S203. Calculate the degree of matching between the current physiological data and the blood pressure parameters corresponding to the current physiological state scenario.

[0060] In this embodiment of the application, the specific calculation process of the matching degree may include: calculating the data difference between the current physiological data and the blood pressure parameter corresponding to the current physiological state scenario; and obtaining the matching degree between the current physiological data and the blood pressure parameter corresponding to the current physiological state scenario based on the data difference.

[0061] Optionally, the calculated data difference can be directly used as the matching degree between the current physiological data and the blood pressure parameter corresponding to the current physiological state scenario; alternatively, the data difference can be normalized, linearly mapped, or otherwise mathematically processed first, and then the processed value can be used as the matching degree between the current physiological data and the blood pressure parameter corresponding to the current physiological state scenario. This application does not limit this.

[0062] Optionally, the specific process of obtaining the matching degree based on the data difference may include: obtaining the data fluctuation tolerance corresponding to the current physiological state scenario; and then, determining the matching degree between the current physiological data and the blood pressure parameter corresponding to the current physiological state scenario based on the data difference and the data fluctuation tolerance.

[0063] Among them, the data fluctuation tolerance refers to the allowable error range of physiological data compared to the corresponding blood pressure parameter in the current physiological state scenario.

[0064] Specifically, the data fluctuation tolerance can be obtained by setting a preset minimum threshold for the physiological data based on historical physiological data corresponding to the current physiological state scenario. This preset minimum threshold can be set manually based on experience, or it can be set by the terminal device or server in the aforementioned system based on the minimum value in historical physiological data; this application does not impose any limitations on this.

[0065] It should be noted that when physiological data includes data from at least two dimensions, the corresponding blood pressure parameters can be calculated for each dimension (such as the baseline systolic blood pressure for the systolic blood pressure dimension and the baseline diastolic blood pressure for the diastolic blood pressure dimension mentioned above); correspondingly, a data fluctuation tolerance can be set for each dimension of data.

[0066] Therefore, the data difference also includes the data difference between each dimension of the current physiological data and the corresponding blood pressure parameter. In this case, the specific process for determining the matching degree based on the data difference and data fluctuation tolerance can include: obtaining the data deviation parameter for each dimension based on the data difference and the corresponding data fluctuation tolerance in the current physiological data; then, weighted summing of the data deviation parameters for all dimensions in the current physiological data to obtain the matching degree between the current physiological data and the blood pressure parameter corresponding to the current physiological state scenario.

[0067] In the current physiological data, the weighting weights of the data deviation parameters corresponding to different dimensions can be the same or different, and this application does not limit this.

[0068] In the specific implementation, following the example in step S201, taking historical physiological data including historically collected blood pressure data as an example, the calculation formula for the data fluctuation tolerance TSYS of systolic blood pressure in the blood pressure data is as follows (3):

[0069] in, The standard deviation of systolic blood pressure in historically collected blood pressure data; A preset minimum threshold for characterizing systolic blood pressure.

[0070] Furthermore, the formula for calculating the diastolic blood pressure data fluctuation tolerance (TDIA) is shown in equation (4) below:

[0071] in, The standard deviation of diastolic blood pressure in historically collected blood pressure data; A preset minimum threshold for characterizing diastolic blood pressure.

[0072] The formula for calculating the matching degree B between the current blood pressure data and the blood pressure parameters of the current physiological state scenario is as follows (5):

[0073] Wherein, D represents the blood pressure deviation index of the current blood pressure data compared to the blood pressure parameters of the current physiological state scenario. The formula for calculating D is shown in the following formula (6):

[0074] in, Characterizing the systolic blood pressure in the current blood pressure data, Characterizes the diastolic pressure in the current blood pressure data. The data deviation parameter characterizing the systolic blood pressure dimension. The data deviation parameter characterizing the diastolic blood pressure dimension.

[0075] Specifically, when the physiological data is blood pressure data, since systolic blood pressure is more sensitive to the daily fluctuations perceived by most users and the effects of exercise and stress, in a preferred embodiment, the weighted weight of the data deviation parameter corresponding to the systolic blood pressure dimension can be greater than the weighted weight of the data deviation parameter corresponding to the diastolic blood pressure dimension. Therefore, in this example, the weighted weight of the data deviation parameter corresponding to the systolic blood pressure dimension is 0.6, and the weighted weight of the data deviation parameter corresponding to the diastolic blood pressure dimension is 0.4.

[0076] By using 25 × D, the blood pressure deviation index can be mapped to a user-understandable score from 0 to 100, so as to transform the blood pressure deviation index from a single numerical difference into a standardized score that can be calculated in a unified manner with dimensions such as exercise, sleep, and physiological stress.

[0077] Optionally, the correspondence between the matching numerical range and the deviation description text can be pre-defined so that the target deviation description text corresponding to the matching numerical range to which the matching degree belongs can be obtained and output.

[0078] For example, the deviation description text corresponding to the matching numerical range [85,100] can be "physiological data is close to the individual's normal state"; the deviation description text corresponding to the matching numerical range [70,84] can be "slight deviation"; the deviation description text corresponding to the matching numerical range [55,69] can be "significant deviation"; and the deviation description text corresponding to the matching numerical range [0,54] can be "high risk of continuous deviation".

[0079] S204. Based on the current physiological state scenario and matching degree, perform a status assessment on the user to obtain the user's physiological state assessment result.

[0080] In this embodiment of the application, the specific process of evaluating a user's status based on the current physiological state scenario and the matching degree may include: calculating the user's status evaluation parameters for the preset attribute dimension based on the user's behavioral state data under the preset attribute dimension; then, obtaining the preset weighted recombination corresponding to the current physiological state scenario; finally, based on the preset weighted recombination, weighting and summing the matching degree and the status evaluation parameters to obtain the user's physiological state evaluation result.

[0081] Among them, the status evaluation parameter is the evaluation value obtained by quantifying the user's behavioral status data under each preset attribute dimension. It is used to characterize the degree of contribution or drag of the behavioral status data under each preset attribute dimension to the stable physiological state of the user.

[0082] It should be noted that the second preset weights corresponding to the state evaluation parameters of different preset attribute dimensions can be the same or different, and this application does not limit this.

[0083] Specifically, as mentioned above, the preset attribute dimensions can include exercise, sleep, and physiological stress dimensions.

[0084] Taking the preset attribute dimension as the motion dimension as an example, the user's status evaluation parameters for the motion dimension (hereinafter referred to as motion evaluation parameters) can be calculated based on the user's behavioral state data (i.e., motion data) under the motion dimension. Among them, the motion evaluation parameters are used to assess whether the current physiological data is within a reasonable range of physiological data during the post-exercise recovery process.

[0085] Specifically, the user's exercise status can be assessed from at least one aspect of exercise load and exercise recovery degree based on the time difference between the user's most recent effective exercise and the current time, the intensity level of the most recent effective exercise, the duration of the most recent effective exercise, and the decline trend of post-exercise physiological data (such as blood pressure and heart rate), so as to obtain the user's exercise assessment parameters.

[0086] In practical applications, the calculation formula for motion evaluation parameters can be shown in the following formula (7):

[0087] in, The time proximity coefficient is used to represent the time proximity. For example, if the time difference between the user's most recent valid movement and the current time is within 0-2 hours, the time proximity coefficient can be 1.0; if the time difference is within 2-6 hours, the time proximity coefficient can be 0.7; if the time difference is within 6-12 hours, the time proximity coefficient can be 0.4; and if the time difference is more than 12 hours, the time proximity coefficient can be 0.1.

[0088] The exercise load score is determined by deducting points. For example, if the intensity level of the most recent effective exercise is low, the exercise load score can be 5 points; if the intensity level of the most recent effective exercise is medium, the exercise load score can be 12 points; if the intensity level of the most recent effective exercise is high, the exercise load score can be 20 points; if the duration of the most recent effective exercise exceeds 45 minutes, the exercise load score determined based on the intensity level of the most recent effective exercise can be increased (e.g., by adding another 5 to 10 points), thus obtaining the final exercise load score.

[0089] The delayed recovery score is characterized by a correlation between the degree of matching calculated based on current physiological data and the time difference between the most recent effective exercise and the current time. For example, when the time difference between the most recent effective exercise and the current time is less than 6 hours and the degree of matching is less than 70, the delayed recovery score can be between 10 and 20 points; when the time difference between the most recent effective exercise and the current time is greater than 6 hours and the degree of matching is still less than 70, the delayed recovery score can be between 20 and 30 points.

[0090] The recovery and decline score is represented by a bonus. For example, historical physiological data of the target can be collected from the end time of the most recent effective exercise to the current physiological data collection time, and the historical matching degree calculated based on the historical physiological data can be obtained. If the increase ratio of the matching degree calculated based on the current physiological data to the historical matching degree exceeds a preset ratio, the recovery and decline score can be within 5 to 15 points. If no effective physiological data is collected from the end time of the most recent effective exercise to the current physiological data collection time, the recovery and decline score can be set to 0.

