CN117196881B - Intelligent cultivation information management system based on big data - Google Patents
Intelligent cultivation information management system based on big data Download PDFInfo
- Publication number
- CN117196881B CN117196881B CN202311452650.5A CN202311452650A CN117196881B CN 117196881 B CN117196881 B CN 117196881B CN 202311452650 A CN202311452650 A CN 202311452650A CN 117196881 B CN117196881 B CN 117196881B
- Authority
- CN
- China
- Prior art keywords
- influence
- factors
- factor
- data
- cultivation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000007613 environmental effect Effects 0.000 claims abstract description 112
- 238000005457 optimization Methods 0.000 claims abstract description 90
- 238000000034 method Methods 0.000 claims abstract description 78
- 238000012216 screening Methods 0.000 claims abstract description 53
- 230000008859 change Effects 0.000 claims abstract description 44
- 230000008569 process Effects 0.000 claims abstract description 42
- 238000011156 evaluation Methods 0.000 claims description 34
- 238000004364 calculation method Methods 0.000 claims description 23
- 238000007726 management method Methods 0.000 claims description 17
- 238000000513 principal component analysis Methods 0.000 claims description 15
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 9
- 238000009360 aquaculture Methods 0.000 claims description 6
- 244000144974 aquaculture Species 0.000 claims description 6
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 5
- 238000013523 data management Methods 0.000 claims description 5
- 229910052760 oxygen Inorganic materials 0.000 claims description 5
- 239000001301 oxygen Substances 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000009313 farming Methods 0.000 claims description 4
- 230000036541 health Effects 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 26
- 238000009395 breeding Methods 0.000 description 4
- 230000001488 breeding effect Effects 0.000 description 4
- 238000005067 remediation Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000003181 biological factor Substances 0.000 description 2
- 238000012258 culturing Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011946 reduction process Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000000246 remedial effect Effects 0.000 description 1
Abstract
The invention relates to the technical field of farm information management, in particular to an intelligent cultivation information management system based on big data. The system firstly collects culture data; further analyzing the change characteristics of the environmental influence factors and the artificial influence factors to screen the environmental influence factors; further screening optimization influence factors which are less limited by the environment and have higher relativity and participation in the cultivation process from the artificial influence factors; and further accurately classifying the culture data according to the influence factors reserved after the multidimensional data screening, and then matching the culture data of the farm with the classification result, so as to predict the profit of the farm. According to the invention, the actual situations in the cultivation process are fully combined, and a plurality of influencing factors are classified and screened, so that the finally reserved main components are more in line with the actual cultivation scenes, and the accuracy of the system is finally improved.
Description
Technical Field
The invention relates to the technical field of farm information management, in particular to an intelligent cultivation information management system based on big data.
Background
The intelligent ocean pasture analyzes the collected data through modern technological means such as the Internet of things, big data, artificial intelligence and the like, optimizes the resource use, finds out the problems in the breeding process and gives out a corresponding solution to improve the yield and quality of ocean breeding, reduce the cost and environmental pollution and provide support for sustainable development.
The yield and profit of the predicted cultured organisms in the culturing process are one of the problems concerned by operators, and the final yield of the predicted cultured organisms can be obtained by utilizing intelligent culturing big data so as to estimate the profit prospect; however, marine culture is a very complex process, various culture influencing factors can have a certain influence on the final yield more or less, and multidimensional influencing factor labels cannot be directly used for yield prediction, so that culture income cannot be predicted.
Disclosure of Invention
In order to solve the technical problems that the screening result is not ideal after the data screening is carried out in the prior art and the prediction result is not ideal, the invention aims to provide an intelligent culture information management system based on big data, and the adopted technical scheme is as follows:
And a data acquisition module: acquiring culture data at a preset acquisition frequency; the cultivation data comprises environmental influence factors, artificial influence factors and biological influence factors;
and a factor screening module: analyzing the change characteristics of each environmental influence factor and each artificial influence factor on time sequence, and obtaining influence characteristic parameters of each environmental influence factor on each artificial influence factor; according to all the influence characteristic parameters in all the cultivation data, screening out the artificial remedy influence factors corresponding to each environmental influence factor from the artificial influence factors; screening out main environmental influence factors from the environmental influence factors according to fluctuation characteristics of influence characteristic parameters of all the artificial remedy influence factors in all the culture data; removing other influence factors of the artificial remedy influence factors corresponding to the main influence factors of the environment from the artificial influence factors as optimization influence factors; in all the cultivation data, analyzing the correlation between each optimization influence factor and the change characteristic of each biological influence factor, and screening out main optimization influence factors from the optimization influence factors by combining the participation degree of each optimization influence factor in the cultivation process;
And a data management module: clustering all the historical culture data according to the main environmental influence factors among all the historical culture data, the corresponding artificial remedy influence factors and the differences of the optimized main influence factors; matching the to-be-predicted cultivation data with the clustering result, and predicting the profit of the cultivation farm by combining the profits corresponding to all the historical cultivation data.
The method for acquiring the influence characteristic parameters comprises the following steps:
obtaining extreme points on a time sequence curve of each influence factor in all the culture data; selecting any cultivation data as target cultivation data; acquiring influence characteristic parameters according to an influence characteristic parameter calculation formula; the influence characteristic parameter calculation formula comprises:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>A category number indicating an environmental impact factor; />A category number indicating the human influence factor,indicate->Personal environmental impact factor->For->Personal influence factor->Is used for influencing characteristic parameters; />Representing +.>The number of extreme points of the individual environmental impact factor change curves; />Represents +.>The number of extreme points of the individual environmental impact factor change curves; / >Represents +.>The number of extreme points of the personal influence factor change curve; />Representing a preset base number; />A sequence number representing an extreme point of an environmental impact factor in the target data; />Representing +.>Personal environmental influence factor->The amplitude of each extreme point; />Representing +.>Personal environmental influence factor->Collecting time of the extreme points; />Representing +.>In the personal influence factor change curve and +.>The acquisition time of the nearest extreme point.
