An unattended rabbit and poultry farming Internet of Things system and environmental parameter monitoring method

Abstract

The present invention relates to the field of data processing technology, and in particular to an unattended rabbit and poultry farming Internet of Things system and an environmental parameter monitoring method. The system includes a first determination module for determining the degree of correlation between high and low noise based on noise data collected by an environmental noise monitor at each location; a second determination module for determining the degree of mutation of noise data points, so as to obtain the location and time of occurrence of interference noise; a third determination module for determining the disorder enhancement factor of noise data points, so as to obtain the location where the rabbit group is active after being affected by the interference noise; a fourth determination module for determining the change value of rabbit activity, so as to capture the activity noise of the rabbit group affected by the noise; and a fifth determination module for determining the noise impact factor. The system can find out the location of the interference noise in time, and grasp the activity of the rabbits after being affected by the interference noise, so as to carry out manual intervention in a timely and accurate manner.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an unattended rabbit and poultry breeding Internet of Things system and an environmental parameter monitoring method. Background Art

[0002] The unattended rabbit and poultry breeding environmental parameter monitoring system uses modern technologies, such as Internet of Things technology, sensor technology and data analysis technology, to monitor and manage various parameters in the breeding environment in real time to ensure the healthy growth of rabbits and poultry and improve breeding efficiency. Excessive noise in rabbit and poultry farms can cause stress reactions in rabbits and poultry, affecting their growth and reproduction. Therefore, the noise in rabbit and poultry farms can be monitored in real time through environmental noise monitors, so that timely manual intervention can be carried out when the noise is too loud.

[0003] At present, the noise monitors installed in rabbit and poultry farms can obtain the noise in rabbit and poultry farms in real time. However, since the rabbits will eat and play in their lives, they will produce different degrees of noise, and the rabbits may have a stress response after being affected by the noise, resulting in more intense noise, thus affecting the accuracy of the noise analysis. Summary of the invention

[0004] In order to solve the technical problem of inaccurate noise analysis, the purpose of the present invention is to provide an unattended rabbit and poultry farming Internet of Things system and an environmental parameter monitoring method. The technical solutions adopted are as follows:

[0005] In a first aspect, the present invention provides an unattended rabbit and poultry farming Internet of Things system, the system comprising:

[0006] An acquisition module is used to acquire noise data collected by multiple environmental noise monitors located at different locations in the rabbit and poultry farm, wherein the noise data includes multiple noise data points, wherein the horizontal axis value of the noise data point is a time value, and the vertical axis value is a noise value;

[0007] A first determination module is used to determine the correlation degree of high and low noise based on the noise data, wherein the correlation degree of high and low noise is used to reflect the correlation between the noise value of each noise data point and the noise values ​​of surrounding noise data points;

[0008] A second determination module is used to determine the mutation degree of the noise data point based on the correlation degree of high and low noise of the noise data point;

[0009] A third determination module is used to determine the disorder enhancement factor of the noise data point;

[0010] A fourth determination module is used to determine the rabbit activity change value based on the average value of the difference between the disorder enhancement factor of the noise data point collected by the environmental noise monitor at other locations other than the current location at the same time and the disorder enhancement factor of the noise data point collected by the environmental noise monitor at the current location;

[0011] A fifth determination module, used for determining a noise impact factor based on the mutation degree and the rabbit activity change value;

[0012] The noise reduction module is used to perform noise reduction processing on the rabbit and poultry farm in response to the noise impact factors of multiple positions at a certain moment being greater than the noise threshold.

[0013] In some embodiments, the first determining module includes:

[0014] A segmentation processing unit is used to segment the noise data collected by the environmental noise monitor at each location, and each threshold number of adjacent noise data points is regarded as a noise area to obtain multiple noise areas;

[0015] A first determining unit, used to determine the maximum value of all noise data points in the noise area;

[0016] A second determination unit is used to calculate, for each noise region, a difference between a noise value of a noise data point with a maximum value in the noise region and noise values ​​of other noise data points in the noise region;

[0017] A fitting unit is used to fit the maximum value of the noise data points in all noise areas to obtain the upper envelope of the noise data points;

[0018] A periodicity unit for determining the autocorrelation function and the autocorrelation period based on the upper envelope of the noise data points;

[0019] A comparison data point unit, used to use a noise data point in the next autocorrelation cycle of the autocorrelation cycle where a noise data point is located and in the same order as the noise data point in the autocorrelation cycle where the noise data point is located as a comparison data point for the noise data point;

[0020] The third determination unit is used to determine the correlation degree of high noise and low noise of each noise data point.

[0021] In some embodiments, the second determining module includes:

[0022] A first calculation unit is used to calculate the high and low noise levels of multiple adjacent noise data points on the left and right of each noise data point for the noise data collected by the environmental noise monitor at each location;

[0023] The second calculation unit is used to calculate the difference between the high and low noise levels of two adjacent noise data points;

[0024] The fourth determining unit is used to determine the mutation degree of the noise data point.