[0091] Optionally, the correspondence between exercise scoring intervals and exercise recovery description texts can be pre-defined so that the target exercise recovery description text corresponding to the exercise scoring interval to which the exercise assessment parameters belong can be obtained and output.

[0092] For example, the exercise recovery description text corresponding to the exercise score interval [85,100] can be "Good recovery"; the exercise recovery description text corresponding to the exercise score interval [70,84] can be "Recovering"; the exercise recovery description text corresponding to the exercise score interval [55,69] can be "Delayed recovery"; and the exercise recovery description text corresponding to the exercise score interval [0,54] can be "Insufficient recovery".

[0093] Optionally, if no valid movement is detected within the previous 12 hours, the movement assessment parameters can be set in the range of 70-100.

[0094] Taking sleep as a preset attribute dimension as an example, user status evaluation parameters (hereinafter referred to as sleep evaluation parameters) can be calculated based on user behavioral state data (i.e., sleep data) under the sleep dimension. These sleep evaluation parameters characterize the degree to which a user's sleep supports a stable physiological state.

[0095] Specifically, sleep assessment parameters can be calculated based on at least one of the user's sleep data, such as sleep duration, sleep quality score, and sleep regularity indicators.

[0096] In practical applications, the calculation formula for sleep assessment parameters can be shown in the following formula (8):

[0097] in, The sleep duration is deducted as follows: For example, if the duration of the most recent sleep is 7 to 9 hours, the sleep duration deduction can be between 0 and 5 points; if the duration of the most recent sleep is 6 to 7 hours, the sleep duration deduction can be 10 points; if the duration of the most recent sleep is 5 to 6 hours, the sleep duration deduction can be 20 points; and if the duration of the most recent sleep is less than 5 hours, the sleep duration deduction can be 30 points.

[0098] The sleep quality score is deducted. For example, if a user wakes up more times than a preset number of times, has a sleep efficiency lower than a preset number of times, or has a deep sleep duration shorter than a preset number of times during their most recent sleep period, the sleep quality score can be deducted between 5 and 20 points.

[0099] Deducting points for sleep patterns. For example, a user's historical sleep time (including at least one of historical sleep onset time and historical wake-up time) can be obtained, and the user's average sleep time can be calculated based on the historical sleep time. If the difference between the user's most recent sleep time and the average sleep time is greater than a preset duration, a sleep pattern deduction can be set between 5 and 10 points. The preset duration can be greater than or equal to 1 hour and less than or equal to 1.5 hours.

[0100] Optionally, the correspondence between sleep score intervals and sleep recovery description texts can be pre-defined so that the target sleep recovery description text corresponding to the sleep score interval to which the sleep assessment parameters belong can be obtained and output.

[0101] For example, the sleep recovery description text corresponding to the sleep score range [85,100] can be "Sleep supports physiological recovery"; the sleep recovery description text corresponding to the sleep score range [70,84] can be "Sleep basically supports physiological recovery"; the sleep recovery description text corresponding to the sleep score range [55,69] can be "Sleep hinders physiological recovery"; and the sleep recovery description text corresponding to the sleep score range [0,54] can be "Sleep significantly hinders physiological recovery".

[0102] Taking physiological stress as a preset attribute dimension as an example, the user's status assessment parameters (hereinafter referred to as stress assessment parameters) can be calculated based on the user's behavioral state data (i.e., stress data) under the physiological stress dimension. Among them, stress assessment parameters are used to characterize the degree to which physiological stress factors boost the user's current physiological data or hinder the recovery of physiological state.

[0103] Specifically, stress assessment parameters can be calculated based on at least one of the following stress data: user stress index, heart rate variability inference results, subjective questionnaire feedback, or continuous high-pressure duration.

[0104] In practical applications, the formula for calculating pressure assessment parameters can be shown in equation (9) below:

[0105] in, Deduct points to represent stress level. For example, if a user's current stress index is between 60 and 79, the stress level will be deducted by 15 points; if the user's current stress index is 80 or above, the stress level will be deducted by 25 points; if the user's current stress index is in the mild stress range (e.g., 40 to 59), the stress level will be deducted by 5 to 10 points.

[0106] Points are deducted for sustained high stress. For example, if a user's sustained high stress lasts for more than 2 hours but no more than half a day, the sustained high stress score will be 5 to 10 points; if the user's sustained high stress lasts for more than half a day, the sustained high stress score will be 10 to 15 points.

[0107] The relaxation correction score is calculated. For example, high-pressure physiological data measured when the user is in a high-pressure state and low-pressure physiological data measured when the user relaxes and rests after being in a high-pressure state can be obtained. A first difference between the high-pressure physiological data and the blood pressure parameter corresponding to the current physiological state data, and a second difference between the low-pressure physiological data and the blood pressure parameter corresponding to the current physiological state data can be calculated. If the second difference is less than the first difference, and the difference between the first difference and the second difference is greater than a preset value, it can be determined that the physiological data of the user when relaxing and resting has significantly decreased towards the user's normal state (i.e., blood pressure parameter) compared to the physiological data of the user when in a high-pressure state. Therefore, the relaxation correction score can be 5 to 10 points.

[0108] Specifically, Equation (9) limits the stress assessment parameter to a scoring range of 0 to 100 through the min and max functions. The higher the parameter value of the stress assessment parameter, the smaller the interference of the stress factor on the physiological homeostasis. The lower the parameter value of the stress assessment parameter, the greater the adverse effect of the stress factor on the current physiological state.

[0109] Optionally, the correspondence between stress scoring intervals and stress recovery description texts can be pre-defined so that the target stress recovery description text corresponding to the scoring interval to which the stress assessment parameters belong can be obtained and output.

[0110] For example, the pressure recovery description text corresponding to the pressure score interval [85,100] can be "low pressure impact"; the pressure recovery description text corresponding to the pressure score interval [70,84] can be "moderate pressure impact"; the pressure recovery description text corresponding to the pressure score interval [55,69] can be "significant pressure impact"; and the pressure recovery description text corresponding to the pressure score interval [0,54] can be "significant impact of high pressure".

[0111] In this embodiment, the preset weighting reassembly includes preset weights for matching degree and preset weights for state evaluation parameters. The preset weighting reassemblies corresponding to different physiological state scenarios can be the same or different; this application does not impose any limitations on this. In specific implementations, a corresponding preset weighting reassembly can be configured for each preset physiological state scenario.

[0112] Optionally, since the matching degree is a benchmark for evaluating whether the collected physiological data deviates from the user's normal physiological state, the preset weight for the matching degree in each preset weighting group can be greater than or equal to the preset weight for the state evaluation parameter.

[0113] Optionally, as mentioned above, the state evaluation parameters are for preset attribute dimensions. If the preset attribute dimensions include at least two, then the corresponding state evaluation parameters will also include at least two.

[0114] Therefore, the preset weighting configuration for each preset physiological state scenario can specifically include: preset weights set for matching degree and preset weights set for state evaluation parameters corresponding to at least two preset attribute dimensions.

[0115] For example, taking preset attribute dimensions including exercise, sleep, and physiological stress as an example, a preset weighted reassembly can be obtained for the current physiological state scenario. ={wB0, wE0, wS0, wP0}. Where wB0+wE0+wS0+wP0=1.

[0116] wB0 is the first preset weight corresponding to the matching degree B in the current physiological state scenario; wE0 is the second preset weight corresponding to the exercise assessment parameter E in the current physiological state scenario; wS0 is the second preset weight corresponding to the sleep assessment parameter S in the current physiological state scenario; wP0 is the second preset weight corresponding to the stress assessment parameter P in the current physiological state scenario.

[0117] By using preset weighted reorganizations corresponding to each preset physiological state scenario, the initial interpretation priority of each physiological impact parameter under different preset physiological state scenarios can be reflected. The physiological impact parameters include at least one of the following: matching degree and state evaluation parameters corresponding to each preset attribute dimension.

[0118] Specifically, the degree to which the same physiological parameter affects a user's physiological state varies depending on the physiological state scenario. For example, in the morning scenario, the user has just finished sleeping at night, and current physiological data (such as blood pressure) is more easily affected by the previous night's sleep duration, sleep quality, deep sleep ratio, nighttime awakenings, and wake-up regularity; exercise usually has a weaker impact on current physiological data; and although the user has not yet fully entered the work state for the day, their current physiological data may still be affected by stress such as tension and anxiety after waking up, work expectation pressure, residual effects of high blood pressure from the previous day, or sympathetic nerve excitation in the morning.

[0119] Therefore, in the morning scenario, the preset weight corresponding to the sleep assessment parameter S can be higher than the preset weight corresponding to the exercise assessment parameter E, and the preset weight corresponding to the sleep assessment parameter S can be higher than the preset weight corresponding to the stress assessment parameter P; while the preset weight corresponding to the stress assessment parameter P can be higher than the preset weight corresponding to the exercise assessment parameter E. Meanwhile, since the matching degree B is the benchmark for assessing physiological state, the preset weight corresponding to the matching degree B can be greater than or equal to the preset weights corresponding to all preset attribute dimensions.

