A respiratory monitoring method and system based on RFID

Abstract

The present invention provides a respiratory monitoring method and system based on RFID, including an RFID scanning reader that sends a read signal to multiple RFID-based strain sensors attached to the abdomen and belly of a user according to a preset frequency and obtains the response information of the RFID, and determines the frequency shift, phase and RSSI according to the response signal; determines the first distance according to the frequency shift-strain distance correspondence relationship of the strain sensor and the frequency shift, fits multiple first distances into a smooth distance curve, fits multiple phases into a smooth phase curve, and fits multiple RSSIs into a smooth RSSI curve; determines the user's respiratory condition according to the distance curve, the phase curve and the RSSI curve. The present invention improves the accuracy of respiratory monitoring, and has the characteristics of comfortable wearing compared to setting sensors in the nostrils.

Description

Technical Field

[0001] The present invention relates to the field of respiratory monitoring, and in particular to a respiratory monitoring method and system based on RFID. Background Art

[0002] Respiratory monitoring is an important part of the medical and health field. It is mainly used to check parameters such as respiratory rate, respiratory rhythm, and respiratory depth. It can be used to diagnose and treat various diseases, such as asthma, COPD (chronic obstructive pulmonary disease), sleep apnea, etc. Common respiratory monitoring methods include doctors or nurses evaluating respiratory conditions by observing and listening to the patient's breathing, pulse oxygen saturation monitoring, monitoring through a sensor array set on the nose, and monitoring using wearable devices and smart homes.

[0003] The above-mentioned methods of respiratory monitoring are either inaccurate or not comfortable to wear. Using RFID for respiratory monitoring can effectively overcome the above problems. The main principle is that when a person breathes, the movement of the chest will cause the position of the RFID tag to change, which will change the distance between the tag and the reader. The distance change is detected by the reader. By collecting and analyzing the changes in this signal, the frequency and depth of breathing can be calculated. However, RFID tags are affected by many factors, such as the relative position of the tag and the reader, metal objects, electromagnetic interference from the surrounding environment, etc., which will affect the accuracy of monitoring. How to use RFID tags to accurately monitor breathing conditions is an urgent problem to be solved. Summary of the invention

[0004] In order to solve the above problems, in a first aspect, the present invention provides a respiratory monitoring method based on RFID, the method comprising the following steps:

[0005] The RFID scanning reader sends a read signal to a plurality of RFID-based strain sensors attached to the abdomen and tummy of the user according to a preset frequency and obtains RFID response information, and determines the frequency shift, phase and RSSI according to the response signal, wherein the RFID scanning reader is located at a preset distance from the user;

[0006] Determine a first distance according to the frequency shift-strain distance correspondence relationship of the strain sensor and the frequency shift, fit multiple first distances into a smooth distance curve, fit multiple phases into a smooth phase curve, and fit multiple RSSIs into a smooth RSSI curve;

[0007] The user's breathing condition is determined according to the distance curve, the phase curve and the RSSI curve.

[0008] Preferably, the RFID scanning reader sends a read signal to a plurality of RFID-based strain sensors attached to the abdomen and tummy of the user according to a preset frequency and obtains RFID response information, and determines the frequency shift, phase and RSSI according to the response signal, specifically:

[0009] A frame-based time slot ALOHA method is used as an anti-collision method between the RFID scanning reader and the RFID-based strain sensor. The number of time slots in a frame is set to be the same as the number of the RFID-based strain sensor. When the RFID scanning reader and the RFID-based strain sensor initially communicate, the RFID scanning reader determines whether a collision exists. If so, the determination continues in the next frame until there is no collision in the frame, and the time slot number of the information sent by itself is recorded in the strain sensor.

