Method for children cough training

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a method for children cough training, which comprises the following steps: acquiring audio information and displacement change characteristics, determining a displacement characteristic time domain segment and a sound characteristic time domain segment, screening the audio information, and analyzing whether target cough is qualified or not; the thoracic cavity fluctuation condition is determined according to the displacement change amplitude and the displacement change rate of the target thoracic cavity part, the cough time interval of the suspected patient is determined according to the obtained sound signal frequency and sound signal amplitude, and the target cough time period is further determined by integrating the target thoracic cavity fluctuation condition and sound. Considering that the sound collection environment is difficult to unify in the actual situation and the environmental noise can influence the analysis of the subsequent target cough information, the target cough condition is comprehensively analyzed according to the collected sound signal and the thoracic cavity fluctuation condition, and the accuracy of analyzing the target cough condition is improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method for children's cough training. Background Art

[0002] Patients undergoing cough training during pulmonary rehabilitation can help clear their airways and actively train to expectorate. This is especially true for pediatric patients, as different pediatric patients are prone to inconsistent descriptions of their own cough conditions, which affects the progress of cough training. On the other hand, it is difficult to control the cough strength of pediatric patients, making it difficult to determine the quality of cough training. The existing technology extracts samples from sound sample signals and electromyography sample signals, and compares the extracted sample signals with the effective sample signals to determine the target cough detection model. However, the influence of surrounding noise during the target cough process is not considered, resulting in inaccurate target cough data being obtained, and the target cough strength is not analyzed. Insufficient cough strength leads to unqualified target coughs, which will affect cough training.

[0003] Chinese Patent Publication No.: CN114446319A discloses a cough detection model training method, a cough detection method and a cough detection device, the method comprising: obtaining a user's cough sample signal and a signal label corresponding to the cough sample signal, the cough sample signal comprising a sound sample signal and an electromyographic sample signal, the signal label being used to indicate a cough state corresponding to the cough sample signal; performing effective sample extraction on the sound sample signal and the electromyographic sample signal to obtain an effective cough sample signal corresponding to the cough sample signal; performing feature extraction on the effective cough sample signal to obtain a peak feature, a Mel frequency cepstral coefficient feature and an energy feature corresponding to the cough sample signal; training a cough detection model according to the peak feature, the Mel frequency cepstral coefficient feature, the energy feature and the signal label to obtain a target cough detection model.

[0004] However, the prior art still has the following problems:

[0005] The influence of surrounding noise during the target coughing process was not considered, resulting in inaccurate target cough data. The target cough strength was not analyzed. Insufficient cough strength resulted in unqualified target cough, which would affect cough training. Summary of the invention

[0006] To this end, the present invention provides a method for children's cough training, which is used to overcome the problems in the prior art that the influence of surrounding noise during the target coughing process is not considered, resulting in inaccurate target cough data being obtained, and the target cough strength is not analyzed. The insufficient cough strength leads to unqualified target cough, which affects the cough training.

[0007] To achieve the above object, the present invention provides a method for children's cough training. The method comprises:

[0008] Step S1, the target wears a monitoring module equipped with a sound sensor and an inertial sensor, and obtains audio information during the target wearing process in a predetermined time period and displacement change characteristics of the position where the monitoring module is set, wherein the monitoring module is set at the target chest area;

[0009] Step S2, determining a displacement change characterization parameter based on the displacement change amplitude and displacement change rate of the displacement change feature in different time domain segments, determining a displacement feature time domain segment in the displacement change feature according to the displacement change characterization parameter, determining a sound characterization parameter based on the sound signal frequency and sound signal amplitude of the audio information, and determining a sound feature time domain segment in the audio information based on the sound characterization parameter;

[0010] Step S3, filtering the audio information during the target wearing process in a predetermined time period based on the overlapping time domain segment of the displacement feature time domain segment and the sound feature time domain segment, and verifying the filtered audio information;

[0011] Step S4, determining a qualified characterization parameter based on the displacement change characterization parameter and the sound characterization parameter, and analyzing the verified audio information according to the qualified characterization parameter to determine whether the target cough is qualified.