[0120] The current physiological data collected from users in the pre-sleep scenario is typically influenced by the day's exercise load, accumulated stress, and sleep readiness. From a health management product perspective, the current physiological data collected in the pre-sleep scenario reflects whether the body has entered a stable state suitable for nighttime recovery and is highly correlated with sleep regularity and nighttime recovery conditions. Therefore, in the pre-sleep scenario, the second preset weight of the sleep assessment parameter S can be increased, while the explanatory role of the stress assessment parameter P can be appropriately retained.

[0121] Specifically, in the bedtime scenario, the preset weight corresponding to the sleep assessment parameter S can be higher than the preset weight corresponding to the exercise assessment parameter E, and the preset weight corresponding to the sleep assessment parameter S can be higher than the preset weight corresponding to the stress assessment parameter P; while the preset weight corresponding to the stress assessment parameter P can be higher than the preset weight corresponding to the exercise assessment parameter E.

[0122] In the post-exercise recovery phase, changes in user physiological data have a stronger temporal proximity and explanatory power compared to the time of the most recent exercise, intensity level, duration of exercise, and the trend of blood pressure decline after exercise. If a user's physiological data (such as blood pressure and heart rate) are higher than the corresponding blood pressure parameters shortly after exercise, this phenomenon may be a normal physiological response after exercise; if the physiological data do not show a significant decline after a longer period, it may indicate a delayed recovery. Therefore, in the post-exercise recovery phase, the preset weight of the exercise assessment parameter E can be increased to avoid misjudging normal fluctuations in post-exercise physiological data as abnormal fluctuations, sleep problems, or stress problems.

[0123] Specifically, in the post-exercise recovery scenario, the preset weight corresponding to the exercise assessment parameter E can be higher than the preset weight corresponding to the sleep assessment parameter S, and the preset weight corresponding to the exercise assessment parameter E can be higher than the preset weight corresponding to the stress assessment parameter P.

[0124] In daytime resting scenarios, users are typically not in a post-exercise window, nor are they in a special state such as just waking up or about to go to sleep. Changes in users' physiological data may be influenced by the day's activity level, the previous night's sleep, and real-time stress levels. Therefore, the explanatory power of dimensions such as exercise, sleep, and physiological stress is relatively balanced. Specifically, in daytime resting scenarios, the preset weights for the exercise assessment parameter E, the sleep assessment parameter S, and the stress assessment parameter P can be the same.

[0125] In high-pressure work environments or emotionally stressful situations, stress indices, duration of continuous high stress, changes in heart rate variability, or subjective stress scores are more explanatory of fluctuations in current physiological data. Therefore, in high-pressure work environments or emotionally stressful situations, the second preset weight corresponding to the stress assessment parameter P can be appropriately increased. Specifically, in high-pressure work environments or emotionally stressful situations, the preset weight corresponding to the stress assessment parameter P can be greater than the preset weight corresponding to the sleep assessment parameter S, and the preset weight corresponding to the stress assessment parameter P can be greater than the preset weight corresponding to the exercise assessment parameter E.

[0126] In some embodiments, the specific process of obtaining the user's physiological state assessment result may include: multiplying the matching degree by a preset weight in a preset weighted reassembly to obtain a first product result; multiplying the state assessment parameter by a preset weight in a preset weighted reassembly to obtain a second product result; and finally, adding the first product result and the second product result to obtain the user's physiological state assessment result.

[0127] It is understandable that subsequent steps involving weighted summation can all be implemented by weighted summation of physiological influence parameters in the manner shown in this embodiment.

[0128] In other embodiments, the specific process of obtaining the user's physiological state assessment result by weighted summation of matching degree and state evaluation parameters based on preset weighted reassembly may include: First, analyzing at least one of the following from a preset correction dimension: behavioral state data, current physiological data, historical physiological data corresponding to each preset physiological state scenario, state evaluation parameters, and historical matching degree between historical physiological data corresponding to the current physiological state scenario and blood pressure parameters corresponding to the current physiological state scenario, to obtain the correction coefficient of each preset weight in the preset weighted reassembly; updating the corresponding preset weight in the preset weighted reassembly according to the correction coefficient of each preset weight to obtain the target weighted reassembly; and weighted summation of matching degree and state evaluation parameters based on the target weighted reassembly to obtain the user's physiological state assessment result.

[0129] The preset correction dimensions include at least one of the following: data integrity dimension, data collection timeliness dimension, abnormal parameter dimension of state assessment parameters, data impact dimension of behavioral state data on current physiological data, and abnormal matching degree dimension of historical matching degree.

[0130] Specifically, the data completeness dimension refers to the dimension used to assess the completeness and reliability of data. When the source data corresponding to any physiological impact parameter has missing data (such as no sleep data within the last 7 days), low data quality (such as the data quality of the collected data being lower than the preset quality threshold), or insufficient reliability (such as the data collection device being unreliable, or the data not being confirmed by the user), the weight reduction correction coefficient (i.e., the correction coefficient used to reduce the preset weight) can be used as the correction coefficient corresponding to that physiological impact parameter.

[0131] In this embodiment, by analyzing the data integrity dimension, the weight of physiological impact parameters obtained from incomplete or unreliable data can be reduced, which is conducive to obtaining more accurate physiological state assessment results.

[0132] As mentioned above, the physiological impact parameters include at least one of the matching degree and the state assessment parameters corresponding to each preset attribute dimension. Accordingly, when any physiological impact parameter is the matching degree, the source data corresponding to any physiological impact parameter includes at least one of historical physiological data and current physiological data used to calculate the matching degree; when any physiological impact parameter is a sleep assessment parameter, the source data corresponding to any physiological impact parameter includes sleep data used to calculate the sleep assessment parameter; when any physiological impact parameter is a stress assessment parameter, the source data corresponding to any physiological impact parameter includes stress data used to calculate the stress assessment parameter; when any physiological impact parameter is an exercise assessment parameter, the source data corresponding to any physiological impact parameter includes exercise data used to calculate the exercise assessment parameter, which will not be elaborated further in this application.

[0133] Optionally, if the correction coefficient corresponding to any physiological influence parameter is a weight reduction correction coefficient, then the weight difference between the updated weight and the preset weight corresponding to any physiological influence parameter can be obtained after updating the preset weight according to the correction coefficient. Then, according to a preset allocation ratio, the preset weights corresponding to other physiological influence parameters are increased based on this weight difference to obtain the increased preset weights corresponding to the other physiological influence parameters. The total increase in the preset weights corresponding to the other physiological influence parameters can be equal to this weight difference, so that the sum of the preset weights corresponding to all physiological influence parameters remains unchanged.

[0134] Taking the sleep dimension as an example, if no recent valid sleep data of the user is collected (e.g., the user falls asleep without wearing the device), the input data for the sleep dimension is deemed insufficient. In this case, the preset weight corresponding to the sleep assessment parameter S can be reduced. Assuming the preset weight corresponding to the sleep assessment parameter S is reduced by 0.2, then this 0.2 can be allocated to at least one of the matching degree B, the exercise assessment parameter E, and the stress assessment parameter P according to the preset allocation ratio.

[0135] Taking a preset allocation ratio where the matching degree B corresponds to a ratio of 0.5, the exercise assessment parameter E corresponds to a ratio of 0.25, and the stress assessment parameter P corresponds to a ratio of 0.25 as an example, then the preset weight corresponding to the matching degree B can be increased by 0.1, the preset weight corresponding to the exercise assessment parameter E can be increased by 0.05, and the preset weight corresponding to the stress assessment parameter P can be increased by 0.05.

[0136] The data collection timeliness dimension refers to the dimension used to assess the time proximity between the current physiological data collection time and the collection time of the source data corresponding to each physiological influence parameter. Specifically, the time interval between the collection time of the source data corresponding to each physiological influence parameter and the current time is inversely correlated with the correction coefficient corresponding to each physiological influence parameter; the larger the correction coefficient, the greater the increase in the preset weight corresponding to each physiological influence parameter.

[0137] Specifically, in this embodiment, by analyzing the data collection timeliness dimension, it can be ensured that physiological impact parameters whose collection time is closer to the current physiological data collection time receive greater explanatory weight, so that subsequent parameter calculations conform to the physiological logic that "recent factors have a stronger explanatory power for the current state", which is conducive to obtaining more accurate physiological state assessment results.

[0138] Taking the exercise dimension as an example, if the current physiological data collection time is within the first preset time window after the most recent effective exercise in the exercise data (such as within 0 to 2 hours), it indicates that the data collection timeliness of the exercise assessment parameter E is high. Therefore, a higher correction coefficient can be assigned to the exercise assessment parameter E to increase the preset weight of the exercise assessment parameter E. If the collection time exceeds the first preset time window, it indicates that the data collection timeliness of the exercise assessment parameter E is not high. In this case, a lower or medium correction coefficient can be assigned to the exercise assessment parameter E to reduce or maintain the preset weight of the exercise assessment parameter E.

