A noise cancellation method and device, electronic equipment and storage medium

Abstract

The application provides a noise elimination method and device, electronic equipment and a computer readable storage medium. The method comprises: acquiring power parameter information, and receiving a diagnosis signal sent by a medical sensor; determining a filtering model according to the power parameter information; and performing filtering processing on the diagnosis signal through the filtering model, and outputting a filtered signal. When the method in the application is used to reduce the noise of the diagnosis signal, the emergency transport device does not need to be modified, and the cost is low. Meanwhile, in the above method, the established filtering model is used to reduce the noise of the diagnosis signal, the method does not introduce new noise signals, can achieve good noise reduction effect, fully ensures that an accurate diagnosis signal can be obtained after noise reduction processing, eliminates the interference of noise signals generated by the emergency transport device on medical diagnosis, and ensures the smooth progress of medical diagnosis.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a noise cancellation method, apparatus, electronic device, and computer-readable storage medium. Background Technology

[0002] Currently, when a patient experiences a sudden illness requiring immediate treatment, an ambulance is typically used to transport them to the hospital. During the journey, doctors usually conduct medical diagnoses within the ambulance's life support compartment. This involves using medical sensors such as stethoscopes to acquire diagnostic signals from the patient, which are then used to make a diagnosis. However, ambulances generate noise during operation, which can interfere with these diagnostic signals, causing distortion and disrupting the diagnostic process. More seriously, the presence of noise can prevent doctors from making a proper diagnosis.

[0003] In existing technologies, the following methods are commonly used for noise reduction:

[0004] (1) Use sound insulation materials to reduce noise;

[0005] (2) Use microphones or other sound-receiving devices to capture noise signals, and then generate a signal with the same magnitude but opposite direction as the noise signal to cancel the noise signal.

[0006] However, while the above method (1) can reduce noise to a small extent, its applicability is limited. Furthermore, the above method (1) requires modifications to the ambulance, resulting in higher costs.

[0007] In the above method (2), the newly generated signal is difficult to align with the noise signal in phase, which causes the newly generated signal to become a new noise signal mixed into the diagnostic signal, further aggravating the distortion of the diagnostic signal. Summary of the Invention

[0008] The purpose of this application is to provide a noise cancellation method, apparatus, electronic device, and computer-readable storage medium that can achieve better noise reduction effect.

[0009] On the one hand, this application provides a noise cancellation method applied to an emergency transport device, which includes a power unit that generates power parameter information during operation; the noise cancellation method includes:

[0010] It acquires power parameter information and receives diagnostic signals sent by medical sensors;

[0011] Based on the dynamic parameter information, determine the filtering model;

[0012] The diagnostic signal is filtered using a filtering model, and the filtered signal is output.

[0013] In one embodiment, determining the filtering model based on dynamic parameter information includes:

[0014] Based on the threshold range where the dynamic parameter information is located, obtain the filtering model associated with the threshold range.

[0015] In one embodiment, before obtaining the filtering model associated with the threshold range based on the threshold range where the dynamic parameter information is located, the method further includes:

[0016] Based on the sample information, a filtering model associated with each threshold interval is established; wherein, the sample information includes the reference signal, the sample diagnostic signal, and the sample noise signal generated when the power unit operates with the sample power parameter information located within each threshold interval.

[0017] In one embodiment, based on sample information, a filtering model associated with each threshold interval is established, including:

[0018] For each threshold interval, an initial filtering model is selected based on the sample noise signal corresponding to the threshold interval;

[0019] The sample diagnostic signal is input into the initial filtering model, and the parameters of the initial filtering model are adjusted according to the output signal of the initial filtering model until the difference between the output signal of the initial filtering model and the reference signal is less than the set threshold, thus obtaining the filtering model corresponding to the threshold interval.

[0020] In one embodiment, before establishing a filtering model associated with each threshold interval based on sample information, the method further includes:

[0021] Acquire reference signals, sample diagnostic signals, and sample noise data generated when the power unit operates with sample dynamic parameter information within each threshold interval;

[0022] Generate sample noise signals based on sample noise data.

[0023] In one embodiment, an initial filtering model is selected based on the sample noise signal corresponding to the threshold interval, including:

[0024] The initial filtering model is selected based on the frequency range of the sample noise signal.

[0025] In one embodiment, generating a sample noise signal based on sample noise data includes:

[0026] The power spectral density function is used to plot the sample noise data as a sample noise signal.