[0010] Acquire the number of preset frequencies, establish a correspondence between preset frequencies and frames in a cycle according to the order of preset frequencies from large to small, determine the preset frequency for each frame according to the correspondence, send read information to the strain sensor, and receive information returned by the strain sensor; the cycle includes the same number of frames as the number of preset frequencies, and each frame includes a number of time slots corresponding to the number of strain sensors;

[0011] Calculate the difference between the preset frequency corresponding to the maximum energy of each strain sensor obtained by the RFID scanning reader and the default frequency in each cycle, and use the difference as the frequency shift; obtain the phase and RSSI of each strain sensor in the cycle according to the response information in each cycle.

[0012] Preferably, the acquiring the phase and RSSI of each strain sensor in each cycle according to the response information is specifically as follows:

[0013] The phase and RSSI of each strain sensor in each frame within the cycle are obtained. After preprocessing, the average phase and average RSSI of each strain sensor within the cycle are determined according to the phase and the RSSI as the phase and RSSI of each strain sensor respectively; a first distance, a phase, and an RSSI are obtained in each cycle.

[0014] Preferably, determining the user's breathing condition according to the distance curve, the phase curve and the RSSI curve is specifically:

[0015] Taking one of the distance curve, the phase curve or the RSSI curve as a reference, moving the other two curves so that the distance between the three curves is the shortest, and the moving distance does not exceed half of the period; the period includes the same number of frames as the number of the preset frequencies, and each frame includes a number of time slots corresponding to the number of the strain sensors;

[0016] The three curves are superimposed according to their corresponding weights to obtain a breathing curve, and the breathing situation is determined according to the distance between the breathing curves of the multiple strain sensors and the preset curve.

[0017] Preferably, determining the user's breathing condition according to the distance curve, the phase curve and the RSSI curve is specifically:

[0018] For each strain sensor, each of the distance curve, the phase curve and the RSSI curve is divided into a plurality of segments according to a period to form a segment sequence corresponding to the curve;

[0019] For each curve of each strain sensor, the segment sequence of the curve is divided into multiple windows in a sliding window manner, each segment in the window is sampled to obtain the embedding of the segment, and the embedding of the segment and the position embedding of the segment are added to obtain a one-dimensional vector of the curve in the window, and the one-dimensional vectors of three curves of multiple strain sensors in the same window are spliced ​​to obtain a two-dimensional vector, and the two-dimensional vector is used as the input of the ViT model to obtain the classification result, and the breathing condition is determined based on the classification results of multiple sliding windows.

[0020] In another aspect, the present invention provides a respiratory monitoring system based on RFID, the system comprising the following modules:

[0021] An information acquisition module, for an RFID scanning reader to send a read signal to a plurality of RFID-based strain sensors attached to the abdomen and tummy of a user according to a preset frequency and acquire RFID response information, and to determine a frequency shift, a phase and RSSI according to the response signal, wherein the RFID scanning reader is located at a preset distance from the user;

[0022] A data processing module, used for determining the first distance according to the frequency shift-strain distance correspondence relationship of the strain sensor and the frequency shift, fitting multiple first distances into a smooth distance curve, fitting multiple phases into a smooth phase curve, and fitting multiple RSSIs into a smooth RSSI curve;

[0023] The breathing condition recognition module is used to determine the user's breathing condition according to the distance curve, the phase curve and the RSSI curve.

[0024] Preferably, the RFID scanning reader sends a read signal to a plurality of RFID-based strain sensors attached to the abdomen and tummy of the user according to a preset frequency and obtains RFID response information, and determines the frequency shift, phase and RSSI according to the response signal, specifically:

[0025] A frame-based time slot ALOHA method is used as an anti-collision method between the RFID scanning reader and the RFID-based strain sensor. The number of time slots in a frame is set to be the same as the number of the RFID-based strain sensor. When the RFID scanning reader and the RFID-based strain sensor initially communicate, the RFID scanning reader determines whether a collision exists. If so, the determination continues in the next frame until there is no collision in the frame, and the time slot number of the information sent by itself is recorded in the strain sensor.

