Signal detection position detection method, device and computer equipment

Abstract

This application relates to a method, apparatus, computer device, storage medium, and computer program product for detecting signal detection locations. The method includes: detecting the current detection location using an ultrasound physiological signal meter probe to acquire a corresponding sound signal to be tested at the current detection location; performing digital signal processing on the sound signal to obtain its two-dimensional audio features; inputting the two-dimensional audio features of the sound signal to a trained sound signal classification model, outputting probability values ​​for classifying the sound signal into various preset sound signal types, and determining the signal type of the sound signal based on the probability values; if the signal type is a target signal type, determining the current detection location as the target detection location, and pushing a correct prompt message indicating that the current detection location is the target detection location. This method can assist the detector in finding the correct detection location, thereby effectively improving the reliability of signal detection.

Description

Technical Field

[0001] The present application relates to the field of signal detection technology, and in particular to a method, device, computer equipment, storage medium and computer program product for detecting a signal detection position. Background Art

[0002] With the continuous development of ultrasound technology, ultrasound-based signal detection technology has become more and more mature. At present, ultrasound-based signal detection technology has been widely used in medical diagnosis, such as detecting physiological and pathological information of the human body through ultrasound physiological signal meters, namely ultrasound diagnosis.

[0003] The ultrasonic diagnosis method generally uses an ultrasonic physiological signal meter probe to transmit ultrasonic signals to specific parts of the human body, and then displays the ultrasonic signals reflected back from specific parts of the human body through a display screen. Based on the waveform, attenuation and other information of the reflected wave, the physiological conditions of the invisible areas below the human skin are determined, such as the activity functions of certain organs inside the human body, whether there is gas or liquid in the tissues and organs, etc.

[0004] Ultrasound-based physiological signal detection has the advantages of being painless, non-destructive, safe, convenient, real-time imaging, and clear imaging, so it has become an indispensable diagnostic method in clinical medicine. However, in traditional ultrasonic physiological signal detection, the detector often relies on experience or senses to determine the position of the ultrasonic physiological signal meter probe. When the detector is inexperienced, it is difficult to find the accurate detection position. At the same time, the detection results are easily disturbed by external noise, and there is a defect that the signal detection is not reliable enough. Summary of the invention

[0005] Based on this, it is necessary to provide a signal detection position detection method, device, computer equipment, computer-readable storage medium and computer program product that can improve the reliability of signal detection in response to the above technical problems.

[0006] In a first aspect, the present application provides a method for detecting a signal detection position. The detection method comprises:

[0007] The current detection position is detected by using an ultrasonic physiological signal meter probe to obtain a sound signal to be detected corresponding to the current detection position;

[0008] Performing digital signal processing on the sound signal to be tested to obtain two-dimensional audio features of the sound signal to be tested;

[0009] Inputting the two-dimensional audio features of the sound signal to be tested into the trained sound signal classification model, outputting the probability value of the sound signal to be tested being classified into each preset sound signal type, and determining the signal type of the sound signal to be tested according to the probability value;

[0010] When the signal type is the target signal type, the current detection position is determined to be the target detection position, and a correct prompt message indicating that the current detection position is the target detection position is pushed.

[0011] In one embodiment, the training process of the sound signal classification model includes:

[0012] Acquire multiple types of sample noise signals and sample ultrasonic signals reflected from the target detection position, and determine the corresponding sample labels of the sample noise signals and the sample ultrasonic signals according to the signal types to which they belong;

[0013] Obtaining two-dimensional audio features corresponding to the sample noise signal and the sample ultrasonic signal, taking the two-dimensional audio features with the sample labels as a sample data set, and dividing the sample data set into a training data set and a test data set;

[0014] Input the two-dimensional audio features in the training data set into the sound signal classification model, and update the parameters of the sound signal classification model according to the difference between the predicted label output by the sound signal classification model and the sample label;

[0015] The test data set is used to verify and evaluate the sound signal classification model to obtain the trained sound signal classification model.

[0016] In one embodiment, detecting the current detection position by using an ultrasonic physiological signal meter probe to obtain a sound signal to be detected corresponding to the current detection position includes:

[0017] Sending an ultrasonic signal to the current detection position through the ultrasonic physiological signal meter probe;

[0018] The sound signal reflected from the current detection position is received, and the reflected sound signal is used as the sound signal to be measured.

[0019] In one embodiment, performing digital signal processing on the sound signal to be tested to obtain the two-dimensional audio features of the sound signal to be tested includes:

[0020] Sampling, quantizing and encoding the sound signal to be tested to obtain the corresponding digital signal;

[0021] Audio feature extraction is performed on the digital signal to obtain the two-dimensional audio features of the sound signal to be tested.

[0022] In one embodiment, after determining the signal type of the sound signal to be tested according to the probability value, the method further includes:

[0023] When the signal type is not the target signal type, determining that the current detection position is not the target detection position, and pushing an error prompt message indicating that the current detection position is not the target detection position;

[0024] Repeat the process of moving the ultrasonic physiological signal meter probe to the detection position until the sound signal type corresponding to the moved detection position is the target signal type, determine that the corresponding moved detection position is the target detection position, and push a correct prompt message indicating that the corresponding moved detection position is the target detection position.

[0025] In one embodiment, the sound signal classification model is a convolutional neural network model; the sound signal classification model includes, in sequence, an input layer, a plurality of combination layers consisting of two-dimensional convolutional layers and maximum pooling layers, a flattening layer, a plurality of combination layers consisting of fully connected layers and random inactivation layers, a fully connected layer, and an output layer.