[0012] Further, the determining of the displacement change characterization parameter includes:

[0013] Solve the ratio of the displacement change amplitude of the current time domain segment to the preset displacement change amplitude standard threshold to obtain the first displacement change feature,

[0014] Solve the ratio of the displacement change rate in the current time domain segment to the preset displacement change rate standard threshold to obtain a second displacement change feature,

[0015] The first displacement change feature and the second displacement change feature are weightedly summed to obtain a displacement change characterization parameter.

[0016] Further, the step of determining the displacement feature time domain segment in the displacement change feature according to the displacement change characterization parameter includes:

[0017] If the displacement change characterization parameter is greater than or equal to the displacement change characterization parameter standard threshold, then determining that the current time domain segment is a displacement characteristic time domain segment;

[0018] If the displacement change characterization parameter is less than the displacement change characterization parameter standard threshold, the current time domain segment is determined to be a non-displacement feature time domain segment.

[0019] Further, the determining of the sound characterization parameters includes:

[0020] Solving the ratio of the sound signal frequency of the current time domain segment of the audio information to a preset sound signal frequency standard threshold value to obtain a first sound feature,

[0021] Solving the ratio of the sound signal amplitude of the current time domain segment of the audio information to a preset sound signal amplitude standard threshold value to obtain a second sound feature,

[0022] The first sound feature and the second sound feature are weighted and summed to obtain a sound characterization parameter.

[0023] Further, the determining the sound feature time domain segment in the audio information based on the sound characterization parameter includes:

[0024] If the sound characterization parameter is greater than or equal to the sound characterization parameter standard threshold, determining that the current time domain segment is a sound feature time domain segment;

[0025] If the sound characterization parameter is less than the sound characterization parameter standard threshold, the current time domain segment is determined to be a non-sound feature time domain segment.

[0026] Furthermore, the method of screening the audio information during the wearing process of the target in the predetermined time period based on the overlapped time domain segment of the displacement feature time domain segment and the sound feature time domain segment includes:

[0027] Determine the overlapping time domain segment of the displacement feature time domain segment and the sound feature time domain segment,

[0028] Filter out the overlapping time domain segments from the audio information during the target wearing process.

[0029] Furthermore, the verifying of the screened audio information includes:

[0030] If the sound signal strength of a single overlapping time domain segment of the filtered audio information is greater than or equal to a preset sound signal strength standard threshold, the overlapping time domain segment is determined to be a non-target cough time domain segment;

[0031] If the sound signal strength of a single overlapping time domain segment of the filtered audio information is less than the preset sound signal strength standard threshold, the overlapping time domain segment is determined to be a target cough time domain segment.

[0032] Further, the determining of the qualified characterization parameter based on the displacement change characterization parameter and the sound characterization parameter includes:

[0033] Solving the ratio of the displacement change characterization parameter of the target cough time domain segment to a preset displacement change characterization parameter standard threshold value to obtain a first characterization feature,

[0034] Solving the ratio of the sound characterization parameter of the target cough time domain segment to a preset sound characterization parameter standard threshold value to obtain a second characterization feature,

[0035] The qualified characterization parameter is obtained by weighted summing the first characterization feature and the second characterization feature.

[0036] Further, the analyzing the verified audio information according to the qualified characterization parameters to determine whether the target cough is qualified includes:

[0037] If the qualified characterization parameter of the audio information that has passed the verification is greater than or equal to the preset qualified characterization parameter standard threshold, then the target cough is determined to be qualified;

[0038] If the qualified characterization parameter of the audio information that has passed the verification is less than the preset qualified characterization parameter standard threshold, the target cough is determined to be unqualified.

[0039] Further, a qualified signal is sent when it is determined that the target cough is qualified.

