Pressure sore detection method and system based on pressure sensor

Abstract

The invention provides a pressure sore detection method and system based on a pressure sensor. The method comprises the following steps: acquiring pressure data of a to-be-detected part of a user through the pressure sensor; preprocessing the collected pressure data to form a pressure matrix; extracting at least one basic pressure characteristic value based on the pressure matrix; calculating characteristic values of any basic pressure characteristic value in a time domain, a frequency domain and a time-frequency domain, and constructing a multi-level pressure characteristic matrix; and inputting the multi-level pressure feature matrix into a pressure sore state detection model to obtain the pressure sore state of the user, through the method, pressure data acquisition can be performed on the body part of the user in a real-time and non-inductive manner, pressure sore detection is performed, autonomous monitoring of the body part of the user is realized by using an artificial intelligence algorithm, and the user experience is improved. The detection process is flexible and efficient, and the privacy of the user is effectively protected.

Description

Technical Field

[0001] The present invention relates to the field of human health monitoring, and in particular to a pressure sore detection method and system based on a pressure sensor. Background Art

[0002] As the aging process of our society intensifies, the research on pressure injury detection has received widespread attention. Pressure injury (PI), also known as pressure sores, is mainly caused by skin damage due to poor blood flow caused by prolonged pressure. The factors causing PI can be roughly divided into intrinsic factors and extrinsic factors. Intrinsic factors are related to specific parameters of the human body, such as body weight, different sitting postures, nutritional factors and disease conditions. External factors refer to environmental conditions, such as the intensity, duration, friction, shear force of the interface pressure between the person and the cushion, and the degree of skin exposure to the external environment. At present, PI detection methods mainly include: biomathematical models, evaluation scales and artificial intelligence detection models.

[0003] At present, the commonly used PI assessment scales in clinical practice include Braden scale, Norton scale and Waterlow scale. The above tools only empirically evaluate the conventional influencing factors of PI (activity, temperature, humidity, etc.), without objective quantitative standards, and are highly subjective; biomathematical models promote the transformation of PI research from subjective qualitative to objective quantitative, but require accurate pressure values, dynamic parameters such as skin elasticity and capillary reperfusion time as input, making data acquisition difficult and lacking in real-time performance. Summary of the invention

[0004] One of the embodiments of this specification provides a method for detecting pressure sores based on a pressure sensor. The law includes:

[0005] Collect pressure data of the user's tested part through a pressure sensor;

[0006] Preprocessing the collected pressure data to form a pressure matrix;

[0007] Extracting at least one basic pressure characteristic value based on the pressure matrix;

[0008] Calculate the eigenvalues ​​of any of the basic pressure eigenvalues ​​in the time domain, frequency domain and time-frequency domain, and construct a multi-level pressure feature matrix;

[0009] The multi-level pressure feature matrix is ​​input into a pressure sore status detection model to obtain the user's pressure sore status.

[0010] One of the embodiments of this specification provides a pressure sore detection system based on a pressure sensor, the system comprising:

[0011] A data acquisition module, used to collect pressure data of the user's tested part through a pressure sensor;

[0012] A first data processing module, used for preprocessing the collected pressure data to form a pressure matrix;

[0013] A second data processing module, configured to extract at least one basic pressure characteristic value based on the pressure matrix;

[0014] A third data processing module is used to calculate the characteristic values ​​of any of the basic pressure characteristic values ​​in the time domain, frequency domain and time-frequency domain, and construct a multi-level pressure characteristic matrix;

[0015] The state detection module is used to input the multi-level pressure feature matrix into the pressure sore state detection model to obtain the user's pressure sore state.

[0016] One of the embodiments of the present specification provides a pressure sore detection device based on a pressure sensor, including a processor, wherein the processor is used to execute a pressure sore detection method based on the pressure sensor.

[0017] One of the embodiments of the present specification provides a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a pressure sore detection method based on a pressure sensor.