[0026] Acquire the number of preset frequencies, establish a correspondence between preset frequencies and frames in a cycle according to the order of preset frequencies from large to small, determine the preset frequency for each frame according to the correspondence, send read information to the strain sensor, and receive information returned by the strain sensor; the cycle includes the same number of frames as the number of preset frequencies, and each frame includes a number of time slots corresponding to the number of strain sensors;

[0027] Calculate the difference between the preset frequency corresponding to the maximum energy of each strain sensor obtained by the RFID scanning reader and the default frequency in each cycle, and use the difference as the frequency shift; obtain the phase and RSSI of each strain sensor in the cycle according to the response information in each cycle.

[0028] Preferably, the acquiring the phase and RSSI of each strain sensor in each cycle according to the response information is specifically as follows:

[0029] The phase and RSSI of each strain sensor in each frame within the cycle are obtained. After preprocessing, the average phase and average RSSI of each strain sensor within the cycle are determined according to the phase and the RSSI as the phase and RSSI of each strain sensor respectively; a first distance, a phase, and an RSSI are obtained in each cycle.

[0030] Preferably, determining the user's breathing condition according to the distance curve, the phase curve and the RSSI curve is specifically:

[0031] Taking one of the distance curve, the phase curve or the RSSI curve as a reference, moving the other two curves so that the distance between the three curves is the shortest, and the moving distance does not exceed half of the period; the period includes the same number of frames as the number of the preset frequencies, and each frame includes a number of time slots corresponding to the number of the strain sensors;

[0032] The three curves are superimposed according to their corresponding weights to obtain a breathing curve, and the breathing situation is determined according to the distance between the breathing curves of the multiple strain sensors and the preset curve.

[0033] Preferably, determining the user's breathing condition according to the distance curve, the phase curve and the RSSI curve is specifically:

[0034] For each strain sensor, each of the distance curve, the phase curve and the RSSI curve is divided into a plurality of segments according to a period to form a segment sequence corresponding to the curve;

[0035] For each curve of each strain sensor, the segment sequence of the curve is divided into multiple windows in a sliding window manner, each segment in the window is sampled to obtain the embedding of the segment, and the embedding of the segment and the position embedding of the segment are added to obtain a one-dimensional vector of the curve in the window, and the one-dimensional vectors of three curves of multiple strain sensors in the same window are spliced ​​to obtain a two-dimensional vector, and the two-dimensional vector is used as the input of the ViT model to obtain the classification result, and the breathing condition is determined based on the classification results of multiple sliding windows.

[0036] Finally, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method described above when executed by a processor.

[0037] The present invention utilizes an RFID scanning reader and a plurality of RFID-based strain sensors to obtain a plurality of parameters, can accurately monitor the user's breathing, and has the advantages of being easy to use and having very little discomfort to the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 This is a flow chart of Embodiment 1;

[0040] Figure 2 It is a relationship diagram of cycle, frame and time slot;

[0041] Figure 3 This is a structural diagram of the second embodiment. DETAILED DESCRIPTION

[0042] In this article, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Embodiment 1

[0045] The present invention provides a respiratory monitoring method based on RFID, such as Figure 1 As shown, the method comprises the following steps:

[0046] S1, an RFID scanning reader sends a read signal to a plurality of RFID-based strain sensors attached to the abdomen and tummy of a user according to a preset frequency and obtains RFID response information, and determines a frequency shift, a phase and RSSI according to the response signal, wherein the RFID scanning reader is located at a preset distance from the user;

[0047] RFID readers can read the contents of RFID tags, but their frequency is fixed. Unlike RFID readers, RFID scanning readers can emit multiple frequencies to read RFID tags. The frequencies emitted by RFID scanning readers can be pre-set. For example, if the scanning interval is 1kHz, a request to read RFID tags can be issued at 120kHz, and the next read request will be issued at 121kHz.