[0027] On the other hand, this application also provides a noise cancellation device mounted on an emergency transport device. The emergency transport device is equipped with a power unit that generates power parameter information during operation. The noise cancellation device includes an acquisition module, a determination module, and an output module. The acquisition module is used to acquire the power parameter information and receive diagnostic signals sent by medical sensors. The determination module is used to determine a filtering model based on the power parameter information. The output module is used to filter the diagnostic signals using the filtering model and output a filtered signal.

[0028] Furthermore, this application also provides an electronic device, which includes:

[0029] processor;

[0030] Memory used to store processor-executable instructions;

[0031] The processor is configured to execute the noise cancellation method described above.

[0032] In addition, this application also provides a computer-readable storage medium storing a computer program that can be executed by a processor to perform the above-described noise cancellation method.

[0033] This application provides a noise cancellation method. The method first acquires the power parameter information of the emergency transport device and the diagnostic signal sent by the medical sensor. After successful acquisition, a filtering model is determined based on the power parameter information. Then, the filtering model is used to filter the diagnostic signal and output the filtered signal.

[0034] Therefore, it can be seen that when using the method in this application to denoise diagnostic signals, no modification to the emergency transport device is required, resulting in lower costs. Furthermore, the method employs a pre-established filtering model to denoise the diagnostic signals without introducing new noise signals, achieving a good denoising effect and ensuring accurate diagnostic signals are obtained after denoising. This eliminates the interference of noise signals generated by the emergency transport device on medical diagnosis, guaranteeing the smooth progress of the medical diagnosis process. Attached Figure Description

[0035] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly described below.

[0036] Figure 1 This is a schematic diagram of the structure of a noise cancellation system provided in an embodiment of this application;

[0037] Figure 2 A schematic flowchart of a noise cancellation method provided in an embodiment of this application;

[0038] Figure 3 A schematic diagram of the process for establishing a filtering model provided in an embodiment of this application;

[0039] Figure 4 A schematic diagram of a sample noise signal provided in an embodiment of this application;

[0040] Figure 5 This is a schematic diagram of the structure of a noise cancellation device provided in an embodiment of this application;

[0041] Figure 6 This is a block diagram of a noise cancellation device provided in an embodiment of this application.

[0042] Figure label:

[0043] 1-Noise cancellation device; 10-Bus; 11-Processor; 12-Memory; 2-Data acquisition device; 3-Medical sensor; 5-Output device; 100-Noise cancellation device; 110-Acquisition module; 120-Determination module; 130-Output module; 200-Noise cancellation system. Detailed Implementation

[0044] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0045] Similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0046] Please refer to Figure 1 This is a schematic diagram of the structure of a noise cancellation system 200 provided in an embodiment of this application. Figure 1As shown, the noise cancellation system 200 of this application includes a noise cancellation device 1, a data acquisition device 2, a medical sensor 3, and an output device 5. The noise cancellation device 1 is connected to the data acquisition device 2, the medical sensor 3, and the output device 5. Specifically, the input terminal of the noise cancellation device 1 is connected to the output terminal of the data acquisition device 2 and the output terminal of the medical sensor 3; the output terminal of the noise cancellation device 1 is connected to the input terminal of the output device 5. The data acquisition device 2 is used to collect power parameter information of the emergency transport device and send the collected power parameter information to the noise cancellation device 1; the medical sensor 3 is used to collect diagnostic signals and send the diagnostic signals to the noise cancellation device 1. The noise cancellation device 1 is used to receive the power parameter information and the diagnostic signals, and determine a filtering model based on the power parameter information; the noise cancellation device 1 is also used to filter the diagnostic signals using the filtering model and send the filtered signal to the output device 5. The output device 5 is used to receive the filtered signal and output the filtered signal.

[0047] In this embodiment, the noise cancellation system 200 can be mounted in an emergency transport device used to transport patients to hospitals. For example, the emergency transport device can be an ambulance, etc. In one embodiment, the emergency transport device may include a life support cabin where doctors perform medical diagnoses on patients; in this case, the noise cancellation system 200 can be mounted in the life support cabin of the emergency transport device.

[0048] Please refer to Figure 2 This is a flowchart illustrating a noise cancellation method provided in an embodiment of this application. The method is applied to... Figure 1 The noise cancellation system 200 in the example. The method includes the following steps S210-S230.