[0018] The beneficial effects of the present invention include:

[0019] (1) The present invention uses a pressure sensor to detect pressure on human body parts, which can realize non-contact real-time data collection, simple data acquisition, more efficient detection process, and protect the privacy of users;

[0020] (2) The present invention adopts a distributed flexible film pressure sensor, which can fit the curved surface of the human body well. The distributed design makes multiple pressure sensing units evenly distributed on the sensor. Each sensing unit can sense the pressure independently with little interference, and realize accurate positioning and feedback of the pressure state of the contact surface;

[0021] (3) The present invention utilizes artificial intelligence algorithms to construct a pressure ulcer status detection model, which can autonomously monitor and evaluate the pressure status of human body parts. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0023] Figure 1 is a schematic diagram of a framework of a wireless human body pressure acquisition system according to some embodiments of this specification;

[0024] Figure 2 is a schematic diagram of a thermal display of human body pressure collected by a pressure sensor according to some embodiments of this specification;

[0025] Figure 3 is an exemplary flow chart of a pressure sore detection method based on a pressure sensor according to some embodiments of this specification;

[0026] Figure 4 is a schematic diagram of a multi-level pressure characteristic matrix according to some embodiments of this specification;

[0027] Figure 5 is a schematic diagram of a random forest model training process according to some embodiments of this specification;

[0028] Figure 6 It is an exemplary structural diagram of a pressure sore detection system based on a pressure sensor according to some embodiments of this specification. DETAILED DESCRIPTION

[0029] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0030] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0031] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0032] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0033] Figure 1 It is a schematic diagram of the framework of the wireless human body pressure acquisition system shown in some embodiments of this specification.

[0034] In some embodiments, the wireless human body pressure acquisition system is composed of a hardware part and a software part. Optionally, the main control chip uses the pressure acquisition module to obtain the pressure data of the pressure sensor, and sends the processed data to the wireless transmission module through a universal asynchronous receiver / transmitter (UART), and then wirelessly transmits the data to the host computer to realize data storage and dynamic display.

[0035] In some embodiments, the pressure sensor described in this embodiment can use a distributed flexible film pressure sensor to collect human body pressure data. The flexible film material can fit the human body curve well. The distributed design allows multiple pressure sensing units to be evenly distributed on the sensor, and each sensing unit can sense pressure independently with little interference, thereby achieving accurate positioning and feedback of the pressure state of the contact surface.

[0036] This type of sensor is also scalable, and its format and sensing point size can be adjusted according to specific needs to meet the needs of different application scenarios. The connection method is flexible and easy to integrate with various systems, which is convenient and flexible. This type of sensor has been widely used in the detection of sole, seat cushion and back force distribution.

[0037] Specifically, the hardware part of the wireless human body pressure acquisition system mainly includes a pressure acquisition module and a wireless transmission module.

[0038] Optionally, the pressure acquisition module is composed of two parts: a matrix switch module and a signal conversion module. Since the distributed pressure sensor adopts a matrix design and has multiple sensing units, considering the cost and the computing power of the main control chip, this embodiment designs a matrix switch module to control the on and off of the rows of distributed pressure sensors, so that all wires are energized in order to complete the scanning of the sensor. Then, the resistance signal is connected to the signal conversion module and converted into a voltage signal.

[0039] Optionally, the wireless transmission module wirelessly sends the real-time collected pressure data to the host computer for processing. Commonly used wireless transmission modules such as Zigbee, Lora and WIFI modules can be directly connected to the serial port of the main control chip to adapt to the flexibility and convenience of the application scenario.

[0040] In some embodiments, the software part of the wireless human body pressure acquisition system has the following system flow: after initializing the system configuration, the host computer sends a control instruction to the slave computer, the slave computer starts to collect and transmit pressure, and the host computer receives it and parses the rows and columns, stores it, and dynamically displays it through a thermal map.