[0048] The RFID-based strain sensor uses the antenna of the RFID tag as an element for inducing strain force. When tension or bending occurs, the resistance, reactance, etc. of the RFID tag antenna change, thereby causing the data read by the RFID reader to change. The antenna uses a strain gauge or a resistance sensing fiber, etc. In the present invention, multiple frequencies are used to read the RFID-based strain sensor, and the stress of the RFID tag is determined according to the frequency shift. The stress is caused by the user's breathing, and the breathing is monitored through frequency shift, phase and RSSI. Frequency shift refers to the situation where the default frequency of the RFID-based strain sensor changes due to stress. Different stresses cause different degrees of deformation of the RFID antenna, and thus different frequency shifts.

[0049] S2, determining a first distance according to the frequency shift-strain distance correspondence relationship of the strain sensor and the frequency shift, fitting multiple first distances into a smooth distance curve, fitting multiple phases into a smooth phase curve, and fitting multiple RSSIs into a smooth RSSI curve;

[0050] When other conditions remain unchanged, the resistance and impedance of the antenna change due to stress, resulting in a change in the resonant frequency of the antenna. When the frequency emitted by the RFID scanning reader is the same as the resonant frequency, the greater the RFID tag reflection power obtained by the RFID scanning reader, the resonant frequency can be obtained by continuously changing the frequency emitted by the RFID scanning reader, and then the stress or movement distance can be obtained. According to the correspondence between the frequency shift and strain distance of the strain sensor and the frequency shift, the movement distance of the strain sensor antenna caused by the user's abdominal or tummy movement can be determined to achieve breathing monitoring. There are different ways to fit discrete points, such as using the Python SciPy library.

[0051] S3, determining the user's breathing condition according to the distance curve, the phase curve and the RSSI curve.

[0052] In a specific embodiment, the RFID scanning reader sends a read signal to a plurality of RFID-based strain sensors attached to the abdomen and stomach of the user according to a preset frequency and obtains RFID response information, and determines the frequency shift, phase and RSSI according to the response signal, specifically:

[0053] A frame-based time slot ALOHA method is used as an anti-collision method between the RFID scanning reader and the RFID-based strain sensor. The number of time slots in a frame is set to be the same as the number of the RFID-based strain sensor. When the RFID scanning reader and the RFID-based strain sensor initially communicate, the RFID scanning reader determines whether a collision exists. If so, the determination continues in the next frame until there is no collision in the frame, and the time slot number of the information sent by itself is recorded in the strain sensor.

[0054] Acquire the number of preset frequencies, establish a correspondence between preset frequencies and frames in a cycle according to the order of preset frequencies from large to small, determine the preset frequency for each frame according to the correspondence, send read information to the strain sensor, and receive information returned by the strain sensor; the cycle includes the same number of frames as the number of preset frequencies, and each frame includes a number of time slots corresponding to the number of strain sensors;

[0055] Calculate the difference between the preset frequency corresponding to the maximum energy of each strain sensor obtained by the RFID scanning reader and the default frequency in each cycle, and use the difference as the frequency shift; obtain the phase and RSSI of each strain sensor in the cycle according to the response information in each cycle.

[0056] The relationship between cycle, frame and time slot is as follows Figure 2 As shown, a cycle includes multiple frames, each frame corresponds to a frequency that can be emitted by the RFID scanning reader, and the number of pre-set RFID scanning frequencies is equal to the number of frames in the cycle; a frame includes multiple time slots, and the number of time slots is the same as the number of RFID-based stress sensors.

[0057] In one cycle, the RFID scanning reader completes one scanning cycle and determines the frequency shift. Since the time slot is very short, usually in the millisecond or microsecond level, the movement distance of the stomach or abdomen in one cycle can be ignored.