Further, the method for acquiring the human remedy influence factors comprises the following steps:
acquiring the average value and standard deviation of the influence characteristic parameters of each environmental influence factor on all the artificial influence factors in all the cultivation data; for each environmental impact, the artificial impact with the smallest sum of the mean and standard deviation is used as the artificial remedy impact of the corresponding environmental impact.
Further, the method for acquiring the environmental main influencing factors comprises the following steps:
mapping and normalizing the sum of the average value and the standard deviation of all influence characteristic parameters of the human remedy influence factors corresponding to each environment influence factor in a negative correlation manner to obtain the degree of unreliability of each environment influence factor;
And sequencing the environmental influence factors according to the unreliability degree, and obtaining the main environmental influence factors by using a principal component analysis algorithm.
Further, the method for acquiring the optimized main influencing factors comprises the following steps:
in all the cultivation data, analyzing the correlation between each optimization influence factor and the change characteristic of each biological influence factor, and combining the participation degree of each optimization influence factor in the cultivation process to obtain the importance degree parameter of each optimization influence factor;
and sequencing the optimization influence factors according to the importance degree parameters and obtaining the main influence factors of optimization by using a principal component analysis algorithm.
Further, the method for acquiring the importance degree parameter comprises the following steps:
analyzing the change characteristics of each biological influence factor, and obtaining an evaluation factor corresponding to each biological influence factor;
obtaining importance parameters according to an importance parameter calculation formula; the importance parameter calculation formula comprises:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing optimization influencing factors; />A sequence number representing the optimization influencing factor; />Indicate->Optimizing importance degree parameters of influencing factors; />Represents +. >Covariance of each optimization influence factor and biological influence factor evaluation factors in all the culture data; />Represents +.>The standard deviation of each optimization influence factor; />Representing the standard deviation of biological influence factor evaluation factors in all the culture data; />Representing the correlation between the optimization influence factors and the evaluation factors; />Serial number representing cultivation data,/->Representing the number of cultivation data; />Indicate->Individual cultivation data->Optimization of influence factor->Extreme point number, < >>Represent the firstIndividual cultivation data->The number of extreme points of the optimization influencing factors; />Indicate->Individual cultivation data->Optimization of influence factor->The time interval between each extreme point and the previous extreme point; />Represents->A cultivation period duration of the individual cultivation data; />Characterizing the participation degree of optimization influence factors in the cultivation process; />Expressed as natural constant->An exponential function that is a base;representing the covariance function.
Further, the method for acquiring the evaluation factor includes:
obtaining an evaluation factor according to an evaluation factor calculation formula; the evaluation factor calculation formula includes:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>A serial number representing a biological influencing factor; />Indicate- >An evaluation factor of the individual biological influence factors; />Indicate->The number of individual biological influencing factors; />Respectively represent +.>Maximum and minimum values of the individual biological influence factor change curves; />Indicate->Extreme points of the variation curve of the individual biological influencing factorsSequence number,/->Indicate->The number of extremal points of the individual biological influencing factors; />Indicate->Personal biological influencing factor->Data values for the extreme points.
Further, the method for predicting profit of the farm comprises the following steps:
taking the environment main influence factors and the corresponding artificial remedy influence factors and the optimizing main influence factors as main influence factors; obtaining profit ratio according to each cultivation data, input cost and income, and further obtaining average profit ratio of each cluster; obtaining average distances between the farm cultivation data and all the main influence factors of the cultivation data in each cluster, and selecting the cluster with the smallest average distance as a matched cluster; the average profit ratio of the matched cluster is taken as the predicted profit ratio of the farm.
Further, the variance contribution ratio threshold in the principal component analysis algorithm is set to 30%.
Further, the environmental impact factors include: water temperature, salinity, dissolved oxygen, turbidity, pH value, flow rate, air temperature, rainfall, wind power, tide and sunshine duration;
Human influencing factors include: cultivation density, bait feeding amount of a bait feeding machine, bait feeding frequency, a water flow controller, a water temperature regulator, power, discharge capacity and filter screen size of a water quality filter;
biological influencing factors include: the size, weight, growth rate, and health data of the farmed organisms.
The invention has the following beneficial effects:
aiming at the technical problems that the culture data has dimension disasters and cannot be used for profit prediction, firstly, the culture data is collected in a classified mode according to the actual culture situation, so that the subsequent classified screening of the data is facilitated, and the screening result is more in line with the culture scene; further analyzing the change characteristics of the environmental influence factors and the artificial influence factors, and screening out the artificial remedy influence factors with the greatest influence of each environmental influence factor on the artificial influence factors; further, according to fluctuation of influence characteristic parameters of the artificial remedy influence factors corresponding to the artificial influence factors, the environment influence factors are screened, so that more important and more focused environment influence factors are reserved, the cultivation scene is more met, and the accuracy and the adaptability of the system are improved; further screening optimization influence factors which are less limited by the environment and have higher relativity and participation in the cultivation process from the artificial influence factors, retaining the artificial influence factors which optimize the income of the cultivation farm, and solving the problem of dimension disasters; the method comprises the steps of screening multi-dimensional data, screening the multi-dimensional data, classifying the multi-dimensional data, and matching the multi-dimensional data with the clustering result, wherein the multi-dimensional data is reserved in the multi-dimensional data, so that the multi-dimensional data is supported by the multi-dimensional data, and the reliability of the multi-dimensional data is improved; and finally, predicting the profit of the farm, and providing reliable yield prediction information for the farm, thereby being beneficial to timely adjusting the cultivation strategy and improving the profit of the farm. According to the invention, the actual situations in the cultivation process are fully combined, and a plurality of influencing factors are classified and screened, so that the finally reserved main components are more in line with the actual cultivation scenes, and the accuracy and reliability of the system are finally improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a system block diagram of an intelligent aquaculture information management system based on big data according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of a big data-based intelligent cultivation information management system according to the invention, which is a specific implementation, structure, characteristics and effects thereof, with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the intelligent cultivation information management system based on big data provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a system block diagram of a smart farming information management system based on big data is provided according to an embodiment of the present invention, and the system includes a data acquisition module 101, a factor screening module 102, and a data management module 103.
