Disease diagnosis auxiliary method and system of micro intelligent lung sound collector

Abstract

The present invention discloses a miniature intelligent lung sound collector and its disease diagnosis auxiliary method and system, which relate to the medical field and solve the problem of poor diagnostic effect of existing lung sound collectors and their disease diagnosis auxiliary methods. The system comprises: step S1: respectively obtaining the lung sound comprehensive frequency deviation and the lung sound period monitoring coefficient to obtain the patient's lung sound monitoring data; step S2: obtaining and analyzing the period characteristic time difference and the symptom monitoring coefficient corresponding to each symptom monitoring sub-period to obtain the patient's symptom analysis coefficient; step S3: obtaining the patient's condition assessment coefficient by analyzing the lung sound comprehensive frequency deviation, the lung sound period monitoring coefficient and the patient's symptom analysis coefficient, obtaining the patient's condition assessment coefficient threshold and performing numerical comparison with the patient's condition assessment coefficient, and performing a diagnosis and assessment of the patient's condition based on the numerical comparison result. The present invention can improve the accuracy and comprehensiveness of disease auxiliary diagnosis.

Description

Technical Field

[0001] The present invention belongs to the medical field and relates to data analysis technology, specifically a disease diagnosis auxiliary method and system of a miniature intelligent lung sound collector. Background Art

[0002] Existing lung sound collectors have the following specific defects when diagnosing diseases:

[0003] 1. Existing lung sound collectors require doctors to rely on their own experience to auscultate different types of lung sounds when diagnosing diseases. Lung sound collectors cannot further analyze the collected data, which makes it difficult to fully utilize medical resources.

[0004] 2. Existing lung sound collectors are unable to conduct a comprehensive analysis based on the patient's clinical symptoms when diagnosing diseases, resulting in a lack of accuracy in the diagnostic results.

[0005] To this end, we propose a disease diagnosis auxiliary method and system based on a miniature intelligent lung sound collector. Summary of the Invention

[0006] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a disease diagnosis auxiliary method and system for a miniature intelligent lung sound collector. The present invention aims to improve the comprehensiveness of data collection and the accuracy of diagnostic results of the lung sound collector.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: a disease diagnosis auxiliary method of a micro intelligent lung sound collector, comprising the following specific steps:

[0008] Step S1: Obtaining a patient's lung sound monitoring cycle, marking multiple lung sound monitoring sub-periods within the patient's lung sound monitoring cycle, and obtaining multiple different types of monitored lung sounds. Frequency monitoring is performed on each type of monitored lung sound to obtain a comprehensive lung sound frequency deviation. Lung sound monitoring is performed on each lung sound monitoring sub-period to obtain a lung sound cycle monitoring coefficient. The comprehensive lung sound frequency deviation and the lung sound cycle monitoring coefficient are defined as the patient's lung sound monitoring data.

[0009] Step S2: Obtain the patient's symptom monitoring period, and mark multiple symptom monitoring sub-periods within the patient's symptom monitoring period, respectively obtain the period characteristic time difference corresponding to each symptom monitoring sub-period, respectively perform clinical symptom analysis on the patient in each symptom monitoring sub-period, obtain the symptom monitoring coefficient corresponding to each symptom monitoring sub-period, and comprehensively analyze the period characteristic time difference and symptom monitoring coefficient corresponding to each symptom monitoring sub-period to obtain the patient's symptom analysis coefficient;

[0010] Step S3: Obtain the patient's condition assessment coefficient by analyzing the comprehensive frequency deviation of lung sounds, the lung sound cycle monitoring coefficient, and the patient's symptom analysis coefficient, obtain the patient's condition assessment coefficient threshold and perform numerical comparison with the patient's condition assessment coefficient, and perform a diagnosis and assessment of the patient's condition based on the numerical comparison result.

[0011] Furthermore, the step S1 further includes the following specific steps:

[0012] Step S11: marking a patient lung sound monitoring cycle within a period of time during which the patient's lung sound is monitored;

[0013] Step S12: Divide the patient's lung sound monitoring period into a plurality of monitoring sub-periods of equal duration, and name the divided multiple monitoring sub-periods as the first lung sound monitoring sub-period to the cth lung sound monitoring sub-period;

[0014] Step S13: During the monitoring of the patient in the first lung sound monitoring sub-period, a plurality of different types of monitored lung sounds are set, and the set plurality of different types of monitored lung sounds are named first type monitored lung sounds to dth type monitored lung sounds, respectively;

[0015] Step S14: monitoring the patient's lung sound frequency to obtain a comprehensive frequency deviation of lung sounds;

[0016] Step S15: performing lung sound monitoring for each lung sound monitoring sub-period to obtain a lung sound cycle monitoring coefficient;

[0017] Step S16: defining the lung sound comprehensive frequency deviation and the lung sound period monitoring coefficient as the patient's lung sound monitoring data.

[0018] Furthermore, the step S14 further includes the following specific steps:

[0019] Step S141: Acquire multiple audio clips of the first type of monitored lung sound within the patient's lung sound monitoring cycle to obtain multiple first lung sound audio clips, acquire the lung sound frequency of each first lung sound audio clip to obtain multiple monitored lung sound frequency values, and average the obtained multiple lung sound frequency values ​​to obtain the first lung sound monitoring frequency;

[0020] Step S142: Obtaining a reference frequency value corresponding to the first type of monitored lung sound to obtain a first reference frequency value, calculating a difference between the first lung sound monitoring frequency and the first reference frequency value, and taking an absolute value of the obtained difference to obtain a first type of lung sound frequency deviation;

[0021] Step S143: respectively acquiring lung sound frequency deviations corresponding to the second type of monitored lung sounds to the dth type of monitored lung sounds, to obtain a frequency deviation of the second type of lung sounds to the dth type of lung sounds;

[0022] Step S144: Calculate the average of the lung sound frequency deviations from the first type to the dth type to obtain a comprehensive lung sound frequency deviation.

[0023] Furthermore, the step S15 further includes the following specific steps:

[0024] Step S151: within the first lung sound monitoring sub-period, obtaining the number of episodes corresponding to the first type of monitored lung sound, obtaining the number of first lung sound utterances; obtaining the number of episodes corresponding to the second type of monitored lung sound, obtaining the number of second lung sound utterances; and so on, obtaining the number of episodes corresponding to the dth type of monitored lung sound, obtaining the number of dth lung sound utterances;

[0025] Step S152: Obtaining the duration of each sound of the first type of monitored lung sound in the first lung sound monitoring sub-period to obtain a plurality of first lung sound onset durations, and averaging the obtained plurality of first lung sound onset durations to obtain an average first lung sound onset duration;

[0026] Step S153: acquiring the average duration of lung sounds corresponding to the second type of monitored lung sounds to the dth type of monitored lung sounds, respectively, to obtain the average duration of lung sounds from the second type to the dth type;

[0027] Step S154: obtaining the time length value corresponding to the first lung sound monitoring sub-period to obtain the lung sound period length value;

[0028] Step S155: Calculating the first lung sound monitoring coefficient by taking the average duration of the first lung sound to the average duration of the d-th lung sound, the number of times the first lung sound is sounded to the d-th lung sound, and the duration of the sub-period;

[0029] The first lung sound monitoring coefficient is calculated using the following formula:

[0030] ;

[0031] Among them, Fjx1 is the first lung sound monitoring coefficient, Fcpi is the average duration of the i-th lung sound, Fszi is the number of times the i-th lung sound is sounded, and Fdc is the value of the lung sound period length;

[0032] Step S156: acquiring the lung sound monitoring coefficients corresponding to the second lung sound monitoring sub-period to the cth lung sound monitoring sub-period respectively, to obtain the second lung sound monitoring coefficient to the cth lung sound monitoring coefficient;

[0033] Step S157: Calculate the average of the first lung sound monitoring coefficient to the cth lung sound monitoring coefficient to obtain the lung sound period monitoring coefficient.