[0040] Compared with the prior art, the beneficial effect of the present invention lies in that, in the present invention, the chest rise and fall condition is comprehensively determined according to the displacement change amplitude and displacement change rate of the target chest part, so as to preliminarily determine the time period of the suspected patient's cough from the perspective of the chest rise and fall condition. In actual situations, the time period of the suspected patient's cough determined according to the target chest rise and fall condition may have other situations, such as rapid breathing of the patient. The sound of the patient and the surrounding environment is comprehensively analyzed according to the acquired sound signal frequency and sound signal amplitude to preliminarily determine the time period of the suspected patient's cough. In actual situations, the time period of the suspected patient's cough determined according to the sound signal may contain external noise, such as the sound of other target coughs. Considering that in actual situations, external conditions such as the sound collection environment are difficult to unify, environmental noise will affect the subsequent analysis of target cough information. If there is noise in the target cough time period at the same time, it will affect the analysis of whether the target cough condition is qualified. Therefore, the present invention further determines the time period of the suspected target cough by combining the chest rise and fall condition of the target and the collected sound, and determines the overlapping part of the time period determined according to the chest rise and fall condition and the sound as the time period containing the patient's cough sound, so as to improve the accuracy of determining the time period of the target cough.

[0041] In particular, the present invention preliminarily determines the time domain segment of the suspected target cough based on the overlapping part of the displacement feature time domain segment and the sound feature time domain segment. The sound signal intensity of the patient's cough in the absence of noise is different from the sound signal intensity in the presence of ambient noise. The present invention obtains the sound signal intensity of the determined time domain segment of the suspected target cough, and compares the sound signal intensity of the time domain segment with the sound signal intensity of a single person coughing in a quiet environment in the historical records, so as to screen out the time period containing ambient noise, and screen out the time domain segment of the target cough in the collected audio information, thereby further narrowing the range of the time period to be analyzed and improving the work efficiency of subsequent analysis of the patient's coughing condition.

[0042] In particular, the present invention uses the sound data parameters of the time period of the patient's cough to filter the collected audio information, so as to avoid analyzing each time period of the audio information, thereby improving the screening efficiency of the time period of the patient's cough in the audio information. In actual situations, if the patient's coughing intensity is too low, it will affect the expected effect of cough training. The present invention calculates the data characterization parameters of the patient's coughing time period, and compares the characterization parameters with the data characterization parameters of qualified cough data in the historical data to ensure the qualification of the patient's cough, thereby further ensuring the effect of the patient's cough training. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a flow chart of the method for children's cough training of the present invention;

[0044] Figure 2 A flow chart for determining a displacement feature time domain segment in a displacement change feature of the present invention;

[0045] Figure 3 A flow chart for determining a time domain segment of a sound feature in audio information according to the present invention;

[0046] Figure 4 The present invention is a flow chart of the determination of verifying the screened audio information. DETAILED DESCRIPTION

[0047] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0048] It should be pointed out that the data in this embodiment are obtained by comprehensive analysis and evaluation of the historical data of the system of the present invention in the six months before this determination and the corresponding historical determination results. Before this detection, the system of the present invention comprehensively determines the values ​​of the preset parameter standards for this determination based on the evaluation values ​​of the 37,383 retrieval results detected cumulatively in the first three months. It can be understood by those skilled in the art that the system of the present invention can determine the single parameter mentioned above by selecting the value with the highest proportion as the preset standard parameter according to the data distribution, using weighted summation to use the obtained value as the preset standard parameter, substituting each historical data into a specific formula and using the value obtained by the formula as the preset standard parameter or other selection methods, as long as the system of the present invention can clearly define the different specific situations in the single determination process through the obtained values.

[0049] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0050] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0051] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0052] See also Figure 1 As shown, it is a flow chart of the method for children's cough training of the present invention.

[0053] The embodiment of the present invention provides a method for children's cough training, comprising:

[0054] Step S1, the target wears a monitoring module equipped with a sound sensor and an inertial sensor, and obtains audio information during the target wearing process in a predetermined time period and displacement change characteristics of the position where the monitoring module is set, wherein the monitoring module is set at the target chest area;

[0055] Step S2, determining a displacement change characterization parameter based on the displacement change amplitude and displacement change rate of the displacement change feature in different time domain segments, determining a displacement feature time domain segment in the displacement change feature according to the displacement change characterization parameter, determining a sound characterization parameter based on the sound signal frequency and sound signal amplitude of the audio information, and determining a sound feature time domain segment in the audio information based on the sound characterization parameter;

[0056] Step S3, filtering the audio information during the target wearing process in a predetermined time period based on the overlapping time domain segment of the displacement feature time domain segment and the sound feature time domain segment, and verifying the filtered audio information;

[0057] Step S4, determining a qualified characterization parameter based on the displacement change characterization parameter and the sound characterization parameter, and analyzing the verified audio information according to the qualified characterization parameter to determine whether the target cough is qualified.

