Intelligent paper diaper monitoring and alarming system and method based on Internet

Abstract

The invention relates to the field of paper diaper monitoring and alarming, and particularly discloses an intelligent paper diaper monitoring and alarming system and method based on the Internet. The method comprises the following steps: firstly, acquiring environment smell data at a plurality of preset time points acquired by a paper diaper inner side smell sensor, paper diaper humidity values at a plurality of preset time points acquired by a paper diaper inner side humidity detection strip, and paper diaper internal environment temperature values at a plurality of preset time points acquired by a paper diaper inner side temperature sensor; the method comprises the following steps of: firstly, performing feature extraction and correlation analysis on the three parts by using a deep learning technology, and finally judging whether to send out a paper diaper replacement prompt through a classifier, so as to perform adjustment according to individual requirements and use conditions and provide more suitable replacement suggestions, thereby reducing skin problems or discomfort caused by not timely replacement of paper diapers, and improving the paper diaper replacement efficiency. The nursing effect is improved.

Description

Technical Field

[0001] The present application relates to the field of diaper monitoring and alarm, and more specifically, to an Internet-based intelligent diaper monitoring and alarm system and method. Background Art

[0002] Traditional diapers are effective in caring for people with poor self-care abilities (such as infants and bedridden patients), but there is a problem of untimely replacement, which may lead to diaper rash, eczema and bacterial infection.

[0003] Existing technologies usually use the wetness reminder function on the surface of diapers to determine when to change diapers, that is, using the color change of water-discolored materials to indicate the need for replacement. However, these technologies mainly rely on close-up visual or tactile inspections, cannot provide real-time and accurate moisture monitoring, and lack the ability to perform remote non-contact monitoring, resulting in inaccurate timing of diaper replacement, affecting the timeliness and reliability of replacement.

[0004] Therefore, an Internet-based smart diaper monitoring and alarm system and method are desired. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides an Internet-based intelligent diaper monitoring alarm system and method, which first obtains the environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper, the diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip inside the diaper, and the diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor inside the diaper, and then uses deep learning technology to perform feature extraction and correlation analysis on the three, and finally uses a classifier to determine whether to issue a diaper replacement reminder, and then adjusts according to individual needs and usage conditions, providing more suitable replacement suggestions, thereby reducing skin problems or discomfort caused by untimely diaper replacement and improving care effects.

[0006] According to one aspect of the present application, there is provided an Internet-based smart diaper monitoring and alarm system, which includes:

[0007] A diaper monitoring data acquisition module, used to acquire environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper, diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip inside the diaper, and diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor inside the diaper;

[0008] A diaper monitoring data extraction module, used to extract a diaper environmental odor feature vector and a diaper state multimodal association vector from the environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper, the diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip inside the diaper, and the diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor inside the diaper;

[0009] The diaper changing reminder judgment module is used to judge whether to issue a diaper changing reminder based on the diaper environment odor feature vector and the diaper state multimodal association vector.

[0010] According to another aspect of the present application, there is provided an Internet-based smart diaper monitoring and alarm method, which includes:

[0011] Acquire environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper, diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip inside the diaper, and diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor inside the diaper;

[0012] Extracting a diaper environmental odor feature vector and a diaper state multimodal association vector from the environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper, the diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip inside the diaper, and the diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor inside the diaper;

[0013] Based on the diaper environment odor feature vector and the diaper state multimodal association vector, it is determined whether to issue a diaper changing reminder.

[0014] Compared with the prior art, the present application provides an Internet-based smart diaper monitoring and alarm system and method, which first obtains environmental odor data at multiple predetermined time points collected by the odor sensor on the inside of the diaper, the diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip on the inside of the diaper, and the diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor on the inside of the diaper, and then uses deep learning technology to perform feature extraction and correlation analysis on the three, and finally uses a classifier to determine whether to issue a diaper replacement reminder, and then adjusts according to individual needs and usage conditions to provide more appropriate replacement suggestions, thereby reducing skin problems or discomfort caused by untimely diaper replacement and improving care effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0016] Figure 1 It is a block diagram of an Internet-based smart diaper monitoring and alarm system according to an embodiment of the present application.

[0017] Figure 2 It is a block diagram of a diaper monitoring data extraction module in an Internet-based smart diaper monitoring and alarm system according to an embodiment of the present application.

[0018] Figure 3 It is a block diagram of a diaper status multimodal feature extraction unit in an Internet-based smart diaper monitoring and alarm system according to an embodiment of the present application.

