Bathtub health monitoring management system and method based on AI control

Abstract

The present application provides a bathtub health monitoring management system and method based on AI control, which relates to the field of smart home technology, by collecting basic information of target users; performing intelligent analysis of bathtub parameters based on the basic information of target users to determine the tolerance range of bathtub parameters; interacting with the sensor array of the target bathtub to collect multiple temperature monitoring data sets, multiple water pressure monitoring data sets, and multiple user monitoring data sets; identifying the degree of abnormality of multiple temperature monitoring data sets, multiple water pressure monitoring data sets, and multiple user monitoring data sets, respectively, to generate a first abnormal coefficient, a second abnormal coefficient, and a third abnormal coefficient; performing health monitoring management of the target bathtub according to the first abnormal coefficient, the second abnormal coefficient, and the third abnormal coefficient. The present application solves the technical problem that traditional bathtubs cannot provide comprehensive and accurate health management according to the personalized needs of users, and improves the accuracy and adaptability of health management.

Description

Technical Field

[0001] The present application relates to the field of smart home technology, and specifically to a bathtub health monitoring management system and method based on AI control. Background Art

[0002] As people's living standards improve, bathtubs are becoming more and more popular as an important device for relaxing the body and mind and relieving fatigue. However, traditional bathtubs usually only provide basic temperature and water pressure adjustment functions during use, and cannot achieve personalized and intelligent health monitoring management. Especially for the elderly, children and some users with special health needs, the safety and comfort of traditional bathtubs are difficult to be fully guaranteed. Therefore, the introduction of intelligent bathtub health monitoring and management technology has become an urgent problem to be solved.

[0003] Existing bathtub health monitoring and management technologies mainly focus on basic temperature and water pressure monitoring, and achieve temperature and water pressure adjustment through simple sensors and control systems. However, these systems have many shortcomings. First, existing systems are usually unable to make personalized adjustments based on individual differences of users, making it difficult to meet the health needs of different users. Secondly, traditional monitoring systems lack real-time data analysis and abnormality recognition functions, and are unable to detect and handle abnormal situations in a timely manner during use, posing potential safety hazards. In addition, the lack of multi-dimensional data integration and analysis capabilities makes the system perform poorly when faced with complex health monitoring needs, making it difficult to provide a comprehensive and accurate health management solution. Summary of the invention

[0004] This application provides a bathtub health monitoring management system and method based on AI control, which solves the technical problem that traditional bathtubs lack real-time data analysis and abnormality recognition functions and cannot provide comprehensive and accurate health management according to users' personalized needs, thereby achieving the technical effect of improving the accuracy and adaptability of bathtub health monitoring management.

[0005] In view of the above problems, on the one hand, the present application provides a bathtub health monitoring and management system based on AI regulation, the system comprising: a basic information collection module, the basic information collection module is used to collect basic information of the target user, wherein the basic information includes a user health data set and a user behavior data set; a parameter analysis module, the parameter analysis module is used to perform intelligent analysis of bathtub parameters based on the user health data set and the user behavior data set, and determine the bathtub parameter tolerance range, wherein the bathtub parameter tolerance range includes a temperature tolerance range and a water pressure tolerance range; a monitoring data collection module, the monitoring data collection module is used to interact with the sensor array of the target bathtub, collect multiple temperature monitoring data sets, multiple water pressure monitoring data sets and multiple user monitoring data sets; a first abnormality recognition module, the A first abnormality identification module is used to identify the degree of abnormality of the multiple temperature monitoring data sets using the temperature tolerance range to generate a first abnormality coefficient; a second abnormality identification module, the second abnormality identification module is used to identify the degree of abnormality of the multiple water pressure monitoring data sets using the water pressure tolerance range to generate a second abnormality coefficient; a third abnormality identification module, the third abnormality identification module is used to use multiple indicator analyzers to respectively identify abnormalities of the multiple user monitoring data sets, and integrate the identification results to obtain a third abnormality coefficient, wherein the multiple indicator analyzers are multiple neural network models with shared weights; a health monitoring management module, the health monitoring management module is used to perform health monitoring management of the target bathtub according to the first abnormality coefficient, the second abnormality coefficient and the third abnormality coefficient.

[0006] On the other hand, the present application also provides a bathtub health monitoring and management method based on AI regulation, the method comprising: collecting basic information of the target user, wherein the basic information includes a user health data set and a user behavior data set; performing intelligent analysis of bathtub parameters based on the user health data set and the user behavior data set, and determining the bathtub parameter tolerance range, wherein the bathtub parameter tolerance range includes a temperature tolerance range and a water pressure tolerance range; interacting with the sensor array of the target bathtub, collecting multiple temperature monitoring data sets, multiple water pressure monitoring data sets and multiple user monitoring data sets; using the temperature tolerance range to identify the degree of abnormality of the multiple temperature monitoring data sets, and generating a first abnormality coefficient; using the water pressure tolerance range to identify the degree of abnormality of the multiple water pressure monitoring data sets, and generating a second abnormality coefficient; using multiple indicator analyzers to respectively identify abnormalities of the multiple user monitoring data sets, and integrating the identification results to obtain a third abnormality coefficient, wherein the multiple indicator analyzers are multiple neural network models with shared weights; performing health monitoring and management of the target bathtub according to the first abnormality coefficient, the second abnormality coefficient and the third abnormality coefficient.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] Collect the user's health and behavior data to provide a basis for subsequent personalized settings and health monitoring, so that the bathtub can be adjusted according to the specific needs of different users. Perform intelligent analysis of bathtub parameters based on user health data sets and user behavior data sets, determine the tolerance range of bathtub parameters, ensure that the bathtub settings are in line with the user's health status and preferences, and reduce discomfort and potential risks. The sensor array of the interactive target bathtub collects multiple temperature monitoring data sets, multiple water pressure monitoring data sets, and multiple user monitoring data sets to monitor the operating status of the bathtub and the user's response in real time, ensuring the real-time and accuracy of the data so as to find problems and respond in time. Identify the degree of abnormality of multiple temperature monitoring data sets, multiple water pressure monitoring data sets, and multiple user monitoring data sets, generate the first abnormal coefficient, the second abnormal coefficient, and the third abnormal coefficient, ensure that the water temperature and water pressure are within the acceptable range for the user, and analyze the user's health status and response from multiple angles to prevent scalding or other discomfort or injury caused by temperature and water pressure, and ensure the safety of the user. Perform health monitoring management of the target bathtub according to the first abnormal coefficient, the second abnormal coefficient, and the third abnormal coefficient to ensure the safety and health of the user.