[0034] Furthermore, the step S2 further includes the following specific steps:

[0035] Step S21: Within the time period before lung sound collection of the patient, a time point is randomly selected and named as the first symptom monitoring time point, the time point when lung sound collection of the patient begins is named as the second symptom monitoring time point, and the period between the first symptom monitoring time point and the second symptom monitoring time point is marked as the patient symptom monitoring cycle;

[0036] Step S22: Divide the patient symptom monitoring period into a plurality of monitoring sub-periods of equal duration, and name the divided monitoring sub-periods as the first symptom monitoring sub-period to the ath symptom monitoring sub-period;

[0037] Step S23: Obtain the characteristic time difference between the first period and the ath period;

[0038] Step S24: performing symptom monitoring on the patient in the first symptom monitoring sub-period to obtain a first symptom monitoring coefficient;

[0039] Step S25: acquiring the symptom monitoring coefficients corresponding to the second symptom monitoring sub-period to the ath symptom monitoring sub-period respectively, to obtain the second symptom monitoring coefficient to the ath symptom monitoring coefficient;

[0040] Step S26: Calculating the patient symptom analysis coefficient by combining the first symptom monitoring coefficient to the ath symptom monitoring coefficient and the first period characteristic time difference to the ath period characteristic time difference;

[0041] The patient symptom analysis coefficient is calculated using the following formula:

[0042] ;

[0043] Among them, Hzz is the patient symptom analysis coefficient, Zjxi is the i-th symptom monitoring coefficient, Sczi is the characteristic time difference of the i-th period, and a is the quantity value corresponding to the symptom monitoring sub-period.

[0044] Furthermore, the step S23 further includes the following specific steps:

[0045] Step S231: respectively obtaining the middle time points of the periods corresponding to the first symptom monitoring sub-period to the ath symptom monitoring sub-period, and obtaining the first middle time point to the ath middle time point;

[0046] Step S232: Calculate the time difference between the first intermediate time point and the second symptom monitoring time point to obtain the characteristic time difference of the first time period; calculate the time difference between the second intermediate time point and the second symptom monitoring time point to obtain the characteristic time difference of the second time period; and so on, calculate the time difference between the ath intermediate time point and the second symptom monitoring time point to obtain the characteristic time difference of the ath time period.

[0047] Furthermore, the step S24 further includes the following specific steps:

[0048] Step S241: in the process of monitoring the patient in the first symptom monitoring sub-period, a plurality of key monitoring symptoms are set respectively, and the set plurality of key monitoring symptoms are named as the first key monitoring symptom to the bth key monitoring symptom respectively;

[0049] Step S242: In the first symptom monitoring sub-period, obtain the number of attacks corresponding to the first key monitoring symptom to obtain the number of attacks of the first symptom, obtain the number of attacks corresponding to the second key monitoring symptom to obtain the number of attacks of the second symptom, and so on, obtain the number of attacks corresponding to the bth key monitoring symptom to obtain the number of attacks of the bth symptom,

[0050] Step S243: Obtaining the duration of each attack of the first key monitored symptom in the first symptom monitoring sub-period, obtaining multiple first symptom attack durations, and averaging the obtained multiple first symptom attack durations to obtain an average first symptom attack duration;

[0051] Step S244: respectively obtaining the average duration of symptom onset corresponding to the second key monitored symptom to the bth key monitored symptom, and obtaining the average duration of symptom onset from the second symptom to the bth symptom;

[0052] Step S245: Acquire the time length value corresponding to the first symptom monitoring sub-period to obtain the sub-period duration value;

[0053] Step S246: Calculate the first symptom monitoring coefficient by combining the average duration of the first symptom onset to the average duration of the bth symptom onset, the number of onsets of the first symptom to the number of onsets of the bth symptom, and the duration of the sub-period.

[0054] The first symptom monitoring coefficient is calculated using the following formula:

[0055] ;

[0056] Among them, Zjx1 is the first symptom monitoring coefficient, Scpi is the average duration of the i-th symptom, Fzci is the number of i-th symptom attacks, and Sdc is the sub-period duration value.

[0057] Furthermore, the step S3 further includes the following specific steps:

[0058] Step S31: Acquire the patient's lung sound monitoring data, and obtain the lung sound comprehensive frequency deviation and lung sound period monitoring coefficient according to the patient's lung sound monitoring data;

[0059] Step S32: Obtaining patient symptom analysis coefficient;

[0060] Step S33: Calculating the patient's condition assessment coefficient by combining the patient's symptom analysis coefficient, the lung sound comprehensive frequency deviation, and the lung sound cycle monitoring coefficient;

[0061] The patient's condition assessment coefficient is calculated using the following formula:

[0062] ;

[0063] Among them, Bpg is the patient's condition assessment coefficient, Hzz is the patient's symptom analysis coefficient, Zpl is the comprehensive frequency deviation of lung sounds, and Fzj is the lung sound period monitoring coefficient;

[0064] Step S34: obtaining the patient's condition assessment coefficient threshold value and performing a numerical comparison with the patient's condition assessment coefficient, and performing a diagnosis and assessment of the patient's condition based on the numerical comparison result.

[0065] Furthermore, the step S34 further includes the following specific steps:

[0066] Step S341: respectively obtaining a patient symptom analysis coefficient threshold, a lung sound comprehensive frequency deviation threshold, and a lung sound period monitoring coefficient threshold;

[0067] Step S342: Calculating the patient symptom analysis coefficient threshold, the lung sound comprehensive frequency deviation threshold, and the lung sound period monitoring coefficient threshold to obtain the patient condition assessment coefficient threshold;

[0068] The patient condition assessment coefficient threshold is calculated using the following formula: ;

[0069] Among them, Bpgy is the patient condition assessment coefficient threshold, Hzzy is the patient symptom analysis coefficient threshold, Zply is the lung sound comprehensive frequency deviation threshold, and Fzjy is the lung sound period monitoring coefficient threshold;

[0070] Step S343: When the patient's condition assessment coefficient is greater than or equal to the patient's condition assessment coefficient threshold, it is determined that the patient's lungs have pathological changes;

[0071] Step S344: When the patient's condition assessment coefficient is less than the patient's condition assessment coefficient threshold, it is determined that there is no obvious abnormality in the patient's lungs.

