Cassava breeding environment monitoring method and system based on data analysis

Abstract

The present invention relates to the field of data processing technology, and in particular to a cassava breeding environment monitoring method and system based on data analysis. The method comprises: obtaining original monitoring data of a breeding sensor; obtaining root tuber growth state parameters of the cassava according to the original monitoring data; obtaining a cassava growth interference degree index of the original monitoring data; obtaining a precision loss parameter of the original monitoring data according to the root tuber growth state parameters and the growth interference degree index; and performing data cleaning on the original monitoring data according to the precision loss parameter to obtain target monitoring data. The embodiment of the present invention can dynamically analyze the precision loss parameter of the monitoring data according to the growth condition of the cassava, and clean the original monitoring data according to the precision loss parameter, thereby improving the data accuracy of the monitoring data.

Description

Technical Field

[0001] The invention belongs to the technical field of data processing, and in particular relates to a cassava breeding environment monitoring method and system based on data analysis. Background Art

[0002] Cassava is an important tropical root crop worldwide, especially grown as a staple food and industrial raw material in many parts of Africa, Asia and Latin America. Cassava cultivation has high requirements for environmental conditions, especially in the seedling stage. Good seedling management is the basis for high yield and high quality of cassava. Cassava seedlings are mainly grown by cuttings, which are cut into cuttings of appropriate lengths from branches of mature cassava plants and then grown and transplanted into the field. The seedling process involves rooting, germination and initial growth of the cuttings, and environmental factors (such as temperature, humidity, light, soil conditions, etc.) are crucial to this process.

[0003] In the actual breeding process, as the cassava seedlings develop, the cassava roots will gradually expand at different growth stages, and the cassava seedling environment monitoring system has a certain number of sensors arranged under and above the soil. When the cassava roots grow to a certain extent, they will affect the soil state of the breeding test site, thereby interfering with the detection accuracy of the sensors in the soil, making it difficult to obtain accurate breeding environment data, and easily affecting the results of breeding environment data analysis. Therefore, it is necessary to clean the original monitoring data to improve the accuracy of the monitoring data. Summary of the invention

[0004] In order to solve the above problems, the first aspect of the present invention provides a cassava breeding environment monitoring method based on data analysis, the method comprising:

[0005] Obtain the original monitoring data of breeding sensors;

[0006] According to the original monitoring data, obtaining the root tuber growth state parameters of the cassava;

[0007] Obtaining the cassava growth interference degree index of the original monitoring data;

[0008] According to the tuberous root growth state parameter and the growth interference degree index, obtaining the precision loss parameter of the original monitoring data;

[0009] The original monitoring data is cleaned according to the precision loss parameter to obtain target monitoring data.

[0010] Optionally, the original monitoring data includes ground sensor monitoring time series data and underground sensor monitoring time series data, and the step of obtaining the root tuber growth state parameters of the cassava includes:

[0011] Using the DTW algorithm to perform time series matching on the above-ground sensor monitoring time series data and the underground sensor monitoring time series data to obtain a matching data sequence combination;

[0012] Obtaining an absolute value of a correlation coefficient of the matching data sequence combination, wherein the absolute value of the correlation coefficient represents the degree to which the underground sensor is affected by the ground sensor;

[0013] Obtaining a mean value of the degree to which any of the underground sensors is affected by all the above-ground sensors;

[0014] Obtaining the mean of the time series difference between any of the underground sensor monitoring time series data and all the ground sensor monitoring time series data;

[0015] According to the mean of the impact degree and the mean of the time series difference, the root tuber growth state parameters of the cassava are obtained.

[0016] Optionally, the original monitoring data includes underground sensor monitoring time series data, and the cassava growth interference degree index of obtaining the original monitoring data includes:

[0017] Obtain the cassava growth impact coefficient from underground sensor monitoring time series data;

[0018] Obtaining cassava growth disturbance factors from underground sensor monitoring time series data;

[0019] According to the cassava growth influence coefficient and the cassava growth interference factor, the cassava growth interference degree index of the original monitoring data is obtained.

[0020] Optionally, the step of obtaining the cassava growth influence coefficient of underground sensor monitoring time series data includes:

[0021] Obtaining a fitting curve of the underground sensor monitoring time series data;

[0022] Segmenting the fitting curve according to the extreme points of the fitting curve to obtain a plurality of monotonic intervals;

[0023] Obtaining the mean of the derivatives of the data points in any of the monotonic intervals;

[0024] Obtaining a first difference, where the first difference is the difference between the mean of all data points in any of the monotonic intervals and the mean of all data points in the fitting curve;

[0025] The cassava growth influence coefficient of the underground sensor monitoring time series data is obtained according to the mean value of the derivative of the data points in the monotonic interval and the first difference.