[0058] In one cycle, each frame will obtain the RSSI and phase of each strain sensor. In a specific embodiment, the phase and RSSI of each strain sensor in the cycle are obtained according to the response information in each cycle, specifically:

[0059] The phase and RSSI of each strain sensor in each frame within the cycle are obtained. After preprocessing, the average phase and average RSSI of each strain sensor within the cycle are determined according to the phase and RSSI as the phase and RSSI of each strain sensor respectively; a first distance, a phase, and an RSSI are obtained in each cycle. The preprocessing method includes but is not limited to removing abnormal values. Figure 2For example, the scanning frequency reader obtains three RSSIs and phases of the strain sensor in cycle 1. After preprocessing, the three RSSIs are averaged and the three phases are averaged to obtain the phase and RSSI of strain sensor 1 in cycle 1.

[0060] In one embodiment, determining the user's breathing condition according to the distance curve, the phase curve, and the RSSI curve is specifically as follows:

[0061] Taking one of the distance curve, the phase curve or the RSSI curve as a reference, the other two curves are moved so that the distance between the three curves is the shortest; the cycle includes the same number of frames as the number of the preset frequencies, and each frame includes a number of time slots corresponding to the number of the strain sensors; in a more specific embodiment, the moving distance does not exceed half of the cycle.

[0062] The three curves are superimposed according to their corresponding weights to obtain a breathing curve, and the breathing situation is determined according to the distance between the breathing curves of the multiple strain sensors and the preset curve.

[0063] For example, if there are four strain sensors, if the four strain sensors best match the preset curve of normal breathing, it is determined that the breathing is normal. If three of them best match the preset curve of apnea, it is determined that there is apnea.

[0064] In another embodiment, determining the user's breathing condition according to the distance curve, the phase curve, and the RSSI curve is specifically:

[0065] For each strain sensor, each of the distance curve, the phase curve and the RSSI curve is divided into a plurality of segments according to a period to form a segment sequence corresponding to the curve;

[0066] For each curve of each strain sensor, the curve segment sequence is divided into multiple windows in a sliding window manner, each segment in the window is sampled to obtain the segment Embedding, and the segment Embedding and the segment position embedding are added to obtain a one-dimensional vector of the curve in the window, and the three curves of multiple strain sensors in the same window are spliced ​​to obtain a two-dimensional vector. The two-dimensional vector is used as the input of the ViT model to obtain the classification result, and the breathing condition is determined based on the classification results of multiple sliding windows.

[0067] A strain sensor has three curves. Each curve of each strain sensor is segmented to obtain three fragment sequences of each strain sensor. Then, each fragment sequence is divided into multiple window sequences according to the sliding window. One period corresponds to one sequence. The sliding window corresponds to multiple periods, that is, multiple sequences. The curve of each period is sampled, and the continuous values ​​are sampled into a discrete sequence. The sequence is used as the feature of the period, that is, the fragment is embedded. The window is larger than the period. In a typical example, a window contains 10 periods, and the number of data sampled in each period is 10. Then, in a sliding window, there are 100 data. As the feature of the sliding window, each of the three curves has 100 data. The one-dimensional vector of the first curve of strain sensor 1 is used as the first row of data of the two-dimensional vector, the one-dimensional vector of the second curve of strain sensor 1 is used as the second row of data of the two-dimensional vector, the one-dimensional vector of the third curve of strain sensor 1 is used as the third row of data of the two-dimensional vector, and the one-dimensional vector of the first curve of strain sensor 2 is used as the fourth row of data of the two-dimensional vector. And so on, a spliced ​​two-dimensional vector is obtained, where the number of rows of the two-dimensional vector is 3n, where n is the number of strain sensors. The ViT model is a Transformer-based network model and will not be described in detail.

[0068] Embodiment 2

[0069] The present invention provides a respiratory monitoring system 100 based on RFID, such as Figure 3 As shown, the system includes the following modules:

[0070] The information acquisition module 101 is used for an RFID scanning reader to send a read signal to a plurality of RFID-based strain sensors attached to the abdomen and tummy of a user according to a preset frequency and obtain RFID response information, and to determine a frequency shift, a phase and RSSI according to the response signal, wherein the RFID scanning reader is located at a preset distance from the user;

[0071] The data processing module 102 is used to determine the first distance according to the frequency shift-strain distance correspondence relationship of the strain sensor and the frequency shift, fit multiple first distances into a smooth distance curve, fit multiple phases into a smooth phase curve, and fit multiple RSSIs into a smooth RSSI curve;

[0072] The breathing condition recognition module 103 is used to determine the user's breathing condition according to the distance curve, the phase curve and the RSSI curve.