[0058] Specifically, the determination of the displacement change characterization parameter includes:

[0059] Solve the ratio of the displacement change amplitude of the current time domain segment to the preset displacement change amplitude standard threshold to obtain the first displacement change feature,

[0060] Solve the ratio of the displacement change rate in the current time domain segment to the preset displacement change rate standard threshold to obtain a second displacement change feature,

[0061] The first displacement change feature and the second displacement change feature are weightedly summed to obtain a displacement change characterization parameter.

[0062] Specifically, in this embodiment, the preset displacement change amplitude standard threshold W0 is obtained in advance, and the displacement change amplitudes of the chest cavity when several different target coughs are qualified are recorded, and the average displacement change amplitude △W is solved, and W0=α×△W is set, α represents the first accuracy coefficient, 0.75<α<0.85.

[0063] Specifically, in this embodiment, the preset displacement change rate standard threshold value B0 is obtained in advance, and the displacement change rates of the chest cavity when several different target coughs are qualified are recorded, and the displacement change rate mean △B is solved, and B0=β×△B is set, β represents the second accuracy coefficient, 0.7<β<0.8.

[0064] Specifically, the weight coefficient w of the first displacement change feature is selected in the interval [0.3, 0.4], the weight coefficient b of the second displacement change feature is selected in the interval [0.6, 0.7], and w+b=1.

[0065] See also Figure 2 As shown, it is a flow chart for determining the time domain segment of the displacement feature in the displacement change feature.

[0066] Specifically, determining the displacement feature time domain segment in the displacement change feature according to the displacement change characterization parameter includes:

[0067] If the displacement change characterization parameter is greater than or equal to the displacement change characterization parameter standard threshold, then determining that the current time domain segment is a displacement characteristic time domain segment;

[0068] If the displacement change characterization parameter is less than the displacement change characterization parameter standard threshold, the current time domain segment is determined to be a non-displacement feature time domain segment.

[0069] Specifically, in this embodiment, the displacement change characterization parameter standard threshold is selected in the interval [0.8, 1.2].

[0070] Specifically, the determining of the sound characterization parameters includes:

[0071] Solving the ratio of the sound signal frequency of the current time domain segment of the audio information to a preset sound signal frequency standard threshold value to obtain a first sound feature,

[0072] Solving the ratio of the sound signal amplitude of the current time domain segment of the audio information to a preset sound signal amplitude standard threshold value to obtain a second sound feature,

[0073] The first sound feature and the second sound feature are weighted and summed to obtain a sound characterization parameter.

[0074] Specifically, in this embodiment, the preset sound signal frequency standard threshold Q0 is obtained by pre-measurement, and the sound signal frequencies of several different target coughs are recorded to solve the sound signal frequency mean △Q, and set Q0=γ×△Q, γ represents the third accuracy coefficient, 0.7<γ<0.85.

[0075] Specifically, in this embodiment, the preset sound signal amplitude standard threshold value Z0 is obtained in advance, and the sound signal amplitudes when several different target coughs are qualified are recorded, and the sound signal amplitude mean △Z is solved, and Z0=z×△Z is set, where z represents the fourth accuracy coefficient, 0.75<z<0.8.

[0076] See also Figure 3 As shown, it is a decision flow chart for determining the time domain segment of the sound features in the audio information.

[0077] Specifically, determining the sound feature time domain segment in the audio information based on the sound characterization parameter includes:

[0078] If the sound characterization parameter is greater than or equal to the sound characterization parameter standard threshold, determining that the current time domain segment is a sound feature time domain segment;

[0079] If the sound characterization parameter is less than the sound characterization parameter standard threshold, the current time domain segment is determined to be a non-sound feature time domain segment.

[0080] Specifically, in this embodiment, the standard threshold of the sound characterization parameter is selected in the interval [0.85, 1.1].