The data acquisition module 101: acquiring culture data at a preset acquisition frequency; the farming data includes environmental, human and biological influencing factors.
In order to analyze the cultivation condition of a farm, cultivation information is managed, and firstly cultivation data needs to be obtained; because the influence factors are various, the controllability of each influence factor and the influence degree on the yield of the farm are inconsistent, in order to accurately screen different influence factors subsequently, the method is more in line with the actual situation of cultivation, and the accuracy of a management system is improved, so that cultivation data are classified; considering that human factors are often influenced by environmental factors and also influence among organisms, the cultivation data are classified according to the environmental factors, the human factors and the biological factors.
In one embodiment of the invention, environmental factors such as water temperature, salinity, dissolved oxygen, turbidity, pH value, flow rate, air temperature, rainfall, wind power, tide and sunshine duration are taken as environmental influence factors; artificial factors such as culture density, bait feeding amount of a bait feeding machine, bait feeding frequency, a water flow controller, a water temperature regulator, power, discharge capacity and filter screen size of a water quality filter are taken as artificial influence factors; biological factors such as the size, weight, growth rate and health data of the cultured organisms are used as biological influence factors; in other embodiments of the present invention, the practitioner can adjust the variety and number of the cultivation data according to the actual needs to meet the actual needs of different farms.
It should be noted that, in one embodiment of the present invention, the preset collection frequency is once a day, and the length of the cultivation data is one cultivation period; the cultivation period is determined by a specific cultivation plan of the farm and is not limited herein; the acquisition frequency can be adjusted by itself.
Factor screening module 102: analyzing the change characteristics of each environmental influence factor and each artificial influence factor on time sequence, and acquiring influence characteristic parameters of each environmental influence factor on each artificial influence factor; according to all influence characteristic parameters in all the cultivation data, screening human remedy influence factors corresponding to each environment influence factor from human influence factors; screening out main environmental influence factors from the environmental influence factors according to fluctuation characteristics of influence characteristic parameters of all artificial remedy influence factors in all the culture data, wherein the influence characteristic parameters correspond to the artificial influence factors; other influence factors of the artificial remedy influence factors corresponding to the main influence factors of the environment are removed from the artificial influence factors and are used as optimization influence factors; and in all the cultivation data, analyzing the correlation between each optimizing influence factor and the change characteristic of each biological influence factor, and screening out main optimizing influence factors from the optimizing influence factors by combining the participation degree of each optimizing influence factor in the cultivation process.
For actual cultivation data, the influence degree of different environmental factor fluctuation on the cultivation process is different, the attention degree of artificial cultivation is different, the traditional method cannot be well adapted to complex situations of artificial cultivation, the result of multi-dimensional data screening is easy to lose important dimension data with higher attention degree, the follow-up prediction result is caused to deviate, and the accuracy of the system is reduced.
The factor screening module 102 fully considers the influence of the environmental influence factors on the artificial breeding process, analyzes the high attention of the artificial breeding process to the environmental influence factors through the change characteristics of the artificial influence factors along with the environmental influence factors, and screens out the main environmental influence factors; meanwhile, other human factors which are slightly influenced by the environment but have a large effect in the cultivation process have a certain influence on the cultivation yield and cannot be ignored, so that the human factors with the optimized property are also screened, the reliability of the multi-dimensional data screening result is further improved, and the reliability of the system is improved.
The factor screening method can be regarded as a dimension reduction process, and a common dimension reduction process, such as a principal component analysis algorithm, realizes dimension screening by finding the direction of the maximum variance in the data and projecting the direction, wherein the sequence in the screening process is determined by the data; if the random mapping algorithm maps high-dimensional data to a low-dimensional space through random mapping, the screening result is also uncontrollable and cannot well adapt to complex situations of artificial culture, in one embodiment of the invention, the screening dimension sequence of the principal component analysis algorithm is adjusted by taking the principal component analysis (Principal Component Analysis, PCA) algorithm as an example, so as to obtain the screening result which is more in line with the cultivation situations; in other embodiments of the present invention, an implementer may adjust the screening dimension sequence of other random sequence dimension screening algorithms, or may obtain a preset number of main influencing factors by using simple statistical feature values and variances of the influencing feature parameters of the artificial remedy influencing factors, such as mean values, minimum values, etc., as influencing degree reference parameters of the environmental influencing factors, and sorting the environmental influencing factors; and the same is true of the main influencing factors of the optimization. It should be noted that the PCA algorithm is a technical means well known to those skilled in the art, and will not be described herein.
It should be noted that, in the process of screening other factors, the data features may be analyzed and extracted to control the screening basis, and the optimal factors are selected as the main influencing factors, which are not described and limited herein.
For human influence factors, one part is greatly limited by the environment influence factors, changes along with the change of the environment, belongs to adjustment by the unreliability component, has strong remedial property and higher attention, and the other part is less limited by the environment influence factors, so that the composition has certain optimization property; therefore, the influence characteristic parameters between the environmental influence factors and the artificial influence factors are analyzed to determine the artificial remedy influence factors and the unreliability degree corresponding to each environmental influence factor, so that the ordering of the environmental influence factors is adjusted, and the main environmental influence factors which are more in line with the actual cultivation scene are obtained.