[0049] Step S210: Obtain power parameter information and receive diagnostic signals sent by medical sensor 3.

[0050] The emergency transport device includes a power unit that generates power parameter information during operation. Specifically, the power unit may include a drive module that powers the emergency transport device, such as an engine, electric motor, or fuel injection unit. The power unit may also include other equipment operating within the emergency transport device, such as drive motors that power cooling equipment like fans and oxygen supply equipment. When the power unit is an engine, the power parameter information can be the engine's rotational speed; when it's an electric motor, the power parameter information can be the electric motor's rotational speed; and when it's a fuel injection unit, the power parameter information can be the fuel injection quantity. Medical sensor 3 is connected to the patient's end and is used by doctors to perform medical diagnoses on patients in the life support cabin. Specifically, medical sensor 3 may include an electronic stethoscope. When medical sensor 3 is an electronic stethoscope, the diagnostic signal can be a cardiopulmonary signal.

[0051] In this step, when the emergency transport device is activated, the noise cancellation device 1 begins acquiring the power parameter information generated by the power unit. Specifically, the acquisition method is as follows: the data acquisition device 2 connects to the OBD (OnBoard Diagnostics) interface of the emergency transport device, and the data acquisition device 2 acquires the power parameter information generated by the power unit through the OBD interface. After successful acquisition, the power parameter information is sent to the noise cancellation device 1. Simultaneously with acquiring the power parameter information, the noise cancellation device 1 also acquires the diagnostic signals for the patient sent by the medical sensor 3. Specifically, the medical sensor 3 acquires the diagnostic signals and sends them to the noise cancellation device 1. After both the power parameter information and the diagnostic signals are successfully acquired, the noise cancellation device 1 can proceed to the subsequent processes.

[0052] Step S220: Determine the filtering model based on the dynamic parameter information.

[0053] The filtering model is used to filter out noise signals in the diagnostic signal.

[0054] Emergency transport devices generate noise signals during operation, which can interfere with diagnostic signals, causing distortion and affecting doctors' medical diagnoses. Therefore, in this step, after acquiring the power parameter information generated by the power unit, the noise cancellation device 1 determines the corresponding filtering model based on this information. Specifically, the noise cancellation device 1 can store multiple filtering models. It can select the appropriate model based on the power parameter information, completing the filtering model determination process upon successful selection; afterwards, the noise cancellation device 1 can continue with subsequent procedures.

[0055] Step S230: Filter the diagnostic signal using a filtering model and output the filtered signal.

[0056] Among them, the filtered signal is the signal obtained after eliminating noise signals in the diagnostic signal, which can accurately represent the patient's current diagnostic data.

[0057] In this step, after selecting a filtering model based on the power parameter information, the noise cancellation device 1 can use the filtering model to filter the diagnostic signal, generating a filtered signal. After generating the filtered signal, the noise cancellation device 1 can send the filtered signal to the output device 5, which then outputs the filtered signal. The output device 5 is connected to the doctor's end, allowing the doctor to obtain the filtered signal and perform medical diagnosis on the patient. For example, the output device 5 can be a monitoring headset, etc.

[0058] Therefore, it can be seen that when using the method in this application to reduce noise in diagnostic signals, no modification to the emergency transport device is required, resulting in lower costs. Furthermore, the method employs a pre-established filtering model to process the diagnostic signals without introducing new noise signals, achieving good noise reduction results and ensuring accurate diagnostic signals after noise reduction. It also eliminates the interference of noise signals generated by the emergency transport device on medical diagnosis, enabling doctors to perform medical diagnoses even in noisy environments, thus guaranteeing the smooth progress of the medical diagnosis process.

[0059] In addition, since the power parameter information reflects the operation of the power unit, and the power unit is the main noise source of the emergency transport device, the corresponding filtering model is selected according to the power parameter information in this application, which can achieve accurate filtering of noise signals and greatly ensure the filtering effect.

[0060] In one embodiment, when the noise cancellation device 1 determines the filtering model based on the power parameter information, it can do so in the following way: based on the threshold range where the power parameter information is located, obtain the filtering model associated with the threshold range.