[0073] Preferably, the RFID scanning reader sends a read signal to a plurality of RFID-based strain sensors attached to the abdomen and tummy of the user according to a preset frequency and obtains RFID response information, and determines the frequency shift, phase and RSSI according to the response signal, specifically:

[0074] A frame-based time slot ALOHA method is used as an anti-collision method between the RFID scanning reader and the RFID-based strain sensor. The number of time slots in a frame is set to be the same as the number of the RFID-based strain sensor. When the RFID scanning reader and the RFID-based strain sensor initially communicate, the RFID scanning reader determines whether a collision exists. If so, the determination continues in the next frame until there is no collision in the frame, and the time slot number of the information sent by itself is recorded in the strain sensor.

[0075] Acquire the number of preset frequencies, establish a correspondence between preset frequencies and frames in a cycle according to the order of preset frequencies from large to small, determine the preset frequency for each frame according to the correspondence, send read information to the strain sensor, and receive information returned by the strain sensor; the cycle includes the same number of frames as the number of preset frequencies, and each frame includes a number of time slots corresponding to the number of strain sensors;

[0076] Calculate the difference between the preset frequency corresponding to the maximum energy of each strain sensor obtained by the RFID scanning reader and the default frequency in each cycle, and use the difference as the frequency shift; obtain the phase and RSSI of each strain sensor in the cycle according to the response information in each cycle.

[0077] Preferably, the acquiring the phase and RSSI of each strain sensor in each cycle according to the response information is specifically as follows:

[0078] The phase and RSSI of each strain sensor in each frame within the cycle are obtained. After preprocessing, the average phase and average RSSI of each strain sensor within the cycle are determined according to the phase and the RSSI as the phase and RSSI of each strain sensor respectively; a first distance, a phase, and an RSSI are obtained in each cycle.

[0079] Preferably, determining the user's breathing condition according to the distance curve, the phase curve and the RSSI curve is specifically:

[0080] Taking one of the distance curve, the phase curve or the RSSI curve as a reference, moving the other two curves so that the distance between the three curves is the shortest, and the moving distance does not exceed half of the period; the period includes the same number of frames as the number of the preset frequencies, and each frame includes a number of time slots corresponding to the number of the strain sensors;

[0081] The three curves are superimposed according to their corresponding weights to obtain a breathing curve, and the breathing situation is determined according to the distance between the breathing curves of the multiple strain sensors and the preset curve.

[0082] Preferably, determining the user's breathing condition according to the distance curve, the phase curve and the RSSI curve is specifically:

[0083] For each strain sensor, each of the distance curve, the phase curve and the RSSI curve is divided into a plurality of segments according to a period to form a segment sequence corresponding to the curve;

[0084] For each curve of each strain sensor, the curve segment sequence is divided into multiple windows in a sliding window manner, each segment in the window is sampled to obtain the segment Embedding, and the segment Embedding and the segment position embedding are added to obtain a one-dimensional vector of the curve in the window, and the three curves of multiple strain sensors in the same window are spliced ​​to obtain a two-dimensional vector. The two-dimensional vector is used as the input of the ViT model to obtain the classification result, and the breathing condition is determined based on the classification results of multiple sliding windows.

[0085] Embodiment 3

[0086] The present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in the first embodiment is implemented.

[0087] Embodiment 4

[0088] The present invention further provides a computer device, which includes a processor and a memory. The memory stores a computer program, and when the computer program is executed by the processor, the method described in the first embodiment is implemented.