[0026] In a second aspect, the present application also provides a detection device for a signal detection position. The detection device comprises:

[0027] A signal acquisition module is used to detect the current detection position through an ultrasonic physiological signal meter probe and obtain a sound signal to be measured corresponding to the current detection position;

[0028] A signal processing module is used to perform digital signal processing on the sound signal to be tested to obtain two-dimensional audio features of the sound signal to be tested;

[0029] A signal classification module, used to input the two-dimensional audio features of the sound signal to be tested into the trained sound signal classification model, output the probability value of the sound signal to be tested being classified into each preset sound signal type, and determine the signal type of the sound signal to be tested according to the probability value;

[0030] The message push module is used to determine that the current detection position is the target detection position when the signal type is the target signal type, and push a correct prompt message indicating that the current detection position is the target detection position.

[0031] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0032] The current detection position is detected by using an ultrasonic physiological signal meter probe to obtain a sound signal to be detected corresponding to the current detection position;

[0033] Performing digital signal processing on the sound signal to be tested to obtain two-dimensional audio features of the sound signal to be tested;

[0034] Inputting the two-dimensional audio features of the sound signal to be tested into the trained sound signal classification model, outputting the probability value of the sound signal to be tested being classified into each preset sound signal type, and determining the signal type of the sound signal to be tested according to the probability value;

[0035] When the signal type is the target signal type, the current detection position is determined to be the target detection position, and a correct prompt message indicating that the current detection position is the target detection position is pushed.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0037] The current detection position is detected by using an ultrasonic physiological signal meter probe to obtain a sound signal to be detected corresponding to the current detection position;

[0038] Performing digital signal processing on the sound signal to be tested to obtain two-dimensional audio features of the sound signal to be tested;

[0039] Inputting the two-dimensional audio features of the sound signal to be tested into the trained sound signal classification model, outputting the probability value of the sound signal to be tested being classified into each preset sound signal type, and determining the signal type of the sound signal to be tested according to the probability value;

[0040] When the signal type is the target signal type, the current detection position is determined to be the target detection position, and a correct prompt message indicating that the current detection position is the target detection position is pushed.

[0041] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0042] The current detection position is detected by using an ultrasonic physiological signal meter probe to obtain a sound signal to be detected corresponding to the current detection position;

[0043] Performing digital signal processing on the sound signal to be tested to obtain two-dimensional audio features of the sound signal to be tested;

[0044] Inputting the two-dimensional audio features of the sound signal to be tested into the trained sound signal classification model, outputting the probability value of the sound signal to be tested being classified into each preset sound signal type, and determining the signal type of the sound signal to be tested according to the probability value;

[0045] When the signal type is the target signal type, the current detection position is determined to be the target detection position, and a correct prompt message indicating that the current detection position is the target detection position is pushed.

[0046] The detection method, device, computer equipment, storage medium and computer program product of the signal detection position described above detect the current detection position through the ultrasonic physiological signal meter probe to obtain the sound signal to be detected corresponding to the current detection position; perform digital signal processing on the sound signal to be detected to obtain the two-dimensional audio features of the sound signal to be detected; input the two-dimensional audio features of the sound signal to be detected into the trained sound signal classification model, output the probability value of the sound signal to be detected being classified as each preset sound signal type, and determine the signal type of the sound signal to be detected according to the probability value; when the signal type is the target signal type, determine the current detection position as the target detection position, and push a correct prompt message indicating that the current detection position is the target detection position. The entire signal detection position detection process, by inputting the two-dimensional audio features of the sound signal to be detected into the sound signal classification model, obtains the signal type of the sound signal to be detected, determines the current detection position as the target detection position according to the signal type, and pushes a prompt message indicating the correct detection position accordingly, thereby assisting the detector to find the correct detection position, and effectively improving the reliability of signal detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A diagram showing an application environment of a method for detecting a signal detection position in an embodiment;

[0048] Figure 2 Schematic diagram of a flow chart of a method for detecting a signal detection position in one embodiment;

[0049] Figure 3 A schematic diagram of a process for training a sound signal classification model in one embodiment;

[0050] Figure 4 A schematic diagram of a flow chart of performing measurement in combination with the classification result of a sound signal classification model in one embodiment;

[0051] Figure 5 is a structural diagram of a sound signal classification model in one embodiment;

[0052] Figure 6 is a flow chart of a method for detecting a signal detection position in another embodiment;

[0053] Figure 7 is a structural block diagram of a detection device for signal detection position in one embodiment;

[0054] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] The signal detection position detection method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The user operates on the terminal 102 side, and the terminal 102 responds to the user operation to detect the signal detection position.

[0057] Specifically, the terminal 102 detects the current detection position through the ultrasonic physiological signal meter probe to obtain the sound signal to be tested corresponding to the current detection position; performs digital signal processing on the sound signal to be tested to obtain the two-dimensional audio features of the sound signal to be tested; inputs the two-dimensional audio features of the sound signal to be tested into the trained sound signal classification model, outputs the probability value of the sound signal to be tested being classified as each preset sound signal type, and determines the signal type of the sound signal to be tested according to the probability value; when the signal type is the target signal type, determines that the current detection position is the target detection position, and pushes a correct prompt message indicating that the current detection position is the target detection position. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices, and the Internet of Things devices can be Internet of Things smart oscilloscopes, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0058] In one embodiment, Figure 2 As shown, a method for detecting a signal detection position is provided, and the detection method is applied to Figure 1 The terminal 102 in the example is used as an example to illustrate, and the following steps are included:

[0059] S100: Detecting the current detection position through an ultrasonic physiological signal meter probe to obtain a sound signal to be detected corresponding to the current detection position.

