Intelligent perinatal fetal heart monitoring system

Abstract

The invention relates to the technical field of signal mode recognition, in particular to a perinatal fetal heart intelligent monitoring system, which comprises a signal acquisition module, a signal processing module and a signal processing module, the signal segmentation module is used for decomposing the fetal heart signal into a plurality of fluctuating segments; the signal segment merging module is used for splicing adjacent fluctuating segments to obtain heart sound segments, calculating the stability degree of the heart sound segments through the fluctuating segments in the heart sound segments, and further judging whether the fluctuating segments in the heart sound segments are the same fetal heart segment or not according to the stability degree of the heart sound segments to obtain a plurality of fetal heart segments; the intelligent monitoring module is used for acquiring the average heart sound frequency of the fetal heart section. By analyzing the heart sound signal of the fetus, the heart sound signal of the fetal heart is decomposed into a plurality of stable fetal heart sections, and by analyzing each fetal heart section, the change condition of the fetal heart sound is monitored, so that the accuracy of judging the health state of the fetus is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of signal pattern recognition, and in particular to an intelligent perinatal fetal heart monitoring system. Background Art

[0002] The perinatal period is a critical period for fetal growth and development, and it is also the period when pregnant women's bodies change most dramatically. During this period, the health of the fetus is directly related to the physical and mental health of the pregnant woman and the happiness of the family. Therefore, it is particularly important to closely monitor the fetal heart rate. In order to better obtain the information in the fetal heart sound signal, it is usually necessary to perform Fourier transform on the heart sound signal; but Fourier transform is a global change and cannot reflect the changes of fetal heart sound over time. Therefore, before Fourier transforming the fetal heart signal, the fetal heart signal needs to be decomposed into several fetal heart signal segments. By performing Fourier transform on each fetal heart signal segment, the fetal heart sound signal can be better analyzed. However, since the fetal heart signal itself is not stable and unchanging, if it is directly divided by a fixed window size, the fetal heart data with different fluctuations may be divided into the same fetal heart segment, thereby affecting the subsequent analysis of the fetal heart signal. Summary of the invention

[0003] The present invention provides a perinatal fetal heart intelligent monitoring system to solve the existing problem that the traditional method of dividing the fetal heart rate signal by a fixed window size may classify fetal heart data with different fluctuations into the same fetal heart segment, thereby affecting the subsequent analysis of the fetal heart signal.

[0004] The present invention provides an intelligent perinatal fetal heart monitoring system using the following technical solutions:

[0005] Includes the following modules:

[0006] A signal acquisition module, used to obtain fetal heart rate signals;

[0007] The signal segmentation module is used to decompose the fetal heart signal into several fluctuation segments; obtain the fluctuation characteristics of each fluctuation segment according to the amplitude and time series length of each fluctuation segment; and merge the fluctuation segments to obtain several fluctuation segments according to the fluctuation characteristics of different fluctuation segments;

[0008] The signal segment merging module is used to obtain the heart sound segment based on the adjacent undulating segments, and obtain the dominance of the undulating segment according to the distribution of the fluctuation segments in the undulating segment in the heart sound segment; obtain the splicing degree of the undulating segment according to the dominance of the adjacent undulating segments in the same heart sound segment and the amplitude in each fluctuation segment in the adjacent undulating segment; obtain the splitting degree and difference degree of the undulating segment according to the difference in the undulating characteristics of the fluctuation segment between the undulating segment in the same heart sound segment and other undulating segments; obtain the stability of the heart sound segment according to the splicing degree, splitting degree and difference degree of the undulating segment in the heart sound segment; determine whether the undulating segment in the heart sound segment is the same fetal heart segment according to the stability of the heart sound segment, and obtain several fetal heart segments;

[0009] Intelligent monitoring module, used to obtain the average heart rate of the fetal heart segment.

[0010] Preferably, the step of decomposing the fetal heart signal into a plurality of fluctuation segments includes the following specific methods:

[0011] The minimum value point in the fetal heart signal is used as the segmentation point to divide the fetal heart signal into several fluctuation segments.

[0012] Preferably, the fluctuation characteristics of each fluctuation segment are obtained according to the amplitude and time series length of each fluctuation segment, and the specific calculation formula included is:

[0013]

[0014] In the formula, S represents the fluctuation characteristics of any fluctuation segment; V max represents the maximum amplitude in the fluctuation segment; t represents the time series length of the fluctuation segment; α represents the preset amplitude weight; norm represents the linear normalization function.

