Urine volume monitoring method and device based on wavelet transform and kalman filtering and medium

Abstract

The application discloses a urine volume monitoring method and device based on wavelet transform and Kalman filtering and a medium, the method comprising: setting a time window and a sampling frequency for a urine weighing device, and collecting urine volume time series data by using the urine weighing device; converting the urine volume time series data into a one-dimensional array, and performing wavelet transform on the one-dimensional array to obtain corresponding first transform data; performing thresholding processing on the first transform data, and performing inverse wavelet transform on the first transform data after the thresholding processing to obtain second transform data; inputting the second transform data into a Kalman filter, and outputting corresponding urine volume monitoring results from the Kalman filter. The application can exclude abnormal interference in the urine volume monitoring process through wavelet transform and thresholding processing, can produce a noise reduction effect while avoiding damage to low-frequency signals, and then can estimate urine volume in combination with a Kalman filtering algorithm, so that the accuracy and monitoring efficiency of urine volume monitoring can be improved.

Description

Technical Field

[0001] This invention relates to the field of computer software technology, and in particular to a urine volume monitoring method, device, and medium based on wavelet transform and Kalman filtering. Background Technology

[0002] Urine volume refers to the total amount of urine excreted daily, usually measured in milliliters. Clinically, urine volume serves as an indicator of kidney function and fluid balance. Normally, an adult's daily urine output should be between 800-2000 ml, but this can vary depending on individual differences, diet, and ambient temperature. Both excessive and insufficient urine output can indicate underlying health problems. Excessive urine output (polyuria) can be caused by various factors, such as thirst leading to excessive water intake, the use of diuretics, and diabetes. Excessive urine output can lead to dehydration and electrolyte imbalances. Insufficient urine output (oliguria) can be caused by abnormal kidney function, dehydration, and low blood pressure. Oliguria can also be a sign of urinary tract obstruction or kidney stones. Insufficient urine output can lead to the accumulation of metabolic waste products and insufficient blood volume. Therefore, in clinical practice, monitoring urine output helps doctors assess a patient's kidney function and fluid balance, and allows for the timely detection of kidney diseases and metabolic abnormalities.

[0003] Currently, there is a urine volume monitoring system that uses gravity and weighing as measurement methods. However, the main technical challenge of this system lies in its inability to perform robust and efficient signal processing on the raw gravity sensor data to shield against disturbances from abnormal events and thus obtain a high-precision estimate of urine weight. Furthermore, the system cannot address how to incorporate human physiological constraints based on a high-precision urine weight estimate to calculate near-true values ​​for urine volume, flow rate, and other measurement indicators, as well as how to calibrate and establish the initial and hyperparameter values ​​of the system model. Summary of the Invention

[0004] This invention provides a urine volume monitoring method, device, computer equipment, and storage medium based on wavelet transform and Kalman filtering, aiming to improve the accuracy and efficiency of urine volume monitoring.

[0005] In a first aspect, embodiments of the present invention provide a urine volume monitoring method based on wavelet transform and Kalman filtering, comprising:

[0006] Set the time window and sampling frequency for the urine weighing device, and use the urine weighing device to collect time-series data of urine volume;

[0007] The urine volume time series data is converted into a one-dimensional array, and wavelet transform is performed on the one-dimensional array to obtain the corresponding first transformed data;

[0008] The first transformed data is thresholded, and the thresholded first transformed data is then subjected to inverse wavelet transform to obtain the second transformed data.

[0009] The second transformed data is input into a Kalman filter, and the Kalman filter outputs the corresponding urine volume monitoring result.

[0010] Secondly, embodiments of the present invention provide a urine volume monitoring device based on wavelet transform and Kalman filtering, comprising:

[0011] The data acquisition unit is used to set the time window and sampling frequency for the urine weighing device, and to collect time-series data of urine volume using the urine weighing device.

