Method and device for processing monitoring data of viticis sea-grape based on big data analysis

Abstract

The present application relates to the technical field of sea grape cultivation data processing, and more particularly to a sea grape cultivation monitoring data processing method and device based on big data analysis, which comprises the following steps: acquiring sea grape cultivation data and analyzing light intensity correction parameters, salinity stability parameters and nutrition imbalance indexes; constructing a first environmental correlation model to obtain a lag response coefficient and determine a warning type; constructing a second environmental correlation model to obtain a salt-oxygen coupling index and determine a warning type; constructing a growth potential evaluation model based on the light intensity correction parameters, the nutrition imbalance indexes, the salinity stability parameters, the salt-oxygen coupling index and the sea grape cultivation data to determine a growth potential grade; and updating the construction process of the first environmental correlation model and the second environmental correlation model based on the growth potential grade, the light intensity correction parameters and the sea grape cultivation data. The present application realizes accurate monitoring and analysis of sea grape cultivation data.

Description

Technical Field

[0001] The present invention relates to the technical field of sea grape aquaculture data processing technology, and in particular to a sea grape aquaculture monitoring data processing method and device based on big data analysis. Background Art

[0002] As a high-value green algae, sea grapes have stringent requirements for environmental parameters such as water quality, light intensity, and water flow. Traditional aquaculture relies on manual sampling, which can lead to data lags and large errors. The recent development of agricultural Internet of Things technology has provided technical support for real-time monitoring and intelligent control of sea grape aquaculture environments.

[0003] There are many defects in the existing technology in the processing of sea grape aquaculture monitoring data: traditional methods rely on threshold warnings of single environmental parameters and do not consider the coupling effects of multiple factors, resulting in low warning accuracy and an inability to identify complex environmental stresses; existing model parameters are fixed and cannot be autonomously optimized according to the dynamic changes of the aquaculture environment, and long-term monitoring is prone to deviations; the judgment of the growth status of sea grapes mostly relies on subjective experience or simple physiological indicators, and a synergistic model of multiple factors such as light, salt, nutrition, and water flow has not been established, making it difficult to accurately divide the growth risk level. Summary of the Invention

[0004] The object of the present invention is to provide a method and device for processing sea grape aquaculture monitoring data based on big data analysis, so as to solve at least one of the problems existing in the prior art.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] A method for processing sea grape aquaculture monitoring data based on big data analysis, comprising:

[0007] Obtain sea grape aquaculture data and analyze light intensity correction parameters, salinity stabilization parameters, and nutrient imbalance index;

[0008] The first environmental association model was constructed based on light intensity correction parameters and sea grape aquaculture data to obtain the hysteresis response coefficient and determine the warning type;

[0009] A second environmental association model was constructed based on sea grape aquaculture data to obtain the salt-oxygen coupling index and determine the warning type;

[0010] A growth potential evaluation model was constructed based on light intensity correction parameters, nutrient imbalance index, salinity stability parameters, salt-oxygen coupling index and sea grape culture data to determine the growth potential level;

[0011] The construction process of updating the first and second environmental association models based on growth potential energy levels, light intensity correction parameters and sea grape cultivation data.

[0012] Furthermore, the spectral light intensity is corrected by spectral weight to obtain a light intensity correction parameter. The expression of the light intensity correction parameter is: PARc=0.46×Blue+0.32×Red+0.22×Green, where PARc represents the light intensity correction parameter, Blue represents the light intensity of blue light in the spectral light intensity, Red represents the light intensity of red light in the spectral light intensity, and Green represents the light intensity of green light in the spectral light intensity.

[0013] Furthermore, a salinity stability parameter is determined based on a salinity standard deviation parameter, and the expression of the salinity stability parameter is: Sst=1-(SD / sd), where Sst represents the salinity stability parameter, SD represents the salinity standard deviation parameter, and sd represents the preset gradient parameter.

[0014] Furthermore, the nutritional factor parameters are compared with the preset factor ratio to establish a nutritional imbalance index. If the nutritional factor parameter is greater than the preset factor ratio, the expression of the nutritional imbalance index is set to: Nb=|lg(NP)-lg16|×1.5; otherwise, the expression of the nutritional imbalance index is set to: Nb=|lg(NP)-lg16|×0.8, where Nb represents the nutritional imbalance index and NP represents the nutritional factor parameter.