[0015] Preferably, the method of merging the fluctuation segments to obtain a plurality of fluctuation segments according to the fluctuation characteristics of different fluctuation segments includes the following specific methods:

[0016] The adjacent fluctuation segments in the fetal heart signal with the same fluctuation characteristics are classified as the same fluctuation segment.

[0017] Preferably, the heart sound segment is obtained based on adjacent undulating segments, and the dominance of the undulating segment is obtained according to the distribution of the fluctuation segment in the undulating segment in the heart sound segment, including the specific method of:

[0018] Starting from the first undulating segment, the first undulating segment and the second undulating segment are classified as one heart sound segment; the ratio of the number of undulating segments in the first undulating segment to the number of undulating segments in the heart sound segment is used as the dominance of the first undulating segment; the ratio of the number of undulating segments in the second undulating segment to the number of undulating segments in the heart sound segment is used as the dominance of the second undulating segment.

[0019] Preferably, the method of obtaining the splicing degree of the undulating segments according to the dominance degree of adjacent undulating segments in the same heart sound segment and the amplitude in each fluctuation segment of the adjacent undulating segments includes the following specific methods:

[0020] For the heart sound segment composed of the first ups and downs segment and the second ups and downs segment, the splicing degree of the second ups and downs segment is obtained according to the dominance degree of the first ups and downs segment and the dominance degree of the second ups and downs segment, combined with the amplitudes in each fluctuation segment of the first ups and downs segment and the second ups and downs segment. The specific calculation formula is:

[0021]

[0022] In the formula, Q 2 Indicates the degree of splicing of the second undulating segment; W 2-1 Indicates the dominance of the first undulation segment; W 2 Indicates the dominance of the second undulating segment; It represents the average of the maximum amplitudes of all fluctuation segments in the first fluctuation segment; Represents the average of the maximum amplitudes of all fluctuation segments within the second fluctuation segment.

[0023] Preferably, the method of obtaining the degree of separation and the degree of difference of the undulating segments according to the difference in the undulation characteristics of the undulating segments and other undulating segments in the same heart sound segment includes the following specific methods:

[0024] For a heart sound segment composed of a first undulating segment and a second undulating segment; according to the undulating characteristics of all the undulating segments in the second undulating segment, combined with the undulating characteristics of all the undulating segments in the heart sound segment, the splitting degree of the second undulating segment is obtained, and the specific calculation formula is:

[0025]

[0026] In the formula, R 2 Indicates the splitting degree of the second undulating segment; It represents the mean value of the fluctuation characteristics of all fluctuation segments in the second fluctuation segment; represents the mean value of the fluctuation characteristics of all fluctuation segments in the heart sound segment; represents the mean value of the fluctuation characteristics of all fluctuation segments in the i-th fluctuation segment in the heart sound segment; n represents the number of fluctuation segments in the heart sound segment;

[0027] According to the fluctuation characteristics of the fluctuation segments within the same heart sound segment and the previous fluctuation segment, the difference degree of the fluctuation segments is obtained.

[0028] Preferably, the method of obtaining the difference degree of the fluctuation segment according to the fluctuation characteristics of the fluctuation segment in the same heart sound segment and the internal fluctuation segment of the previous fluctuation segment includes the following specific methods:

[0029] For a heart sound segment consisting of a first undulating segment and a second undulating segment, the absolute value of the difference between the mean of the undulating features of all undulating segments in the second undulating segment and the mean of the undulating features of all undulating segments in the first undulating segment is taken as the difference degree of the second undulating segment.

[0030] Preferably, the method of obtaining the stability of the heart sound segment according to the degree of splicing, splitting and difference of the undulating segments in the heart sound segment includes the following specific methods:

[0031] For a heart sound segment composed of the first undulating segment and the second undulating segment, the stability of the heart sound segment is obtained according to the degree of splicing, degree of difference and degree of splitting of all undulating segments except the first undulating segment in the heart sound segment. The specific calculation formula is:

[0032]

[0033] Where, E represents the stability of the heart sound segment; n represents the number of ups and downs in the heart sound segment; Q i Indicates the degree of splicing of the ith undulating segment; D i Indicates the difference degree of the i-th fluctuation segment; R i Indicates the degree of splitting of the i-th fluctuation segment; sigmoid() represents the sigmoid function.