[0081] Specifically, the method of screening the audio information during the wearing process of the target in a predetermined time period based on the overlapped time domain segment of the displacement feature time domain segment and the sound feature time domain segment includes:

[0082] Determine the overlapping time domain segment of the displacement feature time domain segment and the sound feature time domain segment,

[0083] The audio information in each overlapping time domain segment is filtered out from the audio information during the target wearing process.

[0084] See also Figure 4As shown, it is a decision flow chart for verifying the filtered audio information.

[0085] Specifically, the verification of the screened audio information includes:

[0086] If the sound signal strength of a single overlapping time domain segment of the filtered audio information is greater than or equal to a preset sound signal strength standard threshold, the overlapping time domain segment is determined to be a non-target cough time domain segment;

[0087] If the sound signal strength of a single overlapping time domain segment of the filtered audio information is less than the preset sound signal strength standard threshold, the overlapping time domain segment is determined to be a target cough time domain segment.

[0088] Specifically, in this embodiment, the preset sound signal strength standard threshold value P0 is obtained in advance, and the sound signal frequencies of several different target coughs are recorded, and the sound signal frequency mean △P is solved, and P0=p×△P is set, p represents the fifth precision coefficient, 0.75<p<0.8.

[0089] Specifically, determining the qualified characterization parameter based on the displacement change characterization parameter and the sound characterization parameter includes:

[0090] Solving the ratio of the displacement change characterization parameter of the target cough time domain segment to a preset displacement change characterization parameter standard threshold value to obtain a first characterization feature,

[0091] Solving the ratio of the sound characterization parameter of the target cough time domain segment to a preset sound characterization parameter standard threshold value to obtain a second characterization feature,

[0092] The qualified characterization parameter is obtained by weighted summing the first characterization feature and the second characterization feature.

[0093] Specifically, in this embodiment, the preset displacement change characterization parameter standard threshold value A0 is obtained in advance, and the displacement change characterization parameters of several different target coughs are calculated respectively, and the mean displacement change characterization parameter △A is solved, and A0 is set to a×△A, where a represents the sixth precision coefficient, 0.75<a<0.8.

[0094] Specifically, in this embodiment, the preset sound characterization parameter standard threshold C0 is obtained in advance, and the sound characterization parameters of several different target coughs are calculated respectively, and the mean value △C of the sound characterization parameters is solved, and C0=c×△C is set, c represents the seventh precision coefficient, 0.7<c<0.8.

[0095] Specifically, in this embodiment, the weight coefficient x of the first characterizing feature is selected in the interval [0.5, 0.6], the weight coefficient y of the second characterizing feature is selected in the interval [0.4, 0.5], and x+y=1.

[0096] Specifically, analyzing the verified audio information according to the qualified characterization parameters to determine whether the target cough is qualified includes:

[0097] If the qualified characterization parameter of the audio information that has passed the verification is greater than or equal to the preset qualified characterization parameter standard threshold, then the target cough is determined to be qualified;

[0098] If the qualified characterization parameter of the audio information that has passed the verification is less than the preset qualified characterization parameter standard threshold, the target cough is determined to be unqualified.

[0099] Specifically, in this embodiment, the preset qualified characterization parameter standard threshold is selected between the interval [1, 1.2].

[0100] Specifically, a qualified signal is issued when it is determined that the target cough is qualified.

[0101] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0102] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for cough training for children, characterized in that: include: Step S1, the target wears a monitoring module equipped with a sound sensor and an inertial sensor, and obtains audio information during the target wearing process in a predetermined time period and displacement change characteristics of the position where the monitoring module is set, wherein the monitoring module is set at the target chest area; Step S2, determining a displacement change characterization parameter based on the displacement change amplitude and displacement change rate of the displacement change feature in different time domain segments, determining a displacement feature time domain segment in the displacement change feature according to the displacement change characterization parameter, determining a sound characterization parameter based on the sound signal frequency and sound signal amplitude of the audio information, and determining a sound feature time domain segment in the audio information based on the sound characterization parameter; Step S3, filtering the audio information during the target wearing process in a predetermined time period based on the overlapping time domain segment of the displacement feature time domain segment and the sound feature time domain segment, and verifying the filtered audio information; Step S4, determining a qualified characterization parameter based on the displacement change characterization parameter and the sound characterization parameter, and analyzing the verified audio information according to the qualified characterization parameter to determine whether the target cough is qualified.