[0009] In summary, this application collects and analyzes the user's health data and behavior data, uses a sensor array to monitor environmental parameters in real time, and uses AI technology to perform intelligent analysis and abnormality identification; it integrates multi-dimensional data to conduct health monitoring management, providing users with a safe and comfortable bathing environment and preventing potential health risks. The technical solution of this application not only improves the intelligence level of the bathtub, but also significantly improves the accuracy and adaptability of the bathtub health monitoring management.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic diagram of the structure of a bathtub health monitoring and management system based on AI control provided in an embodiment of the present application;

[0012] Figure 2 A schematic diagram of a process for determining a bathtub parameter tolerance range in a bathtub health monitoring and management system based on AI control provided in an embodiment of the present application;

[0013] Figure 3A schematic diagram of a process for obtaining multiple indicator analyzers in a bathtub health monitoring and management system based on AI control provided in an embodiment of the present application;

[0014] Figure 4 A flow chart of a bathtub health monitoring and management method based on AI control provided in an embodiment of the present application.

[0015] Explanation of the accompanying drawings: basic information collection module 10, parameter analysis module 20, monitoring data collection module 30, first abnormality identification module 40, second abnormality identification module 50, third abnormality identification module 60, health monitoring management module 70. DETAILED DESCRIPTION

[0016] The embodiments of the present application provide a bathtub health monitoring management system and method based on AI control to solve the technical problem that traditional bathtubs lack real-time data analysis and abnormality recognition functions and cannot provide comprehensive and accurate health management according to the personalized needs of users. By real-time monitoring and analysis of user behavior data, the technical effect of improving the accuracy and adaptability of bathtub health management is achieved.

[0017] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a bathtub health monitoring and management system based on AI regulation, and the system includes:

[0018] The basic information collection module 10 is used to collect basic information of the target user, wherein the basic information includes a user health data set and a user behavior data set.

[0019] Specifically, target users refer to the objects of the system service, that is, users who use the bathtub. The system will collect and analyze specific information of these users. The user health data set refers to the user's physiological indicator data, including age, weight, heart rate, blood pressure, body temperature, etc. These data help the system better understand the user's health status. The user behavior data set refers to the user's behavior pattern data, including bathing frequency, preferred temperature, bathing time, etc. These data help the system analyze the user's usage habits.

[0020] The basic information of the target user is collected by the user through the mobile application or web interface, including personal health data, including age, weight, medical history, etc.; the system collects the user's health data by interacting with wearable health monitoring devices, for example, the user can wear a smart bracelet or smart watch, which can monitor and record the user's heart rate, blood pressure, body temperature and other health indicators in real time; through the built-in sensor of the bathtub or interacting with the application on the user's mobile phone, the user's bathing behavior data, such as the start time, end time and water temperature setting of each bath, etc. These data are integrated into a user health data set and a user behavior data set by the module and transmitted to the parameter analysis module 20 for analysis through wireless transmission technology, such as Bluetooth or Wi-Fi.

[0021] The basic information collection module 10 creates a user portrait by collecting the user's health and behavior data, providing a basis for subsequent personalized settings and health monitoring, so that the bathtub can be adjusted according to the specific needs of different users.

[0022] The parameter analysis module 20 is used to perform intelligent analysis of bathtub parameters based on the user health data set and the user behavior data set to determine the bathtub parameter tolerance range, wherein the bathtub parameter tolerance range includes a temperature tolerance range and a water pressure tolerance range.

[0023] Specifically, bathtub parameters refer to various physical conditions that affect the bathing experience, including water temperature, water pressure, water flow rate, etc. Bathtub parameter tolerance range refers to a safe range of bathtub parameters, that is, a parameter range that meets user needs and physical conditions, including temperature tolerance range and water pressure tolerance range. The temperature tolerance range refers to the water temperature range that users can accept, and the water pressure tolerance range refers to the water pressure range that users can accept.

[0024] The parameter analysis module 20 uses data mining technology to analyze the user health data set and the user behavior data set collected by the basic information collection module 10. For example, regression analysis or classification algorithms can be used to combine the user's health data and behavior data to predict the user's reaction to different temperatures and water pressures. Through these analyses, the system can determine the temperature and water pressure range suitable for the user, and form a temperature tolerance range and a water pressure tolerance range.

[0025] Through intelligent analysis by the parameter analysis module 20, the system can set the best bathtub parameter range for the user to ensure the safety and comfort of the user when using the bathtub. If the system finds that the user has an abnormal condition when exceeding these ranges, such as a high heart rate or abnormal body temperature, the water temperature and water pressure can be adjusted in time, or an alarm can be issued to ensure the health and safety of the user.

[0026] The monitoring data collection module 30 is used to interact with the sensor array of the target bathtub to collect multiple temperature monitoring data sets, multiple water pressure monitoring data sets and multiple user monitoring data sets.

[0027] Specifically, the sensor array refers to a plurality of sensors installed in the bathtub for monitoring temperature, water pressure and physiological data of the user, including temperature sensors, pressure sensors, bioelectric sensors, etc. The temperature sensor is installed inside the bathtub for monitoring the water temperature. The temperature data is transmitted to the monitoring data acquisition module 30 via a digital signal or an analog signal. The water pressure sensor is installed in the water pipe system for monitoring changes in water pressure. The water pressure data is converted into an electrical signal by the sensor and transmitted to the monitoring data acquisition module 30. Bioelectric sensors include heart rate monitors, skin contact sensors, etc., which are installed inside the bathtub and can monitor heart rate, body temperature and other data in a non-invasive manner, and transmit the data to the monitoring data acquisition module 30 via wireless communication methods such as Bluetooth.