[0034] Preferably, the method of determining whether the fluctuating segments in the heart sound segment are the same fetal heart segment according to the stability of the heart sound segment and obtaining a plurality of fetal heart segments includes the following specific methods:

[0035] A stability threshold β is preset, and for a heart sound segment composed of a first undulating segment and a second undulating segment, if the stability of the heart sound segment is less than or equal to β, the first undulating segment is regarded as a fetal heart segment;

[0036] If the stability of the heart sound segment is greater than β, the first undulating segment, the second undulating segment and the third undulating segment are classified as a new heart sound segment, the splicing degree, the difference degree and the splitting degree of all the undulating segments except the first undulating segment in the new heart sound segment are obtained, and the stability of the new heart sound segment is further obtained. If the stability of the new heart sound segment is less than or equal to β, the heart sound segment before the undulating segment is added to the new heart sound segment as a fetal heart segment;

[0037] If the stability of the new heart sound segment is greater than β, the first ups and downs segment, the second ups and downs segment, the third ups and downs segment and the fourth ups and downs segment are classified as a new heart sound segment; and so on until the stability of the new heart sound segment is less than or equal to β, a fetal heart segment is obtained;

[0038] Cutting out the fetal heart segment from the fetal heart signal to obtain the fetal heart segment and the remaining fetal heart signal;

[0039] Fetal heart segments are continuously extracted from the remaining fetal heart signals until the fetal heart signals are decomposed into several fetal heart segments.

[0040] The beneficial effects of the technical solution of the present invention are as follows: the present application uses a signal acquisition module to obtain a fetal heart signal; uses a signal segmentation module to decompose the fetal heart signal into a plurality of fluctuation segments, and when the fluctuation characteristics of different fluctuation segments in the fetal heart signal are the same, it means that the different fluctuation segments have the same fluctuation conditions. At this time, if different fluctuation segments are adjacent, the different fluctuation segments can be classified as the same fluctuation segment; the signal segment merging module is used to combine adjacent fluctuation segments to obtain a heart sound segment, calculate the stability of the heart sound segment through the fluctuation segments in the heart sound segment, and further judge the heart sound segment according to the stability of the heart sound segment. Whether the ups and downs in the data are the same fetal heart segment, several fetal heart segments are obtained. In the actual process of detecting the fetal heart signal, the fetal heart signal may change briefly due to certain physiological activities of the pregnant woman during the collection process. When a short ups and downs segment appears and the difference between it and the adjacent ups and downs segment is small, the short ups and downs segment and the adjacent ups and downs segment should also be classified into the same fetal heart segment; the intelligent monitoring module is used to obtain the average heart sound frequency of the fetal heart segment, and by analyzing each fetal heart segment, the changes in the fetal heart sound can be accurately monitored, so as to accurately obtain the health status of the fetus. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 It is a structural block diagram of an intelligent perinatal fetal heart monitoring system of the present invention;

[0043] Figure 2 It is a schematic diagram of the undulating section. DETAILED DESCRIPTION

[0044] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation, structure, features and effects of a perinatal fetal heart rate intelligent monitoring system proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0045] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0046] The specific scheme of the intelligent perinatal fetal heart monitoring system provided by the present invention is described in detail below with reference to the accompanying drawings.

[0047] See also Figure 1 , which shows a structural block diagram of a perinatal fetal heart rate intelligent monitoring system provided by an embodiment of the present invention, the system includes the following modules:

[0048] The signal acquisition module 101 is used to acquire fetal heart rate signals.

[0049] It should be noted that the perinatal period is a critical period for fetal growth and development, and is also the period when pregnant women's bodies undergo the most dramatic changes. During this period, the health of the fetus is directly related to the physical and mental health of the pregnant woman and the happiness of the family. Therefore, it is particularly important to closely monitor the fetal heart rate of the fetus. As a perinatal fetal heart rate intelligent monitoring system, this embodiment first needs to obtain the fetal heart sound signal.