[0089] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course can also be implemented by combining hardware and software. Based on such an understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a computer product, and the present invention can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A respiratory monitoring method based on RFID, characterized in that: The method comprises the following steps: The RFID scanning reader sends a read signal to a plurality of RFID-based strain sensors attached to the abdomen and tummy of the user according to a preset frequency and obtains RFID response information, and determines the frequency shift, phase and RSSI according to the response information, wherein the RFID scanning reader is located at a preset distance from the user; Determine a first distance according to the frequency shift-strain distance correspondence relationship of the strain sensor and the frequency shift, fit multiple first distances into a smooth distance curve, fit multiple phases into a smooth phase curve, and fit multiple RSSIs into a smooth RSSI curve; Determine the user's breathing condition according to the distance curve, the phase curve and the RSSI curve; The determining of the user's breathing condition according to the distance curve, the phase curve and the RSSI curve is specifically as follows: Taking one of the distance curve, the phase curve or the RSSI curve as a reference, moving the other two curves so that the distance between the three curves is the shortest, and the moving distance does not exceed half of the period; the period includes the same number of frames as the number of the preset frequencies, and each frame includes a number of time slots corresponding to the number of the strain sensors; The three curves are superimposed according to their corresponding weights to obtain a breathing curve, and the breathing situation is determined according to the distance between the breathing curves of the multiple strain sensors and the preset curve.

2. The method according to claim 1, characterized in that The RFID scanning reader sends a read signal to a plurality of RFID-based strain sensors attached to the abdomen and stomach of the user according to a preset frequency and obtains the response information of the RFID, and determines the frequency shift, phase and RSSI according to the response information, specifically: A frame-based time slot ALOHA method is used as an anti-collision method between the RFID scanning reader and the RFID-based strain sensor. The number of time slots in a frame is set to be the same as the number of the RFID-based strain sensor. When the RFID scanning reader and the RFID-based strain sensor initially communicate, the RFID scanning reader determines whether a collision exists. If so, the determination continues in the next frame until there is no collision in the frame, and the time slot number of the information sent by itself is recorded in the strain sensor. Acquire the number of preset frequencies, establish a correspondence between preset frequencies and frames in a cycle according to the order of preset frequencies from large to small, determine the preset frequency for each frame according to the correspondence, send read information to the strain sensor, and receive information returned by the strain sensor; the cycle includes the same number of frames as the number of preset frequencies, and each frame includes a number of time slots corresponding to the number of strain sensors; Calculate the difference between a preset frequency corresponding to the maximum energy of each strain sensor acquired by the RFID scanning frequency reader and a default frequency in each cycle, and use the difference as a frequency shift; In each cycle, the phase and RSSI of each strain sensor in the cycle are acquired according to the response information.

3. The method according to claim 2, characterized in that The phase and RSSI of each strain sensor in each cycle are obtained according to the response information, specifically: The phase and RSSI of each strain sensor in each frame within the cycle are obtained. After preprocessing, the average phase and average RSSI of each strain sensor within the cycle are determined according to the phase and the RSSI as the phase and RSSI of each strain sensor respectively; a first distance, a phase, and an RSSI are obtained in each cycle.

4. The method according to any one of claims 1 to 3, characterized in that: The determining of the user's breathing condition according to the distance curve, the phase curve and the RSSI curve is specifically as follows: For each strain sensor, each of the distance curve, the phase curve and the RSSI curve is divided into a plurality of segments according to a period to form a segment sequence corresponding to the curve; For each curve of each strain sensor, the curve segment sequence is divided into multiple windows in a sliding window manner, each segment in the window is sampled to obtain the segment Embedding, and the segment Embedding and the segment position embedding are added to obtain a one-dimensional vector of the curve in the window, and the three curves of multiple strain sensors in the same window are spliced ​​to obtain a two-dimensional vector. The two-dimensional vector is used as the input of the ViT model to obtain the classification result, and the breathing condition is determined based on the classification results of multiple sliding windows.