[0028] The monitoring data acquisition module 30 interacts with the sensor array in the bathtub, collects real-time temperature monitoring data, real-time water pressure monitoring data and real-time user monitoring data, and pre-processes the received data, such as denoising, filtering and data format conversion, and integrates the data through information such as timestamp and user ID to obtain multiple temperature monitoring data sets, multiple water pressure monitoring data sets and multiple user monitoring data sets, thereby ensuring the synchronization and accuracy of the data and realizing real-time health monitoring of the user's bathing process.

[0029] The first abnormality identification module 40 is used to identify the abnormality degree of the plurality of temperature monitoring data sets by using the temperature tolerance interval to generate a first abnormality coefficient.

[0030] Specifically, the first abnormality identification module 40 uses the temperature tolerance interval as a benchmark to analyze the temperature monitoring data, compares the temperature monitoring data with the temperature tolerance interval, identifies the data points that exceed the tolerance interval, and quantifies their degree of abnormality. The degree of abnormality can be quantified by calculating the deviation of the temperature value that exceeds the tolerance interval. Based on the calculated temperature deviation, a first abnormality coefficient is generated. This first abnormality coefficient is an indicator of the severity of the abnormal situation in the temperature monitoring data set, and reflects the degree of abnormality of the overall temperature data. Through the first abnormality coefficient, the system can evaluate the degree of abnormality of the water temperature, so that timely adjustments can be made when abnormalities are found to prevent overheating or overcooling and maintain the water temperature within a safe range.

[0031] The second abnormality identification module 50 is used to identify the abnormality degree of the plurality of water pressure monitoring data sets by using the water pressure tolerance interval to generate a second abnormality coefficient.

[0032] Specifically, the set water pressure tolerance interval is obtained from the parameter analysis module 20, and the multiple water pressure monitoring data sets obtained by the monitoring data acquisition module 30 are compared with the water pressure tolerance interval, the data points exceeding the tolerance interval are identified, and their abnormality is quantified. The degree of abnormality can be quantified by calculating the deviation of the water pressure value exceeding the tolerance interval. If there are data points exceeding the water pressure tolerance interval, the module will calculate the degree to which these data points deviate from the normal interval and generate an abnormality coefficient to represent this deviation, namely the second abnormality coefficient. This second abnormality coefficient is an indicator to measure the severity of abnormal conditions in the water pressure monitoring data set, reflecting the degree of abnormality of the overall water pressure data. Through the second abnormality coefficient, the system can evaluate the degree of abnormality of the water pressure, so as to make timely adjustments when abnormalities are found, prevent the water flow from being too weak or too strong, and maintain the water pressure within a safe range.

[0033] The third anomaly identification module 60 is used to use multiple indicator analyzers to respectively identify anomalies of the multiple user monitoring data sets, and integrate the identification results to obtain a third anomaly coefficient, wherein the multiple indicator analyzers are multiple neural network models with shared weights.

[0034] Specifically, an indicator analyzer is a tool or model for analyzing a specific indicator. In an embodiment of the present application, multiple indicator analyzers are multiple neural network models that share weights, that is, these neural network models are trained using the same weights to ensure the consistency of analysis of different data sets. First, multiple neural network models are trained using historical data and the same weights to obtain multiple indicator analyzers, each of which is responsible for analyzing a specific aspect of the user's monitoring data. Exemplary multiple indicator analyzers include a heart rate data analyzer, a body temperature data analyzer, and a respiratory rate data analyzer. The heart rate data analyzer is used to analyze heart rate data and identify abnormal heart rate events. The body temperature data analyzer is used to analyze body temperature data and identify abnormal changes in body temperature. The respiratory rate data analyzer is used to analyze respiratory rate data and identify abnormal breathing patterns. Multiple indicator analyzers are used to perform abnormal identification on multiple user monitoring data sets respectively, and the abnormal identification results of each indicator analyzer are integrated to generate a comprehensive abnormal identification result. According to the integrated identification results, the third abnormal coefficient is calculated to quantify the overall abnormal degree of the user's physiological data. Among them, the third abnormal coefficient is an indicator reflecting the severity of abnormal conditions in the user monitoring data set.

[0035] Through the above process, the third abnormality identification module 60 uses multiple neural network models with shared weights to comprehensively evaluate the user's physical condition from multiple perspectives, integrates the identification results to generate a third abnormality coefficient, and thus quantifies the degree of abnormality of the user's physiological data. This coefficient can be used for further health monitoring and automatic adjustment to ensure the safety of the user when using the bathtub.

[0036] A health monitoring management module 70 is used to perform health monitoring management of the target bathtub according to the first abnormality coefficient, the second abnormality coefficient and the third abnormality coefficient.

[0037] Specifically, the health monitoring management module 70 receives the first abnormal coefficient, the second abnormal coefficient and the third abnormal coefficient from the first abnormal identification module 40, the second abnormal identification module 50 and the third abnormal identification module 60, and comprehensively evaluates the overall health status of the user when using the bathtub through these abnormal coefficients. According to the results of the comprehensive evaluation, the module generates corresponding health monitoring management decisions and adjusts the parameters of the bathtub to ensure the safety and comfort of the user. For example, if the first abnormal coefficient is high, the system may need to lower or increase the water temperature; if the second abnormal coefficient is high, the system may need to adjust the water pressure. In addition to adjusting the bathtub parameters, the system can also take other management measures, such as issuing an alarm, notifying the user or starting an emergency procedure. For example, if the third abnormal coefficient is high, the system may issue an alarm to notify the user to pay attention to the physical condition, or contact emergency medical services when necessary. Among them, health management decisions include prompting maintenance, adjusting bathtub settings or notifying users. These health management decisions are pre-stored in the decision library embedded in the module. The module traverses this decision library according to the corresponding comprehensive evaluation results to obtain the corresponding health management decisions, so as to achieve comprehensive and accurate health monitoring management.

