A humidity monitoring and replacement reminder system integrated into smart diapers

Abstract

This invention relates to the field of electronic digital data processing technology, specifically to a humidity monitoring and replacement reminder system integrated into smart diapers. The corresponding steps include: determining a disease descriptor based on the user's clinical data; determining a metabolic descriptor based on medication, diet, and excretion data; determining a reference user for the target user based on the similarity of the disease descriptors; determining the metabolic consistency between the reference user and the target user based on the similarity of the metabolic descriptors; determining reference excretion data corresponding to the reference subsequences that match the medication and diet time-series data of the target user; determining the target user's excretion prediction sequence using the metabolic consistency and reference excretion data; and executing a replacement reminder decision based on the excretion prediction sequence and the remaining absorbable amount of the current diaper. This invention effectively improves the accuracy and reliability of diaper replacement identification and reminders.

Description

Technical Field

[0001] This invention relates to the field of electronic digital data processing technology, specifically to a humidity monitoring and replacement reminder system integrated into smart diapers. Background Technology

[0002] Traditional diaper changing relies primarily on regular checks by caregivers or patient self-reporting. This method has several drawbacks: firstly, it can lead to delayed diaper changes, causing skin inflammation, urinary tract infections, and other health problems; secondly, frequent checks increase the workload and waste resources. Smart adult diapers, by integrating humidity sensors, temperature sensors, and wireless communication modules, can monitor the diaper's humidity level in real time and automatically remind users when a change is needed, thus achieving precise and intelligent incontinence care management. This technology not only improves care efficiency but also significantly enhances user comfort and health.

[0003] Current smart diaper humidity monitoring and replacement reminder systems primarily rely on real-time detection values ​​from built-in humidity sensors. A replacement reminder is triggered when the detected value reaches a preset threshold. This solution is widely used in adult care scenarios, especially for patients who are bedridden for extended periods or suffer from chronic diseases. However, existing technology has significant limitations when dealing with the complex excretory environment of adult patients: patients often require long-term medication, resulting in multiple drug residues in their excrement, which can be identified through urine component analysis. Furthermore, patients' excretory patterns are highly irregular due to their illnesses. Existing systems, relying solely on current humidity to determine replacement timing, cannot predict future excretion patterns, leading to low reminder accuracy and failing to meet the actual needs of clinical care. Summary of the Invention

[0004] To address the current technical problem of low accuracy in identifying and reminding when to change smart diapers, the present invention aims to provide a humidity monitoring and replacement reminder system integrated into smart diapers. The specific technical solution adopted is as follows: This invention provides a humidity monitoring and replacement reminder system integrated into smart diapers, the system comprising: The feature extraction module is used to determine disease descriptors representing disease states based on the user's clinical data, and to determine metabolic descriptors representing metabolic processes based on the user's medication, diet, and excretion data during the metabolic cycle. The excretion prediction module is used to determine the reference users of the target user based on the similarity of disease descriptors between users, and to determine the metabolic consistency of the reference users with respect to the target user based on the similarity of metabolic descriptors between the target user and the reference users. Based on the reference subsequences of the reference users that match the medication and diet time series data of the target user in the most recent preset time period, the module determines the reference excretion data corresponding to the reference subsequences. The module uses the metabolic consistency and reference excretion data to determine the excretion prediction sequence of the target user, and executes a replacement reminder decision based on the excretion prediction sequence and the remaining absorbable amount of the current diaper.

[0005] Furthermore, the step of determining the disease descriptor representing the disease state based on the user's clinical data includes: Based on the user's clinical data, extract the medication feature vector, clinical symptom vector, and basic condition vector; The drug use feature vector, clinical symptom vector, and basic condition vector are fused and quantized into a multidimensional disease descriptor representing the disease state.

[0006] Furthermore, the step of determining the reference users for the target user based on the similarity of disease descriptors between users includes: Determine the cosine similarity of the vectors with the same dimensions in the disease descriptors between the target user and other users; The disease similarity between the target user and other users on the disease descriptor is obtained by combining the various cosine similarities. Other users whose disease similarity is greater than or equal to a preset similarity threshold are used as reference users for the target user.

[0007] Furthermore, the step of determining metabolic descriptors characterizing metabolic processes based on the user's medication, diet, and excretion data during the metabolic cycle includes: Centered on any medication event of the user, the preset time period before and after medication is used as the metabolic cycle; The vectors of medication use, diet, and excretion at each recording point in the metabolic cycle are arranged in chronological order and fused and quantified into a multidimensional metabolic descriptor representing the metabolic process.