[0012] The wavelet transform unit is used to convert the urine volume time series data into a one-dimensional array and perform wavelet transform on the one-dimensional array to obtain the corresponding first transformed data.

[0013] A thresholding unit is used to threshold the first transformed data and perform inverse wavelet transform on the thresholded first transformed data to obtain the second transformed data.

[0014] The filter output unit is used to input the second transformed data into a Kalman filter, and the Kalman filter outputs the corresponding urine volume monitoring result.

[0015] Thirdly, embodiments of the present invention provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the urine volume monitoring method based on wavelet transform and Kalman filtering as described in the first aspect.

[0016] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the urine volume monitoring method based on wavelet transform and Kalman filtering as described in the first aspect.

[0017] This invention provides a urine volume monitoring method, apparatus, computer device, and storage medium based on wavelet transform and Kalman filtering. The method includes: setting a time window and sampling frequency for a urine weighing device, and collecting time-series urine volume data using the urine weighing device; converting the time-series urine volume data into a one-dimensional array, and performing a wavelet transform on the one-dimensional array to obtain corresponding first transformed data; thresholding the first transformed data, and performing an inverse wavelet transform on the thresholded first transformed data to obtain second transformed data; inputting the second transformed data into a Kalman filter, and having the Kalman filter output the corresponding urine volume monitoring result. This invention uses wavelet transform and thresholding to eliminate abnormal interference during urine volume monitoring, achieving noise reduction while avoiding damage to important low-frequency signals. Combining this with the Kalman filtering algorithm for urine volume estimation and monitoring improves the accuracy and efficiency of urine volume monitoring. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a urine volume monitoring method based on wavelet transform and Kalman filtering provided in an embodiment of the present invention;

[0020] Figure 2 A schematic diagram of a sub-process of a urine volume monitoring method based on wavelet transform and Kalman filtering provided in an embodiment of the present invention;

[0021] Figure 3 A schematic block diagram of a urine volume monitoring device based on wavelet transform and Kalman filtering provided in an embodiment of the present invention;

[0022] Figure 4 This is a schematic block diagram of a urine volume monitoring device based on wavelet transform and Kalman filtering, provided as an embodiment of the present invention. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0025] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0026] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0027] Please see below. Figure 1 , Figure 1 The flowchart of a urine volume monitoring method based on wavelet transform and Kalman filtering provided in an embodiment of the present invention specifically includes steps S101 to S104.

[0028] S101. Set the time window and sampling frequency for the urine weighing device, and use the urine weighing device to collect urine volume time series data.

[0029] S102. Convert the urine volume time series data into a one-dimensional array, and perform wavelet transform on the one-dimensional array to obtain the corresponding first transformed data;

[0030] S103. Threshold the first transformed data and perform inverse wavelet transform on the thresholded first transformed data to obtain the second transformed data.

[0031] S104. Input the second transformed data into a Kalman filter, and have the Kalman filter output the corresponding urine volume monitoring result.

[0032] In this embodiment, a corresponding time window and sampling frequency are first set for the urine weighing device. Then, based on this time window and sampling frequency, time-series data of urine volume are collected. For the collected urine volume time-series data, wavelet transform is used to perform signal filtering processing to obtain the corresponding first transform data. Then, thresholding processing is used to process the coefficient amplitude values ​​of the first transform data to achieve noise reduction and anti-abnormal interference. Next, inverse wavelet transform is used to obtain the second transform data, and Kalman filter is used to filter the second transform data to obtain the final urine volume monitoring result.

[0033] This embodiment uses wavelet transform and thresholding to eliminate abnormal interference in the urine volume monitoring process. While producing a noise reduction effect, it can also avoid destroying important low-frequency signals. Then, it combines the Kalman filter algorithm for urine volume estimation and monitoring, which can improve the accuracy and efficiency of urine volume monitoring.