[0026] Optionally, the step of obtaining the cassava growth interference factor from underground sensor monitoring time series data includes:

[0027] Obtaining a second difference, where the second difference is a difference between any two adjacent data points in any of the monotonic intervals;

[0028] Obtaining the variance of the second difference;

[0029] Obtaining the mean of the variance of all the monotonic intervals;

[0030] The mean value of the variance is used as the cassava growth interference factor of the underground sensor monitoring time series data.

[0031] Optionally, the obtaining of the cassava growth interference degree index of the original monitoring data includes:

[0032] Obtaining a normalized value of the cassava growth influence coefficient;

[0033] According to the normalized value of the cassava growth influence coefficient and the cassava growth interference factor, the cassava growth interference degree index of the original monitoring data is obtained.

[0034] Optionally, obtaining the accuracy loss parameter of the original monitoring data includes:

[0035] Obtaining the product of the tuberous root growth state parameter and the growth interference degree index;

[0036] According to the product, the accuracy loss parameter of the original monitoring data is obtained.

[0037] Optionally, performing data cleaning on the original monitoring data according to the precision loss parameter to obtain target monitoring data includes:

[0038] Based on the precision loss parameter, a filtering and denoising algorithm is used to perform denoising processing on the original monitoring data to obtain target monitoring data.

[0039] Optionally, the filtering and denoising algorithm includes a Wiener filtering algorithm, and based on the precision loss parameter, the filtering and denoising algorithm is used to perform denoising processing on the original monitoring data to obtain target monitoring data, including:

[0040] Obtaining the mean lengths of the multiple monotonic intervals;

[0041] Using the length mean as the length of the filter kernel of the Wiener filter;

[0042] Using the precision loss parameter as a filtering parameter of the Wiener filter;

[0043] The original monitoring data is subjected to noise reduction processing using the Wiener filtering algorithm to obtain target monitoring data.

[0044] A second aspect of the present invention provides a cassava breeding environment monitoring system based on data analysis, the system comprising a breeding sensor and a breeding monitoring platform, the breeding monitoring platform comprising:

[0045] a memory having a computer program stored thereon;

[0046] A processor is used to execute the computer program in the memory to implement the steps of any one of the methods in the first aspect.

[0047] In summary, the present invention provides a cassava breeding environment monitoring method based on data analysis, the method comprising: obtaining original monitoring data of a breeding sensor; obtaining root tuber growth state parameters of the cassava according to the original monitoring data; obtaining a cassava growth interference degree index of the original monitoring data; obtaining a precision loss parameter of the original monitoring data according to the root tuber growth state parameters and the growth interference degree index; performing data cleaning on the original monitoring data according to the precision loss parameter to obtain target monitoring data. The present invention can dynamically analyze the precision loss parameter of the monitoring data according to the growth condition of cassava, and clean the original monitoring data according to the precision loss parameter, thereby improving the data accuracy of the monitoring data. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the implementation scheme of the present invention, the drawings required for use in the implementation scheme will be briefly introduced below. It should be understood that the drawings only show certain implementation schemes of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on the drawings without paying creative work.

[0049] Figure 1 is a flow chart of a cassava breeding environment monitoring method based on data analysis according to an exemplary embodiment;

[0050] Figure 2 is a flow chart showing a method for obtaining root tuber growth state parameters of cassava according to an exemplary embodiment;

[0051] Figure 3 is a flow chart of a method for obtaining a cassava growth interference degree index of original monitoring data according to an exemplary embodiment;

[0052] Figure 4 is a flow chart showing a method for obtaining cassava growth influence coefficients from underground sensor monitoring time series data according to an exemplary embodiment;

[0053] Figure 5is a flow chart showing a method for obtaining cassava growth interference factors from underground sensor monitoring time series data according to an exemplary embodiment;

[0054] Figure 6 is a flow chart showing another method for obtaining a cassava growth interference degree index of original monitoring data according to an exemplary embodiment;

[0055] Figure 7 is a flow chart showing a method for obtaining precision loss parameters of original monitoring data according to an exemplary embodiment;

[0056] Figure 8 It is a flow chart of a method for performing data cleaning on original monitoring data according to an accuracy loss parameter to obtain target monitoring data according to an exemplary embodiment;

[0057] Fig. 9 is a flow chart of a method for performing noise reduction processing on raw monitoring data by using a filtering noise reduction algorithm based on an accuracy loss parameter to obtain target monitoring data according to an exemplary embodiment;

[0058] Fig.10 is a block diagram of a cassava breeding environment monitoring system based on data analysis according to an exemplary embodiment;

[0059] Fig.11 It is a block diagram of a breeding monitoring platform according to an exemplary embodiment. DETAILED DESCRIPTION

[0060] In order to clearly illustrate the technical features of the present invention, the present invention is described in detail below through specific implementation methods in conjunction with the accompanying drawings.