[0060] The current detection position refers to the part of the human body that is currently being detected, such as the abdomen, face, brain, etc.; the sound signal to be detected refers to the sound signal reflected back from the current detection position.

[0061] Optionally, a specific ultrasonic signal is emitted to the currently detected part of the human body (abdomen, face, brain, etc.) through the ultrasonic physiological signal meter probe, and a sound signal returned by the currently detected part of the human body is received, and the reflected sound signal is used as the sound signal to be tested.

[0062] S200: Perform digital signal processing on the sound signal to be tested to obtain two-dimensional audio features of the sound signal to be tested.

[0063] The sound signal to be tested is an ultrasonic continuous signal in analog form.

[0064] Optionally, the returned analog ultrasonic continuous signal is converted into a digital ultrasonic discrete signal through an analog-to-digital converter (ADC), and finally the digital ultrasonic discrete signal is transmitted to a smart device terminal such as a mobile phone. The smart device terminal such as the mobile phone performs spectrum analysis, Mel Frequency Cepstrum Coefficient (MFCC) and other sound wave signal processing on the digital ultrasonic discrete signal to obtain the two-dimensional audio characteristics of the sound signal to be tested.

[0065] S300: Inputting the two-dimensional audio features of the sound signal to be tested into the trained sound signal classification model, outputting the probability value of the sound signal to be tested being classified into each preset sound signal type, and determining the signal type of the sound signal to be tested according to the probability value.

[0066] Among them, the sound signal classification model is a convolutional neural network model; the number of each preset sound signal type can be set according to actual conditions. For example, the preset sound signal type can be set to a friction noise type, a background noise type, and a target signal type returned by the target detection position.

[0067] Optionally, the two-dimensional audio features of the sound signal to be tested are input into a pre-trained convolutional neural network model, and the probability value of the sound signal to be tested being classified as each preset sound signal type is output. Among them, the range of the output probability value is [0,1] and the sum of the output probability values ​​is 1, and the preset sound signal type corresponding to the maximum probability value is used as the signal type of the sound signal to be tested. Taking the predicted sound signal type as a friction noise type, a background noise type, and a target signal type as an example, assuming that the probability value of the sound signal to be tested being classified as a friction noise type is 0.2, the probability value of being classified as a background noise type is 0.1, and the probability value of being classified as a target signal type is 0.7, then the target signal type corresponding to the highest probability value is used as the signal type of the sound signal to be tested.

[0068] S400: When the signal type is a target signal type, determining that the current detection position is a target detection position, and pushing a correct prompt message indicating that the current detection position is the target detection position.

[0069] Optionally, when the sound signal type to be tested output by the sound signal classification model is the target signal type, the current detection position is determined to be the target detection position, and a correct prompt message indicating that the current detection position is the target detection position is displayed on a smart terminal device such as a mobile phone. The smart terminal device can specifically provide a prompt message that the current detection position is correct by means of sound and light (voice prompt, indicator light) or display (picture display, text display). For example, two indicator lights, red and green, can be provided on the terminal device. When the green light is on, it indicates that the current detection position is correct. When the current detection position is the target detection position, the green light on the terminal device is on, and "The current detection position is correct! Please start measuring" is displayed.

[0070] In the above-mentioned signal detection position detection method, the current detection position is detected by an ultrasonic physiological signal meter probe to obtain the sound signal to be detected corresponding to the current detection position; the sound signal to be detected is digitally processed to obtain the two-dimensional audio features of the sound signal to be detected; the two-dimensional audio features of the sound signal to be detected are input into the trained sound signal classification model, and the probability value of the sound signal to be detected being classified into each preset sound signal type is output, and the signal type of the sound signal to be detected is determined according to the probability value; when the signal type is the target signal type, the current detection position is determined to be the target detection position, and a correct prompt message indicating that the current detection position is the target detection position is pushed. The entire signal detection position detection process, by inputting the two-dimensional audio features of the sound signal to be detected into the sound signal classification model, obtaining the signal type of the sound signal to be detected, determining the current detection position as the target detection position according to the signal type, and pushing a prompt message indicating the correct detection position accordingly, thereby assisting the detector to find the correct detection position, can effectively improve the reliability of signal detection.

[0071] In one embodiment, Figure 3 As shown in FIG. 1 , the training process of the sound signal classification model includes:

[0072] S210: Acquire multiple types of sample noise signals and sample ultrasonic signals reflected from the target detection position, and determine corresponding sample labels of the sample noise signals and the sample ultrasonic signals according to their respective signal types;

[0073] S220: Obtain two-dimensional audio features corresponding to the sample noise signal and the sample ultrasonic signal, use the two-dimensional audio features with sample labels as a sample data set, and divide the sample data set into a training data set and a test data set;

[0074] S230: inputting the two-dimensional audio features in the training data set into the sound signal classification model, and updating the parameters of the sound signal classification model according to the difference between the predicted label output by the sound signal classification model and the sample label;

[0075] S240: Using the test data set to verify and evaluate the sound signal classification model to obtain a trained sound signal classification model.

[0076] First, according to the actual situation, various noises that may be generated during the signal detection process, such as background noise, friction noise, etc., and sample ultrasonic signals reflected from the target detection position are obtained. According to the signal types to which the various sample noise signals and sample ultrasonic signals belong, their corresponding sample labels are determined. Then, digital signal processing is performed on the sound signal marked with the sample label, and the obtained sound signal is converted into a two-dimensional audio feature. The two-dimensional audio feature with the sample label is used as a sample data set, and the sample data set is randomly divided into a training data set and a test data set according to a preset ratio.