[0034] In practical applications, the time window T for signal processing of the urine weighing device can be set to 1 minute, and the sampling frequency Fs to 32 Hz, meaning 32 data points are sampled per second. When converting the collected urine volume time-series data into a one-dimensional array, specifically, it is converted into a one-dimensional array of length 32 * 60 = 1920. Furthermore, when performing wavelet transform on this one-dimensional array, a relatively smooth db2 wavelet with a level of 7 can be selected, and the wavelet coefficients after the wavelet transform are c. Wavelet transform (WT) is a transform analysis method that inherits and develops the idea of ​​localization from short-time Fourier transform, while overcoming the shortcomings such as the window size not changing with frequency. It can provide a "time-frequency" window that changes with frequency, making it an ideal tool for signal time-frequency analysis and processing. The main characteristics of wavelet transform are that it can fully highlight certain features of a problem through transformation, enabling localized analysis of time (space) and frequency, and gradually refining the signal (function) at multiple scales through scaling and translation operations, ultimately achieving the effect of time subdivision at high frequencies and frequency subdivision at low frequencies. The inverse wavelet transform refers to performing a reverse transformation on the result of the wavelet transform to recover the original signal. The specific implementation method of the inverse wavelet transform is to use the inverse transform matrix of the wavelet transform and perform matrix multiplication on the result of the wavelet transform to recover the original signal.

[0035] In one embodiment, the thresholding process for the first transformed data includes:

[0036] The first transformed data is subjected to a lower bound threshold processing according to the following formula:

[0037]

[0038] And the first transformed data is subjected to an upper bound threshold processing according to the following formula:

[0039]

[0040] Where c represents the wavelet coefficient, thr l The lower bound threshold is represented by thr u This represents the upper threshold.

[0041] The thresholding process described in this embodiment specifically includes lower bound thresholding and upper bound thresholding. The lower bound thresholding uses a soft thresholding method, while the upper bound thresholding uses a hard thresholding method. The specific processing method is shown in the formula above.

[0042] In one embodiment, the urine volume monitoring method based on wavelet transform and Kalman filtering further includes:

[0043] Based on the linearization and white noise assumptions, the dynamic equation for urine weighing is established as follows:

[0044]

[0045] y t =[1 0]x t +δ

[0046]

[0047]

[0048] Where, x t The urine state variable is represented by a two-dimensional vector, w. t v represents the estimated weight of urine at time t. t Let y represent the estimated rate of change of urine weight at time t, W represent the process white noise vector, and y represent the estimated rate of change of urine weight at time t. t This represents the weight value output by the gravity sensor in the urine weighing device, and δ represents the measurement white noise.

[0049] Furthermore, the urine volume monitoring method based on wavelet transform and Kalman filtering also includes:

[0050] Collect standard urine volume data;

[0051] The measurement variance is constructed using the following formula, combining the weight value output by the gravity sensor and standard urine volume data:

[0052]

[0053] Where, d 2 The measurement method is indicated by n, n represents n time points, t represents time t, and z represents the standard urine output data.

[0054] Set the covariance matrix based on the measurement variance:

[0055]

[0056] Where Q represents the covariance matrix.

[0057] In this embodiment, a urine weighing dynamic equation is first established based on the linearization and white noise assumptions for urine volume time-series data, where the urine state variable x... t =(w t v t The urine weighing dynamic equation is a two-dimensional vector consisting of the estimated urine weight (g) and the estimated rate of change of urine weight (mg / s). The process white noise vector W in the urine weighing dynamic equation has a normal distribution with a mean of 0 and a covariance matrix of Q. The measurement white noise δ has a normal distribution with a mean of 0 and a variance of d. 2 .