[0008] Further, determining the degree of metabolic consistency between the reference user and the target user based on the similarity of metabolic descriptors between the target user and the reference user includes: Determine the DTW distance between the target user and the reference user for each vector sequence with the same dimension in the metabolic descriptor. The metabolic consistency of the reference user with respect to the target user is determined by using the DTW distances.

[0009] Furthermore, the step of determining the metabolic consistency of the reference user with respect to the target user using each DTW distance includes: The degree of local metabolic consistency between the reference user and the target user in a single metabolic cycle pair is determined by using the DTW distances. A metabolic descriptor sequence composed of multiple metabolic cycles is determined, and the global matching distance between the metabolic descriptor sequences of the target user and the reference user is determined based on dynamic time warping. The global metabolic consistency of the reference user relative to the target user is obtained by using the average local metabolic consistency of multiple metabolic cycle pairs and the global matching distance.

[0010] Further, the step of determining the reference excretion data corresponding to the reference subsequence based on the reference subsequence matching the medication and diet time-series data of the reference users within the most recent preset time period with the target user includes: Using the medication and diet time series data of the target user within the most recent preset time period as a query template, the reference subsequence with the highest matching degree is extracted from the medication and diet time series data of the reference user; Based on the metabolic descriptor of the reference user, the excretion data corresponding to the reference subsequence within a preset time period are determined as the reference excretion data sequence.

[0011] Furthermore, the step of determining the target user's predicted excretion sequence using metabolic consistency and reference excretion data includes: The degree of metabolic consistency is used as the weight of the corresponding reference excretion data, and the weighted average of the reference excretion data of all reference users is calculated to obtain the excretion prediction sequence of the target user.

[0012] Furthermore, the step of making a replacement reminder decision based on the excretion prediction sequence and the remaining absorbable amount of the current diaper includes: The remaining absorbable amount of the diaper is obtained by using its current humidity value and maximum absorbency, and the predicted excretion amount in the earliest future prediction time window in the excretion prediction sequence is determined. An emergency diaper change reminder will be issued immediately when the predicted excretion exceeds the remaining absorbable amount.

[0013] Furthermore, the step of making a replacement reminder decision based on the excretion prediction sequence and the remaining absorbable amount of the current diaper also includes: When the predicted discharge amount is less than or equal to the remaining absorbable amount, the cumulative predicted discharge amount within multiple consecutive prediction time windows in the discharge prediction sequence is determined. When the cumulative predicted excretion exceeds the safety limit of the remaining absorbable amount, a future reminder time is determined and a diaper replacement warning is issued at the future reminder time.

[0014] The present invention has the following beneficial effects: This invention constructs disease descriptors representing user disease states and metabolic descriptors representing metabolic processes using a historical database including clinical, dietary, and excretion data. It then mines similar metabolic patterns among users in the database to build a personalized excretion prediction model for the target user. This model can more accurately predict the user's excretion time and volume over a future period based on multi-dimensional data matched with other similar users. This allows the system to proactively make decisions based on future predictions, rather than reacting passively. This effectively improves the accuracy and reliability of diaper change recognition and reminders, maximizing diaper utilization while ensuring user comfort. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 The flowchart illustrates the steps of a humidity monitoring and replacement reminder system integrated into a smart diaper, as provided in one embodiment of the present invention. Figure 2 A detailed flowchart of step S2 in a humidity monitoring and replacement reminder system integrated into a smart diaper, provided as an embodiment of the present invention; Figure 3 A detailed flowchart of step S2 in a humidity monitoring and replacement reminder system integrated into a smart diaper, provided in another embodiment of the present invention; Figure 4 A detailed flowchart of step S3 in a humidity monitoring and replacement reminder system integrated into a smart diaper, provided in an embodiment of the present invention; Figure 5 A detailed flowchart of step S4 in a humidity monitoring and replacement reminder system integrated into a smart diaper, provided as an embodiment of the present invention; Figure 6 This is a schematic diagram of the hardware operating environment of the humidity monitoring and replacement reminder device integrated into a smart diaper, as described in an embodiment of the present invention. Figure 7 This is a schematic diagram of the framework structure of the humidity monitoring and replacement reminder system integrated into a smart diaper, which is involved in the embodiment of the present invention. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a humidity monitoring and replacement reminder system integrated into a smart diaper according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0019] To facilitate understanding of the various embodiments of the present invention, the technical concept of the present invention is described below: The patient's disease state determines the treatment plan, and the treatment plan (medication) and diet together affect the metabolic process, which is ultimately reflected in the patient's excretion pattern. Therefore, by mining the relevant data patterns of patients with similar disease and similar metabolic rhythm in the past, we can predict the current patient's excretion behavior based on their excretion after similar current medication and diet.