[0139] Taking the sleep dimension as an example, if the current physiological data collection time is within the second preset time window (e.g., within 0 to 1 hour) after the most recent sleep episode, it indicates that the data collection timeliness of sleep assessment parameter S is high. Therefore, a higher correction coefficient can be assigned to sleep assessment parameter S to increase its preset weight. Similarly, if the collection time exceeds the second preset time window, it indicates that the data collection timeliness of sleep assessment parameter S is low. In this case, a lower or medium correction coefficient can be assigned to sleep assessment parameter S to reduce or maintain its preset weight.

[0140] Taking the stress dimension as an example, if the current physiological data collection time is within the third preset time window after the occurrence of a stress event (such as detecting a high-pressure state), it indicates that the data collection timeliness of the stress assessment parameter P is high. Therefore, a higher correction coefficient can be assigned to the stress assessment parameter P to increase its preset weight. Similarly, if the collection time exceeds the third preset time window, it indicates that the data collection timeliness of the stress assessment parameter P is low. In this case, a lower or medium correction coefficient can be assigned to the stress assessment parameter P to reduce or maintain its preset weight.

[0141] The parameter anomaly dimension refers to the dimension used to assess whether the value of each physiological impact parameter is within an abnormal range. In practice, an anomaly threshold can be set for each physiological impact parameter. If any physiological impact parameter is less than the set anomaly threshold, it can be determined that the parameter is in an abnormal range, meaning that it significantly hinders or interferes with the stability of the physiological state (or homeostasis). In this case, the preset weight of the parameter can be increased to highlight its explanatory power for the deviation from the current physiological state. Therefore, if any physiological impact parameter is less than the set anomaly threshold, a correction coefficient can be generated to increase its weight, and this correction coefficient will be used as the correction coefficient for that physiological impact parameter.

[0142] Specifically, when a physiological influence parameter itself has shown obvious abnormalities, increasing its weight during the correction process helps to give the "abnormal physiological influence parameter" a higher explanatory power, thereby accurately reflecting the dominant role of the physiological influence parameter in the current physiological deviation, which is conducive to obtaining more accurate physiological state assessment results.

[0143] Optionally, multiple abnormality judgment thresholds (such as a first judgment threshold, a second judgment threshold, etc.) can be set for each physiological impact parameter, with different judgment thresholds corresponding to different weight increase magnitudes. Among them, the more severe the deviation of the physiological impact parameter from the normal range, the greater the weight increase magnitude.

[0144] Taking the sleep assessment parameter S as an example, when the sleep assessment parameter S is below 70 points, it indicates that sleep has hindered the recovery of physiological state, and a correction coefficient is generated to increase the preset weight corresponding to the sleep assessment parameter S. When the sleep assessment parameter S is below 55 points, it indicates that the degree of sleep hindrance has intensified, and at this time, a correction coefficient can be generated to increase the preset weight corresponding to the sleep assessment parameter S. Among the two generated correction coefficients, the latter is greater than the former.

[0145] Taking exercise assessment parameter E as an example, when exercise assessment parameter E is below 70 points and the current physiological data collection time is within the aforementioned first preset time window, it indicates that there is a delay in post-exercise recovery. At this time, a correction coefficient can be generated to increase the preset weight of exercise assessment parameter E. When exercise assessment parameter E is below 55 points, it indicates that exercise recovery is significantly insufficient. At this time, a correction coefficient can be further generated to further increase the preset weight of exercise assessment parameter E.

[0146] Taking the pressure assessment parameter P as an example, when the pressure assessment parameter P is below 70 points, it indicates that the pressure effect is already quite significant. At this time, a correction coefficient can be generated to increase the preset weight of the pressure assessment parameter P. When the pressure assessment parameter P is below 55 points, it indicates that the high pressure state has a greater impact. At this time, a correction coefficient can be generated to further increase the preset weight of the pressure assessment parameter P.

[0147] The data impact dimension refers to the dimension used to assess the historical correlation between behavioral state data and current physiological data. Specifically, based on the user's personal historical data (including at least one of the following: behavioral state data under each preset attribute dimension, historical physiological data corresponding to each preset physiological state scenario, and the historical matching degree between historical physiological data corresponding to the current physiological state scenario and the blood pressure parameter corresponding to the current physiological state scenario), the correlation degree between behavioral state data under each preset attribute dimension and current physiological data can be statistically analyzed, and the correction coefficient for the state assessment parameter corresponding to each preset attribute dimension can be determined based on this correlation degree.

[0148] The correlation degree is positively correlated with the determined correction coefficient. Simply put, the higher the statistical correlation degree, the more significant the behavioral state data of each preset attribute dimension has on the current user's individualization. In this case, the preset weight of the corresponding state evaluation parameter can be increased by a greater margin.

[0149] Taking the sleep dimension as an example, if a user's personal historical data shows that, over multiple periods, the user's historical physiological data measured upon waking after insufficient sleep has significantly deviated from the corresponding blood pressure parameter (i.e., low historical match), it indicates that the sleep dimension has a strong individualized correlation with the deviation of the user's physiological data upon waking. Therefore, if the current physiological state scenario is a morning scenario, a correction coefficient can be generated to increase the preset weight corresponding to the sleep assessment parameter S.

[0150] Taking the stress dimension as an example, if a user's personal historical data shows that multiple measurements of their historical physiological data after periods of high-pressure work significantly deviate from the corresponding blood pressure parameter (i.e., low historical match), it indicates that the physiological stress dimension has a strong individualized correlation with the user's physiological data. Therefore, if the current physiological state scenario is a high-pressure work scenario, a correction coefficient can be generated to increase the preset weight of the stress assessment parameter P.

[0151] The anomaly matching dimension refers to the dimension used to assess whether historical matching is abnormal. It can obtain the historical matching degree between historical physiological data and blood pressure parameters corresponding to the current physiological state scenario, and determine whether the historical matching degree meets the anomaly judgment criteria.

[0152] Specifically, the anomaly detection conditions include at least one of the following: multiple consecutive historical match scores are all less than the preset match score (i.e., the historical match score is consistently low); multiple consecutive historical match scores obtained under the same preset physiological state scenario are all less than the preset match score; the number of historical match scores less than the preset match score obtained within a fourth preset time window from the current time exceeds a preset number, etc. When the above anomaly detection conditions are met, a correction coefficient for increasing the preset weight of match score B can be generated to avoid prematurely judging the user's overall physiological state as well recovered due to a single or short-term improvement in behavioral state.

[0153] In the above embodiments, it is mentioned that a preset weighting reorganization can be configured for each preset physiological state scenario. In specific implementation, after obtaining the preset weighting reorganization configured for the current physiological state scenario, it is possible to further analyze at least one of the following from the preset correction dimension: behavioral state data, current physiological data, historical physiological data corresponding to each preset physiological state scenario, state evaluation parameters, and historical matching degree between historical physiological data corresponding to the current physiological state scenario and blood pressure parameters corresponding to the current physiological state scenario, to obtain the correction coefficient of each preset weight in the preset weighting reorganization corresponding to the current physiological state scenario; and, according to the correction coefficient of each preset weight, each preset weight is updated to obtain the target weight corresponding to each preset weight to obtain a target weighting reorganization containing the target weight corresponding to each preset weight.

[0154] For example, suppose the preset weighting configuration corresponding to the current physiological state scenario is as follows: ={wB0, wE0, wS0, wP0}, and from the above-mentioned data integrity dimension, data collection timeliness dimension, parameter anomaly dimension, data impact dimension, and matching degree anomaly dimension, the correction coefficients KB, KE, KS, and KP of wB0 can be obtained.

[0155] Then, the target weight wB corresponding to wB0, the target weight wE corresponding to wE0, the target weight wS corresponding to wS, and the target weight wP corresponding to wP0 can be calculated according to the following formula (10):

[0156] Where Z = wB0 × KB + wE0 × KE + wS0 × KS + wP0 × KP. Therefore, the target weight reorganization can be obtained. ={wB, wE, wS, wP}, and satisfy wB+wE+wS+wP=1.

[0157] In this embodiment of the application, the user's physiological state assessment result may specifically include at least one of physiological homeostasis assessment parameters and health status assessment parameters.

[0158] Among them, the physiological homeostasis assessment parameter is used to characterize the stability of the user's physiological state as reflected in the current physiological data. The health status assessment parameter is used to characterize the stability of the user's current overall health status. Specifically, the physiological homeostasis assessment parameter is positively correlated with the matching degree and positively correlated with the status assessment parameter, and the health status assessment parameter is positively correlated with the matching degree and positively correlated with the status assessment parameter. Therefore, the preset weighting reassembly may specifically include a first preset weighting reassembly used when calculating the physiological homeostasis assessment parameter, and a second preset weighting reassembly used when calculating the health status assessment parameter. The first preset weighting reassembly may include the preset weights corresponding to the matching degree when calculating the physiological homeostasis assessment parameter, and the preset weights corresponding to the status assessment parameter when calculating the physiological homeostasis assessment parameter; and the second preset weighting reassembly may include the preset weights corresponding to the matching degree when calculating the health status assessment parameter, and the preset weights corresponding to the status assessment parameter when calculating the health status assessment parameter.