[0077] The two-dimensional audio features in the training data set are input into the sound signal classification model, the loss function value is calculated using the difference between the model output value and the sample label, and the loss function value is applied to update the parameters of the sound signal classification model, thereby training the sound signal classification model; the test data set is imported into the sound signal classification model after the parameter update, and the sound signal classification model is verified and evaluated. After the verification and evaluation pass, the trained sound signal classification model is obtained.

[0078] In this embodiment, multiple types of sample noise signals and sample ultrasonic signals reflected based on the target detection position are obtained, and the sample labels and two-dimensional audio features corresponding to each of the acquired sound signals are determined. The two-dimensional audio features with the sample labels are used as a sample data set, and the sample data set is randomly divided into a training data set and a test data set, so as to obtain a trained sound signal classification model for subsequent determination of the type of sound signal to be tested, thereby improving the reliability of signal detection.

[0079] In one embodiment, the current detection position is detected by using an ultrasonic physiological signal meter probe to obtain a sound signal to be detected corresponding to the current detection position, including:

[0080] Sending an ultrasonic signal to the current detection position through the ultrasonic physiological signal meter probe;

[0081] The sound signal reflected from the current detection position is received, and the reflected sound signal is used as the sound signal to be measured.

[0082] Generally speaking, the specific detection method of an ultrasonic physiological signal meter is to use a probe that emits ultrasonic signals to emit ultrasonic signals to the area below the human skin, and then receive the reflected sound signals to determine the shape and characteristics of the invisible area below the human skin for various medical purposes. However, the specific detection angle, position, moving distance, etc. of the ultrasonic physiological signal meter probe often need to rely on the experience of the tester. When the tester is inexperienced, the received echo signal (reflected sound signal) is easily disturbed by the friction noise generated by the mobile device and other background noise, making the detected signal waveform difficult to distinguish.

[0083] Based on the signal detection position detection method provided in this embodiment, when using an ultrasonic physiological signal meter for signal detection, the reflected sound signal does not need to be directly analyzed and displayed. Instead, the reflected sound signal is used as the sound signal to be tested, and the type of the sound signal to be tested is determined by a sound signal classification model. When the type of the sound signal to be tested is the target signal type, a prompt message indicating that the current detection position is correct is pushed, thereby assisting the tester in finding the correct detection position.

[0084] In this embodiment, after receiving the sound signal reflected from the current detection position, the reflected sound signal is used as the sound signal to be tested, and the signal type of the sound signal to be tested is determined based on the sound signal classification model. When the current detection position is the target detection position, the corresponding current detection position prompt message is pushed, which can assist inexperienced detectors to find the correct detection position, thereby improving the efficiency and reliability of signal detection.

[0085] In one embodiment, performing digital signal processing on the sound signal to be tested to obtain the two-dimensional audio features of the sound signal to be tested includes:

[0086] Sampling, quantizing and encoding the sound signal to be tested to obtain the corresponding digital signal;

[0087] Audio feature extraction is performed on the digital signal to obtain the two-dimensional audio features of the sound signal to be tested.

[0088] For the received sound signal to be tested, the returned analog ultrasonic continuous signal is first sampled, quantized and encoded through the ADC to convert it into a digital ultrasonic discrete signal. The digital ultrasonic discrete signal is then transmitted to smart device terminals such as mobile phones. The smart device terminal performs spectrum analysis, MFCC feature extraction and other sound wave signal processing on the digital ultrasonic discrete signal to obtain the two-dimensional spectrum characteristics of the sound signal to be tested.

[0089] In this embodiment, digital signal processing is performed on the received analog ultrasonic continuous signal. First, the ultrasonic discrete signal in digital form is obtained through ADC conversion and transmitted to a smart device terminal such as a mobile phone. Then, the digital ultrasonic discrete signal is further subjected to spectrum analysis, MFCC feature extraction and other processing through the smart device terminal to obtain the two-dimensional spectrum characteristics of the sound signal to be tested, thereby improving the accuracy of signal detection.

[0090] In one embodiment, after determining the signal type of the sound signal to be tested according to the probability value, the method further includes:

[0091] When the signal type is not the target signal type, determining that the current detection position is not the target detection position, and pushing an error prompt message indicating that the current detection position is not the target detection position;

[0092] Repeat the process of moving the ultrasonic physiological signal meter probe to the detection position until the sound signal type corresponding to the moved detection position is the target signal type, determine that the corresponding moved detection position is the target detection position, and push a correct prompt message indicating that the corresponding moved detection position is the target detection position.

[0093] When the sound signal type to be tested output by the sound signal classification model is not the target signal type, it is determined that the current detection position is not the target detection position, and an error prompt message that the current detection position is not the target detection position is displayed on a smart terminal device such as a mobile phone. The smart terminal device can specifically provide a prompt message that the current detection position is correct by means of sound and light (voice prompt, indicator light) or display (picture display, text display). For example, two red and green indicator lights can be set on the smart terminal device. When the red light is on, it indicates that the current detection position is wrong, and when the green light is on, it indicates that the current detection position is correct. When the current detection position is not the target detection position, the red light on the terminal device is on, and it is displayed "The current detection position is wrong! Please try to move the probe to another position". After repeatedly moving the detection position of the ultrasonic physiological signal meter probe until the sound signal type corresponding to the detection position after the movement is the target signal type, the detection position after the movement is determined to be the target detection position, and at the same time, the smart device terminal pushes a correct prompt message indicating that the corresponding detection position after the movement is the target detection position, for example, the green light on the terminal device is on, and it is displayed "The current detection position is correct! Please start measuring".