[0025] In some embodiments, the third determination module includes:

[0026] A window setting unit, used to set a window with a length equal to a threshold length, wherein a sliding step length of the window is a difference between the horizontal coordinate values ​​of two adjacent noise data points;

[0027] A first acquisition unit is used to acquire the number of extreme value points of noise data points in each window after sliding;

[0028] A third calculation unit is used to calculate the difference between adjacent maximum values ​​and adjacent minimum values ​​of the noise data points in each window after sliding;

[0029] A second acquisition unit is used to acquire a difference between a noise value corresponding to any maximum value point and a minimum value point closest to the maximum value point in each window after sliding, and use the difference between the noise value corresponding to any maximum value point and the minimum value point closest to the maximum value point as the extreme value point difference of the maximum value point;

[0030] A fourth calculation unit is used to calculate the average value of all the extreme point difference values ​​in each window after sliding, so as to obtain the average value of the window extreme point difference values;

[0031] A fifth calculation unit, used for calculating the difference between the average values ​​of the window extreme point difference values ​​of the two adjacent windows on the left and right during sliding, and obtaining the difference between the average extreme point difference values ​​of the left window;

[0032] The fifth determining unit is used to determine the disorder enhancement factor of the noise data point.

[0033] In some embodiments, the correlation degree of high and low noise for each noise data point is determined according to the following formula:

[0034] ;

[0035] In the formula, Indicates The correlation degree of high and low noise of each noise data point, Indicates the serial number of the noise data point collected by the environmental noise monitor at the current location. Indicates The serial numbers of other noise data points in the noise region where the noise data point is located, Indicates The number of other noise data points in the noise region where the noise data point is located, Indicates The fluctuation of other noise data points in the noise region where the noise data point is located, Indicates The first of the other noise data points in the noise region where the noise data point is located The noise value of the noise data point, Indicates The first of the other noise data points in the noise region where the noise data point is located The noise data point corresponds to The noise value of the comparison data point, Indicates The first of the other noise data points in the noise region where the noise data point is located The sequence number of the comparison data point of the noise data point, represents a hyperbolic function, where the fluctuation of other noise data points in the noise region where the noise data point is located is It is the difference between the noise value of the noise data point that obtains the maximum value in the noise area where the noise data point is located and the average noise value of other noise data points in the noise area where the noise data point is located.

[0036] In some embodiments, the mutation degree of the noise data point is determined according to the following formula:

[0037] ;

[0038] In the formula, It is The mutation degree of each noise data point is Indicates The average value of the high and low noise correlation degree of multiple adjacent noise data points to the right of a noise data point, Indicates The average value of the high and low noise correlation degree of multiple adjacent noise data points to the left of a noise data point, Indicates The number of adjacent noise data points on the left and right sides of a noise data point The correlation between the high and low noise of the noise data point is The difference between the high and low noise correlation levels of the noise data points, Indicates The serial numbers of multiple adjacent noise data points on the left and right sides of a noise data point. N represents the The number of multiple adjacent noise data points on the left and right sides of a noise data point, represents a hyperbolic function, Indicates the serial number of the noise data point collected by the environmental noise monitor at the current location.

[0039] In some embodiments, the disorder enhancement factor of the noise data point is determined according to the following formula:

[0040] ;

[0041] In the formula, When all noise data points at the same position are traversed, all windows contain the first The sequence number of the window corresponding to the noise data point, When all noise data points at the same position are traversed, all windows contain the first The number of windows corresponding to the noise data points, It is The disorder enhancement factor of the noise data points is It is The noise data point corresponds to The difference between the average extreme point differences of the windows, It is The noise data point corresponds to The number of extreme points of the noise data points in the sliding window is The difference between the number of extreme points of the noise data points in the first adjacent window to the right of the window, is a hyperbolic function, Indicates the serial number of the noise data point collected by the environmental noise monitor at the current location.

[0042] In some embodiments, the rabbit activity change value is determined according to the following formula:

[0043] ;

[0044] In the formula, Indicates the noise level collected by the environmental noise monitor at the current location. The change value of rabbit activity for each noise data point, Indicates the first The disorder enhancement factor of the noise data point is related to the noise data collected by the environmental noise monitor at the current location. The average value of the difference between the disorder enhancement factors of the noise data points, Indicates the noise level collected by the environmental noise monitor at the current location. The disorder enhancement factor of the noise data points is represents a hyperbolic function, Indicates the sequence number of the noise data point collected by the environmental noise monitor at the current location or other locations, where the sequence number of the noise data point collected by the environmental noise monitor at the current location and other locations is The noise data points have a corresponding relationship in time value. The environmental noise monitor at the current location collects the first Noise data points and the first noise data points collected by environmental noise monitors at other locations The noise data points are collected at the same time.

[0045] In some embodiments, the noise impact factor is determined according to the following formula:

[0046] ;

[0047] In the formula, Indicates the noise level collected by the environmental noise monitor at the current location. The noise impact factor of the noise data point is Indicates the noise level collected by the environmental noise monitor at the current location. The mutation degree of each noise data point is Indicates the noise level collected by the environmental noise monitor at the current location. The change value of rabbit activity for each noise data point, Indicates the serial number of the noise data point collected by the environmental noise monitor at the current location.