[0019] Figure 4 It is a block diagram of a diaper changing reminder judgment module in an Internet-based smart diaper monitoring and alarm system according to an embodiment of the present application.

[0020] Figure 5 The figure is a flow chart of an Internet-based smart diaper monitoring and alarm method according to an embodiment of the present application. DETAILED DESCRIPTION

[0021] Various exemplary embodiments, features and aspects of the present application will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0022] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0023] In addition, in order to better illustrate the present application, numerous specific details are provided in the following specific embodiments. It should be understood by those skilled in the art that the present application can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present application.

[0024] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0025] Figure 1 FIG. 1 is a block diagram of an Internet-based smart diaper monitoring and alarm system according to an embodiment of the present application. Figure 1 As shown, according to the embodiment of the present application, the Internet-based smart diaper monitoring and alarm system 100 includes: a diaper monitoring data acquisition module 110, which is used to obtain environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper, diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip inside the diaper, and diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor inside the diaper; a diaper monitoring data extraction module 120, which is used to extract diaper environmental odor feature vectors and diaper state multimodal association vectors from the environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper, the diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip inside the diaper, and the diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor inside the diaper; a diaper changing reminder judgment module 130, which is used to judge whether to issue a diaper changing reminder based on the diaper environmental odor feature vector and the diaper state multimodal association vector.

[0026] In the above-mentioned Internet-based intelligent diaper monitoring and alarm system 100, the diaper monitoring data acquisition module 110 is used to obtain the environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper, the diaper humidity values ​​at multiple predetermined times collected by the humidity detection strip inside the diaper, and the diaper internal environmental temperature values ​​at multiple predetermined times collected by the temperature sensor inside the diaper. It should be understood that traditional diapers perform well when caring for infants or bedridden patients and other people with poor self-care ability, but there is a problem of untimely replacement, which may lead to diaper rash, eczema and bacterial infection. Current technology usually relies on materials with color-changing functions on the surface of diapers to indicate whether they need to be replaced. However, these methods can only be judged by close-range visual or tactile detection, and cannot monitor humidity in real time and accurately, and there is no remote contactless monitoring function, which may lead to inaccurate replacement timing, thereby affecting the timeliness and reliability of replacement. Therefore, in the technical solution of the present application, by taking the environmental odor data at multiple predetermined time points collected by the odor sensor on the inside of the diaper, the diaper humidity values ​​at multiple predetermined times collected by the humidity detection strip on the inside of the diaper, and the diaper internal environmental temperature values ​​at multiple predetermined times collected by the temperature sensor on the inside of the diaper, and combining with deep learning technology, it is determined whether to issue a diaper changing reminder, and adjustments are made according to personal needs and actual usage, so as to provide more appropriate changing suggestions, which can reduce skin problems or discomfort caused by untimely diaper changing, thereby improving the care effect.

[0027] Specifically, obtaining the environmental odor data, humidity value and temperature value inside the diaper can provide comprehensive and accurate monitoring to ensure that the diaper is changed at the right time. Among them, the odor sensor on the inside of the diaper captures the environmental odor data, which is essential for identifying the presence of urine and other excrement. Secondly, the humidity detection strip provides the humidity data of the diaper, which can directly reflect the usage status of the diaper. Finally, the monitoring of the temperature inside the diaper is equally important. The temperature sensor can detect the temperature changes inside the diaper. These data can reveal the comfort of the diaper and whether the temperature rises due to humidity. The comprehensive odor, humidity and temperature data can form a comprehensive monitoring system. Through multi-dimensional data acquisition, it not only improves the accuracy and timeliness of diaper replacement, but also effectively prevents skin problems and infections. This comprehensive data collection and analysis method provides a more comprehensive monitoring capability than a single sensor data, optimizing the user experience and health management of diapers.

[0028] In the above-mentioned Internet-based intelligent diaper monitoring and alarm system 100, the diaper monitoring data extraction module 120 is used to extract the diaper environmental odor feature vector and the diaper state multimodal association vector from the environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper, the diaper humidity values ​​at multiple predetermined times collected by the humidity detection strip inside the diaper, and the diaper internal environmental temperature values ​​at multiple predetermined times collected by the temperature sensor inside the diaper. It should be understood that comprehensive analysis of odor, humidity and temperature data and multimodal association analysis can form a comprehensive state assessment model that can capture the relationship between different sensor data and identify potential patterns and abnormal situations. This comprehensive analysis method helps to detect the use status of diapers in real time, optimize the replacement time, reduce the occurrence of problems such as diaper rash and eczema, and improve care efficiency.

