Method and system for monitoring growth environment of pearl shellfish

Abstract

The invention relates to a pearl cultivation shell growth environment monitoring method and system, and relates to the field of environment monitoring, and the method comprises the steps: carrying out the abnormal environment parameter classification of a plurality of environment parameter sets, and obtaining a first abnormal proportion and a second abnormal proportion; according to the first abnormal proportion and the second abnormal proportion, a third abnormal proportion is obtained through correction, the abnormities recognition scale of the pearl culture environment and the pearl environment is configured, environment parameter abnormities are recognized, and abnormities of the pearl culture environment and the pearl environment are obtained; according to the first abnormal proportion and the third abnormal proportion, weighted calculation is conducted on the abnormities of the pearl breeding shell and pearl environment, and the abnormities of the growth environment are obtained to serve as environment monitoring results. According to the method, the technical problem that the accuracy and reliability of environment monitoring are insufficient due to the fact that an existing method lacks comprehensive analysis on the interactive influence between the growth environment of the pearl shellfish and the pearl quality can be solved, the accuracy and reliability of environment monitoring can be remarkably improved, and the health condition of the pearl shellfish and the change of the pearl quality can be comprehensively and accurately reflected.

Description

Technical Field

[0001] The present invention relates to the field of environmental monitoring, and particularly to a method and system for monitoring the growth environment of pearl oysters. Background Art

[0002] During the breeding of pearl oysters and the production of pearls, the monitoring and optimization of the growth environment are crucial for ensuring the healthy growth of pearl oysters and the high-quality formation of pearls. The health status of pearl oysters is closely related to the quality of pearls, and the growth environment of pearl oysters has a direct impact on the uniformity and quality of pearl formation.

[0003] However, existing environmental monitoring systems usually regard the growth environment of pearl oysters and the quality of pearls as two independent monitoring objects, lacking a comprehensive analysis of the interaction between the two, and unable to accurately reveal the overall impact of environmental factors on pearl formation, resulting in insufficient accuracy and reliability of environmental monitoring. Summary of the Invention

[0004] Aiming at the technical problem that the existing method for monitoring the growth environment of pearl oysters lacks a comprehensive analysis of the interaction between the growth environment of pearl oysters and the quality of pearls, resulting in insufficient accuracy and reliability of environmental monitoring, the present invention provides a method and system for monitoring the growth environment of pearl oysters to solve this problem.

[0005] The technical solutions of the present invention for solving the above technical problems are as follows:

[0006] In the first aspect, the present invention provides a method for monitoring the growth environment of pearl oysters, including: during the growth process of pearl oysters, monitoring and collecting environmental parameters of multiple categories of environmental parameter types to obtain multiple environmental parameter sets, where the multiple categories of environmental parameter types include water temperature, salinity, and dissolved oxygen; respectively using a pearl oyster anomaly classifier and a pearl anomaly classifier to classify the abnormal environmental parameters of the multiple environmental parameter sets to obtain a first anomaly ratio and a second anomaly ratio, where the pearl oyster anomaly classifier and the pearl anomaly classifier include multiple anomaly classification paths corresponding to the multiple categories of environmental parameter types; according to the first anomaly ratio and the second anomaly ratio, correcting to obtain a third anomaly ratio, configuring the scale of pearl oyster environmental anomaly recognition and the scale of pearl environmental anomaly recognition, and respectively performing environmental parameter anomaly recognition on the multiple environmental parameter sets to obtain the pearl oyster environmental anomaly level and the pearl environmental anomaly level; according to the first anomaly ratio and the third anomaly ratio, performing weighted calculation on the pearl oyster environmental anomaly level and the pearl environmental anomaly level to obtain the growth environment anomaly level as the monitoring result of the growth environment of pearl oysters.

[0007] Further, during the growth process of pearl oysters, monitoring and collecting environmental parameters of multiple categories of environmental parameter types to obtain multiple environmental parameter sets, including:

[0008] During the growth of pearl oysters, according to multiple categories of environmental parameter types, collect the set of environmental parameters at the first position in the growth environment, where the multiple categories of environmental parameter types include water temperature, salinity, and dissolved oxygen;

[0009] Continue to collect and obtain the sets of environmental parameters at multiple positions, obtaining multiple sets of environmental parameters.

[0010] Furthermore, respectively use the pearl oyster anomaly classifier and the pearl anomaly classifier to classify the abnormal environmental parameters of the multiple sets of environmental parameters, obtaining the first anomaly ratio and the second anomaly ratio, including:

[0011] Divide the multiple sets of environmental parameters according to the multiple categories of environmental parameter types to obtain a water temperature set, a salinity set, and a dissolved oxygen set;

[0012] Input the water temperature set, the salinity set, and the dissolved oxygen set into the pearl oyster anomaly classifier respectively for abnormal environmental parameter classification, obtaining the first water temperature anomaly ratio, the first salinity anomaly ratio, and the first dissolved oxygen anomaly ratio, and calculate to obtain the first anomaly ratio, where the pearl oyster anomaly classifier is constructed based on the normal environmental parameters of pearl oyster growth within the historical time, including the first water temperature abnormal classification path, the first salinity abnormal classification path, and the first dissolved oxygen abnormal classification path;

[0013] Construct a pearl anomaly classifier according to the normal environmental parameters of pearl cultivation within the historical time, where the pearl anomaly classifier includes a second water temperature abnormal classification path, a second salinity abnormal classification path, and a second dissolved oxygen abnormal classification path;

[0014] Input the water temperature set, the salinity set, and the dissolved oxygen set into the second water temperature abnormal classification path, the second salinity abnormal classification path, and the second dissolved oxygen abnormal classification path respectively for abnormal environmental parameter classification, obtaining the second water temperature anomaly ratio, the second salinity anomaly ratio, and the second dissolved oxygen anomaly ratio, and calculate to obtain the second anomaly ratio.

[0015] Furthermore, input the water temperature set, the salinity set, and the dissolved oxygen set into the pearl oyster anomaly classifier respectively for abnormal environmental parameter classification, obtaining the first water temperature anomaly ratio, the first salinity anomaly ratio, and the first dissolved oxygen anomaly ratio, and calculate to obtain the first anomaly ratio, including:

[0016] Obtain the normal growth environmental parameters of pearl oysters within the preset historical time range and divide them into a normal water temperature set, a normal salinity set, and a normal dissolved oxygen set;

[0017] Construct binary classification nodes using the normal water temperature set, normal salinity set, and normal dissolved oxygen set respectively, obtain the first water temperature division node set, the first salinity division node set, and the first dissolved oxygen division node set, and construct the first water temperature anomaly classification path, the first salinity anomaly classification path, and the first dissolved oxygen anomaly classification path;

[0018] Input the water temperature set, salinity set, and dissolved oxygen set into the first water temperature anomaly classification path, the first salinity anomaly classification path, and the first dissolved oxygen anomaly classification path respectively for division, screen the proportions of single water temperature parameters, single salinity parameters, and single dissolved oxygen parameters, and obtain the first water temperature anomaly proportion, the first salinity anomaly proportion, and the first dissolved oxygen anomaly proportion;

[0019] Calculate the mean of the first water temperature anomaly proportion, the first salinity anomaly proportion, and the first dissolved oxygen anomaly proportion to obtain the first anomaly proportion.