[0072] The disease diagnosis auxiliary system of the micro intelligent lung sound collector includes:

[0073] Lung sound data module: used to obtain the patient's lung sound monitoring cycle, mark multiple lung sound monitoring sub-periods within the patient's lung sound monitoring cycle, and obtain multiple different types of monitored lung sounds. By monitoring the frequency of each type of monitored lung sound, the comprehensive lung sound frequency deviation is obtained. Lung sound monitoring is performed on each lung sound monitoring sub-period to obtain the lung sound cycle monitoring coefficient. The comprehensive lung sound frequency deviation and the lung sound cycle monitoring coefficient are defined as the patient's lung sound monitoring data.

[0074] Symptom data module: used to obtain the patient's symptom monitoring cycle, and mark multiple symptom monitoring sub-periods within the patient's symptom monitoring cycle, respectively obtain the time difference corresponding to each symptom monitoring sub-period, respectively perform clinical symptom analysis on the patient in each symptom monitoring sub-period, respectively obtain the symptom monitoring coefficient corresponding to each symptom monitoring sub-period, and comprehensively analyze the time difference corresponding to each symptom monitoring sub-period and the symptom monitoring coefficient to obtain the patient's symptom analysis coefficient;

[0075] Disease diagnosis module: used to obtain the patient's condition assessment coefficient by analyzing the comprehensive frequency deviation of lung sounds, the lung sound cycle monitoring coefficient and the patient's symptom analysis coefficient, obtain the patient's condition assessment coefficient threshold and perform numerical comparison with the patient's condition assessment coefficient, and perform a diagnosis and assessment of the patient's condition based on the numerical comparison results.

[0076] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0077] 1. The present invention obtains a patient's lung sound monitoring cycle, marks multiple lung sound monitoring sub-periods within the patient's lung sound monitoring cycle, and obtains multiple different types of monitored lung sounds. Frequency monitoring is performed on each type of monitored lung sound to obtain a comprehensive lung sound frequency deviation. Lung sound monitoring is performed on each lung sound monitoring sub-period to obtain a lung sound cycle monitoring coefficient. The comprehensive lung sound frequency deviation and lung sound cycle monitoring coefficient are used as monitoring results to provide diagnostic assistance to medical personnel, effectively improving the clinical utilization efficiency of lung sound data.

[0078] 2. The present invention obtains the patient's condition assessment coefficient by analyzing the comprehensive frequency deviation of lung sounds, the lung sound period monitoring coefficient and the patient's symptom analysis coefficient, and performs a diagnosis and assessment of the patient's condition based on the patient's condition assessment coefficient, which can effectively improve the accuracy of the diagnosis and assessment results. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] To facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0080] Figure 1 It is a diagram of the implementation steps of the present invention;

[0081] Figure 2 This is a block diagram of the overall system of the present invention. DETAILED DESCRIPTION

[0082] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0083] Example 1

[0084] See also Figure 1 The present invention provides a technical solution: a disease diagnosis auxiliary method using a micro intelligent lung sound collector, comprising the following specific steps:

[0085] Step S1: Obtaining a patient's lung sound monitoring cycle, marking multiple lung sound monitoring sub-periods within the patient's lung sound monitoring cycle, and obtaining multiple different types of monitored lung sounds. Frequency monitoring is performed on each type of monitored lung sound to obtain a comprehensive lung sound frequency deviation. Lung sound monitoring is performed on each lung sound monitoring sub-period to obtain a lung sound cycle monitoring coefficient. The comprehensive lung sound frequency deviation and the lung sound cycle monitoring coefficient are defined as the patient's lung sound monitoring data.

[0086] The step S1 further includes the following specific steps:

[0087] Step S11: marking a patient lung sound monitoring cycle within a period of time during which the patient's lung sound is monitored;

[0088] Step S12: Divide the patient's lung sound monitoring period into a plurality of monitoring sub-periods of equal duration, and name the divided multiple monitoring sub-periods as the first lung sound monitoring sub-period to the cth lung sound monitoring sub-period;

[0089] Step S13: During the monitoring of the patient in the first lung sound monitoring sub-period, a plurality of different types of monitored lung sounds are set, and the set plurality of different types of monitored lung sounds are named first type monitored lung sounds to dth type monitored lung sounds, respectively;

[0090] Step S14: monitoring the patient's lung sound frequency to obtain a comprehensive frequency deviation of lung sounds;

[0091] The step S14 further includes the following specific steps:

[0092] Step S141: Acquire multiple audio clips of the first type of monitored lung sound within the patient's lung sound monitoring cycle to obtain multiple first lung sound audio clips, acquire the lung sound frequency of each first lung sound audio clip to obtain multiple monitored lung sound frequency values, and average the obtained multiple lung sound frequency values ​​to obtain the first lung sound monitoring frequency;

[0093] Step S142: Obtaining a reference frequency value corresponding to the first type of monitored lung sound to obtain a first reference frequency value, calculating a difference between the first lung sound monitoring frequency and the first reference frequency value, and taking an absolute value of the obtained difference to obtain a first type of lung sound frequency deviation;

[0094] Step S143: respectively acquiring lung sound frequency deviations corresponding to the second type of monitored lung sounds to the dth type of monitored lung sounds, to obtain a frequency deviation of the second type of lung sounds to the dth type of lung sounds;

[0095] Step S144: averaging the lung sound frequency deviations from the first type to the dth type to obtain a comprehensive lung sound frequency deviation.

[0096] Step S15: performing lung sound monitoring for each lung sound monitoring sub-period to obtain a lung sound cycle monitoring coefficient;

[0097] The step S15 further includes the following specific steps:

[0098] Step S151: In the first lung sound monitoring sub-period, the number of episodes corresponding to the first type of monitored lung sound is obtained, and the number of first lung sound sounds is obtained. The number of episodes corresponding to the second type of monitored lung sound is obtained, and the number of second lung sound sounds is obtained. Similarly, the number of episodes corresponding to the dth type of monitored lung sound is obtained, and the number of dth lung sound sounds is obtained.

[0099] Step S152: Obtaining the duration of each sound of the first type of monitored lung sound in the first lung sound monitoring sub-period to obtain a plurality of first lung sound onset durations, and averaging the obtained plurality of first lung sound onset durations to obtain an average first lung sound onset duration;

[0100] Step S153: acquiring the average duration of lung sounds corresponding to the second type of monitored lung sounds to the dth type of monitored lung sounds, respectively, to obtain the average duration of lung sounds from the second type to the dth type;

[0101] Step S154: obtaining the time length value corresponding to the first lung sound monitoring sub-period to obtain the lung sound period length value;

[0102] Step S155: Calculating the first lung sound monitoring coefficient by taking the average duration of the first lung sound to the average duration of the d-th lung sound, the number of times the first lung sound is sounded to the d-th lung sound, and the duration of the sub-period;

[0103] The first lung sound monitoring coefficient is calculated using the following formula:

[0104] ;

[0105] Among them, Fjx1 is the first lung sound monitoring coefficient, Fcpi is the average duration of the i-th lung sound, Fszi is the number of times the i-th lung sound is sounded, and Fdc is the value of the lung sound period length;