[0041] Specifically, the main control chip scans the rows and columns of sensors through the pressure acquisition module, uses the ADC+DMA independent mode multi-channel acquisition method to read the voltage value of each sensor unit, and converts the pressure value through the formula. The main control chip adds a frame header and a frame footer to each frame of pressure data, and sends the data frame to the host computer through the wireless transmission module.

[0042] Furthermore, the host computer receives the pressure data and completes the data analysis, storage and display functions. According to the needs, you can choose a serial port screen, edge computing device or server as the host computer.

[0043] 1. Data analysis

[0044] The host computer uses the frame header and frame tail to parse the pressure data. The frame header: identifies the starting position of the data frame to ensure correct identification and start reading data; the frame tail: identifies the end position of the data frame to ensure that all data has been successfully transmitted. Through the above serial communication protocol, it can be ensured that data is not lost or damaged during transmission, improving the reliability and accuracy of communication.

[0045] 2. Data Storage

[0046] The parsed data can be saved in .txt, .csv or .json files for easy PI analysis.

[0047] 3. Data display

[0048] Figure 2 It is a schematic diagram of the thermal display of human body pressure collected by the pressure sensor according to some embodiments of this specification, using a thermal map to describe the pressure matrix, thereby displaying the pressure distribution. The thermal map uses a color gradient to indicate the high and low data values, gradually changing from cold colors (such as blue) to warm colors (such as red). High data value areas are displayed in warm colors, and low data value areas are displayed in cold colors. Among them, the vertical axis and horizontal axis of the thermal map describe the columns and rows of the pressure sensor respectively, and the color bar on the right is used to explain the relationship between the value and the color, and the unit is kg.

[0049] It should be understood that Figure 1The system and its modules shown can be implemented in various ways. It should be noted that the above description of the candidate display and determination system and its modules is only for the convenience of description and cannot limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. In some embodiments, Figure 1 The modules disclosed in the specification may be different modules in a system, or one module may realize the functions of two or more modules. For example, the modules may share a storage module, or each module may have its own storage module. Such variations are within the scope of protection of this specification.

[0050] Figure 3 is an exemplary flow chart of a pressure sore detection method based on a pressure sensor according to some embodiments of this specification. Figure 3 As shown, the process includes the following steps.

[0051] Step S310: collecting pressure data of the user's tested part through a pressure sensor.

[0052] In some embodiments, the pressure sensor can be a distributed flexible film pressure sensor, which can be bent in any shape and embedded in products such as seat cushions, backrests, and foot pads to obtain pressure data of different parts of the human body. Optionally, this embodiment will take a seat cushion as an example to describe how the pressure sensor obtains pressure data of a user's sitting posture.

[0053] Step S320: pre-process the collected pressure data to form a pressure matrix.

[0054] In some embodiments, preprocessing the collected pressure data to form a pressure matrix includes: the pressure sensor is composed of at least one collection unit, and the pressure value corresponding to each collection unit is obtained; based on the coordinate position of the collection unit, the pressure values ​​corresponding to the collection unit are formed into a matrix as the pressure matrix.

[0055] In some embodiments, the pressure sensor is composed of M×N pressure acquisition units, where M and N represent the number of rows and columns of the pressure sensor matrix, respectively. x,y (t) represents the pressure value of the sensor at the acquisition unit coordinate (x, y) at time t. The pressure value of a frame collected by the entire sensor at time t is represented by:

[0056] .

[0057] Step S330: extract at least one basic pressure characteristic value based on the pressure matrix.

[0058] In some embodiments, the basic pressure characteristic values ​​include a maximum pressure value, an average pressure value, a pressure intensity, and a contact area.

[0059] Specifically, the maximum pressure P m It refers to the maximum value among all test points, and the calculation formula is formula (2):

[0060] P m =max(P(t)) (2),

[0061] Among them, P m This reflects that the seat cushion in contact with the human body has a larger P m Value, from the perspective of human bone and muscle structure, P m Generally located on the bony prominences of the human body and parts that can bear the weight of the human body, such as the ischial tuberosity under the human body when sitting, these parts are also prone to pressure sores. m It is an important pressure indicator that reflects the stiffness of the seat cushion and the comfort of human sitting posture.