[0020] The following description, in conjunction with the accompanying drawings, details a specific solution for a humidity monitoring and replacement reminder system integrated into a smart diaper, provided by the present invention.

[0021] Example 1: For the humidity monitoring and replacement reminder system integrated into smart diapers (hereinafter referred to as the "humidity monitoring and replacement reminder system" or the "system") provided by this invention, please refer to [link to relevant documentation]. Figure 7 , Figure 7 This is a schematic diagram of the framework structure of the humidity monitoring and replacement reminder system integrated into a smart diaper, which is involved in the embodiment of the present invention.

[0022] The humidity monitoring and replacement reminder system integrated into the smart diaper includes: The feature extraction module A10 is used to determine disease descriptors representing disease states based on the user's clinical data, and to determine metabolic descriptors representing metabolic processes based on the user's medication, diet and excretion data during the metabolic cycle. The excretion prediction module A20 is used to determine the reference user for the target user based on the similarity of disease descriptors between users, and to determine the metabolic consistency of the reference user with respect to the target user based on the similarity of metabolic descriptors between the target user and the reference user; to determine the reference excretion data corresponding to the reference subsequence based on the reference subsequence that matches the medication and diet time series data of the target user in the most recent preset time period among the reference users; to determine the excretion prediction sequence for the target user using the metabolic consistency and reference excretion data, and to execute a replacement reminder decision based on the excretion prediction sequence and the remaining absorbable amount of the current diaper.

[0023] Please see Figure 1 , Figure 1 The diagram shows a flowchart of the steps involved in a humidity monitoring and replacement reminder system integrated into a smart diaper, according to an embodiment of the present invention.

[0024] The methods and steps corresponding to the humidity monitoring and replacement reminder system integrated into smart diapers include: Step S1: Determine the disease descriptor representing the disease state based on the user's clinical data, and determine the metabolic descriptor representing the metabolic process based on the user's medication, diet and excretion data during the metabolic cycle. First, it connects to the API (Application Programming Interface) of the hospital's EMR (Electronic Medical Record) system to collect basic condition data and clinical data of patients. Basic condition data mainly includes age, gender, etc., while clinical data includes disease diagnosis labels, clinical symptoms, medication records (type, dosage, frequency, timestamp). Basic condition data can also be included in clinical data. At the same time, patients' dietary data (food types, intake, timestamps) are entered through the nursing mobile app. In addition, by reading the patient's smart diaper replacement records and obtaining the patient's excretion event data through weighing detection, including excretion volume, drug residue concentration in excrement and timestamp; by monitoring the saturation detection value of the sensor built into the diaper at a frequency of once per minute, and at the same time reading the diaper's factory-calibrated maximum absorbency from the product database; The pressure sensor built into the diaper is used to obtain the current amount of excretion in real time, and the ratio of this weight to the factory-calibrated maximum absorbency is calculated as the saturation detection value; or the built-in multi-point distributed humidity sensor array is used to obtain the dry and wet status of each point, and the saturation detection value representing the overall absorbent layer is calculated based on the weighted ratio of wet points to total points.

[0025] After the above data is collected, preprocessing is performed to remove outliers; all time series data are aligned; parameters such as medication dosage, food intake, and excretion are normalized to 0~1 (i.e., the value range is 0~1) to eliminate the influence of units. Unless otherwise specified, the normalization method in this invention can be the maximum and minimum value normalization.

[0026] The final result is a structured, time-aligned standardized dataset, providing high-quality input for subsequent diaper monitoring and replacement reminders.

[0027] At this point, data information from several parameters has been collected to form the database used in subsequent embodiments.

[0028] Specifically, step S1, which involves determining a disease descriptor representing the disease state based on the user's clinical data, includes: Based on the user's clinical data, extract the medication feature vector, clinical symptom vector, and basic condition vector; The drug use feature vector, clinical symptom vector, and basic condition vector are fused and quantized into a multidimensional disease descriptor representing the disease state.