[0058] In practical applications, the measurement variance d can be determined based on laboratory conditions. 2 In collecting standard urine volume data, a standard weight can be used instead of a urine collection bag, hung on a urine weighing device to collect the standard urine volume data. For example, a 500g weight can be used to collect 500g of standard urine volume data. Then, urine volume time-series data is continuously collected for one minute, resulting in a one-dimensional array y. Simultaneously, the value of the covariance matrix Q can be set based on historical urine volume monitoring experience. This setting improves the smoothness of the filtering results, and the coefficients can be fine-tuned in practical use to improve the monitoring effect. Furthermore, based on industry data on normal human urine flow rate, the initial urine weight estimate w0 = 0g and the initial urine weight change rate estimate v0 = 15mg / s are set, thus initializing the covariance matrix to P0.

[0059]

[0060] In one embodiment, the step of inputting the second transformed data to a Kalman filter and having the Kalman filter output the corresponding urine volume monitoring result includes:

[0061] Based on the urine weighing dynamic equation, the prior state and first variance estimate of the urine state variable at time t are calculated, and the posterior state estimate and second variance estimate of the urine state variable at time t are updated based on the weight value output by the gravity sensor.

[0062]

[0063]

[0064]

[0065]

[0066] P t =(IK t [1 0])P t -

[0067] in, This represents the estimated value of the urine state variable at time t. K represents the estimated value of the urine state variable at time t-1. t P represents the Kalman gain at time t. t - P represents the first variance estimate. t This indicates the second variance estimate;

[0068] Based on the prior state and first variance estimate of the urine state variable, as well as the posterior state estimate and second variance estimate, the estimated urine weight and estimated urine weight change rate of the urine state variable are output.

[0069] This embodiment uses a two-dimensional vector composed of weight and weight change rate as the state vector to establish the urine weighing dynamic equation. Then, Kalman filtering, combined with human urinary physiology, is used to improve the accuracy of urine volume estimation. Kalman filtering is an algorithm that uses the state equation of a linear system to optimally estimate the system state using system input and output observation data. Since the observation data includes the influence of noise and interference in the system, the optimal estimation can also be regarded as a filtering process. This embodiment calculates the prior state and first variance estimate of the urine state variable based on the urine weighing dynamic equation. Then, it updates the posterior state estimate and second variance estimate of the urine state variable by combining the weight value output by the gravity sensor, thereby obtaining an accurate urine state variable, and thus obtaining the corresponding urine weight estimate and urine weight change rate estimate.

[0070] In one embodiment, such as Figure 2 As shown, the step of inputting the second transformed data into a Kalman filter and having the Kalman filter output the corresponding urine volume monitoring result further includes steps S201 to S204.

[0071] S201. Obtain the estimated urine weight and urine weight change rate at time t from the Kalman filter output.

[0072] S202. Compare the estimated urine weight change rate with a preset change rate range;

[0073] S203. If the estimated value of the urine weight change rate is within the preset change rate range, then the estimated value of the urine weight change rate and the estimated value of the urine weight are output as the urine volume monitoring result.

[0074] S204. If the estimated value of the urine weight change rate is not within the preset change rate range, then obtain the estimated value of urine weight and the urine weight change rate at time t-1, and output them as the urine volume monitoring result.

[0075] In this embodiment, after obtaining the estimated urine weight and urine weight change rate at time t from the Kalman filter output, the estimated urine weight change rate is compared with a preset change rate range, which can be set based on industry data in actual scenarios. If the estimated urine weight change rate is within the preset change rate range, it is adopted and output as the final urine volume monitoring result. If the estimated urine weight change rate exceeds the preset change rate range, it indicates that there is an abnormal bias in the Kalman filter. In this case, the estimated urine weight change rate from the previous time (i.e., time t-1) can be obtained and assigned to the estimated urine weight change rate at time t. At the same time, the estimated urine weight at time t is also updated, and then the final urine volume monitoring result is output.

[0076] In one embodiment, the urine volume monitoring method based on wavelet transform and Kalman filtering further includes:

[0077] Urine monitoring is performed using an asynchronous parallel process according to the following formula:

[0078] m = w N / ρ

[0079]

[0080] Where m represents urine volume, r represents urine flow rate, N represents N data points collected per minute, ρ represents urine density, and w N v represents the final estimated urine weight. t This represents the estimated rate of change of urine weight at each data point.