[0020] Furthermore, according to the first anomaly proportion and the second anomaly proportion, correct and obtain the third anomaly proportion, configure the pearl oyster environment anomaly recognition scale and the pearl environment anomaly recognition scale, and respectively perform environment parameter anomaly recognition on multiple environment parameter sets to obtain the pearl oyster environment anomaly level and the pearl environment anomaly level, including:

[0021] Use the sum of 1 and the first anomaly proportion as the correction coefficient, multiply it by the second anomaly proportion to obtain the third anomaly proportion;

[0022] Obtain the maximum anomaly recognition scale, where the maximum anomaly recognition scale includes the maximum integrated anomaly recognition quantity;

[0023] Respectively multiply the first anomaly proportion and the third anomaly proportion by the maximum integrated anomaly recognition quantity and round up to obtain the pearl oyster integrated anomaly recognition quantity and the pearl integrated anomaly recognition quantity, which are used as the pearl oyster environment anomaly recognition scale and the pearl environment anomaly recognition scale;

[0024] According to the maximum integrated anomaly recognition quantity, based on ensemble learning, construct a pearl oyster environment anomaly recognizer including multiple first environment anomaly recognition branches and a pearl environment anomaly recognizer including multiple second environment anomaly recognition branches;

[0025] Respectively input the multiple environment parameter sets into the first environment anomaly recognition branches of the pearl oyster integrated anomaly recognition quantity and the second environment anomaly recognition branches of the pearl integrated anomaly recognition quantity, output and obtain multiple pearl oyster environment anomaly level sets and multiple pearl environment anomaly level sets, and calculate the mean respectively to obtain the pearl oyster environment anomaly level and the pearl environment anomaly level.

[0026] Further, according to the maximum integrated anomaly recognition quantity, based on ensemble learning, construct a pearl oyster environmental anomaly recognizer including multiple first environmental anomaly recognition branches and a pearl environmental anomaly recognizer including multiple second environmental anomaly recognition branches, including:

[0027] According to the historical growth environment data of pearl oysters and pearls, collect multiple sets of sample environmental parameters, respectively perform pearl oyster environmental anomaly level identification and pearl environmental anomaly level identification, and obtain a sample pearl oyster environmental anomaly level set and a sample pearl environmental anomaly level set;

[0028] According to the maximum integrated anomaly recognition quantity, divide the multiple sets of sample environmental parameters, the sample pearl oyster environmental anomaly level set and the sample pearl environmental anomaly level set to obtain multiple portions of input data, multiple portions of first output data and multiple portions of second output data;

[0029] Use the multiple portions of input data to respectively combine the multiple portions of first output data and multiple portions of second output data to train multiple first environmental anomaly recognition branches and multiple second environmental anomaly recognition branches;

[0030] Respectively combine the multiple first environmental anomaly recognition branches and multiple second environmental anomaly recognition branches to obtain a pearl oyster environmental anomaly recognizer and a pearl environmental anomaly recognizer.

[0031] Further, according to the first anomaly ratio and the third anomaly ratio, perform weighted calculation on the pearl oyster environmental anomaly level and the pearl environmental anomaly level to obtain a growth environment anomaly level as the monitoring result of the pearl oyster growth environment, including:

[0032] Configure a pearl oyster weight and a pearl weight according to the first anomaly ratio and the third anomaly ratio;

[0033] Use the pearl oyster weight and the pearl weight to perform weighted calculation on the pearl oyster environmental anomaly level and the pearl environmental anomaly level to obtain a growth environment anomaly level as the monitoring result of the pearl oyster growth environment.

[0034] Second aspect, the present invention provides a growth environment monitoring system for pearl oysters, comprising: an environmental parameter monitoring module, configured to monitor and collect environmental parameters of multiple environmental parameter categories during the growth process of pearl oysters, obtaining multiple environmental parameter sets, wherein the multiple environmental parameter categories include water temperature, salinity, and dissolved oxygen; an abnormal environmental parameter classification module, configured to respectively use a pearl oyster abnormality classifier and a pearl abnormality classifier to classify abnormal environmental parameters for the multiple environmental parameter sets, obtaining a first abnormality ratio and a second abnormality ratio, wherein the pearl oyster abnormality classifier and the pearl abnormality classifier include multiple abnormal classification paths corresponding to the multiple environmental parameter categories; an environmental parameter abnormality recognition module, configured to correct and obtain a third abnormality ratio according to the first abnormality ratio and the second abnormality ratio, configure the pearl oyster environmental abnormality recognition scale and the pearl environmental abnormality recognition scale, and respectively perform environmental parameter abnormality recognition on the multiple environmental parameter sets, obtaining a pearl oyster environmental abnormality level and a pearl environmental abnormality level; an environmental monitoring result obtaining module, configured to perform weighted calculation on the pearl oyster environmental abnormality level and the pearl environmental abnormality level according to the first abnormality ratio and the third abnormality ratio, obtaining a growth environment abnormality level as the growth environment monitoring result of the pearl oysters.

[0035] Third aspect, the present invention further provides an electronic device, comprising:

[0036] At least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the steps of the method according to any one of the above first aspects.

[0037] Fourth aspect, a computer-readable storage medium, on which a computer program is stored, and the computer program realizes the steps of the method according to any one of the above first aspects when executed.

[0038] The beneficial effects of the present invention are as follows: During the growth process of pearl oysters, environmental parameters of multiple environmental parameter categories are monitored and collected to obtain multiple environmental parameter sets. Among them, the multiple environmental parameter categories include water temperature, salinity, and dissolved oxygen. Then, a pearl oyster anomaly classifier and a pearl anomaly classifier are respectively used to classify the abnormal environmental parameters of the multiple environmental parameter sets to obtain a first anomaly ratio and a second anomaly ratio. Among them, the pearl oyster anomaly classifier and the pearl anomaly classifier include multiple anomaly classification paths corresponding to the multiple environmental parameter categories. Then, according to the first anomaly ratio and the second anomaly ratio, a third anomaly ratio is corrected and obtained, and the scale of pearl oyster environmental anomaly recognition and the scale of pearl environmental anomaly recognition are configured to respectively identify the abnormal environmental parameters of the multiple environmental parameter sets to obtain the pearl oyster environmental anomaly level and the pearl environmental anomaly level. Finally, according to the first anomaly ratio and the third anomaly ratio, a weighted calculation is performed on the pearl oyster environmental anomaly level and the pearl environmental anomaly level to obtain the growth environment anomaly level, which is used as the monitoring result of the pearl oyster growth environment. That is to say, through the comprehensive analysis of multi-dimensional environmental parameters and the interactive influence analysis of the pearl oyster growth environment and pearl quality, the accuracy and reliability of the pearl oyster growth environment monitoring can be significantly improved, and the health status of the pearl oyster and the changes in pearl quality can be more comprehensively and accurately reflected, thereby providing a more scientific and refined environmental regulation basis for pearl quality control. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic flowchart of a method for monitoring the growth environment of pearl oysters provided by the present invention;

[0040] Figure 2 It is a schematic structural diagram of a system for monitoring the growth environment of pearl oysters provided by the present invention;

[0041] Figure 3 It is a schematic structural diagram of an electronic device provided by the present invention;

[0042] Figure 4 It is a schematic structural diagram of a computer-readable storage medium provided by the present invention.

[0043] In the drawings, the components represented by each reference numeral are described as follows:

[0044] Environmental parameter monitoring module 01, abnormal environmental parameter classification module 02, environmental parameter anomaly recognition module 03, environmental monitoring result obtaining module 04, electronic device 500, memory 510, processor 520, first computer program 511, computer-readable storage medium 600, second computer program 611. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0046] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, "a plurality of" means two or more, unless otherwise specifically defined.

[0047] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as being more preferred or having more advantages than other embodiments. In order for any person skilled in the art to implement and use the present invention, the following description is given. In the following description, details are set forth for the purpose of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid unnecessary details from obscuring the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope that conforms to the principles and features disclosed in the present invention.