[0015] Furthermore, the absolute value of the difference between the light intensity correction parameter and the preset deviation parameter is used as the light deviation, and the change in nitrate concentration within 3 hours is used as the nitrate concentration change parameter;

[0016] The hysteresis response coefficient was analyzed based on the light deviation and nitrate concentration variation parameters. The expression of the hysteresis response coefficient is: LRC=cov(ΔPARc,ΔNO3) / [σ(ΔPARc)×σ(ΔNO3)], where LRC represents the hysteresis response coefficient, ΔPARc represents the light deviation, ΔNO3 represents the nitrate concentration variation parameter, and σ() represents the standard deviation of the data in the brackets within one hour.

[0017] The warning type is determined based on the hysteresis response coefficient. If the hysteresis response coefficient is greater than the hysteresis response threshold, the warning type is set to trigger a light nutrition unqualified warning. Otherwise, the warning type is not set.

[0018] Furthermore, the salt-oxygen coupling index is analyzed based on the saturated dissolved oxygen content, dissolved oxygen content and salinity mean parameters. The expression of the salt-oxygen coupling index is: SO=O1 / [O2×(1+0.02×|Sa-sa|)], where SO represents the salt-oxygen coupling index, O1 represents the dissolved oxygen content, O2 represents the saturated dissolved oxygen content, Sa represents the salinity mean parameter, and sa represents the preset salinity parameter;

[0019] The warning type is determined based on the salt-oxygen coupling index. If the salt-oxygen coupling index is less than the salt-oxygen coupling threshold for three consecutive hours, the warning type is set to trigger the salt-oxygen inhibition warning. Otherwise, no warning type is set.

[0020] Furthermore, the growth potential index is determined based on the light intensity correction parameter, the nutrient imbalance index, the salinity stability parameter and the salt-oxygen coupling index. The expression of the growth potential index is: G=μ(PARc) / parc×e -0.5×Nb ×[Sst×μ(SO)] 0.5 , where G represents the growth potential index, parc represents the preset light intensity parameter, and μ() represents the average value of the data in brackets within one hour;

[0021] When the water disturbance coefficient is greater than the water disturbance threshold, the growth potential energy index is attenuated and the expression of the growth potential energy index is corrected to: G = μ (PARc) / parc × e -0.5×Nb ×[Sst×μ(SO)] 0.5 ×[1-0.4×(CV-cv)], where CV represents the water flow disturbance coefficient and cv represents the water flow disturbance threshold;

[0022] The growth potential energy level is determined based on the growth potential energy index, and the growth potential energy level includes a risk zone, a sub-health zone, and an optimal growth zone.

[0023] Furthermore, the light intensity correction parameter of the optimal growth zone with the growth potential energy level within 7 days is extracted as the optimal light intensity parameter, and the salinity mean parameter of the optimal growth zone with the growth potential energy level within 7 days is extracted as the optimal salinity parameter.

[0024] Furthermore, the light intensity reference parameter is analyzed according to the optimal light intensity parameter, and the value of the preset deviation parameter is updated to be equal to the light intensity reference parameter, so as to update the construction process of the first environment association model;

[0025] The salinity benchmark parameters were analyzed according to the optimal salinity parameters, the median of the optimal salinity parameters was used as the salinity benchmark parameter, and the value of the preset salinity parameter was updated to be equal to 0.8 times the salinity benchmark parameter to update the construction process of the second environmental association model.

[0026] On the other hand, the present invention also provides a sea grape cultivation monitoring data processing device based on big data analysis, comprising:

[0027] Data acquisition module, used to obtain sea grape aquaculture data and analyze light intensity correction parameters, salinity stability parameters and nutrient imbalance index;

[0028] A hysteresis analysis module is used to construct a first environmental association model based on the light intensity correction parameter and the sea grape cultivation data to obtain a hysteresis response coefficient and determine the warning type;

[0029] The salt-oxygen analysis module is used to construct a second environmental correlation model based on sea grape aquaculture data to obtain the salt-oxygen coupling index and determine the warning type;

[0030] Growth analysis module, used to construct a growth potential assessment model based on light intensity correction parameters, nutrient imbalance index, salinity stability parameters, salt-oxygen coupling index and sea grape aquaculture data to determine the growth potential level;

[0031] The model updating module is used to update the construction process of the first environment association model and the second environment association model based on the growth potential energy level, light intensity correction parameters and sea grape cultivation data.