[0038] Furthermore, if Figure 2 As shown, the execution steps of the parameter analysis module 20 in the embodiment of the present application also include:

[0039] Collect a bathtub adjustment parameter database of the target bathtub, wherein the bathtub adjustment parameter database includes a plurality of local adjustment parameter data; perform consistency analysis on the plurality of local adjustment parameter data to generate a data consistency factor; when the data consistency factor is greater than or equal to a preset consistency factor, generate a database expansion instruction; perform cloud data mining based on the database expansion instruction, update the bathtub adjustment parameter database according to the mining results, and generate an updated bathtub adjustment parameter database, wherein the updated bathtub adjustment parameter database includes a plurality of updated adjustment parameter data; search the updated bathtub adjustment parameter database based on the user health data set and the user behavior data set to determine the bathtub parameter tolerance range.

[0040] Specifically, the bathtub parameter adjustment database is a database that stores data about bathtub parameter adjustment, including multiple local parameter adjustment data. Among them, local parameter adjustment data refers to specific data about bathtub parameter adjustment collected in a specific user or environment. First, the bathtub parameter adjustment database is collected from the target bathtub, which contains multiple local parameter adjustment data. These data are recorded by sensors and control systems, reflecting the temperature and water pressure adjustment of the bathtub in different usage scenarios. Next, the module uses statistical analysis tools such as standard deviation analysis or covariance matrix to perform consistency analysis on these local parameter adjustment data, measure the consistency of the data, and generate a data consistency factor. Among them, the data consistency factor is an indicator of data consistency, which is used to judge whether the data is reliable and consistent. Assuming that the module finds that some data has a large deviation under specific temperature and water pressure conditions, the consistency factor may be low; while under other conditions, the data consistency factor may be high.

[0041] A consistency factor threshold is customized in advance, that is, the preset consistency factor, which is used to determine whether the data is sufficiently consistent and reliable. The generated data consistency factor is compared with the preset consistency factor. When the data consistency factor reaches or exceeds the preset consistency factor, the module will generate a database expansion instruction. At this time, the module will use cloud computing and big data technology to conduct cloud data mining, analyze a large amount of bathtub usage data, and find a wider range of parameter adjustment patterns and rules. Based on the results of cloud data mining, the bathtub parameter adjustment database is updated to generate an updated bathtub parameter adjustment database containing multiple updated parameter adjustment data. Among them, the updated parameter adjustment data refers to the new data obtained through data mining, which is used to enrich and improve the bathtub parameter adjustment database. These new data may include more diverse user usage habits and optimal bathtub parameters under environmental conditions. An updated bathtub parameter adjustment database refers to a parameter adjustment database that is updated based on the results of cloud data mining.

[0042] Finally, the module searches the updated bathtub parameter database based on the user health data set and the user behavior data set. Using big data analysis and machine learning algorithms such as (k nearest neighbor algorithm) or decision tree, the system can find the bathtub parameter tolerance range that best matches the target user.

[0043] For example, suppose a user's local parameter adjustment data shows that in the past month, his bath water temperature is often between 36°C and 38°C, and the water pressure is between 2bar and 2.5bar. After the module performs consistency analysis, it finds that the consistency factor of these data is 0.9 (the full score is 1), reaching the preset consistency factor of 0.8, so it generates a database expansion instruction. Through cloud data mining, the module found that the parameters of similar users in the range of 37°C to 39°C and 2.5bar to 3bar are more optimized. Therefore, the module updates the bathtub parameter adjustment database and integrates these new data. Finally, based on the updated database, when setting the bathtub parameters for the user, the module recommends setting the water temperature between 37°C and 39°C and the water pressure between 2.5bar and 3bar. This not only improves the user's comfort, but also enhances health protection.

[0044] Preferably, the execution steps of the parameter analysis module 20 in the embodiment of the present application further include:

[0045] The user health data set and the user behavior data set are used for searching to obtain a plurality of matching updated parameter adjustment data, wherein the plurality of matching updated parameter adjustment data include a plurality of temperature values ​​and a plurality of water pressure values; the plurality of temperature values ​​and the plurality of water pressure values ​​are interlocked to generate a temperature-water pressure mapping relationship; the plurality of temperature values ​​are centrally screened to obtain a plurality of target temperature values; the temperature tolerance range is determined according to the plurality of target temperature values; mapping and matching are performed based on the temperature-water pressure mapping relationship, the plurality of water pressure values ​​and the temperature tolerance range to generate a water pressure tolerance range.

[0046] Specifically, matching and updating parameter data means finding parameter data that matches the user's health data and behavior data in the database, including multiple temperature values ​​and multiple water pressure values. First, retrieve the parameter data that matches the user's health data and behavior data from the updated bathtub parameter database, which includes multiple temperature values ​​and multiple water pressure values. For example, the module will retrieve the temperature and water pressure data used by the user in different time periods and different environments based on the user's historical bathing data and current health status.

[0047] Next, the module uses statistical analysis tools such as correlation analysis or multiple regression analysis to determine the water pressure value corresponding to a specific temperature. These temperature values ​​and water pressure values ​​are interlocked to generate a temperature-water pressure mapping relationship. Interlocking refers to associating two or more data sets to form a mapping relationship. After that, these temperature values ​​are centrally screened to select multiple target temperature values. The target temperature value refers to the temperature value that is most frequently used and most suitable for the user after screening. Assuming that the module finds that the user uses it most frequently and feels most comfortable at temperatures of 37°C, 38°C, and 39°C, then these temperature values ​​are selected as target temperature values.

[0048] Finally, based on the temperature-water pressure mapping relationship, multiple water pressure values ​​and temperature tolerance range, the module performs mapping matching and generates a water pressure tolerance range. By analyzing the water pressure values ​​within the temperature tolerance range, the module can determine the optimal water pressure range. For example, within the temperature range of 36°C to 40°C, if the corresponding water pressure value is most suitable between 2.5 bar and 3.5 bar, then the water pressure tolerance range can be set to 2.5 bar to 3.5 bar.

[0049] Through the above-mentioned retrieval, screening, mapping and matching process, the optimal temperature tolerance range and water pressure tolerance range that meet the user's needs and health conditions can be determined, providing the user with a more personalized, healthy and safe bathing environment.