[0061] Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0062] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0063] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0064] It should be noted that the concepts such as "first" and "second" mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0065] It should be noted that the modifications of "one" and "multiple" mentioned in the present invention are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more". In the description of the present invention, unless otherwise specified, "multiple" refers to two or more than two, and other quantifiers are similar; "at least one item", "one or more items" or similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one item a can represent any number of a; for another example, one or more items of a, b and c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple; "and / or" is a kind of association relationship that describes the associated objects, indicating that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural.

[0066] Although operations or steps are described in a specific order in the drawings in the embodiments of the present invention, it should not be understood that it is required to perform these operations or steps in the specific order shown or in a serial order, or that all the operations or steps shown must be performed to obtain the desired results. In the embodiments of the present invention, these operations or steps may be performed in series; these operations or steps may also be performed in parallel; or some of these operations or steps may be performed.

[0067] Figure 1 FIG. 1 is a flow chart of a method for monitoring cassava breeding environment based on data analysis according to an exemplary embodiment. Figure 1 As shown, the embodiment of the present invention provides a cassava breeding environment monitoring method based on data analysis, which may include the following steps:

[0068] In step S10, the original monitoring data of the breeding sensor is obtained.

[0069] In this step, the original monitoring data of the breeding sensor is obtained. Exemplarily, the breeding sensor can be at least one of a temperature sensor, a humidity sensor, a light sensor, a soil nutrient sensor (such as nitrogen, phosphorus, potassium concentration), a CO sensor, and a pH sensor. The breeding sensor is used to collect the current breeding environment data, and the collection time is recorded to obtain the original monitoring data of the breeding sensor.

[0070] In step S20, the root tuber growth state parameters of the cassava are obtained according to the original monitoring data.

[0071] In this step, the tuber growth state parameters of cassava are obtained based on the original monitoring data. Exemplarily, the DTW (Dynamic Time Warping) algorithm can be used to match the time series data of the aboveground sensor monitoring and the underground sensor monitoring to obtain a matching data sequence combination, and then the absolute value of the correlation coefficient of the matching data sequence combination is obtained, the absolute value of the correlation coefficient represents the degree of influence of the underground sensor by the aboveground sensor, and then the mean of the degree of influence of any underground sensor by all aboveground sensors is obtained, and then the mean of the time difference between any underground sensor monitoring time series data and all aboveground sensor monitoring time series data is obtained, and finally the tuber growth state parameters of cassava are obtained based on the mean of the influence degree and the mean of the time difference.

[0072] In step S30, the cassava growth interference degree index of the original monitoring data is obtained.

[0073] In this step, the cassava growth interference degree index of the original monitoring data is obtained. Exemplarily, the cassava growth influence coefficient of the underground sensor monitoring time series data can be obtained first, and then the cassava growth interference factor of the underground sensor monitoring time series data can be obtained, and then the cassava growth interference degree index of the original monitoring data can be obtained based on the cassava growth influence coefficient and the cassava growth interference factor.

[0074] In step S40, the precision loss parameter of the original monitoring data is obtained according to the tuberous root growth state parameter and the growth interference degree index.

[0075] In this step, the precision loss parameter of the original monitoring data is obtained according to the root growth state parameter and the growth interference degree index. Exemplarily, the product of the root growth state parameter and the growth interference degree index can be obtained first, and then the precision loss parameter of the original monitoring data can be obtained according to the product.

[0076] In step S50, the original monitoring data is cleaned according to the precision loss parameter to obtain target monitoring data.

[0077] In this step, the original monitoring data is cleaned according to the precision loss parameter to obtain the target monitoring data. Exemplarily, the original monitoring data can be subjected to noise reduction processing using a filtering noise reduction algorithm based on the precision loss parameter to obtain the target monitoring data.

[0078] In summary, the embodiment of the present invention provides a cassava breeding environment monitoring method based on data analysis, the method comprising: obtaining the original monitoring data of the breeding sensor; obtaining the tuber growth state parameters of the cassava according to the original monitoring data; obtaining the cassava growth interference degree index of the original monitoring data; obtaining the precision loss parameter of the original monitoring data according to the tuber growth state parameters and the growth interference degree index; performing data cleaning on the original monitoring data according to the precision loss parameter to obtain target monitoring data. The embodiment of the present invention can dynamically analyze the precision loss parameter of the monitoring data according to the growth condition of cassava, and clean the original monitoring data according to the precision loss parameter, thereby improving the data accuracy of the monitoring data.