[0061] The threshold range refers to the standard numerical range corresponding to the power parameter information. Specifically, when the power parameter information is engine speed information, the threshold range can be the standard numerical range corresponding to the engine speed. When the power parameter information is electric motor speed information, the threshold range can be the standard numerical range corresponding to the electric motor speed. When the power parameter information is fuel injection quantity information of the fuel injection unit, the threshold range can be the standard numerical range corresponding to the fuel injection quantity.

[0062] In this embodiment, the noise cancellation device 1 stores multiple filtering models, each of which is associated with a corresponding threshold range. Specifically, each filtering model can be associated with multiple threshold ranges simultaneously; for example, the threshold range corresponding to the generator's rotational speed information is 1000 r / min to 1200 r / min, and the threshold range corresponding to the fuel injection quantity information of the fuel injection unit is 100 mm. 3 / H~120mm 3 In this embodiment, both threshold intervals can be associated with filter model A. Secondly, each filter model can be associated with only one threshold interval. For example, if the threshold interval corresponding to the motor speed information is 1200 r / min to 1400 r / min, then in this embodiment, this threshold interval can be associated with filter model B. Similarly, if the threshold interval corresponding to the engine speed information is 1600 r / min to 1800 r / min, then in this embodiment, this threshold interval can be associated with filter model C.

[0063] Furthermore, each filtering model can accurately filter out noise signals corresponding to its associated threshold range. Since the intensity of the noise signal corresponding to each threshold range is different, the filtering model can filter out noise signals of the corresponding intensity corresponding to its associated threshold range. For example, if the threshold range of 1200 r / min to 1400 r / min corresponding to the motor's speed information is associated with filtering model A, and the emergency transport device generates noise signals of corresponding intensity when the motor's speed information is within the aforementioned threshold range, then this noise signal corresponds to the noise signal within the threshold range of 1200 r / min to 1400 r / min associated with filtering model A; in this example, filtering model A can filter out this noise signal.

[0064] In this embodiment, after acquiring the power parameter information, the noise cancellation device 1 can further determine the threshold range in which the power parameter information falls, and then acquire a filtering model associated with the threshold range. For example, the noise cancellation device 1 stores a filtering model A associated with the threshold range of 1000 r / min to 1200 r / min corresponding to the engine speed information, and a filtering model B associated with the threshold range of 1200 r / min to 1400 r / min corresponding to the engine speed information. After acquiring the engine speed information, the noise cancellation device 1 determines that the engine speed information is within the threshold range of 1000 r / min to 1200 r / min. At this time, the noise cancellation device 1 selects filtering model A as the final filtering model and uses filtering model A to filter the diagnostic signal.

[0065] As can be seen from the above, this embodiment obtains a filtering model associated with the threshold range where the power parameter information is located, and then filters the diagnostic signal according to the filtering model. This achieves accurate filtering of noise signals of different intensities, greatly improves the noise reduction effect, and has strong compatibility.

[0066] In one embodiment, before performing the above steps, and obtaining the filtering model associated with the threshold interval based on the threshold interval where the dynamic parameter information is located, as follows: Figure 3 As shown, the following steps S310-S320 will be performed to establish a filtering model associated with each threshold interval.

[0067] Step S310: Obtain sample information.

[0068] The sample information includes a reference signal, a sample diagnostic signal, and a sample noise signal generated when the power unit operates with sample dynamic parameters within each threshold interval. The reference signal is a diagnostic signal completely free of noise. The sample diagnostic signal is a diagnostic signal mixed with noise, and the sample diagnostic signal has the same signal type as the reference signal. For example, both the reference signal and the sample diagnostic signal can be cardiopulmonary signals or both can be thoracic signals.

[0069] In this step, before building the filtering model associated with each threshold interval, it is first necessary to obtain sample information. The specific method for obtaining this information is as follows:

[0070] ① The method of obtaining the reference signal is as follows: the medical sensor 3 can obtain the reference signal when the emergency transport device is not activated, and after successful acquisition, the reference signal is sent to the noise cancellation device 1.

[0071] ② The method for acquiring sample noise signals is as follows: Multiple threshold intervals are automatically generated. Within each threshold interval, a set of sample dynamic parameter information is selected. Then, the power unit is controlled to operate according to the aforementioned sample dynamic parameter information. During operation, sample noise data generated by the power unit is acquired. Finally, a sample noise signal is generated based on the sample noise data. After successful generation, the sample noise signal corresponding to each threshold interval is obtained.