[0029] In this embodiment, in clinical practice, patients with the same or similar diseases and using similar medication regimens often have more comparable physiological responses and metabolic processes. Therefore, before using data from others to predict the current patient (target user, referring to any patient user), it is necessary to first screen based on "disease status" to ensure that the reference subject is biologically similar to the target user.

[0030] First, a patient's disease status consists of three core dimensions: medication characteristics (what medications he is using, and the dosage and frequency), clinical symptoms (what symptoms he exhibits), and basic conditions (age, gender).

[0031] Medication feature vector The construction method is as follows: all possible drugs in the database (preset key drug categories, such as diuretics, laxatives, or high-frequency drugs) are arranged in a fixed order, and each drug corresponds to three components—whether it is used (represented by the code 0 / 1), normalized dose (the ratio of the current dose to the maximum single dose of the drug in clinical practice), and normalized dosing frequency. Thus, It not only includes information on the types of medications used, but also the intensity and pace of medication administration, providing a comprehensive picture of the treatment plan.

[0032] Clinical symptom vector The presence of various possible symptoms is represented by 0 / 1 encoding.

[0033] Basic condition vector Includes normalized age and gender labels.

[0034] By combining and integrating these three elements, a disease descriptor that can fully describe the patient's disease state can be obtained. This quantifies each patient's disease state into a high-dimensional vector, i.e., a disease descriptor. .

[0035] Specifically, step S1 involves determining metabolic descriptors characterizing the metabolic process based on the user's medication, diet, and excretion data during the metabolic cycle, including: Centered on any medication event of the user, the preset time period before and after medication is used as the metabolic cycle; The vectors of medication use, diet, and excretion at each recording point in the metabolic cycle are arranged in chronological order and fused and quantified into a multidimensional metabolic descriptor representing the metabolic process.

[0036] In this embodiment, the patient's entire process from each medication administration and food intake to excretion can be considered as a metabolic cycle, which best reflects the patient's metabolic capacity at that time. This cycle includes not only excretion after medication administration but also the influence of other factors such as diet, and the entire process changes dynamically over time.

[0037] To quantify the metabolic cycle, the physiological process within two hours before and after a single medication administration (a preset time period, adjustable) can be recorded as one metabolic cycle. Recording intervals can be 15 minutes. Record a state of your body, which consists of three parts: What medications have you taken at this moment? What foods did you ingest at the current moment? What was discharged at the current moment? ).

[0038] Medication usage vector The dimension is the same as the drug type, and the value is the normalized dose taken at that moment (0 if no drug is taken). Dietary status vector The dimensions are the same as for drinking water and food types, and the value is the normalized intake at that moment; Excretion status vector Includes residual concentrations of each drug and total excretion, all of which are normalized values.

[0039] It should be noted that the dietary data includes both the patient's water intake and food intake. Arranging these "state vectors" in chronological order (columns representing time, rows representing vectors of different dimensions) creates a metabolic descriptor describing the entire metabolic process. Based on this, data from N time points before and after each medication event are extracted to form matrix M (e.g., N=8, representing 17 time points from 2 hours before to 2 hours after medication): Matrix M is the metabolic descriptor M for each metabolic cycle.

[0040] Step S2: Determine the reference user for the target user based on the similarity of disease descriptors between users, and determine the degree of metabolic consistency between the reference user and the target user based on the similarity of metabolic descriptors between the target user and the reference user. Specifically, in one embodiment, please refer to Figure 2 ; Step S2, determining the reference users for the target user based on the similarity of disease descriptors between users, includes: Step S21: Determine the cosine similarity of the vectors with the same dimension in the disease descriptor between the target user and other users; Step S22: Combine the cosine similarity scores to obtain the disease similarity between the target user and other users on the disease descriptor. Step S23: Other users whose disease similarity is greater than or equal to a preset similarity threshold are used as reference users for the target user.

[0041] In this embodiment, similarity is calculated based on the descriptor, and reference patients with higher rankings are selected.

[0042] Based on the above embodiments, after constructing the quantified disease descriptor, the focus shifts to whether the disease state composition patterns of two patients are consistent. For example, even if the absolute values ​​of the medication dosages of two patients are different, if they both follow a pattern of using drug A as the primary treatment and drug B as a secondary treatment, then the directions of the two medication feature vectors will be similar. Cosine similarity can capture this pattern similarity, thereby avoiding misjudgments caused by differences in absolute values. The closer the value is to 1, the more similar the disease and medication regimen are.