[0079] Figure 2 FIG. 1 is a flow chart showing a method for obtaining the growth state parameters of cassava roots according to an exemplary embodiment. Figure 2 As shown, the original monitoring data includes ground sensor monitoring time series data and underground sensor monitoring time series data, and the acquisition of the cassava root growth state parameters may include the following steps:

[0080] In step S201, the DTW algorithm is used to perform time series matching on the above-ground sensor monitoring time series data and the underground sensor monitoring time series data to obtain a matching data sequence combination.

[0081] In this step, the DTW algorithm is used to match the time series data monitored by the above-ground sensors and the time series data monitored by the underground sensors to obtain a matching data sequence combination. For example, cassava breeding is a process based on the natural environment to select and cultivate cassava varieties with excellent traits to improve crop yield, disease resistance and other economic values. Its purpose is to ensure the smooth breeding process and evaluate the stress resistance and genetic improvement feedback of cassava varieties. The seedling cultivation environment will be affected by changes in the natural state. In order to evaluate the impact of changes in the natural state of the current breeding environment on the soil state, it is necessary to segment the data change characteristics of some sensors.

[0082] Sensors are divided into above-ground sensors and underground sensors according to their locations, where the underground sensor sensing components (such as sensor probes or probes, etc.) are located inside the soil. The soil environment during cassava breeding is monitored by underground sensors, and the soil environment is affected by the external environment. Before further analyzing the soil sensor data, it is necessary to judge the sensitivity of different underground sensor data to external influences in order to determine the impact of above-ground factors on underground sensor data.

[0083] The time series data of each sensor is plotted in the form of a signal broken line. There is usually a certain delay between the impact of the air environment changes above the ground and the impact on the ground below and being detected by the sensor, so the signals cannot be directly compared; the DTW algorithm is used to re-match the time series of the underground sensor and the ground sensor signals; for the data after the re-matching of the signals of any combination of ground and underground sensors, a matching sequence is established (any combination of underground sensors and any combination of ground sensors has two matching sequences corresponding to the signal elements of the ground and underground sensors respectively), where the sequence order is the processed signal time series order, and the sequence elements are the elements corresponding to the matching order. The DTW algorithm ensures that the signals from different sources can match each other on the time axis through nonlinear adjustment, so that a matching data sequence combination can be obtained.

[0084] In step S202, the absolute value of the correlation coefficient of the matching data sequence combination is obtained, and the absolute value of the correlation coefficient represents the degree to which the underground sensor is affected by the ground sensor.

[0085] In this step, the absolute value of the correlation coefficient of the matching data series combination is obtained , the absolute value of the correlation coefficient Characterizes the degree to which underground sensors are affected by ground sensors. For example, DTW matching reduces the delay of the impact of ground natural state changes on underground sensors, and then the matched data is placed in a sequence to calculate the absolute value of the correlation coefficient. , the absolute value represents the impact of the ground environmental conditions monitored by the current above-ground sensor on the soil conditions monitored by the underground sensor. The larger the value, the greater the impact.

[0086] After obtaining the degree of influence, the current tuber growth status of cassava was evaluated in combination with the specific data changes of the above-ground sensors: different developmental stages of cassava seedlings have different impacts on external environmental conditions. For example, the water absorption and fertilizer nutrient absorption rate during the germination and seedling stages are lower than those during the tuber formation and growth stages. At this time, the underground sensors respond relatively positively to the environmental changes above ground, that is, the underground sensors are more affected by the above-ground sensors.

[0087] In step S203, the average value of the degree to which any underground sensor is affected by all ground sensors is obtained.

[0088] In this step, the average value of the degree of influence of any underground sensor v on all ground sensors is obtained. For example, the larger the value is, the more obvious the influence of the ground sensor on the underground sensor is, and the more likely the cassava seedlings are in the initial growth stage.

[0089] When the growth status of cassava seedlings is evaluated only by the data changes of above-ground and underground sensors, it is easy to be disturbed by the root maturity period: during the root maturity period, the cassava tubers have fully expanded, the above-ground part has almost stopped growing, most of the leaves have fallen off, and the tubers have basically stopped thickening. At this time, the above-ground sensors have a great impact on the underground sensors, so they need to be further distinguished.

[0090] For cassava fields in the tuber maturity stage, the soil is affected by the growth of cassava tubers, causing changes in the physical structure of the soil, such as soil compaction, which affects the burial depth and contact density of soil sensors. In addition to causing inaccurate sensor readings, it may also cause underground sensors to increase the detection delay of changes in ground conditions. Therefore, it is necessary to combine the DTW matching results to further increase the accuracy of cassava growth stage analysis and evaluation.

