Intelligent drinking water reminder method, device, computer equipment and readable storage medium

Abstract

The present application relates to a smart drinking water reminder method, device, computer equipment, and readable storage medium. The method includes: traversing the target object's unit time after drinking water, obtaining the target object's body temperature change value within the traversed unit time; determining the target object's body temperature change rate within the traversed unit time based on the body temperature change value and the duration of the traversed unit time; determining the target object's body temperature adjustment parameter within the traversed unit time based on the body temperature change value and the body temperature change rate; stopping the traversal when the target object's body temperature adjustment parameter within the traversed unit time meets the preset drinking water condition, and using the traversed unit time as the waiting time for drinking water. The use of this method can avoid ineffective or even harmful premature or delayed drinking behaviors, and can also promote the formation of good living habits, further supporting long-term health maintenance and personal immunity enhancement.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an intelligent water drinking reminder method, device, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] In modern society, personal health management and immune system enhancement are becoming increasingly important. Basal body temperature (BBT) is a key indicator of human health, and regulating it is crucial for maintaining good health and enhancing immunity. However, there is currently a lack of methods on the market that can monitor and intelligently regulate BBT in real time to optimize immune system management.

[0003] Traditional methods rely primarily on users manually recording their body temperature and hydration intake and adjusting based on past experience. However, this method is not only time-consuming and labor-intensive, but also difficult to ensure scientific and accurate adjustments. With the continuous advancement of science and technology, developing a method that can optimize basal body temperature through real-time monitoring, precise prediction, and scientific regulation has become increasingly feasible and urgent. Summary of the Invention

[0004] Based on this, it is necessary to provide an intelligent water drinking reminder method, device, computer equipment, computer-readable storage medium and computer program product that can monitor in real time, accurately predict and scientifically regulate to optimize basal body temperature in response to the above technical problems.

[0005] In a first aspect, the present application provides a smart water drinking reminder method, comprising:

[0006] Traversing the unit time of the target object after drinking the water, and obtaining the temperature change value of the target object in the traversed unit time;

[0007] Determine the temperature change rate of the target object within the unit time traversed according to the temperature change value and the duration of the unit time traversed;

[0008] Determining a body temperature adjustment parameter of the target object within a unit time traversed to according to the body temperature change value and the body temperature change rate;

[0009] When the body temperature adjustment parameter of the target object in the traversed unit time meets the preset drinking water condition, the traversal is stopped, and the traversed unit time is used as the waiting drinking water time.

[0010] In one embodiment, the preset drinking water condition is a body temperature parameter threshold; when the body temperature adjustment parameter of the target object within the traversed unit time meets the preset drinking water condition, the traversal is stopped, and the traversed unit time is used as the waiting drinking water time, including:

[0011] Match the body temperature regulation parameter of the target object in the traversed unit time with the body temperature parameter threshold to obtain a parameter matching result; when the parameter matching result indicates that the body temperature regulation parameter of the target object in the traversed unit time is greater than the body temperature parameter threshold, stop traversing, and use the traversed unit time as the waiting time for drinking water.

[0012] In one embodiment, determining the body temperature adjustment parameter of the target object during the traversal unit time according to the body temperature change value and the body temperature change rate includes:

[0013] For each of the multiple unit times traversed, determine the adjacent unit time located behind the unit time traversed; determine the rate of change of the target object's body temperature change rate in the unit time traversed according to the duration of the unit time traversed, the body temperature change rate of the target object in the unit time traversed, and the body temperature change rate in the adjacent unit time; determine the body temperature regulation parameter of the target object in the unit time traversed based on the duration of the unit time traversed, the body temperature change rate of the target object in the unit time traversed, and the change rate of the body temperature change rate of the target object in the unit time traversed.

[0014] In one embodiment, the determining of the body temperature adjustment parameter of the target object in the unit time traversed to is based on the duration of the unit time traversed to, the body temperature change rate of the target object in the unit time traversed to, and the rate of change of the body temperature change rate of the target object in the unit time traversed to, and is achieved by the following calculation formula:

[0015] d 2 T / dt 2 -μ(1-T 2 )dT / dt+T=0

[0016] Among them, d 2 T / dt 2 is the rate of change of the target object's body temperature change rate during the unit time traversed to, dT / dt is the rate of change of the target object's body temperature during the unit time traversed to, μ is the body temperature adjustment parameter of the target object during the unit time traversed to, T is the body temperature change value of the target object during the unit time traversed to, and t is the duration of the unit time traversed to.

[0017] In one embodiment, the body temperature value, body temperature change value, body temperature change rate, and rate of change of the body temperature change rate of the target object during the waiting time for drinking water are obtained; based on the body temperature value, body temperature change value, body temperature change rate, and rate of change of the body temperature change rate of the target object during the waiting time for drinking water, an image to be detected is generated; a drinking water prediction model is obtained, and the image to be detected is processed by the drinking water prediction model to obtain the amount of drinking water and the drinking water temperature required by the target object.

[0018] In one embodiment, the drinking water detection model includes at least a backbone network, a drinking water volume branch module, and a drinking water temperature branch module; the processing of the image to be detected by the drinking water prediction model to obtain the drinking water volume and drinking water temperature required by the target object includes:

[0019] Obtain a water intake weight matrix and a water intake temperature weight matrix; perform feature extraction on the image to be detected through the backbone network to obtain an initial feature map; perform linear and nonlinear transformations on the initial feature map corresponding to the water intake weight matrix through the water intake branch module to obtain a water intake convolution feature map; determine a water intake pooling feature map based on the maximum eigenvalue of the water intake convolution feature map on each feature channel; perform linear and nonlinear transformations on the initial feature map corresponding to the water intake temperature weight matrix through the water intake temperature branch module to obtain a water intake temperature convolution feature map. A drinking water temperature pooled feature map is determined based on the average eigenvalue of the drinking water temperature convolution feature map on each feature channel; the drinking water amount pooled feature map and the drinking water temperature pooled feature map are flattened and straightened respectively to obtain a drinking water amount feature vector and a drinking water temperature feature vector; the drinking water amount feature vector is converted into a drinking water amount probability distribution feature vector, and the drinking water temperature feature vector is converted into a drinking water temperature probability distribution feature vector; the drinking water amount required by the target object is determined based on the drinking water amount probability distribution feature vector, and the drinking water temperature required by the target object is determined based on the drinking water temperature probability distribution feature vector.

[0020] In one embodiment, the body temperature data of the target object regarding the amount of water drunk and the temperature of the water drunk is received; the body temperature parameter threshold is updated according to the body temperature data of the target object regarding the amount of water drunk and the temperature of the water drunk to obtain an updated body temperature parameter threshold; and the updated body temperature parameter threshold is used as the preset drinking condition for the target object after the waiting time for drinking water.

[0021] In a second aspect, the present application also provides an intelligent water drinking reminder device, comprising:

[0022] An acquisition module is used to traverse the unit time of the target object after drinking the water, and obtain the body temperature change value of the target object during the traversed unit time;

[0023] A first determining module is configured to determine a body temperature change rate of the target object within a unit time traversed according to the body temperature change value and a duration of the unit time traversed;

[0024] a second determining module, configured to determine a body temperature adjustment parameter of the target object during the unit time traversed to according to the body temperature change value and the body temperature change rate;

[0025] The stopping module is used to stop traversing when the body temperature adjustment parameter of the target object in the traversed unit time meets the preset drinking water condition, and use the traversed unit time as the waiting drinking water time.

[0026] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0027] Traversing the unit time of the target object after drinking the water, and obtaining the temperature change value of the target object in the traversed unit time;

[0028] Determine the temperature change rate of the target object within the unit time traversed according to the temperature change value and the duration of the unit time traversed;

[0029] Determining a body temperature adjustment parameter of the target object within a unit time traversed to according to the body temperature change value and the body temperature change rate;

[0030] When the body temperature adjustment parameter of the target object in the traversed unit time meets the preset drinking water condition, the traversal is stopped, and the traversed unit time is used as the waiting drinking water time.