[0094] See also Figure 4In practical applications, after obtaining the sound signal to be measured corresponding to the current detection position, the classification result of the sound signal classification model and the waveform of the sound signal to be measured observed by the human eye can be combined to determine whether the current detection position is the target detection position. When the current detection position is the target detection position, the detector can start measurement based on the current detection position; when the current detection position is not the target detection position, the detector can continuously move the position of the ultrasonic physiological signal meter probe until the sound signal type returned by the moved detection position is the target signal type and the waveform of the sound signal to be measured observed by the human eye is the target signal waveform, and then start measurement based on the correct position after the movement.

[0095] In this embodiment, when the signal type output by the sound signal classification model is not the target signal type, an error prompt message is pushed to indicate that the current detection position is not the target detection position, prompting the detector to try to move the probe to other positions; when the sound signal type returned by the moved detection position is the target signal type, the smart device terminal pushes a correct prompt message indicating that the current detection position is the target detection position, to assist the detector to measure at the correct detection position, effectively improving the reliability of signal detection.

[0096] In one embodiment, the sound signal classification model is a convolutional neural network model; the sound signal classification model includes, in sequence, an input layer, multiple groups of combination layers consisting of two-dimensional convolutional layers and maximum pooling layers, a flattening layer, multiple groups of combination layers consisting of fully connected layers and random inactivation layers, a fully connected layer, and an output layer.

[0097] See also Figure 5 The sound signal classification model consists of an input layer, n groups of combination layers consisting of two-dimensional convolutional layers and maximum pooling layers, a flattening layer, n groups of combination layers consisting of fully connected layers and random dropout layers, a fully connected layer, and an input layer. The activation function used by the sound signal model can be ReLU, Sigmoid, tanh, softmax and other activation functions. For example, the softmax function can be used to process the output value of the fully connected layer and convert the output value into a probability value. Among them, the range of the output probability value is [0,1] and the sum of the output probability values ​​is 1. The sound signal classification model uses the preset sound signal type corresponding to the maximum probability value as the signal type of the sound signal to be tested.

[0098] In this embodiment, a convolutional neural network model consisting of an input layer, n groups of combined layers consisting of a two-dimensional convolutional layer and a maximum pooling layer, a flattening layer, n groups of combined layers consisting of a fully connected layer and a random inactivation layer, a fully connected layer, and an input layer is set as a sound signal classification model. By constructing a convolutional neural network model, the input two-dimensional audio features are analyzed and processed to obtain the signal type of the sound signal to be tested, so as to assist the detector in finding the correct detection position, thereby effectively improving the reliability of signal detection.

[0099] In order to explain the technical solution of the detection method of the signal detection position of the present application in detail, the following will use a specific application example and combine Figure 6 The whole processing process is described, which specifically includes the following steps:

[0100] 1. Use the ultrasonic physiological signal meter probe to detect the current detection position and obtain the corresponding sound signal to be measured at the current detection position. Specifically including:

[0101] a) The ultrasonic physiological signal meter probe transmits a specific ultrasonic signal to the currently detected part of the human body (abdomen, face, brain, etc.).

[0102] b) receiving the sound signal returned by the currently detected human body part, and using the reflected sound signal as the sound signal to be measured.

[0103] 2. Perform digital signal processing on the reflected sound signal to be tested to obtain the two-dimensional audio features of the sound signal to be tested. Specifically including:

[0104] a) The reflected analog sound signal to be tested is sampled, quantized and encoded by ADC to convert it into a digital ultrasonic discrete signal.

[0105] b) Transmitting the ultrasonic discrete signal in digital form to a smart device terminal such as a mobile phone, and the smart device terminal performs spectrum analysis, MFCC feature extraction and other acoustic signal processing on the digital ultrasonic discrete signal to obtain the two-dimensional spectrum characteristics of the sound signal to be tested.

[0106] 3. Train the sound signal classification model. The sound signal classification model is a convolutional neural network model, which includes an input layer, multiple groups of combination layers consisting of two-dimensional convolutional layers and maximum pooling layers, a flattening layer, multiple groups of combination layers consisting of fully connected layers and random inactivation layers, a fully connected layer, and an output layer. The specific process of training the sound signal classification model includes:

[0107] a) Obtain the friction noise signal, background noise signal and sample ultrasonic signal reflected from the target detection position during the signal detection process, and determine their corresponding sample labels according to the signal types of the friction noise signal, background noise signal and sample ultrasonic signal.

[0108] b) Perform digital signal processing on the sound signal marked with sample labels, convert the acquired sound signal into two-dimensional audio features, use the two-dimensional audio features with sample labels as sample data sets, and randomly divide the sample data sets into training data sets and test data sets according to a preset ratio.

[0109] c) Input the two-dimensional audio features in the training data set into the sound signal classification model, calculate the loss function value using the difference between the model output value and the sample label, and apply the loss function value to update the parameters of the sound signal classification model, thereby training the sound signal classification model.

[0110] d) Import the test data set into the sound signal classification model with updated parameters, verify and evaluate the sound signal classification model, and obtain the trained sound signal classification model after the verification and evaluation passes.

[0111] 4. Input the two-dimensional audio features of the sound signal to be tested into the trained sound signal classification model, output the probability value of the sound signal to be tested being classified into each preset sound signal type (friction noise signal type, background noise signal type and target signal type), and determine the signal type of the sound signal to be tested according to the probability value.

[0112] 5. According to the signal type of the sound signal to be tested, determine whether the current detection position is the target detection position, and push prompt messages accordingly through sound and light (voice prompt, indicator light) or display (picture display, text display). Specifically including:

[0113] a) When the signal type is the target signal type, the current detection position is determined to be the target detection position, and a correct prompt message indicating that the current detection position is the target detection position is pushed. For example, the green light on the terminal device is on, and "The current detection position is correct! Please start measuring" is displayed.