[0081] In this embodiment, an asynchronous parallel process is used to monitor urine volume, which can further improve monitoring efficiency. For example, an asynchronous parallel process can be used to calculate the urine volume m and urine flow rate r in ml once per minute. In addition, the urine density can be set based on industry data in actual scenarios. For example, the normal urine density range is [1.003, 1.030]. Therefore, this embodiment can take the middle value of 1.015 g / ml as the urine density. Of course, other values ​​within the range can also be selected.

[0082] Figure 3 A schematic block diagram of a urine volume monitoring device 300 based on wavelet transform and Kalman filtering provided in an embodiment of the present invention. The device 300 includes:

[0083] The data acquisition unit 301 is used to set the time window and sampling frequency for the urine weighing device, and to collect urine volume time-series data using the urine weighing device.

[0084] Wavelet transform unit 302 is used to convert the urine volume time series data into a one-dimensional array and perform wavelet transform on the one-dimensional array to obtain the corresponding first transformed data;

[0085] The thresholding unit 303 is used to threshold the first transformed data and perform inverse wavelet transform on the thresholded first transformed data to obtain the second transformed data.

[0086] The filter output unit 304 is used to input the second transformed data into a Kalman filter, and the Kalman filter outputs the corresponding urine volume monitoring result.

[0087] In one embodiment, the thresholding unit 303 includes:

[0088] The lower bound processing unit is used to perform lower bound threshold processing on the first transformed data according to the following formula:

[0089]

[0090] The upper bound processing unit is used to perform upper bound threshold processing on the first transformed data according to the following formula:

[0091]

[0092] Where c represents the wavelet coefficient, thr l The lower bound threshold is represented by thr. u This represents the upper threshold.

[0093] In one embodiment, the urine volume monitoring device 300 based on wavelet transform and Kalman filtering further includes:

[0094] The dynamic equation establishment unit is used to establish the dynamic equation for urine weighing according to the following formula, based on the linearization assumption and the white noise assumption:

[0095]

[0096] y t =[1 0]x t +δ

[0097]

[0098]

[0099] Where, x t The urine state variable is represented by a two-dimensional vector, w. tv represents the estimated weight of urine at time t. t Let y represent the estimated rate of change of urine weight at time t, W represent the process white noise vector, and y represent the estimated rate of change of urine weight at time t. t This represents the weight value output by the gravity sensor in the urine weighing device, and δ represents the measurement white noise.

[0100] In one embodiment, the urine volume monitoring device 300 based on wavelet transform and Kalman filtering further includes:

[0101] The test acquisition unit is used to collect standard urine volume data.

[0102] The variance construction unit is used to construct the measurement variance by combining the weight value output by the gravity sensor and standard urine volume data according to the following formula:

[0103]

[0104] Where, d 2 The measurement method is indicated by n, n represents n time points, t represents time t, and z represents the standard urine output data.

[0105] The matrix setting unit is used to set the covariance matrix based on the measurement variance:

[0106]

[0107] Where Q represents the covariance matrix.

[0108] In one embodiment, the filter output unit 304 includes:

[0109] The variable update unit is used to calculate the prior state and first variance estimate of the urine state variable at time t based on the urine weighing dynamic equation, and to update the posterior state estimate and second variance estimate of the urine state variable at time t based on the weight value output by the gravity sensor.

[0110]

[0111]

[0112]

[0113]

[0114] P t =(IK t [1 0])P t -

[0115] in, This represents the estimated value of the urine state variable at time t. K represents the estimated value of the urine state variable at time t-1. t P represents the Kalman gain at time t. t - P represents the first variance estimate. t This indicates the second variance estimate;

[0116] The estimation output unit is used to output the estimated value of urine weight and the estimated value of urine weight change rate of the urine state variable based on the prior state and first variance estimate, as well as the posterior state estimate and second variance estimate of the urine state variable.