[0091] In step S204, the average value of the time series difference between any of the underground sensor monitoring time series data and all the ground sensor monitoring time series data is obtained.

[0092] In this step, the time difference between the monitoring time series data of any underground sensor v and the monitoring time series data of all ground sensors is obtained. The mean . Exemplarily, the timing difference The time series difference is obtained by subtracting the time series data of the monitoring time series data of the ground sensor from the time series data of the underground sensor. The mean The larger it is, the longer the response delay of the underground sensor to the change of the aboveground sensor is, and the closer the current cassava tuber is to the maturity stage.

[0093] In step S205, the root tuber growth state parameters of the cassava are obtained according to the mean value of the influence degree and the mean value of the time series difference.

[0094] In this step, the mean of the influence and the mean of the timing differences , obtain the root growth state parameter L of cassava. Exemplarily, the root growth state parameter L of cassava can be obtained by the following formula:

[0095]

[0096] Among them, u represents the number of underground sensors in the current cassava breeding environment. The larger the value of the cassava root growth state parameter L, the closer the current root is to the maturity stage.

[0097] Figure 3 FIG. 1 is a flow chart showing a method for obtaining a cassava growth interference index from raw monitoring data according to an exemplary embodiment. Figure 3 As shown, the original monitoring data includes underground sensor monitoring time series data, and the method of obtaining the cassava growth interference degree index of the original monitoring data may include the following steps:

[0098] In step S301, the cassava growth influence coefficient of the underground sensor monitoring time series data is obtained.

[0099] In this step, the cassava growth influence coefficient of the underground sensor monitoring time series data is obtained. Exemplarily, the fitting curve of the underground sensor monitoring time series data can be first obtained, and then the fitting curve is segmented by the extreme points of the fitting curve to obtain multiple monotonic intervals, and then the mean of the derivatives of the data points in any monotonic interval is obtained, and then the difference between the mean of all data points in any monotonic interval and the mean of all data points in the fitting curve is obtained, and finally, according to the difference between the mean of the derivatives of the data points in the monotonic interval and the mean, the cassava growth influence coefficient of the underground sensor monitoring time series data is obtained.

[0100] In step S302, the cassava growth interference factor of the underground sensor monitoring time series data is obtained.

[0101] In this step, the cassava growth interference factor of the underground sensor monitoring time series data is obtained. Exemplarily, the difference between any two adjacent data points in any monotonic interval can be obtained first, and then the variance of the difference in any monotonic interval can be obtained, and then the mean of the variance in all monotonic intervals can be obtained, and finally the mean of the variance can be used as the cassava growth interference factor of the underground sensor monitoring time series data.

[0102] In step S303, the cassava growth interference degree index of the original monitoring data is obtained according to the cassava growth influence coefficient and the cassava growth interference factor.

[0103] In this step, the cassava growth interference degree index of the original monitoring data is obtained according to the cassava growth influence coefficient and the cassava growth interference factor. Exemplarily, the normalized value of the cassava growth influence coefficient can be obtained first, and then the cassava growth interference degree index of the original monitoring data can be obtained according to the normalized value of the cassava growth influence coefficient and the cassava growth interference factor.

[0104] Figure 4FIG. 1 is a flow chart showing a method for obtaining a cassava growth influence coefficient from underground sensor monitoring time series data according to an exemplary embodiment. Figure 4 As shown, the acquisition of the cassava growth influence coefficient of the underground sensor monitoring time series data may include the following steps:

[0105] In step S3011, a fitting curve of the underground sensor monitoring time series data is obtained.

[0106] In this step, a fitting curve of the underground sensor monitoring time series data is obtained. For example, in order to blur the influence of data fluctuation caused by the reduction of sensor detection accuracy, the underground sensor monitoring time series data can be fitted using the least squares method to obtain a fitting curve, the horizontal axis of the curve is time, and the vertical axis is the sensor data fitting value.

[0107] In step S3012, the fitting curve is segmented according to the extreme points of the fitting curve to obtain a plurality of monotonic intervals.

[0108] In this step, the fitting curve is segmented by the extreme points of the fitting curve to obtain multiple monotonic intervals. For example, for underground sensors, affected by the soil structure, the soil environment changes are usually relatively slow. Therefore, when analyzing the monitoring data of the underground sensor, the data curve can be segmented by the extreme points to obtain multiple monotonic intervals. Different monotonic intervals may represent the impact of different external conditions on the underground sensor monitoring time series data.