[0032] The beneficial effects of the present invention are as follows: through the dual-path early warning mechanism of the light nutrition hysteresis model and the salt-oxygen coupling model, the main types of environmental stress are covered, and the detection rate and accuracy of complex risks are significantly improved. By objectively dividing the growth levels based on the multi-factor dynamic weight model to guide precise intervention strategies, the model parameters are reversely updated by using the optimal growth zone data to form a self-iterative system for monitoring and evaluation optimization, ensuring the adaptability and reliability of long-term monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0034] Figure 1 This is a flow chart of the sea grape aquaculture monitoring data processing method based on big data analysis in this embodiment.

[0035] Figure 2 Flowchart of the analysis method of key parameters of this embodiment.

[0036] Figure 3 This is a flow chart of the method for constructing the growth potential energy evaluation model of this embodiment.

[0037] Figure 4 Schematic diagram of the structure of the sea grape cultivation monitoring data processing device based on big data analysis in this embodiment. DETAILED DESCRIPTION

[0038] In order to more clearly illustrate the present invention, the present invention is further described below in conjunction with preferred embodiments and accompanying drawings. Similar components in the accompanying drawings are represented by the same reference numerals. It should be understood by those skilled in the art that the following detailed description is illustrative rather than restrictive and should not be used to limit the scope of protection of the present invention.

[0039] It should be noted that, although the terms "first," "second," and "third" may be used to describe the embodiments of the present application, the description should not be limited to these terms. These terms are merely used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, "first" may also be referred to as "second," and similarly, "second" may also be referred to as "first."

[0040] See also Figure 1 As shown, this is the sea grape cultivation monitoring data processing method based on big data analysis in this embodiment, including:

[0041] Step S1, obtaining sea grape aquaculture data and analyzing light intensity correction parameters, salinity stability parameters and nutrient imbalance index, the sea grape aquaculture data includes spectral light intensity, salinity standard deviation parameter, salinity mean parameter, nutrient factor parameter, water flow disturbance coefficient and dissolved oxygen content, the spectral light intensity is the photosynthetically active radiation value with a wavelength of 400-700nm, and its unit is μmol / m² / s, the unit of the dissolved oxygen content is mg / L, the salinity standard deviation parameter is the standard deviation of the salinity values ​​of the surface, middle and bottom water samples in the sea grape aquaculture water environment, the salinity is a percentage parameter, and the salinity mean parameter is the standard deviation of the salinity values ​​of the surface, middle and bottom water samples in the sea grape aquaculture water environment. The average salinity values ​​of surface, middle and bottom water samples in the water environment; the nutrient factor parameter is the ratio of nitrate concentration to phosphate concentration; the water flow disturbance coefficient is the coefficient of variation of water flow velocity within one hour, which is calculated as the ratio of the standard deviation of water flow velocity within one hour to the average value of water flow velocity within one hour; the sea grape aquaculture data is obtained through background data analysis of the sea grape aquaculture environment data management; the dissolved oxygen content, salinity, light intensity, water flow velocity, nitrate concentration and phosphate concentration are collected by sensors installed in the sea grape growth environment and uploaded to the sea grape aquaculture environment data management system.

[0042] See also Figure 2 As shown, it is an analysis method for key parameters, including:

[0043] Step S11 , performing spectral weight correction on the spectral illumination intensity to obtain a light intensity correction parameter.

[0044] Specifically, in step S11 described in this embodiment, the spectral light intensity is spectrally weighted corrected to obtain a light intensity correction parameter. The expression of the light intensity correction parameter is: PARc=0.46×Blue+0.32×Red+0.22×Green, where PARc represents the light intensity correction parameter, Blue represents the light intensity of blue light in the spectral light intensity, Red represents the light intensity of red light in the spectral light intensity, and Green represents the light intensity of green light in the spectral light intensity.

[0045] Please continue reading Figure 2 As shown, the analysis method of the key parameters also includes:

[0046] Step S12: determining a salinity stability parameter based on the salinity standard deviation parameter.