[0114] b) When the signal type is not the target signal type, it is determined that the current detection position is not the target detection position, and an error prompt message is pushed to indicate that the current detection position is not the target detection position. For example, the red light on the terminal device is on, and it is displayed "The current detection position is wrong! Please try to move the probe to another position". When the sound signal type returned by the detection position after the movement is the target signal type, it is determined that the detection position after the movement is the target detection position, and a correct prompt message is pushed to indicate that the detection position after the movement is the target detection position, for example, the green light on the terminal device is on, and it is displayed "The current detection position is correct! Please start measuring".

[0115] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0116] Based on the same inventive concept, Figure 7 As shown, the embodiment of the present application also provides a signal detection position detection device for implementing the signal detection position detection method involved above. The detection device includes:

[0117] The signal acquisition module 701 is used to detect the current detection position through the ultrasonic physiological signal meter probe and obtain the sound signal to be measured corresponding to the current detection position;

[0118] The signal processing module 702 is used to perform digital signal processing on the sound signal to be tested to obtain the two-dimensional audio features of the sound signal to be tested;

[0119] The signal classification module 703 is used to input the two-dimensional audio features of the sound signal to be tested into the trained sound signal classification model, output the probability value of the sound signal to be tested being classified into each preset sound signal type, and determine the signal type of the sound signal to be tested according to the probability value;

[0120] The message push module 704 is used to determine that the current detection position is the target detection position when the signal type is the target signal type, and push a correct prompt message indicating that the current detection position is the target detection position.

[0121] The detection device of the signal detection position detects the current detection position through the ultrasonic physiological signal meter probe to obtain the sound signal to be detected corresponding to the current detection position; performs digital signal processing on the sound signal to be detected to obtain the two-dimensional audio features of the sound signal to be detected; inputs the two-dimensional audio features of the sound signal to be detected into the trained sound signal classification model, outputs the probability value of the sound signal to be detected being classified into each preset sound signal type, and determines the signal type of the sound signal to be detected according to the probability value; when the signal type is the target signal type, determines the current detection position as the target detection position, and pushes a correct prompt message indicating that the current detection position is the target detection position. The entire signal detection position detection process, by inputting the two-dimensional audio features of the sound signal to be detected into the sound signal classification model, obtains the signal type of the sound signal to be detected, determines the current detection position as the target detection position according to the signal type, and pushes a prompt message indicating the correct detection position accordingly, thereby assisting the detector to find the correct detection position, and effectively improving the reliability of signal detection.

[0122] In one embodiment, the signal classification module 703 is also used to obtain multiple types of sample noise signals and sample ultrasonic signals reflected based on the target detection position, and determine the corresponding sample labels according to the signal types of the sample noise signals and the sample ultrasonic signals; obtain the two-dimensional audio features corresponding to the sample noise signals and the sample ultrasonic signals, use the two-dimensional audio features with the sample labels as the sample data set, and divide the sample data set into a training data set and a test data set; input the two-dimensional audio features in the training data set into the sound signal classification model, and update the parameters of the sound signal classification model according to the difference between the predicted label output by the sound signal classification model and the sample label; use the test data set to verify and evaluate the sound signal classification model to obtain the trained sound signal classification model.

[0123] In one embodiment, the signal acquisition module 701 is further used to send an ultrasonic signal to the current detection position through an ultrasonic physiological signal meter probe; receive a sound signal reflected from the current detection position, and use the reflected sound signal as the sound signal to be measured.

[0124] In one embodiment, the signal processing module 702 is further used to perform sampling, quantization and encoding processing on the sound signal to be tested to obtain a corresponding digital signal; and perform audio feature extraction on the digital signal to obtain a two-dimensional audio feature of the sound signal to be tested.

[0125] In one of the embodiments, the message push module 704 is also used to determine that the current detection position is not the target detection position when the signal type is not the target signal type, and push an error prompt message indicating that the current detection position is not the target detection position; repeatedly execute the detection position of the moving ultrasonic physiological signal meter probe until the sound signal type corresponding to the moved detection position is the target signal type, determine that the corresponding moved detection position is the target detection position, and push a correct prompt message indicating that the corresponding moved detection position is the target detection position.

[0126] In one embodiment, the signal classification module 703 is also used to construct a sound signal classification model, which is a convolutional neural network model; the sound signal classification model includes, in sequence, an input layer, multiple groups of combination layers consisting of two-dimensional convolutional layers and maximum pooling layers, a flattening layer, multiple groups of combination layers consisting of fully connected layers and random inactivation layers, a fully connected layer, and an output layer.

[0127] Each module in the above-mentioned signal detection position detection device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0128] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 8As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for detecting a signal detection position is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0129] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0130] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0131] The current detection position is detected by using an ultrasonic physiological signal meter probe to obtain a sound signal to be detected corresponding to the current detection position;

[0132] Performing digital signal processing on the sound signal to be tested to obtain two-dimensional audio features of the sound signal to be tested;

[0133] Inputting the two-dimensional audio features of the sound signal to be tested into the trained sound signal classification model, outputting the probability value of the sound signal to be tested being classified into each preset sound signal type, and determining the signal type of the sound signal to be tested according to the probability value;

[0134] When the signal type is the target signal type, the current detection position is determined to be the target detection position, and a correct prompt message indicating that the current detection position is the target detection position is pushed.