[0106] Step S156: acquiring the lung sound monitoring coefficients corresponding to the second lung sound monitoring sub-period to the cth lung sound monitoring sub-period respectively, to obtain the second lung sound monitoring coefficient to the cth lung sound monitoring coefficient;

[0107] Step S157: averaging the first lung sound monitoring coefficient to the cth lung sound monitoring coefficient to obtain a lung sound cycle monitoring coefficient;

[0108] Step S16: defining the lung sound comprehensive frequency deviation and the lung sound period monitoring coefficient as the patient's lung sound monitoring data;

[0109] Step S2: Obtain the patient's symptom monitoring period, and mark multiple symptom monitoring sub-periods within the patient's symptom monitoring period, respectively obtain the period characteristic time difference corresponding to each symptom monitoring sub-period, respectively perform clinical symptom analysis on the patient in each symptom monitoring sub-period, obtain the symptom monitoring coefficient corresponding to each symptom monitoring sub-period, and comprehensively analyze the period characteristic time difference and symptom monitoring coefficient corresponding to each symptom monitoring sub-period to obtain the patient's symptom analysis coefficient;

[0110] The step S2 further includes the following specific steps:

[0111] Step S21: Within the time period before lung sound collection of the patient, a time point is randomly selected and named as the first symptom monitoring time point, the time point when lung sound collection of the patient begins is named as the second symptom monitoring time point, and the period between the first symptom monitoring time point and the second symptom monitoring time point is marked as the patient symptom monitoring cycle;

[0112] Step S22: Divide the patient symptom monitoring period into a plurality of monitoring sub-periods of equal duration, and name the divided monitoring sub-periods as the first symptom monitoring sub-period to the ath symptom monitoring sub-period;

[0113] Step S23: Obtain the characteristic time difference between the first period and the ath period;

[0114] The step S23 further includes the following specific steps:

[0115] Step S231: respectively obtaining the middle time points of the periods corresponding to the first symptom monitoring sub-period to the ath symptom monitoring sub-period, and obtaining the first middle time point to the ath middle time point;

[0116] Step S232: Calculate the time difference between the first intermediate time point and the second symptom monitoring time point to obtain the characteristic time difference of the first period; calculate the time difference between the second intermediate time point and the second symptom monitoring time point to obtain the characteristic time difference of the second period; and so on, calculate the time difference between the ath intermediate time point and the second symptom monitoring time point to obtain the characteristic time difference of the ath period;

[0117] Step S24: Perform symptom monitoring on the patient in the first symptom monitoring sub-period to obtain a first symptom monitoring coefficient.

[0118] The step S24 further includes the following specific steps:

[0119] Step S241: in the process of monitoring the patient in the first symptom monitoring sub-period, a plurality of key monitoring symptoms are set respectively, and the set plurality of key monitoring symptoms are named as the first key monitoring symptom to the bth key monitoring symptom respectively;

[0120] Step S242: In the first symptom monitoring sub-period, obtain the number of attacks corresponding to the first key monitoring symptom to obtain the number of attacks of the first symptom, obtain the number of attacks corresponding to the second key monitoring symptom to obtain the number of attacks of the second symptom, and so on, obtain the number of attacks corresponding to the bth key monitoring symptom to obtain the number of attacks of the bth symptom,

[0121] Step S243: Obtaining the duration of each attack of the first key monitored symptom in the first symptom monitoring sub-period, obtaining multiple first symptom attack durations, and averaging the obtained multiple first symptom attack durations to obtain an average first symptom attack duration;

[0122] Step S244: respectively obtaining the average duration of symptom onset corresponding to the second key monitored symptom to the bth key monitored symptom, and obtaining the average duration of symptom onset from the second symptom to the bth symptom;

[0123] Step S245: Acquire the time length value corresponding to the first symptom monitoring sub-period to obtain the sub-period duration value;

[0124] Step S246: Calculate the first symptom monitoring coefficient by combining the average duration of the first symptom onset to the average duration of the bth symptom onset, the number of onsets of the first symptom to the number of onsets of the bth symptom, and the duration of the sub-period.

[0125] The first symptom monitoring coefficient is calculated using the following formula:

[0126] ;

[0127] Among them, Zjx1 is the first symptom monitoring coefficient, Scpi is the average duration of the i-th symptom, Fzci is the number of i-th symptom attacks, and Sdc is the duration value of the sub-period;

[0128] Step S25: acquiring the symptom monitoring coefficients corresponding to the second symptom monitoring sub-period to the ath symptom monitoring sub-period respectively, to obtain the second symptom monitoring coefficient to the ath symptom monitoring coefficient;

[0129] Step S26: Calculating the patient symptom analysis coefficient by combining the first symptom monitoring coefficient to the ath symptom monitoring coefficient and the first period characteristic time difference to the ath period characteristic time difference;

[0130] The patient symptom analysis coefficient is calculated using the following formula:

[0131] ;

[0132] Among them, Hzz is the patient symptom analysis coefficient, Zjxi is the i-th symptom monitoring coefficient, Sczi is the characteristic time difference of the i-th period, and a is the quantity value corresponding to the symptom monitoring sub-period.

[0133] Step S3: Obtain the patient's condition assessment coefficient by analyzing the comprehensive frequency deviation of lung sounds, the lung sound cycle monitoring coefficient, and the patient's symptom analysis coefficient, obtain the patient's condition assessment coefficient threshold and perform numerical comparison with the patient's condition assessment coefficient, and perform a diagnosis and assessment of the patient's condition based on the numerical comparison result.

[0134] The step S3 further includes the following specific steps:

[0135] Step S31: Acquire the patient's lung sound monitoring data, and obtain the lung sound comprehensive frequency deviation and lung sound period monitoring coefficient according to the patient's lung sound monitoring data;

[0136] Step S32: Obtaining patient symptom analysis coefficient;

[0137] Step S33: Calculating the patient's condition assessment coefficient by combining the patient's symptom analysis coefficient, the lung sound comprehensive frequency deviation, and the lung sound cycle monitoring coefficient;

[0138] The patient's condition assessment coefficient is calculated using the following formula:

[0139] ;

[0140] Among them, Bpg is the patient's condition assessment coefficient, Hzz is the patient's symptom analysis coefficient, Zpl is the comprehensive frequency deviation of lung sounds, and Fzj is the lung sound period monitoring coefficient;

[0141] Step S34: obtaining the patient's condition assessment coefficient threshold value and performing a numerical comparison with the patient's condition assessment coefficient, and performing a diagnosis and assessment of the patient's condition based on the numerical comparison result.

[0142] The step S34 further includes the following specific steps:

[0143] Step S341: respectively obtaining a patient symptom analysis coefficient threshold, a lung sound comprehensive frequency deviation threshold, and a lung sound period monitoring coefficient threshold;

[0144] Step S342: Calculating the patient symptom analysis coefficient threshold, the lung sound comprehensive frequency deviation threshold, and the lung sound period monitoring coefficient threshold to obtain the patient condition assessment coefficient threshold;

[0145] The patient condition assessment coefficient threshold is calculated using the following formula: ;

[0146] Among them, Bpgy is the patient condition assessment coefficient threshold, Hzzy is the patient symptom analysis coefficient threshold, Zply is the lung sound comprehensive frequency deviation threshold, and Fzjy is the lung sound period monitoring coefficient threshold;

[0147] Step S343: When the patient's condition assessment coefficient is greater than or equal to the patient's condition assessment coefficient threshold, it is determined that the patient's lungs have pathological changes;

[0148] Step S344: When the patient's condition assessment coefficient is less than the patient's condition assessment coefficient threshold, it is determined that there is no obvious abnormality in the patient's lungs.