[0072] For example, the threshold range of 1000 r / min to 1200 r / min corresponding to the generation of engine speed information, and / or the threshold range of 100 mm corresponding to the generation of fuel injection quantity of the fuel injection unit. 3 / H~120mm 3 / H, within the above threshold range, select engine speed information of 1100 r / min, and / or, fuel injection quantity of 110 mm. 3The engine speed ( / H) is used as the sample power parameter information. The engine is then controlled to operate at the aforementioned speed, and the fuel injection unit is simultaneously controlled to inject fuel at the specified injection quantity. During operation, sample noise data generated by the engine and fuel injection unit is acquired. Finally, a sample noise signal is generated based on the sample noise data. The generated sample noise signal corresponds to the threshold range of 1000 r / min to 1200 r / min for the engine speed information, and / or the threshold range of 100 mm for the fuel injection quantity. 3 / H~120mm 3 / H is associated.

[0073] Specifically, the method for collecting sample noise signals is as follows: First, the emergency transport device is activated. After activation, the data acquisition device 2 collects the power parameter information of the power unit in real time through the OBD interface, and then sends the power parameter information to the noise cancellation device 1. The noise cancellation device 1 then determines whether the acquired power parameter information meets the aforementioned sample power parameter information. If the determination result indicates that the power parameter information does not meet the aforementioned sample power parameter information, the power parameter information is adjusted. If the determination result indicates that the power parameter information meets the sample power parameter information, no further adjustment is made, and the power unit continues to operate according to the aforementioned sample power parameter information. During operation, the data acquisition device 2 can collect sample noise data through a sound acquisition device. After successful acquisition, the sample noise data is sent to the noise cancellation device 1; after successful transmission, the process of acquiring sample noise data is completed. The life support cabin of the emergency transport device can be equipped with a microphone or other sound acquisition device, and the data acquisition device 2 is connected to the aforementioned sound acquisition device.

[0074] The method for generating sample noise signals based on sample noise data is as follows: the sample noise data is plotted into a sample noise signal using the power spectral density function described in formula (1) below. It is worth noting that the sample noise data mentioned in this article refers to the sample noise time-domain data, and the sample noise signal refers to the sample noise spectrum signal.

[0075]

[0076] Where f is the frequency, X T (f) is the Fourier transform result of the sample noise data within the time window T, and E represents the energy of the sample noise data. The energy of the sample noise data can be determined by the following formula (2).

[0077] E=∫|x(t)| 2 dt (2)

[0078] Where x(t) is the sample noise time-domain data within the time window T, and the integration interval is the time window T.

[0079] ③ The method for acquiring sample diagnostic signals is as follows: multiple threshold intervals are automatically generated. Within each threshold interval, a set of sample dynamic parameter information is selected. Then, the power unit is controlled to operate according to the aforementioned sample dynamic parameter information. During operation, the sample diagnostic signal is acquired through the medical sensor 3. After successful acquisition, the sample diagnostic signal is sent to the noise cancellation device 1. After successful transmission, the sample diagnostic signal corresponding to each threshold interval is obtained.

[0080] Once all sample information has been successfully acquired, the sample noise signal and sample diagnostic signal corresponding to each threshold interval are matched one-to-one.

[0081] In one embodiment, to ensure the accuracy of modeling, sample diagnostic signals and baseline signals can be collected from the same organism.

[0082] Step S320: Based on the sample information, establish a filtering model associated with each threshold interval.

[0083] In this step, after successfully acquiring the sample information, the noise cancellation device 1 can establish a filtering model associated with each threshold interval based on the sample information. Specifically, the noise cancellation device 1 can store multiple filtering models. For each threshold interval, the noise cancellation device 1 can select an initial filtering model based on the sample noise signal corresponding to each threshold interval. For example, the filtering models include, but are not limited to, Butterworth filtering models, Chebyshev filtering models, and Bessel filtering models.

[0084] In one embodiment, the noise cancellation device 1 can select an initial filtering model based on the frequency range of the sample noise signal corresponding to each threshold interval. Each filtering model corresponds to a frequency range of noise signals that it can cancel; therefore, the initial filtering model corresponding to each threshold interval can be selected based on the frequency range of the sample noise signal. For example, as shown... Figure 4 As shown, the frequency range of the sample noise signal corresponding to the threshold interval A is 2000~2600HZ. At this time, the Chebyshev filtering model described in the following formula (3) can be selected as the initial filtering model.