[0135] In one embodiment, the processor also implements the following steps when executing the computer program: obtaining multiple types of sample noise signals and sample ultrasonic signals reflected based on the target detection position, and determining the corresponding sample labels according to the signal types to which the sample noise signals and the sample ultrasonic signals belong respectively; obtaining the two-dimensional audio features corresponding to the sample noise signals and the sample ultrasonic signals respectively, using the two-dimensional audio features with the sample labels as the sample data sets, and dividing the sample data sets into a training data set and a test data set; inputting the two-dimensional audio features in the training data set into a sound signal classification model, and updating the parameters of the sound signal classification model according to the difference between the predicted label output by the sound signal classification model and the sample label; and using the test data set to verify and evaluate the sound signal classification model to obtain the trained sound signal classification model.

[0136] In one embodiment, when the processor executes the computer program, the following steps are also implemented: sending an ultrasonic signal to the current detection position through the ultrasonic physiological signal meter probe; receiving a sound signal reflected back from the current detection position, and using the reflected sound signal as the sound signal to be tested.

[0137] In one embodiment, when the processor executes the computer program, the following steps are also implemented: sampling, quantizing and encoding the sound signal to be tested to obtain a corresponding digital signal; and extracting audio features from the digital signal to obtain two-dimensional audio features of the sound signal to be tested.

[0138] In one embodiment, the processor further implements the following steps when executing the computer program: when the signal type is not the target signal type, determining that the current detection position is not the target detection position, and pushing an error prompt message indicating that the current detection position is not the target detection position; repeatedly moving the detection position of the ultrasonic physiological signal meter probe until the sound signal type corresponding to the moved detection position is the target signal type, determining that the corresponding moved detection position is the target detection position, and pushing a correct prompt message indicating that the corresponding moved detection position is the target detection position.

[0139] In one embodiment, when the processor executes the computer program, the following steps are also implemented: constructing a sound signal classification model, wherein the sound signal classification model is a convolutional neural network model; the sound signal classification model sequentially includes an input layer, multiple groups of combination layers consisting of two-dimensional convolutional layers and maximum pooling layers, a flattening layer, multiple groups of combination layers consisting of fully connected layers and random inactivation layers, a fully connected layer, and an output layer.

[0140] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0141] The current detection position is detected by using an ultrasonic physiological signal meter probe to obtain a sound signal to be detected corresponding to the current detection position;

[0142] Performing digital signal processing on the sound signal to be tested to obtain two-dimensional audio features of the sound signal to be tested;

[0143] Inputting the two-dimensional audio features of the sound signal to be tested into the trained sound signal classification model, outputting the probability value of the sound signal to be tested being classified into each preset sound signal type, and determining the signal type of the sound signal to be tested according to the probability value;

[0144] When the signal type is the target signal type, the current detection position is determined to be the target detection position, and a correct prompt message indicating that the current detection position is the target detection position is pushed.

[0145] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining multiple types of sample noise signals and sample ultrasonic signals reflected based on the target detection position, and determining the corresponding sample labels according to the signal types to which the sample noise signals and the sample ultrasonic signals belong respectively; obtaining the two-dimensional audio features corresponding to the sample noise signals and the sample ultrasonic signals respectively, using the two-dimensional audio features with the sample labels as the sample data sets, and dividing the sample data sets into a training data set and a test data set; inputting the two-dimensional audio features in the training data set into a sound signal classification model, and updating the parameters of the sound signal classification model according to the difference between the predicted label output by the sound signal classification model and the sample label; and using the test data set to verify and evaluate the sound signal classification model to obtain the trained sound signal classification model.

[0146] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: sending an ultrasonic signal to the current detection position through the ultrasonic physiological signal meter probe; receiving a sound signal reflected back from the current detection position, and using the reflected sound signal as the sound signal to be tested.

[0147] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: sampling, quantizing and encoding the sound signal to be tested to obtain a corresponding digital signal; extracting audio features from the digital signal to obtain two-dimensional audio features of the sound signal to be tested.

[0148] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when the signal type is not the target signal type, determining that the current detection position is not the target detection position, and pushing an error prompt message indicating that the current detection position is not the target detection position; repeatedly moving the detection position of the ultrasonic physiological signal meter probe until the sound signal type corresponding to the moved detection position is the target signal type, determining that the corresponding moved detection position is the target detection position, and pushing a correct prompt message indicating that the corresponding moved detection position is the target detection position.

[0149] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: constructing a sound signal classification model, wherein the sound signal classification model is a convolutional neural network model; the sound signal classification model sequentially includes an input layer, multiple groups of combination layers consisting of two-dimensional convolutional layers and maximum pooling layers, a flattening layer, multiple groups of combination layers consisting of fully connected layers and random inactivation layers, a fully connected layer, and an output layer.

[0150] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0151] The current detection position is detected by using an ultrasonic physiological signal meter probe to obtain a sound signal to be detected corresponding to the current detection position;

[0152] Performing digital signal processing on the sound signal to be tested to obtain two-dimensional audio features of the sound signal to be tested;

[0153] Inputting the two-dimensional audio features of the sound signal to be tested into the trained sound signal classification model, outputting the probability value of the sound signal to be tested being classified into each preset sound signal type, and determining the signal type of the sound signal to be tested according to the probability value;

[0154] When the signal type is the target signal type, the current detection position is determined to be the target detection position, and a correct prompt message indicating that the current detection position is the target detection position is pushed.