[0031] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0032] Traversing the unit time of the target object after drinking the water, and obtaining the temperature change value of the target object in the traversed unit time;

[0033] Determine the temperature change rate of the target object within the unit time traversed according to the temperature change value and the duration of the unit time traversed;

[0034] Determining a body temperature adjustment parameter of the target object within a unit time traversed to according to the body temperature change value and the body temperature change rate;

[0035] When the body temperature adjustment parameter of the target object in the traversed unit time meets the preset drinking water condition, the traversal is stopped, and the traversed unit time is used as the waiting drinking water time.

[0036] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0037] Traversing the unit time of the target object after drinking the water, and obtaining the temperature change value of the target object in the traversed unit time;

[0038] Determine the temperature change rate of the target object within the unit time traversed according to the temperature change value and the duration of the unit time traversed;

[0039] Determining a body temperature adjustment parameter of the target object within a unit time traversed to according to the body temperature change value and the body temperature change rate;

[0040] When the body temperature adjustment parameter of the target object in the traversed unit time meets the preset drinking water condition, the traversal is stopped, and the traversed unit time is used as the waiting drinking water time.

[0041] The above-mentioned intelligent drinking water reminder method, device, computer equipment, computer-readable storage medium and computer program product traverse the unit time of the target object after drinking water to obtain the temperature change value of the target object within the traversed unit time; achieve detailed tracking of the user's body temperature changes after drinking water, and can more accurately capture the trend of body temperature changes over time, ensuring the timeliness and accuracy of the data.

[0042] Based on the temperature change value and the duration of the traversed unit time, the target subject's temperature change rate within the traversed unit time is determined. Understanding the temperature change rate can help the system better understand the user's physiological response patterns and the impact of drinking water on their body temperature. Calculating the temperature change rate provides a basis for scientifically evaluating the timing and amount of drinking water, making regulatory measures more targeted and effective.

[0043] Based on the temperature change value and temperature change rate, the target subject's temperature regulation parameters for the unit time traversed are determined. The specific temperature change information and change rate are combined to set personalized temperature regulation parameters. These parameters reflect the user's current physical condition and their response to specific water volume, temperature, and intake time. Based on this, more reasonable recommendations or automatic adjustment strategies can be made to achieve optimal health management and immunity enhancement.

[0044] When the target subject's body temperature regulation parameters within the traversed unit time meet the preset drinking conditions, the traversal stops and the traversed unit time is set as the waiting time for drinking water. Once the appropriate time for drinking water is determined (i.e., when the body temperature regulation parameters fall within the preset ideal range), action is immediately taken or corresponding guidance is provided to the user. This not only avoids ineffective or even harmful premature or delayed drinking behaviors, but also promotes the formation of good living habits, further supporting long-term health maintenance and strengthening personal immunity. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 This is a diagram of an application environment of an intelligent water drinking reminder method in one embodiment;

[0047] Figure 2 A schematic diagram of a flow chart of an intelligent water drinking reminder method according to an embodiment;

[0048] Figure 3 A schematic flow chart of an intelligent water drinking reminder method in another embodiment;

[0049] Figure 4 This is a structural block diagram of an intelligent water drinking reminder device in one embodiment;

[0050] Figure 5 This is a structural block diagram of an intelligent water drinking reminder device in another embodiment;

[0051] Figure 6 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0053] The intelligent drinking water reminder method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store data that server 104 needs to process. The data storage system can be integrated with server 104, or located in the cloud or on another network server. Terminal 102 is configured to generate a smart drinking reminder request and send it to server 104. Server 104 stops traversing when the target subject's body temperature adjustment parameters meet preset drinking conditions within a traversed unit time and sets the traversed unit time as the waiting time for drinking water. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart car devices, projectors, etc. Portable wearable devices can include smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices can include virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 may be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0054] In an exemplary embodiment, Figure 2 As shown, a smart drinking water reminder method is provided, which is applied to Figure 1 The server 104 in the example is used as an example to illustrate the process, including the following steps 202 to 208.

[0055] Step 202: traverse the unit time of the target object after drinking the water, and obtain the temperature change value of the target object in the traversed unit time.

[0056] The target user is the user who uses this intelligent drinking water regulation method. By monitoring the user's various physiological parameters (such as body temperature, heart rate, etc.) and environmental factors (such as ambient temperature), personalized health management suggestions are provided to the user.

[0057] A unit time is the time interval used to monitor and analyze a user's body temperature changes. For example, data collection and processing can be performed every minute or every five minutes. By continuously observing the user's physiological state within each unit time period, more detailed body temperature fluctuation patterns can be captured.

[0058] The temperature change value refers to the change in a user's body temperature during a specific unit of time relative to the previous unit of time or baseline level. Specifically, it is the difference between the temperature measurement at the current unit of time and the temperature measurement at the previous unit of time. This metric is crucial for understanding how drinking affects human body temperature and forms the basis for subsequently calculating the temperature change rate and determining temperature regulation parameters.

[0059] Specifically, the first step is to define the unit time and the monitoring start point. Set a reasonable unit time length (for example, every 5 or 10 minutes) as the interval for analyzing the user's body temperature changes. Also, record the specific time when the user actually drinks the recommended amount of water. This time point will serve as the starting point for subsequent traversal analysis.

[0060] The second step is to start traversing unit time, starting from the moment the user drinks water and setting the first unit time window (for example, 0 to 5 minutes after drinking water). During each unit time, the sensor continuously monitors the user's body temperature and saves the reading.

[0061] The third step is to calculate the temperature change per unit time. At the end of that unit time (e.g., the 5th minute), the user's temperature is recorded. This temperature value is subtracted from the end of the previous unit time (if it is the first unit time, this may be the baseline temperature before drinking water) or the temperature at the time of drinking water to calculate the temperature change for that unit time. The calculated temperature change value is saved along with the corresponding timestamp for further analysis.

[0062] The fourth step is to iterate through more time units. If the stopping condition (i.e., the body temperature regulation parameters meet the preset drinking conditions) has not been reached, the current time unit is advanced by one time unit (for example, from the 5th minute to the 10th minute), and steps 2 and 3 are repeated. This process continues until a time unit is found during which the body temperature regulation parameters meet the predetermined standard.

[0063] Step 204 : determining the temperature change rate of the target object within the traversed unit time according to the temperature change value and the duration of the traversed unit time.

[0064] The unit time duration refers to a fixed period of time set to monitor the user's physiological response after drinking water. For example, a unit time could be 1 minute, 5 minutes, or 10 minutes. During this fixed period, the user's body temperature data is collected and analyzed accordingly. The choice of unit time depends on the required data resolution and real-time requirements; shorter unit times can provide more detailed trends but may require more computing resources.

[0065] The body temperature rate of change refers to the rate at which body temperature changes within a given unit of time. It can be calculated by dividing the temperature change by the corresponding unit of time (temperature rate of change = temperature change / unit of time). This metric reflects the speed of body temperature change over time and is crucial for understanding how hydration affects body temperature. The temperature rate of change helps identify rapid increases or decreases in body temperature, enabling the system to determine when and how to intervene to achieve optimal temperature regulation.

[0066] Specifically, first obtain the temperature change value, and obtain the user's temperature reading at the end of a specific unit time from the sensor. Compare the body temperature at the end of the current unit time with the body temperature at the end of the previous unit time (or the basal body temperature before drinking water) to obtain the temperature change during this period. The temperature change value in this step is expressed as , where Tend is the body temperature at the end of the current unit time, and Tstart is the body temperature at the end of the previous unit time.

[0067] Then confirm the unit time length and make sure that the specific duration of each unit time has been defined, such as 5 minutes, 10 minutes, etc. Optionally, if the actual duration deviates slightly due to some reasons during the actual monitoring process, you need to record the actual time interval for subsequent accurate calculation of the body temperature change rate.

[0068] Next, calculate the temperature change rate using the known temperature change value ΔT and the corresponding unit time length Δt. The temperature change rate, R, can be calculated using the following formula: R = ΔT\Δt, where ΔT is the temperature change value and Δt is the actual unit time length. To facilitate comparison across different time periods, the calculated temperature change rate may need to be normalized, for example, by converting it to a change per minute or hour.