Preferably, in one embodiment of the present invention, the extreme point is a node where the influence factor changes greatly, and the fluctuation caused by the change of one factor on another factor can be reflected more obviously, so that the influence characteristic parameter is obtained according to the fluctuation similarity between the environmental influence factor and the extreme point of the artificial influence factor. Firstly, extreme points on a time sequence curve of each influence factor in all the culture data are obtained, the quantity similarity of the extreme points of the environmental influence factors and the artificial influence factors is analyzed on the whole data, the acquisition time interval similarity of the two influence factors is analyzed on the local data, and any culture data is selected as target culture data; acquiring influence characteristic parameters according to an influence characteristic parameter calculation formula; the influence characteristic parameter calculation formula comprises:
The method comprises the steps of carrying out a first treatment on the surface of the Wherein,a category number indicating an environmental impact factor; />Class number indicating human influence factor +.>Indicate->Personal environmental impact factor->For->Personal influence factor->Is used for influencing characteristic parameters; />Representing +.>The number of extreme points of the individual environmental impact factor change curves; />Representing the first of all cultivation dataThe number of extreme points of the individual environmental impact factor change curves; />Represents +.>The number of extreme points of the personal influence factor change curve; />Representing a preset base number; />A sequence number representing an extreme point of an environmental impact factor in the target data; />Representing +.>Personal environmental influence factor->The amplitude of each extreme point; />Representing +.>Personal environmental influence factor->Collecting time of the extreme points; />Representing +.>In the personal influence factor change curve and +.>The acquisition time of the nearest extreme point. In one embodiment of the present invention,。
in the calculation formula of the influencing characteristic parameters, the more similar the environment influencing factors are to the number of extreme points of the artificial influencing factors, the closer the ratio is to 1,the closer to 0, the smaller the influencing feature parameters; the smaller the acquisition time interval between the environmental impact factors and the extreme points of the artificial impact factors, the more possible the artificial impact factors are to cope with the fluctuation of the environmental impact factors, and the smaller the impact characteristic parameters are; the smaller the influencing characteristic parameters are, the larger the influence of the environmental factors on human factors is, and the environmental influence factors are in the artificial culture process The higher the attention, the greater the possibility that the environmental influence factors are reserved as main components in the subsequent multidimensional data screening process, the more the actual cultivation situation is met, and the accuracy of the cultivation information management system is improved.
In the actual cultivation process, certain fluctuation exists in the influencing factors, and certain fluctuation exists in the corresponding influencing characteristic parameters. In order to reduce the accidental influence on the characteristic parameters and improve the reliability of the characteristic parameters, all the cultivation big data are combined for analysis, the most accurate artificial remedy influence factors corresponding to each environmental influence factor are searched, the accidental influence on the data is reduced, and the system error is reduced.
Preferably, in one embodiment of the present invention, considering that the average value may show a central tendency of data, the overall influence condition of the environmental influence factor on a certain human influence factor is reflected; the standard deviation can reflect the fluctuation condition of the data and reflect the influence fluctuation condition of the environmental influence factors on a certain artificial influence factor, so that the average value and the standard deviation of the influence characteristic parameters of each artificial influence factor by each environmental influence factor in all the culture data are obtained; the smaller the sum of the average value and the standard deviation is, the greater the overall influence degree of the environmental influence factors on the artificial influence factors is, and the stability is improved, so that the artificial influence factors with the smallest sum of the average value and the standard deviation of the influence characteristic parameters are taken as the artificial remedy influence factors of the environmental influence factors. For example, if the sum of the average value and the standard deviation of all the characteristic parameters affecting the culture density by the dissolved oxygen is the smallest in all the culture data, the artificial influence factor of the culture density is the artificial remedy influence factor of the environmental influence factor of the dissolved oxygen.
The artificial remedy influence factors are factors which correspond to each environmental influence factor and can best reflect the concerned degree and influence degree of the environmental influence factors, after the artificial remedy influence factors of each environmental influence factor are determined, the irresistible degree can be obtained according to the influence characteristic parameters of the environmental influence factors and the corresponding artificial remedy influence factors, a measurement basis is provided for the importance degree of the environmental influence factors, the sequence of the environmental influence factors is adjusted according to the irresistible degree, and data screening which is more in line with actual cultivation scenes is carried out.
Preferably, in one embodiment of the present invention, the method for obtaining the degree of unreliability includes: and mapping and normalizing the sum of the average value and the standard deviation of all the influence characteristic parameters of the artificial remedy influence factors corresponding to each environment influence factor in a negative correlation way, so as to obtain the degree of unreliability of each environment influence factor. The calculation formula of the degree of unreliability includes:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>A category number indicating an environmental impact factor; />Indicate->Individual environmental impact factors; />Indicate->The average value of all influence characteristic parameters of the artificial remedy influence factors corresponding to the individual environmental influence factors; / >Indicate->Standard deviations of all influence characteristic parameters of the human remedy influence factors corresponding to the individual environmental influence factors; />Expressed as natural constant->Is an exponential function of the base.
In the calculation formula of the degree of unreliability, the smaller the sum of the average value and the standard deviation of all influence characteristic parameters of the artificial remediation influence factors corresponding to the environment influence factors is, the more similar the artificial remediation influence factors are to the fluctuation and change characteristics of the artificial influence factors and the environment influence factors under the action of the environment influence factors, the more obvious the characteristics of the artificial remediation influence factors react along with the change of the environment influence factors are, the stronger the decision action of the environment influence factors on the artificial remediation influence factors is reflected, and the greater the degree of attention and influence of the environment influence factors is, the greater the degree of unreliability is.
The greater the degree of unreliability, the greater the degree of attention of the man-made to such environmental impact factors in the cultivation process, the greater the importance of such environmental impact factors, taking the principal component analysis algorithm as an example of an algorithm for screening factors, the more front positions are required to be arranged when the principal component analysis algorithm is used for multi-dimensional data screening processing, and the omission is avoided, so in the embodiment of the invention, the environmental impact factors are ordered in descending order according to the degree of unreliability, PCA mapping is carried out according to the order from large to small until the variance contribution rate reaches 30%, and the principal component analysis algorithm is used for obtaining the main environmental impact factors in the environmental impact factors; in other embodiments of the present invention, the variance contribution rate threshold may be set and adjusted by itself; all the environmental influence factors can be simply ranked according to the degree of unreliability, and the required number of environmental main influence factors can be selected according to the order from large to small.