[0029] Figure 2 FIG. 1 is a block diagram of a diaper monitoring data extraction module in an Internet-based smart diaper monitoring and alarm system according to an embodiment of the present application. Figure 2 As shown, in a specific embodiment of the present application, the diaper monitoring data extraction module 120 includes: a diaper odor feature extraction unit 121, used to perform feature extraction on the environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper to obtain the diaper environmental odor feature vector; a diaper state multimodal feature extraction unit 122, used to perform feature extraction on the diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip inside the diaper and the diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor inside the diaper to obtain the diaper state multimodal association vector.

[0030] It should be understood that environmental odor data usually contains a lot of raw information, and directly using this data for analysis may be complicated and unintuitive. The feature extraction process converts the raw data into useful feature vectors, making analysis and processing more efficient. Among them, the environmental odor data collected by the odor sensor can reflect whether there is urine or other excrement inside the diaper. Since the changes in odor are usually subtle and occur gradually, the feature extraction process can identify the changing patterns and characteristics of odor by processing time series data, which is crucial for accurately determining whether diapers need to be changed. Through feature extraction, complex odor data can be converted into concise and informative feature vectors, which summarize the key features of the odor data, such as changes in odor intensity, odor type, etc.

[0031] Furthermore, the feature extraction of humidity and temperature values ​​is integrated into a multimodal correlation vector of diaper status, which can realize a comprehensive analysis of diaper status. Analyzing humidity or temperature alone may not fully understand the use of diapers, while the multimodal correlation vector can integrate data from different sensors and capture the relationship and interaction effects between them.

[0032] In a specific embodiment of the present application, the diaper odor feature extraction unit 121 includes: constructing the environmental odor data at multiple predetermined time points collected by the odor sensor on the inside of the diaper into a diaper environmental odor input vector; passing the diaper environmental odor input vector through a diaper environmental odor sequence encoder including a one-dimensional convolutional layer and a fully connected layer to obtain the diaper environmental odor feature vector.

[0033] It should be understood that the environmental odor data on the inside of diapers often exists in the form of continuous time series. These data contain information such as the intensity, type, and change trend of the odor. Directly using these raw data for analysis may result in low processing efficiency due to the large amount and complexity of the data. By constructing the time series odor data as an input vector, the temporal order and diversity of the raw data can be converted into structured information, simplifying the data processing process.

[0034] Furthermore, the diaper environment odor input vector is processed by a diaper environment odor sequence encoder including a one-dimensional convolutional layer and a fully connected layer in order to transform the complex odor data into a more refined and structured feature representation for further processing and application. Among them, the one-dimensional convolutional layer can effectively capture the local features and patterns in the data when processing time series data. In the diaper environment odor input vector, the odor data changes over time and has time dependence and local features. By applying the one-dimensional convolution operation, local patterns in the odor data, such as fluctuations in odor intensity and changing trends, can be extracted. These local features are very important for understanding the changes in odor and its impact on the state of diapers. The design of the convolutional layer can extract key information from the input vector through a sliding window mechanism, thereby effectively extracting features from the odor data. Then, the fully connected layer is used to integrate and transform the features extracted by the convolutional layer. The fully connected layer can combine and map the local features obtained by the convolutional layer at a high level to form a compact and global feature representation. Through the combination of one-dimensional convolutional layers and fully connected layers, the diaper environment odor sequence encoder can take into account both local feature extraction and global feature integration when processing time series data. This method can convert the original odor data into high-dimensional feature vectors, which not only contain the key patterns and trends of the time series data, but also capture the complex relationship of odor changes. Specifically, the fully connected layer of the diaper environment odor sequence encoder containing a one-dimensional convolutional layer and a fully connected layer is used to fully connect the diaper environment odor input vector to extract the high-dimensional implicit features of the eigenvalues ​​at each position in the diaper environment odor input vector; and, the one-dimensional convolutional layer of the diaper environment odor sequence encoder containing a one-dimensional convolutional layer and a fully connected layer is used to one-dimensionally encode the diaper environment odor input vector to extract the high-dimensional implicit correlation features of the correlation between the eigenvalues ​​at each position in the diaper environment odor input vector.