[0048] In a second aspect, the present invention provides an environmental parameter monitoring method, the method comprising:

[0049] Acquire noise data collected by multiple environmental noise monitors located at different locations in a rabbit and poultry farm, wherein the noise data includes multiple noise data points, wherein the horizontal axis value of the noise data point is a time value, and the vertical axis value is a noise value;

[0050] Based on the noise data collected by the environmental noise monitor at each location, determine the correlation degree of high and low noise, wherein the correlation degree of high and low noise is used to reflect the correlation between the noise value of each noise data point and the noise values ​​of the surrounding noise data points;

[0051] Determine the mutation degree of the noise data point based on the correlation degree between high and low noise of the noise data point;

[0052] Determine the disorder enhancement factor of the noise data points;

[0053] Determine the rabbit activity change value based on the average value of the difference between the disorder enhancement factor of the noise data point collected by the environmental noise monitor at other locations other than the current location at the same time and the disorder enhancement factor of the noise data point collected by the environmental noise monitor at the current location;

[0054] Determining a noise impact factor based on the mutation degree and the rabbit activity change value;

[0055] In response to the noise impact factors of multiple locations at a certain moment being greater than the noise threshold, noise reduction treatment is performed on the rabbit and poultry farm.

[0056] The present invention has the following beneficial effects:

[0057] The present invention provides an unattended rabbit and poultry farming Internet of Things system and an environmental parameter monitoring method. The system comprises an acquisition module for acquiring noise data collected by multiple environmental noise monitors located at different positions of a rabbit and poultry farm, so as to provide a data basis for subsequent analysis; comprises a first determination module for determining the degree of correlation between high and low noise based on the noise data collected by the environmental noise monitor at each position, so as to grasp the correlation between the noise value of each noise data point and the noise values ​​of surrounding noise data points; comprises a second determination module for determining the degree of mutation of a noise data point based on the degree of correlation between the high and low noise of the noise data point, so as to obtain the occurrence position and occurrence time of the interference noise; comprises a third determination module for determining the disorder enhancement factor of the noise data point, so as to obtain the interference noise. The location of the rabbit group after the noise affects the activity; including a fourth determination module for determining the rabbit activity change value based on the average value of the difference between the disorder enhancement factor of the noise data point collected by the environmental noise monitor at other locations other than the current location at the same time and the disorder enhancement factor of the noise data point collected by the environmental noise monitor at the current location, so as to grasp the rabbit activity situation, so as to better capture the activity noise of the rabbit group affected by the noise; including a fifth determination module for determining the noise impact factor based on the mutation degree and the rabbit activity change value, so as to obtain the situation of the rabbit group affected by the noise; a noise reduction module for performing noise reduction treatment on the rabbit and poultry farm in response to the noise impact factors of multiple locations at a certain moment being greater than the noise threshold, and timely manual intervention to ensure that the breeding of rabbits and poultry is not affected. The system can find out the location of the interference noise in time, and grasp the activity of the rabbits after being affected by the interference noise, so as to timely and accurately carry out manual intervention to provide a normal growth environment for the rabbit group. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are 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.

[0059] Figure 1 A schematic structural diagram of an unattended rabbit and poultry farming Internet of Things system provided by one embodiment of the present invention;

[0060] Figure 2 A method flow chart of an environmental parameter monitoring method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] 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.

[0063] In the first aspect, the present invention provides an unattended rabbit and poultry farming Internet of Things system, see Figure 1 The system comprises:

[0064] The acquisition module 101 is used to acquire noise data collected by multiple environmental noise monitors located at different locations in the rabbit and poultry farm. The noise data includes multiple noise data points. The horizontal axis value of the noise data point is the time value, and the vertical axis value is the noise value.

[0065] Obtain noise data collected by multiple environmental noise monitors located in different locations of rabbit and poultry farms to provide a data basis for subsequent analysis.

[0066] It should be noted that environmental noise monitors can record data for a long time and are usually placed in the main areas where rabbits and poultry are active, such as rabbit cage areas, feeding areas, and birthing areas, so that the noise in rabbit and poultry farms can be fully monitored.

[0067] The noise data collected by the environmental noise monitors installed at various locations in the rabbit farm include the sounds naturally generated by rabbits in their daily activities, such as eating, playing, and calling. These sounds are part of the rabbit's behavior and are usually common in the breeding environment. They also include interference noise caused by the external environment or human factors, such as equipment operation or mechanical sounds. This continuous interference may have a long-term impact on the rabbit. This sound is usually irregular and has nothing to do with the normal life of the rabbit. The noise of normal rabbit activities is some sounds with moderate frequency and volume, while interference noise usually occurs intermittently and suddenly. In addition, the noise generated by human activities such as mechanical operation will make the operation of the noise more regular due to the operation of the machinery, and because the decibel of the noise is large, the noise of the normal life of the rabbit will be covered. Therefore, when noise occurs, the noise data points will change from disorder to regular changes. Therefore, it is necessary to analyze the interference noise according to the characteristics of the noise and analyze its impact in the rabbit breeding process.

[0068] The first determination module 102 is used to determine the correlation degree between high noise and low noise based on the noise data.

[0069] The high and low noise correlation degree can reflect the correlation between the noise value of each noise data point and the noise values ​​of the surrounding noise data points. The greater the high and low noise correlation degree, the higher the correlation between the noise value of each noise data point and the noise values ​​of the surrounding noise data points, and the more likely the noise is caused by interference noise.

[0070] In some embodiments, the first determination module 102 includes:

[0071] The segmentation processing unit 1021 is used to perform segmentation processing on the noise data collected by the environmental noise monitor at each location, and each threshold number of adjacent noise data points is regarded as a noise area to obtain multiple noise areas.