[0149] In this application, if a corresponding calculation formula appears, the above calculation formula is dimensionless and its numerical calculation is performed. The weight coefficient, proportional coefficient and other coefficients in the formula are set to a result value obtained by quantifying each parameter. Regarding the size of the weight coefficient and the proportional coefficient, as long as it does not affect the proportional relationship between the parameter and the result value, it is acceptable.

[0150] Example 2

[0151] See also Figure 2 Based on another concept of the same invention, a disease diagnosis auxiliary system of a micro-intelligent lung sound collector is proposed, including a lung sound data module, a symptom data module, a disease diagnosis module and a server. The lung sound data module, symptom data module and disease diagnosis module are respectively connected to the server, and the server controls the lung sound data module, symptom data module and disease diagnosis module respectively.

[0152] The lung sound data module obtains the patient's lung sound monitoring cycle, marks multiple lung sound monitoring sub-periods within the patient's lung sound monitoring cycle, and obtains multiple different types of monitored lung sounds. The module obtains the comprehensive lung sound frequency deviation by frequency monitoring each type of monitored lung sound. The module monitors each lung sound monitoring sub-period to obtain the lung sound cycle monitoring coefficient. The comprehensive lung sound frequency deviation and the lung sound cycle monitoring coefficient are defined as the patient's lung sound monitoring data.

[0153] During the period of lung sound monitoring of the patient, mark a lung sound monitoring cycle of the patient;

[0154] Divide the patient's lung sound monitoring period into a plurality of monitoring sub-periods of equal duration, and name the divided multiple monitoring sub-periods as the first lung sound monitoring sub-period to the cth lung sound monitoring sub-period;

[0155] During monitoring of the patient in the first lung sound monitoring sub-period, several different types of monitored lung sounds are set, and the several different types of monitored lung sounds are named first type monitored lung sounds to dth type monitored lung sounds, respectively;

[0156] It should be noted here that:

[0157] In this application, d referred to herein is the quantity value corresponding to the type of monitored lung sound, and d is an integer greater than 0;

[0158] In this application, the monitored lung sounds designed here are all lung sounds related to lung diseases. The first type of monitored lung sounds involved here can be wheezing, the second type of monitored lung sounds can be dry rales, the third type of monitored lung sounds can be wet rales... The dth type of monitored lung sounds can be pleural friction sounds.

[0159] Monitor the patient's lung sound frequency and obtain the comprehensive frequency deviation of lung sounds;

[0160] The details are as follows:

[0161] Acquiring multiple audio clips of the first type of monitored lung sound within a patient's lung sound monitoring cycle to obtain multiple first lung sound audio clips, acquiring the lung sound frequency of each first lung sound audio clip to obtain multiple monitored lung sound frequency values, and averaging the obtained multiple lung sound frequency values ​​to obtain a first lung sound monitoring frequency;

[0162] Obtaining a reference frequency value corresponding to the first type of monitored lung sound to obtain a first reference frequency value, calculating a difference between the first lung sound monitoring frequency and the first reference frequency value, and taking an absolute value of the obtained difference to obtain a first type of lung sound frequency deviation;

[0163] Repeat the process of obtaining the first type of lung sound frequency deviation, and obtain the lung sound frequency deviations corresponding to the second type of monitored lung sounds to the dth type of monitored lung sounds, respectively, to obtain the second type of lung sound frequency deviation to the dth type of lung sound frequency deviation;

[0164] Calculate the average of the first type of lung sound frequency deviation to the dth type of lung sound frequency deviation to obtain the comprehensive lung sound frequency deviation;

[0165] Perform lung sound monitoring on each lung sound monitoring sub-period to obtain the lung sound cycle monitoring coefficient;

[0166] The details are as follows:

[0167] In the first lung sound monitoring sub-period, the number of episodes corresponding to the first type of monitored lung sound is obtained, and the number of first lung sound sounds is obtained. The number of episodes corresponding to the second type of monitored lung sound is obtained, and the number of second lung sound sounds is obtained. Similarly, the number of episodes corresponding to the dth type of monitored lung sound is obtained, and the number of dth lung sound sounds is obtained.

[0168] Obtaining the duration of each sound of the first type of monitored lung sound in the first lung sound monitoring sub-period respectively to obtain multiple first lung sound onset durations, and averaging the obtained multiple first lung sound onset durations to obtain an average first lung sound onset duration;

[0169] Repeat the process of obtaining the average duration of the first lung sound, and obtain the average duration of the lung sounds corresponding to the second type of monitored lung sounds to the dth type of monitored lung sounds, and obtain the average duration of the second lung sound to the dth lung sound;

[0170] Acquire the time length value corresponding to the first lung sound monitoring sub-period to obtain the lung sound period length value;

[0171] The first lung sound monitoring coefficient is obtained by calculating the average duration of the first lung sound to the average duration of the dth lung sound, the number of times the first lung sound is uttered to the dth lung sound, and the duration of the sub-period;

[0172] The first lung sound monitoring coefficient is calculated using the following formula:

[0173] ;

[0174] Among them, Fjx1 is the first lung sound monitoring coefficient, Fcpi is the average duration of the i-th lung sound, Fszi is the number of times the i-th lung sound is sounded, and Fdc is the value of the lung sound period length;

[0175] It should be noted here that:

[0176] In the present application, the i-th average lung sound duration involved herein may be any one of the average lung sound durations from the first average lung sound duration to the average lung sound duration of the d-th average lung sound, and the i-th number of lung sound sounds involved herein may be any one of the number of lung sound sounds from the first average lung sound duration to the d-th average lung sound duration;

[0177] Repeat the process of obtaining the first lung sound monitoring coefficient, and obtain the lung sound monitoring coefficients corresponding to the second lung sound monitoring sub-period to the cth lung sound monitoring sub-period respectively, to obtain the second lung sound monitoring coefficient to the cth lung sound monitoring coefficient;

[0178] The lung sound cycle monitoring coefficient is obtained by averaging the first lung sound monitoring coefficient to the cth lung sound monitoring coefficient;

[0179] The lung sound comprehensive frequency deviation and lung sound period monitoring coefficient are defined as the patient's lung sound monitoring data;

[0180] The symptom data module obtains the patient's symptom monitoring cycle and marks multiple symptom monitoring sub-periods within the patient's symptom monitoring cycle, obtains the time difference corresponding to each symptom monitoring sub-period, performs clinical symptom analysis on the patient in each symptom monitoring sub-period, obtains the symptom monitoring coefficient corresponding to each symptom monitoring sub-period, and comprehensively analyzes the time difference corresponding to each symptom monitoring sub-period and the symptom monitoring coefficient to obtain the patient's symptom analysis coefficient;

[0181] In the time period before lung sound collection of the patient, a time point is randomly selected and named as the first symptom monitoring time point, the time point when lung sound collection of the patient begins is named as the second symptom monitoring time point, and the period between the first symptom monitoring time point and the second symptom monitoring time point is marked as the patient symptom monitoring cycle;

[0182] Divide the patient's symptom monitoring period into a number of monitoring sub-periods of equal duration, and name the divided multiple monitoring sub-periods as the first symptom monitoring sub-period to the ath symptom monitoring sub-period;

[0183] Obtain the middle time points of the periods corresponding to the first symptom monitoring sub-period to the ath symptom monitoring sub-period respectively, and obtain the first middle time point to the ath middle time point;

[0184] Calculate the time difference between the first intermediate time point and the second symptom monitoring time point to obtain the characteristic time difference of the first time period; calculate the time difference between the second intermediate time point and the second symptom monitoring time point to obtain the characteristic time difference of the second time period; and so on, calculate the time difference between the ath intermediate time point and the second symptom monitoring time point to obtain the characteristic time difference of the ath time period.