[0043] Furthermore, the average value of the cosine similarity between the target user and other patients in the database on the medication feature vector, clinical symptom vector, and basic condition vector, respectively, after positive correlation normalization, can be used as the average value of the target user and other patients on the disease descriptor. Disease similarity.

[0044] Next, other patients whose disease similarity to the target user is greater than or equal to a preset similarity threshold (obtained based on the actual similarity value distribution, such as a preset threshold of 0.6) are selected as reference patients (reference users) for the target user.

[0045] Specifically, in another embodiment, please refer to Figure 3 ; Step S2, determining the degree of metabolic consistency between the reference user and the target user based on the similarity of metabolic descriptors between the target user and the reference user, includes: Step S201: Determine the DTW distance between the target user and the reference user for each vector sequence with the same dimension in the metabolic descriptor. Step S202: Use the DTW distances to determine the metabolic consistency of the reference user with respect to the target user.

[0046] More specifically, step S202 includes: The degree of local metabolic consistency between the reference user and the target user in a single metabolic cycle pair is determined by using the DTW distances. A metabolic descriptor sequence composed of multiple metabolic cycles is determined, and the global matching distance between the metabolic descriptor sequences of the target user and the reference user is determined based on dynamic time warping. The global metabolic consistency of the reference user relative to the target user is obtained by using the average local metabolic consistency of multiple metabolic cycle pairs and the global matching distance.

[0047] Based on the above embodiments, in this embodiment, even if two patients have similar diseases, their metabolic rate and absorption efficiency may differ (e.g., differences in metabolic rate). Therefore, after finding reference patients with similar diseases, it is necessary to compare long-term metabolic processes to screen out reference patients whose "metabolic rhythm" is most consistent with the target user. Only the excretion data of these patients are the most valuable for reference.

[0048] First, it is necessary to compare the individual metabolic cycles of the two patients (two... Similarity between matrices. Since different patients may take medication at different times (e.g., one at 8 am and another at 8 pm), simple alignment along the timeline is not feasible. Therefore, the DTW (Dynamic Time Warping) algorithm is introduced, which can relatively accurately find the most similar change patterns between two sequences. Between patients DTW matching is performed on the three rows of the matrix (medication sequence, diet sequence, and excretion sequence), using the cosine distance of vectors in the sequence as the distance metric, resulting in three... Distance value, then Distance is converted into similarity through negative correlation normalization. (Drug sequence similarity) (Dietary sequence similarity) (Excretion sequence similarity), taking the average of the above similarities as the similarity between the reference user and the target user in this metabolic cycle. This is recorded as the degree of local metabolic consistency. .

[0049] Secondly, it is necessary to compare the similarity of long-term metabolic rhythms composed of multiple metabolic cycles. Therefore, DTW was used again, but this time the comparison focused on the metabolic descriptors of each of the two patients. The time sequence (i.e., the temporal arrangement of multiple metabolic cycles, denoted as a metabolic descriptor sequence) is used. The distance metric for DTW employs... (i.e., the difference between two metabolic cycles), and find the optimal matching path between the two long-term sequences through dynamic programming to obtain the global matching distance. (DTW distance for this match), and also record the average similarity (average local metabolic consistency) of each metabolic cycle pair matched. Ultimately, the similarity of long-term metabolic trends (using...) The average similarity between the two patients' metabolic cycles (measured by the metabolic rate itself) and the metabolic cycle itself can be used to derive a global metabolic consistency score (global metabolic consistency level) between them. : An ideal reference patient not only has a similar single metabolic process to the target user ( More importantly, the long-term trends in their metabolic capacity (e.g., whether their metabolism gradually increases as their condition improves with treatment, or whether it remains stable) must also be consistent. The small value is added to the denominator position by 0.001 to prevent calculation errors caused by a denominator of 0, and the resulting error is within the allowable range.

[0050] Similarly, we can obtain the relationship between each reference patient and the target user. The score, which represents the similarity between its metabolic rhythm and that of the target user, will be used as the weighting basis for subsequent predictions.

[0051] Step S3: Based on the reference subsequence that matches the medication and diet time series data of the target user within the most recent preset time period among the reference users, determine the reference excretion data corresponding to the subsequent reference subsequence; Specifically, please refer to Figure 4 Step S3 includes: Step S31: Use the medication and diet time series data of the target user in the most recent preset time period as a query template, and extract the reference subsequence with the highest matching degree from the medication and diet time series data of the reference user; Step S32: Based on the metabolic descriptor of the reference user, determine the excretion data corresponding to the reference subsequence within a preset time period as the reference excretion data sequence.

[0052] In this embodiment, if it is known that the long-term metabolic rhythms of two patients are synchronized, and their medication and diet in a recent period (e.g., the last 24 hours) are almost the same, then it is reasonable to infer that their excretion patterns in the next preset period (e.g., the next 24 hours) should also be similar.

[0053] Furthermore, while any single reference patient may exhibit individualized random biases, the shared trends among multiple highly similar patients are closer to the true pattern. Therefore, the overall metabolic consistency... High reference patients Its metabolic behavior is more reliable and should therefore account for a larger proportion in the final prediction of excretion results: First, extract the target user's medication and diet timeline data for the most recent 24 hours (the most recent preset time period, which can be adjusted). ( This serves as a query template, representing 96 past record timestamps, one every 15 minutes.

[0054] Then, within each reference patient's entire historical database, primarily from the corresponding medication and diet time-series data, a sliding window is used to search for the 24-hour medication and diet subsequences that best match the query template; these are collectively referred to as reference subsequences. The matching degree can be calculated using cosine similarity. Once found, it can be further analyzed using metabolic descriptors. Find the excretion data for the next 24 hours corresponding to this reference subsequence. ( (For 96 future recording points), this excretion data can be regarded as reference excretion data of the reference patient under similar circumstances to the target user's current situation. The reference discharge data at each time point constitute the reference discharge data sequence.

[0055] Step S4: Determine the excretion prediction sequence for the target user using metabolic consistency and reference excretion data, and make a replacement reminder decision based on the excretion prediction sequence and the remaining absorbable amount of the current diaper.

[0056] Specifically, step S4, which uses metabolic consistency and reference excretion data to determine the target user's predicted excretion sequence, includes: The degree of metabolic consistency is used as the weight of the corresponding reference excretion data, and the weighted average of the reference excretion data of all reference users is calculated to obtain the excretion prediction sequence of the target user.

[0057] Based on the above embodiments, in this embodiment, all previously screened reference patients will be included. (For example, all reference patients have) The reference excretion data provided by the patient were weighted and averaged, with the weight being the weight of each reference patient. metabolic consistency Ultimately, this will allow us to obtain the target user's potential excretion patterns over a future period (e.g., 24 hours). : This allows us to calculate the recording timestamps for the next 24 hours. The possible discharge scenarios at the site are used to obtain the discharge prediction sequence. The discharge status refers to the discharge volume. Adding 0.001 to the denominator is to prevent the denominator from being 0, which would cause calculation errors. The resulting error is within the allowable range.

[0058] Specifically, please refer to Figure 5 Step S4, which involves making a replacement reminder decision based on the excretion prediction sequence and the remaining absorbable amount of the current diaper, includes: Step S41: Use the current humidity value and maximum absorbency of the diaper to obtain its remaining absorbable amount, and determine the predicted excretion amount within the earliest prediction time window in the excretion prediction sequence. Step S42: When the predicted excretion amount is greater than the remaining absorbable amount, an emergency reminder to change the diaper is issued immediately.

[0059] Based on the above embodiments, in this embodiment, the target user's excretion prediction sequence for the next 24 hours is... and the detected current saturation level of the diaper. Combined with the maximum absorbency of diapers It can make optimal decisions on changing reminders and also develop disease monitoring functions.

[0060] Remaining absorbency calculation: Calculate the remaining absorbable capacity of the current diaper. .

[0061] Change reminder decision: It compares the predicted future discharge volume with the data and performs multi-level intelligent judgment.

[0062] If the earliest predicted excretion volume is within the first prediction time window (e.g., the previously preset recording time interval of 15 minutes), then... An urgent reminder to replace it should be issued immediately.

[0063] Based on the above embodiments, in one embodiment, step S4, which involves making a replacement reminder decision based on the excretion prediction sequence and the remaining absorbable amount of the current diaper, further includes: When the predicted discharge amount is less than or equal to the remaining absorbable amount, the cumulative predicted discharge amount within multiple consecutive prediction time windows in the discharge prediction sequence is determined. When the cumulative predicted excretion exceeds the safety limit of the remaining absorbable amount, a future reminder time is determined and a diaper replacement warning is issued at the future reminder time.