[0048] Embodiment 1, as Figure 1 shown, the embodiment of the present invention provides a method for monitoring the growth environment of pearl oysters, specifically including the following steps:

[0049] S100: During the growth process of pearl oysters, monitor and collect environmental parameters of multiple categories of environmental parameters to obtain multiple environmental parameter sets, where the multiple categories of environmental parameters include water temperature, salinity, and dissolved oxygen.

[0050] Further, step S100 of the present invention further includes:

[0051] S110: During the growth process of pearl oysters, collect an environmental parameter set at the first position in the growth environment according to multiple categories of environmental parameters, where the multiple categories of environmental parameters include water temperature, salinity, and dissolved oxygen; S120: Continue to collect environmental parameter sets at multiple positions to obtain multiple environmental parameter sets.

[0052] Specifically, in the process of pearl oyster farming and pearl production, the growth environment of pearl oysters plays a decisive role. The growth of pearl oysters and the formation of pearls are jointly affected by environmental parameters such as water temperature, salinity, and dissolved oxygen. These environmental parameters not only affect the growth of shellfish individually but also have complex interaction relationships with each other, thereby affecting the quality and uniformity of pearls. Therefore, accurately monitoring and analyzing the changes in environmental parameters are crucial for optimizing the growth environment of pearl oysters and improving pearl quality.

[0053] Obtain multiple categories of environmental parameters that affect the growth process of pearl oysters. Among them, the multiple categories of environmental parameters include water temperature, salinity, and dissolved oxygen, which have important effects on shellfish growth and pearl quality respectively. For example, water temperature affects the metabolism and growth rate of shellfish; salinity affects the adaptability of shellfish and the pearl formation process; dissolved oxygen directly affects the respiration and metabolic activities of shellfish and also affects the texture uniformity of pearls.

[0054] Pearl oysters are usually distributed at multiple positions in the aquaculture water body, and the environmental parameters at each position may be different. In order to accurately understand the impact of the entire aquaculture environment on pearl oysters, it is necessary to collect environmental parameter data at multiple positions to reflect the environmental states such as water temperature, salinity, and dissolved oxygen at different positions. First, based on the actual aquaculture scenario of pearl oysters, arrange multiple environmental parameter collection positions. These positions can be different regions in the water body (such as near the shore, deep water area, different water depths, etc.) to obtain more extensive and comprehensive environmental data. Then, randomly select any one position from the multiple collection positions as the first position, and collect the environmental parameter set at the first position in the growth environment according to the multiple categories of environmental parameters. Using the same method, continue to collect the environmental parameter sets (water temperature data, salinity data, and dissolved oxygen data) at multiple positions to obtain multiple environmental parameter sets, where the environmental parameter sets and the collection positions correspond one by one. By arranging multiple environmental parameter collection positions in the actual aquaculture scenario of pearl oysters and collecting multiple categories of environmental parameters such as water temperature, salinity, and dissolved oxygen, the changes in the growth environment of pearl oysters can be comprehensively and accurately reflected, providing a basis for subsequent data analysis and anomaly detection.

[0055] S200: Respectively use the pearl oyster anomaly classifier and the pearl anomaly classifier to classify the abnormal environmental parameters of the multiple environmental parameter sets to obtain the first abnormal ratio and the second abnormal ratio, where the pearl oyster anomaly classifier and the pearl anomaly classifier include multiple abnormal classification paths corresponding to the multiple categories of environmental parameters.

[0056] Furthermore, step S200 of the present invention further includes:

[0057] S210: Divide the multiple environmental parameter sets according to the multiple categories of environmental parameters to obtain a water temperature set, a salinity set, and a dissolved oxygen set.

[0058] Specifically, the multiple sets of environmental parameters are divided according to the multiple categories of environmental parameters (water temperature, salinity, and dissolved oxygen), that is, the water temperature data, salinity data, and dissolved oxygen data at each collection location are grouped into one category, obtaining a water temperature set, a salinity set, and a dissolved oxygen set.

[0059] S220: Input the water temperature set, salinity set, and dissolved oxygen set into the pearl oyster abnormality classifier respectively to conduct abnormal environmental parameter classification, obtaining a first water temperature abnormality ratio, a first salinity abnormality ratio, and a first dissolved oxygen abnormality ratio, and calculating to obtain a first abnormality ratio, where the pearl oyster abnormality classifier is constructed based on the normal environmental parameters of pearl oyster growth within a historical time, including a first water temperature abnormal classification path, a first salinity abnormal classification path, and a first dissolved oxygen abnormal classification path.

[0060] Furthermore, step S220 of the present invention further includes:

[0061] S221: Obtain the normal growth environmental parameters of pearl oysters within a preset historical time range and divide them into a normal water temperature set, a normal salinity set, and a normal dissolved oxygen set; S222: Respectively use the normal water temperature set, normal salinity set, and normal dissolved oxygen set to construct binary classification nodes, obtaining a first water temperature division node set, a first salinity division node set, and a first dissolved oxygen division node set, and constructing a first water temperature abnormal classification path, a first salinity abnormal classification path, and a first dissolved oxygen abnormal classification path; S223: Input the water temperature set, salinity set, and dissolved oxygen set into the first water temperature abnormal classification path, first salinity abnormal classification path, and first dissolved oxygen abnormal classification path respectively for division, and screen the ratios of the divided single water temperature parameter, single salinity parameter, and single dissolved oxygen parameter to obtain a first water temperature abnormality ratio, a first salinity abnormality ratio, and a first dissolved oxygen abnormality ratio; S224: Calculate the mean value of the first water temperature abnormality ratio, first salinity abnormality ratio, and first dissolved oxygen abnormality ratio to obtain a first abnormality ratio.

[0062] Specifically, first, collect the normal growth environment data of pearl oysters within a preset historical time range (such as the past day, week, or month, etc.). That is, set a normal environmental range that conforms to the actual aquaculture scenario and the growth requirements of pearl oysters. For example, the normal water temperature range for pearl oysters is 20 to 28 °C, and this temperature range is considered the most suitable for the growth of pearl oysters; the normal salinity range for pearl oysters is generally 15‰ to 30‰, and salinity fluctuations will directly affect the adaptability and growth rate of shellfish; the normal dissolved oxygen range is 4 to 8 mg / L, and the concentration of dissolved oxygen is crucial for the physiological activities of shellfish. Then, divide the normal growth environment data within the historical time range to obtain a normal water temperature set, a normal salinity set, and a normal dissolved oxygen set. Among them, the normal water temperature set refers to all environmental data that meet the water temperature conditions (20 °C to 28 °C) within the historical time range and will be divided into the normal water temperature set; the normal salinity set contains all salinity data within the range of 15‰ to 30‰ within the historical time range; the normal dissolved oxygen set refers to all environmental data with a dissolved oxygen concentration within the range of 4 to 8 mg / L within the historical time range.

[0063] Next, use the normal water temperature set, the normal salinity set, and the normal dissolved oxygen set to construct binary classification nodes respectively. The binary classification node is a threshold point that divides the environmental parameter data into two categories. Set a boundary according to the normal environmental parameter data, and then judge whether the parameter exceeds the normal range to obtain the first water temperature division node set, the first salinity division node set, and the first dissolved oxygen division node set. Further, construct the first water temperature anomaly classification path according to the first water temperature division node set. This path determines whether the water temperature is abnormal through a series of judgment conditions, and further classifies the abnormal water temperature into different levels. For example, at node 1, if the water temperature is less than 20 °C, it is directly judged as abnormal water temperature and enters the "too low water temperature" anomaly category; at node 2, if the water temperature is between 20 °C and 28 °C, it is determined as normal water temperature and no further classification is required, and the classification path ends; at node 3, if the water temperature is greater than 28 °C, it is judged as abnormal water temperature and enters the "too high water temperature" anomaly category. By constructing the first water temperature anomaly classification path, it is possible to quickly judge whether the water temperature data is within the normal range each time it is collected. On the other hand, using the same method, construct the first salinity anomaly classification path according to the first salinity division node set, and construct the first dissolved oxygen anomaly classification path according to the first dissolved oxygen division node set.