[0047] Specifically, in step S12 of this embodiment, the salinity stability parameter is determined based on the salinity standard deviation parameter. The expression of the salinity stability parameter is: Sst=1-(SD / sd), where Sst represents the salinity stability parameter, SD represents the salinity standard deviation parameter, and sd represents the preset gradient parameter.

[0048] Specifically, in this embodiment, the preset gradient parameter is set to 0.35. In this embodiment, there is no specific limitation on the setting of the preset gradient parameter. Those skilled in the art can set it freely as long as the setting of the salinity stability parameter is satisfied. The role of the preset gradient parameter is to reset the salinity stability parameter to zero when the salinity standard deviation parameter is greater than the preset gradient parameter.

[0049] Please continue reading Figure 2 As shown, the analysis method of the key parameters also includes:

[0050] Step S13: establishing a nutritional imbalance index based on the nutritional factor parameters.

[0051] Specifically, in step S13 of this embodiment, the nutritional factor parameter is compared with the preset factor ratio to establish a nutritional imbalance index. If the nutritional factor parameter is greater than the preset factor ratio, the expression of the nutritional imbalance index is set to: Nb=|lg(NP)-lg16|×1.5; otherwise, the expression of the nutritional imbalance index is set to: Nb=|lg(NP)-lg16|×0.8, where Nb represents the nutritional imbalance index and NP represents the nutritional factor parameter.

[0052] Specifically, in this embodiment, the preset factor ratio is set to 20. In this embodiment, there is no specific limitation on the setting of the preset factor ratio, and those skilled in the art can freely set it. The setting of the preset factor ratio should meet the requirements of [18,22].

[0053] Specifically, in step S1 of this embodiment, spectral weight correction is performed to improve the biological effectiveness of light intensity analysis, overcoming the defect of traditional PAR values ​​that ignore the differences in photosynthesis between different bands in sea grapes. The salinity stratification stability is quantified using the salinity stability parameter to intuitively reflect the uniformity of water mixing and avoid the risk of osmotic stress caused by sudden salinity changes. The nutrient imbalance index is calculated in sections, and the weights are dynamically adjusted according to the degree of deviation of nutrient factors from the ideal value to accurately identify the inhibitory effect of nitrogen-phosphorus imbalance on growth.

[0054] Please continue readingFigure 1 As shown, the big data analysis-based sea grape cultivation monitoring data processing method further comprises:

[0055] In step S2, a first environment correlation model is constructed based on the light intensity correction parameter and the sea grape cultivation data to obtain a lag response coefficient and determine a warning type.

[0056] Specifically, in step S2, the absolute value of the difference between the light intensity correction parameter and the preset deviation parameter is taken as the light deviation, and the variation of the nitrate concentration within 3 hours is taken as the nitrate concentration variation parameter.

[0057] Specifically, in the present embodiment, the preset deviation parameter is set to 1200. The setting of the preset deviation parameter is not specifically limited in the present embodiment, and can be freely set by those skilled in the art, as long as it meets the analysis of the light deviation.

[0058] Specifically, in step S2, the lag response coefficient is analyzed based on the light deviation and the nitrate concentration variation parameter. The expression of the lag response coefficient is: LRC = cov(ΔPARc, ΔNO3) / [σ(ΔPARc) x σ(ΔNO3)], wherein LRC represents the lag response coefficient, ΔPARc represents the light deviation, ΔNO3 represents the nitrate concentration variation parameter, and σ() represents the standard deviation of the data in the parentheses within one hour.

[0059] Specifically, in step S2, the warning type is determined according to the lag response coefficient. If the lag response coefficient is greater than a lag response threshold, the warning type is set to trigger a light nutrient unqualified warning, otherwise, no warning type is set.

[0060] Specifically, in the present embodiment, the lag response threshold is set to 0.65. The setting of the lag response threshold is not specifically limited in the present embodiment, and can be freely set by those skilled in the art, and the setting of the lag response threshold should meet the condition of [0.6, 0.8].