[0069] Finally, the temperature change rate is recorded and analyzed, and the calculated temperature change rate and corresponding time point are stored for subsequent data analysis. Based on the temperature change rate over multiple consecutive time units, the user's temperature change trend can be further analyzed to identify any significant change patterns or abnormalities.

[0070] Step 206 : Determine the temperature adjustment parameter of the target object within the unit time of the traversal according to the temperature change value and the temperature change rate.

[0071] Thermoregulation parameters refer to a set of data used to evaluate or guide thermoregulation, determined based on the target subject's temperature change value and temperature change rate. These parameters are derived by analyzing the user's physiological data (such as body temperature, heart rate, ambient temperature, water intake, and exercise intensity) using the Vanderpol oscillator equation and machine learning algorithms.

[0072] Specifically, the approach begins by analyzing temperature trends. Using the Vanderpol oscillator equation combined with historical temperature data, the team predicts likely future temperature trends. Using machine learning algorithms, the team then analyzes current temperature changes and their rates of change against patterns from similar past events to identify patterns.

[0073] Then, the body temperature regulation parameters are determined. Based on the body temperature change value and the body temperature change rate, combined with the prediction results of the Vanderpol oscillator equation and the evaluation of the drinking water intervention effect by the machine learning model, a series of evaluation indicators are set as the body temperature regulation parameters. It can be understood that the body temperature regulation parameters can be set according to actual needs. For example:

[0074] Optionally, the temperature regulation parameter is the expected body temperature, which predicts the future body temperature level based on the current body temperature change trend.

[0075] Optionally, the temperature regulation parameter is the temperature adjustment speed, which is the time required for the body temperature to reach the expected healthy range from the current value.

[0076] Optionally, the temperature regulation parameter is an intervention effectiveness score that quantifies the effect of drinking water on temperature regulation, such as whether the temperature drop meets the expected value.

[0077] Step 208: When the temperature regulation parameter of the target object in the traversed unit time meets the preset drinking water condition, the traversal is stopped, and the traversed unit time is used as the waiting time for drinking water.

[0078] The preset drinking water conditions refer to a series of standards or thresholds set based on the user's health management and body temperature regulation goals. When the conditions are met, it means that drinking water can most effectively help the user achieve their health management goals, especially the optimization and regulation of basal body temperature. It is understandable that the preset drinking water conditions can be set according to actual needs. For example:

[0079] Optionally, the body temperature is varied within a specified range, such as a decrease in body temperature to a level believed to be beneficial for immune system health.

[0080] Optionally, the body temperature change rate (i.e., the rate at which the body temperature changes over time) meets certain requirements, for example, the rate at which the body temperature drops is as expected.

[0081] Optionally, other physiological parameters (such as heart rate, ambient temperature, etc.) are in ideal conditions or have no negative impact on body temperature regulation.

[0082] Optionally, the body temperature prediction result calculated based on the Vanderpol oscillator equation and the machine learning algorithm indicates that it is the best time to drink water.

[0083] The optimal drinking time is determined after traversal analysis. Specifically, after drinking water, the system monitors the user's body temperature per unit time (e.g., per minute) and calculates the corresponding temperature change rate. When the monitored data meets the preset drinking conditions, further traversal stops and the corresponding unit time is marked as the optimal drinking time recommended to the user. This time point is designed to ensure that the user can consume water at the most appropriate time to effectively regulate basal body temperature and promote overall health.

[0084] Specifically, first check whether the preset drinking water conditions are met, and compare the body temperature regulation parameters in the current unit time with the ideal health management standards or thresholds preset by the system. Then determine and record the time to drink water. If the body temperature regulation parameters in the current unit time meet the preset drinking water conditions, it indicates that this is the ideal time to drink water. Stop further traversal. Mark the current traversed unit time as the time to drink water and record it. Finally, the user interface module displays the time to drink water and the recommended specific drinking water temperature and amount to the user. Optionally, the user is allowed to manually adjust the drinking water parameters according to personal circumstances, and user feedback is incorporated into subsequent model optimization.

[0085] In one embodiment, the body temperature regulation parameter of the target object in the traversed unit time is matched with the body temperature parameter threshold to obtain a parameter matching result; when the parameter matching result indicates that the body temperature regulation parameter of the target object in the traversed unit time is greater than the body temperature parameter threshold, the traversal is stopped, and the traversed unit time is used as the waiting time for drinking water.

[0086] The temperature parameter threshold refers to a set of values ​​preset by the system to determine whether the user's body temperature has reached an ideal health standard. Understandably, this temperature parameter threshold is used to ensure that drinking water intervention can effectively and safely regulate body temperature to achieve the goal of optimizing immune function.

[0087] The parameter matching result is obtained by comparing the actual measured temperature regulation parameters with the preset temperature parameter thresholds. This process involves evaluating whether the temperature regulation parameters meet the preset threshold conditions. If the temperature regulation parameters exceed the preset thresholds (for example, if the temperature drops too much or the temperature changes too quickly), it is considered not meeting health requirements. Conversely, if the temperature regulation parameters remain within the ideal range, it is considered to meet health management standards.

[0088] Specifically, data collection is first performed, using sensors (such as body temperature sensors, heart rate sensors, etc.) to monitor the user's physiological parameters in real time. After the user drinks a certain amount of water, the user's body temperature changes within each unit of time (for example, every minute) are recorded.

[0089] Thermoregulation parameters are then calculated. For each unit time point, the temperature change (i.e., the temperature difference between the current time point and the previous time point) is calculated. Based on the temperature change and the unit time length, the temperature change rate is calculated. Future temperature trends are predicted using the Vanderpol oscillator equation, and this data is analyzed with a machine learning algorithm to determine the thermoregulation parameters for that unit time.

[0090] Next, the temperature parameter thresholds are set, and a series of temperature parameter thresholds are pre-set. Optionally, these thresholds are ideal health ranges defined based on medical standards or research results. And the parameters are matched, and the temperature regulation parameters calculated in each unit time are compared with the preset temperature parameter thresholds. If a temperature regulation parameter exceeds the corresponding threshold (for example, the temperature change rate is greater than the maximum allowable change rate), it is considered that the time point has been reached to stop traversal and recommend drinking water. It can be understood that the "matching" in this step means checking whether the actually measured temperature regulation parameters meet or exceed the pre-set health management standards.

[0091] The matching results are then determined and analyzed. If the temperature regulation parameters exceed the preset threshold, the current unit time is a critical node, and further traversal should be stopped. For example, if the temperature change rate exceeds the preset maximum value, it indicates that the temperature regulation effect is significant and has reached the ideal state.

[0092] Finally, the waiting time for drinking water is determined. When the parameter matching result shows that the body temperature regulation parameter is greater than the preset threshold, the system marks the currently traversed unit time as the waiting time for drinking water. It can be understood that the waiting time for drinking water is the best time for the system to recommend the user to drink water next time. Drinking water at this time is considered to be the most effective way to help the user maintain a healthy body temperature level. Optionally, the recommended waiting time for drinking water and related drinking water suggestions, such as the recommended drinking water temperature and amount, are displayed through the user interface. Users are allowed to view specific monitoring data, prediction results, and personalized drinking water suggestions, and manual adjustment options are provided.

[0093] Since the body temperature parameter threshold is pre-set, if the body temperature regulation parameter exceeds the preset threshold, it may indicate that the body is undergoing some adverse changes. Promptly detecting these situations can help users take measures to avoid physical discomfort or other health problems caused by improper drinking.

[0094] In one embodiment, for each of a plurality of traversed unit times, an adjacent unit time located behind the traversed unit time is determined; based on the length of the traversed unit time, the temperature change rate of the target object in the traversed unit time, and the temperature change rate in the adjacent unit time, the rate of change of the temperature change rate of the target object in the traversed unit time is determined; based on the length of the traversed unit time, the temperature change rate of the target object in the traversed unit time, and the rate of change of the temperature change rate of the target object in the traversed unit time, the temperature regulation parameter of the target object in the traversed unit time is determined.