[0072] Segmented processing can ensure the adequacy of the research on the fluctuation of each local noise data point (i.e. each noise area) of the noise data. The number of thresholds can be set by the implementer according to the actual situation, and is not specifically limited here.

[0073] The first determining unit 1022 is used to determine the maximum value of the noise data points in all noise areas.

[0074] The maximum value of the noise data point in the noise area can reflect the value of the peak of the noise in the noise area.

[0075] The second determining unit 1023 is used to calculate, for each noise region, the difference between the noise value of the noise data point that obtains the maximum value in the noise region and the noise values ​​of other noise data points in the noise region.

[0076] The difference between the noise value of the noise data point that obtains the maximum value in the noise region and the noise values ​​of other noise data points in the noise region can reflect the fluctuation of the noise data points in the noise region.

[0077] The fitting unit 1024 is used to fit the maximum values ​​of the noise data points in all the noise regions to obtain the upper envelope of the noise data points.

[0078] The upper envelope of the noise data points can reflect the fluctuation of the maximum value.

[0079] The periodicity unit 1025 is used to determine the autocorrelation function and the autocorrelation period based on the upper envelope of the noise data points.

[0080] The autocorrelation function can reflect the fluctuation law of the maximum value and can be used to determine the autocorrelation period, that is, the periodicity of the upper envelope, so as to grasp the fluctuation period of the maximum value.

[0081] The comparison data point unit 1026 is used to use a noise data point in the next autocorrelation cycle of the autocorrelation cycle where a noise data point is located and in the same order as the noise data point in the autocorrelation cycle where the noise data point is located as a comparison data point for the noise data point.

[0082] A noise data point and its corresponding comparison data point can be used to analyze the correlation between the noise data points in two adjacent autocorrelation periods.

[0083] The third determining unit 1027 is used to determine the correlation degree of high and low noise of each noise data point.

[0084] In some embodiments, the correlation degree of high and low noise for each noise data point is determined according to the following formula:

[0085] .

[0086] In the formula, Indicates The correlation degree of high and low noise of each noise data point reflects the The correlation between the noise value of a noise data point and the noise values ​​of the surrounding noise data points. Indicates the serial number of the noise data point collected by the environmental noise monitor at the current location. Indicates The serial numbers of other noise data points in the noise region where the noise data point is located, Indicates The number of other noise data points in the noise region where the noise data point is located and its value is not zero. Indicates The fluctuation degree of other noise data points in the noise area where the noise data point is located reflects the fluctuation of the noise data points in the noise area. The larger the value, the greater the difference in the noise values ​​of the noise data points in the noise area, that is, the greater the fluctuation. Indicates The first of the other noise data points in the noise region where the noise data point is located The noise value of the noise data point reflects the The noise size of the noise data point is Indicates The first of the other noise data points in the noise region where the noise data point is located The noise data point corresponds to The noise value of the comparison data point reflects the The noise size of the noise data point is Indicates The first of the other noise data points in the noise region where the noise data point is located The sequence number of the comparison data point of the noise data point, represents a hyperbolic function, where the fluctuation of other noise data points in the noise region where the noise data point is located is It is the difference between the noise value of the noise data point that obtains the maximum value in the noise area where the noise data point is located and the average noise value of other noise data points in the noise area where the noise data point is located. The bigger, The larger the The higher the correlation between the noise value of a noise data point and the noise values ​​of its surrounding noise data points, the higher the correlation between the noise value of a noise data point and its surrounding noise data points. The bigger.

[0087] The high and low noise correlation obtained by the above operation indicates the correlation between the high and low noise values ​​of the noise data point and the noise data points around it. The higher the high and low noise correlation, the higher the correlation between the noise value of the noise data point and the noise values ​​of the noise data points around it. Since the noise of normal rabbit activities is the disordered noise generated by each rabbit, its high and low noise correlation is low, while the high and low noise correlation of interference noise is often high, and the appearance of interference noise is often sudden. When interference noise occurs, there will be a sudden increase in the high and low noise correlation, and the high and low noise correlation will be maintained at a high level. Therefore, the change in the high and low noise correlation of the noise data point can be analyzed to find the sudden noise data point.

[0088] The second determination module 103 is used to determine the mutation degree of the noise data point based on the correlation degree between the high noise and the low noise of the noise data point.

[0089] The mutation degree of the noise data point can reflect the mutation of the high and low noise correlation degree of the noise data point, so as to determine the location and time of occurrence of the interference noise.

[0090] In some embodiments, the second determining module 103 includes:

[0091] The first calculation unit 1031 is used to calculate the noise level of multiple adjacent noise data points on the left and right of each noise data point for the noise data collected by the environmental noise monitor at each location, so as to obtain the correlation between the noise level of each noise data point and the noise data points on its left and right.

[0092] The second calculation unit 1032 is used to calculate the difference between the high and low noise levels of two adjacent noise data points, so as to grasp the difference between the high and low noise levels of the two adjacent noise data points.

[0093] The fourth determining unit 1033 is used to determine the mutation degree of the noise data point, so as to obtain the mutation situation of the high and low noise correlation degree of the noise data point.

[0094] In some embodiments, the mutation degree of the noise data point is determined according to the following formula:

[0095] .

[0096] In the formula, It is The mutation degree of each noise data point reflects the The mutation of the correlation degree between high and low noise of each noise data point, Indicates The average value of the high and low noise correlation of multiple adjacent noise data points to the right of the noise data point reflects the The overall situation of the correlation between the high and low noise of the noise data point and the noise data point on its right, Indicates The average value of the high and low noise correlation of multiple adjacent noise data points on the left side of the noise data point reflects the The overall situation of the correlation between the high and low noise of the noise data point and the noise data point on its left. Indicates The number of adjacent noise data points on the left and right sides of a noise data point The correlation between the high and low noise of the noise data point is The difference between the high and low noise correlation levels of the noise data points reflects the The correlation between the high and low noise of the noise data point is The difference in the degree of correlation between high and low noise of the noise data points, Indicates The serial numbers of multiple adjacent noise data points on the left and right sides of a noise data point. N represents the The number of adjacent noise data points on the left and right sides of a noise data point, and the value is not zero. represents a hyperbolic function, Indicates the serial number of the noise data point collected by the environmental noise monitor at the current location. The larger the The greater the difference in the correlation between the high and low noise of the noise data points on the left and right sides of a noise data point, The larger the The correlation degree of high and low noise of N adjacent noise data points on the left and right sides of a noise data point is the same as that of the The greater the difference in the correlation between high and low noise of the noise data points, the The greater the mutation degree of a noise data point, the more obvious the mutation is. The bigger.

[0097] Environmental noise during rabbit breeding will have an impact on the health of rabbits and poultry, and when there is severe noise, it will also affect the normal life of rabbits and poultry, causing them to react with stress and fear, which will cause them to panic; when rabbits and poultry panic, there will be commotion in the group of rabbits, and the group of rabbits will try to stay away from the noise source due to fright. Therefore, when noise occurs, the noise value of the noise data point collected by the environmental noise monitor close to the noise source will increase, and the group of rabbits will stay away from the noise source due to fright. Therefore, it is particularly important to understand the impact of noise interference on the activities of rabbits.

[0098] The third determination module 104 is used to determine the disorder enhancement factor of the noise data point.

[0099] The disorder enhancement factor of the noise data point can reflect the disorder of the noise data point. The stronger the disorder of the noise data point, the more likely it is that the moment corresponding to the noise data point will have disordered noise data affected by the interference noise, and the position corresponding to the noise data point is more likely to be close to the position where the rabbit group is active after being affected by the interference noise.

[0100] It should be noted that the rabbits will be stressed and move away from the noise source after being disturbed by noise. The environmental noise monitors far away from the noise source will collect gradually dense and disordered noise data due to the approach of the rabbits. Therefore, the disorder enhancement factor of the noise data point is determined to understand the disorder of the noise data point.

[0101] In some embodiments, the third determination module 104 includes:

[0102] The window setting unit 1041 is used to set a window whose length is the threshold length, and the sliding step length of the window is the difference between the horizontal coordinate values ​​of two adjacent noise data points.

[0103] The window can be slid according to the sliding step size to traverse the noisy data.

[0104] In some embodiments, the threshold length may be determined based on the number of the noise data point and the noise data points surrounding it, without specific limitation.

[0105] The first acquisition unit 1042 is used to acquire the number of extreme value points of the noise data points in each window after sliding, so as to capture the high and low fluctuation of the noise value of the local noise data points in the window.

[0106] The third calculation unit 1043 is used to calculate the difference between adjacent maximum values ​​and adjacent minimum values ​​of the noise data points in each window after sliding, so as to obtain the difference between the maximum values ​​and the difference between the minimum values.

[0107] The second acquisition unit 1044 is used to obtain the difference between the noise values ​​corresponding to any maximum point and the minimum point closest to the maximum point in each window after sliding, and take the difference between the noise values ​​corresponding to any maximum point and the minimum point closest to the maximum point as the extreme point difference of the maximum point, so as to obtain the difference between the maximum and the minimum, and grasp the fluctuation of the noise value from high to low.

[0108] The fourth calculation unit 1045 is used to calculate the average value of all extreme point difference values ​​in each window after sliding, and obtain the average value of the window extreme point difference values, so as to grasp the overall situation of the window extreme point difference values.

[0109] The fifth calculation unit 1046 is used to calculate the difference between the average values ​​of the window extreme point difference values ​​of the two adjacent windows on the left and right during sliding, and obtain the difference between the average extreme point difference values ​​of the left window, so as to grasp the difference between the average values ​​of the window extreme point difference values ​​of the two adjacent windows on the left and right.

[0110] The fifth determining unit 1047 is used to determine the disorder enhancement factor of the noise data point, so as to obtain the disorder condition of the noise data point.

[0111] In some embodiments, the disorder enhancement factor of the noise data point is determined according to the following formula:

[0112] .

[0113] In the formula, When all noise data points at the same position are traversed, all windows contain the first The sequence number of the window corresponding to the noise data point, When all noise data points at the same position are traversed, all windows contain the first The number of windows corresponding to the noise data points and the value is not zero, It is The disorder enhancement factor of the noise data point reflects the The disorder of the noise data points, It is The noise data point corresponds to The difference between the average extreme point difference values ​​of the windows reflects the The difference between the average value of the window extreme point difference between a window and its first adjacent window on the right, It is The noise data point corresponds to The number of extreme points of the noise data points in the sliding window is The difference between the number of extreme points of noise data points in the first adjacent window to the right of the window reflects the The difference in the number of extreme points of noise data points in a window and the first adjacent window on its right, is a hyperbolic function, Indicates the serial number of the noise data point collected by the environmental noise monitor at the current location. The bigger, The larger the The larger the The larger the disorder enhancement factor of the noise data point, the The stronger the disorder of a noise data point, the more likely it is that disordered noise data will appear at the moment corresponding to the noise data point after being affected by the interference noise, and the position corresponding to the noise data point is more likely to be close to the position where the rabbit group is active after being affected by the interference noise.

[0114] So far, the unattended rabbit and poultry farming IoT system provided by the embodiment of the present application has captured the interference noise in the noise data and the activity noise of the rabbit group after being affected by the interference noise. In order to further grasp the rabbit activity situation, the fourth determination module 105 is introduced.

[0115] The fourth determination module 105 is used to determine the rabbit activity change value based on the average value of the difference between the disorder enhancement factor of the noise data points collected by the environmental noise monitors at other locations other than the current location at the same time and the disorder enhancement factor of the noise data points collected by the environmental noise monitor at the current location.

[0116] The rabbit activity change value can reflect the rabbit activity situation to better capture the activity noise of rabbits affected by noise.

[0117] In some embodiments, the rabbit activity change value is determined according to the following formula:

[0118] .

[0119] In the formula, Indicates the noise level collected by the environmental noise monitor at the current location. The rabbit activity change value of the noise data point reflects the rabbit activity situation. Indicates the first The disorder enhancement factor of the noise data point is related to the noise data collected by the environmental noise monitor at the current location. The average value of the difference between the disorder enhancement factors of the noise data points reflects the first The overall situation of the difference between the disorder enhancement factors of the noise data points, Indicates the noise level collected by the environmental noise monitor at the current location. The disorder enhancement factor of the noise data point. In this embodiment, the case where the disorder enhancement factor is zero is not considered. represents a hyperbolic function, Indicates the sequence number of the noise data point collected by the environmental noise monitor at the current location or other locations, where the sequence number of the noise data point collected by the environmental noise monitor at the current location and other locations is The noise data points have a corresponding relationship in time value. The environmental noise monitor at the current location collects the first Noise data points and the first noise data points collected by environmental noise monitors at other locations The noise data points are collected at the same time. The bigger, The smaller the The larger the value, the more the environmental noise monitor at the current location has collected the The lower the disorder enhancement factor of the noise data point is, the lower the disorder enhancement factor of the noise data point is. The overall level of the difference between the disorder enhancement factors of the noise data points, that is, the greater the rabbit activity change value of the noise data points collected by the environmental noise monitor at the current location, that is, The larger it is, the more likely the current location is where the interference noise comes from, and the more likely the noise of rabbit activity changes will appear in other locations.

[0120] The fifth determination module 106 is used to determine the noise impact factor based on the mutation degree and the rabbit activity change value.

[0121] The noise impact factor can reflect the impact of noise on the rabbit population.

[0122] In some embodiments, the noise impact factor is determined according to the following formula:

[0123] .

[0124] In the formula, Indicates the noise level collected by the environmental noise monitor at the current location. The noise impact factor of each noise data point reflects the impact of noise on the rabbit population. Indicates the noise level collected by the environmental noise monitor at the current location. The mutation degree of each noise data point is Indicates the noise level collected by the environmental noise monitor at the current location. The change value of rabbit activity for each noise data point, Indicates the serial number of the noise data point collected by the environmental noise monitor at the current location. The bigger, The larger the value, the more obvious the mutation of the noise data point collected by the environmental noise monitor at the current location. The larger the change value of the rabbit activity of the noise data point collected by the environmental noise monitor at the current location, the greater the change of the rabbit activity of the noise data point collected by the environmental noise monitor at the current location. The larger it is, the more the rabbits are affected by the noise.

[0125] The noise reduction module 107 is used to respond to the noise impact factors of multiple locations at a certain moment being greater than the noise threshold, to perform noise reduction processing on the rabbit and poultry farm, and to perform manual intervention in time to ensure that the breeding of rabbits and poultry is not affected.

[0126] In some embodiments, the noise threshold may be 0.7.

[0127] In some embodiments, the noise reduction module 107 can be specifically used to: in response to the noise impact factor of a certain location at a certain moment being greater than the noise threshold, mark the location as a high-impact location; in response to multiple locations being marked as high-impact locations at a certain moment, perform noise reduction processing on the rabbit and poultry farm.

[0128] In summary, the present invention provides an unattended rabbit and poultry farming Internet of Things system, which can promptly locate the location of interference noise and grasp the activities of rabbits affected by the interference noise, so that manual intervention can be carried out in a timely and accurate manner to provide a normal growth environment for the rabbit population.

[0129] In a second aspect, the present invention provides an environmental parameter monitoring method, comprising: Figure 2 , the method comprising:

[0130] Step 201, obtaining noise data collected by multiple environmental noise monitors located at different locations in the rabbit and poultry farm, the noise data including multiple noise data points, the horizontal axis value of the noise data point is the time value, and the vertical axis value is the noise value.

[0131] Step 202, based on the noise data collected by the environmental noise monitor at each location, determine the correlation between high and low noise, wherein the correlation between the high and low noise is used to reflect the correlation between the noise value of each noise data point and the noise values ​​of the surrounding noise data points.

[0132] Step 203, determining the mutation degree of the noise data point based on the correlation degree between the high noise and low noise of the noise data point.

[0133] Step 204, determining the disorder enhancement factor of the noise data point.

[0134] Step 205, determining the rabbit activity change value based on the average value of the difference between the disorder enhancement factor of the noise data points collected by the environmental noise monitors at other locations other than the current location at the same time and the disorder enhancement factor of the noise data points collected by the environmental noise monitor at the current location.

[0135] Step 206, determining the noise impact factor based on the mutation degree and the rabbit activity change value.

[0136] Step 207, in response to the noise impact factors of multiple locations at a certain moment being greater than the noise threshold, noise reduction processing is performed on the rabbit and poultry farm.

[0137] In summary, the present invention provides an environmental parameter monitoring method, which can timely find the location of the interference noise and grasp the activities of the rabbits after being affected by the interference noise, so that artificial intervention can be carried out in a timely and accurate manner to provide a normal growth environment for the rabbit group.

[0138] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0139] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. An unattended rabbit and poultry farming Internet of Things system, characterized in that: The system comprises: An acquisition module is used to acquire noise data collected by multiple environmental noise monitors located at different locations in the rabbit and poultry farm, wherein the noise data includes multiple noise data points, wherein the horizontal axis value of the noise data point is a time value, and the vertical axis value is a noise value; A first determination module is used to determine the correlation between high and low noise based on the noise data collected by the environmental noise monitor at each location, wherein the correlation between the high and low noise is used to reflect the correlation between the noise value of each noise data point and the noise values ​​of the surrounding noise data points; A second determination module is used to determine the mutation degree of the noise data point based on the correlation degree of high and low noise of the noise data point; A third determination module is used to determine the disorder enhancement factor of the noise data point; A fourth determination module is used to determine the rabbit activity change value based on the average value of the difference between the disorder enhancement factor of the noise data point collected by the environmental noise monitor at other locations other than the current location at the same time and the disorder enhancement factor of the noise data point collected by the environmental noise monitor at the current location; A fifth determination module, used for determining a noise impact factor based on the mutation degree and the rabbit activity change value; The noise reduction module is used to perform noise reduction processing on the rabbit and poultry farm in response to the noise impact factors of multiple positions at a certain moment being greater than the noise threshold.

2. The unattended rabbit and poultry farming Internet of Things system according to claim 1, characterized in that: The first determining module comprises: A segmentation processing unit is used to segment the noise data collected by the environmental noise monitor at each location, and each threshold number of adjacent noise data points is regarded as a noise area to obtain multiple noise areas; A first determining unit, used to determine the maximum value of all noise data points in the noise area; A second determination unit is used to calculate, for each noise region, a difference between a noise value of a noise data point with a maximum value in the noise region and noise values ​​of other noise data points in the noise region; A fitting unit is used to fit the maximum value of the noise data points in all noise areas to obtain the upper envelope of the noise data points; A periodicity unit for determining the autocorrelation function and the autocorrelation period based on the upper envelope of the noise data points; A comparison data point unit, used to use a noise data point in the next autocorrelation cycle of the autocorrelation cycle where a noise data point is located and in the same order as the noise data point in the autocorrelation cycle where the noise data point is located as a comparison data point for the noise data point; The third determination unit is used to determine the correlation degree of high noise and low noise of each noise data point.

3. The unattended rabbit and poultry farming Internet of Things system according to claim 1, characterized in that: The second determining module comprises: A first calculation unit is used to calculate the high and low noise levels of multiple adjacent noise data points on the left and right of each noise data point for the noise data collected by the environmental noise monitor at each location; The second calculation unit is used to calculate the difference between the high and low noise levels of two adjacent noise data points; The fourth determining unit is used to determine the mutation degree of the noise data point.

4. The unattended rabbit and poultry farming Internet of Things system according to claim 1, characterized in that: The third determination module includes: A window setting unit, used to set a window with a length equal to a threshold length, wherein a sliding step length of the window is a difference between the horizontal coordinate values ​​of two adjacent noise data points; A first acquisition unit is used to acquire the number of extreme value points of noise data points in each window after sliding; A third calculation unit is used to calculate the difference between adjacent maximum values ​​and adjacent minimum values ​​of the noise data points in each window after sliding; A second acquisition unit is used to acquire a difference between a noise value corresponding to any maximum value point and a minimum value point closest to the maximum value point in each window after sliding, and use the difference between the noise value corresponding to any maximum value point and the minimum value point closest to the maximum value point as the extreme value point difference of the maximum value point; A fourth calculation unit is used to calculate the average value of all the extreme point difference values ​​in each window after sliding, so as to obtain the average value of the window extreme point difference values; A fifth calculation unit, used for calculating the difference between the average values ​​of the window extreme point difference values ​​of the two adjacent windows on the left and right during sliding, and obtaining the difference between the average extreme point difference values ​​of the left window; The fifth determining unit is used to determine the disorder enhancement factor of the noise data point.