[0062] Average pressure P v It refers to the arithmetic mean of the pressure values ​​of all unit sensors, and the calculation formula is (3):

[0063]

[0064] Where Z is the number of acquisition units of the sensor. v It reflects the concentration trend of pressure. When the human body is in different sitting postures, the contact area between the body and the cushion is different. v There will also be differences in size. In addition, P v It is also related to the hardness of the cushion and the body shape. Generally speaking, the softer the cushion, the more dispersed the pressure. v The smaller the body, the larger the contact area, P v Also smaller.

[0065] The pressure intensity P refers to the sum of the pressure values ​​of all sensors, and the calculation formula (4) is as follows:

[0066]

[0067] The pressure intensity P reflects the characteristics of the cushion and the overall effect of the pressure on the human body. The larger the value, the greater the support for the human body.

[0068] The contact area S refers to the size of the area between the seat cushion and the human body, that is, the sum of the areas of all sensor points in contact with the human body. The calculation method is as shown in formula (5):

[0069]

[0070] Among them, Si refers to the area of ​​the sensor unit. S reflects the fit between the human body and the cushion. The closer the contact between the human body and the cushion, the larger the contact area. It is also related to the hardness of the cushion. The larger the contact area, the softer the cushion tends to be.

[0071] Step S340, calculating the eigenvalues ​​of any of the basic pressure eigenvalues ​​in the time domain, frequency domain and time-frequency domain, and constructing a multi-level pressure feature matrix.

[0072] In some embodiments, the calculation of the eigenvalues ​​of the basic pressure eigenvalues ​​in the time domain, frequency domain, and time-frequency domain to construct a multi-level pressure feature matrix includes: calculating the eigenvalues ​​of any of the basic pressure eigenvalues ​​in the time domain, frequency domain, and time-frequency domain, and sequentially forming a eigenvector; and forming the multi-level pressure feature matrix based on the eigenvectors calculated based on each of the basic pressure eigenvalues.

[0073] Optionally, the basic pressure characteristic values ​​all have time series information, and the characteristic values ​​of each feature in the time domain, frequency domain and time-frequency domain are calculated based on the basic pressure characteristic values.

[0074] Specifically, the maximum pressure value, the average pressure value, the pressure intensity and the contact area are respectively calculated by the following method to obtain their characteristic values ​​in the time domain, the frequency domain and the time-frequency domain.

[0075] First, select the root mean square RMS and variance Var in the time domain. The effective value represents the stability of the sitting posture, and the variance can measure the fluctuation of the sitting posture. The formulas are as follows (6) and (7):

[0076]

[0077]

[0078] Among them, x i Represents the i-th data in the signal, is the average of all data points and N is the number of data points in the signal.

[0079] Secondly, the discrete Fourier transform (DFT) is used in the frequency domain to perform spectrum analysis on the basic time series features, and the peak value and root mean square (RMS) are extracted as features. The peak value represents the maximum deviation of the sitting posture, and the root mean square reflects the overall stability of the sitting posture control. The methods are as follows:

[0080]

[0081] PSD k =|X[k]| 2 (9);

[0082] peak=max(PSD k ) (10);

[0083] Among them, X[k] is the signal spectrum obtained by DFT, PSD k is the power spectral density.

[0084] Finally, the Daubechies wavelet basis function is selected in the time-frequency domain to perform a three-layer wavelet decomposition on the basic features, and the average energy of each frequency band signal is calculated to obtain 8 energy feature parameters, which can characterize the distribution of sitting posture in different frequency domains. The method is shown in formula (11):

[0085]

[0086] Among them, E 3,i is the energy of the ith frequency node at level 3; S 3,i is the wavelet packet decomposition coefficient of the ith frequency band at level 3; x 3,i Represents S with length N 3,i The discrete waveform signal corresponding to the reconstruction of wavelet coefficients.