[0117] In one embodiment, such as Figure 4 As shown, the filter output unit 304 further includes:

[0118] The estimation acquisition unit 401 is used to acquire the estimated value of urine weight and the estimated rate of change of urine weight at time t of the Kalman filter output;

[0119] The estimation comparison unit 402 is used to compare the estimated value of the urine weight change rate with a preset change rate range;

[0120] The first output unit 403 is used to output the estimated urine weight change rate and the estimated urine weight as the urine volume monitoring result if the estimated urine weight change rate is within a preset change rate range.

[0121] The second output unit 404 is used to obtain the estimated urine weight and urine weight change rate at time t-1 if the estimated urine weight change rate is not within the preset change rate range, and output them as the urine volume monitoring result.

[0122] In one embodiment, the urine volume monitoring device 300 based on wavelet transform and Kalman filtering further includes:

[0123] A parallel monitoring unit is used to monitor urine output using an asynchronous parallel process according to the following formula:

[0124] m = w N / ρ

[0125]

[0126] Where m represents urine volume, r represents urine flow rate, N represents N data points collected per minute, ρ represents urine density, and w N v represents the final estimated urine weight. t This represents the estimated rate of change of urine weight at each data point.

[0127] Since the embodiments of the apparatus and the embodiments of the method correspond to each other, please refer to the description of the embodiments of the method for the embodiments of the apparatus, which will not be repeated here.

[0128] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed, can perform the steps provided in the above embodiments. The storage medium may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0129] This invention also provides a computer device, which may include a memory and a processor. The memory stores a computer program, and when the processor calls the computer program in the memory, it can implement the steps provided in the above embodiments. Of course, the computer device may also include various network interfaces, power supplies, and other components.

[0130] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0131] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A urine volume monitoring method based on wavelet transform and Kalman filtering, characterized in that, include: Set the time window and sampling frequency for the urine weighing device, and use the urine weighing device to collect time-series data of urine volume; The urine volume time series data is converted into a one-dimensional array, and wavelet transform is performed on the one-dimensional array to obtain the corresponding first transformed data; The first transformed data is thresholded, and the thresholded first transformed data is then subjected to inverse wavelet transform to obtain the second transformed data. The second transformed data is input into a Kalman filter, and the Kalman filter outputs the corresponding urine volume monitoring result. Also includes: Based on the linearization and white noise assumptions, the dynamic equation for urine weighing is established as follows: Where, x t The urine state variable is represented by a two-dimensional vector, w. t v represents the estimated weight of urine at time t. t Let y represent the estimated rate of change of urine weight at time t, W represent the process white noise vector, and y represent the estimated rate of change of urine weight at time t. t This represents the weight value output by the gravity sensor in the urine weighing device, where δ represents the measurement white noise. Collect standard urine volume data; The measurement variance is constructed using the following formula, combining the weight value output by the gravity sensor and standard urine volume data: Where, d 2 The variance represents the measurement, n represents the n times, t represents time t, and z represents the standard urine volume data. Set the covariance matrix based on the measurement variance: Where Q represents the covariance matrix; The step of inputting the second transformed data into a Kalman filter and having the Kalman filter output the corresponding urine volume monitoring result includes: Based on the urine weighing dynamic equation, the prior state and first variance estimate of the urine state variable at time t are calculated, and the posterior state estimate and second variance estimate of the urine state variable at time t are updated based on the weight value output by the gravity sensor. in, This represents the estimated value of the urine state variable at time t. This represents the estimated value of the urine state variable at time t-1. This represents the Kalman gain at time t. This represents the first variance estimate. This indicates the second variance estimate; Based on the prior state and first variance estimate of the urine state variable, as well as the posterior state estimate and second variance estimate, the estimated urine weight and estimated urine weight change rate of the urine state variable are output.