The environmental influence factors can be obtained after factor screeningThe main influencing factors of the individual environment are obtained at the same time>Personal remedy influencing factors, i.e.)>Personal influencing factors; other human factors are less influenced by the environment, and when the environment factors fluctuate, the process advancesThe degree of unreliability that the line must be actively remedied is low, and the line has a certain influence in the cultivation process, so that the line has the possibility of optimization and certain optimization property, so that the optimization influence factors need to be screened, and the main optimization influence factors with great influence on the cultivation process are obtained. In one embodiment of the invention, other influence factors of the artificial remedy influence factors corresponding to the main influence factors of the environment are removed from the artificial influence factors to be used as optimization influence factors.
Among the optimization influence factors, different optimization influence factors have different influence degrees on the cultivated objects in the cultivation process, and the influence degree of the optimization influence factors on the cultivated objects is analyzed similarly, so that the dimension of cultivation data is further reduced, and meanwhile, the useful optimization influence factors are not ignored. Considering that the multidimensional data screening can not be accurate enough only by means of correlation, the screening result with higher accuracy and reliability is obtained by analyzing the participation degree of the optimization influence factors in the cultivation process in order to further improve the reliability of the screening result; meanwhile, in order to reduce errors generated by fluctuation of certain culture data, all the culture data are combined for analysis, and large data are fully utilized to obtain a screening result with higher reliability.
Preferably, in one embodiment of the present invention, in order to measure the influence degree of an optimization influence factor on a cultivation process, first, an importance degree parameter positively correlated with the influence degree of the optimization influence factor is obtained, so as to perform multidimensional data screening according to the importance degree parameter, and based on this, the method for obtaining the optimization main influence factor includes: in all the cultivation data, analyzing the correlation between each optimization influence factor and the change characteristic of each biological influence factor, and combining the participation degree of each optimization influence factor in the cultivation process to obtain the importance degree parameter of each optimization influence factor; and sequencing the optimization influence factors according to the importance degree parameters and obtaining the main influence factors by using a principal component analysis algorithm. In other embodiments of the present invention, the implementer may simply sort the optimization influencing factors according to the importance parameters, and select the required number of optimization influencing factors according to the order from large to small.
Preferably, in one embodiment of the present invention, in consideration of the fact that the pearson correlation coefficient can calculate the correlation between two variables conveniently, the greater the deviation from zero is, the stronger the correlation is, which means that the correlation between the optimization influence factor and the evaluation factor is stronger, in order to avoid the problem that the pearson correlation coefficient is smaller than zero, the actual correlation is strong and the calculated importance parameter is smaller, so that the absolute value of the correlation coefficient is required to be taken, and the normal relation of the positive correlation between the correlation and the importance parameter is ensured; meanwhile, the more regular the change of the extreme points of the optimization influence factors is considered, the smaller the interval fluctuation of the adjacent extreme points is, which shows that the more stable the participation state of the optimization influence factors in the cultivation process is, the higher the participation degree is. The method for acquiring the importance degree parameter comprises the following steps:
Analyzing the change characteristics of each biological influence factor, and obtaining an evaluation factor corresponding to each biological influence factor;
obtaining importance parameters according to an importance parameter calculation formula; the importance parameter calculation formula comprises:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Representing optimization influencing factors; />A sequence number representing the optimization influencing factor; />Indicate->Optimizing importance degree parameters of influencing factors; />Represents +.>Covariance of each optimization influence factor and biological influence factor evaluation factors in all the culture data; />Represents +.>The standard deviation of each optimization influence factor; />Representing the standard deviation of biological influence factor evaluation factors in all the culture data; />Representing the correlation between the optimization influence factors and the evaluation factors; />Serial number representing cultivation data,/->Representing the number of cultivation data; />Indicate->Individual cultivation data->Optimization of influence factor->Extreme point number, < >>Represent the firstIndividual cultivation data->The number of extreme points of the optimization influencing factors; />Indicate->Individual cultivation data->Optimization of influence factor->The time interval between each extreme point and the previous extreme point; />Represents->A cultivation period duration of the individual cultivation data; / >Characterizing the participation degree of optimization influence factors in the cultivation process; />Expressed as natural constant->An exponential function that is a base; />Representing the covariance function.
In the calculation formula of the importance degree parameter, the absolute value of the pearson correlation coefficient isThe larger the optimization influence factor is, the stronger the correlation between the optimization influence factor and the evaluation factor is, the larger the function possibly plays in the cultivation process, and the larger the importance degree parameter is; />The smaller the optimization influence factor extreme points are, the smaller the variation rule of the optimization influence factor extreme points is, the smaller the interval fluctuation of the adjacent extreme points is, the more stable the participation state of the optimization influence factors in the cultivation process is, so that the participation degree of the optimization influence factors in the cultivation process can be represented after the negative correlation mapping and normalization>The larger the participation, the higher the importance of optimizing the influencing factors, and the larger the importance parameters. In other embodiments of the present invention, the practitioner may choose other mathematical negative correlation mapping relationships, and choose other methods for calculating correlations, such as Cramer's V correlation coefficients, to calculate the importance of the optimization influencing factors in the cultivation process.
In order to measure the influence degree of the optimization influence factors on the culture, the change characteristics of the biological influence factors in the culture process are required to be obtained to obtain evaluation factors, and then the similarity of the optimization influence factors and the biological influence factor evaluation factors is analyzed and compared to provide a basis for judging the influence degree of the optimization influence factors on the culture.