[0050] Specifically, an ultrasonic Doppler probe is used to collect fetal heart sound signals, which are amplified and denoised to obtain a fetal heart signal. Since the use of an ultrasonic Doppler probe to collect fetal heart sound signals and the amplification and denoising of fetal heart sound signals are both well-known existing technologies, they will not be described in detail in this embodiment.

[0051] At this point, the fetal heart signal is obtained.

[0052] The signal segmentation module 102 is used to decompose the fetal heart signal into a plurality of fluctuation segments; obtain the fluctuation characteristics of each fluctuation segment according to the amplitude and time series length of each fluctuation segment; and merge the fluctuation segments to obtain a plurality of fluctuation segments according to the fluctuation characteristics of different fluctuation segments.

[0053] It should be noted that in order to better analyze the fetal heart signal collected in the signal acquisition module 101, it is necessary to perform Fourier transform on the fetal heart signal collected in the acquisition module 101, but Fourier transform is a global change and cannot reflect the change of fetal heart sound over time. Therefore, before performing Fourier transform on the fetal heart signal, the fetal heart signal needs to be decomposed into several fetal heart signal segments, and each fetal heart signal segment is Fourier transformed to better analyze the fetal heart sound signal. However, since the fetal heart signal itself is not stable and unchanging, directly dividing it with a fixed window size may divide the fetal heart data with different fluctuation conditions into the same fetal heart segment, thereby affecting the subsequent analysis of the fetal heart signal. Therefore, the fetal heart signal is first divided into several fluctuation segments, and the continuous and identical fluctuation segments are classified as the same fluctuation segment according to the fluctuation of each fluctuation segment, so as to perform preliminary segmentation on the fetal heart signal to avoid backing up the fetal heart data with different fluctuation conditions into the same fetal heart segment.

[0054] Preferably, in a specific embodiment of the present invention, the fetal heart signal is divided into several fluctuation segments by taking the minimum value point in the fetal heart signal as the segmentation point. The minimum value point is obtained by an existing method, which will not be described in detail in this embodiment. For any fluctuation segment, the fluctuation characteristics of the fluctuation segment are obtained according to the time series length of the fluctuation segment and the maximum amplitude of the fluctuation segment. The specific calculation formula is:

[0055]

[0056] Wherein, S represents the fluctuation characteristics of the fluctuation segment; V max represents the maximum amplitude in the fluctuation segment; t represents the time series length of the fluctuation segment; α represents the preset amplitude weight, and the specific value of α can be set according to the actual situation. This embodiment does not make a rigid requirement. In this embodiment, α=0.7 is used for description; norm represents a linear normalization function, and its normalization range is all fluctuation segments.

[0057] It should be noted that the fluctuation characteristics of the fluctuation segment represent the steepness of the fluctuation segment. When the maximum amplitude in the fluctuation segment is larger and the time series length of the fluctuation segment is shorter, the fluctuation segment is steeper and its fluctuation characteristics are larger. At the same time, for the fetal heart sound performance, the amplitude change of the heart sound is more stable for the cardiac cycle. Therefore, when calculating the fluctuation characteristics of the fluctuation segment, a larger calculation weight is given to the heart sound amplitude to obtain a more accurate fluctuation characteristic. When the fluctuation characteristics of different fluctuation segments in the fetal heart signal are the same, it means that the different fluctuation segments have the same fluctuation. At this time, if the different fluctuation segments are adjacent, the different fluctuation segments can be classified as the same fluctuation segment.

[0058] Specifically, adjacent fluctuation segments with the same fluctuation characteristics in the fetal heart signal are classified as the same fluctuation segment.

[0059] At this point, several undulating segments are obtained.

[0060] The signal segment merging module 103 is used to obtain heart sound segments based on adjacent undulating segments, and to obtain the dominance of the undulating segments based on the distribution of fluctuation segments in the undulating segments in the heart sound segments; to obtain the degree of splicing of the undulating segments based on the dominance of adjacent undulating segments in the same heart sound segment and the amplitudes in each fluctuation segment in the adjacent undulating segments; to obtain the degree of splitting and the degree of difference of the undulating segments based on the difference in the undulating characteristics of the fluctuation segments between the undulating segments in the same heart sound segment and other undulating segments; to obtain the degree of stability of the heart sound segment based on the degree of splicing, splitting and difference of the undulating segments in the heart sound segment; and to determine whether the undulating segments in the heart sound segment are the same fetal heart segment based on the degree of stability of the heart sound segment, and to obtain a number of fetal heart segments.

