Method and system for regulating and controlling water quality of snail breeding and storage medium

Abstract

The invention relates to a snail breeding water quality regulation and control method and system and a storage medium, and belongs to the technical field of snail breeding. And identifying the state information of the membership degree of the snail living environment at the current timestamp to obtain an identification result, finally generating a related regulation and control scheme according to the identification result, and arranging a snail breeding area based on the related regulation and control scheme. According to the method, the deep neural network, the decision tree model and the Markov chain are fused to evaluate and predict the activity membership state of the current water environment characteristic data, so that the prediction precision of the margarya melanioides culture water quality can be improved, and the margarya melanioides culture water quality can be monitored for a long time; the abnormal state of the water quality can be found in time.

Description

Technical Field

[0001] The present invention relates to the technical field of aquaculture water quality control, and in particular to a method, system and storage medium for controlling water quality in aquaculture of snails. Background Art

[0002] The cultivated snails mainly include the freshwater economic snails of the genus Atropheus and the genus Atropheus of the family Atrophicidae, such as the common Atropheus, such as the square Atropheus, the pear-shaped Atropheus, the copper-rust Atropheus, and the round Atropheus. In recent years, with the surge in the sales of snail noodles, the market demand for snails has increased, and the breeding area and output have also continued to increase. Water quality is a key factor affecting the growth of snails. When the water quality environment is very poor, snails will die in large numbers, which will cause heavy losses to farmers. In the prior art, water quality is often sampled regularly to determine whether the water quality meets the preset requirements. This method cannot detect water quality abnormalities in a timely manner. When water quality abnormalities are found, significant losses have been caused to the breeders. Summary of the invention

[0003] The present invention overcomes the shortcomings of the prior art and provides a method, system and storage medium for regulating water quality in snail farming.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] The first aspect of the present invention provides a method for regulating water quality in snail farming, comprising the following steps:

[0006] Acquire water environment characteristic data information of the snail breeding area within a preset time, and acquire snail survival environment membership status information of the snail breeding area by evaluating the water environment characteristic data information of the snail breeding area within the preset time;

[0007] An active state transition probability prediction model is constructed based on a deep neural network, and the snail living environment membership status information of the snail breeding area is input into the active state transition probability prediction model for encoding learning;

[0008] Predicting the snail survival environment membership state information at the current timestamp according to the active state transition probability prediction model, and obtaining the recognition result by identifying the snail survival environment membership state information at the current timestamp;

[0009] Relevant control plans are generated according to the identification results, and the snail breeding area is arranged based on the relevant control plans.

[0010] Furthermore, in this method, obtaining water environment characteristic data information of the snail breeding area within a preset time specifically includes the following steps:

[0011] Construct a timestamp, obtain the water environment characteristic data information of each timestamp through water quality monitoring equipment, and introduce the skewness-windiness test method to sort the water environment characteristic data information of each timestamp from small to large to obtain the sorting result;

[0012] A sample data set is constructed based on the sorting results, the skewness statistic of each sample data in the sample data set is calculated by the skewness-style test method, and it is determined whether the skewness statistic is greater than the preset skewness threshold;

[0013] When the skewness statistic is greater than the preset skewness threshold, the water environment characteristic data information of the corresponding timestamp is regarded as abnormal data and the abnormal data is removed;

[0014] When the skewness statistic is not greater than the preset skewness threshold, the water environment characteristic data information of the corresponding timestamp is taken as normal data, and the water environment characteristic data information of the snail breeding area within the preset time is constructed based on the normal data.