[0095] The adjacent unit time refers to the next unit time immediately following the currently traversed unit time. For example, if the currently traversed time period is from minute n to minute n+1, then the adjacent unit time is from minute n+1 to minute n+2. It can be understood that by comparing the data of the current unit time with its adjacent unit time, the trend of body temperature changes can be analyzed in more detail, thereby providing more accurate information for subsequent calculation of body temperature regulation parameters.

[0096] The rate of change of body temperature refers to how the rate of temperature change itself changes over time. It describes how the rate of temperature change accelerates or decelerates over time. Simply put, it is the first derivative of the rate of temperature change. For example, if the rate of temperature change is 0.1°C / minute over a certain unit of time, and then changes to 0.2°C / minute over the next unit of time, then the rate of change is (0.2 - 0.1) / unit of time = 0.1°C / minute.

[0097] Specifically, the adjacent unit time is first determined. For each unit time (e.g., every minute) after the user drinks the water, the adjacent unit time is processed one by one. For each unit time currently traversed, the immediately following unit time is found. For example, if the current unit time is from minute t to minute t+1, the adjacent unit time is from minute t+1 to minute t+2.

[0098] Then calculate the rate of change of body temperature change rate, based on the user's body temperature change value and unit time length in the current unit time, calculate the body temperature change rate R in the current unit time t Similarly, based on the user's body temperature change value and unit time length in adjacent unit time, the body temperature change rate R in adjacent unit time is calculated. t+1 The body temperature change rate ΔR is calculated using the body temperature change rate of the current unit time and the adjacent unit time. The specific formula is: ΔR=(R t+1 -R t )\Δt.

[0099] Among them, Δt is the duration of unit time, ΔR is the rate of change of body temperature, R t R is the rate of change of body temperature per unit time. t+1 is the rate of change of body temperature in adjacent unit time.

[0100] Finally, the temperature regulation parameters are determined based on the duration of the unit time traversed and the temperature change rate R in the current unit time. t , and the rate of change of body temperature change rate ΔR, to comprehensively analyze the user's body temperature regulation status. Based on these data analysis results, the target object's body temperature regulation parameters in the current unit time are determined.

[0101] By analyzing temperature changes within each unit of time and its adjacent units of time in detail, the system can capture subtle dynamics of temperature changes. This provides more information than temperature measurements taken at a single point in time, helping to more accurately understand the user's physiological state. Furthermore, by comprehensively considering an individual's temperature change rate and its rate of change, the system can provide personalized hydration recommendations. This personalized health management solution better meets the specific needs of users, improving user experience and satisfaction.

[0102] In one embodiment, based on the duration of the unit time traversed to, the temperature change rate of the target object in the unit time traversed to, and the rate of change of the temperature change rate of the target object in the unit time traversed to, the temperature adjustment parameter of the target object in the unit time traversed to is determined by the following calculation formula: 2 T / dt 2 -μ(1-T 2 )dT / dt+T=0.

[0103] Among them, d 2 T / dt 2 is the rate of change of the target object's body temperature change rate during the unit time traversed to, dT / dt is the rate of change of the target object's body temperature during the unit time traversed to, μ is the body temperature regulation parameter of the target object during the unit time traversed to, T is the target object's body temperature change value during the unit time traversed to, and t is the duration of the unit time traversed to.

[0104] Specifically, data collection is first performed, using the sensor module to monitor the user's physiological parameters in real time, including body temperature, heart rate, ambient temperature, water intake, and exercise volume. The temperature change value T per unit time after the user drinks water is recorded.

[0105] Then calculate the body temperature change rate. For each unit time, calculate the body temperature change rate dT / dt. This can be obtained by dividing the body temperature difference between two adjacent time points by the unit time length: dT / dt=(T t+1 -Tt )\Δt.

[0106] Among them, T t and T t+1 are the body temperature values ​​at the current time and the next time point respectively, and Δt is the length of the unit time.

[0107] Next, calculate the rate of change of body temperature change rate, and calculate the rate of change of body temperature change rate d 2 T / dt 2 , which can be obtained by dividing the difference in the body temperature change rate between two adjacent unit times by the unit time length:

[0108] d 2 T / dt 2 =[(dT / dt) t+1 -(dT / dt) t ] / Δt.

[0109] Where, (dT / dt) t and (dT / dt) t+1 are the body temperature change rates of the current unit time and the next unit time respectively.

[0110] Then determine the thermoregulatory parameter μ and use the Vanderpol oscillator equation to determine the thermoregulatory parameter μ. 2 T / dt 2 , dT / dt and T value are substituted into the equation: 2 T / dt 2 -μ(1-T 2 )dT / dt+T=0. By solving this nonlinear equation, the value of μ can be obtained.

[0111] The μ value calculated through the above steps reflects the intensity of body temperature regulation required within the current unit time to ensure that body temperature changes conform to the pattern described by the Vanderpol oscillator equation. For example, a large μ may indicate more drastic body temperature changes, requiring stronger regulation; a small μ may indicate more gradual body temperature changes, requiring less regulation. Optionally, based on the calculated μ value and other relevant data, personalized water drinking recommendations can be generated, such as the optimal time, temperature, and amount of water to drink, to help users scientifically regulate their basal body temperature, thereby enhancing immune system function and overall health.

[0112] The Vanderpol oscillator equation allows for more accurate simulation and prediction of the cyclical changes in body temperature. This nonlinear differential equation captures the complex dynamics of body temperature changes, providing more precise predictions than simple linear models. Furthermore, the determination of the thermoregulatory parameter μ enables the system to scientifically control the timing, temperature, and amount of water intake. By optimizing these parameters, basal body temperature can be more effectively regulated, thereby enhancing immune system function.

[0113] In one embodiment, the body temperature value, body temperature change value, body temperature change rate, and rate of change of the body temperature change rate of the target object during the time waiting to drink water are obtained; based on the body temperature value, body temperature change value, body temperature change rate, and rate of change of the body temperature change rate of the target object during the time waiting to drink water, an image to be detected is generated; a drinking water prediction model is obtained, and the image to be detected is processed by the drinking water prediction model to obtain the amount of drinking water and the drinking water temperature required by the target object.

[0114] The body temperature value refers to the actual body temperature value measured at a specific time point (i.e., the time to drink water). This is usually collected in real time by the body temperature sensor in the sensor module, reflecting the user's current body temperature status.

[0115] The image to be tested refers to a visual representation generated based on the target subject's body temperature value, temperature change value, temperature change rate, and rate of change of temperature change rate during the drinking time. It can be understood that the image to be tested is generated to facilitate analysis and processing by the machine learning model, and it can intuitively reflect the user's physiological state. The image to be tested can be in various forms, such as:

[0116] Optional, time series graph showing the trend of body temperature over time.

[0117] Optionally, a scatter plot or heat map can be used to show the relationship between different physiological parameters.

[0118] Optionally, a multi-dimensional feature vector graph combines multiple physiological parameters into a feature vector and represents it in the form of an image.

[0119] A water intake prediction model is a machine learning model trained based on historical data. Its purpose is to predict the optimal amount and temperature of water intake based on input physiological parameters (such as body temperature and temperature fluctuation). This application does not impose specific restrictions on the water intake prediction model, and it can be configured according to actual needs. For example, the model can use a variety of algorithms, such as neural networks, support vector machines, and decision trees. By learning from a large amount of historical data, the model can identify the complex relationship between body temperature fluctuations and water intake needs and make accurate predictions based on this relationship.

[0120] The recommended amount of water a user should consume during their drinking time is the recommended amount of water. This amount is based on the user's current physiological state (including body temperature and its fluctuations) and personal health goals, and is intended to help maintain good physical condition and optimize immune function.

[0121] Drinking water temperature refers to the specific temperature of water recommended for users to drink. This temperature is also recommended based on the user's current physiological state and health needs. Different body temperature regulation needs may correspond to different drinking water temperatures to achieve the best body temperature regulation effect.