[0035] Figure 3 FIG. 1 is a block diagram of a diaper state multimodal feature extraction unit in an Internet-based smart diaper monitoring and alarm system according to an embodiment of the present application. Figure 3 As shown, in a specific embodiment of the present application, the diaper state multimodal feature extraction unit 122 includes: a diaper state feature arrangement subunit 1221, used to arrange the diaper humidity values ​​at multiple predetermined times collected by the humidity detection strip on the inside of the diaper and the diaper internal environment temperature values ​​at multiple predetermined times collected by the temperature sensor on the inside of the diaper to obtain a diaper humidity change input vector and a diaper internal environment temperature input vector; a diaper state multimodal feature encoding subunit 1222, used to feature encode the diaper humidity change input vector and the diaper internal environment temperature input vector to obtain the diaper state multimodal association vector.

[0036] It should be understood that time series data usually contains key information that changes over time, and the changes in humidity and temperature values ​​can reflect the actual use and status of diapers. By arranging the humidity values ​​and temperature values ​​into input vectors respectively, the information in the time series can be organized in chronological order to form a structured data representation. Secondly, constructing the humidity values ​​and temperature values ​​into input vectors respectively helps to extract these two aspects of information separately. The humidity input vector can reflect the moisture absorption of the diaper and reveal the pattern of humidity changes, such as the rising or falling trend of humidity. The temperature input vector reflects the ambient temperature inside the diaper, including the increase or decrease in temperature. By constructing these two input vectors separately, the changes in humidity and temperature can be analyzed independently, and combined with these two data for comprehensive evaluation, so as to have a more comprehensive understanding of the status of the diaper.

[0037] Furthermore, the diaper humidity change input vector and the ambient temperature input vector provide information on different aspects of the diaper state. Analyzing these two vectors alone may not fully grasp the comprehensive state of the diaper, so they need to be feature encoded to fuse this information. The feature encoding process aims to transform the original humidity and temperature input vectors into a comprehensive and more refined representation, namely the diaper state multimodal association vector. Feature encoding usually uses some advanced machine learning or deep learning techniques, such as encoder modules in neural networks. These techniques can learn how to extract meaningful features from humidity and temperature data and map them into a unified feature space. This can capture the complex relationship between humidity and temperature, and their correlation with the overall state of the diaper.

[0038] In a specific embodiment of the present application, the diaper state multimodal feature encoding subunit 1222 includes: calculating the association matrix between the diaper humidity change input vector and the diaper internal environment temperature input vector to obtain the diaper state multimodal association matrix; passing the diaper state multimodal association matrix through a diaper state multimodal feature encoder based on a convolutional neural network to obtain the diaper state multimodal association vector.

[0039] It should be understood that humidity and temperature are two important aspects of the diaper status. The humidity value reflects the moisture absorption of the diaper, while the temperature value provides the thermal condition of the internal environment. Although these two data come from different sources, they jointly affect the performance of the diaper. The calculation of the correlation matrix can reveal the correlation between humidity and temperature data. By calculating the correlation matrix between the humidity change input vector and the temperature input vector, the strength and direction of the relationship between the two sets of data can be determined. The correlation matrix reflects the linear relationship between humidity and temperature, for example, when the humidity increases, whether the temperature also changes accordingly, or whether there is some regular linkage between the two. This matrix can help identify the interdependence between humidity and temperature, and how they jointly affect the status of diapers.

[0040] Furthermore, the diaper status multimodal association matrix contains the association information between humidity and temperature data. This matrix presents the relationship between these two data types, but the data in the original matrix may be complex and high-dimensional. In order to effectively utilize this data, the convolutional neural network can extract local features and patterns in the matrix through its convolutional layer. The convolution operation can identify specific patterns in the matrix, such as the linkage effect of humidity and temperature, which are crucial to understanding the comprehensive status of diapers. The feature encoding ability of the convolutional neural network enables it to process and extract key information from multimodal data. CNN gradually transforms the input matrix into higher-level feature representations through multiple layers of convolution and pooling operations. These high-level features can capture more complex relationships and patterns, such as the nonlinear dependence between humidity and temperature. In this way, CNN can transform the information in the diaper status multimodal association matrix into a more compact and meaningful diaper status multimodal association vector. Specifically, each layer of the diaper state multimodal feature encoder based on convolutional neural network is used to perform convolution processing, mean pooling processing based on local feature matrix and nonlinear activation processing on the input data in the forward pass of the layer, so that the last layer of the diaper state multimodal feature encoder based on convolutional neural network outputs the diaper state multimodal association vector, wherein the input of the diaper state multimodal feature encoder based on convolutional neural network is the diaper state multimodal association matrix.