[0087] Furthermore, the effective value and variance are selected in the time domain as the first to second eigenvalues ​​(U1~U2) to construct the first part of the eigenvector; the peak value and root mean square are extracted from the frequency domain as the third to fourth eigenvalues ​​(U3~U4) to construct the second part of the eigenvector; the energy of each frequency band node after three-layer wavelet packet decomposition is selected in the time-frequency domain as the fifth to twelfth eigenvalues ​​(U5~U12) to construct the third part of the eigenvector; the eigenvector U composed of the above 12-dimensional eigenvalues ​​is shown in formula (12):

[0088] U=(U1,U2,…,U 12 ) T (12).

[0089] like Figure 4 As shown, a feature vector U is constructed based on each basic pressure feature, and then a multi-level pressure feature matrix with a dimension of 4 rows and 12 columns is constructed.

[0090] Step S350: input the multi-level pressure feature matrix into a pressure sore status detection model to obtain the user's pressure sore status.

[0091] In some embodiments, the pressure ulcer status detection model is obtained by training a random forest model. The machine forest algorithm (Random Forest, RF) is a multi-decision tree ensemble learning algorithm built based on the Bootstrap sampling idea, and its classification result is determined by voting of all decision trees in the forest. Due to its advantages such as low overfitting, strong generalization ability, and good robustness, the random forest model is widely used and popular in the field of personnel status detection and classification.

[0092] like Figure 5 As shown, the training process of the random forest model includes:

[0093] Acquire an original training data set, where the original training data set includes at least one training subset;

[0094] Build a decision tree based on a training subset, and repeat the construction multiple times to form a forest of multiple decision trees;

[0095] Calculate the running results of each decision tree and vote to get the prediction results;

[0096] The random forest model is trained and optimized based on the pressure sore samples in the original training data set to obtain the pressure sore status detection model.

[0097] In some embodiments, the data set is divided into a training set, a validation set, and a test set, where 80% of the data set is used as a training set to train the classification model; 10% of the data set is used as a validation set to dynamically adjust hyperparameters during the training process, and the validation set does not participate in the actual training of the model; 10% of the data set is used as a test set to evaluate the generalization ability of the model. In this study, pressure ulcer detection is set as a binary classification problem, in which pressure ulcer samples are assigned the label "1" and non-pressure ulcer samples are assigned the label "0", representing positive samples and negative samples, respectively.

[0098] Figure 6 600 is an exemplary structural diagram of a pressure sore detection system based on a pressure sensor according to some embodiments of this specification. The pressure sore detection system 600 includes:

[0099] The data acquisition module 610 is used to collect pressure data of the user's tested part through a pressure sensor;

[0100] A first data processing module 620 is used to pre-process the collected pressure data to form a pressure matrix;

[0101] A second data processing module 630, configured to extract at least one basic pressure characteristic value based on the pressure matrix;

[0102] The third data processing module 640 is used to calculate the characteristic values ​​of any of the basic pressure characteristic values ​​in the time domain, the frequency domain and the time-frequency domain, and construct a multi-level pressure characteristic matrix;

[0103] The state detection module 650 is used to input the multi-level pressure feature matrix into the pressure sore state detection model to obtain the user's pressure sore state.

[0104] The first data processing module 620 can also be used for the pressure sensor to be composed of at least one acquisition unit, to obtain the pressure value corresponding to each acquisition unit; based on the coordinate position of the acquisition unit, the pressure values ​​corresponding to the acquisition unit are formed into a matrix as the pressure matrix.

[0105] The third data processing module 640 can also be used to calculate the eigenvalues ​​of any of the basic pressure eigenvalues ​​in the time domain, frequency domain and time-frequency domain, and sequentially form a eigenvector; the eigenvector calculated based on each of the basic pressure eigenvalues ​​constitutes the multi-level pressure feature matrix.