[0050] Preferably, the execution steps of the parameter analysis module 20 in the embodiment of the present application further include:

[0051] Taking the mode of the multiple temperature values ​​as a starting point, searching among the multiple temperature values ​​according to a preset concentration step length, constructing a first temperature interval, wherein the first temperature interval includes a first temperature concentration coefficient; expanding the first temperature interval according to the preset concentration step length to obtain a second temperature interval, wherein the second temperature interval includes a second temperature concentration coefficient; determining whether the first temperature concentration coefficient is less than or equal to the second temperature concentration coefficient, and if so, continuing to expand based on the second temperature interval until a preset stop condition is met to obtain a target temperature interval; taking the multiple temperature values ​​within the target temperature interval as multiple target temperature values.

[0052] Preferably, the preset stop condition in the execution step of the parameter analysis module 20 in the embodiment of the present application is that the difference in temperature concentration coefficients of two temperature intervals obtained by two adjacent expansions is less than or equal to a preset coefficient difference.

[0053] Specifically, the mode refers to the value with the highest frequency in a set of data. The first temperature interval and the second temperature interval refer to temperature ranges constructed at different levels, and they both have their own temperature concentration coefficients, where the temperature concentration coefficient is a value that measures the density of temperature values ​​distributed within the interval, and can be calculated by standard deviation, frequency distribution or other statistical methods. The preset stop condition is the condition that determines when to stop expanding the temperature interval. In a preferred embodiment, the preset stop condition is that the difference in temperature concentration coefficients of two temperature intervals obtained from two adjacent expansions is less than or equal to the preset coefficient difference. Among them, the preset coefficient difference is a pre-defined coefficient difference used to determine whether the temperature interval continues to expand.

[0054] First, find the mode from multiple temperature values, that is, the temperature value with the highest frequency, as the starting point for constructing the temperature interval. Next, search among multiple temperature values ​​according to the preset concentration step, construct the first temperature interval, and calculate the first temperature concentration coefficient. Among them, the preset concentration step refers to the pre-defined incremental step for each expansion of the temperature interval. For example, if the mode is 39°C and the preset step is 2°C, then the first temperature interval may be 38°C to 40°C. Then the module continues to expand the first temperature interval with the same step to form a larger temperature interval, namely the second temperature interval, and calculates the second temperature concentration coefficient. For example, if the preset step is still 2°C, then the second temperature interval may be 37°C to 41°C.

[0055] Compare the first temperature concentration coefficient and the second temperature concentration coefficient. If the concentration coefficient of the second temperature interval is greater than or equal to the concentration coefficient of the first temperature interval, the module continues to expand based on the second temperature interval until the change of the temperature concentration coefficient meets the preset stop condition, that is, the difference in the temperature concentration coefficients of the temperature intervals obtained by two adjacent expansions is less than or equal to the preset coefficient difference. The temperature interval at this time is the target temperature interval. The module uses multiple temperature values ​​within the target temperature interval as multiple target temperature values.

[0056] Exemplarily, assume that the temperature values ​​in the user's health data are: 35°C, 36°C, 37°C, 37°C, 38°C, 39°C, 37°C, 40°C. First, determine that the mode is 37°C, because 37°C appears most frequently. Starting from 37°C, set the preset concentration step size to 1°C, and construct the first temperature interval: 36°C to 38°C. The temperature value data in the first temperature interval are: 36°C, 37°C, 37°C, 38°C. Calculate the standard deviation of these temperature values, and the first temperature concentration coefficient is 0.707. Continue to expand the first temperature interval with the same step size, and the second temperature interval is 35°C to 39°C. The temperature value data in the first temperature interval are 35°C, 36°C, 37°C, 37°C, 38°C, and 39°C. Calculate the standard deviation of these temperature values, and the second temperature concentration coefficient is 1.29. Compare the concentration coefficients, 0.707<1.29, so continue to expand. The expansion interval is to 34°C to 40°C. The temperature value data is: 34℃, 35℃, 36℃, 37℃, 37℃, 38℃, 39℃, 40℃. The temperature concentration coefficient of the third temperature interval is 1.87. Comparing the concentration coefficients, 1.29<1.87, so continue to expand. Set the preset stop condition as the difference in concentration coefficients between two adjacent expansions is less than or equal to 0.1. Assuming that when expanding to 33℃ to 41℃, the temperature concentration coefficient changes less than 0.1, then stop expanding. At this time, the temperature value data is: 33℃, 34℃, 35℃, 36℃, 37℃, 37℃, 38℃, 39℃, 40℃, 41℃. The final target temperature interval is 33℃ to 41℃. Take multiple temperature values ​​in the target temperature interval: 33℃, 34℃, 35℃, 36℃, 37℃, 38℃, 39℃, 40℃, 41℃ as multiple target temperature values.

[0057] Through the above process, the module uses the mode, preset concentration step and temperature concentration coefficient to gradually expand and judge, and finally determines the target temperature range and multiple target temperature values ​​that are most suitable for the user to achieve intelligent and personalized health monitoring management.

[0058] Furthermore, if Figure 3 As shown, the execution steps of the third abnormality identification module 60 in the embodiment of the present application also include:

[0059] Acquire multiple sample user monitoring data sets and multiple sample anomaly recognition results as training data; equally divide the training data into multiple sub-training data, use the multiple sub-training data to train a framework based on a recurrent neural network until the model converges, and obtain multiple network parameters; calculate the mean of the multiple network parameters to obtain updated network parameters; distribute the updated network parameters to the multiple neural network models to obtain multiple indicator analyzers.

[0060] Specifically, the sample user monitoring data set is a series of user monitoring data collected in advance and used to train the neural network model. The sample anomaly recognition result is the real anomaly label corresponding to the user monitoring data set, which is used to guide the model to learn to correctly distinguish between normal and abnormal states.