[0185] It should be noted here that:

[0186] In this application, a designed here is a numerical value corresponding to the symptom monitoring sub-period, and a is an integer greater than 0.

[0187] Performing symptom monitoring on patients in the first symptom monitoring sub-period to obtain a first symptom monitoring coefficient;

[0188] The details are as follows:

[0189] In the process of monitoring the patient in the first symptom monitoring sub-period, a number of key monitoring symptoms are set, and the set key monitoring symptoms are named as the first key monitoring symptom to the bth key monitoring symptom respectively;

[0190] It should be noted here that:

[0191] In this application, b referred to herein is the numerical value corresponding to the key monitored symptom, and b is an integer greater than 0;

[0192] In this application, the key monitoring symptoms designed here are all symptoms related to lung diseases. The first key symptom involved here can be cough, the second key symptom can be difficulty breathing, the third key monitoring symptom can be chest pain... The bth key monitoring symptom can be fever.

[0193] In the first symptom monitoring sub-period, the number of attacks corresponding to the first key monitoring symptom is obtained, and the number of attacks of the first symptom is obtained. The number of attacks corresponding to the second key monitoring symptom is obtained, and the number of attacks of the second symptom is obtained. Similarly, the number of attacks corresponding to the bth key monitoring symptom is obtained, and the number of attacks of the bth symptom is obtained.

[0194] Obtaining the duration of each attack of the first key monitored symptom in the first symptom monitoring sub-period respectively to obtain multiple first symptom attack durations, and averaging the obtained multiple first symptom attack durations to obtain an average first symptom attack duration;

[0195] Repeat the process of obtaining the average onset duration of the first symptom, and obtain the average onset duration of the symptoms corresponding to the second key monitoring symptom to the bth key monitoring symptom, and obtain the average onset duration of the second symptom to the average onset duration of the bth symptom.

[0196] Obtain the time length value corresponding to the first symptom monitoring sub-period to obtain the sub-period duration value;

[0197] The first symptom monitoring coefficient is obtained by calculating the average duration of the first symptom onset to the average duration of the bth symptom onset, the number of first symptom onset to the number of bth symptom onset, and the duration of the sub-period;

[0198] The first symptom monitoring coefficient is calculated using the following formula:

[0199] ;

[0200] Among them, Zjx1 is the first symptom monitoring coefficient, Scpi is the average duration of the i-th symptom, Fzci is the number of i-th symptom attacks, and Sdc is the duration value of the sub-period;

[0201] It should be noted here that:

[0202] In the present application, the average duration of the i-th symptom onset involved here can be any one of the average duration of the 1st symptom onset to the average duration of the b-th symptom onset, and the number of i-th symptom onsets involved here can be any one of the number of symptom onsets from the first symptom onset to the b-th symptom onset.

[0203] Repeat the process of obtaining the first symptom monitoring coefficient, and obtain the symptom monitoring coefficients corresponding to the second symptom monitoring sub-period to the ath symptom monitoring sub-period respectively, to obtain the second symptom monitoring coefficients to the ath symptom monitoring coefficients;

[0204] The patient symptom analysis coefficient is obtained by calculating the first symptom monitoring coefficient to the ath symptom monitoring coefficient and the first period characteristic time difference to the ath period characteristic time difference;

[0205] The patient symptom analysis coefficient is calculated using the following formula:

[0206] ;

[0207] Among them, Hzz is the patient symptom analysis coefficient, Zjxi is the i-th symptom monitoring coefficient, Sczi is the characteristic time difference of the i-th period, and a is the quantity value corresponding to the symptom monitoring sub-period.

[0208] It should be noted here that:

[0209] In this application, the i-th symptom monitoring coefficient involved here can be any one of the symptom monitoring coefficients from the first symptom monitoring coefficient to the a-th symptom monitoring coefficient, and the i-th time period characteristic time difference designed here can be any one of the time period characteristic time difference from the first time period characteristic time difference to the a-th time period characteristic time difference.

[0210] The disease diagnosis module obtains the patient's condition assessment coefficient by analyzing the comprehensive frequency deviation of lung sounds, the lung sound cycle monitoring coefficient, and the patient's symptom analysis coefficient. The obtained patient's condition assessment coefficient threshold is compared with the patient's condition assessment coefficient, and the patient's condition is diagnosed and assessed based on the numerical comparison results.

[0211] The details are as follows:

[0212] Acquire the patient's lung sound monitoring data, and obtain the lung sound comprehensive frequency deviation and the lung sound period monitoring coefficient according to the patient's lung sound monitoring data;

[0213] Obtain patient symptom analysis coefficients;

[0214] The patient's condition assessment coefficient is obtained by calculating the patient's symptom analysis coefficient, lung sound comprehensive frequency deviation and lung sound cycle monitoring coefficient;

[0215] The patient's condition assessment coefficient is calculated using the following formula:

[0216] ;

[0217] Among them, Bpg is the patient condition assessment coefficient, Hzz is the patient symptom analysis coefficient, Zpl is the comprehensive frequency deviation of lung sounds, and Fzj is the lung sound period monitoring coefficient.

[0218] Obtaining the patient's condition assessment coefficient threshold and performing numerical comparison with the patient's condition assessment coefficient, and performing a diagnosis and assessment of the patient's condition based on the numerical comparison result;

[0219] The details are as follows:

[0220] Obtain the patient symptom analysis coefficient threshold, lung sound comprehensive frequency deviation threshold, and lung sound cycle monitoring coefficient threshold respectively;

[0221] It should be noted here that:

[0222] The patient symptom analysis coefficient threshold, lung sound comprehensive frequency deviation threshold, and lung sound cycle monitoring coefficient threshold designed here are the maximum patient symptom analysis coefficient, maximum lung sound comprehensive frequency deviation, and maximum lung sound cycle monitoring coefficient corresponding to patients with no obvious lung abnormalities.