[0085]

[0086] Where ε is the stopband attenuation of the filtering model, and n is the order of the filtering model; ω c denoted as the cutoff frequency of the filtering model; z is the input signal; H(z) is the output signal after filtering the input signal.

[0087] While selecting the initial filtering model as described above, it is necessary to determine the initial values ​​of the corresponding parameters in the initial filtering model based on the frequency range of the sample noise signal corresponding to each threshold interval. For example, taking formula (3) as an example, it is necessary to determine the parameters ε, n, and ω. c The initial values ​​of ω are determined; where the initial values ​​of n and ε can be determined based on experience, with n typically being 6 and ε being 2 dB; when determining ω... c In this case, the starting frequency freq1 and ending frequency freq2 can be determined first based on the frequency range of the sample noise signal, and then the cutoff frequency ω can be determined based on the starting frequency freq1 and ending frequency freq2. c ;like Figure 4 As shown, the frequency range of the sample noise signal is 2000-2600Hz. At this time, the initial value of the starting frequency freq1 can be determined to be 2000Hz, and the initial value of the ending frequency freq2 can be determined to be 2600Hz.

[0088] By taking the above measures, the filtering model is selected according to the frequency range of the sample noise signal corresponding to each threshold interval, which fully ensures that the trained filtering model can filter out the sample noise signal of the corresponding frequency band of each threshold interval, thereby achieving accurate filtering of noise signals.

[0089] After the initial filtering model is selected, the noise cancellation device 1 can input the sample diagnostic signal corresponding to each threshold interval into the initial filtering model, and adjust the corresponding parameters in the initial filtering model according to the output signal of the initial filtering model until the difference between the output signal of the initial filtering model and the reference signal is less than the set threshold, thus obtaining the filtering model corresponding to each threshold interval.

[0090] Specifically, after inputting the sample diagnostic signal corresponding to each threshold interval into the initial filtering model, the initial filtering model will output a filtered signal. At this time, the noise cancellation device 1 can compare the filtered signal with the reference signal. It is determined whether the difference between the filtered signal and the reference signal is less than a set threshold. If the difference between the filtered signal and the reference signal is not less than the set threshold and is greater than the set threshold, the corresponding parameters of the initial filtering model are adjusted according to the preset adjustment method. Among them, when calculating the difference, the Euclidean distance between the filtered signal and the reference signal can be calculated by the following formula (4), and then the difference between the filtered signal and the reference signal can be determined by the Euclidean distance.

[0091]

[0092] Where d is the Euclidean distance between the reference signal and the filtered signal, x(i) is the time-domain data of the reference signal, y(i) is the time-domain data of the filtered signal, and i is time. The value of i determines the Euclidean distance between the filtered signal and the reference signal within which a preset time period is being calculated. For example, the value of i can be N1 to N2.

[0093] The preset adjustment method can be to decrease or increase the corresponding parameter within the corresponding adjustment range; for example, taking the above formula (3) as an example, when adjusting the parameter, n can be adjusted in the range of 6 to 20, ε can be adjusted in the range of 2dB to 10dB, the starting frequency freq1 can be adjusted in the range of 1750HZ to 2250HZ, and the ending frequency freq2 can be adjusted in the range of 2350HZ to 2850HZ.

[0094] After adjustment, an initial filtering model with adjusted parameters is obtained. The sample diagnostic signal is then input into this adjusted model. The difference between the filtered signal output by the adjusted model and the reference signal is then checked to see if it is less than a set threshold. If the difference is still not less than the set threshold, the parameters are adjusted again in the same way, iterating the filter parameters until the filtered signal output by the initial model gradually approaches the reference signal. When the difference between the filtered signal output by the initial model and the reference signal is less than the set threshold, the adjustment of the corresponding filter parameters is stopped, and the parameters are recorded. These recorded parameters are then input into the initial filtering model, resulting in the filtering model corresponding to each threshold interval. Upon successful acquisition, the noise cancellation device 1 stores the filtering model corresponding to each threshold interval for subsequent noise reduction processing of the diagnostic signal using the trained model.

[0095] Please refer to Figure 5 This is a schematic diagram of the structure of a noise cancellation device 1 provided in an embodiment of this application. Figure 5 As shown, the noise cancellation device 1 in this application includes at least one processor 11 and a memory 12. Figure 5 Taking a processor 11 as an example. The processor 11 and the memory 12 are connected via a bus 10. The memory 12 stores instructions that can be executed by the processor 11. The instructions are executed by the processor 11 to enable the noise cancellation device 1 to perform all or part of the process of the method in the above embodiments.