2. The urine volume monitoring method based on wavelet transform and Kalman filtering according to claim 1, characterized in that, The thresholding process for the first transformed data includes: The first transformed data is subjected to a lower bound threshold processing according to the following formula: And the first transformed data is subjected to an upper bound threshold processing according to the following formula: Where c represents the wavelet coefficient, thr l The lower bound threshold is represented by thr u This represents the upper threshold.

3. The urine volume monitoring method based on wavelet transform and Kalman filtering according to claim 1, characterized in that, The step of inputting the second transformed data into a Kalman filter and having the Kalman filter output the corresponding urine monitoring result further includes: Obtain the estimated urine weight and urine weight change rate at time t from the Kalman filter output; The estimated rate of change in urine weight is compared with a preset range of change rates. If the estimated rate of change of urine weight is within the preset range, then the estimated rate of change of urine weight and the estimated urine weight are output as the urine volume monitoring result. If the estimated rate of change of urine weight is not within the preset range, the estimated urine weight and the rate of change of urine weight at time t-1 are obtained and output as the urine volume monitoring result.

4. The urine volume monitoring method based on wavelet transform and Kalman filtering according to claim 1, characterized in that, Also includes: Urine monitoring is performed using an asynchronous parallel process according to the following formula: Where m represents urine volume, r represents urine flow rate, N represents N data points collected per minute, ρ represents urine density, and w N v represents the final estimated urine weight. t This represents the estimated rate of change of urine weight at each data point.

5. A urine volume monitoring device based on wavelet transform and Kalman filtering, characterized in that, include: The data acquisition unit is used to set the time window and sampling frequency for the urine weighing device, and to collect time-series data of urine volume using the urine weighing device. The wavelet transform unit is used to convert the urine volume time series data into a one-dimensional array and perform wavelet transform on the one-dimensional array to obtain the corresponding first transformed data. A thresholding unit is used to threshold the first transformed data and perform inverse wavelet transform on the thresholded first transformed data to obtain the second transformed data. A filtering output unit is used to input the second transformed data into a Kalman filter, and the Kalman filter outputs the corresponding urine monitoring result. The urine volume monitoring device 300 based on wavelet transform and Kalman filtering also includes: The dynamic equation establishment unit is used to establish the dynamic equation for urine weighing according to the following formula, based on the linearization assumption and the white noise assumption: Where, x t The urine state variable is represented by a two-dimensional vector, w. t v represents the estimated weight of urine at time t. t Let y represent the estimated rate of change of urine weight at time t, W represent the process white noise vector, and y represent the estimated rate of change of urine weight at time t. t This represents the weight value output by the gravity sensor in the urine weighing device, where δ represents the measurement white noise. The test acquisition unit is used to collect standard urine volume data. The variance construction unit is used to construct the measurement variance by combining the weight value output by the gravity sensor and standard urine volume data according to the following formula: Where, d 2 The variance represents the measurement, n represents the n times, t represents time t, and z represents the standard urine volume data. The matrix setting unit is used to set the covariance matrix based on the measurement variance: Where Q represents the covariance matrix; The filter output unit 304 includes: The variable update unit is used to calculate the prior state and first variance estimate of the urine state variable at time t based on the urine weighing dynamic equation, and to update the posterior state estimate and second variance estimate of the urine state variable at time t based on the weight value output by the gravity sensor. in, This represents the estimated value of the urine state variable at time t. This represents the estimated value of the urine state variable at time t-1. This represents the Kalman gain at time t. This represents the first variance estimate. This indicates the second variance estimate; The estimation output unit is used to output the estimated value of urine weight and the estimated value of urine weight change rate of the urine state variable based on the prior state and first variance estimate, as well as the posterior state estimate and second variance estimate of the urine state variable.

6. A computer device, characterized in that, The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the urine volume monitoring method based on wavelet transform and Kalman filtering as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the urine volume monitoring method based on wavelet transform and Kalman filtering as described in any one of claims 1 to 4.

Images