[0061] Specifically, in step S2, the lag response coefficient is analyzed by using the covariance of the light deviation and the nitrate concentration variation, so as to effectively capture the delayed effect of nutrient absorption after light change, solve the missing warning problem caused by time lag in the traditional method, trigger a light nutrient unqualified warning based on the LRC threshold, intervene in advance in the abnormal nutrient metabolism caused by light intensity fluctuation, and reduce the risk of growth stagnation.

[0062] Please continue to refer to Figure 1 As shown, the big data analysis-based sea grape cultivation monitoring data processing method further comprises:

[0063] Step S3, constructing a second environment correlation model based on the sea grape cultivation data to obtain a salt-oxygen coupling index and determine a warning type.

[0064] Specifically, in step S3 of the embodiment, the saturation dissolved oxygen content of seawater when the oxygen in seawater is in a saturated state is determined using the Weiss equation, which is a set of equations for the relationship between the solubility of oxygen in seawater and temperature and salinity.

[0065] Specifically, in step S3 of the embodiment, the salt-oxygen coupling index is analyzed based on the saturation dissolved oxygen content, the dissolved oxygen content, and the salinity average parameter, and the expression of the salt-oxygen coupling index is SO = O1 / [O2 x (1 + 0.02 x |Sa-sa|)], where SO represents the salt-oxygen coupling index, O1 represents the dissolved oxygen content, O2 represents the saturation dissolved oxygen content, Sa represents the salinity average parameter, and sa represents the preset salinity parameter.

[0066] Specifically, in the embodiment, the preset salinity parameter is set to 32, and in the embodiment, the setting of the preset salinity parameter is not specifically limited, and a person skilled in the art can freely set it, as long as it meets the analysis of the salt-oxygen coupling index.

[0067] Specifically, in step S3 of the embodiment, the warning type is determined according to the salt-oxygen coupling index, and if the salt-oxygen coupling index of the continuous 3 hours is less than the salt-oxygen coupling threshold value, the warning type is set to trigger the salt-oxygen inhibition warning, otherwise, the warning type is not set.

[0068] Specifically, in the embodiment, the salt-oxygen coupling threshold value is set to 0.8, and in the embodiment, the setting of the salt-oxygen coupling threshold value is not specifically limited, and a person skilled in the art can freely set it, and the setting of the salt-oxygen coupling threshold value should meet the condition that it belongs to [0.75, 0.85].

[0069] Specifically, in step S3 of the embodiment, the salt-oxygen coupling index is calculated by introducing a salinity correction factor to dynamically quantify the influence of salinity on the utilization rate of dissolved oxygen, overcome the limitation that the traditional dissolved oxygen monitoring ignores the interference of salinity, trigger the salt-oxygen inhibition warning through the continuous period determination mechanism, avoid false positives caused by instantaneous fluctuations, and accurately identify the problem of persistent oxygen deficiency.

[0070] Please continue to refer to Figure 1 As shown in the figure, the sea grape cultivation monitoring data processing method based on big data analysis further comprises:

[0071] Step S4, constructing a growth potential evaluation model based on the light intensity correction parameter, the nutrition imbalance index, the salinity stability parameter, the salt-oxygen coupling index, and the sea grape cultivation data to determine the growth potential grade.

[0072] Please refer to Figure 3As shown, it is a method for constructing a growth potential energy evaluation model, including:

[0073] Step S41 : determining a growth potential index based on the light intensity correction parameter, the nutrient imbalance index, the salinity stability parameter, and the salt-oxygen coupling index.

[0074] Specifically, in step S41 of this embodiment, the growth potential index is determined based on the light intensity correction parameter, the nutrient imbalance index, the salinity stability parameter, and the salt-oxygen coupling index. The expression of the growth potential index is: G = μ(PARc) / parc×e -0.5×Nb ×[Sst×μ(SO)] 0.5 , where G represents the growth potential index, parc represents the preset light intensity parameter, and μ() represents the average value of the data in brackets within one hour.

[0075] Specifically, in this embodiment, the preset light intensity parameter is set to 1500. In this embodiment, there is no specific limitation on the setting of the preset light intensity parameter, and those skilled in the art can set it freely. The setting of the preset light intensity parameter should satisfy [1300, 1600].

[0076] Please continue reading Figure 3 As shown, the method for constructing the growth potential energy evaluation model further includes:

[0077] Step S42: performing attenuation correction on the growth potential energy index according to the water flow disturbance coefficient.