2. The method for children's cough training according to claim 1, characterized in that: The step of determining the displacement change characterization parameter comprises: Solve the ratio of the displacement change amplitude of the current time domain segment to the preset displacement change amplitude standard threshold to obtain the first displacement change feature, Solve the ratio of the displacement change rate in the current time domain segment to the preset displacement change rate standard threshold to obtain a second displacement change feature, The first displacement change feature and the second displacement change feature are weightedly summed to obtain a displacement change characterization parameter.

3. The method for children's cough training according to claim 1, characterized in that: The step of determining the displacement feature time domain segment in the displacement change feature according to the displacement change characterization parameter comprises: If the displacement change characterization parameter is greater than or equal to the displacement change characterization parameter standard threshold, then determining that the current time domain segment is a displacement characteristic time domain segment; If the displacement change characterization parameter is less than the displacement change characterization parameter standard threshold, the current time domain segment is determined to be a non-displacement feature time domain segment.

4. The method for children's cough training according to claim 1, characterized in that: The determining of the sound characterization parameter comprises: Solving the ratio of the sound signal frequency of the current time domain segment of the audio information to a preset sound signal frequency standard threshold value to obtain a first sound feature, Solving the ratio of the sound signal amplitude of the current time domain segment of the audio information to a preset sound signal amplitude standard threshold value to obtain a second sound feature, The first sound feature and the second sound feature are weighted and summed to obtain a sound characterization parameter.

5. The method for children's cough training according to claim 1, characterized in that: The determining of the sound feature time domain segment in the audio information based on the sound characterization parameter includes: If the sound characterization parameter is greater than or equal to the sound characterization parameter standard threshold, determining that the current time domain segment is a sound feature time domain segment; If the sound characterization parameter is less than the sound characterization parameter standard threshold, the current time domain segment is determined to be a non-sound feature time domain segment.

6. The method for children's cough training according to claim 1, characterized in that: The method of screening the audio information during the wearing process of the target in the predetermined time period based on the overlapping time domain segment of the displacement feature time domain segment and the sound feature time domain segment includes: Determine the overlapping time domain segment of the displacement feature time domain segment and the sound feature time domain segment, The audio information in each overlapping time domain segment is filtered out from the audio information during the target wearing process.

7. The method for children's cough training according to claim 1, characterized in that: The verifying of the screened audio information includes: If the sound signal strength of a single overlapping time domain segment of the filtered audio information is greater than or equal to a preset sound signal strength standard threshold, the overlapping time domain segment is determined to be a non-target cough time domain segment; If the sound signal strength of a single overlapping time domain segment of the filtered audio information is less than the preset sound signal strength standard threshold, the overlapping time domain segment is determined to be a target cough time domain segment.

8. The method for children's cough training according to claim 7, characterized in that: The determining of the qualified characterization parameter based on the displacement change characterization parameter and the sound characterization parameter comprises: Solving the ratio of the displacement change characterization parameter of the target cough time domain segment to a preset displacement change characterization parameter standard threshold value to obtain a first characterization feature, Solving the ratio of the sound characterization parameter of the target cough time domain segment to a preset sound characterization parameter standard threshold value to obtain a second characterization feature, The qualified characterization parameter is obtained by weighted summing the first characterization feature and the second characterization feature.

9. The method for children's cough training according to claim 7, characterized in that: The step of analyzing the verified audio information according to the qualified characterization parameters to determine whether the target cough is qualified includes: If the qualified characterization parameter of the audio information that has passed the verification is greater than or equal to the preset qualified characterization parameter standard threshold, then the target cough is determined to be qualified; If the qualified characterization parameter of the audio information that has passed the verification is less than the preset qualified characterization parameter standard threshold, the target cough is determined to be unqualified.

10. The method for children's cough training according to claim 9, characterized in that: When the target cough is judged to be qualified, a qualified signal is sent.

Images