[0061] It should be noted that the fluctuation segment obtained in the signal segmentation module 102 is a preliminary decomposition result of the fetal heart signal. Although the fluctuation of the fetal heart signal in the fluctuation segment is the same, in the actual detection process of the fetal heart signal, the fetal heart signal may have a short-term change due to certain physiological activities of the pregnant woman during the collection process, such as Figure 2 As shown, Figure 2 This is a schematic diagram of an undulating segment. When a short undulating segment appears in the segment and the difference between the short undulating segment and the adjacent undulating segment is small, the short undulating segment and the adjacent undulating segment should also be included in the same fetal heart segment.

[0062] Preferably, in a specific embodiment of the present invention, starting from the first undulating segment, the first undulating segment and the second undulating segment are classified as one heart sound segment; the ratio of the number of undulating segments in the first undulating segment to the number of undulating segments in the heart sound segment is used as the dominance of the first undulating segment; the ratio of the number of undulating segments in the second undulating segment to the number of undulating segments in the heart sound segment is used as the dominance of the second undulating segment.

[0063] Furthermore, for the heart sound segment composed of the first ups and downs segment and the second ups and downs segment, the splicing degree of the second ups and downs segment is obtained according to the dominance degree of the first ups and downs segment and the dominance degree of the second ups and downs segment, combined with the amplitudes in each fluctuation segment of the first ups and downs segment and the second ups and downs segment. The specific calculation formula is:

[0064]

[0065] In the formula, Q 2 Indicates the degree of splicing of the second undulating segment; W 2-1 Indicates the dominance of the first undulation segment; W 2 Indicates the dominance of the second undulating segment; It represents the average of the maximum amplitudes of all fluctuation segments in the first fluctuation segment; Represents the average of the maximum amplitudes of all fluctuation segments within the second fluctuation segment.

[0066] It should be noted that the degree of splicing of the second undulation segment refers to the degree to which the first undulation segment and the second undulation segment can be classified as the same fetal heart segment. The greater the difference in the dominant degree between the first undulation segment and the second undulation segment, the more likely it is that one of the first undulation segment or the second undulation segment is a short-term change in the fetal heart signal. At this time, the first undulation segment and the second undulation segment should be classified as the same fetal heart segment. The smaller the value of is, the less its short-term transformation will affect the Fourier transform of the remaining fluctuation segments. The smaller the value is, the more likely it is that the first undulation segment and the second undulation segment should be classified as the same fetal heart segment.

[0067] Furthermore, for the heart sound segment composed of the first undulating segment and the second undulating segment, according to the undulating characteristics of all the undulating segments in the second undulating segment, combined with the undulating characteristics of all the undulating segments in the heart sound segment, the splitting degree of the second undulating segment is obtained, and the specific calculation formula is:

[0068]

[0069] In the formula, R 2 Indicates the splitting degree of the second undulating segment; It represents the mean value of the fluctuation characteristics of all fluctuation segments in the second fluctuation segment; represents the mean value of the fluctuation characteristics of all fluctuation segments in the heart sound segment; represents the mean value of the fluctuation characteristics of all fluctuation segments in the i-th fluctuation segment in the heart sound segment; n represents the number of fluctuation segments in the heart sound segment;

[0070] According to the fluctuation characteristics of the fluctuation segments within the same heart sound segment and the previous fluctuation segment, the difference degree of the fluctuation segments is obtained.

[0071] It should be noted that the degree of splitting of the second undulating segment represents the difference between the fluctuation of the second undulating segment and the fluctuation of the remaining undulating segments in the heart sound segment. The greater the difference in the fluctuation, the less likely it is that the first undulating segment and the second undulating segment should be classified as the same fetal heart segment.

[0072] Furthermore, for the heart sound segment composed of the first undulating segment and the second undulating segment, the absolute value of the difference between the mean of the undulating features of all the undulating segments in the second undulating segment and the mean of the undulating features of all the undulating segments in the first undulating segment is taken as the difference degree of the second undulating segment.

[0073] It should be noted that the difference degree of the second undulation segment represents the difference between the fluctuation of the second undulation segment and the fluctuation of the first undulation segment. The greater the difference in the fluctuation, the less likely it is that the first undulation segment and the second undulation segment should be classified as the same fetal heart segment.