[0109] In step S3013, the mean value of the derivative of any data point in the monotonic interval is obtained.

[0110] In this step, the mean of the derivatives of the data points in any monotonic interval j is obtained For example, the derivative of a data point in any monotonic interval j of the fitting curve can be calculated first. , and then according to the derivative of any data point in the monotonic interval j , get the mean of the derivative of any data point in the monotonic interval j ,The larger the value is, the greater the impact of the current sensor’s monitoring data on the current cassava growth stage.

[0111] In addition to the different growth stages of cassava, the impact of the monitoring data is also reflected by the sensor's growth density of the cassava root system near the probe. In areas with dense roots in the soil, the sensor data changes quickly while the monitoring data remains at a certain level for a long time. This is the result of the balance between the long-term impact of the roots on soil conditions and the impact of the natural system. Therefore, it is necessary to further adjust the data change rate in the monotonic interval of the data.

[0112] In step S3014, a first difference is obtained, where the first difference is the difference between the mean of all data points in any monotonic interval and the mean of all data points in the fitting curve.

[0113] In this step, the first difference is obtained , the first difference is the difference between the mean of all data points in any monotonic interval j and the mean of all data points in the fitting curve. Exemplarily, the larger the value is, the greater the impact of the monitoring data of the current sensor on the current cassava growth stage is.

[0114] In step S3015, the cassava growth influence coefficient of the underground sensor monitoring time series data is obtained according to the mean of the derivatives of the data points in the monotonic interval and the first difference.

[0115] In this step, according to the mean of the derivatives of the data points in the monotonic interval j and the first difference , obtain the cassava growth influence coefficient of underground sensor monitoring time series data For example, the cassava growth impact coefficient of underground sensor monitoring time series data It can be obtained by the following formula:

[0116] Formula 2

[0117] Among them, m represents the number of monotonic intervals of the current monitoring data, Represents the normalized value of the time series length of the jth monotonic interval.

[0118] Figure 5 FIG. 1 is a flow chart showing a method for obtaining cassava growth interference factors from underground sensor monitoring time series data according to an exemplary embodiment. Figure 5 As shown, the acquisition of cassava growth interference factors from underground sensor monitoring time series data may include the following steps:

[0119] In step S3021, a second difference is obtained, where the second difference is the difference between any two adjacent data points in any of the monotonic intervals.

[0120] In this step, a second difference △x is obtained, where the second difference △x is the difference between any two adjacent data points in any monotonic interval.

[0121] In step S3022, the variance of the second difference is obtained.

[0122] In this step, the variance of the second difference △x of any monotonic interval is obtained .

[0123] In step S3023, the mean of the variance of all the monotonic intervals is obtained.

[0124] In this step, the mean of the variances of all monotonic intervals is obtained .

[0125] In step S3024, the mean of the variance is used as the cassava growth interference factor of the underground sensor monitoring time series data.

[0126] In this step, the mean of the variances of all monotonic intervals is , as disturbance factors of cassava growth in underground sensor monitoring time series data.

[0127] Figure 6 FIG. 4 is a flow chart showing another method for obtaining a cassava growth interference index from raw monitoring data according to an exemplary embodiment. Figure 6 As shown, the obtaining of the cassava growth interference degree index of the original monitoring data may include the following steps:

[0128] In step S3031, a normalized value of the cassava growth influence coefficient is obtained.

[0129] In this step, the normalized value of the cassava growth impact coefficient is obtained. .

[0130] In step S3032, the cassava growth interference degree index of the original monitoring data is obtained according to the normalized value of the cassava growth influence coefficient and the cassava growth interference factor.

[0131] In this step, the normalized value of the cassava growth impact coefficient and cassava growth interfering factors , obtain the cassava growth disturbance index of the original monitoring data Example, cassava growth disturbance index of the original monitoring data It can be obtained by the following formula:

[0132] Formula 3

[0133] Cassava Growth Disturbance Index The larger the value is, the greater the impact of the current sensor on the cassava growth process is.

[0134] Figure 7 FIG. 1 is a flow chart showing a method for obtaining precision loss parameters of original monitoring data according to an exemplary embodiment. Figure 7 As shown, the obtaining of the accuracy loss parameter of the original monitoring data may include the following steps:

[0135] In step S401, the product of the tuberous root growth state parameter and the growth interference degree index is obtained.

[0136] In this step, the root growth state parameter L and the growth disturbance index are obtained. The product of .

[0137] In step S402, the accuracy loss parameter of the original monitoring data is obtained according to the product.

[0138] In this step, according to the product , get the accuracy loss parameter of the original monitoring data For example, the accuracy loss parameter of the original monitoring data is It can be obtained by the following formula:

[0139] Formula 4

[0140] in, is the hyperbolic tangent function.