[0159] Therefore, the specific process of obtaining the user's physiological state assessment result by weighted summing of matching degree and state assessment parameters based on a preset weighted reassembly may include: weighted summing of matching degree and state assessment parameters based on a first preset weighted reassembly to obtain the user's physiological homeostasis assessment parameters; weighted summing of matching degree and state assessment parameters based on a second preset weighted reassembly to obtain the user's health status assessment parameters; and generating the user's physiological state assessment result based on the physiological homeostasis assessment parameters and health status assessment parameters.

[0160] Optionally, the specific process of obtaining the user's physiological homeostasis assessment parameters by weighted summation of the matching degree and state evaluation parameters based on the first preset weighted reassembly may include: analyzing at least one of the following from a preset correction dimension: behavioral state data, current physiological data, historical physiological data corresponding to each preset physiological state scenario, state evaluation parameters, and historical matching degree between historical physiological data corresponding to the current physiological state scenario and blood pressure parameters corresponding to the current physiological state scenario, to obtain the correction coefficient of each preset weight in the first preset weighted reassembly; then, updating the corresponding preset weight in the first preset weighted reassembly according to the correction coefficient of each preset weight in the first preset weighted reassembly to obtain the first target weighted reassembly; finally, weighted summation of the matching degree and state evaluation parameters based on the first target weighted reassembly to obtain the user's physiological homeostasis assessment parameters.

[0161] Optionally, the specific process of obtaining the user's health status assessment parameters by weighted summing of the matching degree and status assessment parameters based on the second preset weighting may include: analyzing at least one of the following from a preset correction dimension: behavioral status data, current physiological data, historical physiological data corresponding to each preset physiological state scenario, status assessment parameters, and historical matching degree between historical physiological data corresponding to the current physiological state scenario and blood pressure parameters corresponding to the current physiological state scenario, to obtain the correction coefficient of each preset weight in the second preset weighting; then, updating the corresponding preset weights in the second preset weighting according to the correction coefficient of each preset weight in the second preset weighting to obtain the second target weighting; finally, weighted summing of the matching degree and status assessment parameters based on the second target weighting to obtain the user's health status assessment parameters.

[0162] It should be noted that the specific methods for determining the correction coefficients of each preset weight in the first preset weight reorganization and the correction coefficients of each preset weight in the second preset weight reorganization can be found in the methods for determining the correction coefficients in the above embodiments, and will not be repeated here.

[0163] Specifically, the matching degree between the current physiological data and the blood pressure parameter corresponding to the current physiological state scenario reflects the degree of deviation of the current physiological data from the user's historical normal state in the same scenario. It is a direct basis for determining whether the user's physiological state has returned to normal. Therefore, in the preset weighting reassembly corresponding to each physiological state scenario, the preset weight of the matching degree can be kept at a high value. The goal of the physiological homeostasis assessment parameter is to directly assess whether "the current physiological data has returned to the user's normal state." Therefore, in the first preset weighting reassembly corresponding to each physiological state scenario, the preset weight of the matching degree can be the maximum weight in the first preset weighting reassembly.

[0164] Meanwhile, the goal of the health status assessment parameters is to assess whether the user's current overall health status is stable. The user's behavioral status has a greater impact on the overall health status. Therefore, the preset weight of the status assessment parameters in the second preset weight reassembly corresponding to each physiological state scenario can be larger than the preset weight of the status assessment parameters in the first preset weight reassembly corresponding to each physiological state scenario.

[0165] In some embodiments, the specific process of generating a user's physiological state assessment result based on physiological homeostasis assessment parameters and health status assessment parameters may include: determining a joint influence parameter based on the numerical range of the state assessment parameters and the numerical range of the matching degree; then, updating the physiological homeostasis assessment parameters and health status assessment parameters according to the joint influence parameter to obtain updated physiological homeostasis assessment parameters and updated health status assessment parameters; finally, generating the user's physiological state assessment result based on the updated physiological homeostasis assessment parameters and updated health status assessment parameters.

[0166] The user's physiological state assessment results may include updated physiological homeostasis assessment parameters and updated health status assessment parameters.

[0167] Optionally, a correspondence between numerical intervals and candidate parameter values ​​of the joint impact parameter can be established in advance; then, the first candidate parameter value corresponding to the numerical interval to which the state assessment parameter belongs, and the second candidate parameter value corresponding to the numerical interval to which the matching degree belongs can be obtained; then, the first candidate parameter value and the second candidate parameter value are added together to obtain the joint impact parameter.

[0168] Optionally, other numerical ranges can be set as judgment conditions or correspondences with the joint impact parameters, so as to determine the joint impact parameters through the set judgment conditions and correspondences.

[0169] Optionally, the following parameters can be used to illustrate the effects: matching score B, sleep assessment parameter S, exercise assessment parameter E, and stress assessment parameter P. When S is between 0 and 55 and P is between 0 and 60, it indicates that the user is sleep-deprived and under high stress, and the combined effect parameter I can be increased by 8 points. When E is between 0 and 70 and S is between 0 and 60, it indicates that the user is not fully recovered after exercise and is sleep-deprived, and the combined effect parameter I can be increased by 8 points. When the historical matching score obtained for two consecutive days is lower than 60 or the matching score obtained for three consecutive times under the current physiological state is lower than 60, the combined effect parameter I can be increased by another 10 points.

[0170] Taking a sleep assessment parameter S of 50, an exercise assessment parameter E of 68, and a stress assessment parameter P of 55 as an example, since S is in the range of 0-55 and P is in the range of 0-60, the combined influence parameter I can be increased to 8; and since E is in the range of 0-70 and S is in the range of 0-60, we can add 8 more to the base of 8, so the final combined influence parameter I = 16.

[0171] In one specific embodiment, physiological homeostasis assessment parameters can be calculated directly based on a first preset weighted recombination, and health status assessment parameters can be calculated directly based on a second preset weighted recombination.

[0172] Taking the first preset weighting set as {0.55, 0.20, 0.15, 0.10} and the second preset weighting set as {0.40, 0.20, 0.20, 0.20} as examples, the calculation formula for the physiological homeostasis assessment parameter R is shown in the following formula (11):

[0173] Furthermore, the formula for calculating the health status assessment parameter H is shown in equation (12) below:

[0174] In another specific embodiment, physiological homeostasis assessment parameters can be calculated based on the first target weighted recombination obtained by updating the first preset weighted recombination, and health status assessment parameters can be calculated based on the second target weighted recombination obtained by updating the second preset weighted recombination.

[0175] Therefore, the formula for calculating the physiological homeostasis assessment parameter R_s is as follows (13):

[0176] Where s represents the current physiological state scenario; wB_Rs, wE_Rs, wS_Rs, and wP_Rs are the first target weight reorganizations used to calculate R_s.

[0177] Furthermore, the formula for calculating the health status assessment parameter H_s is shown in equation (14) below:

[0178] Among them, wB_Hs, wE_Hs, wS_Hs, and wP_Hs are the second target weight reorganizations used to calculate H_s.

[0179] In some possible implementations, as mentioned above, the physiological state assessment results include physiological homeostasis assessment parameters. Then, after obtaining the user's physiological state assessment results, the target homeostasis description text corresponding to the parameter range to which the physiological homeostasis assessment parameters belong in the physiological state assessment results can be obtained according to the pre-set correspondence between parameter ranges and homeostasis description texts. Then, a physiological data analysis interface containing physiological homeostasis assessment parameters and target homeostasis description texts is displayed.

[0180] Specifically, by displaying a physiological data analysis interface that simultaneously includes physiological homeostasis assessment parameters and target homeostasis description text, users can clearly understand whether their physiological state is in a normal state and the recovery status of their physiological state based on the target homeostasis description text, further reducing the user's understanding cost of physiological homeostasis assessment parameters.

[0181] For example, the steady-state description text corresponding to the parameter range [85,100] can be set to "Good recovery"; the steady-state description text corresponding to the parameter range [70,84] can be set to "Recovering in progress"; the steady-state description text corresponding to the parameter range [55,69] can be set to "Slow recovery"; the steady-state description text corresponding to the parameter range [40,54] can be set to "Insufficient recovery"; and the steady-state description text corresponding to the parameter range [0,39] can be set to "High recovery risk".

[0182] Optionally, as mentioned above, the physiological state assessment results may include health state assessment parameters. After obtaining the user's health state assessment parameters, the target health state description text corresponding to the parameter range to which the health state assessment parameters belong in the physiological state assessment results can be obtained according to the pre-set correspondence between parameter ranges and health state description texts. Then, a physiological data analysis interface containing health state assessment parameters and target health state description texts is displayed.

[0183] Specifically, by displaying a physiological data analysis interface that simultaneously includes health status assessment parameters and target health status description text, users can clearly understand their overall health status based on the target health status description text, further reducing the user's understanding cost of health status assessment parameters.

[0184] For example, the health status description text corresponding to the parameter range [85,100] can be set to "Good condition"; the health status description text corresponding to the parameter range [70,84] can be set to "Basically stable"; the health status description text corresponding to the parameter range [55,69] can be set to "Needs attention"; the health status description text corresponding to the parameter range [40,54] can be set to "Insufficient recovery"; and the health status description text corresponding to the parameter range [0,39] can be set to "Important reminder".