[0074] It should be further explained that, for a heart sound segment composed of a first undulating segment and a second undulating segment, the greater the degree of splicing of the second undulating segment and the smaller the degree of splitting and the degree of difference of the second undulating segment, the smoother the heart sound segment is, and the smoothness of the heart sound segment can be quantified by this.

[0075] Preferably, in a specific embodiment of the present invention, for a heart sound segment composed of a first undulating segment and a second undulating segment, the stability of the heart sound segment is obtained according to the degree of splicing, degree of difference and degree of splitting of all undulating segments except the first undulating segment in the heart sound segment, and the specific calculation formula is:

[0076]

[0077] Where, E represents the stability of the heart sound segment; n represents the number of ups and downs in the heart sound segment; Q i Indicates the degree of splicing of the ith undulating segment; D i Indicates the difference degree of the i-th fluctuation segment; R i represents the splitting degree of the i-th undulation segment; sigmoid() represents the sigmoid function, which is used for normalization processing in this embodiment.

[0078] It should be noted that, for the heart sound segment composed of the first undulating segment and the second undulating segment, the greater the degree of splicing of the second undulating segment and the smaller the degree of splitting and the degree of difference of the second undulating segment, the smoother the heart sound segment is, and the more likely the first undulating segment and the second undulating segment are to be classified as the same fetal heart segment. Therefore, based on this, the fetal heart signal can be iteratively segmented continuously to obtain several fetal heart segments.

[0079] Further, a stability threshold β is preset. The specific value of β can be set according to the actual situation. This embodiment does not make a rigid requirement. In this embodiment, β=0.7 is used for description. For a heart sound segment composed of a first undulating segment and a second undulating segment, if the stability of the heart sound segment is less than or equal to β, the first undulating segment is regarded as a fetal heart segment.

[0080] If the stability of the heart sound segment is greater than β, the first undulating segment, the second undulating segment and the third undulating segment are classified as a new heart sound segment, the splicing degree, the difference degree and the splitting degree of all the undulating segments except the first undulating segment in the new heart sound segment are obtained, and the stability of the new heart sound segment is further obtained. If the stability of the new heart sound segment is less than or equal to β, the heart sound segment before the undulating segment is added to the new heart sound segment as a fetal heart segment;

[0081] It should be noted that the logic and process of obtaining the degree of splicing, difference and splitting of all the undulating segments except the first undulating segment in the new heart sound segment are the same as those of obtaining the degree of splicing, difference and splitting of all the undulating segments except the first undulating segment in the heart sound segment composed of the first undulating segment and the second undulating segment; and the logic and process of obtaining the degree of stability of the new heart sound segment are the same as those of obtaining the degree of stability of the heart sound segment composed of the first undulating segment and the second undulating segment, so they will not be repeated in this embodiment.

[0082] If the stability of the new heart sound segment is greater than β, the first ups and downs segment, the second ups and downs segment, the third ups and downs segment and the fourth ups and downs segment are classified as a new heart sound segment; and so on until the stability of the new heart sound segment is less than or equal to β, a fetal heart segment is obtained;

[0083] Cutting out the fetal heart segment from the fetal heart signal to obtain the fetal heart segment and the remaining fetal heart signal;

[0084] Furthermore, fetal heart segments are continuously intercepted from the remaining fetal heart signals until the fetal heart signals are decomposed into a plurality of fetal heart segments.

[0085] At this point, several fetal heart segments are obtained.

[0086] The intelligent monitoring module 104 is used to obtain the average heart rate of the fetal heart segment.

[0087] It should be noted that after obtaining several fetal heart segments through the signal segment merging module 103, each fetal heart segment can be Fourier transformed to obtain a two-dimensional time-frequency diagram of each fetal heart segment, so as to better obtain the fetal heart sound change characteristics and accurately monitor the fetal heart sound signal.

[0088] Specifically, a Fourier transform is performed on each fetal heart segment to obtain a two-dimensional time-frequency diagram of each fetal heart segment; a peak detection algorithm is used to obtain the peak frequency and peak time interval of each two-dimensional time-frequency diagram. Since the Fourier transform and the peak detection algorithm are both well-known existing technologies, they will not be described in detail in this embodiment.

[0089] Furthermore, the average heart rate of the fetus within each fetal heart segment is obtained by using an electrocardiogram method. Since the electrocardiogram method is a well-known prior art, it will not be described in detail in this embodiment.

[0090] It should be noted that the normal heart sounds of the perinatal fetus are maintained between 110 and 160 beats per minute. If the average heart sound frequency of the fetus within the fetal heart segment is greater than 160 beats per minute or less than 110 beats per minute, it means that there is an abnormality in the fetus in the uterus and the relevant medical staff must be notified immediately for further examination.

[0091] At this point, this embodiment is completed.

[0092] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A perinatal fetal heart rate intelligent monitoring system, characterized in that: The system includes the following modules: A signal acquisition module, used to obtain fetal heart rate signals; The signal segmentation module is used to decompose the fetal heart signal into several fluctuation segments; according to the amplitude and time series length of each fluctuation segment, the fluctuation characteristics of each fluctuation segment are obtained; According to the fluctuation characteristics of different fluctuation segments, the fluctuation segments are merged to obtain several fluctuation segments; The signal segment merging module is used to obtain the heart sound segment based on the adjacent undulating segments, and obtain the dominance of the undulating segment according to the distribution of the fluctuation segments in the undulating segment in the heart sound segment; obtain the splicing degree of the undulating segment according to the dominance of the adjacent undulating segments in the same heart sound segment and the amplitude in each fluctuation segment in the adjacent undulating segment; obtain the splitting degree and difference degree of the undulating segment according to the difference in the undulating characteristics of the fluctuation segment between the undulating segment in the same heart sound segment and other undulating segments; obtain the stability of the heart sound segment according to the splicing degree, splitting degree and difference degree of the undulating segment in the heart sound segment; determine whether the undulating segment in the heart sound segment is the same fetal heart segment according to the stability of the heart sound segment, and obtain several fetal heart segments; Intelligent monitoring module, used to obtain the average heart rate of the fetal heart segment.

2. According to claim 1, a perinatal fetal heart rate intelligent monitoring system is characterized in that: The specific method of decomposing the fetal heart signal into a plurality of fluctuation segments includes: The minimum value point in the fetal heart signal is used as the segmentation point to divide the fetal heart signal into several fluctuation segments.

3. According to claim 1, a perinatal fetal heart rate intelligent monitoring system is characterized in that: The fluctuation characteristics of each fluctuation segment are obtained according to the amplitude and time series length of each fluctuation segment, and the specific calculation formula included is: In the formula, S represents the fluctuation characteristics of any fluctuation segment; V max represents the maximum amplitude in the fluctuation segment; t represents the time series length of the fluctuation segment; α represents the preset amplitude weight; norm represents the linear normalization function.

4. The intelligent perinatal fetal heart monitoring system according to claim 1, characterized in that: The method of combining the fluctuation segments to obtain a plurality of fluctuation segments according to the fluctuation characteristics of different fluctuation segments includes the following specific methods: The adjacent fluctuation segments in the fetal heart signal with the same fluctuation characteristics are classified as the same fluctuation segment.

5. The intelligent perinatal fetal heart monitoring system according to claim 1, characterized in that: The method of obtaining the heart sound segment based on adjacent undulating segments and obtaining the dominance of the undulating segment based on the distribution of the fluctuation segment in the undulating segment in the heart sound segment includes the following specific methods: Starting from the first undulating segment, the first undulating segment and the second undulating segment are classified as one heart sound segment; the ratio of the number of undulating segments in the first undulating segment to the number of undulating segments in the heart sound segment is used as the dominance of the first undulating segment; the ratio of the number of undulating segments in the second undulating segment to the number of undulating segments in the heart sound segment is used as the dominance of the second undulating segment.

6. The intelligent perinatal fetal heart monitoring system according to claim 1, characterized in that: The method of obtaining the splicing degree of the undulating segments according to the dominance degree of the adjacent undulating segments in the same heart sound segment and the amplitude in each fluctuation segment of the adjacent undulating segments includes the following specific methods: For the heart sound segment composed of the first ups and downs segment and the second ups and downs segment, the splicing degree of the second ups and downs segment is obtained according to the dominance degree of the first ups and downs segment and the dominance degree of the second ups and downs segment, combined with the amplitudes in each fluctuation segment of the first ups and downs segment and the second ups and downs segment. The specific calculation formula is: Where Q2 represents the degree of splicing of the second undulating segment; W 2-1 Indicates the dominance of the first undulating segment; W2 indicates the dominance of the second undulating segment; It represents the average of the maximum amplitudes of all fluctuation segments in the first fluctuation segment; Represents the average of the maximum amplitudes of all fluctuation segments within the second fluctuation segment.