Preferably, in one embodiment of the present invention, considering that the extremum points are nodes where the influence factor changes greatly, the amplitude difference between adjacent extremum points may reflect the slope of the change curve of the biological influence factor, and the average slope of the change curve may be represented after the average is taken, and the average result of all the biological influence factors may reflect the change characteristics of the biological influence factor, so the method for obtaining the evaluation factor includes: obtaining an evaluation factor according to an evaluation factor calculation formula; the evaluation factor calculation formula includes:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>A serial number representing a biological influencing factor; />Indicate->An evaluation factor of the individual biological influence factors; />Indicate->The number of individual biological influencing factors; />Respectively represent +.>Maximum and minimum values of the individual biological influence factor change curves; />Indicate->Extreme point sequence number of individual biological influencing factor change curve, < ->Indicate->The number of extremal points of the individual biological influencing factors; />Indicate->Personal biological influencing factor->Data values for the extreme points.
In the calculation formula of the evaluation factor,the larger, i.e. the greater the margin, the more the change in the biological influencing factor is accounted forThe larger the range, the larger the evaluation factor; the smaller the average slope, the smaller the fluctuation of the biological influence factor change, and the smaller the evaluation factor.
Similar to the environmental impact factor data screening process, after importance degree parameters of each optimization impact factor are obtained, the optimization impact factors can be ordered in descending order, PCA mapping is carried out according to the order from large to small until the variance contribution rate reaches 30%, and the principal component analysis algorithm is utilized to obtain the optimization impact factorsThe main influencing factors of the optimization.
Data management module 103: obtaining clustering distances according to the differences of the main environmental influence factors and the corresponding human remedy influence factors and the optimized main influence factors among all the historical culture data, and clustering all the historical culture data; matching the to-be-predicted cultivation data with the clustering result, and predicting the profit of the cultivation farm by combining the profits corresponding to all the historical cultivation data.
After the culture data passes through the factor screening module 102, it can be obtainedPersonal environmental major influencing factors, < >>Personal remedy influencing factors->The main influencing factor of the optimization, namely->Personal influencing factors, total->The method solves the problem of dimension disaster existing in multidimensional data and prepares for data management of farms.
In order to accurately predict the profit of the farm, historical data which is most similar to the farm cultivation data is required to be searched, so that a data set which is more similar to the cultivation data is required to be acquired, all different cultivation data are classified through clustering, so that cluster clusters which are most matched with the current cultivation data are searched later, and the profit is accurately predicted.
In one embodiment of the invention, in order to avoid improper setting of the number of clusters, the risk of selecting the number of improper clusters is reduced, and the number of clusters is determined by using an elbow method; based on the above, according to the main environmental influence factors and the corresponding artificial remedy influence factors among all the cultivation data, the differences of the main influence factors are optimized, namelyAnd calculating European norms according to the differences of the main influencing factors, obtaining the clustering quantity by using an elbow method, and carrying out k-means clustering on all the culture data. It should be noted that the k-means clustering algorithm and the elbow method are well known to those skilled in the art, and are not described in detail herein; in other embodiments of the invention, the number of clusters may be set empirically, e.g., according to breed, cultivation period, etc.
All the different cultivation data are classified through clustering, the cultivation data with higher similarity of main influence factors are used as a cluster, the cultivation data to be predicted of the cultivation farm are classified, profit prediction is prepared by means of the cluster which is most matched, and therefore profit of the cultivation farm is predicted immediately.
Preferably, in one embodiment of the present invention, fluctuations between the cultivation data are taken into account in the best-matching clusters, and averaging them eliminates such fluctuations, enabling accurate prediction of profit. Based on this, the method for predicting profit of the farm includes: taking the main environmental influence factors and the corresponding human remedy influence factors and optimizing the main influence factors as main influence factors; obtaining profit ratio according to each cultivation data, input cost and income, and further obtaining average profit ratio of each cluster; obtaining average distances between the culture data of the farm and all main influencing factors of the culture data in each cluster, and selecting the cluster with the smallest average distance as a matched cluster; the average profit ratio of the matched cluster is taken as the predicted profit ratio of the farm. In other embodiments of the invention, the practitioner may take as the predicted profit margin other suitable statistical features such as the mode or median of the profit margins of the matching cluster.