[0061] First, a large amount of user monitoring data and its corresponding abnormal identification results are collected as training data through the monitoring data acquisition module 30. The training data is divided into several parts according to the data type to facilitate model training and verification, including heart rate data training set, blood pressure data training set, body temperature data training set and respiratory rate data training set. Then these sub-training data are used to train the framework based on the recurrent neural network, and the network parameters are continuously adjusted through multiple iterations and optimization algorithms until the model performance is no longer improved, that is, the model converges. The mean of the multiple network parameters obtained by training is calculated to obtain a set of updated network parameters. These updated network parameters represent the optimal configuration of the model. Finally, these updated network parameters are applied to multiple neural network models to form multiple indicator analyzers. These analyzers will be used to monitor and evaluate user data in real time to identify abnormal situations.

[0062] For example, suppose there is a training data set containing one week of user monitoring data and corresponding abnormal labels. These data are divided into heart rate data training set, blood pressure data training set, body temperature data training set and respiratory rate data training set according to the data type, which are used to train different recurrent neural networks. Each network learns to identify abnormal situations from the corresponding user monitoring data. After training, the parameters of each network are averaged to obtain a set of optimal parameters, which are applied to all neural network models to enable them to predict abnormal situations more accurately. Finally, these optimized neural network models form multiple indicator analyzers to monitor users' real-time monitoring data.

[0063] The above process improves the generalization ability and accuracy of the model, so that the third abnormality identification module 60 can better adapt to the changing state of the user and detect abnormal physical condition of the user in time.

[0064] Furthermore, the execution steps of the first abnormality identification module 40 in the embodiment of the present application also include:

[0065] The temperature tolerance range is used to perform abnormal screening on the multiple temperature monitoring data sets to determine multiple abnormal data amounts; the multiple abnormal data amounts are compared with the multiple temperature monitoring data sets respectively to obtain multiple first sub-abnormal coefficients; the multiple first sub-abnormal coefficients are averaged to obtain the first abnormal coefficient.

[0066] Specifically, the temperature monitoring data set is screened using the temperature tolerance interval to determine which data exceeds the set range, thereby identifying abnormal data and obtaining multiple abnormal data amounts, which refer to the amount of data that is screened out of the temperature tolerance interval. Next, the system compares the multiple abnormal data amounts with the multiple temperature monitoring data sets to obtain multiple first sub-abnormal coefficients. The multiple first sub-abnormal coefficients are coefficients obtained by quantifying the ratio of each abnormal data amount to the temperature monitoring data set. For example, if a certain abnormal data amount accounts for 10% of the total data amount, the system may assign a first sub-abnormal coefficient of 0.1 to this data point. Finally, the system averages the multiple first sub-abnormal coefficients, that is, calculates the average of the multiple first sub-abnormal coefficients, and uses the result as the first abnormal coefficient. This coefficient reflects the overall abnormality of the temperature monitoring data. For example, if there are three temperature monitoring data sets, and the sub-abnormal coefficients calculated are 0.4, 0.2 and 0.6, respectively, then the first abnormal coefficient is 0.4.

[0067] The first abnormality identification module 40 generates a first abnormality coefficient through the above process, quantifies the abnormal water temperature during the user process, and further determines the degree of abnormality of the temperature monitoring data, so as to facilitate subsequent timely adjustments. In addition, the second abnormality coefficient can be calculated in the same way, and those skilled in the art can refer to the above process to clearly know the process of obtaining the second abnormality coefficient. In order to avoid redundancy in the specification, no further introduction is given here.

[0068] In summary, the bathtub health monitoring and management system based on AI control provided in the embodiments of the present application has the following technical effects:

[0069] The basic information collection module 10 collects the user's health and behavior data to provide a basis for subsequent personalized settings and health monitoring, so that the bathtub can be adjusted according to the specific needs of different users. The parameter analysis module 20 performs intelligent analysis of the bathtub parameters based on the user health data set and the user behavior data set, determines the bathtub parameter tolerance range, ensures that the bathtub settings are in line with the user's health status and preferences, and reduces discomfort and potential risks. The monitoring data collection module 30 interacts with the sensor array of the target bathtub to collect multiple temperature monitoring data sets, multiple water pressure monitoring data sets, and multiple user monitoring data sets; monitors the operating status of the bathtub and the user's response in real time to ensure the real-time and accuracy of the data, so as to find problems and respond in time. The first abnormal identification module 40, the second abnormal identification module 50, and the third abnormal identification module 60 respectively identify the degree of abnormality of multiple temperature monitoring data sets, multiple water pressure monitoring data sets, and multiple user monitoring data sets, generate the first abnormal coefficient, the second abnormal coefficient, and the third abnormal coefficient, ensure that the water temperature and water pressure are within the acceptable range for the user, and analyze the user's health status and response from multiple angles to prevent scalding or other discomfort or injury caused by temperature and water pressure, and ensure the safety of the user. The health monitoring management module 70 performs health monitoring management of the target bathtub according to the first abnormality coefficient, the second abnormality coefficient and the third abnormality coefficient to ensure the safety and health of the user.

[0070] In general, the embodiments of the present application collect and analyze the user's health data and behavior data to achieve personalized bathtub parameter settings; use sensor arrays to monitor environmental parameters in real time, and use AI technology to perform intelligent analysis and abnormality identification; integrate multi-dimensional data to perform health monitoring management, provide users with a safe and comfortable bathing environment, and prevent potential health risks. The technical solution of this application not only improves the intelligence level of the bathtub, but also significantly improves the accuracy and adaptability of bathtub health monitoring management.

[0071] Embodiment 2, as Figure 4 As shown, the embodiment of the present application provides a bathtub health monitoring and management method based on AI regulation, the method comprising:

[0072] Collect the basic information of the target user, wherein the basic information includes a user health data set and a user behavior data set.

[0073] Based on the user health data set and the user behavior data set, intelligent analysis of bathtub parameters is performed to determine bathtub parameter tolerance ranges, wherein the bathtub parameter tolerance ranges include a temperature tolerance range and a water pressure tolerance range.

[0074] The sensor array of the interactive target bathtub collects multiple temperature monitoring data sets, multiple water pressure monitoring data sets and multiple user monitoring data sets.

[0075] The temperature tolerance interval is used to identify the degree of abnormality of the plurality of temperature monitoring data sets, and a first abnormality coefficient is generated.

[0076] The water pressure tolerance interval is used to identify the abnormality of the multiple water pressure monitoring data sets to generate a second abnormality coefficient.