[0015] Furthermore, in this method, by evaluating the water environment characteristic data information of the snail breeding area within a preset time, the snail survival environment membership status information of the snail breeding area is obtained, which specifically includes:

[0016] Introduce a decision tree algorithm, set a threshold range for water environment characteristic data, set a splitting standard based on the threshold range for water environment characteristic data, and construct a root node based on the water environment characteristic data information of the snail breeding area within a preset time;

[0017] Initialize the splitting of the root node according to the splitting standard to generate several new nodes, and determine whether there are at least two sample data within the threshold range of the water environment characteristic data in the new nodes;

[0018] When there are at least two sample data within the water environment characteristic data threshold range in the new node, the new node is continuously split until there are no at least two sample data within the water environment characteristic data threshold range in the new node, a leaf node is output, and a local outlier detection algorithm is introduced;

[0019] The outlier value of the sample data in the leaf node is calculated by the outlier detection algorithm. When the outlier value is greater than the preset outlier value, the corresponding leaf node is re-split according to the splitting standard until there is no outlier value greater than the preset outlier value. The final leaf node is output, and the snail living environment membership status information of the snail breeding area is generated.

[0020] Furthermore, in this method, an active state transition probability prediction model is constructed based on a deep neural network, and the snail survival environment membership state information of the snail breeding area is input into the active state transition probability prediction model for encoding learning, specifically including:

[0021] The Markov chain is introduced to calculate the state transition probability value of the snail living environment membership state information of the snail breeding area in each timestamp through the Markov chain, and the state transition probability matrix is ​​constructed according to the state transition probability value;

[0022] An active state transition probability prediction model is constructed based on a deep neural network, and the state transition probability matrix is ​​input into the active state transition probability prediction model for encoding learning;

[0023] When the model parameters of the active state transition probability prediction model meet the preset model parameter requirements, the model parameters of the active state transition probability prediction model are saved, and the active state transition probability prediction model is output.

[0024] Furthermore, in this method, the snail survival environment membership state information of the current timestamp is predicted according to the active state transition probability prediction model, and the snail survival environment membership state information of the current timestamp is identified to obtain the identification result, which specifically includes:

[0025] Inputting the snail survival environment membership state information of the snail breeding area into the active state transition probability prediction model for prediction, and obtaining the state transition probability value of the snail survival environment membership state transferring to the next level membership state at the current timestamp;

[0026] When the state transition probability value is greater than the preset state transition probability value, the next level membership state of the snail survival environment membership state in the current timestamp is used as the real-time snail survival environment membership state in the current timestamp;

[0027] Determine whether the real-time snail survival environment membership state in the current timestamp is greater than the preset snail survival environment membership state. If the real-time snail survival environment membership state in the current timestamp is greater than the preset snail survival environment membership state, mark it as an abnormal activity state;

[0028] If the real-time snail living environment membership state in the current timestamp is not greater than the preset snail living environment membership state, it is marked as a normal activity state, and the recognition result is generated according to the abnormal activity state and the normal activity state.

[0029] Furthermore, in this method, a relevant control scheme is generated according to the identification result, and the snail breeding area is arranged based on the relevant control scheme, specifically including:

[0030] If the recognition result is an abnormally active state, the control parameter range of the water purification equipment and the area information of the snail breeding area are obtained, and the estimated number of water purification equipment is calculated based on the control parameter range of the water purification equipment and the area information of the snail breeding area;

[0031] A particle swarm algorithm is introduced, an iteration algebra is set according to the particle swarm algorithm, and the installation position of the water purification equipment is initialized, the water purification equipment is arranged according to the installation position of the water purification equipment, and the total working range of the water purification equipment is calculated according to the installation position of the water purification equipment and the control parameter range of the water purification equipment;

[0032] When the total working range of the water purification equipment is smaller than the breeding area area information of the snail breeding area, the installation position of the water purification equipment is adjusted, and iterative calculation is performed according to iterative algebra until the total working range of the water purification equipment is not smaller than the breeding area area information of the snail breeding area, and the installation position of the water purification equipment is output;

[0033] Relevant control plans are generated according to the installation location of the water purification equipment, and the snail breeding area is arranged based on the relevant control plans.

[0034] A second aspect of the present invention provides a snail farming water quality control system, the system includes a memory and a processor, the memory includes a snail farming water quality control method program, and when the snail farming water quality control method program is executed by the processor, the following steps are implemented:

[0035] Acquire water environment characteristic data information of the snail breeding area within a preset time, and acquire snail survival environment membership status information of the snail breeding area by evaluating the water environment characteristic data information of the snail breeding area within the preset time;

[0036] An active state transition probability prediction model is constructed based on a deep neural network, and the snail living environment membership status information of the snail breeding area is input into the active state transition probability prediction model for encoding learning;

[0037] Predicting the snail survival environment membership state information at the current timestamp according to the active state transition probability prediction model, and obtaining the recognition result by identifying the snail survival environment membership state information at the current timestamp;

[0038] Relevant control schemes are generated according to the identification results, and the snail breeding area is arranged based on the relevant control schemes, and the water quality of the snail breeding area is regulated by purification.

[0039] A third aspect of the present invention provides a computer-readable storage medium, which includes a program for a method for regulating water quality for snail farming. When the program for the method for regulating water quality for snail farming is executed by a processor, any step of the method for regulating water quality for snail farming is implemented.

[0040] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0041] The present invention obtains water environment characteristic data information of the snail breeding area within the preset time, evaluates the water environment characteristic data information of the snail breeding area within the preset time, obtains the snail survival environment membership state information of the snail breeding area, thereby constructing an active state transfer probability prediction model based on a deep neural network, inputs the snail survival environment membership state information of the snail breeding area into the active state transfer probability prediction model for coding learning, and then predicts the snail survival environment membership state information of the current timestamp according to the active state transfer probability prediction model, and identifies the snail survival environment membership state information of the current timestamp, obtains the identification result, and finally generates the relevant control scheme according to the identification result, and arranges the snail breeding area based on the relevant control scheme. The present invention can evaluate and predict the active membership state of the current water environment characteristic data by fusing a deep neural network, a decision tree model and a Markov chain, can improve the prediction accuracy of the snail breeding water quality, can monitor the snail breeding water quality for a long time, and can timely find the abnormal state of the water quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0043] Figure 1 The present invention shows an overall method flow chart of a method for regulating water quality in snail farming;

[0044] Figure 2 A first method flow chart of a method for regulating water quality in snail farming is shown;

[0045] Figure 3 A second method flow chart of a method for regulating water quality in snail farming is shown;

[0046] Figure 4 The system block diagram of a snail farming water quality control system is shown. DETAILED DESCRIPTION

[0047] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0048] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0049] like Figure 1 As shown, the first aspect of the present invention provides a method for regulating water quality in snail farming, comprising the following steps:

[0050] S102: Obtain water environment characteristic data information of the snail breeding area within a preset time, and obtain the snail living environment membership status information of the snail breeding area by evaluating the water environment characteristic data information of the snail breeding area within the preset time;

[0051] S104: constructing an active state transfer probability prediction model based on a deep neural network, and inputting the snail living environment membership state information of the snail breeding area into the active state transfer probability prediction model for coding learning;

[0052] S106: predicting the snail survival environment membership state information of the current timestamp according to the active state transition probability prediction model, and obtaining the recognition result by identifying the snail survival environment membership state information of the current timestamp;

[0053] S108: Generate relevant control schemes according to the identification results, and arrange the snail breeding area based on the relevant control schemes.

[0054] It should be noted that the present invention can evaluate and predict the activity membership state of current water environment characteristic data by integrating deep neural networks, decision tree models and Markov chains, thereby improving the prediction accuracy of snail breeding water quality, enabling long-term monitoring of snail breeding water quality, and timely detection of abnormal water quality.

[0055] like Figure 2 As shown, further, in this method, obtaining water environment characteristic data information of the snail breeding area within a preset time specifically includes the following steps:

[0056] S202: construct a timestamp, obtain water environment characteristic data information of each timestamp through water quality monitoring equipment, and introduce the skewness-windiness test method to sort the water environment characteristic data information of each timestamp from small to large to obtain the sorting result;

[0057] S204: construct a sample data set according to the sorting results, calculate the skewness statistic of each sample data in the sample data set by the skewness-style test method, and determine whether the skewness statistic is greater than a preset skewness threshold;

[0058] S206: When the skewness statistic is greater than a preset skewness threshold, the water environment characteristic data information corresponding to the timestamp is regarded as abnormal data and the abnormal data is removed;

[0059] S208: When the skewness statistic is not greater than the preset skewness threshold, the water environment characteristic data information of the corresponding timestamp is used as normal data, and the water environment characteristic data information of the snail breeding area within the preset time is constructed based on the normal data.

[0060] It should be noted that the skewness-windiness test is an outlier detection method. This method can eliminate abnormal data collected by water quality monitoring equipment. Since temperature and related chemical components will affect the survival activity of snails, when the activity is very low, the snails will die. Among them, water quality monitoring equipment includes water quality temperature wireless sensors, humidity sensors, chemical composition sensors, etc.

[0061] like Figure 3 As shown, further, in this method, by evaluating the water environment characteristic data information of the snail breeding area within a preset time, the snail living environment membership status information of the snail breeding area is obtained, specifically including:

[0062] S302: Introduce a decision tree algorithm, set a water environment characteristic data threshold range, set a splitting standard according to the water environment characteristic data threshold range, and construct a root node based on the water environment characteristic data information of the snail breeding area within a preset time;

[0063] S304: Initialize the splitting of the root node according to the splitting standard to generate several new nodes, and determine whether there are sample data within the threshold range of at least two water environment characteristic data in the new nodes;

[0064] S306: When there are at least two sample data within the water environment characteristic data threshold range in the new node, the new node is continuously split until there are no at least two sample data within the water environment characteristic data threshold range in the new node, a leaf node is output, and a local outlier detection algorithm is introduced;

[0065] S308: Calculate the outlier value of the sample data in the leaf node through the outlier detection algorithm. When the outlier value is greater than the preset outlier value, the corresponding leaf node is re-split according to the splitting standard until there is no outlier value greater than the preset outlier value. Output the final leaf node and generate the snail living environment membership status information of the snail breeding area.

[0066] It should be noted that the threshold range of water environment characteristic data is set by the user, such as the temperature of -20 to 0 degrees Celsius is a low activity state membership, the concentration of a certain metal ion is 5-10 mol / L is a low activity state membership, etc., which is not too restricted in this implementation, and technicians in this field can set it according to the actual situation. When the outlier value is greater than the preset outlier value, it means that sample data of other water environment characteristic data threshold ranges appear in the leaf node, indicating that the decision tree algorithm has a local optimal solution. Among them, the outlier detection algorithm is integrated into the decision tree model, which can further improve the classification accuracy and avoid the phenomenon of the decision tree algorithm having a local optimal solution, thereby improving the prediction accuracy of the water quality activity state membership.

[0067] Furthermore, in this method, an active state transition probability prediction model is constructed based on a deep neural network, and the snail survival environment membership state information of the snail breeding area is input into the active state transition probability prediction model for encoding learning, specifically including:

[0068] The Markov chain is introduced to calculate the state transition probability value of the snail living environment membership state information of the snail breeding area in each timestamp through the Markov chain, and the state transition probability matrix is ​​constructed according to the state transition probability value;

[0069] An active state transition probability prediction model is constructed based on a deep neural network, and the state transition probability matrix is ​​input into the active state transition probability prediction model for encoding learning;

[0070] When the model parameters of the active state transition probability prediction model meet the preset model parameter requirements, the model parameters of the active state transition probability prediction model are saved, and the active state transition probability prediction model is output.

[0071] It should be noted that in a long time series, the Markov chain can calculate the state transition probability value of the snail living environment membership state information in the snail breeding area in the timestamp to another membership state. In the process of transfer, it can be seen that the high activity state is transferred to the low activity state, and the low activity state is also transferred to the high activity state. This is due to the self-regulation function of the ecological chain in the environment. When the self-regulation function is not sufficient for regulation, it will transfer from the low activity state to the high activity state, resulting in abnormal water quality. This method can further improve the prediction accuracy of the water quality activity state membership.

[0072] Furthermore, in this method, the snail survival environment membership state information of the current timestamp is predicted according to the active state transition probability prediction model, and the snail survival environment membership state information of the current timestamp is identified to obtain the identification result, which specifically includes:

[0073] Inputting the snail survival environment membership state information of the snail breeding area into the active state transition probability prediction model for prediction, and obtaining the state transition probability value of the snail survival environment membership state transferring to the next level membership state at the current timestamp;

[0074] When the state transition probability value is greater than the preset state transition probability value, the next level membership state of the snail survival environment membership state in the current timestamp is used as the real-time snail survival environment membership state in the current timestamp;

[0075] Determine whether the real-time snail survival environment membership state in the current timestamp is greater than the preset snail survival environment membership state. If the real-time snail survival environment membership state in the current timestamp is greater than the preset snail survival environment membership state, mark it as an abnormal activity state;

[0076] If the real-time snail living environment membership state in the current timestamp is not greater than the preset snail living environment membership state, it is marked as a normal activity state, and the recognition result is generated according to the abnormal activity state and the normal activity state.

[0077] It should be noted that when the state transition probability value is greater than the preset state transition probability value, it indicates that the state membership of the current timestamp has been transferred. This method can further improve the prediction accuracy of the water quality activity state membership.

[0078] Furthermore, in this method, a relevant control scheme is generated according to the identification result, and the snail breeding area is arranged based on the relevant control scheme, specifically including:

[0079] If the recognition result is an abnormally active state, the control parameter range of the water purification equipment and the area information of the snail breeding area are obtained, and the estimated number of water purification equipment is calculated based on the control parameter range of the water purification equipment and the area information of the snail breeding area;

[0080] A particle swarm algorithm is introduced, an iteration algebra is set according to the particle swarm algorithm, and the installation position of the water purification equipment is initialized, the water purification equipment is arranged according to the installation position of the water purification equipment, and the total working range of the water purification equipment is calculated according to the installation position of the water purification equipment and the control parameter range of the water purification equipment;

[0081] When the total working range of the water purification equipment is smaller than the breeding area area information of the snail breeding area, the installation position of the water purification equipment is adjusted, and iterative calculation is performed according to iterative algebra until the total working range of the water purification equipment is not smaller than the breeding area area information of the snail breeding area, and the installation position of the water purification equipment is output;

[0082] Relevant control plans are generated according to the installation location of the water purification equipment, and the snail breeding area is arranged based on the relevant control plans.

[0083] It should be noted that, in fact, water purification equipment has a suitable range of control parameters. This method can improve the rationality of the control scheme, improve the control effect of water purification, and complete rapid and reasonable water quality control in snail breeding areas.

[0084] like Figure 4 As shown, the second aspect of the present invention provides a snail farming water quality control system 4, the system 4 includes a memory 41 and a processor 42, the memory 41 includes a snail farming water quality control method program, and when the snail farming water quality control method program is executed by the processor 42, the following steps are implemented:

[0085] Acquire water environment characteristic data information of the snail breeding area within a preset time, and acquire snail survival environment membership status information of the snail breeding area by evaluating the water environment characteristic data information of the snail breeding area within the preset time;

[0086] An active state transition probability prediction model is constructed based on a deep neural network, and the snail living environment membership status information of the snail breeding area is input into the active state transition probability prediction model for encoding learning;

[0087] Predicting the snail survival environment membership state information at the current timestamp according to the active state transition probability prediction model, and obtaining the recognition result by identifying the snail survival environment membership state information at the current timestamp;

[0088] Relevant control schemes are generated according to the identification results, and the snail breeding area is arranged based on the relevant control schemes, and the water quality of the snail breeding area is regulated by purification.

[0089] Furthermore, in this system, the water environment characteristic data information of the snail breeding area within a preset time is obtained, which specifically includes the following steps:

[0090] Construct a timestamp, obtain the water environment characteristic data information of each timestamp through water quality monitoring equipment, and introduce the skewness-windiness test method to sort the water environment characteristic data information of each timestamp from small to large to obtain the sorting result;

[0091] A sample data set is constructed based on the sorting results, the skewness statistic of each sample data in the sample data set is calculated by the skewness-style test method, and it is determined whether the skewness statistic is greater than the preset skewness threshold;

[0092] When the skewness statistic is greater than the preset skewness threshold, the water environment characteristic data information of the corresponding timestamp is regarded as abnormal data and the abnormal data is removed;

[0093] When the skewness statistic is not greater than the preset skewness threshold, the water environment characteristic data information of the corresponding timestamp is taken as normal data, and the water environment characteristic data information of the snail breeding area within the preset time is constructed based on the normal data.

[0094] Furthermore, in this system, by evaluating the water environment characteristic data information of the snail breeding area within a preset time, the snail living environment membership status information of the snail breeding area is obtained, specifically including:

[0095] Introduce a decision tree algorithm, set a threshold range for water environment characteristic data, set a splitting standard based on the threshold range for water environment characteristic data, and construct a root node based on the water environment characteristic data information of the snail breeding area within a preset time;

[0096] Initialize the splitting of the root node according to the splitting standard to generate several new nodes, and determine whether there are at least two sample data within the threshold range of the water environment characteristic data in the new nodes;

[0097] When there are at least two sample data within the water environment characteristic data threshold range in the new node, the new node is continuously split until there are no at least two sample data within the water environment characteristic data threshold range in the new node, a leaf node is output, and a local outlier detection algorithm is introduced;

[0098] The outlier detection algorithm is used to calculate the outlier value of the sample data in the leaf node. When the outlier value is greater than the preset outlier value, the corresponding leaf node is re-split according to the splitting standard until there is no outlier value greater than the preset outlier value. The final leaf node is output and the snail survival environment membership status information of the snail breeding area is generated.

[0099] Furthermore, in this system, an active state transition probability prediction model is constructed based on a deep neural network, and the snail living environment membership state information of the snail breeding area is input into the active state transition probability prediction model for coding learning, specifically including:

[0100] The Markov chain is introduced to calculate the state transition probability value of the snail living environment membership state information of the snail breeding area in each timestamp through the Markov chain, and the state transition probability matrix is ​​constructed according to the state transition probability value;

[0101] An active state transition probability prediction model is constructed based on a deep neural network, and the state transition probability matrix is ​​input into the active state transition probability prediction model for encoding learning;

[0102] When the model parameters of the active state transition probability prediction model meet the preset model parameter requirements, the model parameters of the active state transition probability prediction model are saved, and the active state transition probability prediction model is output.

[0103] Furthermore, in this system, the snail survival environment membership state information of the current timestamp is predicted according to the active state transition probability prediction model, and the snail survival environment membership state information of the current timestamp is identified to obtain the identification result, which specifically includes:

[0104] Inputting the snail survival environment membership state information of the snail breeding area into the active state transition probability prediction model for prediction, and obtaining the state transition probability value of the snail survival environment membership state transferring to the next level membership state at the current timestamp;

[0105] When the state transition probability value is greater than the preset state transition probability value, the next level membership state of the snail survival environment membership state in the current timestamp is used as the real-time snail survival environment membership state in the current timestamp;

[0106] Determine whether the real-time snail survival environment membership state in the current timestamp is greater than the preset snail survival environment membership state. If the real-time snail survival environment membership state in the current timestamp is greater than the preset snail survival environment membership state, mark it as an abnormal activity state;

[0107] If the real-time snail living environment membership state in the current timestamp is not greater than the preset snail living environment membership state, it is marked as a normal activity state, and the recognition result is generated according to the abnormal activity state and the normal activity state.

[0108] Furthermore, in this system, a relevant control scheme is generated according to the recognition result, and the snail breeding area is arranged based on the relevant control scheme, specifically including:

[0109] If the recognition result is an abnormally active state, the control parameter range of the water purification equipment and the area information of the snail breeding area are obtained, and the estimated number of water purification equipment is calculated based on the control parameter range of the water purification equipment and the area information of the snail breeding area;

[0110] A particle swarm algorithm is introduced, an iteration algebra is set according to the particle swarm algorithm, and the installation position of the water purification equipment is initialized, the water purification equipment is arranged according to the installation position of the water purification equipment, and the total working range of the water purification equipment is calculated according to the installation position of the water purification equipment and the control parameter range of the water purification equipment;

[0111] When the total working range of the water purification equipment is smaller than the breeding area area information of the snail breeding area, the installation position of the water purification equipment is adjusted, and iterative calculation is performed according to iterative algebra until the total working range of the water purification equipment is not smaller than the breeding area area information of the snail breeding area, and the installation position of the water purification equipment is output;

[0112] Relevant control plans are generated according to the installation location of the water purification equipment, and the snail breeding area is arranged based on the relevant control plans.

[0113] A third aspect of the present invention provides a computer-readable storage medium, which includes a program for a method for regulating water quality for snail farming. When the program for the method for regulating water quality for snail farming is executed by a processor, any step of the method for regulating water quality for snail farming is implemented.

[0114] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0115] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0116] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0117] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0118] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0119] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for regulating water quality in snail farming, It is characterized in that The following steps are involved: Acquire water environment characteristic data information of a snail breeding area within a preset time, and acquire snail survival environment membership status information of the snail breeding area by evaluating the water environment characteristic data information of the snail breeding area within the preset time; An active state transition probability prediction model is constructed based on a deep neural network, and the snail living environment membership state information of the snail breeding area is input into the active state transition probability prediction model for coding learning; Predicting the snail survival environment membership state information of the current timestamp according to the active state transition probability prediction model, and obtaining the recognition result by identifying the snail survival environment membership state information of the current timestamp; A relevant control scheme is generated according to the identification result, and the snail breeding area is arranged based on the relevant control scheme.

2. A method for controlling water quality in snail farming according to claim 1, It is characterized in that Obtaining water environment characteristic data information of the snail breeding area within a preset time specifically includes the following steps: Constructing a timestamp, obtaining water environment characteristic data information of each timestamp through a water quality monitoring device, and introducing a skewness-windiness test method to sort the water environment characteristic data information of each timestamp from small to large to obtain a sorting result; Constructing a sample data set according to the sorting result, calculating the skewness statistic of each sample data in the sample data set by the skewness-style test method, and determining whether the skewness statistic is greater than a preset skewness threshold; When the skewness statistic is greater than the preset skewness threshold, the water environment characteristic data information of the corresponding timestamp is regarded as abnormal data, and the abnormal data is removed; When the skewness statistic is not greater than the preset skewness threshold, the water environment characteristic data information of the corresponding timestamp is used as normal data, and the water environment characteristic data information of the snail breeding area within the preset time is constructed according to the normal data.

3. A method for controlling water quality in snail farming according to claim 1, It is characterized in that By evaluating the water environment characteristic data information of the snail breeding area within the preset time, the snail living environment membership status information of the snail breeding area is obtained, specifically including: Introducing a decision tree algorithm, setting a threshold range for water environment characteristic data, setting a splitting standard according to the threshold range for water environment characteristic data, and constructing a root node based on the water environment characteristic data information of the snail breeding area within the preset time; Initializing the splitting of the root node according to the splitting standard to generate a number of new nodes, and determining whether there are sample data within at least two water environment characteristic data threshold ranges in the new nodes; When there are at least two sample data within the water environment characteristic data threshold range in the new node, the new node is continuously split until there are no at least two sample data within the water environment characteristic data threshold range in the new node, a leaf node is output, and a local outlier detection algorithm is introduced; The outlier detection algorithm is used to calculate the outlier value of the sample data in the leaf node. When the outlier value is greater than the preset outlier value, the corresponding leaf node is re-split according to the splitting standard until the outlier value is no longer greater than the preset outlier value. The final leaf node is output, and the snail living environment membership status information of the snail breeding area is generated.

4. A method for controlling water quality in snail farming according to claim 1, It is characterized in that An active state transition probability prediction model is constructed based on a deep neural network, and the snail living environment membership state information of the snail breeding area is input into the active state transition probability prediction model for coding learning, specifically including: A Markov chain is introduced, and a state transition probability value of the snail living environment membership state information of the snail breeding area in each timestamp is calculated by the Markov chain, and a state transition probability matrix is ​​constructed according to the state transition probability value; Building an active state transition probability prediction model based on a deep neural network, and inputting the state transition probability matrix into the active state transition probability prediction model for encoding learning; When the model parameters of the activity state transition probability prediction model meet the preset model parameter requirements, the model parameters of the activity state transition probability prediction model are saved, and the activity state transition probability prediction model is output.

5. A method for controlling water quality in snail farming according to claim 1, It is characterized in that Predicting the snail survival environment membership state information at the current timestamp according to the active state transition probability prediction model, and obtaining the recognition result by identifying the snail survival environment membership state information at the current timestamp, specifically including: Inputting the snail living environment membership state information of the snail breeding area into the active state transition probability prediction model for prediction, and obtaining the state transition probability value of the snail living environment membership state transferring to the next level membership state at the current timestamp; When the state transition probability value is greater than the preset state transition probability value, the next level membership state of the snail living environment membership state in the current timestamp is used as the real-time snail living environment membership state in the current timestamp; Determine whether the real-time snail living environment membership state in the current timestamp is greater than the preset snail living environment membership state, if the real-time snail living environment membership state in the current timestamp is greater than the preset snail living environment membership state, mark it as an abnormal activity state; If the real-time snail living environment membership state in the current timestamp is not greater than the preset snail living environment membership state, it is marked as a normal activity state, and an identification result is generated according to the abnormal activity state and the normal activity state.

6. A method for controlling water quality in snail farming according to claim 1, It is characterized in that Generate a relevant control scheme according to the identification result, and arrange the snail breeding area based on the relevant control scheme, specifically including: If the identification result is an abnormally active state, obtaining the control parameter range of the water purification equipment and the breeding area area information of the snail breeding area, and calculating the estimated quantity information of the water purification equipment according to the control parameter range of the water purification equipment and the breeding area area information of the snail breeding area; Introducing a particle swarm algorithm, setting an iteration number according to the particle swarm algorithm, and initializing the installation position of the water purification equipment, arranging the water purification equipment according to the installation position of the water purification equipment, and calculating the total working range of the water purification equipment according to the installation position of the water purification equipment and the control parameter range of the water purification equipment; When the total working range of the water purification equipment is smaller than the breeding area area information of the snail breeding area, the installation position of the water purification equipment is adjusted, and iterative calculation is performed according to the iterative algebra until the total working range of the water purification equipment is not smaller than the breeding area area information of the snail breeding area, and the installation position of the water purification equipment is output; A relevant control scheme is generated according to the installation position of the water purification equipment, and the snail breeding area is arranged based on the relevant control scheme.

7. A water quality control system for snail farming, It is characterized in that The system includes a memory and a processor, wherein the memory includes a method program for regulating water quality for snail farming, and when the method program for regulating water quality for snail farming is executed by the processor, the following steps are implemented: Acquire water environment characteristic data information of a snail breeding area within a preset time, and acquire snail survival environment membership status information of the snail breeding area by evaluating the water environment characteristic data information of the snail breeding area within the preset time; An active state transition probability prediction model is constructed based on a deep neural network, and the snail living environment membership state information of the snail breeding area is input into the active state transition probability prediction model for coding learning; Predicting the snail survival environment membership state information of the current timestamp according to the active state transition probability prediction model, and obtaining the recognition result by identifying the snail survival environment membership state information of the current timestamp; A relevant control scheme is generated according to the identification result, and the snail breeding area is arranged based on the relevant control scheme, and the water quality of the snail breeding area is regulated by purification.

8. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a program for a method for regulating water quality for snail farming. When the program for regulating water quality for snail farming is executed by a processor, the steps of the method for regulating water quality for snail farming as described in any one of claims 1 to 6 are implemented.

Images