[0185] Optionally, as mentioned above, the physiological state assessment results may include physiological homeostasis assessment parameters and health status assessment parameters; then, a physiological data analysis interface containing physiological homeostasis assessment parameters, target homeostasis description text, health status assessment parameters, and target health status description text can be displayed.

[0186] Specifically, existing solutions lack a final overall health status output; what users are truly concerned about is not isolated raw values, but rather "how well my current physiological state (such as blood vessels, blood pressure, heart rate, etc.) is recovering," "whether I am in a good, stable, or needing attention state today," etc. This embodiment upgrades the physiological data collected in a single instance into a state result that users can understand, track, and make decisions about through a dual scoring mechanism of physiological homeostasis assessment parameters and health status assessment parameters; and further reduces the user's understanding cost through target homeostasis description text and target health status description text.

[0187] In some embodiments, at least one influencing attribution parameter may be obtained; then, based on the parameter size of the at least one influencing attribution parameter, a primary influencing attribution parameter and a secondary influencing attribution parameter for the physiological state assessment result may be determined from the at least one influencing attribution parameter; subsequently, an attribution description text for the physiological state assessment result may be obtained based on the primary influencing attribution parameter and the secondary influencing attribution parameter.

[0188] Among them, different influence attribution parameters are used to characterize the degree of influence of behavioral state data under different preset attribute dimensions on the physiological state assessment results. The number of primary influence attribution parameters may include at least one; the number of secondary influence attribution parameters may also include at least one.

[0189] The attribution description text may specifically include at least one of the following: a first text describing the preset attribute dimension corresponding to the main influencing attribution parameter as the main factor affecting physiological state; a second text describing the preset attribute dimension corresponding to the secondary influencing attribution parameter as the secondary factor affecting physiological state; and a third text describing the preset attribute dimension corresponding to the main influencing attribution parameter and the preset attribute dimension corresponding to the secondary influencing attribution parameter as a joint factor affecting physiological state.

[0190] Therefore, when displaying a physiological data analysis interface that includes physiological homeostasis assessment parameters and target homeostasis description text, it is also possible to display a physiological data analysis interface that includes physiological homeostasis assessment parameters, target homeostasis description text, and attribution description text.

[0191] Optionally, the largest of the attribution parameters can be determined as the primary attribution parameter; then, secondary attribution parameters can be obtained based on the other attribution parameters besides the primary attribution parameter.

[0192] Furthermore, all other attribution parameters can be treated as secondary attribution parameters, or the parameter with the largest impact among the other attribution parameters can be determined as a secondary attribution parameter.

[0193] In practical implementation, following the example above, after obtaining the four scores of B, E, S, and P, the corresponding influence attribution parameters can be obtained by combining the scene matching coefficient between each preset attribute dimension and different physiological state scenarios.

[0194] Specifically, the formula for calculating the influence attribution parameter Me corresponding to the motion dimension is shown in equation (15) below:

[0195] The motion scene matching coefficient can be obtained based on the time interval between the current time and the end time of the previous motion. For example, the motion scene matching coefficient can be set to 1 if the current time is within 6 hours after the end of the previous motion; 0.5 if the current time is between 6 and 12 hours after the end of the previous motion; and 0.2 in other cases.

[0196] The formula for calculating the attribution parameter Ms corresponding to the sleep dimension is shown in equation (16) below:

[0197] Among them, the matching coefficient of the sleep scene corresponding to the morning scene can be 1; the matching coefficient of the sleep scene corresponding to the bedtime scene can be 1.0; and the matching coefficient of the sleep scene corresponding to the other scenes can be 0.7.

[0198] The formula for calculating the attribution parameter Mp corresponding to the physiological stress dimension is shown in equation (17) below:

[0199] If recent stress data indicates that the user's stress is high (e.g., greater than the preset stress threshold), the stress scenario matching coefficient can be 1.0; otherwise, the stress scenario matching coefficient can be 0.6.

[0200] For example, if the matching score B is greater than or equal to 85 and Me, Ms, and Mp are all low, then attribution description text that characterizes the user's physiological state as close to their normal state can be generated; if the first parameter with the highest value among Me, Ms, and Mp is at least 10 points higher than the second parameter with the second highest value among Me, Ms, and Mp, then the first parameter can be used as the primary influencing attribution parameter; if the difference between the first parameter and the second parameter is less than 10 points, then the first parameter and the second parameter can be used as a joint influencing factor, and the first parameter and the second parameter can be labeled as the primary influencing attribution parameter and the secondary influencing attribution parameter respectively according to their numerical values.

[0201] In the morning scenario, if the sleep assessment parameter S is low, the stress assessment parameter P is low, and the sleep explanatory value Ms is higher than the stress explanatory value Mp, then an attribution description text indicating "sleep is the primary cause and stress is the secondary cause" can be generated. In the post-exercise recovery scenario, if the exercise explanatory value Me is high, the matching degree B is not high (i.e., the current blood pressure deviates from the individual's baseline to a certain extent), and the current time is still within the reasonable post-exercise recovery window, then an attribution description text indicating "exercise recovery in progress" can be generated. If both the exercise explanatory value Ms and the sleep explanatory value Ms are relatively high, then an attribution description text indicating "joint effect of exercise and sleep" can be generated, triggering a deduction for the joint effect.

[0202] If the matching degree B is low, but Me, Ms, and Mp are also low, it is not forcibly attributed to exercise, sleep, or stress. Instead, a prompt message indicating "abnormal fluctuations require retesting" can be generated. Thus, this embodiment avoids erroneously attributing unexplained physiological data fluctuations to behavioral states of a certain preset attribute dimension, improving the accuracy of cause explanation and product credibility.

[0203] In one feasible implementation, the physiological data analysis interface may include one of the following: physiological homeostasis assessment parameters, target homeostasis description text, health status assessment parameters, target health status description text, and attribution description text.

[0204] In one specific embodiment, the physiological state assessment results displayed on the physiological data analysis interface are divided into two aspects. One aspect is the physiological homeostasis assessment parameters, used to answer whether the current physiological data, relative to the user's baseline physiological data, has recovered, is recovering, is recovering slowly, or is recovering insufficiently. The other aspect is the attribution description text (i.e., the causes affecting the physiological state), used to answer whether the dominant, secondary, or combined factors leading to the current state are the primary, secondary, or combined factors. Therefore, in the physiological data analysis interface, users can not only see their current physiological state but also understand the reasons for this state and the direction for future lifestyle adjustments.

[0205] Optionally, when the physiological status assessment results indicate that the user is in a stable or healthy physiological state, the physiological data analysis interface can also display positive factors and maintenance suggestions, such as "Blood pressure is close to the user's normal level, sleep supports recovery" and "Blood pressure has dropped after exercise, it is recommended to maintain the current pace." When the physiological status assessment results indicate that the user is in an unstable physiological state or in a state requiring attention, the physiological data analysis interface can prioritize presenting negative factors and improvement suggestions, such as "Insufficient sleep slows down recovery, it is recommended to prioritize getting more sleep" and "Stress has a significant impact, it is recommended to increase relaxation or retest after high-pressure work." This stable / unstable feedback mechanism achieves a closed loop from data judgment to user action suggestions.

[0206] Taking blood pressure data as an example (using physiological data), please refer to the appendix. Figure 3 The diagram illustrates a blood pressure data analysis interface. Figure 3 As shown, the blood pressure data analysis interface 301 may include at least one of the following data: the current blood pressure measurement result (i.e., "most recent measurement: 124 / 79 mmHg"), vascular recovery degree (i.e., the name of the physiological homeostasis assessment parameter when the physiological data is blood pressure data, which is 91 points in the figure), overall health status (i.e., the health status assessment parameter, which is 90 points in the figure), blood pressure baseline matching score (i.e., the matching degree B when the physiological data is blood pressure data, which is 92 points in the figure), exercise recovery score (i.e., the exercise assessment parameter E, which is 90 points in the figure), sleep support score (i.e., the sleep assessment parameter S, which is 92 points in the figure), stress stability score (i.e., the stress assessment parameter P, which is 88 points in the figure), analysis of the causes of physiological state formation and health suggestions (corresponding to the content of area 302 in the figure).

[0207] Specifically, the top of the blood pressure data analysis interface 301 displays the immediate vascular recovery level and overall health status based on the blood pressure data obtained in this measurement. For example... Figure 3 As shown, the vascular recovery level is 91, indicating good recovery; and the overall health status is 90, indicating a good condition. Additionally, a summary of the user's current physiological state can be provided in a single explanatory sentence, such as... Figure 3 The results indicate that "blood pressure is close to normal, sleep is supporting recovery, stress has a low impact, and the current good condition should be maintained."

[0208] The blood pressure data analysis interface 301 also displays the blood pressure measurement result, the current physiological state scenario (morning in the image), and the measurement time (07:32 in the image). This allows users to understand which measurement, which measurement scenario, and when the system's judgment of their current physiological state is based.

[0209] The blood pressure data analysis interface 301 can also display baseline matching status display area 303, exercise recovery status display area 304, sleep support status display area 305, and pressure stability status display area 306. Each display area includes at least the name of the corresponding preset attribute dimension, the status assessment parameter of the corresponding preset attribute dimension, the descriptive text of the corresponding status assessment parameter (such as the deviation degree description text, exercise recovery description text, sleep recovery description text, or pressure recovery description text), a progress bar, and an explanatory sentence.

[0210] like Figure 3 As shown, the baseline matching display area 303 displays "Blood pressure baseline matching score 92 points, good matching, current blood pressure is close to the individual's baseline"; the exercise recovery display area 304 displays "Exercise recovery score 90 points, good recovery, no effective exercise in the past 12 hours, no significant impact on this blood pressure"; the sleep support display area 305 displays "Sleep support score 92 points, sleep support recovered, good sleep quality last night, providing good support for blood pressure recovery"; and the stress stability display area 306 displays "Stress stability score 88 points, low stress impact, current stress level is low, with little impact on blood pressure".

[0211] The area 302 at the bottom of the blood pressure data analysis interface 301 is used to display the attribution results and suggestions obtained based on B, E, S, P and the influencing attribution parameters Me, Ms, Mp.

[0212] Through the blood pressure data analysis interface described above, the calculated vascular recovery level, overall health status, factor scores, explanations of causes, and health recommendations can be presented to the user in a unified manner. This allows the user to not only see the blood pressure value, but also understand whether the current status is good, what factors mainly affect it, and whether improvement is needed.

[0213] In practical applications, a product system for processing physiological data can be built. This system may include a data access module, a scene recognition module, a baseline parameter calculation module, a matching degree calculation module, a movement assessment parameter calculation module, a sleep assessment parameter calculation module, a stress assessment parameter calculation module, a joint influence parameter calculation module, a physiological homeostasis assessment parameter calculation module, a health status assessment parameter calculation module, and an interface display module. The data access module is used to access the collected physiological data, behavioral status data, etc.

[0214] The modules in this product system can be deployed in Figure 1 The terminal devices or servers in the system shown can also be deployed in a distributed manner. Figure 1 The present application does not limit the terminal devices and servers in the system shown (i.e., some modules of the product system are deployed in the terminal devices and other modules are deployed in the servers).

[0215] In this embodiment, by calculating user-specific blood pressure parameters based on corresponding historical physiological data for each preset physiological state scenario, a personalized benchmark for the normal fluctuation range of a user's blood pressure can be established from the dual dimensions of physiological state scenario and individual differences. This fundamentally avoids individual bias caused by using a uniform threshold or population statistical mean. Furthermore, this embodiment matches the current physiological data collected from the user in the current physiological state scenario with the corresponding blood pressure parameters. By using the user's own longitudinal historical data as a reference, the interference of individual differences can be effectively eliminated, ensuring that the obtained matching degree accurately and truthfully reflects the degree of deviation of the current physiological data from the user's own normal benchmark.

[0216] In this way, subsequent embodiments of this application can combine the matching degree with the current physiological state scenario to evaluate the user's state. On the one hand, the degree of deviation represented by the matching degree can be used to accurately determine whether the user is in an abnormal or specific physiological state. On the other hand, the current physiological state scenario can be used to impose scenario constraints on the evaluation process to avoid the state evaluation result deviating from the actual situation.

[0217] Therefore, the physiological state assessment result obtained in this embodiment is generated by integrating the deviation of the current physiological data from the user's own blood pressure parameters under the constraints of the current physiological state scenario. Compared with the "data presentation" mode of traditional solutions that are based only on single data or uniform thresholds, this embodiment achieves a leap towards personalized, scenario-adaptive, and accurate state assessment, significantly improving the accuracy of physiological data analysis and thus greatly improving the accuracy and reliability of the physiological state assessment results.

[0218] Based on the aforementioned method embodiments, this application also proposes a physiological state assessment device, which can be mounted on an electronic device and used to achieve the above-mentioned... Figure 2 The described method embodiments include some or all of the functionalities. Specifically, a schematic structure of the device can be found in [reference needed]. Figure 4 .like Figure 4 The device may include: The data acquisition unit 401 is used to acquire the user's historical physiological data collected under each preset physiological state scenario, and to calculate the user's blood pressure parameters for each preset physiological state scenario based on the historical physiological data corresponding to each preset physiological state scenario. The scene acquisition unit 402 is used to acquire the current physiological state scene of the user if the user's current physiological data is collected. The matching degree calculation unit 403 is used to calculate the matching degree between the current physiological data and the blood pressure parameters corresponding to the current physiological state scenario; The result generation unit 404 is used to evaluate the user's status based on the current physiological state scenario and matching degree, and obtain the user's physiological state evaluation result.

[0219] In one implementation, when the result generation unit 404 performs a status assessment on the user based on the current physiological state scenario and the matching degree to obtain the user's physiological state assessment result, it can be specifically used for: Based on the user's behavioral state data under the preset attribute dimensions, calculate the user's state evaluation parameters for the preset attribute dimensions; wherein, the preset attribute dimensions include at least one of the following: exercise dimension, sleep dimension, and physiological stress dimension; Obtain the preset weighted recombination corresponding to the current physiological state scenario; the preset weighted recombination includes the preset weight of the matching degree and the preset weight of the state evaluation parameter; Based on the preset weighted recombination, the matching degree and the state evaluation parameters are weighted and added together to obtain the user's physiological state evaluation result.

[0220] In another embodiment, when the result generation unit 404 obtains the user's physiological state assessment result by weighted summation of the matching degree and the state assessment parameters based on the preset weighted reassembly, it can be specifically used for: The correction coefficient for each preset weight in the preset weighting is obtained by analyzing at least one of the following from the preset correction dimension: the behavioral state data, the current physiological data, the historical physiological data corresponding to each preset physiological state scenario, the state evaluation parameters, and the historical matching degree between the historical physiological data corresponding to the current physiological state scenario and the blood pressure parameters corresponding to the current physiological state scenario. The preset correction dimensions include at least one of the following: data integrity dimension, data collection timeliness dimension, parameter anomaly dimension of the state evaluation parameters, data influence dimension of the behavioral state data on the current physiological data, and anomaly dimension of the historical matching degree. Based on the correction coefficient of each preset weight, the corresponding preset weight in the preset weight reorganization is updated to obtain the target weight reorganization; Based on the target weighting, the matching degree and the state evaluation parameters are weighted and added together to obtain the user's physiological state evaluation result.

[0221] In another embodiment, the preset weighting recombination includes a first preset weighting recombination and a second preset weighting recombination; when the result generation unit 404 obtains the user's physiological state assessment result by weighted summation of the matching degree and the state assessment parameters based on the preset weighting recombination, it can specifically be used for: Based on the first preset weighted recombination, the matching degree and the state evaluation parameters are weighted and added together to obtain the user's physiological homeostasis evaluation parameters; Based on the second preset weighted recombination, the matching degree and the status evaluation parameters are weighted and added together to obtain the user's health status evaluation parameters; The physiological state assessment result of the user is generated based on the physiological homeostasis assessment parameters and the health status assessment parameters.

[0222] In another embodiment, when the result generation unit 404 generates the user's physiological state assessment result based on the physiological homeostasis assessment parameters and the health state assessment parameters, it can be specifically used for: Based on the numerical range of the state assessment parameters and the numerical range of the matching degree, the joint influence parameters are determined; Based on the joint influence parameters, the physiological homeostasis assessment parameters and the health status assessment parameters are updated to obtain the updated physiological homeostasis assessment parameters and the updated health status assessment parameters. Based on the updated physiological homeostasis assessment parameters and the updated health status assessment parameters, the user's physiological status assessment result is generated.

[0223] In another embodiment, when calculating the matching degree between the current physiological data and the blood pressure parameter corresponding to the current physiological state scenario, the matching degree calculation unit 403 can be specifically used for: Calculate the data difference between the current physiological data and the blood pressure parameter corresponding to the current physiological state scenario; Obtain the data fluctuation tolerance corresponding to the current physiological state scenario; The matching degree is determined based on the data difference and the data fluctuation tolerance.

[0224] In another embodiment, the physiological state assessment result includes physiological homeostasis assessment parameters; the result generation unit 404 can also be used to: obtain the target homeostasis description text corresponding to the parameter interval to which the physiological homeostasis assessment parameters belong, according to the pre-set correspondence between parameter intervals and homeostasis description text; The device may further include an interface display unit, which can be used to display a physiological data analysis interface containing the physiological homeostasis assessment parameters and the target homeostasis description text.

[0225] In another embodiment, the result generation unit 404 can also be used for: At least one influence attribution parameter is obtained; wherein, different influence attribution parameters are used to characterize the degree of influence of behavioral state data under different preset attribute dimensions on the physiological state assessment results; Based on the parameter magnitude of the at least one influencing attribution parameter, determine the primary and secondary influencing attribution parameters for the physiological state assessment results from the at least one influencing attribution parameter; Based on the primary influence attribution parameters and the secondary influence attribution parameters, the attribution description text of the physiological state assessment results is obtained; The interface display unit can also be used to display a physiological data analysis interface containing the physiological homeostasis assessment parameters, the target homeostasis description text, and the attribution description text.

[0226] In one embodiment, Figure 4 Each unit in the illustrated device can be individually or entirely combined into one or more other units, or some of the units can be further divided into multiple functionally smaller units. This achieves the same operation without affecting the technical effects of the embodiments of this application. In other words, the above units are based on logical function division. In practical applications, the function of one unit can be implemented by multiple units, or the function of multiple units can be implemented by one unit. In other embodiments of this application, Figure 4 The device shown may also include other units, and in practical applications, these functions may also be implemented with the assistance of other units, and may be implemented by multiple units working together.

[0227] According to another embodiment of this application, the following can be executed by running on a computing device including processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM). Figure 2 The computer program (including program code) involved in each step of the corresponding method shown, to construct such... Figure 4 The apparatus shown. A computer program may be recorded on, for example, a computer-readable storage medium, loaded onto the apparatus via the computer-readable storage medium, and executed therein.

[0228] Based on the description of the method and device embodiments above, this invention also provides an electronic device. Please refer to... Figure 5 The electronic device includes at least a processor 501, an input interface 502, an output interface 503, and a computer storage medium 504. The processor 501, input interface 502, output interface 503, and computer storage medium 504 within the electronic device can be connected via a bus or other means.

[0229] The computer storage medium 504 can be stored in the memory of the electronic device. The computer storage medium 504 is used to store computer programs, which include program instructions. The processor 501 is used to execute the program instructions stored in the computer storage medium 504. The processor 501 (or CPU (Central Processing Unit)) is the computing and control core of the electronic device. It is suitable for implementing one or more instructions, specifically for loading and executing one or more instructions to achieve corresponding method flows or corresponding functions.

[0230] In one embodiment, processor 501 may load and execute one or more computer programs stored in computer storage medium 502 to achieve the aforementioned related functions. Figure 3 The corresponding method steps in the method embodiments shown; in specific implementation, one or more computer programs in the computer storage medium 502 can be loaded by the processor 501 and executed in the method steps described in the above embodiments.

[0231] This application embodiment also provides a computer-readable storage medium (Memory), which is a memory device in a physiological state assessment device for storing programs and data. It is understood that the computer-readable storage medium here may include the built-in storage medium in the physiological state assessment device, or it may include extended storage media supported by the physiological state assessment device. The computer-readable storage medium provides storage space that stores the processing system of the physiological state assessment device. Furthermore, the storage space also stores one or more instructions suitable for loading and execution by the processor 501, which may be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here may be a high-speed RAM memory, or a non-volatile memory, such as at least one disk storage device; optionally, it may also be at least one readable storage medium located remotely from the aforementioned processor.

[0232] This application also provides a computer program product, which includes computer instructions. The processor of the physiological state assessment device can execute the above-described method embodiments by loading the computer instructions.

[0233] Based on the same inventive concept, the principles and beneficial effects of the devices, physiological state assessment equipment, computer-readable storage media and computer program products provided in the embodiments of this application are similar to those described in the foregoing corresponding method embodiments. Therefore, the corresponding method implementation principles and beneficial effects can be referred to, which will not be repeated here for the sake of brevity.

Claims

1. A method for assessing physiological state, characterized in that, The method includes: The system acquires the user's historical physiological data collected under each preset physiological state scenario, and calculates the user's blood pressure parameters for each preset physiological state scenario based on the historical physiological data corresponding to each preset physiological state scenario. If the user's current physiological data is collected, then the user's current physiological state scenario is obtained; Calculate the degree of matching between the current physiological data and the blood pressure parameters corresponding to the current physiological state scenario; Based on the current physiological state scenario and the matching degree, the user's state is evaluated to obtain the user's physiological state evaluation result.

2. The method according to claim 1, characterized in that, The step of assessing the user's state based on the current physiological state scenario and the matching degree to obtain the user's physiological state assessment result includes: Based on the user's behavioral state data under the preset attribute dimensions, calculate the user's state evaluation parameters for the preset attribute dimensions; wherein, the preset attribute dimensions include at least one of the following: exercise dimension, sleep dimension, and physiological stress dimension; Obtain the preset weighted recombination corresponding to the current physiological state scenario; the preset weighted recombination includes the preset weight of the matching degree and the preset weight of the state evaluation parameter; Based on the preset weighted recombination, the matching degree and the state evaluation parameters are weighted and added together to obtain the user's physiological state evaluation result.

3. The method according to claim 2, characterized in that, The step of weighting and adding the matching degree and the state evaluation parameters based on the preset weighted reassembly to obtain the user's physiological state evaluation result includes: The correction coefficient for each preset weight in the preset weighting is obtained by analyzing at least one of the following from the preset correction dimension: the behavioral state data, the current physiological data, the historical physiological data corresponding to each preset physiological state scenario, the state evaluation parameters, and the historical matching degree between the historical physiological data corresponding to the current physiological state scenario and the blood pressure parameters corresponding to the current physiological state scenario. The preset correction dimensions include at least one of the following: data integrity dimension, data collection timeliness dimension, parameter anomaly dimension of the state evaluation parameters, data influence dimension of the behavioral state data on the current physiological data, and anomaly dimension of the historical matching degree. Based on the correction coefficient of each preset weight, the corresponding preset weight in the preset weight reorganization is updated to obtain the target weight reorganization; Based on the target weighting, the matching degree and the state evaluation parameters are weighted and added together to obtain the user's physiological state evaluation result.

4. The method according to claim 2, characterized in that, The preset weighting reassembly includes a first preset weighting reassembly and a second preset weighting reassembly; the step of weightedly adding the matching degree and the state evaluation parameters based on the preset weighting reassembly to obtain the user's physiological state evaluation result includes: Based on the first preset weighted recombination, the matching degree and the state evaluation parameters are weighted and added together to obtain the user's physiological homeostasis evaluation parameters; Based on the second preset weighted recombination, the matching degree and the status evaluation parameters are weighted and added together to obtain the user's health status evaluation parameters; The physiological state assessment result of the user is generated based on the physiological homeostasis assessment parameters and the health status assessment parameters.

5. The method according to claim 4, characterized in that, The step of generating the user's physiological state assessment result based on the physiological homeostasis assessment parameters and the health state assessment parameters includes: Based on the numerical range of the state assessment parameters and the numerical range of the matching degree, the joint influence parameters are determined; Based on the joint influence parameters, the physiological homeostasis assessment parameters and the health status assessment parameters are updated to obtain the updated physiological homeostasis assessment parameters and the updated health status assessment parameters. Based on the updated physiological homeostasis assessment parameters and the updated health status assessment parameters, the user's physiological status assessment result is generated.

6. The method according to claim 1, characterized in that, The calculation of the matching degree between the current physiological data and the blood pressure parameters corresponding to the current physiological state scenario includes: Calculate the data difference between the current physiological data and the blood pressure parameter corresponding to the current physiological state scenario; Obtain the data fluctuation tolerance corresponding to the current physiological state scenario; The matching degree is determined based on the data difference and the data fluctuation tolerance.

7. The method according to any one of claims 1 to 6, characterized in that, The physiological state assessment result includes physiological homeostasis assessment parameters; after assessing the user's state based on the current physiological state scenario and the matching degree to obtain the user's physiological state assessment result, the method further includes: According to the pre-defined correspondence between parameter ranges and steady-state description texts, obtain the target steady-state description text corresponding to the parameter range to which the physiological steady-state assessment parameter belongs; The interface displays a physiological data analysis interface that includes the physiological homeostasis assessment parameters and the target homeostasis description text.

8. The method according to claim 7, characterized in that, The method further includes: At least one influence attribution parameter is obtained; wherein, different influence attribution parameters are used to characterize the degree of influence of behavioral state data under different preset attribute dimensions on the physiological state assessment results; Based on the parameter magnitude of the at least one influencing attribution parameter, determine the primary and secondary influencing attribution parameters for the physiological state assessment results from the at least one influencing attribution parameter; Based on the primary influence attribution parameters and the secondary influence attribution parameters, the attribution description text of the physiological state assessment results is obtained; The physiological data analysis interface, which displays the physiological homeostasis assessment parameters and the target homeostasis description text, includes: The interface displays a physiological data analysis interface that includes the physiological homeostasis assessment parameters, the target homeostasis description text, and the attribution description text.

9. A physiological state assessment device, characterized in that, The device includes a data acquisition unit, a scene acquisition unit, a matching degree calculation unit, and a result generation unit, wherein: The data acquisition unit is used to acquire the user's historical physiological data collected under each preset physiological state scenario, and to calculate the user's blood pressure parameters for each preset physiological state scenario based on the historical physiological data corresponding to each preset physiological state scenario. The scene acquisition unit is used to acquire the current physiological state scene of the user if the user's current physiological data is collected. The matching degree calculation unit is used to calculate the matching degree between the current physiological data and the blood pressure parameter corresponding to the current physiological state scenario; The result generation unit is used to perform a status assessment on the user based on the current physiological state scenario and the matching degree, and obtain the physiological state assessment result of the user.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the physiological state assessment method as described in any one of claims 1 to 8.

Images