[0141] Figure 8 FIG. 1 is a flow chart showing a method for performing data cleaning on raw monitoring data according to an accuracy loss parameter to obtain target monitoring data according to an exemplary embodiment. Figure 8 As shown, the data cleaning of the original monitoring data according to the precision loss parameter to obtain the target monitoring data may include the following steps:

[0142] In step S501, based on the precision loss parameter, a filtering noise reduction algorithm is used to perform noise reduction processing on the original monitoring data to obtain target monitoring data.

[0143] In this step, based on the precision loss parameter, the original monitoring data is subjected to noise reduction processing using a filtering noise reduction algorithm to obtain target monitoring data. Exemplarily, the length mean of multiple monotonic intervals can be obtained first, and then the length mean is used as the length of the filter kernel of the Wiener filter, and then the precision loss parameter is used as the filter parameter of the Wiener filter, and then the original monitoring data is subjected to noise reduction filtering processing using the Wiener filter algorithm to achieve data cleaning to obtain target monitoring data, thereby improving the accuracy of the monitoring data.

[0144] Fig. 9 1 is a flow chart showing a method for performing noise reduction processing on raw monitoring data using a filtering noise reduction algorithm based on an accuracy loss parameter to obtain target monitoring data according to an exemplary embodiment. Fig. 9As shown, the filtering noise reduction algorithm includes a Wiener filtering algorithm, and based on the precision loss parameter, the filtering noise reduction algorithm is used to perform noise reduction processing on the original monitoring data to obtain target monitoring data, which may include the following steps:

[0145] In step S5011, the mean lengths of the multiple monotonic intervals are obtained.

[0146] In this step, the mean of the time lengths of multiple monotonic intervals is obtained.

[0147] In step S5012, the length mean is used as the length of the filter kernel of the Wiener filter.

[0148] In this step, the mean of the time lengths of multiple monotonic intervals is used as the length of the filter kernel of the Wiener filter.

[0149] In step S5013, the precision loss parameter is used as a filtering parameter of the Wiener filter.

[0150] In this step, the precision loss parameter N is used as the filtering parameter k of the Wiener filter.

[0151] In step S5014, the original monitoring data is subjected to noise reduction processing using the Wiener filtering algorithm to obtain target monitoring data.

[0152] In this step, the original monitoring data is subjected to noise reduction and filtering processing using the Wiener filtering algorithm to achieve data cleaning in order to obtain target monitoring data, thereby improving the accuracy of the monitoring data.

[0153] In summary, the embodiment of the present invention provides a cassava breeding environment monitoring method based on data analysis, the method comprising: obtaining the original monitoring data of the breeding sensor; obtaining the tuber growth state parameters of the cassava according to the original monitoring data; obtaining the cassava growth interference degree index of the original monitoring data; obtaining the precision loss parameter of the original monitoring data according to the tuber growth state parameters and the growth interference degree index; performing data cleaning on the original monitoring data according to the precision loss parameter to obtain target monitoring data. The embodiment of the present invention can dynamically analyze the precision loss parameter of the monitoring data according to the growth condition of cassava, and clean the original monitoring data according to the precision loss parameter, thereby improving the data accuracy of the monitoring data.

[0154] In some embodiments, the present invention further provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the steps of the cassava breeding environment monitoring method based on data analysis provided by the present invention.

[0155] Fig.10FIG. 1 is a block diagram of a cassava breeding environment monitoring system based on data analysis according to an exemplary embodiment. Fig.10 As shown, an embodiment of the present invention provides a cassava breeding environment monitoring system 1000 based on data analysis, including a breeding monitoring platform 1100 and the breeding sensor described in the above embodiment.

[0156] Fig.11 1 is a block diagram of a breeding monitoring platform according to an exemplary embodiment. For example, the breeding monitoring platform 1100 may be provided as a server. Fig.11 The breeding monitoring platform 1100 includes a processing component 1122, which further includes one or more processors, and a memory resource represented by a memory 1132 for storing instructions that can be executed by the processing component 1122, such as an application. The application stored in the memory 1132 can include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1122 is configured to execute instructions to perform the above-mentioned cassava breeding environment monitoring method based on data analysis.

[0157] The breeding monitoring platform 1100 may further include a power supply component 1126 configured to perform power management of the breeding monitoring platform 1100 , a communication component 1150 configured to connect the breeding monitoring platform 1100 to a network, and an input / output interface 1158 . The breeding monitoring platform 1100 may operate based on an operating system stored in the memory 1132 .