[0078] Specifically, in step S42 of this embodiment, when the water flow disturbance coefficient is greater than the water flow disturbance threshold, the growth potential energy index is attenuated and the expression of the growth potential energy index is corrected to: G = μ (PARc) / parc × e -0.5×Nb ×[Sst×μ(SO)] 0.5 ×[1-0.4×(CV-cv)], where CV represents the water flow disturbance coefficient, and cv represents the water flow disturbance threshold, 0.2≤cv≤0.3.

[0079] Specifically, in this embodiment, the water flow disturbance threshold is set to 0.25. In this embodiment, there is no specific limitation on the setting of the water flow disturbance threshold, and those skilled in the art can freely set it as long as it satisfies the attenuation correction of the growth potential energy index.

[0080] Please continue reading Figure 3 As shown, the method for constructing the growth potential energy evaluation model further includes:

[0081] Step S43: determining the growth potential energy level according to the growth potential energy index.

[0082] Specifically, in step S43 described in this embodiment, the growth potential energy level is judged based on the growth potential energy index. If the growth potential energy index is less than the first growth threshold, the growth potential energy level is determined to be in the risk zone. If the growth potential energy index is greater than or equal to the first growth threshold and less than the second growth threshold, the growth potential energy level is determined to be in the sub-health zone. If the growth potential energy index is greater than or equal to the second growth threshold, the growth potential energy level is determined to be in the optimal growth zone.

[0083] Specifically, in this embodiment, the first growth threshold is set to 0.6, and the second growth threshold is set to 0.85. In this embodiment, there is no specific limitation on the settings of the first growth threshold and the second growth threshold, and those skilled in the art can set them freely. The setting of the first growth threshold should satisfy [0.5, 0.7], and the setting of the second growth threshold should satisfy [0.8, 0.9].

[0084] Specifically, in step S4 described in this embodiment, the growth potential index is generated by integrating the four-dimensional parameters of light intensity, nutrition, salinity stability and salt-oxygen coupling to achieve a quantitative evaluation of the synergistic effect of multiple environmental factors. By introducing a water disturbance correction term, the impact of strong water flow on the growth potential is dynamically attenuated to improve the applicability of the model in complex flow field environments. By dividing the potential energy into three levels: risk zone, sub-health zone and optimal growth zone, a clear basis is provided for differentiated regulation.

[0085] Please continue reading Figure 1 As shown, the sea grape aquaculture monitoring data processing method based on big data analysis also includes:

[0086] Step S5, a process of updating the construction of the first environment association model and the second environment association model based on the growth potential energy level, the light intensity correction parameter and the sea grape cultivation data.

[0087] Specifically, in step S5 of this embodiment, the light intensity correction parameter of the optimal growth zone within the growth potential energy level within 7 days is extracted as the optimal light intensity parameter, and the salinity mean parameter of the optimal growth zone within the growth potential energy level within 7 days is extracted as the optimal salinity parameter.

[0088] Specifically, in step S5 described in this embodiment, the light intensity reference parameter is analyzed based on the optimal light intensity parameter. The expression of the light intensity reference parameter is: PARbl=μ(PARb)+0.5×σ(PARb), where PARbl represents the light intensity reference parameter, PARb represents the optimal light intensity parameter, and the value of the preset deviation parameter is updated to be equal to the light intensity reference parameter to update the construction process of the first environment association model.

[0089] Specifically, in step S5 described in this embodiment, the salinity reference parameter is analyzed according to the optimal salinity parameter, the median of the optimal salinity parameter is used as the salinity reference parameter, and the value of the preset salinity parameter is updated to be equal to 0.8 times the salinity reference parameter to update the construction process of the second environmental association model.

[0090] Specifically, in step S5 described in this embodiment, the light intensity benchmark parameters and salinity benchmark parameters are extracted based on the historical data of the optimal growth zone, so that the warning threshold is adaptively adjusted according to the actual growth status. Through periodic model updates, it is ensured that the early warning system can adapt to changes in the breeding environment in the long term, avoiding the attenuation of monitoring efficiency caused by parameter solidification.

[0091] See also Figure 4 As shown in FIG. 1 , the data processing device for monitoring sea grape cultivation based on big data analysis in this embodiment includes:

[0092] Data acquisition module, used to obtain sea grape aquaculture data and analyze light intensity correction parameters, salinity stability parameters and nutrient imbalance index;

[0093] A hysteresis analysis module is used to construct a first environmental association model based on the light intensity correction parameter and the sea grape cultivation data to obtain a hysteresis response coefficient and determine the warning type;

[0094] The salt-oxygen analysis module is used to construct a second environmental correlation model based on sea grape aquaculture data to obtain the salt-oxygen coupling index and determine the warning type;

[0095] Growth analysis module, used to construct a growth potential assessment model based on light intensity correction parameters, nutrient imbalance index, salinity stability parameters, salt-oxygen coupling index and sea grape aquaculture data to determine the growth potential level;

[0096] The model updating module is used to update the construction process of the first environment association model and the second environment association model based on the growth potential energy level, light intensity correction parameters and sea grape cultivation data.

[0097] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not limitations on the implementation methods of the present invention. For ordinary technicians in this field, other different forms of changes or modifications can be made based on the above description. It is impossible to list all the implementation methods here. All obvious changes or modifications derived from the technical solution of the present invention are still within the scope of protection of the present invention.

Claims

1. A method for processing sea grape cultivation monitoring data based on big data analysis, characterized in that: include: Acquire sea grape aquaculture data and analyze light intensity correction parameters, salinity stability parameters, and nutrient imbalance index. The light intensity correction parameters are obtained by performing spectral weight correction on the intensity of blue light, red light, green light, and the sum of the light intensity in the spectral light intensity. The first environmental association model was constructed based on light intensity correction parameters and sea grape aquaculture data to obtain the hysteresis response coefficient and determine the warning type; In the first environmental correlation model, the absolute value of the difference between the light intensity correction parameter and the preset deviation parameter is used as the light deviation, and the change in nitrate concentration within 3 hours is used as the nitrate concentration change parameter, and the hysteresis response coefficient is analyzed based on the light deviation and the nitrate concentration change parameter; A second environmental association model was constructed based on sea grape aquaculture data to obtain the salt-oxygen coupling index and determine the warning type; A growth potential evaluation model was constructed based on light intensity correction parameters, nutrient imbalance index, salinity stability parameters, salt-oxygen coupling index and sea grape culture data to determine the growth potential level; The growth potential energy evaluation model determines the growth potential energy index based on the light intensity correction parameter, the nutrient imbalance index, the salinity stability parameter and the salt-oxygen coupling index. The expression of the growth potential energy index is: G=μ(PARc) / parc×e -0.5×Nb ×[Sst×μ(SO)] 0.5 , where G represents the growth potential index, parc represents the preset light intensity parameter, μ() represents the average value of the data in brackets within one hour, PARc represents the light intensity correction parameter, Nb represents the nutrient imbalance index, Sst represents the salinity stability parameter, and SO represents the salt-oxygen coupling index; When the water disturbance coefficient is greater than the water disturbance threshold, the growth potential energy index is attenuated and the expression of the growth potential energy index is corrected to: G = μ (PARc) / parc × e-0.5×Nb ×[Sst×μ(SO)] 0.5 ×[1-0.4×(CV-cv)], where CV represents the water flow disturbance coefficient and cv represents the water flow disturbance threshold; Determining the growth potential energy level based on the growth potential energy index, wherein the growth potential energy level includes risk zone, sub-health zone and optimal growth zone; The construction process of updating the first and second environmental association models based on growth potential energy levels, light intensity correction parameters and sea grape cultivation data.

2. The method for processing sea grape cultivation monitoring data based on big data analysis according to claim 1, characterized in that: The spectral light intensity is corrected by spectral weight to obtain a light intensity correction parameter. The expression of the light intensity correction parameter is: PARc=0.46×Blue+0.32×Red+0.22×Green, where PARc represents the light intensity correction parameter, Blue represents the light intensity of blue light in the spectral light intensity, Red represents the light intensity of red light in the spectral light intensity, and Green represents the light intensity of green light in the spectral light intensity.

3. The method for processing sea grape aquaculture monitoring data based on big data analysis according to claim 2, characterized in that: The salinity stability parameter is determined based on the salinity standard deviation parameter. The expression of the salinity stability parameter is: Sst=1-(SD / sd), where Sst represents the salinity stability parameter, SD represents the salinity standard deviation parameter, and sd represents the preset gradient parameter.