[0122] Specifically, first obtain physiological parameters and use sensor modules (such as body temperature sensors, heart rate sensors, etc.) to monitor the user's body temperature in real time during the waiting time for drinking water. Record the user's body temperature change from the previous unit time to the current waiting time for drinking water. For example, if the body temperature in the previous unit time is T t-1 , the current body temperature at the time of drinking water is T t , then the body temperature change value is Δt=T t - T t-1 Based on the temperature change value and the unit time duration, calculate the temperature change rate. The formula is: dT / dt=ΔT\Δt. Where Δt is the unit time duration. Determine the temperature change rate in adjacent unit times and calculate the rate of change of the temperature change rate. The formula is:

[0123] d 2 T / dt 2 =[(dT / dt) t+1 -(dT / dt) t ] / Δt.

[0124] Where, (dT / dt) t and (dT / dt) t+1 are the body temperature change rates of the current unit time and the next unit time respectively.

[0125] The calculated body temperature value, temperature change value, temperature change rate, and rate of change of temperature change rate are then integrated. Based on these physiological parameters, a visualization image is generated. The generated image is then preprocessed, such as normalization and noise reduction, to facilitate subsequent machine learning model processing.

[0126] This application does not make any specific limitation on the visual image, and it can be set according to actual needs.

[0127] Optional, a time series graph to show the temperature trend over time.

[0128] Optionally, a scatter plot or heat map can be used to show the relationship between different physiological parameters.

[0129] Optionally, a multi-dimensional feature vector map is used to combine multiple physiological parameters into a feature vector and represent it in the form of an image.

[0130] Finally, a pre-trained water consumption prediction model is loaded. This model may have been trained based on historical data, using algorithms such as neural networks, support vector machines, and decision trees. The generated image to be tested is provided as input to the water consumption prediction model. The water consumption prediction model analyzes and processes the input image, identifying patterns within the image and making predictions based on them. After processing, the model outputs the target user's required water consumption and drinking temperature. These predictions provide recommendations based on the user's current physiological state and health needs.

[0131] Because users can visually visualize their physiological status (e.g., images to be tested) and understand how the system generates drinking recommendations based on this data, this transparency increases user trust and engagement. Drinking recommendations are generated based on the user's actual physiological parameters, ensuring that the recommended amount and temperature are tailored to individual needs. This personalized advice can better meet the user's specific health needs than generic recommendations, thereby improving health management effectiveness.

[0132] In one embodiment, a water intake weight matrix and a water temperature weight matrix are obtained; a feature extraction is performed on the image to be detected through a backbone network to obtain an initial feature map; a linear transformation and a nonlinear transformation corresponding to the water intake weight matrix are performed on the initial feature map through a water intake branch module to obtain a water intake convolution feature map; a water intake pooling feature map is determined based on the maximum eigenvalue of the water intake convolution feature map on each feature channel; a linear transformation and a nonlinear transformation corresponding to the water intake temperature weight matrix are performed on the initial feature map through a water intake temperature branch module to obtain a water intake temperature convolution feature map. The drinking water temperature pooling feature map is determined according to the average eigenvalue of the drinking water temperature convolution feature map on each feature channel; the drinking water amount pooling feature map and the drinking water temperature pooling feature map are flattened and straightened respectively to obtain the drinking water amount feature vector and the drinking water temperature feature vector; the drinking water amount feature vector is converted into the drinking water amount probability distribution feature vector, and the drinking water temperature feature vector is converted into the drinking water temperature probability distribution feature vector; the drinking water amount required by the target object is determined according to the drinking water amount probability distribution feature vector, and the drinking water temperature required by the target object is determined according to the drinking water temperature probability distribution feature vector.

[0133] The water intake weight matrix is ​​a pre-trained weight matrix used for linear transformation in the water intake branch module. It contains all the weight parameters required to transform the initial feature map into the water intake convolution feature map.

[0134] The water temperature weight matrix is ​​another pre-trained weight matrix used for linear transformation in the water temperature branch module. It contains all the weight parameters required to transform the initial feature map into the water temperature convolution feature map.

[0135] The backbone network is a deep neural network structure that is typically composed of multiple convolutional layers, pooling layers, and activation functions. Its main function is to extract high-level feature representations (i.e., initial feature maps) from the input image to be detected.

[0136] The water intake branch module is a submodule of the water intake prediction model that is specifically designed to process features related to water intake. It further processes the initial feature map extracted by the backbone network to generate the final water intake prediction result.

[0137] The convolutional feature map of water intake is the intermediate result obtained by performing linear transformations (using the water intake weight matrix) and nonlinear transformations (such as the ReLU activation function) on the initial feature map through the water intake branch module. This feature map contains detailed feature information related to water intake.

[0138] The water intake pooling feature map is obtained by taking the maximum value (max pooling operation) on each feature channel of the convolutional water intake feature map. This step helps reduce the spatial dimension of the feature map and retain the most important feature information.

[0139] The initial feature map refers to the high-level feature representation extracted by the backbone network from the input image to be detected. It is the basis for subsequent branch module processing.

[0140] The water temperature branch module is another submodule of the water prediction model, specifically designed to process features related to water temperature. It further processes the initial feature map extracted by the backbone network to generate the final water temperature prediction result.

[0141] The convolutional feature map of drinking water temperature is the intermediate result obtained by performing a linear transformation (using the drinking water temperature weight matrix) and a nonlinear transformation (such as the ReLU activation function) on the initial feature map through the drinking water temperature branch module. This feature map contains detailed feature information related to drinking water temperature.

[0142] The pooled drinking water temperature feature map is obtained by taking the average value of the convolutional feature map across each feature channel (average pooling). This step also helps reduce the spatial dimension of the feature map while retaining important feature information.

[0143] The water intake feature vector is the vector obtained by flattening and straightening the pooled water intake feature map. This vector contains all the feature information related to water intake and can be used for subsequent probability distribution calculations.

[0144] The drinking water temperature feature vector is the vector obtained by flattening and straightening the pooled drinking water temperature feature map. This vector contains all the feature information related to drinking water temperature and can be used for subsequent probability distribution calculations.

[0145] The water intake probability distribution feature vector is a vector obtained by converting the water intake feature vector into a probability distribution. Each element in this vector represents the probability of a different water intake amount, reflecting the system's confidence in the different water intake amounts.

[0146] The water temperature probability distribution feature vector is a vector obtained by converting the water temperature feature vector into a probability distribution. Each element in this vector represents the probability of a different water temperature, reflecting the system's confidence in the different water temperatures.

[0147] Specifically, the model first obtains the water intake and water temperature weight matrices. An image to be processed is fed into the model's backbone network. The backbone network typically contains multiple convolutional layers, activation functions such as ReLU (Rectified Linear Unit), and pooling layers to extract high-level, abstract features from the original input image. After a series of operations, one or more high-dimensional feature maps are output as "initial feature maps," capturing the key visual information of the input image.

[0148] The resulting "initial feature map" is then fed into the water intake branch module. A linear transformation is performed on this feature map using the water intake weight matrix. A nonlinear activation function (such as ReLU) is then applied to generate a convolutional water intake feature map. For each channel of the convolutional water intake feature map, the maximum value is pooled to form a new feature map, the pooled water intake feature map. This process helps emphasize the most important features and reduces computational complexity.

[0149] Next, the initial feature map is used again and fed into the water temperature branch module. A linear transformation is applied using the water temperature weight matrix, combined with nonlinear activation to generate a convolutional feature map for water temperature. Afterwards, average pooling is applied to each channel to create a pooled water temperature feature map. Average pooling helps preserve more detail while reducing dimensionality.

[0150] The pooled feature maps of water consumption and water temperature are then straightened into one-dimensional vectors, the so-called water consumption feature vector and water temperature feature vector, respectively. This step converts the spatially structured data into a format that is easier to process.

[0151] Finally, the water intake feature vector is converted into a water intake probability distribution feature vector using a fully connected layer or other appropriate method, where each element represents the probability of a different water intake level. The same method is applied to the water temperature feature vector to obtain a water temperature probability distribution feature vector, indicating the likelihood of different temperature levels. Based on the water intake probability distribution feature vector, the water intake with the highest probability is selected as the optimal water intake recommended to the user. Similarly, based on the water temperature probability distribution feature vector, the water temperature most likely to be suitable for the user is determined.

[0152] The above solution can achieve the following beneficial effects:

[0153] First, by using the pre-trained water intake weight matrix and water temperature weight matrix, personalized water intake recommendations can be provided based on individual user differences, better adapting to the needs of different users.

[0154] Second, the backbone network extracts features from the input image to be tested, capturing key information in the image. This provides high-quality basic features for subsequent water intake and temperature prediction.

[0155] Third, the model includes both a water intake branch module and a water temperature branch module, enabling simultaneous prediction of both water intake and water temperature during a single forward propagation. This multi-task learning approach improves the model's efficiency and accuracy.

[0156] Fourthly, through linear and nonlinear transformations, we generate convolutional feature maps of water intake and water temperature. These feature maps contain rich detailed information, which helps to more accurately predict water intake and water temperature.

[0157] Fifth, the water consumption feature map uses max pooling to retain the most important features in each feature channel. The water temperature feature map uses average pooling to smooth features and reduce noise. These two pooling methods combine their respective strengths to improve feature validity and robustness.

[0158] Sixth, flattening the pooled feature map into a feature vector simplifies the data structure and facilitates subsequent fully connected layer processing. This allows for efficient mapping of high-dimensional features to a low-dimensional space, reducing computational complexity.

[0159] Seventh aspect: By converting the feature vector into a probability distribution feature vector, the system can output the probability of each possible water consumption amount and water temperature. This method not only provides specific prediction results, but also gives the confidence level of the prediction, increasing the reliability and interpretability of the system.

[0160] Eighth aspect: The final water intake and drinking temperature are determined based on the probability distribution eigenvector, making the recommendations more scientific and reasonable. This data-driven approach can help users better regulate their body temperature, enhance the function of the immune system, and thus improve their overall health.

[0161] In one embodiment, the body temperature data of the target subject regarding the amount of water drunk and the temperature of the water drunk is received; the body temperature parameter threshold is updated according to the body temperature data of the target subject regarding the amount of water drunk and the temperature of the water drunk, to obtain an updated body temperature parameter threshold; and the updated body temperature parameter threshold is used as the preset drinking condition for the target subject after the waiting time for drinking.

[0162] Body temperature data refers to the actual body temperature measurement returned by the target user after drinking water according to the system's recommended amount and temperature. This data is typically collected in real time by sensors (such as body temperature sensors) and records the user's body temperature changes after drinking water.

[0163] Updated temperature parameter thresholds are the result of adjustments and optimizations to the original thresholds based on actual user feedback. This update is based on individual user differences and actual user experiences, making the thresholds more tailored to the user's actual situation, thereby improving the personalization and accuracy of health management. For example, if a user's temperature changes unexpectedly after drinking water as recommended by the system, the system may adjust the temperature change rate threshold to better suit the user's physiological characteristics.

[0164] The preset drinking conditions after the waiting time are the ideal conditions set by the system for the next drink after the user has finished drinking. These conditions are based on the updated body temperature parameter thresholds, ensuring more effective body temperature regulation the next time the user drinks.

[0165] Specifically, after the target subject drinks water according to the system's recommended amount and temperature, a sensor (such as a body temperature sensor) collects the user's body temperature data in real time. The immediate body temperature after drinking water and the temperature changes over time are recorded.

[0166] The collected feedback temperature data is then analyzed to assess the difference between actual temperature changes and expected results. Based on the analysis results, the original temperature parameter thresholds are adjusted. Optionally, machine learning algorithms or other optimization methods can be used to iterate and optimize the temperature parameter thresholds to better reflect individual user differences and actual conditions. For example, gradient descent methods or genetic algorithms can be used to find the optimal threshold.

[0167] Finally, the updated temperature parameter thresholds are stored as new preset drinking conditions. These conditions will serve as a reference for the next drinking session. As can be understood, based on the updated temperature parameter thresholds, new drinking recommendations are generated, including: determining the optimal time for the next drinking session based on temperature trends and prediction models; recommending an appropriate amount of water based on the temperature change rate and the user's historical data; and recommending the optimal drinking temperature based on temperature changes and user feedback.

[0168] By receiving actual user feedback, the system can continuously adjust and optimize temperature parameter thresholds to better suit individual user differences. This personalized management approach provides more precise health recommendations to meet the specific needs of different users. Through continuous data feedback and model updates, the system continuously learns and improves, gradually enhancing its performance. This continuous optimization capability allows the system to become increasingly intelligent and effective over time.

[0169] In an exemplary embodiment, Figure 3 As shown, it includes steps 302 to 312. Among them:

[0170] Step 302: traverse the unit time of the target object after drinking the water, and obtain the temperature change value of the target object during the traversed unit time;

[0171] Step 304: Determine the target object's body temperature change rate within the traversed unit time based on the body temperature change value and the duration of the traversed unit time;

[0172] Step 306: For each of the multiple traversed unit times, determine an adjacent unit time that follows the targeted traversed unit time; determine a rate of change of the target object's body temperature change rate within the targeted traversed unit time based on the duration of the traversed unit time, the target object's body temperature change rate within the targeted traversed unit time, and the body temperature change rate within the adjacent unit time; and determine a body temperature regulation parameter for the target object within the traversed unit time based on the duration of the traversed unit time, the target object's body temperature change rate within the traversed unit time, and the rate of change of the target object's body temperature change rate within the traversed unit time.

[0173] Step 308: Match the target subject's body temperature regulation parameter during the traversed unit time with the body temperature parameter threshold to obtain a parameter matching result. When the parameter matching result indicates that the target subject's body temperature regulation parameter during the traversed unit time is greater than the body temperature parameter threshold, the traversal is stopped and the traversed unit time is used as the waiting time for drinking water.

[0174] Step 310, obtain the target object's body temperature value, body temperature change value, body temperature change rate, and rate of change of the body temperature change rate during the drinking time; generate an image to be detected based on the target object's body temperature value, body temperature change value, body temperature change rate, and rate of change of the body temperature change rate during the drinking time; obtain a drinking water prediction model, obtain a drinking water weight matrix and a drinking water temperature weight matrix; perform feature extraction on the image to be detected through the backbone network to obtain an initial feature map; perform linear transformation and nonlinear transformation on the initial feature map corresponding to the drinking water weight matrix through the drinking water branch module to obtain a drinking water convolution feature map, and determine a drinking water pooling feature map based on the maximum eigenvalue of the drinking water convolution feature map on each feature channel; The water temperature branch module performs linear and nonlinear transformations on the initial feature map corresponding to the drinking water temperature weight matrix to obtain a drinking water temperature convolution feature map. Based on the average eigenvalue of the drinking water temperature convolution feature map on each feature channel, the drinking water temperature pooling feature map is determined. The drinking water volume pooling feature map and the drinking water temperature pooling feature map are flattened and straightened respectively to obtain a drinking water volume feature vector and a drinking water temperature feature vector. The drinking water volume feature vector is converted into a drinking water volume probability distribution feature vector, and the drinking water temperature feature vector is converted into a drinking water temperature probability distribution feature vector. Based on the drinking water volume probability distribution feature vector, the required drinking water volume of the target object is determined, and based on the drinking water temperature probability distribution feature vector, the required drinking water temperature of the target object is determined.

[0175] Step 312: Receive the temperature data of the target subject regarding the amount of water consumed and the temperature of the water consumed; update the temperature parameter threshold according to the temperature data of the target subject regarding the amount of water consumed and the temperature of the water consumed to obtain an updated temperature parameter threshold; and use the updated temperature parameter threshold as the preset drinking condition for the target subject after the waiting time for drinking water.

[0176] It should be understood that, although the steps in the flowcharts of the above embodiments are shown in sequence as indicated by the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily to be performed in sequence, but can be performed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0177] Based on the same inventive concept, embodiments of the present application also provide a smart drinking water reminder device for implementing the aforementioned smart drinking water reminder method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more smart drinking water reminder device embodiments provided below can be found in the above-described limitations of the smart drinking water reminder method and will not be further elaborated here.

[0178] In an exemplary embodiment, Figure 4 As shown, a smart drinking water reminder device 400 is provided, including: an acquisition module 402, a first determination module 404, a second determination module 406 and a stop module 408, wherein:

[0179] An acquisition module 402 is configured to traverse the target object's unit time after drinking the water, and obtain the target object's body temperature change value within the traversed unit time;

[0180] A first determining module 404 is configured to determine a temperature change rate of the target object within the traversed unit time according to the temperature change value and the duration of the traversed unit time;

[0181] The second determining module 406 is used to determine the temperature adjustment parameter of the target object within the unit time of the traversal according to the temperature change value and the temperature change rate;

[0182] The stopping module 408 is configured to stop traversing when the temperature adjustment parameter of the target object in the traversed unit time meets the preset drinking water condition, and use the traversed unit time as the waiting drinking water time.

[0183] In one embodiment, the stop module 408 is used to match the body temperature regulation parameter of the target object in the unit time traversed to the body temperature parameter threshold to obtain a parameter matching result; when the parameter matching result indicates that the body temperature regulation parameter of the target object in the unit time traversed to the body temperature parameter threshold is greater than the body temperature parameter threshold, the traversal is stopped, and the traversed unit time is used as the waiting time for drinking water.

[0184] In one embodiment, the second determination module 406 is used to determine, for each of a plurality of traversed unit times, an adjacent unit time located behind the traversed unit time; determine the rate of change of the target object's body temperature change rate in the traversed unit time according to the length of the traversed unit time, the target object's body temperature change rate in the traversed unit time, and the body temperature change rate in the adjacent unit time; determine the temperature regulation parameter of the target object in the traversed unit time based on the length of the traversed unit time, the target object's body temperature change rate in the traversed unit time, and the rate of change of the target object's body temperature change rate in the traversed unit time.

[0185] In one embodiment, the second determining module 406 is configured to be implemented by the following calculation formula:

[0186] d 2 T / dt 2 -μ(1-T 2 )dT / dt+T=0

[0187] Among them, d 2 T / dt 2 is the rate of change of the target object's body temperature change rate during the unit time traversed to, dT / dt is the rate of change of the target object's body temperature during the unit time traversed to, μ is the body temperature regulation parameter of the target object during the unit time traversed to, T is the target object's body temperature change value during the unit time traversed to, and t is the duration of the unit time traversed to.

[0188] In one embodiment, the intelligent drinking water reminder device also includes a prediction module 410, which is used to obtain the target object's body temperature value, body temperature change value, body temperature change rate, and rate of change of the body temperature change rate during the drinking water waiting time; generate an image to be detected based on the target object's body temperature value, body temperature change value, body temperature change rate, and rate of change of the body temperature change rate during the drinking water waiting time; obtain a drinking water prediction model, and process the image to be detected through the drinking water prediction model to obtain the amount of drinking water and the drinking water temperature required by the target object.

[0189] In one embodiment, the intelligent drinking water reminder device further includes a prediction module 410 for obtaining a water intake weight matrix and a water intake temperature weight matrix; performing feature extraction on the image to be detected through the backbone network to obtain an initial feature map; performing linear transformation and nonlinear transformation corresponding to the water intake weight matrix on the initial feature map through the water intake branch module to obtain a water intake convolution feature map; determining a water intake pooling feature map based on the maximum eigenvalue of the water intake convolution feature map on each feature channel; performing linear transformation and nonlinear transformation corresponding to the water intake temperature weight matrix on the initial feature map through the water intake branch module. The drinking water temperature convolution feature map is obtained by performing the transformation, and the drinking water temperature pooling feature map is determined according to the average eigenvalue of the drinking water temperature convolution feature map on each feature channel; the drinking water amount pooling feature map and the drinking water temperature pooling feature map are flattened and straightened respectively to obtain the drinking water amount feature vector and the drinking water temperature feature vector; the drinking water amount feature vector is converted into the drinking water amount probability distribution feature vector, and the drinking water temperature feature vector is converted into the drinking water temperature probability distribution feature vector; the drinking water amount required by the target object is determined according to the drinking water amount probability distribution feature vector, and the drinking water temperature required by the target object is determined according to the drinking water temperature probability distribution feature vector.

[0190] In one embodiment, the intelligent drinking water reminder device also includes an updating module 412, which is used to receive the body temperature data of the target object regarding the amount of water drunk and the temperature of the water drunk; based on the body temperature data of the target object regarding the amount of water drunk and the temperature of the water drunk, the body temperature parameter threshold is updated to obtain an updated body temperature parameter threshold; and the updated body temperature parameter threshold is used as the preset drinking condition for the target object after the waiting time for drinking water.

[0191] In another embodiment, if Figure 5 As shown, Figure 5This is a structural block diagram of an intelligent water drinking reminder device in another embodiment, comprising: an acquisition module 402, a first determination module 404, a second determination module 406 and a stop module 408. The intelligent water drinking reminder device 400 further comprises a prediction module 410 and an update module 412. The prediction module 410 is used to obtain the target object's body temperature value, body temperature change value, body temperature change rate and the rate of change of the body temperature change rate during the time to drink water; based on the target object's body temperature value, body temperature change value, body temperature change rate and the rate of change of the body temperature change rate during the time to drink water, generate an image to be detected; obtain a water drinking prediction model, obtain a water drinking weight matrix and a water drinking temperature weight matrix; perform feature extraction on the image to be detected through the backbone network to obtain an initial feature map; perform linear transformation and nonlinear transformation on the initial feature map corresponding to the water drinking weight matrix through the water drinking branch module to obtain a water drinking convolution feature map, and determine a water drinking pooling feature map based on the maximum eigenvalue of the water drinking convolution feature map on each feature channel; The drinking water temperature branch module performs linear and nonlinear transformations on the initial feature map corresponding to the drinking water temperature weight matrix to obtain a drinking water temperature convolution feature map. Based on the average eigenvalue of the drinking water temperature convolution feature map on each feature channel, a drinking water temperature pooled feature map is determined. The drinking water volume pooled feature map and the drinking water temperature pooled feature map are flattened and straightened, respectively, to obtain a drinking water volume feature vector and a drinking water temperature feature vector. The drinking water volume feature vector is converted into a drinking water volume probability distribution feature vector, and the drinking water temperature feature vector is converted into a drinking water temperature probability distribution feature vector. The target subject's required drinking water volume is determined based on the drinking water volume probability distribution feature vector, and the target subject's required drinking water temperature is determined based on the drinking water temperature probability distribution feature vector. The updating module 412 is configured to receive body temperature data feedback from the target subject regarding drinking water volume and drinking water temperature. Based on the body temperature data feedback from the target subject regarding drinking water volume and drinking water temperature, the target subject's body temperature parameter threshold is updated to obtain an updated body temperature parameter threshold. The updated body temperature parameter threshold serves as the target subject's preset drinking condition after the waiting time for drinking water.

[0192] Each module in the aforementioned intelligent water drinking reminder device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device's memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0193] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data related to smart water drinking reminders. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a smart water drinking reminder method is implemented.