[0158] In another exemplary embodiment, a computer program product is also provided, which includes a computer program that can be executed by a programmable electronic device, and the computer program has a code portion for executing the above-mentioned cassava breeding environment monitoring method based on data analysis when executed by the programmable electronic device.

[0159] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A cassava breeding environment monitoring method based on data analysis, characterized in that, The method comprises: Obtain the original monitoring data of breeding sensors; According to the original monitoring data, obtaining the root tuber growth state parameters of the cassava; Obtaining the cassava growth interference degree index of the original monitoring data; According to the tuberous root growth state parameter and the growth interference degree index, obtaining the precision loss parameter of the original monitoring data; Performing data cleaning on the original monitoring data according to the precision loss parameter to obtain target monitoring data; The original monitoring data includes ground sensor monitoring time series data and underground sensor monitoring time series data, and the step of obtaining the root tuber growth state parameters of the cassava includes: Using the DTW algorithm to perform time series matching on the above-ground sensor monitoring time series data and the underground sensor monitoring time series data to obtain a matching data sequence combination; Obtaining an absolute value of a correlation coefficient of the matching data sequence combination, wherein the absolute value of the correlation coefficient represents the degree to which the underground sensor is affected by the ground sensor; Obtaining a mean value of the degree to which any of the underground sensors is affected by all the above-ground sensors; Obtaining the mean of the time series difference between any of the underground sensor monitoring time series data and all the ground sensor monitoring time series data; According to the mean of the impact degree and the mean of the time series difference, obtaining the root tuber growth state parameter of the cassava; The original monitoring data includes underground sensor monitoring time series data, and the cassava growth interference degree index for obtaining the original monitoring data includes: Obtain the cassava growth impact coefficient from underground sensor monitoring time series data; Obtaining cassava growth disturbance factors from underground sensor monitoring time series data; According to the cassava growth influence coefficient and the cassava growth interference factor, obtaining the cassava growth interference degree index of the original monitoring data; The method of obtaining the cassava growth influence coefficient of underground sensor monitoring time series data includes: Obtaining a fitting curve of the underground sensor monitoring time series data; Segmenting the fitting curve according to the extreme points of the fitting curve to obtain a plurality of monotonic intervals; Obtaining the mean of the derivatives of the data points in any of the monotonic intervals; Obtaining a first difference, where the first difference is the difference between the mean of all data points in any of the monotonic intervals and the mean of all data points in the fitting curve; Obtaining a cassava growth influence coefficient of the underground sensor monitoring time series data according to the mean of the derivatives of the data points in the monotonic interval and the first difference; The method for obtaining the cassava growth interference factors of underground sensor monitoring time series data includes: Obtaining a second difference, where the second difference is a difference between any two adjacent data points in any of the monotonic intervals; Obtaining the variance of the second difference; Obtaining the mean of the variance of all the monotonic intervals; The mean value of the variance is used as the cassava growth interference factor of the underground sensor monitoring time series data.

2. The cassava breeding environment monitoring method based on data analysis according to claim 1, characterized in that, The method of obtaining the cassava growth interference degree index of the original monitoring data includes: Obtaining a normalized value of the cassava growth influence coefficient; According to the normalized value of the cassava growth influence coefficient and the cassava growth interference factor, the cassava growth interference degree index of the original monitoring data is obtained.

3. The cassava breeding environment monitoring method based on data analysis according to claim 1, characterized in that, The obtaining of the precision loss parameter of the original monitoring data includes: Obtaining the product of the tuberous root growth state parameter and the growth interference degree index; According to the product, the accuracy loss parameter of the original monitoring data is obtained.

4. The cassava breeding environment monitoring method based on data analysis according to claim 1, characterized in that, The step of performing data cleaning on the original monitoring data according to the precision loss parameter to obtain target monitoring data includes: Based on the precision loss parameter, a filtering and denoising algorithm is used to perform denoising processing on the original monitoring data to obtain target monitoring data.

5. The cassava breeding environment monitoring method based on data analysis according to claim 4, characterized in that, The filtering and denoising algorithm includes a Wiener filtering algorithm. Based on the precision loss parameter, the filtering and denoising algorithm is used to perform denoising processing on the original monitoring data to obtain target monitoring data, including: Obtaining the mean lengths of the multiple monotonic intervals; Using the length mean as the length of the filter kernel of the Wiener filter; Using the precision loss parameter as a filtering parameter of the Wiener filter; The original monitoring data is subjected to noise reduction processing using the Wiener filtering algorithm to obtain target monitoring data.

6. A cassava breeding environment monitoring system based on data analysis, characterized in that: The system includes a breeding sensor and a breeding monitoring platform, and the breeding monitoring platform includes: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 5.

Images