[0041] In the above-mentioned Internet-based intelligent diaper monitoring and alarm system 100, the diaper replacement reminder judgment module 130 is used to determine whether to issue a diaper replacement reminder based on the diaper environment odor feature vector and the diaper state multimodal association vector. It should be understood that combining the odor feature vector with the state multimodal association vector can comprehensively evaluate the state of the diaper from two different angles. The odor feature vector mainly focuses on the hygiene status and odor changes of the diaper after use, while the multimodal association vector provides detailed information on technical indicators such as humidity and temperature of the diaper. By combining the information of the two, it is possible to more accurately judge whether the diaper has reached the conditions for replacement, so as to ensure that a reminder can be issued in time when the diaper reaches the replacement standard, thereby maintaining the comfort and hygiene of the user. This multi-angle evaluation method can provide a more comprehensive and accurate basis for judgment and improve the efficiency and quality of diaper management.

[0042] Figure 4 FIG. 1 is a block diagram of a diaper replacement reminder judgment module in an Internet-based smart diaper monitoring and alarm system according to an embodiment of the present application. Figure 4 As shown, in a specific embodiment of the present application, the diaper changing reminder judgment module 130 includes: a diaper feature fusion unit 131, used to perform manifold smoothness optimization based on attribute fine-grained correlation on the diaper environment odor feature vector and the diaper state multimodal association vector to obtain a diaper changing reminder judgment feature vector; a diaper changing reminder classification judgment unit 132, used to pass the diaper changing reminder judgment feature vector through a classifier to obtain a classification result, and the classification result is used to determine whether to issue a diaper changing reminder.

[0043] It should be understandable that the diaper environmental odor feature vector mainly reflects the odor generated by the diaper during use. Changes in odor usually indicate changes in the humidity of the diaper, the length of use, and possible bacterial growth. On the other hand, the diaper state multimodal association vector reveals the physical state of the diaper by integrating technical data such as humidity and temperature. These data can accurately reflect the moisture absorption of the diaper and the current environmental conditions, thereby helping to determine whether the diaper has reached the critical point where it needs to be replaced. Different features may have different effects on the state of the diaper. By fusing the feature vectors of the two, the misjudgment caused by a single feature can be reduced, thereby improving the accuracy of the reminder.

[0044] In particular, in the technical solution of the present application, considering that the diaper environmental odor feature vector and the diaper state multimodal association vector are extracted from different physical properties and processing paths respectively, they represent different aspects of information during the use of diapers. Due to the essential differences in these features and the different extraction methods, the two feature vectors have significant feature heterogeneity. Specifically, they are extracted from the environmental odor data collected by the odor sensor inside the diaper, focusing on the changing trend of the odor. Extracted from the humidity value collected by the humidity detection strip inside the diaper and the internal environment temperature value collected by the temperature sensor, the main focus is on the changes in humidity and temperature and their relationship. The diaper environmental odor feature vector and the diaper state multimodal association vector may exist on different manifolds, which means that they have different distribution patterns in their respective spaces. Directly splicing them together may result in the final feature vector not having a clear manifold in the new space, that is, the feature manifold smoothness is insufficient. Since the two feature vectors come from different sources, they may not be well mapped to each other in the fused feature space, that is, one type of feature may not accurately reflect the feature changes of another type, resulting in increased uncertainty in feature expression. Based on this, in the technical solution of the present application, the manifold smoothness optimization based on attribute fine-grained correlation is performed on the diaper environmental odor feature vector and the diaper state multimodal association vector.

[0045] Specifically, in an embodiment of the present application, the diaper environment odor feature vector and the diaper state multimodal association vector are optimized for manifold smoothness based on attribute fine-grained correlation to obtain a diaper change reminder judgment feature vector, including: constructing a diaper environment odor-state distance topological matrix between the diaper environment odor feature vector and the diaper state multimodal association vector; constructing a diaper environment odor-state eigenvalue granularity association matrix between the diaper environment odor feature vector and the diaper state multimodal association vector; and optimizing the diaper environment odor-state distance topological matrix based on the diaper environment odor-state distance topological matrix. The environmental odor-state eigenvalue granularity association matrix is ​​topologically modulated to obtain a diaper environmental odor-state topological modulation association matrix; the diaper environmental odor-state topological modulation association matrix is ​​used as a perspective co-projection space, and the diaper environmental odor feature vector and the diaper state multimodal association vector are projected into the perspective co-projection space to obtain a perspective-modulated diaper environmental odor feature vector and a perspective-modulated diaper state multimodal association vector; the perspective-modulated diaper environmental odor feature vector and the perspective-modulated diaper state multimodal association vector are fused to obtain the diaper change reminder judgment feature vector.

[0046] In an embodiment of the present application, another implementation expression of performing manifold smoothness optimization based on attribute fine-grained correlation on the diaper environment odor feature vector and the diaper state multimodal association vector to obtain a diaper change reminder judgment feature vector may be: processing the diaper environment odor feature vector and the diaper state multimodal association vector using the following formula to obtain a diaper change reminder judgment feature vector; wherein the formula is:

[0047] M t =D(V1,V2)

[0048]

[0049] V c =α·V1′+β·V2′

[0050] Wherein, V1 represents the diaper environment odor feature vector, V2 represents the diaper state multimodal association vector, and D(V1, V2) is the distance topological matrix between the diaper environment odor feature vector and the diaper state multimodal association vector, that is, d i,j =d(v 1i ,v 2j ), d i,j is the eigenvalue of the position (i, j) in the distance topology matrix, d(v 1i ,v 2j ) represents the distance between the eigenvalue of the diaper environment odor feature vector at the i-th position and the eigenvalue of the diaper state multimodal association vector at the j-th position, and V1 and V2 are both column vectors, M t represents the distance topology matrix, T represents the transpose of the vector, Represents matrix multiplication, M v represents the eigenvalue granularity correlation matrix, exp represents the natural exponential function, M c represents the topological modulation association matrix, V1' represents the odor feature vector of the diaper environment modulated by the viewing angle, V2' represents the multimodal association vector of the diaper state modulated by the viewing angle, α and β represent weighted hyperparameters, V c Represents the diaper changing reminder judgment feature vector.

[0051] That is, in the technical solution of the present application, the manifold smoothness optimization based on the fine-grained attribute correlation is performed on the diaper environment odor feature vector and the diaper state multimodal association vector, which first constructs the diaper environment odor-state distance topological matrix between the diaper environment odor feature vector and the diaper state multimodal association vector. This step utilizes the idea of ​​graph theory, takes the eigenvalues ​​of each position in the diaper environment odor feature vector and the diaper state multimodal association vector as nodes, and uses the distance metric function to determine the low-dimensional embedding expression of the edges between nodes, so as to construct a feature expression that can quantify the topological association relationship between the diaper environment odor feature vector and the diaper state multimodal association vector. This step is crucial to understanding the spatial distribution of data points and their mutual connections, and also provides basic structural information for subsequent steps.

[0052] Next, a diaper environment odor-state feature value granularity association matrix is ​​constructed between the diaper environment odor feature vector and the diaper state multimodal association vector. This step focuses on exploring the correlation between the internal attributes of the feature vector. In a specific example, the product between the transposed vectors of the diaper environment odor feature vector and the diaper state multimodal association vector is calculated to obtain the diaper environment odor-state feature value granularity association matrix. Furthermore, the diaper environment odor-state feature value granularity association matrix is ​​topologically modulated based on the diaper environment odor-state distance topological matrix to obtain the diaper environment odor-state topological modulation association matrix. That is, the feature value granularity association information of the diaper environment odor feature vector and the diaper state multimodal association vector is driven to wander on the distance topological map to construct a low-dimensional modulated perspective co-projection space domain for mapping the diaper environment odor feature vector and the diaper state multimodal association vector to a continuous high-dimensional regression space attribute.

[0053] Next, the diaper environment odor-state topological modulation association matrix is ​​used as the perspective co-projection space, and the diaper environment odor feature vector and the diaper state multimodal association vector are projected into the perspective co-projection space to obtain the perspective modulated diaper environment odor feature vector and the perspective modulated diaper state multimodal association vector. That is, the key to this technical solution is to find an implicit third space with modulation capability, in which as much information of the original high-dimensional data as possible is retained, so that the converted new feature vector not only reduces the dimension, but also maintains the relative position relationship between the original features.

[0054] Finally, the perspective-modulated diaper environment odor feature vector and the perspective-modulated diaper state multimodal association vector are fused to obtain the diaper change reminder judgment feature vector. Fusion can be achieved in a variety of forms, ranging from simple arithmetic averages to complex ensemble learning algorithms, depending on the application scenario and the goals pursued. The final diaper change reminder judgment feature vector combines the main features of the two sets of input data and provides a more comprehensive data representation, which is not only conducive to improving the performance of machine learning models, but also promotes the ability of cross-modal or multi-source data analysis, thereby significantly enhancing the understanding and utilization efficiency of complex data structures.