In summary, the method aims at the technical problems that the prediction result is not ideal due to the fact that the dimension of the culture influence factors is excessive and the screening result is inaccurate after the multidimensional data screening is carried out in the prior art, and firstly, culture data are collected in a classified mode according to the actual culture situation; further analyzing the change characteristics of the environmental influence factors and the artificial influence factors to carry out multidimensional data screening on the environmental influence factors; further screening optimization influence factors which are less limited by the environment and have higher relativity and participation in the cultivation process from the artificial influence factors; and further accurately classifying the culture data according to the influence factors reserved after the multidimensional data screening, and then matching the culture data of the farm with the clustering result, so as to predict the profit of the farm. According to the invention, the actual situations in the cultivation process are fully combined, and a plurality of influencing factors are classified and screened, so that the finally reserved main components are more in line with the actual cultivation scene, the reliability of the predicted data is higher, and the accuracy of the system is finally improved.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (7)
1. An intelligent aquaculture information management system based on big data, the system comprising:
and a data acquisition module: acquiring culture data at a preset acquisition frequency; the cultivation data comprises environmental influence factors, artificial influence factors and biological influence factors;
and a factor screening module: analyzing the change characteristics of each environmental influence factor and each artificial influence factor on time sequence, and obtaining influence characteristic parameters of each environmental influence factor on each artificial influence factor; according to all the influence characteristic parameters in all the cultivation data, screening out the artificial remedy influence factors corresponding to each environmental influence factor from the artificial influence factors; screening out main environmental influence factors from the environmental influence factors according to fluctuation characteristics of influence characteristic parameters of all the artificial remedy influence factors corresponding to the artificial influence factors in all the culture data; removing other influence factors of the artificial remedy influence factors corresponding to the main influence factors of the environment from the artificial influence factors as optimization influence factors; in all the cultivation data, analyzing the correlation between each optimization influence factor and the change characteristic of each biological influence factor, and screening out main optimization influence factors from the optimization influence factors by combining the participation degree of each optimization influence factor in the cultivation process;
And a data management module: clustering all the historical culture data according to the main environmental influence factors among all the historical culture data, the corresponding artificial remedy influence factors and the differences of the optimized main influence factors; matching the culture data to be predicted with the clustering result, and predicting the profit of the farm by combining the profits corresponding to all the historical culture data;
the method for acquiring the influence characteristic parameters comprises the following steps:
obtaining extreme points on a time sequence curve of each influence factor in all the culture data; selecting any cultivation data as target cultivation data; acquiring influence characteristic parameters according to an influence characteristic parameter calculation formula; the influence characteristic parameter calculation formula comprises:
；
wherein,a category number indicating an environmental impact factor; />A category number indicating the human influence factor,indicate->Personal environmental impact factor->For->Personal influence factor->Is used for influencing characteristic parameters; />Representing +.>The number of extreme points of the individual environmental impact factor change curves; />Represents +.>The number of extreme points of the individual environmental impact factor change curves; / >Represents +.>The number of extreme points of the personal influence factor change curve; />Representing a preset base number; />A sequence number representing an extreme point of an environmental impact factor in the target data; />Representing +.>Personal environmental influence factor->The amplitude of each extreme point; />Representing +.>Personal environmental influence factor->Collecting time of the extreme points; />Representing +.>In the personal influence factor change curve and +.>The most recent extremumThe acquisition time of the point;
the method for acquiring the optimized main influencing factors comprises the following steps:
in all the cultivation data, analyzing the correlation between each optimization influence factor and the change characteristic of each biological influence factor, and combining the participation degree of each optimization influence factor in the cultivation process to obtain the importance degree parameter of each optimization influence factor;
sequencing the optimization influence factors according to the importance degree parameters and obtaining main optimization influence factors by using a principal component analysis algorithm; the variance contribution ratio threshold in the principal component analysis algorithm is set to 30%.
2. The intelligent aquaculture information management system according to claim 1, wherein said human remedy influencing factor obtaining method comprises:
Acquiring the average value and standard deviation of the influence characteristic parameters of each environmental influence factor on all the artificial influence factors in all the cultivation data; for each environmental impact, the artificial impact with the smallest sum of the mean and standard deviation is used as the artificial remedy impact of the corresponding environmental impact.
3. The intelligent aquaculture information management system according to claim 2, wherein said method for obtaining environmental primary influencing factors comprises:
mapping and normalizing the sum of the average value and the standard deviation of all influence characteristic parameters of the human remedy influence factors corresponding to each environment influence factor in a negative correlation manner to obtain the degree of unreliability of each environment influence factor;
and sequencing the environmental influence factors according to the unreliability degree, and obtaining the main environmental influence factors by using a principal component analysis algorithm.
4. The intelligent aquaculture information management system based on big data according to claim 1, wherein the method for obtaining the importance parameter comprises:
analyzing the change characteristics of each biological influence factor, and obtaining an evaluation factor corresponding to each biological influence factor;
Obtaining importance parameters according to an importance parameter calculation formula; the importance parameter calculation formula comprises:
；
wherein,representing optimization influencing factors; />A sequence number representing the optimization influencing factor; />Indicate->Optimizing importance degree parameters of influencing factors; />Represents +.>Covariance of each optimization influence factor and biological influence factor evaluation factors in all the culture data; />Represents +.>The standard deviation of each optimization influence factor; />Representing the standard deviation of biological influence factor evaluation factors in all the culture data;representing the correlation between the optimization influence factors and the evaluation factors; />Serial number representing cultivation data,/->Representing the number of cultivation data; />Indicate->Individual cultivation data->Optimization of influence factor->Extreme point number, < >>Indicate->Individual cultivation data->The number of extreme points of the optimization influencing factors; />Indicate->Individual cultivation data->Optimization of influence factor->The time interval between each extreme point and the previous extreme point; />Represents->A cultivation period duration of the individual cultivation data;characterizing the participation degree of optimization influence factors in the cultivation process; />Expressed as natural constant- >An exponential function that is a base; />Representing the covariance function.
5. The intelligent aquaculture information management system based on big data according to claim 4, wherein the method for obtaining the evaluation factor comprises:
obtaining an evaluation factor according to an evaluation factor calculation formula; the evaluation factor calculation formula includes:
；
wherein,a serial number representing a biological influencing factor; />Indicate->An evaluation factor of the individual biological influence factors;indicate->The number of individual biological influencing factors; />Respectively represent +.>Maximum and minimum values of the individual biological influence factor change curves; />Indicate->Extreme point sequence numbers of the individual biological influencing factor change curves,indicate->The number of extremal points of the individual biological influencing factors; />Indicate->Personal biological influencing factor->Data values for the extreme points.
6. The intelligent farming information management system according to claim 1, wherein said method for predicting profits of a farm comprises:
taking the environment main influence factors and the corresponding artificial remedy influence factors and the optimizing main influence factors as main influence factors; obtaining profit ratio according to each cultivation data, input cost and income, and further obtaining average profit ratio of each cluster; obtaining average distances between the farm cultivation data and all the main influence factors of the cultivation data in each cluster, and selecting the cluster with the smallest average distance as a matched cluster; the average profit ratio of the matched cluster is taken as the predicted profit ratio of the farm.