5. The unattended rabbit and poultry farming Internet of Things system according to claim 2, characterized in that: The correlation between high and low noise for each noise data point is determined according to the following formula: ； In the formula, Indicates The correlation degree of high and low noise of each noise data point, Indicates the serial number of the noise data point collected by the environmental noise monitor at the current location. Indicates The serial numbers of other noise data points in the noise region where the noise data point is located, Indicates The number of other noise data points in the noise region where the noise data point is located, Indicates The fluctuation of other noise data points in the noise region where the noise data point is located, Indicates The first of the other noise data points in the noise region where the noise data point is located The noise value of the noise data point, Indicates The first of the other noise data points in the noise region where the noise data point is located The noise data point corresponds to The noise value of the comparison data point, Indicates The first of the other noise data points in the noise region where the noise data point is located The serial number of the comparison data point of the noise data point, represents a hyperbolic function, where the fluctuation of other noise data points in the noise region where the noise data point is located is It is the difference between the noise value of the noise data point that obtains the maximum value in the noise area where the noise data point is located and the average noise value of other noise data points in the noise area where the noise data point is located.

6. The unattended rabbit and poultry farming Internet of Things system according to claim 3, characterized in that: According to the following formula, the mutation degree of the noise data point is determined: ； In the formula, It is The mutation degree of each noise data point is Indicates The average value of the high and low noise correlation degree of multiple adjacent noise data points to the right of a noise data point, Indicates The average value of the high and low noise correlation degree of multiple adjacent noise data points to the left of a noise data point, Indicates The number of adjacent noise data points on the left and right sides of a noise data point The correlation between the high and low noise of the noise data point is The difference between the high and low noise correlation levels of the noise data points, Indicates The serial numbers of multiple adjacent noise data points on the left and right sides of a noise data point. N represents the The number of multiple adjacent noise data points on the left and right sides of a noise data point, represents a hyperbolic function, Indicates the serial number of the noise data point collected by the environmental noise monitor at the current location.

7. The unattended rabbit and poultry farming Internet of Things system according to claim 4, characterized in that: According to the following formula, the disorder enhancement factor of the noise data point is determined: ； In the formula, When all noise data points at the same position are traversed, all windows contain the first The sequence number of the window corresponding to the noise data point, When all noise data points at the same position are traversed, all windows contain the first The number of windows corresponding to the noise data points, It is The disorder enhancement factor of the noise data points is It is The noise data point corresponds to The difference between the average extreme point differences of the windows, It is The noise data point corresponds to The number of extreme points of the noise data points in the sliding window is The difference between the number of extreme points of the noise data points in the first adjacent window to the right of the window, is a hyperbolic function, Indicates the serial number of the noise data point collected by the environmental noise monitor at the current location.

8. The unattended rabbit and poultry farming Internet of Things system according to claim 1, characterized in that: Determine the rabbit activity change value according to the following formula: ； In the formula, Indicates the noise level collected by the environmental noise monitor at the current location. The change value of rabbit activity for each noise data point, Indicates the first The disorder enhancement factor of the noise data point is related to the noise data collected by the environmental noise monitor at the current location. The average value of the difference between the disorder enhancement factors of the noise data points, Indicates the noise level collected by the environmental noise monitor at the current location. The disorder enhancement factor of the noise data points is represents a hyperbolic function, Indicates the sequence number of the noise data point collected by the environmental noise monitor at the current location or other locations, where the sequence number of the noise data point collected by the environmental noise monitor at the current location and other locations is The noise data points have a corresponding relationship in time value. The environmental noise monitor at the current location collects the first Noise data points and the first noise data points collected by environmental noise monitors at other locations The noise data points are collected at the same time.

9. The unattended rabbit and poultry farming Internet of Things system according to claim 1, characterized in that: Determine the noise impact factor according to the following formula: ； In the formula, Indicates the noise level collected by the environmental noise monitor at the current location. The noise impact factor of the noise data point is Indicates the noise level collected by the environmental noise monitor at the current location. The mutation degree of each noise data point is Indicates the noise level collected by the environmental noise monitor at the current location. The change value of rabbit activity for each noise data point, Indicates the serial number of the noise data point collected by the environmental noise monitor at the current location.

10. A method for monitoring environmental parameters, characterized in that: The method comprises: Acquire noise data collected by multiple environmental noise monitors located at different locations in a rabbit and poultry farm, wherein the noise data includes multiple noise data points, wherein the horizontal axis value of the noise data point is a time value, and the vertical axis value is a noise value; Based on the noise data collected by the environmental noise monitor at each location, determine the correlation degree of high and low noise, wherein the correlation degree of high and low noise is used to reflect the correlation between the noise value of each noise data point and the noise values ​​of the surrounding noise data points; Determine the mutation degree of the noise data point based on the correlation degree between high and low noise of the noise data point; Determine the disorder enhancement factor of the noise data points; Determine the rabbit activity change value based on the average value of the difference between the disorder enhancement factor of the noise data point collected by the environmental noise monitor at other locations other than the current location at the same time and the disorder enhancement factor of the noise data point collected by the environmental noise monitor at the current location; Determining a noise impact factor based on the mutation degree and the rabbit activity change value; In response to the noise impact factors of multiple locations at a certain moment being greater than the noise threshold, noise reduction treatment is performed on the rabbit and poultry farm.

Images