[0064] Then, input the water temperature set into the first water temperature anomaly classification path for partitioning, that is, use the Isolation Forest algorithm or other classification methods for binary classification (such as less than 20 °C and greater than or equal to 20 °C). According to the input water temperature data, judge whether it deviates from the normal range. When using the Isolation Forest algorithm to classify the environmental parameter set, isolated data points (i.e., outliers) will be identified as isolated single data points, while normal data will be grouped into relatively dense clusters. That is, the Isolation Forest discovers outliers by randomly partitioning the data feature space and "isolating" data points, obtaining the proportion of a single water temperature parameter. That is, through the Isolation Forest algorithm, identify the single water temperature data points (such as the abnormal water temperature of 19 °C) determined to be abnormal in the water temperature set, calculate the proportion of these abnormal data points, which is the proportion of a single water temperature parameter (the ratio of abnormal water temperature data to the total amount of water temperature data), and set the proportion of the single water temperature parameter as the first water temperature anomaly proportion. Among them, the first water temperature anomaly proportion represents the proportion of water temperature abnormal data in all water temperature data.

[0065] On the other hand, input the salinity set into the first salinity anomaly classification path for partitioning, use the Isolation Forest algorithm to identify abnormal data, obtain the proportion of a single salinity parameter (the ratio of abnormal salinity data to the total amount of salinity data), and set the proportion of the single salinity parameter as the first salinity anomaly proportion, which represents the proportion of salinity abnormal data in all salinity data. Input the dissolved oxygen set into the first dissolved oxygen anomaly classification path for partitioning, obtain the proportion of a single dissolved oxygen parameter (the ratio of abnormal dissolved oxygen data to the total amount of dissolved oxygen data), and set the proportion of the single dissolved oxygen parameter as the first dissolved oxygen anomaly proportion, which represents the proportion of dissolved oxygen abnormal data in all dissolved oxygen data.

[0066] In addition, the above scheme only describes a method for calculating the first water temperature anomaly proportion, the first salinity anomaly proportion, and the first dissolved oxygen anomaly proportion. Those skilled in the art can also select other appropriate methods for calculating the anomaly proportion according to the actual situation. For example, set the normal water temperature range of pearl oysters to 20 to 28 °C, the normal salinity range to 15‰ to 30‰, and the normal dissolved oxygen range to 4 to 8 mg / L; then judge the water temperature set, salinity set, and dissolved oxygen set according to the normal water temperature range, normal salinity range, and normal dissolved oxygen range, set the environmental parameters not within the range as abnormal parameters (such as the water temperature of 19.5 °C is an abnormal water temperature), count the proportion of abnormal parameters (the ratio of the number of abnormal parameters to the total number of parameters), and obtain the abnormal proportion of environmental parameters. For example, if the number of abnormal water temperature data is 10 times and the number of water temperature data in the water temperature set is 100 times, then the first water temperature anomaly proportion is 10 / 100 = 10%.

[0067] Further, calculate the mean values of the first water temperature anomaly ratio, the first salinity anomaly ratio, and the first dissolved oxygen anomaly ratio, and set the result of the mean value calculation as the first anomaly ratio. Among them, the first anomaly ratio reflects the overall anomaly situation of environmental parameters such as water temperature, salinity, and dissolved oxygen in the growth environment of pearl oysters.

[0068] S230: Construct a pearl anomaly classifier based on the normal environmental parameters of pearl cultivation within a historical time. Among them, the pearl anomaly classifier includes a second water temperature anomaly classification path, a second salinity anomaly classification path, and a second dissolved oxygen anomaly classification path; S240: Input the water temperature set, salinity set, and dissolved oxygen set into the second water temperature anomaly classification path, the second salinity anomaly classification path, and the second dissolved oxygen anomaly classification path respectively for classifying abnormal environmental parameters, and obtain the second water temperature anomaly ratio, the second salinity anomaly ratio, and the second dissolved oxygen anomaly ratio, and calculate to obtain the second anomaly ratio.

[0069] Specifically, based on the same method of constructing the above pearl oyster anomaly classifier (including the first water temperature anomaly classification path, the first salinity anomaly classification path, and the first dissolved oxygen anomaly classification path), obtain the second normal water temperature set, the second normal salinity set, and the second normal dissolved oxygen set according to the normal environmental parameters of pearl cultivation within a historical time; then use the second normal water temperature set, the second normal salinity set, and the second normal dissolved oxygen set to construct binary classification nodes to obtain the second water temperature anomaly classification path, the second salinity anomaly classification path, and the second dissolved oxygen anomaly classification path. Finally, input the water temperature set, salinity set, and dissolved oxygen set into the second water temperature anomaly classification path, the second salinity anomaly classification path, and the second dissolved oxygen anomaly classification path respectively for classifying abnormal environmental parameters, and obtain the second water temperature anomaly ratio, the second salinity anomaly ratio, and the second dissolved oxygen anomaly ratio; then calculate the mean values of the second water temperature anomaly ratio, the second salinity anomaly ratio, and the second dissolved oxygen anomaly ratio, and set the result of the mean value calculation as the second anomaly ratio. The second anomaly ratio reflects the overall anomaly situation of environmental parameters such as water temperature, salinity, and dissolved oxygen in the growth environment of pearls.

[0070] S300: Modify according to the first anomaly ratio and the second anomaly ratio to obtain the third anomaly ratio, configure the scale of identifying environmental anomalies of pearl oysters and the scale of identifying environmental anomalies of pearls, and respectively perform environmental parameter anomaly identification on multiple environmental parameter sets to obtain the environmental anomaly level of pearl oysters and the environmental anomaly level of pearls.

[0071] Furthermore, step S300 of the present invention further includes:

[0072] S310: Use the sum of 1 and the first anomaly ratio as a correction factor, multiply it by the second anomaly ratio to obtain the third anomaly ratio; S320: Obtain the maximum anomaly recognition scale, where the maximum anomaly recognition scale includes the maximum integrated anomaly recognition quantity; S330: Respectively multiply the first anomaly ratio and the third anomaly ratio by the maximum integrated anomaly recognition quantity and round to obtain the integrated pearl oyster anomaly recognition quantity and the integrated pearl anomaly recognition quantity, which are used as the pearl oyster environmental anomaly recognition scale and the pearl environmental anomaly recognition scale.

[0073] Specifically, during the growth process of pearl oysters, the growth environment of pearl oysters (such as water temperature, salinity, and dissolved oxygen, etc.) has a significant impact on the uniformity and quality of pearls. If the growth environment of pearl oysters undergoes abnormal changes, the pearl formation process may also be affected, resulting in uneven texture or decreased quality of pearls. First, add 1 and the first anomaly ratio, and use the sum as the correction factor. That is, in order to comprehensively consider the interaction between the growth environment of pearl oysters and the quality of pearls, it is necessary to correct the second anomaly ratio. This correction factor reflects the degree of environmental anomaly of pearl oysters. If the anomaly ratio of the growth environment of pearl oysters is relatively large, the correction factor will increase accordingly, thereby amplifying the anomaly impact of pearls. Then multiply the correction factor by the second anomaly ratio, and use the product as the third anomaly ratio. By introducing the correction factor, it is possible to effectively comprehensively consider the impact of the growth environment of pearl oysters on the quality of pearls and improve the accuracy of environmental monitoring.