[0064] In this embodiment, if However, the cumulative predicted discharge volume within multiple consecutive forecast time windows (e.g., a total of 6 hours, 24 windows) in the future... Here, 0.8 is used as a safety factor. The safety limit is set 30 minutes in advance of the time corresponding to the 6th hour in the future as the future reminder time, and a replacement warning is issued at that future reminder time to prompt nursing staff to make preparations.

[0065] In addition, it can provide hygiene reminders: if the diaper is used continuously for more than 8 hours, even if there is still enough absorbency, a replacement reminder will be issued based on hygiene considerations to prevent bacterial growth and skin infections.

[0066] This invention constructs disease descriptors representing user disease states and metabolic descriptors representing metabolic processes using a historical database including clinical, dietary, and excretion data. It then mines similar metabolic patterns among users in the database to build a personalized excretion prediction model for the target user. This model can more accurately predict the user's excretion time and volume over a future period based on multi-dimensional data matched with other similar users. This allows the system to proactively make decisions based on future predictions, rather than reacting passively. This effectively improves the accuracy and reliability of diaper change recognition and reminders, maximizing diaper utilization while ensuring user comfort.

[0067] Example 2: This invention also proposes a humidity monitoring and replacement reminder device integrated into a smart diaper. The device can be a data processing device such as a computer or server, or a combination of multiple devices.

[0068] like Figure 6 As shown, Figure 6 This is a schematic diagram of the hardware operating environment of the humidity monitoring and replacement reminder device integrated into a smart diaper, which is involved in the embodiment of the present invention.

[0069] like Figure 6As shown, the humidity monitoring and replacement reminder device integrated into a smart diaper may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display or an input unit such as a control panel; the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed RAM or a stable, non-volatile memory, such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001. The memory 1005, as a computer storage medium, may include a humidity monitoring and replacement reminder program integrated into the smart diaper (hereinafter referred to as the "humidity monitoring and replacement reminder program").

[0070] Those skilled in the art will understand that Figure 6 The hardware structure shown does not constitute a limitation on the device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0071] Continue to refer to Figure 6 , Figure 6 The memory 1005, which is a computer-readable storage medium, may include an operating device, a user interface module, a network communication module, and a humidity monitoring and replacement reminder program integrated into the smart diaper.

[0072] exist Figure 6 In this embodiment, the network communication module is mainly used to connect to the server and can communicate with the server for data; while the processor 1001 can call the humidity monitoring and replacement reminder program integrated into the smart diaper stored in the memory 1005 and execute the steps in the above embodiments.

[0073] Based on the hardware structure of the humidity monitoring and replacement reminder device integrated into the smart diaper described above, various embodiments of the humidity monitoring and replacement reminder system integrated into the smart diaper of the present invention are implemented.

[0074] Furthermore, the present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a humidity monitoring and replacement reminder program integrated into a smart diaper, wherein, when executed by a processor, the humidity monitoring and replacement reminder program integrated into the smart diaper implements the steps of the method corresponding to the humidity monitoring and replacement reminder system integrated into the smart diaper as described above.

[0075] The method implemented when the humidity monitoring and replacement reminder program integrated into the smart diaper is executed can be referred to in the various embodiments of the humidity monitoring and replacement reminder system integrated into the smart diaper of the present invention, and will not be repeated here.

[0076] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0077] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0078] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] The above description is only a preferred embodiment of the present invention and does not limit the scope of protection of the present invention. All equivalent structural / method transformations made under the inventive concept of the present invention using the contents of the present invention specification and drawings, or direct / indirect applications in other related technical fields, are included within the scope of protection of the present invention.

Claims

1. A humidity monitoring and replacement reminder system integrated into a smart diaper, characterized in that, The system includes: The feature extraction module is used to determine disease descriptors representing disease states based on the user's clinical data, and to determine metabolic descriptors representing metabolic processes based on the user's medication, diet, and excretion data during the metabolic cycle. The excretion prediction module is used to determine the reference user for the target user based on the similarity of disease descriptors between users, and to determine the degree of metabolic consistency between the reference user and the target user based on the similarity of metabolic descriptors between the target user and the reference user. Based on the reference subsequence that matches the medication and diet time series data of the target user within the most recent preset time period among the reference users, determine the reference excretion data corresponding to the subsequent reference subsequence; By utilizing metabolic consistency and reference excretion data, an excretion prediction sequence for the target user is determined, and a replacement reminder decision is made based on the excretion prediction sequence and the remaining absorbable amount of the current diaper.