[0194] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0195] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0196] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0197] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0198] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0199] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0200] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0201] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. An intelligent drinking water reminder method, characterized in that: The intelligent water drinking reminder method includes: Traversing the unit time of the target object after drinking the water, and obtaining the temperature change value of the target object in the traversed unit time; Determine the temperature change rate of the target object within the unit time traversed according to the temperature change value and the duration of the unit time traversed; For each of the plurality of traversed unit times, determining an adjacent unit time located after the traversed unit time; Determine, based on the duration of the traversed unit time, the body temperature change rate of the target object in the traversed unit time, and the body temperature change rate in the adjacent unit time, a rate of change of the body temperature change rate of the target object in the traversed unit time, where the rate of change of the body temperature change rate is a first-order derivative of the body temperature change rate, which is used to reflect the change of the body temperature change rate over time; Based on the duration of the unit time traversed to, the body temperature change rate of the target object in the unit time traversed to, and the rate of change of the body temperature change rate of the target object in the unit time traversed to, the body temperature adjustment parameter of the target object in the unit time traversed to is determined, which is achieved by the following calculation formula: d 2 T / dt 2 -μ(1-T 2 )dT / dt+T=0; dT / dt=(T t+1 -T t ) / Δt; Among them, T t and T t+1 are the body temperature values ​​at the current time and the next time point, Δt is the length of unit time, d 2 T / dt 2 is the rate of change of the target object's body temperature change rate during the unit time traversed to, dT / dt is the rate of change of the target object's body temperature during the unit time traversed to, μ is the body temperature adjustment parameter of the target object during the unit time traversed to, T is the body temperature change value of the target object during the unit time traversed to, and t is the duration of the unit time traversed to; Matching the target object's body temperature regulation parameter within the traversed unit time with the body temperature parameter threshold to obtain a parameter matching result; stopping the traversal when the parameter matching result indicates that the target object's body temperature regulation parameter within the traversed unit time is greater than the body temperature parameter threshold, and setting the traversed unit time as the waiting time for drinking water; Obtaining the target object's body temperature value, body temperature change value, body temperature change rate, and rate of change of the body temperature change rate during the waiting time for drinking water; generating an image to be detected based on the target object's body temperature value, body temperature change value, body temperature change rate, and rate of change of the body temperature change rate during the waiting time for drinking water; obtaining a water drinking prediction model, and processing the image to be detected using the water drinking prediction model to obtain the amount of water and the drinking temperature required by the target object; Receive the body temperature data of the target subject in response to the drinking water amount and the drinking water temperature; update the body temperature parameter threshold according to the body temperature data of the target subject in response to the drinking water amount and the drinking water temperature to obtain an updated body temperature parameter threshold; and use the updated body temperature parameter threshold as the body temperature parameter threshold of the target subject after the waiting time for drinking water.

2. The intelligent drinking water reminder method according to claim 1, characterized in that: The drinking water prediction model at least includes a backbone network, a drinking water volume branch module, and a drinking water temperature branch module.

3. The intelligent drinking water reminder method according to claim 2, characterized in that: The step of processing the image to be detected by using the drinking water prediction model to obtain the drinking water amount and drinking water temperature required by the target object includes: Get the water intake weight matrix; Extract features of the image to be detected through the backbone network to obtain an initial feature map; The water intake branch module performs linear and nonlinear transformations on the initial feature map corresponding to the water intake weight matrix to obtain a water intake convolution feature map, and determines a water intake pooling feature map based on the maximum eigenvalue of the water intake convolution feature map on each feature channel; Flattening and straightening the water intake pooled feature map to obtain a water intake feature vector; Converting the water intake feature vector into a water intake probability distribution feature vector; The amount of water required by the target object is determined according to the water intake probability distribution feature vector.

4. The intelligent drinking water reminder method according to claim 3, characterized in that: The step of processing the image to be detected by using the drinking water prediction model to obtain the drinking water amount and drinking water temperature required by the target object further includes: Get the drinking water temperature weight matrix; The drinking water temperature branch module performs linear and nonlinear transformations on the initial feature map corresponding to the drinking water temperature weight matrix to obtain a drinking water temperature convolution feature map, and determines a drinking water temperature pooling feature map based on the average eigenvalue of the drinking water temperature convolution feature map on each feature channel; Flattening and straightening the drinking water temperature pooled feature map to obtain a drinking water temperature feature vector; Converting the drinking water temperature feature vector into a drinking water temperature probability distribution feature vector; The drinking water temperature required by the target object is determined according to the drinking water temperature probability distribution eigenvector.

5. An intelligent water drinking reminder device, characterized in that: The intelligent drinking water reminder device includes: An acquisition module is used to traverse the unit time of the target object after drinking the water, and obtain the body temperature change value of the target object during the traversed unit time; A first determining module is configured to determine a body temperature change rate of the target object within a unit time traversed according to the body temperature change value and a duration of the unit time traversed; The second determination module is used to determine, for each of the multiple traversed unit times, an adjacent unit time located behind the traversed unit time; determine the rate of change of the target object's body temperature change rate in the traversed unit time according to the duration of the traversed unit time, the body temperature change rate of the target object in the traversed unit time, and the body temperature change rate in the adjacent unit time, where the rate of change of the body temperature change rate is a first-order derivative of the body temperature change rate, which is used to reflect the change of the body temperature change rate over time; determine the body temperature regulation parameter of the target object in the traversed unit time based on the duration of the traversed unit time, the body temperature change rate of the target object in the traversed unit time, and the rate of change of the body temperature change rate of the target object in the traversed unit time, which is achieved by the following calculation formula: d 2 T / dt 2 -μ(1-T 2 )dT / dt+T=0; dT / dt=(T t+1 -T t ) / Δt; Among them, T t and T t+1 are the body temperature values ​​at the current time and the next time point, Δt is the length of unit time, d 2 T / dt 2 is the rate of change of the target object's body temperature change rate during the unit time traversed to, dT / dt is the rate of change of the target object's body temperature during the unit time traversed to, μ is the body temperature adjustment parameter of the target object during the unit time traversed to, T is the body temperature change value of the target object during the unit time traversed to, and t is the duration of the unit time traversed to; a stopping module, configured to match the target object's body temperature regulation parameter within the traversed unit time with a body temperature parameter threshold to obtain a parameter matching result; when the parameter matching result indicates that the target object's body temperature regulation parameter within the traversed unit time is greater than the body temperature parameter threshold, the traversal is stopped, and the traversed unit time is used as the waiting time for drinking water; a prediction module for obtaining the target subject's body temperature value, body temperature change value, body temperature change rate, and rate of change of the body temperature change rate during the waiting time for drinking water; generating an image to be detected based on the target subject's body temperature value, body temperature change value, body temperature change rate, and rate of change of the body temperature change rate during the waiting time for drinking water; obtaining a water drinking prediction model, and processing the image to be detected using the water drinking prediction model to obtain the amount of water and the drinking temperature required by the target subject; An updating module is configured to receive the body temperature data fed back by the target subject regarding the amount of water drunk and the temperature of the water drunk; update the body temperature parameter threshold value based on the body temperature data fed back by the target subject regarding the amount of water drunk and the temperature of the water drunk to obtain an updated body temperature parameter threshold value; and use the updated body temperature parameter threshold value as the body temperature parameter threshold value of the target subject after the waiting time for drinking water.

6. The intelligent water drinking reminder device according to claim 5, characterized in that: The drinking water prediction model at least includes a backbone network, a drinking water volume branch module, and a drinking water temperature branch module.

7. The intelligent water drinking reminder device according to claim 6, characterized in that: The prediction module is further used to obtain a water intake weight matrix; perform feature extraction on the image to be detected through the backbone network to obtain an initial feature map; perform linear and nonlinear transformations on the initial feature map corresponding to the water intake weight matrix through the water intake branch module to obtain a water intake convolution feature map; determine a water intake pooling feature map based on the maximum eigenvalue of the water intake convolution feature map on each feature channel; flatten and straighten the water intake pooling feature map to obtain a water intake feature vector; convert the water intake feature vector into a water intake probability distribution feature vector; and determine the water intake required by the target object based on the water intake probability distribution feature vector.

8. The intelligent water drinking reminder device according to claim 7, characterized in that: The prediction module is also used to obtain a drinking water temperature weight matrix; through the drinking water temperature branch module, the initial feature map is subjected to linear and nonlinear transformations corresponding to the drinking water temperature weight matrix to obtain a drinking water temperature convolution feature map; the drinking water temperature pooling feature map is determined based on the average eigenvalue of the drinking water temperature convolution feature map on each feature channel; the drinking water temperature pooling feature map is flattened and straightened to obtain a drinking water temperature feature vector; the drinking water temperature feature vector is converted into a drinking water temperature probability distribution feature vector; and the drinking water temperature required by the target object is determined based on the drinking water temperature probability distribution feature vector.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent water drinking reminder method according to any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent water drinking reminder method according to any one of claims 1 to 4 are implemented.

Images