[0055] Furthermore, the classifier is an effective tool for processing such complex data. It learns patterns and regularities in the data through training algorithms, so that it can classify new feature vectors. The core function of the classifier is to map the input feature vector to predefined categories. In the application of diaper changing reminder, the task of the classifier is to classify the input feature vector into two categories: "need to be changed" or "no need to be changed". The output of the classifier can be directly used as the decision basis for the changing reminder. For example, if the classifier determines that the feature vector belongs to the "need to be changed" category, the system will issue a changing reminder to prompt the user to change the diaper in time. This automated decision-making process can effectively reduce the error of human judgment and improve the timeliness and accuracy of the reminder. In this way, machine learning technology can be used to intelligently analyze the status of diapers, thereby providing accurate and timely changing reminders, improving user comfort and diaper management efficiency.

[0056] In summary, the embodiments of the present application first obtain the environmental odor data at multiple predetermined time points collected by the odor sensor on the inside of the diaper, the diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip on the inside of the diaper, and the diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor on the inside of the diaper, and then use deep learning technology to perform feature extraction and correlation analysis on the three, and finally use a classifier to determine whether to issue a diaper replacement reminder, and then make adjustments based on individual needs and usage conditions to provide more appropriate replacement suggestions, thereby reducing skin problems or discomfort caused by untimely diaper replacement and improving care effects.

[0057] As described above, the Internet-based smart diaper monitoring and alarm system 100 according to the embodiment of the present application can be implemented in various terminal devices. In one example, the Internet-based smart diaper monitoring and alarm system 100 can be integrated into the terminal device as a software module and / or a hardware module. For example, the Internet-based smart diaper monitoring and alarm system 100 can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the Internet-based smart diaper monitoring and alarm system 100 can also be one of the many hardware modules of the terminal device.

[0058] Alternatively, in another example, the Internet-based smart diaper monitoring alarm system 100 and the terminal device may also be separate devices, and the Internet-based smart diaper monitoring alarm system 100 may be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0059] Figure 5 FIG. 1 is a flow chart of an Internet-based smart diaper monitoring and alarm method according to an embodiment of the present application. Figure 5 As shown, according to the Internet-based smart diaper monitoring and alarm method of the embodiment of the present application, it includes: S110, acquiring environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper, diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip inside the diaper, and diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor inside the diaper; S120, extracting diaper environmental odor feature vectors and diaper state multimodal association vectors from the environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper, the diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip inside the diaper, and the diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor inside the diaper; S130, judging whether to issue a diaper changing reminder based on the diaper environmental odor feature vector and the diaper state multimodal association vector.

[0060] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned Internet-based smart diaper monitoring and alarm method have been referred to above. Figures 1 to 4 The description of the Internet-based smart diaper monitoring alarm system has been introduced in detail, and therefore, its repeated description will be omitted.

[0061] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0062] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0063] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0064] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0065] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0066] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The second and other words are used to indicate names, but not to indicate any particular order.

[0067] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit of the technical solution of the present invention.

Claims

1. An Internet-based intelligent diaper monitoring and alarm system, characterized in that: include: A diaper monitoring data acquisition module, used to acquire environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper, diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip inside the diaper, and diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor inside the diaper; A diaper monitoring data extraction module, used to extract a diaper environmental odor feature vector and a diaper state multimodal association vector from the environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper, the diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip inside the diaper, and the diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor inside the diaper; The diaper changing reminder judgment module is used to judge whether to issue a diaper changing reminder based on the diaper environment odor feature vector and the diaper state multimodal association vector.

2. The Internet-based smart diaper monitoring and alarm system according to claim 1, characterized in that: The diaper monitoring data extraction module comprises: A diaper odor feature extraction unit, used for extracting features from the environmental odor data at a plurality of predetermined time points collected by the odor sensor inside the diaper to obtain the diaper environmental odor feature vector; The diaper state multimodal feature extraction unit is used to extract features from the diaper humidity values ​​at multiple predetermined times collected by the humidity detection strip inside the diaper and the diaper internal environment temperature values ​​at multiple predetermined times collected by the temperature sensor inside the diaper to obtain the diaper state multimodal association vector.

3. The Internet-based smart diaper monitoring and alarm system according to claim 2, characterized in that: The diaper odor feature extraction unit comprises: constructing the environmental odor data at a plurality of predetermined time points collected by the odor sensor inside the diaper as a diaper environmental odor input vector; The diaper environment odor input vector is passed through a diaper environment odor sequence encoder including a one-dimensional convolutional layer and a fully connected layer to obtain the diaper environment odor feature vector.

4. The Internet-based smart diaper monitoring and alarm system according to claim 3, characterized in that: The diaper state multimodal feature extraction unit comprises: A diaper state feature arrangement subunit, used for arranging the diaper humidity values ​​at a plurality of predetermined times collected by the diaper inner humidity detection strip and the diaper inner environment temperature values ​​at a plurality of predetermined times collected by the diaper inner temperature sensor to obtain a diaper humidity change input vector and a diaper inner environment temperature input vector; The diaper state multimodal feature encoding subunit is used to perform feature encoding on the diaper humidity change input vector and the diaper internal environment temperature input vector to obtain the diaper state multimodal association vector.

5. The Internet-based smart diaper monitoring and alarm system according to claim 4, characterized in that: The diaper state multimodal feature encoding subunit includes: Calculating the association matrix between the diaper humidity change input vector and the diaper internal environment temperature input vector to obtain a diaper state multimodal association matrix; The diaper state multimodal association matrix is ​​passed through a diaper state multimodal feature encoder based on a convolutional neural network to obtain the diaper state multimodal association vector.

6. The Internet-based smart diaper monitoring and alarm system according to claim 5, characterized in that: The diaper state multimodal association matrix is ​​passed through a diaper state multimodal feature encoder based on a convolutional neural network to obtain the diaper state multimodal association vector, including: Each layer of the diaper state multimodal feature encoder based on convolutional neural network is used to perform convolution processing, mean pooling processing based on local feature matrix and nonlinear activation processing on the input data in the forward transmission of the layer, so that the last layer of the diaper state multimodal feature encoder based on convolutional neural network outputs the diaper state multimodal association vector, wherein the input of the diaper state multimodal feature encoder based on convolutional neural network is the diaper state multimodal association matrix.

7. The Internet-based smart diaper monitoring and alarm system according to claim 6, characterized in that: The diaper replacement reminder judgment module includes: A diaper feature fusion unit, used for performing manifold smoothness optimization based on attribute fine-grained correlation on the diaper environment odor feature vector and the diaper state multimodal association vector to obtain a diaper change reminder judgment feature vector; The diaper changing reminder classification judgment unit is used to pass the diaper changing reminder judgment feature vector through a classifier to obtain a classification result, and the classification result is used to judge whether to issue a diaper changing reminder.

8. The Internet-based smart diaper monitoring and alarm system according to claim 7, characterized in that: The diaper feature fusion unit is used for: Constructing a diaper environment odor-state distance topological matrix between the diaper environment odor feature vector and the diaper state multimodal association vector; Constructing a diaper environment odor-state feature value granularity association matrix between the diaper environment odor feature vector and the diaper state multimodal association vector; Based on the diaper environment odor-state distance topological matrix, the diaper environment odor-state characteristic value granularity association matrix is ​​topologically modulated to obtain a diaper environment odor-state topological modulation association matrix; Taking the diaper environment odor-state topological modulation association matrix as the perspective co-projection space, projecting the diaper environment odor feature vector and the diaper state multimodal association vector into the perspective co-projection space to obtain the perspective-modulated diaper environment odor feature vector and the perspective-modulated diaper state multimodal association vector; The diaper changing reminder judgment feature vector is obtained by fusing the perspective-modulated diaper environment odor feature vector and the perspective-modulated diaper state multimodal association vector.

9. An Internet-based smart diaper monitoring and alarm method, characterized in that: include: Acquire environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper, diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip inside the diaper, and diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor inside the diaper; Extracting a diaper environmental odor feature vector and a diaper state multimodal association vector from the environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper, the diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip inside the diaper, and the diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor inside the diaper; Based on the diaper environment odor feature vector and the diaper state multimodal association vector, it is determined whether to issue a diaper changing reminder.

10. The Internet-based smart diaper monitoring and alarm method according to claim 9, characterized in that: Extracting a diaper environmental odor feature vector and a diaper state multimodal association vector from the environmental odor data at multiple predetermined time points collected by the odor sensor inside the diaper, the diaper humidity values ​​at multiple predetermined time points collected by the humidity detection strip inside the diaper, and the diaper internal environmental temperature values ​​at multiple predetermined time points collected by the temperature sensor inside the diaper, including: Performing feature extraction on the environmental odor data at a plurality of predetermined time points collected by the odor sensor inside the diaper to obtain the diaper environmental odor feature vector; Feature extraction is performed on the diaper humidity values ​​at multiple predetermined times collected by the diaper inner side humidity detection strip and the diaper internal environment temperature values ​​at multiple predetermined times collected by the diaper inner side temperature sensor to obtain the diaper state multimodal association vector.

Images