2. The humidity monitoring and replacement reminder system integrated into smart diapers according to claim 1, characterized in that, The process of determining disease descriptors representing disease states based on user clinical data includes: Based on the user's clinical data, extract the medication feature vector, clinical symptom vector, and basic condition vector; The drug use feature vector, clinical symptom vector, and basic condition vector are fused and quantized into a multidimensional disease descriptor representing the disease state.

3. The humidity monitoring and replacement reminder system integrated into smart diapers according to claim 1, characterized in that, The step of determining reference users for the target user based on the similarity of disease descriptors between users includes: Determine the cosine similarity of the vectors with the same dimensions in the disease descriptors between the target user and other users; The disease similarity between the target user and other users on the disease descriptor is obtained by combining the various cosine similarities. Other users whose disease similarity is greater than or equal to a preset similarity threshold are used as reference users for the target user.

4. The humidity monitoring and replacement reminder system integrated into smart diapers according to claim 1, characterized in that, The process of determining metabolic descriptors characterizing metabolic processes based on user medication, diet, and excretion data during the metabolic cycle includes: Centered on any medication event of the user, the preset time period before and after medication is used as the metabolic cycle; The vectors of medication use, diet, and excretion at each recording point in the metabolic cycle are arranged in chronological order and fused and quantified into a multidimensional metabolic descriptor representing the metabolic process.

5. The humidity monitoring and replacement reminder system integrated into smart diapers according to claim 1, characterized in that, The step of determining the degree of metabolic consistency between the reference user and the target user based on the similarity of metabolic descriptors between the target user and the reference user includes: Determine the DTW distance between the target user and the reference user for each vector sequence with the same dimension in the metabolic descriptor. The metabolic consistency of the reference user with respect to the target user is determined by using the DTW distances.

6. The humidity monitoring and replacement reminder system integrated into smart diapers according to claim 5, characterized in that, The method of determining the metabolic consistency of the reference user with respect to the target user using each DTW distance includes: The degree of local metabolic consistency between the reference user and the target user in a single metabolic cycle pair is determined by using the DTW distances. A metabolic descriptor sequence composed of multiple metabolic cycles is determined, and the global matching distance between the metabolic descriptor sequences of the target user and the reference user is determined based on dynamic time warping. The global metabolic consistency of the reference user relative to the target user is obtained by using the average local metabolic consistency of multiple metabolic cycle pairs and the global matching distance.

7. The humidity monitoring and replacement reminder system integrated into smart diapers according to claim 1, characterized in that, The step of determining the reference excretion data corresponding to the reference subsequence based on the reference subsequence matching the medication and diet time series data of the reference users within the most recent preset time period with the target user includes: Using the medication and diet time series data of the target user within the most recent preset time period as a query template, the reference subsequence with the highest matching degree is extracted from the medication and diet time series data of the reference user; Based on the metabolic descriptor of the reference user, the excretion data corresponding to the reference subsequence within a preset time period are determined as the reference excretion data sequence.

8. The humidity monitoring and replacement reminder system integrated into smart diapers according to claim 1, characterized in that, The method of determining the target user's excretion prediction sequence using metabolic consistency and reference excretion data includes: The degree of metabolic consistency is used as the weight of the corresponding reference excretion data, and the weighted average of the reference excretion data of all reference users is calculated to obtain the excretion prediction sequence of the target user.

9. The humidity monitoring and replacement reminder system integrated into smart diapers according to claim 1, characterized in that, The process of making a replacement reminder decision based on the excretion prediction sequence and the remaining absorbable amount of the current diaper includes: The remaining absorbable amount of the diaper is obtained by using its current humidity value and maximum absorbency, and the predicted excretion amount in the earliest future prediction time window in the excretion prediction sequence is determined. An emergency diaper change reminder will be issued immediately when the predicted excretion exceeds the remaining absorbable amount.

10. The humidity monitoring and replacement reminder system integrated into smart diapers according to claim 9, characterized in that, The method of making a replacement reminder decision based on the excretion prediction sequence and the remaining absorbable amount of the current diaper also includes: When the predicted discharge amount is less than or equal to the remaining absorbable amount, the cumulative predicted discharge amount within multiple consecutive prediction time windows in the discharge prediction sequence is determined. When the cumulative predicted excretion exceeds the safety limit of the remaining absorbable amount, a future reminder time is determined and a diaper replacement warning is issued at the future reminder time.

Images