[0223] The patient's condition assessment coefficient threshold is obtained by calculating the patient's symptom analysis coefficient threshold, the lung sound comprehensive frequency deviation threshold, and the lung sound cycle monitoring coefficient threshold;

[0224] The patient condition assessment coefficient threshold is calculated using the following formula: ;

[0225] Among them, Bpgy is the patient condition assessment coefficient threshold, Hzzy is the patient symptom analysis coefficient threshold, Zply is the lung sound comprehensive frequency deviation threshold, and Fzjy is the lung sound period monitoring coefficient threshold;

[0226] When the patient's condition assessment coefficient is greater than or equal to the patient's condition assessment coefficient threshold, it is determined that the patient's lungs have pathological changes;

[0227] When the patient's condition assessment coefficient is less than the patient's condition assessment coefficient threshold, it is judged that there is no obvious abnormality in the patient's lungs.

[0228] It should be noted here that:

[0229] In this application, the pathological changes herein refer to abnormal changes in the structure and function of tissues, organs or cells in an organism caused by factors such as disease or injury.

[0230] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A disease diagnosis auxiliary method using a miniature intelligent lung sound collector, characterized in that: include: Step S1: Obtaining a patient's lung sound monitoring cycle, marking multiple lung sound monitoring sub-periods within the patient's lung sound monitoring cycle, and obtaining multiple different types of monitored lung sounds. Frequency monitoring is performed on each type of monitored lung sound to obtain a comprehensive lung sound frequency deviation. Lung sound monitoring is performed on each lung sound monitoring sub-period to obtain a lung sound cycle monitoring coefficient. The comprehensive lung sound frequency deviation and the lung sound cycle monitoring coefficient are defined as the patient's lung sound monitoring data. Step S2: Obtain the patient's symptom monitoring period, and mark multiple symptom monitoring sub-periods within the patient's symptom monitoring period, respectively obtain the period characteristic time difference corresponding to each symptom monitoring sub-period, respectively perform clinical symptom analysis on the patient in each symptom monitoring sub-period, obtain the symptom monitoring coefficient corresponding to each symptom monitoring sub-period, and comprehensively analyze the period characteristic time difference and symptom monitoring coefficient corresponding to each symptom monitoring sub-period to obtain the patient's symptom analysis coefficient; Step S3: Obtain the patient condition assessment coefficient by analyzing the comprehensive frequency deviation of lung sounds, the lung sound cycle monitoring coefficient, and the patient symptom analysis coefficient, obtain the patient condition assessment coefficient threshold and perform numerical comparison with the patient condition assessment coefficient, and perform a diagnosis and assessment of the patient's condition based on the numerical comparison result.

2. The disease diagnosis auxiliary method of the micro intelligent lung sound collector according to claim 1 is characterized in that: The step S1 further includes the following specific steps: Step S11: marking a patient lung sound monitoring cycle within a period of time during which the patient's lung sound is monitored; Step S12: Divide the patient's lung sound monitoring period into a plurality of monitoring sub-periods of equal duration, and name the divided multiple monitoring sub-periods as the first lung sound monitoring sub-period to the cth lung sound monitoring sub-period; Step S13: during the lung sound monitoring of the patient in the first lung sound monitoring sub-period, setting a plurality of different types of monitored lung sounds, and naming the plurality of different types of monitored lung sounds as first type monitored lung sounds to dth type monitored lung sounds, respectively; Step S14: monitoring the patient's lung sound frequency to obtain a comprehensive lung sound frequency deviation; Step S15: performing lung sound monitoring for each lung sound monitoring sub-period to obtain a lung sound cycle monitoring coefficient; Step S16: defining the lung sound comprehensive frequency deviation and the lung sound period monitoring coefficient as the patient's lung sound monitoring data.

3. The disease diagnosis auxiliary method of the micro intelligent lung sound collector according to claim 2 is characterized in that: The step S14 further includes the following specific steps: Step S141: Acquire multiple audio clips of the first type of monitored lung sound within the patient's lung sound monitoring cycle to obtain multiple first lung sound audio clips, acquire the lung sound frequency of each first lung sound audio clip to obtain multiple monitored lung sound frequency values, and average the obtained multiple lung sound frequency values ​​to obtain the first lung sound monitoring frequency; Step S142: Obtaining a reference frequency value corresponding to the first type of monitored lung sound to obtain a first reference frequency value, calculating a difference between the first lung sound monitoring frequency and the first reference frequency value, and taking an absolute value of the obtained difference to obtain a first type of lung sound frequency deviation; Step S143: respectively acquiring lung sound frequency deviations corresponding to the second type of monitored lung sounds to the dth type of monitored lung sounds, to obtain a frequency deviation of the second type of lung sounds to the dth type of lung sounds; Step S144: Calculate the average of the lung sound frequency deviations from the first type to the dth type to obtain a comprehensive lung sound frequency deviation.

4. The disease diagnosis auxiliary method of the micro intelligent lung sound collector according to claim 2 is characterized in that: The step S15 further includes the following specific steps: Step S151: within the first lung sound monitoring sub-period, obtaining the number of episodes corresponding to the first type of monitored lung sound, obtaining the number of first lung sound utterances; obtaining the number of episodes corresponding to the second type of monitored lung sound, obtaining the number of second lung sound utterances; and so on, obtaining the number of episodes corresponding to the dth type of monitored lung sound, obtaining the number of dth lung sound utterances; Step S152: Obtaining the duration of each sound of the first type of monitored lung sound in the first lung sound monitoring sub-period to obtain a plurality of first lung sound onset durations, and averaging the obtained plurality of first lung sound onset durations to obtain an average first lung sound onset duration; Step S153: acquiring the average duration of lung sounds corresponding to the second type of monitored lung sounds to the dth type of monitored lung sounds, respectively, to obtain the average duration of lung sounds from the second type to the dth type; Step S154: obtaining the time length value corresponding to the first lung sound monitoring sub-period to obtain the lung sound period length value; Step S155: Calculating the first lung sound monitoring coefficient by taking the average duration of the first lung sound to the average duration of the d-th lung sound, the number of times the first lung sound is sounded to the d-th lung sound, and the duration of the sub-period; The first lung sound monitoring coefficient is calculated using the following formula: ； Among them, Fjx1 is the first lung sound monitoring coefficient, Fcpi is the average duration of the i-th lung sound, Fszi is the number of times the i-th lung sound is sounded, and Fdc is the value of the lung sound period length; Step S156: acquiring the lung sound monitoring coefficients corresponding to the second lung sound monitoring sub-period to the cth lung sound monitoring sub-period respectively, to obtain the second lung sound monitoring coefficient to the cth lung sound monitoring coefficient; Step S157: Calculate the average of the first lung sound monitoring coefficient to the cth lung sound monitoring coefficient to obtain the lung sound period monitoring coefficient.