[0106] The status detection module 650 can also be used to obtain an original training data set, which includes at least one training subset; construct a decision tree based on a training subset, and form a forest of multiple decision trees by repeating the construction multiple times; calculate the running results of each decision tree and vote to obtain a prediction result; train and optimize the random forest model based on the pressure sore samples in the original training data set, so as to obtain the pressure sore status detection model.

[0107] This embodiment also provides a pressure sore detection device based on a pressure sensor, including a processor, wherein the processor is used to execute a pressure sore detection method based on the pressure sensor.

[0108] This embodiment also provides a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a pressure sore detection method based on a pressure sensor.

[0109] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0110] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0111] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0112] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0113] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0114] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification are hereby incorporated by reference in their entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0115] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for detecting pressure sores based on a pressure sensor, characterized in that: include: Collect pressure data of the user's tested part through a pressure sensor; Preprocessing the collected pressure data to form a pressure matrix; Extracting at least one basic pressure characteristic value based on the pressure matrix; Calculate the eigenvalues ​​of any of the basic pressure eigenvalues ​​in the time domain, frequency domain and time-frequency domain, and construct a multi-level pressure feature matrix; The multi-level pressure feature matrix is ​​input into a pressure sore status detection model to obtain the user's pressure sore status.

2. The pressure sore detection method based on pressure sensor according to claim 1 is characterized in that: The pressure sensor is a distributed flexible film pressure sensor.

3. The pressure sore detection method based on pressure sensor according to claim 1 is characterized in that: The preprocessing of the collected pressure data to form a pressure matrix comprises: The pressure sensor is composed of at least one acquisition unit, and the pressure value corresponding to each acquisition unit is obtained; The pressure values ​​corresponding to the acquisition units are formed into a matrix based on the coordinate positions of the acquisition units, which serves as the pressure matrix.

4. The pressure sore detection method based on pressure sensor according to claim 1, characterized in that: The basic pressure characteristic values ​​include a maximum pressure value, an average pressure value, a pressure intensity and a contact area.

5. The pressure sore detection method based on pressure sensor according to claim 1, characterized in that: The calculating of the characteristic values ​​of the basic pressure characteristic values ​​in the time domain, the frequency domain and the time-frequency domain to construct a multi-level pressure characteristic matrix comprises: Calculate the characteristic values ​​of any of the basic pressure characteristic values ​​in the time domain, the frequency domain and the time-frequency domain, and sequentially form a characteristic vector; The multi-level pressure feature matrix is ​​constructed based on the feature vectors calculated based on each of the basic pressure feature values.

6. The pressure sore detection method based on pressure sensor according to claim 1, characterized in that: The pressure sore status detection model is obtained by training a random forest model, and the training process of the random forest model includes: Acquire an original training data set, where the original training data set includes at least one training subset; Build a decision tree based on a training subset, and repeat the construction multiple times to form a forest of multiple decision trees; Calculate the running results of each decision tree and vote to get the prediction results; The random forest model is trained and optimized based on the pressure sore samples in the original training data set to obtain the pressure sore status detection model.

7. A pressure sore detection system based on a pressure sensor, characterized in that: include: A data acquisition module, used to collect pressure data of the user's tested part through a pressure sensor; A first data processing module, used for preprocessing the collected pressure data to form a pressure matrix; A second data processing module, configured to extract at least one basic pressure characteristic value based on the pressure matrix; A third data processing module is used to calculate the characteristic values ​​of any of the basic pressure characteristic values ​​in the time domain, frequency domain and time-frequency domain, and construct a multi-level pressure characteristic matrix; The state detection module is used to input the multi-level pressure feature matrix into the pressure sore state detection model to obtain the user's pressure sore state.

8. A pressure sore detection device based on a pressure sensor, comprising a processor, wherein the processor is used to execute the pressure sore detection method based on a pressure sensor according to any one of claims 1 to 6.

9. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the pressure sore detection method based on a pressure sensor as described in any one of claims 1 to 6.

Images