4. The method for processing sea grape aquaculture monitoring data based on big data analysis according to claim 3, characterized in that: Compare the nutritional factor parameters with the preset factor ratio to establish the nutritional imbalance index. If the nutritional factor parameter is greater than the preset factor ratio, the expression of the nutritional imbalance index is set to: Nb=|lg(NP)-lg16|×1.5; otherwise, the expression of the nutritional imbalance index is set to: Nb=|lg(NP)-lg16|×0.8, where Nb represents the nutritional imbalance index and NP represents the nutritional factor parameter.

5. The method for processing sea grape cultivation monitoring data based on big data analysis according to claim 4, characterized in that: The hysteresis response coefficient was analyzed based on the light deviation and nitrate concentration variation parameters. The expression of the hysteresis response coefficient is: LRC=cov(ΔPARc,ΔNO3) / [σ(ΔPARc)×σ(ΔNO3)], where LRC represents the hysteresis response coefficient, ΔPARc represents the light deviation, ΔNO3 represents the nitrate concentration variation parameter, and σ() represents the standard deviation of the data in the brackets within one hour. The warning type is determined based on the hysteresis response coefficient. If the hysteresis response coefficient is greater than the hysteresis response threshold, the warning type is set to trigger a light nutrition unqualified warning. Otherwise, the warning type is not set.

6. The method for processing sea grape cultivation monitoring data based on big data analysis according to claim 5, characterized in that: The salt-oxygen coupling index is analyzed based on the saturated dissolved oxygen content, dissolved oxygen content, and salinity mean parameters. The expression of the salt-oxygen coupling index is: SO=O1 / [O2×(1+0.02×|Sa-sa|)], where SO represents the salt-oxygen coupling index, O1 represents the dissolved oxygen content, O2 represents the saturated dissolved oxygen content, Sa represents the salinity mean parameter, and sa represents the preset salinity parameter; The warning type is determined based on the salt-oxygen coupling index. If the salt-oxygen coupling index is less than the salt-oxygen coupling threshold for three consecutive hours, the warning type is set to trigger the salt-oxygen inhibition warning. Otherwise, no warning type is set.

7. The method for processing sea grape cultivation monitoring data based on big data analysis according to claim 6, characterized in that: The light intensity correction parameter of the optimal growth zone with the growth potential energy level within 7 days was extracted as the optimal light intensity parameter, and the salinity mean parameter of the optimal growth zone with the growth potential energy level within 7 days was extracted as the optimal salinity parameter.

8. The method for processing sea grape cultivation monitoring data based on big data analysis according to claim 7, characterized in that: Analyzing the light intensity reference parameter according to the optimal light intensity parameter, and updating the value of the preset deviation parameter to be equal to the light intensity reference parameter, so as to update the construction process of the first environment association model; The salinity benchmark parameters were analyzed according to the optimal salinity parameters, the median of the optimal salinity parameters was used as the salinity benchmark parameter, and the value of the preset salinity parameter was updated to be equal to 0.8 times the salinity benchmark parameter to update the construction process of the second environmental association model.

9. A sea grape aquaculture monitoring data processing device based on big data analysis, applied to the sea grape aquaculture monitoring data processing method based on big data analysis according to any one of claims 1 to 8, characterized in that: include: Data acquisition module, used to obtain sea grape aquaculture data and analyze light intensity correction parameters, salinity stability parameters and nutrient imbalance index; A hysteresis analysis module is used to construct a first environmental association model based on the light intensity correction parameter and the sea grape cultivation data to obtain a hysteresis response coefficient and determine the warning type; The salt-oxygen analysis module is used to construct a second environmental correlation model based on sea grape aquaculture data to obtain the salt-oxygen coupling index and determine the warning type; Growth analysis module, used to construct a growth potential assessment model based on light intensity correction parameters, nutrient imbalance index, salinity stability parameters, salt-oxygen coupling index and sea grape aquaculture data to determine the growth potential level; The model updating module is used to update the construction process of the first environment association model and the second environment association model based on the growth potential energy level, light intensity correction parameters and sea grape cultivation data.

Images