5. The disease diagnosis auxiliary method of the miniature intelligent lung sound collector according to claim 1 is characterized in that: The step S2 further includes the following specific steps: Step S21: Within the time period before lung sound collection of the patient, a time point is randomly selected and named as the first symptom monitoring time point, the time point when lung sound collection of the patient begins is named as the second symptom monitoring time point, and the period between the first symptom monitoring time point and the second symptom monitoring time point is marked as the patient symptom monitoring cycle; Step S22: Divide the patient symptom monitoring period into a plurality of monitoring sub-periods of equal duration, and name the divided monitoring sub-periods as the first symptom monitoring sub-period to the ath symptom monitoring sub-period; Step S23: Obtain the characteristic time difference between the first period and the ath period; Step S24: performing symptom monitoring on the patient in the first symptom monitoring sub-period to obtain a first symptom monitoring coefficient; Step S25: acquiring the symptom monitoring coefficients corresponding to the second symptom monitoring sub-period to the ath symptom monitoring sub-period respectively, to obtain the second symptom monitoring coefficient to the ath symptom monitoring coefficient; Step S26: Calculating the patient symptom analysis coefficient by combining the first symptom monitoring coefficient to the ath symptom monitoring coefficient and the first period characteristic time difference to the ath period characteristic time difference; The patient symptom analysis coefficient is calculated using the following formula: ； Among them, Hzz is the patient symptom analysis coefficient, Zjxi is the i-th symptom monitoring coefficient, Sczi is the characteristic time difference of the i-th period, and a is the quantity value corresponding to the symptom monitoring sub-period.

6. The disease diagnosis auxiliary method of the micro intelligent lung sound collector according to claim 5 is characterized in that: The step S23 further includes the following specific steps: Step S231: respectively obtaining the middle time points of the periods corresponding to the first symptom monitoring sub-period to the ath symptom monitoring sub-period, and obtaining the first middle time point to the ath middle time point; Step S232: Calculate the time difference between the first intermediate time point and the second symptom monitoring time point to obtain the characteristic time difference of the first time period; calculate the time difference between the second intermediate time point and the second symptom monitoring time point to obtain the characteristic time difference of the second time period; and so on, calculate the time difference between the ath intermediate time point and the second symptom monitoring time point to obtain the characteristic time difference of the ath time period.

7. The disease diagnosis auxiliary method of the micro intelligent lung sound collector according to claim 5 is characterized in that: The step S24 further includes the following specific steps: Step S241: in the process of monitoring the patient in the first symptom monitoring sub-period, a plurality of key monitoring symptoms are set respectively, and the set plurality of key monitoring symptoms are named as the first key monitoring symptom to the bth key monitoring symptom respectively; Step S242: In the first symptom monitoring sub-period, obtain the number of attacks corresponding to the first key monitoring symptom to obtain the number of attacks of the first symptom, obtain the number of attacks corresponding to the second key monitoring symptom to obtain the number of attacks of the second symptom, and so on, obtain the number of attacks corresponding to the bth key monitoring symptom to obtain the number of attacks of the bth symptom, Step S243: Obtaining the duration of each attack of the first key monitored symptom in the first symptom monitoring sub-period, obtaining multiple first symptom attack durations, and averaging the obtained multiple first symptom attack durations to obtain an average first symptom attack duration; Step S244: respectively obtaining the average duration of symptom onset corresponding to the second key monitored symptom to the bth key monitored symptom, and obtaining the average duration of symptom onset from the second symptom to the bth symptom; Step S245: Acquire the time length value corresponding to the first symptom monitoring sub-period to obtain the sub-period duration value; Step S246: Calculate the first symptom monitoring coefficient by combining the average duration of the first symptom onset to the average duration of the bth symptom onset, the number of onsets of the first symptom to the number of onsets of the bth symptom, and the duration of the sub-period. The first symptom monitoring coefficient is calculated using the following formula: ； Among them, Zjx1 is the first symptom monitoring coefficient, Scpi is the average duration of the i-th symptom, Fzci is the number of i-th symptom attacks, and Sdc is the sub-period duration value.

8. The disease diagnosis auxiliary method of the micro intelligent lung sound collector according to claim 1 is characterized in that: The step S3 further includes the following specific steps: Step S31: Acquire the patient's lung sound monitoring data, and obtain the lung sound comprehensive frequency deviation and lung sound period monitoring coefficient according to the patient's lung sound monitoring data; Step S32: Obtaining patient symptom analysis coefficient; Step S33: Calculating the patient's condition assessment coefficient by combining the patient's symptom analysis coefficient, the lung sound comprehensive frequency deviation, and the lung sound cycle monitoring coefficient; The patient's condition assessment coefficient is calculated using the following formula: ； Among them, Bpg is the patient's condition assessment coefficient, Hzz is the patient's symptom analysis coefficient, Zpl is the comprehensive frequency deviation of lung sounds, and Fzj is the lung sound period monitoring coefficient; Step S34: obtaining the patient's condition assessment coefficient threshold value and performing a numerical comparison with the patient's condition assessment coefficient, and performing a diagnosis and assessment of the patient's condition based on the numerical comparison result.

9. The disease diagnosis auxiliary method using the miniature intelligent lung sound collector according to claim 8, characterized in that: The step S34 further includes the following specific steps: Step S341: respectively obtaining a patient symptom analysis coefficient threshold, a lung sound comprehensive frequency deviation threshold, and a lung sound period monitoring coefficient threshold; Step S342: Calculating the patient symptom analysis coefficient threshold, the lung sound comprehensive frequency deviation threshold, and the lung sound period monitoring coefficient threshold to obtain the patient condition assessment coefficient threshold; Step S343: When the patient's condition assessment coefficient is greater than or equal to the patient's condition assessment coefficient threshold, it is determined that the patient's lungs have pathological changes; Step S344: When the patient's condition assessment coefficient is less than the patient's condition assessment coefficient threshold, it is determined that there is no obvious abnormality in the patient's lungs.

10. A disease diagnosis assistance system for a micro intelligent lung sound collector, applicable to a disease diagnosis assistance method for a micro intelligent lung sound collector according to any one of claims 1 to 9, characterized in that: The disease diagnosis auxiliary system comprises: Lung sound data module: used to obtain the patient's lung sound monitoring cycle, mark multiple lung sound monitoring sub-periods within the patient's lung sound monitoring cycle, and obtain multiple different types of monitored lung sounds. By monitoring the frequency of each type of monitored lung sound, the comprehensive lung sound frequency deviation is obtained. Lung sound monitoring is performed on each lung sound monitoring sub-period to obtain the lung sound cycle monitoring coefficient. The comprehensive lung sound frequency deviation and the lung sound cycle monitoring coefficient are defined as the patient's lung sound monitoring data. Symptom data module: used to obtain the patient's symptom monitoring cycle, and mark multiple symptom monitoring sub-periods within the patient's symptom monitoring cycle, respectively obtain the time difference corresponding to each symptom monitoring sub-period, respectively perform clinical symptom analysis on the patient in each symptom monitoring sub-period, respectively obtain the symptom monitoring coefficient corresponding to each symptom monitoring sub-period, and comprehensively analyze the time difference corresponding to each symptom monitoring sub-period and the symptom monitoring coefficient to obtain the patient's symptom analysis coefficient; Disease diagnosis module: used to obtain the patient's condition assessment coefficient by analyzing the comprehensive frequency deviation of lung sounds, the lung sound cycle monitoring coefficient and the patient's symptom analysis coefficient, obtain the patient's condition assessment coefficient threshold and perform numerical comparison with the patient's condition assessment coefficient, and perform a diagnosis and assessment of the patient's condition based on the numerical comparison results.

Images