[0077] A plurality of indicator analyzers are used to respectively identify anomalies on the plurality of user monitoring data sets, and the identification results are integrated to obtain a third anomaly coefficient, wherein the plurality of indicator analyzers are a plurality of neural network models with shared weights.

[0078] Health monitoring management of the target bathtub is performed according to the first abnormality coefficient, the second abnormality coefficient, and the third abnormality coefficient.

[0079] Furthermore, the embodiment of the present application performs intelligent analysis of bathtub parameters based on the user health data set and the user behavior data set to determine the bathtub parameter tolerance range, and further includes:

[0080] Collect a bathtub adjustment parameter database of the target bathtub, wherein the bathtub adjustment parameter database includes a plurality of local adjustment parameter data; perform consistency analysis on the plurality of local adjustment parameter data to generate a data consistency factor; when the data consistency factor is greater than or equal to a preset consistency factor, generate a database expansion instruction; perform cloud data mining based on the database expansion instruction, update the bathtub adjustment parameter database according to the mining results, and generate an updated bathtub adjustment parameter database, wherein the updated bathtub adjustment parameter database includes a plurality of updated adjustment parameter data; search the updated bathtub adjustment parameter database based on the user health data set and the user behavior data set to determine the bathtub parameter tolerance range.

[0081] Preferably, the embodiment of the present application further includes: searching the updated bathtub parameter adjustment database based on the user health data set and the user behavior data set to determine the bathtub parameter tolerance range;

[0082] The user health data set and the user behavior data set are used for searching to obtain a plurality of matching updated parameter adjustment data, wherein the plurality of matching updated parameter adjustment data include a plurality of temperature values ​​and a plurality of water pressure values; the plurality of temperature values ​​and the plurality of water pressure values ​​are interlocked to generate a temperature-water pressure mapping relationship; the plurality of temperature values ​​are centrally screened to obtain a plurality of target temperature values; the temperature tolerance range is determined according to the plurality of target temperature values; mapping and matching are performed based on the temperature-water pressure mapping relationship, the plurality of water pressure values ​​and the temperature tolerance range to generate a water pressure tolerance range.

[0083] Preferably, the centralized screening of the multiple temperature values ​​to obtain multiple target temperature values ​​described in the embodiment of the present application further includes:

[0084] Taking the mode of the multiple temperature values ​​as a starting point, searching among the multiple temperature values ​​according to a preset concentration step length, constructing a first temperature interval, wherein the first temperature interval includes a first temperature concentration coefficient; expanding the first temperature interval according to the preset concentration step length to obtain a second temperature interval, wherein the second temperature interval includes a second temperature concentration coefficient; determining whether the first temperature concentration coefficient is less than or equal to the second temperature concentration coefficient, and if so, continuing to expand based on the second temperature interval until a preset stop condition is met to obtain a target temperature interval; taking the multiple temperature values ​​within the target temperature interval as multiple target temperature values.

[0085] Preferably, the preset stop condition is that the difference in temperature concentration coefficients between two temperature intervals obtained by two adjacent expansions is less than or equal to a preset coefficient difference.

[0086] Furthermore, the embodiment of the present application obtains the multiple indicator analyzers, and further includes:

[0087] Acquire multiple sample user monitoring data sets and multiple sample anomaly recognition results as training data; equally divide the training data into multiple sub-training data, use the multiple sub-training data to train a framework based on a recurrent neural network until the model converges, and obtain multiple network parameters; calculate the mean of the multiple network parameters to obtain updated network parameters; distribute the updated network parameters to the multiple neural network models to obtain multiple indicator analyzers.

[0088] Furthermore, the embodiment of the present application uses the temperature tolerance interval to identify the abnormality of the multiple temperature monitoring data sets and generates a first abnormality coefficient, and also includes:

[0089] The temperature tolerance range is used to perform abnormal screening on the multiple temperature monitoring data sets to determine multiple abnormal data amounts; the multiple abnormal data amounts are compared with the multiple temperature monitoring data sets respectively to obtain multiple first sub-abnormal coefficients; the multiple first sub-abnormal coefficients are averaged to obtain the first abnormal coefficient.

[0090] Through the above detailed description of the bathtub health monitoring and management system based on AI control in this specification, those skilled in the art can clearly understand the bathtub health monitoring and management method based on AI control in this embodiment. For the method disclosed in Example 2, since it corresponds to the system disclosed in Example 1 and has corresponding execution steps and beneficial effects, the relevant parts can be referred to the description of the method part.

[0091] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. Bathtub health monitoring and management system based on AI control, characterized by: The system comprises: A basic information collection module, which is used to collect basic information of the target user, wherein the basic information includes a user health data set and a user behavior data set; A parameter analysis module, the parameter analysis module is used to perform intelligent analysis of bathtub parameters based on the user health data set and the user behavior data set, and determine a bathtub parameter tolerance range, wherein the bathtub parameter tolerance range includes a temperature tolerance range and a water pressure tolerance range; A monitoring data collection module, the monitoring data collection module is used to interact with the sensor array of the target bathtub to collect multiple temperature monitoring data sets, multiple water pressure monitoring data sets and multiple user monitoring data sets; A first abnormality identification module, the first abnormality identification module is used to identify the abnormality degree of the plurality of temperature monitoring data sets by using the temperature tolerance interval to generate a first abnormality coefficient; A second abnormality identification module, the second abnormality identification module is used to identify the abnormality degree of the plurality of water pressure monitoring data sets by using the water pressure tolerance interval to generate a second abnormality coefficient; a third anomaly identification module, the third anomaly identification module being used to use a plurality of index analyzers to respectively identify anomalies on the plurality of user monitoring data sets, and to integrate the identification results to obtain a third anomaly coefficient, wherein the plurality of index analyzers are a plurality of neural network models with shared weights; a health monitoring management module, the health monitoring management module being used to perform health monitoring management of the target bathtub according to the first abnormality coefficient, the second abnormality coefficient and the third abnormality coefficient; The execution steps of the parameter analysis module also include: Acquiring a bathtub parameter adjustment database of the target bathtub, wherein the bathtub parameter adjustment database includes a plurality of local parameter adjustment data; Performing consistency analysis on the multiple local parameter adjustment data to generate a data consistency factor; When the data consistency factor is greater than or equal to a preset consistency factor, generating a database expansion instruction; Performing cloud data mining based on the database expansion instruction, updating the bathtub parameter adjustment database according to the mining result, and generating an updated bathtub parameter adjustment database, wherein the updated bathtub parameter adjustment database includes a plurality of updated parameter adjustment data; Based on the user health data set and the user behavior data set, searching the updated bathtub parameter adjustment database, determining a bathtub parameter tolerance range; The execution steps of the parameter analysis module also include: Retrieving the user health data set and the user behavior data set to obtain a plurality of matching updated parameter adjustment data, wherein the plurality of matching updated parameter adjustment data include a plurality of temperature values ​​and a plurality of water pressure values; interlocking the plurality of temperature values ​​and the plurality of water pressure values ​​to generate a temperature-water pressure mapping relationship; Centrally screening the multiple temperature values ​​to obtain multiple target temperature values; Determining the temperature tolerance range according to the multiple target temperature values; Mapping and matching is performed based on the temperature-water pressure mapping relationship, multiple water pressure values, and the temperature tolerance range to generate a water pressure tolerance range.