[0096] The memory 12 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0097] This application also provides a computer-readable storage medium storing a computer program that can be executed by a processor to perform the noise cancellation method provided in the above embodiments of this application.

[0098] Please refer to Figure 6 This is a block diagram of a noise cancellation device 100 provided in an embodiment of this application. Figure 6 As shown, the noise cancellation device 100 provided in this application includes an acquisition module 110, a determination module 120, and an output module 130. The purpose of each module is described in detail below. In this embodiment, the noise cancellation device 100 can be mounted in the noise cancellation equipment 1.

[0099] The acquisition module 110 is used to acquire power parameter information and receive diagnostic signals sent by the medical sensor 3.

[0100] The determination module 120 is used to determine the filtering model based on the dynamic parameter information.

[0101] Output module 130 is used to filter the diagnostic signal through a filtering model and output a filtered signal.

[0102] The specific implementation process of the functions and roles of each module in the above device is detailed in the implementation process of the corresponding steps mentioned above, and will not be repeated here.

[0103] The apparatuses and methods disclosed in the several embodiments provided in this application can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatuses, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0104] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0105] If a function is implemented as a software module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

Claims

1. A noise cancellation method, characterized by, The noise elimination method is applied to an emergency transport device, wherein a power unit is arranged in the emergency transport device, and power parameter information is generated during operation of the power unit; The noise elimination method comprises: acquiring the power parameter information and receiving a diagnosis signal sent by a medical sensor; determining a filter model according to the power parameter information; filtering the diagnosis signal through the filter model and outputting a filtered signal; The determination of the filter model according to the power parameter information comprises: acquiring a filter model associated with a threshold interval in which the power parameter information is located according to the threshold interval; Before the acquisition of the filter model associated with the threshold interval in which the power parameter information is located, the method further comprises: establishing a filter model associated with each threshold interval based on sample information, wherein the sample information comprises a reference signal, a sample diagnosis signal and a sample noise signal generated when the power unit operates with sample power parameter information located in each threshold interval.

2. The noise cancellation method of claim 1, wherein, The establishment of the filter model associated with each threshold interval based on the sample information comprises: for each threshold interval, selecting a filter initial model according to a sample noise signal corresponding to the threshold interval; inputting the sample diagnosis signal into the filter initial model and adjusting parameters of the filter initial model according to an output signal of the filter initial model until a difference between the output signal of the filter initial model and the reference signal is less than a set threshold, thereby obtaining a filter model corresponding to the threshold interval.

3. The noise cancellation method of claim 1, wherein, Before the establishment of the filter model associated with each threshold interval based on the sample information, the method further comprises: acquiring a reference signal, a sample diagnosis signal and sample noise data generated when the power unit operates with sample power parameter information located in each threshold interval; generating the sample noise signal based on the sample noise data.

4. The noise cancellation method of claim 2, wherein, The selection of the filter initial model according to the sample noise signal comprises: selecting the filter initial model according to a frequency range of the sample noise signal.

5. The noise cancellation method of claim 3, wherein, The generation of the sample noise signal based on the sample noise data comprises: drawing the sample noise data into the sample noise signal by using a power spectral density function.

6. A noise cancellation apparatus, characterized by, The noise elimination device is arranged in an emergency transport device, wherein a power unit is arranged in the emergency transport device, and power parameter information is generated during operation of the power unit; The noise elimination device comprises: an acquisition module, configured to acquire the power parameter information and receive a diagnosis signal sent by a medical sensor; a determination module, configured to determine a filter model according to the power parameter information; an output module, configured to filter the diagnosis signal through the filter model and output a filtered signal; The determination module is further configured to: Based on sample information, a filter model associated with each threshold interval is established; wherein the sample information includes a reference signal, a sample diagnostic signal, and a sample noise signal generated when the power unit operates with sample power parameter information located in each threshold interval; According to the threshold interval where the power parameter information is located, the filter model associated with the threshold interval is obtained.

7. An electronic device, comprising: The electronic device includes: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to perform the noise cancellation method of any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which can be executed by the processor to complete the noise cancellation method of any one of claims 1-5.

Images