7. The intelligent perinatal fetal heart monitoring system according to claim 1, characterized in that: The method of obtaining the degree of separation and the degree of difference of the undulating segments according to the difference in the undulating characteristics of the undulating segments and other undulating segments in the same heart sound segment includes the following specific methods: For a heart sound segment composed of a first undulating segment and a second undulating segment; according to the undulating characteristics of all the undulating segments in the second undulating segment, combined with the undulating characteristics of all the undulating segments in the heart sound segment, the splitting degree of the second undulating segment is obtained, and the specific calculation formula is: In the formula, R2 represents the splitting degree of the second undulating segment; It represents the mean value of the fluctuation characteristics of all fluctuation segments in the second fluctuation segment; represents the mean value of the fluctuation characteristics of all fluctuation segments in the heart sound segment; represents the mean value of the fluctuation characteristics of all fluctuation segments in the i-th fluctuation segment in the heart sound segment; n represents the number of fluctuation segments in the heart sound segment; According to the fluctuation characteristics of the fluctuation segments within the same heart sound segment and the previous fluctuation segment, the difference degree of the fluctuation segments is obtained.

8. The intelligent perinatal fetal heart monitoring system according to claim 7, characterized in that: The specific method of obtaining the difference degree of the fluctuation segment according to the fluctuation characteristics of the fluctuation segment in the same heart sound segment and the internal fluctuation segment of the previous fluctuation segment is as follows: For a heart sound segment consisting of a first undulating segment and a second undulating segment, the absolute value of the difference between the mean of the undulating features of all undulating segments in the second undulating segment and the mean of the undulating features of all undulating segments in the first undulating segment is taken as the difference degree of the second undulating segment.

9. The intelligent perinatal fetal heart monitoring system according to claim 1, characterized in that: The method of obtaining the stability of the heart sound segment according to the degree of splicing, splitting and difference of the undulating segments in the heart sound segment includes: For a heart sound segment composed of the first undulating segment and the second undulating segment, the stability of the heart sound segment is obtained according to the degree of splicing, degree of difference and degree of splitting of all undulating segments except the first undulating segment in the heart sound segment. The specific calculation formula is: Where, E represents the stability of the heart sound segment; n represents the number of ups and downs in the heart sound segment; Q i Indicates the degree of splicing of the ith undulating segment; D i Indicates the difference degree of the i-th fluctuation segment; R i Indicates the degree of splitting of the i-th fluctuation segment; sigmoid() represents the sigmoid function.

10. The intelligent perinatal fetal heart monitoring system according to claim 1, characterized in that: The method of determining whether the fluctuating segments in the heart sound segment are the same fetal heart segment according to the stability of the heart sound segment and obtaining a plurality of fetal heart segments includes: A stability threshold β is preset, and for a heart sound segment composed of a first undulating segment and a second undulating segment, if the stability of the heart sound segment is less than or equal to β, the first undulating segment is regarded as a fetal heart segment; If the stability of the heart sound segment is greater than β, the first undulating segment, the second undulating segment and the third undulating segment are classified as a new heart sound segment, the splicing degree, the difference degree and the splitting degree of all the undulating segments except the first undulating segment in the new heart sound segment are obtained, and the stability of the new heart sound segment is further obtained. If the stability of the new heart sound segment is less than or equal to β, the heart sound segment before the undulating segment is added to the new heart sound segment as a fetal heart segment; If the stability of the new heart sound segment is greater than β, the first ups and downs segment, the second ups and downs segment, the third ups and downs segment and the fourth ups and downs segment are classified as a new heart sound segment; and so on until the stability of the new heart sound segment is less than or equal to β, a fetal heart segment is obtained; Cutting out the fetal heart segment from the fetal heart signal to obtain the fetal heart segment and the remaining fetal heart signal; Fetal heart segments are continuously extracted from the remaining fetal heart signals until the fetal heart signals are decomposed into several fetal heart segments.

Images