2. The bathtub health monitoring and management system based on AI control as claimed in claim 1, characterized in that: The execution steps of the parameter analysis module also include: Taking the mode of the plurality of temperature values ​​as a starting point, searching among the plurality of temperature values ​​according to a preset concentration step length to construct a first temperature interval, wherein the first temperature interval includes a first temperature concentration coefficient; Expanding the first temperature interval according to the preset concentration step length to obtain a second temperature interval, wherein the second temperature interval includes a second temperature concentration coefficient; Determine whether the first temperature concentration coefficient is less than or equal to the second temperature concentration coefficient, and if so, continue to expand based on the second temperature interval until a preset stop condition is met to obtain a target temperature interval; A plurality of temperature values ​​within the target temperature interval are used as a plurality of target temperature values.

3. The bathtub health monitoring and management system based on AI control as claimed in claim 2, characterized in that: The preset stop condition is that the difference in temperature concentration coefficients between two temperature intervals obtained by two adjacent expansions is less than or equal to a preset coefficient difference.

4. The bathtub health monitoring and management system based on AI control as claimed in claim 1, characterized in that: The execution steps of the third abnormality identification module also include: Acquire multiple sample user monitoring data sets and multiple sample anomaly recognition results as training data; The training data is equally divided into a plurality of sub-training data, and a framework based on a recurrent neural network is trained using the plurality of sub-training data until the model converges to obtain a plurality of network parameters; Calculating the mean of the plurality of network parameters to obtain updated network parameters; The updated network parameters are distributed to the multiple neural network models to obtain multiple indicator analyzers.

5. The bathtub health monitoring and management system based on AI control as claimed in claim 1, characterized in that: The execution step of the first abnormality identification module also includes: Using the temperature tolerance interval to perform abnormal screening on the plurality of temperature monitoring data sets, and determining a plurality of abnormal data amounts; Comparing the multiple abnormal data amounts with the multiple temperature monitoring data sets respectively to obtain multiple first sub-abnormal coefficients; The first abnormal coefficient is obtained by performing mean processing on the multiple first sub-abnormal coefficients.

6. The bathtub health monitoring and management method based on AI control is characterized by: The method comprises: Collecting basic information of the target user, wherein the basic information includes a user health data set and a user behavior data set; Performing intelligent analysis of bathtub parameters based on the user health data set and the user behavior data set to determine a bathtub parameter tolerance range, wherein the bathtub parameter tolerance range includes a temperature tolerance range and a water pressure tolerance range; The sensor array of the interactive target bathtub collects multiple temperature monitoring data sets, multiple water pressure monitoring data sets, and multiple user monitoring data sets; Using the temperature tolerance interval to identify the degree of abnormality of the plurality of temperature monitoring data sets, and generating a first abnormality coefficient; Using the water pressure tolerance interval to identify the abnormality of the plurality of water pressure monitoring data sets, and generating a second abnormality coefficient; Using a plurality of indicator analyzers to respectively identify anomalies on the plurality of user monitoring data sets, and integrating the identification results to obtain a third anomaly coefficient, wherein the plurality of indicator analyzers are a plurality of neural network models with shared weights; Perform health monitoring management of the target bathtub according to the first abnormality coefficient, the second abnormality coefficient and the third abnormality coefficient; The intelligent analysis of bathtub parameters based on the user health data set and the user behavior data set to determine the bathtub parameter tolerance range also includes: Acquiring a bathtub parameter adjustment database of the target bathtub, wherein the bathtub parameter adjustment database includes a plurality of local parameter adjustment data; Performing consistency analysis on the multiple local parameter adjustment data to generate a data consistency factor; When the data consistency factor is greater than or equal to a preset consistency factor, generating a database expansion instruction; Performing cloud data mining based on the database expansion instruction, updating the bathtub parameter adjustment database according to the mining result, and generating an updated bathtub parameter adjustment database, wherein the updated bathtub parameter adjustment database includes a plurality of updated parameter adjustment data; Based on the user health data set and the user behavior data set, searching the updated bathtub parameter adjustment database, determining a bathtub parameter tolerance range; The step of searching the updated bathtub parameter adjustment database based on the user health data set and the user behavior data set to determine the bathtub parameter tolerance range further includes: Retrieving the user health data set and the user behavior data set to obtain a plurality of matching updated parameter adjustment data, wherein the plurality of matching updated parameter adjustment data include a plurality of temperature values ​​and a plurality of water pressure values; interlocking the plurality of temperature values ​​and the plurality of water pressure values ​​to generate a temperature-water pressure mapping relationship; Centrally screening the multiple temperature values ​​to obtain multiple target temperature values; Determining the temperature tolerance range according to the multiple target temperature values; Mapping and matching is performed based on the temperature-water pressure mapping relationship, multiple water pressure values, and the temperature tolerance range to generate a water pressure tolerance range.

Images