[0074] Obtain the maximum anomaly recognition scale, where the maximum anomaly recognition scale includes the maximum integrated anomaly recognition quantity. That is, in order to ensure the efficiency and accuracy of environmental anomaly detection, a maximum anomaly recognition scale is set, which is the maximum number of anomalies that can be processed simultaneously. The maximum integrated anomaly recognition quantity can be determined based on various factors such as historical data, laboratory capacity, and computing resources. For example, set the maximum integrated anomaly recognition quantity to 10. Further multiply the first anomaly ratio by the maximum integrated anomaly recognition quantity and round to obtain the integrated pearl oyster anomaly recognition quantity, which is used as the pearl oyster environmental anomaly recognition scale; multiply the third anomaly ratio by the maximum integrated anomaly recognition quantity and round to obtain the integrated pearl anomaly recognition quantity, which is used as the pearl environmental anomaly recognition scale.

[0075] By setting the appropriate anomaly recognition quantity according to the anomaly ratio, it is possible to improve the fitness of the anomaly recognition quantity to the actual anomaly state, thereby improving the accuracy of anomaly recognition, avoiding over - calculation or under - calculation, and further improving the analysis efficiency and resource utilization rate, ensuring that the monitoring system can efficiently and accurately identify anomalies under different environmental conditions.

[0076] S340: Based on the maximum integrated anomaly recognition quantity, construct a pearl oyster environmental anomaly recognizer including multiple first environmental anomaly recognition branches and a pearl environmental anomaly recognizer including multiple second environmental anomaly recognition branches by means of ensemble learning.

[0077] Furthermore, step S340 of the present invention further includes:

[0078] S341: According to the historical growth environment data of pearl oysters and pearls, collect multiple sets of sample environmental parameters, respectively perform pearl oyster environmental anomaly level identification and pearl environmental anomaly level identification, and obtain a sample pearl oyster environmental anomaly level set and a sample pearl environmental anomaly level set; S342: According to the maximum integrated anomaly recognition quantity, divide the multiple sets of sample environmental parameters, the sample pearl oyster environmental anomaly level set and the sample pearl environmental anomaly level set to obtain multiple portions of input data, multiple portions of first output data and multiple portions of second output data; S343: Use the multiple portions of input data to respectively combine the multiple portions of first output data and multiple portions of second output data to train multiple first environmental anomaly recognition branches and multiple second environmental anomaly recognition branches; S344: Combine the multiple first environmental anomaly recognition branches and multiple second environmental anomaly recognition branches respectively to obtain a pearl oyster environmental anomaly recognizer and a pearl environmental anomaly recognizer.

[0079] Specifically, according to the historical growth environment data of pearl oysters and pearls, collect multiple sets of sample environmental parameters, and then identify the pearl oyster environmental anomaly levels and pearl environmental anomaly levels under different sets of sample environmental parameters. For example, for the environmental data of each sample, identify it as a normal, mildly abnormal, moderately abnormal or severely abnormal level according to the detection results, and these levels reflect the health status and stability of the pearl oyster growth environment; through anomaly detection, identify the quality anomaly levels of pearls, and these anomaly levels reflect the impact of the environment on pearl quality, so as to obtain a sample pearl oyster environmental anomaly level set and a sample pearl environmental anomaly level set.

[0080] Then, according to the maximum integrated anomaly recognition quantity (for example, 10), divide the multiple sets of sample environmental parameters, the sample pearl oyster environmental anomaly level set and the sample pearl environmental anomaly level set. Use the set of sample environmental parameters as the input data, set the sample pearl oyster environmental anomaly levels as the first output data, and set the sample pearl environmental anomaly levels as the second output data to obtain multiple portions of input data, multiple portions of first output data and multiple portions of second output data. Among them, each portion of input data includes several sets of sample environmental parameters, each portion of first output data includes several sample pearl oyster environmental anomaly levels, and each portion of second output data includes several sample pearl environmental anomaly levels.

[0081] Construct the first environmental anomaly recognition branch and the second environmental anomaly recognition branch based on the BP neural network. The first environmental anomaly recognition branch and the second environmental anomaly recognition branch are BP neural network models in machine learning that can be iteratively optimized. The first environmental anomaly recognition branch includes an input layer, multiple hidden layers, and an output layer. The input data of its input layer is the sample environmental parameter set, and the output data of the output layer is the sample pearl oyster environmental anomaly level. The second environmental anomaly recognition branch also includes an input layer, multiple hidden layers, and an output layer. The input data of its input layer is the sample environmental parameter set, and the output data of the output layer is the sample pearl environmental anomaly level.

[0082] Further, use the multiple input data to combine the multiple first output data to perform supervised training on multiple first environmental anomaly recognition branches. For example, use the first input data combination (several sample environmental parameter sets) and the first first input data (several sample pearl oyster environmental anomaly levels) to perform supervised training on the first environmental anomaly recognition branch. First, pair the input data with the target output through a training algorithm, and calculate the error between each input data and the target output (such as using the cross-entropy loss function or the mean squared error). Then use an optimization algorithm (such as the gradient descent method) to minimize the error. During the training process, the model will adjust its parameters according to different combinations of input features, thereby improving the prediction accuracy. Perform iterative training. In each round, the model will adjust the weights and parameters according to the error feedback until the error converges to a smaller value (such as less than the expected error index), indicating that the model has learned the relationship between the input features and the anomaly level, and obtain the first environmental anomaly recognition branch that has completed training. On the other hand, use the multiple input data to combine the multiple second output data to perform supervised training on multiple second environmental anomaly recognition branches. Among them, the training method of the second environmental anomaly recognition branch is the same as the training method of the above first environmental anomaly recognition branch, and will not be elaborated here.

[0083] Finally, combine the multiple first environmental anomaly recognition branches to construct a pearl oyster environmental anomaly recognizer, and combine the multiple second environmental anomaly recognition branches to construct a pearl environmental anomaly recognizer.

[0084] S350: Input the multiple environmental parameter sets into the first environmental anomaly recognition branches of the integrated anomaly recognition quantity of pearl oysters and the second environmental anomaly recognition branches of the integrated anomaly recognition quantity of pearls respectively, and output to obtain multiple pearl oyster environmental anomaly level sets and multiple pearl environmental anomaly level sets, and calculate the mean values respectively to obtain the pearl oyster environmental anomaly level and the pearl environmental anomaly level.

[0085] Specifically, according to the number of integrated abnormal identifications of the pearl oyster, a first environmental abnormal identification branch is randomly called in the environmental abnormal identifier of the pearl oyster. For example, assuming that the environmental abnormal identifier of the pearl oyster includes 10 first environmental abnormal identification branches and the number of integrated abnormal identifications of the pearl oyster is 3, then any 3 first environmental abnormal identification branches are randomly selected from the 10 first environmental abnormal identification branches. Then, the multiple sets of environmental parameters are input into the first environmental abnormal identification branches corresponding to the number of integrated abnormal identifications of the pearl oyster to obtain multiple sets of pearl oyster environmental abnormal level sets; then, the average value of the multiple sets of pearl oyster environmental abnormal level sets is calculated to obtain the pearl oyster environmental abnormal level. On the other hand, the multiple sets of environmental parameters are input into the second environmental abnormal identification branches corresponding to the number of integrated abnormal identifications of the pearl to obtain multiple sets of pearl environmental abnormal level sets, and the average value of the multiple sets of pearl environmental abnormal level sets is calculated to obtain the pearl environmental abnormal level.

[0086] S400: According to the first abnormal ratio and the third abnormal ratio, perform weighted calculation on the pearl oyster environmental abnormal level and the pearl environmental abnormal level to obtain the growth environment abnormal level, which is used as the monitoring result of the growth environment of the pearl oyster.