5. A respiratory monitoring system based on RFID, characterized in that: The system includes the following modules: An information acquisition module, for an RFID scanning reader to send a read signal to a plurality of RFID-based strain sensors attached to the abdomen and tummy of a user according to a preset frequency and acquire RFID response information, and to determine a frequency shift, a phase and RSSI according to the response information, wherein the RFID scanning reader is located at a preset distance from the user; A data processing module, used for determining the first distance according to the frequency shift-strain distance correspondence relationship of the strain sensor and the frequency shift, fitting multiple first distances into a smooth distance curve, fitting multiple phases into a smooth phase curve, and fitting multiple RSSIs into a smooth RSSI curve; A breathing condition identification module, used to determine the user's breathing condition based on the distance curve, the phase curve and the RSSI curve; The determining of the user's breathing condition according to the distance curve, the phase curve and the RSSI curve is specifically as follows: Taking one of the distance curve, the phase curve or the RSSI curve as a reference, moving the other two curves so that the distance between the three curves is the shortest, and the moving distance does not exceed half of the period; the period includes the same number of frames as the number of the preset frequencies, and each frame includes a number of time slots corresponding to the number of the strain sensors; The three curves are superimposed according to their corresponding weights to obtain a breathing curve, and the breathing situation is determined according to the distance between the breathing curves of the multiple strain sensors and the preset curve.

6. The system according to claim 5, characterized in that The RFID scanning reader sends a read signal to a plurality of RFID-based strain sensors attached to the abdomen and stomach of the user according to a preset frequency and obtains the response information of the RFID, and determines the frequency shift, phase and RSSI according to the response information, specifically: A frame-based time slot ALOHA method is used as an anti-collision method between the RFID scanning reader and the RFID-based strain sensor. The number of time slots in a frame is set to be the same as the number of the RFID-based strain sensor. When the RFID scanning reader and the RFID-based strain sensor initially communicate, the RFID scanning reader determines whether a collision exists. If so, the determination continues in the next frame until there is no collision in the frame, and the time slot number of the information sent by itself is recorded in the strain sensor. Acquire the number of preset frequencies, establish a correspondence between preset frequencies and frames in a cycle according to the order of preset frequencies from large to small, determine the preset frequency for each frame according to the correspondence, send read information to the strain sensor, and receive information returned by the strain sensor; the cycle includes the same number of frames as the number of preset frequencies, and each frame includes a number of time slots corresponding to the number of strain sensors; Calculate the difference between a preset frequency corresponding to the maximum energy of each strain sensor acquired by the RFID scanning frequency reader and a default frequency in each cycle, and use the difference as a frequency shift; In each cycle, the phase and RSSI of each strain sensor in the cycle are acquired according to the response information.

7. The system according to claim 6, characterized in that The phase and RSSI of each strain sensor in each cycle are obtained according to the response information, specifically: The phase and RSSI of each strain sensor in each frame within the cycle are obtained. After preprocessing, the average phase and average RSSI of each strain sensor within the cycle are determined according to the phase and the RSSI as the phase and RSSI of each strain sensor respectively; a first distance, a phase, and an RSSI are obtained in each cycle.

8. The system according to any one of claims 5 to 7, characterized in that: The determining of the user's breathing condition according to the distance curve, the phase curve and the RSSI curve is specifically as follows: For each strain sensor, each of the distance curve, the phase curve and the RSSI curve is divided into a plurality of segments according to a period to form a segment sequence corresponding to the curve; For each curve of each strain sensor, the curve segment sequence is divided into multiple windows in a sliding window manner, each segment in the window is sampled to obtain the segment Embedding, and the segment Embedding and the segment position embedding are added to obtain a one-dimensional vector of the curve in the window, and the three curves of multiple strain sensors in the same window are spliced ​​to obtain a two-dimensional vector. The two-dimensional vector is used as the input of the ViT model to obtain the classification result, and the breathing condition is determined based on the classification results of multiple sliding windows.

Images