[0155] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining multiple types of sample noise signals and sample ultrasonic signals reflected based on the target detection position, and determining the corresponding sample labels according to the signal types to which the sample noise signals and the sample ultrasonic signals belong respectively; obtaining the two-dimensional audio features corresponding to the sample noise signals and the sample ultrasonic signals respectively, using the two-dimensional audio features with the sample labels as the sample data sets, and dividing the sample data sets into a training data set and a test data set; inputting the two-dimensional audio features in the training data set into a sound signal classification model, and updating the parameters of the sound signal classification model according to the difference between the predicted label output by the sound signal classification model and the sample label; and using the test data set to verify and evaluate the sound signal classification model to obtain the trained sound signal classification model.

[0156] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: sending an ultrasonic signal to the current detection position through the ultrasonic physiological signal meter probe; receiving a sound signal reflected back from the current detection position, and using the reflected sound signal as the sound signal to be tested.

[0157] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: sampling, quantizing and encoding the sound signal to be tested to obtain a corresponding digital signal; extracting audio features from the digital signal to obtain two-dimensional audio features of the sound signal to be tested.

[0158] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: when the signal type is not the target signal type, determining that the current detection position is not the target detection position, and pushing an error prompt message indicating that the current detection position is not the target detection position; repeatedly moving the detection position of the ultrasonic physiological signal meter probe until the sound signal type corresponding to the moved detection position is the target signal type, determining that the corresponding moved detection position is the target detection position, and pushing a correct prompt message indicating that the corresponding moved detection position is the target detection position.

[0159] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: constructing a sound signal classification model, wherein the sound signal classification model is a convolutional neural network model; the sound signal classification model sequentially includes an input layer, multiple groups of combination layers consisting of two-dimensional convolutional layers and maximum pooling layers, a flattening layer, multiple groups of combination layers consisting of fully connected layers and random inactivation layers, a fully connected layer, and an output layer.

[0160] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0161] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0162] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0163] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for detecting a signal detection position, characterized in that: The detection method comprises: Detecting the current detection position by using an ultrasonic physiological signal meter probe to obtain a sound signal to be detected corresponding to the current detection position; Performing digital signal processing on the sound signal to be tested to obtain a two-dimensional audio feature of the sound signal to be tested; Inputting the two-dimensional audio features of the sound signal to be tested into a trained sound signal classification model, outputting probability values ​​of the sound signal to be tested being classified into various preset sound signal types, and determining the signal type of the sound signal to be tested according to the probability values; In the case where the signal type is a target signal type, the current detection position is determined to be a target detection position, and a correct prompt message indicating that the current detection position is a target detection position is pushed.

2. The detection method according to claim 1, characterized in that: The training process of the sound signal classification model includes: Acquire multiple types of sample noise signals and sample ultrasonic signals reflected from the target detection position, and determine corresponding sample labels of the sample noise signals and the sample ultrasonic signals according to their respective signal types; Acquire two-dimensional audio features corresponding to the sample noise signal and the sample ultrasonic signal, use the two-dimensional audio features with sample labels as a sample data set, and divide the sample data set into a training data set and a test data set; Inputting the sample ultrasound signal and the sample noise signal in the training data set into the sound signal classification model, and updating the parameters of the sound signal classification model according to the difference between the predicted label output by the sound signal classification model and the sample label; The test data set is used to verify and evaluate the sound signal classification model to obtain a trained sound signal classification model.

3. The detection method according to claim 1, characterized in that: The method of detecting the current detection position by using an ultrasonic physiological signal meter probe to obtain a sound signal to be detected corresponding to the current detection position includes: Sending an ultrasonic signal to the current detection position through an ultrasonic physiological signal meter probe; A sound signal reflected from the current detection position is received, and the reflected sound signal is used as the sound signal to be detected.

4. The detection method according to claim 1, characterized in that: The step of performing digital signal processing on the sound signal to be tested to obtain the two-dimensional audio features of the sound signal to be tested includes: Sampling, quantizing and encoding the sound signal to be tested to obtain a corresponding digital signal; Audio feature extraction is performed on the digital signal to obtain two-dimensional audio features of the sound signal to be tested.

5. The detection method according to claim 1, characterized in that: After determining the signal type of the sound signal to be tested according to the probability value, the method further includes: In a case where the signal type is not a target signal type, determining that the current detection position is not a target detection position, and pushing an error prompt message indicating that the current detection position is not a target detection position; Repeat the process of moving the detection position of the ultrasonic physiological signal meter probe until the sound signal type corresponding to the moved detection position is the target signal type, determine that the corresponding moved detection position is the target detection position, and push a correct prompt message indicating that the corresponding moved detection position is the target detection position.

6. The detection method according to any one of claims 1 to 5, characterized in that: The sound signal classification model is a convolutional neural network model; the sound signal classification model includes, in sequence, an input layer, multiple groups of combination layers consisting of two-dimensional convolutional layers and maximum pooling layers, a flattening layer, multiple groups of combination layers consisting of fully connected layers and random inactivation layers, a fully connected layer, and an output layer.

7. A detection device for signal detection position, characterized in that: The detection device comprises: A signal acquisition module, used to detect the current detection position through an ultrasonic physiological signal meter probe, and obtain a sound signal to be measured corresponding to the current detection position; A signal processing module, used for performing digital signal processing on the sound signal to be tested to obtain a two-dimensional audio feature of the sound signal to be tested; A signal classification module, used for inputting the two-dimensional audio features of the sound signal to be tested into a trained sound signal classification model, outputting a probability value of the sound signal to be tested being classified into each preset sound signal type, and determining the signal type of the sound signal to be tested according to the probability value; The message push module is used to determine that the current detection position is a target detection position when the signal type is a target signal type, and push a correct prompt message indicating that the current detection position is a target detection position.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the detection method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the detection method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the detection method according to any one of claims 1 to 6 are implemented.

Images