[0087] Furthermore, step S400 of the present invention further includes:

[0088] S410: Configure the pearl oyster weight and the pearl weight according to the first abnormal ratio and the third abnormal ratio; S420: Use the pearl oyster weight and the pearl weight to perform weighted calculation on the pearl oyster environmental abnormal level and the pearl environmental abnormal level to obtain the growth environment abnormal level, which is used as the monitoring result of the growth environment of the pearl oyster.

[0089] Specifically, first, according to the first abnormal ratio and the third abnormal ratio, configure the pearl oyster weight and the pearl weight. Among them, the first abnormal ratio represents the degree of abnormality of the growth environment of the pearl oyster. The larger this ratio is, the more abnormal the growth environment of the pearl oyster is, and the more significant the impact on the growth of the pearl oyster is. Therefore, its weight should be appropriately increased. The pearl oyster weight can be set as a certain proportional coefficient of the first abnormal ratio, or the first abnormal ratio can be directly used as the weight; the third abnormal ratio represents the degree of influence of the environmental abnormality on the pearl quality. The pearl weight can be set as a certain proportional coefficient of the third abnormal ratio, or the third abnormal ratio can be directly used as the weight; thus, the pearl oyster weight and the pearl weight are obtained.

[0090] Finally, use the pearl oyster weight and the pearl weight to perform weighted calculation on the pearl oyster environmental abnormal level and the pearl environmental abnormal level, set the weighted calculation result as the growth environment abnormal level, and use the growth environment abnormal level as the monitoring result of the growth environment of the pearl oyster.

[0091] A method for monitoring the growth environment of pearl oysters provided by an embodiment of the present invention has at least the following technical effects:

[0092] 1. Through comprehensive analysis of multi-dimensional environmental parameters and analysis of the interactive effects between the growth environment of pearl oysters and pearl quality, the accuracy and reliability of monitoring the growth environment of pearl oysters can be significantly improved, and the health status of pearl oysters and the changes in pearl quality can be reflected more comprehensively and accurately, thereby providing a more scientific and refined environmental regulation basis for pearl quality control.

[0093] 2. By setting an appropriate number of abnormal identifications according to the abnormal ratio, the adaptability of the number of abnormal identifications to the actual abnormal state can be improved, thereby improving the accuracy of abnormal identification, avoiding over-computation or under-computation, and further improving the analysis efficiency and resource utilization rate, ensuring that the monitoring system can efficiently and accurately identify abnormalities under different environmental conditions.

[0094] Embodiment 2, as Figure 2 shown, based on the same inventive concept as the method for monitoring the growth environment of pearl oysters provided in Embodiment 1, an embodiment of the present invention further provides a monitoring system for the growth environment of pearl oysters, including:

[0095] An environmental parameter monitoring module 01, configured to monitor and collect environmental parameters of multiple categories of environmental parameter categories during the growth process of pearl oysters, and obtain multiple environmental parameter sets, wherein the multiple categories of environmental parameter categories include water temperature, salinity, and dissolved oxygen; an abnormal environmental parameter classification module 02, configured to respectively use a pearl oyster abnormal classifier and a pearl abnormal classifier to classify abnormal environmental parameters of the multiple environmental parameter sets, and obtain a first abnormal ratio and a second abnormal ratio, wherein the pearl oyster abnormal classifier and the pearl abnormal classifier include multiple abnormal classification paths corresponding to the multiple categories of environmental parameter categories; an environmental parameter abnormal identification module 03, configured to correct and obtain a third abnormal ratio according to the first abnormal ratio and the second abnormal ratio, configure the scale of pearl oyster environmental abnormal identification and the scale of pearl environmental abnormal identification, and respectively perform environmental parameter abnormal identification on the multiple environmental parameter sets to obtain the pearl oyster environmental abnormal level and the pearl environmental abnormal level; an environmental monitoring result obtaining module 04, configured to perform weighted calculation on the pearl oyster environmental abnormal level and the pearl environmental abnormal level according to the first abnormal ratio and the third abnormal ratio, and obtain the growth environment abnormal level as the monitoring result of the growth environment of pearl oysters.

[0096] Further, the monitoring system for the growth environment of pearl oysters further includes: during the growth process of pearl oysters, collect an environmental parameter set at a first position in the growth environment according to multiple categories of environmental parameter categories, wherein the multiple categories of environmental parameter categories include water temperature, salinity, and dissolved oxygen; continue to collect environmental parameter sets at multiple positions to obtain multiple environmental parameter sets.

[0097] Furthermore, the pearl oyster growth environment monitoring system further includes: dividing the multiple environmental parameter sets according to the multiple categories of environmental parameters to obtain a water temperature set, a salinity set, and a dissolved oxygen set; inputting the water temperature set, the salinity set, and the dissolved oxygen set into a pearl oyster anomaly classifier respectively to conduct anomaly environmental parameter classification, obtaining a first water temperature anomaly ratio, a first salinity anomaly ratio, and a first dissolved oxygen anomaly ratio, and calculating to obtain a first anomaly ratio, wherein the pearl oyster anomaly classifier is constructed based on the normal environmental parameters of pearl oysters during the historical time, and includes a first water temperature anomaly classification path, a first salinity anomaly classification path, and a first dissolved oxygen anomaly classification path; constructing a pearl anomaly classifier according to the normal environmental parameters of pearl cultivation during the historical time, wherein the pearl anomaly classifier includes a second water temperature anomaly classification path, a second salinity anomaly classification path, and a second dissolved oxygen anomaly classification path; inputting the water temperature set, the salinity set, and the dissolved oxygen set into the second water temperature anomaly classification path, the second salinity anomaly classification path, and the second dissolved oxygen anomaly classification path respectively to conduct anomaly environmental parameter classification, obtaining a second water temperature anomaly ratio, a second salinity anomaly ratio, and a second dissolved oxygen anomaly ratio, and calculating to obtain a second anomaly ratio.

[0098] Furthermore, the pearl oyster growth environment monitoring system further includes: obtaining the normal growth environmental parameters of pearl oysters within a preset historical time range and dividing them into a normal water temperature set, a normal salinity set, and a normal dissolved oxygen set; respectively using the normal water temperature set, the normal salinity set, and the normal dissolved oxygen set to construct binary classification nodes, obtaining a first water temperature division node set, a first salinity division node set, and a first dissolved oxygen division node set, and constructing a first water temperature anomaly classification path, a first salinity anomaly classification path, and a first dissolved oxygen anomaly classification path; inputting the water temperature set, the salinity set, and the dissolved oxygen set into the first water temperature anomaly classification path, the first salinity anomaly classification path, and the first dissolved oxygen anomaly classification path respectively for division, screening the ratios of the divided single water temperature parameters, single salinity parameters, and single dissolved oxygen parameters, obtaining a first water temperature anomaly ratio, a first salinity anomaly ratio, and a first dissolved oxygen anomaly ratio; calculating the mean values of the first water temperature anomaly ratio, the first salinity anomaly ratio, and the first dissolved oxygen anomaly ratio to obtain a first anomaly ratio.

[0099] Further, the pearl oyster growth environment monitoring system further includes: using the sum of 1 and the first anomaly ratio as a correction factor, multiplying the correction factor by the second anomaly ratio to obtain a third anomaly ratio; obtaining a maximum anomaly recognition scale, where the maximum anomaly recognition scale includes a maximum integrated anomaly recognition quantity; respectively multiplying the first anomaly ratio and the third anomaly ratio by the maximum integrated anomaly recognition quantity and taking the integer to obtain the integrated anomaly recognition quantity of pearl oysters and the integrated anomaly recognition quantity of pearls, which are used as the environment anomaly recognition scale of pearl oysters and the environment anomaly recognition scale of pearls; based on the maximum integrated anomaly recognition quantity, constructing a pearl oyster environment anomaly recognizer including multiple first environment anomaly recognition branches and a pearl environment anomaly recognizer including multiple second environment anomaly recognition branches through ensemble learning; respectively inputting the multiple sets of environmental parameters into the first environment anomaly recognition branches corresponding to the integrated anomaly recognition quantity of pearl oysters and the second environment anomaly recognition branches corresponding to the integrated anomaly recognition quantity of pearls, and outputting to obtain multiple sets of pearl oyster environment anomaly levels and multiple sets of pearl environment anomaly levels, and respectively calculating the mean values to obtain the pearl oyster environment anomaly level and the pearl environment anomaly level.

[0100] Further, the pearl oyster growth environment monitoring system further includes: according to the historical growth environment data of pearl oysters and pearls, collecting multiple sets of sample environmental parameters, respectively performing pearl oyster environment anomaly level identification and pearl environment anomaly level identification to obtain a set of sample pearl oyster environment anomaly levels and a set of sample pearl environment anomaly levels; dividing the multiple sets of sample environmental parameters, the set of sample pearl oyster environment anomaly levels, and the set of sample pearl environment anomaly levels according to the maximum integrated anomaly recognition quantity to obtain multiple sets of input data, multiple sets of first output data, and multiple sets of second output data; using the multiple sets of input data to respectively combine the multiple sets of first output data and the multiple sets of second output data to train multiple first environment anomaly recognition branches and multiple second environment anomaly recognition branches; respectively combining the multiple first environment anomaly recognition branches and the multiple second environment anomaly recognition branches to obtain a pearl oyster environment anomaly recognizer and a pearl environment anomaly recognizer.

[0101] Further, the pearl oyster growth environment monitoring system further includes: configuring a pearl oyster weight and a pearl weight according to the first anomaly ratio and the third anomaly ratio; using the pearl oyster weight and the pearl weight to perform weighted calculation on the pearl oyster environment anomaly level and the pearl environment anomaly level to obtain a growth environment anomaly level, which is used as the monitoring result of the pearl oyster growth environment.

[0102] Example 3, please refer to Figure 3 , Figure 3 which is a schematic diagram of an embodiment of the electronic device provided by the embodiment of the present invention. As Figure 3As shown in the figure, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a first computer program 511 stored on the memory 510 and executable on the processor 520. When the processor 520 executes the first computer program 511, the following steps are implemented: During the growth process of pearl oysters, monitor and collect environmental parameters of multiple environmental parameter categories to obtain multiple environmental parameter sets, where the multiple environmental parameter categories include water temperature, salinity, and dissolved oxygen; respectively use a pearl oyster anomaly classifier and a pearl anomaly classifier to classify the abnormal environmental parameters of the multiple environmental parameter sets to obtain a first anomaly ratio and a second anomaly ratio, where the pearl oyster anomaly classifier and the pearl anomaly classifier include multiple anomaly classification paths corresponding to the multiple environmental parameter categories; according to the first anomaly ratio and the second anomaly ratio, correct and obtain a third anomaly ratio, configure the pearl oyster environmental anomaly recognition scale and the pearl environmental anomaly recognition scale, respectively perform environmental parameter anomaly recognition on the multiple environmental parameter sets to obtain a pearl oyster environmental anomaly level and a pearl environmental anomaly level; according to the first anomaly ratio and the third anomaly ratio, perform weighted calculation on the pearl oyster environmental anomaly level and the pearl environmental anomaly level to obtain a growth environment anomaly level as the monitoring result of the growth environment of pearl oysters.

[0103] Embodiment 4, please refer to Figure 4 , Figure 4 which is a schematic diagram of an embodiment of a computer-readable storage medium provided by an embodiment of the present invention. As Figure 4 shown, this embodiment provides a computer-readable storage medium 600, on which a second computer program 611 is stored. When the second computer program 611 is executed by a processor, the following steps are implemented: During the growth process of pearl oysters, monitor and collect environmental parameters of multiple environmental parameter categories to obtain multiple environmental parameter sets, where the multiple environmental parameter categories include water temperature, salinity, and dissolved oxygen; respectively use a pearl oyster anomaly classifier and a pearl anomaly classifier to classify the abnormal environmental parameters of the multiple environmental parameter sets to obtain a first anomaly ratio and a second anomaly ratio, where the pearl oyster anomaly classifier and the pearl anomaly classifier include multiple anomaly classification paths corresponding to the multiple environmental parameter categories; according to the first anomaly ratio and the second anomaly ratio, correct and obtain a third anomaly ratio, configure the pearl oyster environmental anomaly recognition scale and the pearl environmental anomaly recognition scale, respectively perform environmental parameter anomaly recognition on the multiple environmental parameter sets to obtain a pearl oyster environmental anomaly level and a pearl environmental anomaly level; according to the first anomaly ratio and the third anomaly ratio, perform weighted calculation on the pearl oyster environmental anomaly level and the pearl environmental anomaly level to obtain a growth environment anomaly level as the monitoring result of the growth environment of pearl oysters.

[0104] It should be noted that in the above embodiments, the descriptions of the various embodiments have their respective emphases. For parts not described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0105] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0106] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0107] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device realizes the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0108] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for realizing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0109] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic inventive concept.

[0110] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the present invention and its equivalent technologies, the present invention also intends to include these changes and modifications.

Claims

1. A method for monitoring the growth environment of pearl oysters, characterized in that the method include: During the growth of pearl oysters, monitoring and collecting environmental parameters of multiple environmental parameter categories to obtain multiple environmental parameter sets, wherein the multiple environmental parameter categories include water temperature, salinity and dissolved oxygen; Using a pearl oyster anomaly classifier and a pearl anomaly classifier respectively, classifying the multiple environmental parameter sets into abnormal environmental parameter categories to obtain a first anomaly ratio and a second anomaly ratio, wherein the pearl oyster anomaly classifier and the pearl anomaly classifier include multiple anomaly classification paths corresponding to the multiple environmental parameter categories; According to the first abnormal ratio and the second abnormal ratio, a third abnormal ratio is corrected and obtained, a pearl oyster environment abnormality identification scale and a pearl environment abnormality identification scale are configured, and environmental parameter abnormality identification is performed on multiple environmental parameter sets respectively to obtain a pearl oyster environment abnormality level and a pearl environment abnormality level; The pearl oyster environment abnormality level and the pearl environment abnormality level are weightedly calculated according to the first abnormality ratio and the third abnormality ratio to obtain the growth environment abnormality level as the pearl oyster growth environment monitoring result.

2. A method for monitoring the growth environment of pearl oysters according to claim 1, characterized in that: During the growth of pearl oysters, multiple environmental parameter categories are monitored and collected to obtain multiple environmental parameter sets, including: During the growth of pearl oysters, collecting a set of environmental parameters at a first location in the growth environment according to multiple environmental parameter categories, wherein the multiple environmental parameter categories include water temperature, salinity, and dissolved oxygen; Continue to collect and obtain environmental parameter sets at multiple locations to obtain multiple environmental parameter sets.

3. A method for monitoring the growth environment of pearl oysters according to claim 1, characterized in that: Using a pearl oyster abnormality classifier and a pearl abnormality classifier respectively to classify the multiple environmental parameter sets into abnormal environmental parameters, and obtaining a first abnormality ratio and a second abnormality ratio, including: Dividing the multiple environmental parameter sets according to the multiple environmental parameter categories to obtain a water temperature set, a salinity set and a dissolved oxygen set; The water temperature set, salinity set and dissolved oxygen set are respectively input into the pearl oyster anomaly classifier to classify the abnormal environmental parameters, obtain the first water temperature anomaly ratio, the first salinity anomaly ratio and the first dissolved oxygen anomaly ratio, and calculate the first anomaly ratio, wherein the pearl oyster anomaly classifier is constructed according to the normal environmental parameters of the pearl oyster growth in the historical time, including the first water temperature anomaly classification path, the first salinity anomaly classification path and the first dissolved oxygen anomaly classification path; According to normal environmental parameters of pearl cultivation in historical time, a pearl anomaly classifier is constructed, wherein the pearl anomaly classifier includes a second water temperature anomaly classification path, a second salinity anomaly classification path, and a second dissolved oxygen anomaly classification path; The water temperature set, salinity set and dissolved oxygen set are respectively input into the second water temperature anomaly classification path, the second salinity anomaly classification path and the second dissolved oxygen anomaly classification path, to classify the abnormal environmental parameters, to obtain the second water temperature anomaly ratio, the second salinity anomaly ratio and the second dissolved oxygen anomaly ratio, and to calculate the second anomaly ratio.

4. A method for monitoring the growth environment of pearl oysters according to claim 3, characterized in that: The water temperature set, salinity set and dissolved oxygen set are respectively input into the pearl oyster anomaly classifier to classify the abnormal environmental parameters, obtain the first water temperature anomaly ratio, the first salinity anomaly ratio and the first dissolved oxygen anomaly ratio, and calculate the first anomaly ratio, including: Obtain normal growth environment parameters of pearl oysters within a preset historical time range, and divide them into a normal water temperature set, a normal salinity set, and a normal dissolved oxygen set; The normal water temperature set, the normal salinity set and the normal dissolved oxygen set are respectively used to construct binary classification nodes, obtain a first water temperature partition node set, a first salinity partition node set and a first dissolved oxygen partition node set, and construct a first water temperature abnormal classification path, a first salinity abnormal classification path and a first dissolved oxygen abnormal classification path; Inputting the water temperature set, salinity set and dissolved oxygen set into the first water temperature anomaly classification path, the first salinity anomaly classification path and the first dissolved oxygen anomaly classification path respectively for classification, screening and classifying into proportions of a single water temperature parameter, a single salinity parameter and a single dissolved oxygen parameter, and obtaining a first water temperature anomaly proportion, a first salinity anomaly proportion and a first dissolved oxygen anomaly proportion; The average of the first water temperature abnormality ratio, the first salinity abnormality ratio and the first dissolved oxygen abnormality ratio is calculated to obtain a first abnormality ratio.

5. A method for monitoring the growth environment of pearl oysters according to claim 1, characterized in that: According to the first abnormal ratio and the second abnormal ratio, the third abnormal ratio is corrected and obtained, the pearl oyster environment abnormality identification scale and the pearl environment abnormality identification scale are configured, and the environmental parameter abnormality identification is performed on multiple environmental parameter sets respectively to obtain the pearl oyster environment abnormality level and the pearl environment abnormality level, including: Using the sum of 1 and the first abnormal ratio as a correction coefficient, multiplying the second abnormal ratio by the sum, to obtain a third abnormal ratio; Obtaining a maximum anomaly recognition scale, wherein the maximum anomaly recognition scale includes a maximum number of integrated anomaly recognitions; The first abnormality ratio and the third abnormality ratio are respectively multiplied by the maximum integrated abnormality identification number and rounded to obtain the integrated abnormality identification number of pearl oysters and the integrated abnormality identification number of pearls as the environmental abnormality identification scale of pearl oysters and the environmental abnormality identification scale of pearls; According to the maximum number of integrated anomaly identification, based on integrated learning, a pearl oyster environment anomaly identifier including a plurality of first environment anomaly identification branches and a pearl environment anomaly identifier including a plurality of second environment anomaly identification branches are constructed; The multiple environmental parameter sets are respectively input into the first environmental anomaly identification branch of the pearl oyster integrated anomaly identification quantity and the second environmental anomaly identification branch of the pearl integrated anomaly identification quantity, and multiple pearl oyster environmental anomaly level sets and multiple pearl environmental anomaly level sets are output, and the averages are calculated to obtain the pearl oyster environmental anomaly level and the pearl environmental anomaly level.

6. A method for monitoring the growth environment of pearl oysters according to claim 5, characterized in that: According to the maximum number of integrated anomaly identification, based on integrated learning, a pearl oyster environment anomaly identifier including a plurality of first environment anomaly identification branches and a pearl environment anomaly identifier including a plurality of second environment anomaly identification branches are constructed, including: According to the historical growth environment data of pearl oysters and pearls, a plurality of sample environmental parameter sets are collected, and the abnormal grade of the pearl oyster environment and the abnormal grade of the pearl environment are marked respectively, so as to obtain a sample pearl oyster environmental abnormal grade set and a sample pearl environmental abnormal grade set; According to the maximum integrated anomaly identification quantity, the multiple sample environmental parameter sets, the sample pearl oyster environmental anomaly level sets and the sample pearl environmental anomaly level sets are divided to obtain multiple input data, multiple first output data and multiple second output data; Using the multiple copies of input data, respectively combining the multiple copies of first output data and the multiple copies of second output data, and training multiple first environment anomaly recognition branches and multiple second environment anomaly recognition branches; The plurality of first environmental anomaly identification branches and the plurality of second environmental anomaly identification branches are respectively combined to obtain a pearl oyster environmental anomaly identifier and a pearl environmental anomaly identifier.

7. A method for monitoring the growth environment of pearl oysters according to claim 1, characterized in that: According to the first abnormal ratio and the third abnormal ratio, weighted calculation is performed on the abnormal grade of the pearl oyster environment and the abnormal grade of the pearl environment to obtain the abnormal grade of the growth environment as the monitoring result of the pearl oyster growth environment, including: According to the first abnormal proportion and the third abnormal proportion, configuring the pearl oyster weight and the pearl weight; The pearl oyster weight and the pearl weight are used to perform weighted calculation on the pearl oyster environment abnormality level and the pearl environment abnormality level to obtain the growth environment abnormality level as the pearl oyster growth environment monitoring result.

8. A pearl oyster growth environment monitoring system, characterized in that: The steps for implementing the method for monitoring the growth environment of pearl oysters as claimed in any one of claims 1 to 7 include: An environmental parameter monitoring module is used to monitor and collect environmental parameters of multiple environmental parameter categories during the growth of pearl oysters to obtain multiple environmental parameter sets, wherein the multiple environmental parameter categories include water temperature, salinity and dissolved oxygen; An abnormal environmental parameter classification module is used to classify the multiple environmental parameter sets using a pearl oyster abnormality classifier and a pearl abnormality classifier, respectively, to obtain a first abnormality ratio and a second abnormality ratio, wherein the pearl oyster abnormality classifier and the pearl abnormality classifier include multiple abnormal classification paths corresponding to the multiple environmental parameter categories; An environmental parameter anomaly identification module is used to correct and obtain a third anomaly ratio according to the first anomaly ratio and the second anomaly ratio, configure a pearl oyster environment anomaly identification scale and a pearl environment anomaly identification scale, perform environmental parameter anomaly identification on multiple environmental parameter sets respectively, and obtain a pearl oyster environment anomaly level and a pearl environment anomaly level; The environmental monitoring result obtaining module is used to perform weighted calculation on the pearl oyster environment abnormality level and the pearl environment abnormality level according to the first abnormality ratio and the third abnormality ratio, and obtain the growth environment abnormality level as the pearl oyster growth environment monitoring result.

9. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the steps of a method for monitoring the growth environment of pearl oysters as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, which, when executed by a processor, implements the steps of a method for monitoring the growth environment of pearl oysters as described in any one of claims 1 to 7.

Images