7. The intelligent farming information management system according to claim 1, wherein the environmental impact factors comprise: water temperature, salinity, dissolved oxygen, turbidity, pH value, flow rate, air temperature, rainfall, wind power, tide and sunshine duration;
human influencing factors include: cultivation density, bait feeding amount of a bait feeding machine, bait feeding frequency, a water flow controller, a water temperature regulator, power, discharge capacity and filter screen size of a water quality filter;
biological influencing factors include: the size, weight, growth rate, and health data of the farmed organisms.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311452650.5A CN117196881B (en) | 2023-11-03 | 2023-11-03 | Intelligent cultivation information management system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311452650.5A CN117196881B (en) | 2023-11-03 | 2023-11-03 | Intelligent cultivation information management system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117196881A CN117196881A (en) | 2023-12-08 |
| CN117196881B true CN117196881B (en) | 2024-02-27 |
Family
ID=89003724
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311452650.5A Active CN117196881B (en) | 2023-11-03 | 2023-11-03 | Intelligent cultivation information management system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117196881B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108665106A (en) * | 2018-05-15 | 2018-10-16 | 中国农业大学 | A kind of aquaculture dissolved oxygen prediction method and device |
| CN112330153A (en) * | 2020-11-06 | 2021-02-05 | 广西电网有限责任公司电力科学研究院 | Non-linear orthogonal regression-based industry scale prediction model modeling method and device |
| CN114331127A (en) * | 2021-12-28 | 2022-04-12 | 海南大学 | Water environment nutrition state evaluation method based on primary productivity model |
| CN115014445A (en) * | 2022-08-10 | 2022-09-06 | 中国农业大学 | Smart fishery multi-dimensional panoramic perception monitoring method, system and device |
| JP2023018569A (en) * | 2021-07-27 | 2023-02-08 | パナソニックＩｐマネジメント株式会社 | Milk yield calculation system |
| CN115859057A (en) * | 2022-12-29 | 2023-03-28 | 山东工商学院 | Sea cucumber culture water quality prediction method based on whale algorithm optimization GRU neural network |
| CN116934088A (en) * | 2023-07-24 | 2023-10-24 | 瑞安市致富鸽业有限公司 | Intelligent pigeon breeding management method and system based on analysis model |
-
2023
- 2023-11-03 CN CN202311452650.5A patent/CN117196881B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108665106A (en) * | 2018-05-15 | 2018-10-16 | 中国农业大学 | A kind of aquaculture dissolved oxygen prediction method and device |
| CN112330153A (en) * | 2020-11-06 | 2021-02-05 | 广西电网有限责任公司电力科学研究院 | Non-linear orthogonal regression-based industry scale prediction model modeling method and device |
| JP2023018569A (en) * | 2021-07-27 | 2023-02-08 | パナソニックＩｐマネジメント株式会社 | Milk yield calculation system |
| CN114331127A (en) * | 2021-12-28 | 2022-04-12 | 海南大学 | Water environment nutrition state evaluation method based on primary productivity model |
| CN115014445A (en) * | 2022-08-10 | 2022-09-06 | 中国农业大学 | Smart fishery multi-dimensional panoramic perception monitoring method, system and device |
| CN115859057A (en) * | 2022-12-29 | 2023-03-28 | 山东工商学院 | Sea cucumber culture water quality prediction method based on whale algorithm optimization GRU neural network |
| CN116934088A (en) * | 2023-07-24 | 2023-10-24 | 瑞安市致富鸽业有限公司 | Intelligent pigeon breeding management method and system based on analysis model |
Non-Patent Citations (2)
| Title |
|---|
| 基于PCA-LSTM神经网络的凡纳滨对虾养殖水质预测;习文双;《上海海洋大学学报》;20230131;第32卷(第1期);第108-117页 * |
| 水产养殖大数据技术研究进展与发展趋势分析;段青玲等;《农业机械学报》;20180630;第49卷(第6期);第1-16页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117196881A (en) | 2023-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111639823B (en) | Building cold and heat load prediction method constructed based on feature set | |
| CN110033141B (en) | Method for establishing desulfurization system operation condition database | |
| CN109558467B (en) | Method and system for identifying user category of electricity utilization | |
| CN110045771B (en) | Intelligent monitoring system for water quality of fishpond | |
| CN112949517B (en) | Plant stomata density and opening degree identification method and system based on deep migration learning | |
| CN111461466A (en) | Heating household valve adjusting method, system and equipment based on L STM time sequence | |
| CN113515512A (en) | Quality control and improvement method for industrial internet platform data | |
| CN115907195A (en) | Photovoltaic power generation power prediction method, system, electronic device and medium | |
| CN117196881B (en) | Intelligent cultivation information management system based on big data | |
| CN115879750B (en) | Aquatic seedling environment monitoring management system and method | |
| CN107808209B (en) | Wind power plant abnormal data identification method based on weighted kNN distance | |
| CN116029604B (en) | Cage-raised meat duck breeding environment regulation and control method based on health comfort level | |
| CN116662832A (en) | Training sample selection method based on clustering and active learning | |
| CN116205508A (en) | Distributed photovoltaic power generation abnormality diagnosis method and system | |
| CN114881429B (en) | Data-driven-based method and system for quantifying line loss of transformer area | |
| Kim et al. | Probabilistic Modeling of Fish Growth in Smart Aquaculture Systems | |
| CN117391315B (en) | Agricultural meteorological data management method and device | |
| CN115100322B (en) | Line element self-adaptive simplification method and device for supervised learning supported multi-reduction algorithm cooperation | |
| CN117786584B (en) | Big data analysis-based method and system for monitoring and early warning of water source pollution in animal husbandry | |
| CN110175705B (en) | Load prediction method and memory and system comprising same | |
| CN117493921B (en) | Artificial intelligence energy-saving management method and system based on big data | |
| CN111539839B (en) | Precise power utilization management method for fishery power users | |
| Wang et al. | Integrating field images and microclimate data to realize multi-day ahead forecasting of maize crop coverage using CNN-LSTM | |
| CN117391395A (en) | Automatic adjusting method and system for water supply system | |
| CN117522207A (en) | Layered identification method for energy storage installation potential of industrial enterprise under user side view angle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |