A method and device for real-time monitoring and control of water temperature in artificially bred Hirudo medicinalis

Abstract

This invention provides a method and device for real-time monitoring and control of water temperature in artificially cultured leeches, relating to the field of leech culture technology. The invention involves randomly selecting leech samples to obtain data such as weight, length, width, and growth stage, and combining this data with environmental data from the culture pond, such as water temperature, pH value, and dissolved oxygen concentration, to establish a growth rate prediction model. The health status of the samples is comprehensively assessed using the analytic hierarchy process (AHP) to determine whether water temperature control is necessary. If health indicators are below a preset threshold, water temperature is controlled to optimize the culture environment. The invention also includes analysis of the controlled environmental data and the health indicators of the leeches to generate a comprehensive health index, further evaluating the health status of the controlled leech samples to assess the control effect. Finally, the health status of the culture pond is determined based on the comprehensive health index. If the number of unhealthy samples exceeds one-quarter, the culture pond is marked as abnormal, and water temperature is continuously monitored and controlled.

Description

Technical Field

[0001] This invention relates to the field of Hirudo medicinalis farming technology, specifically to a method and device for real-time monitoring and control of water temperature in artificially farmed Hirudo medicinalis. Background Technology

[0002] The artificial breeding of Hirudo nipponia has attracted increasing attention in recent years, mainly due to its wide application in medicine, ecological restoration, and water management. Hirudo nipponia possesses significant economic value and biological characteristics, effectively purifying water and reducing water pollution, while also showing promising prospects in drug development. However, the growth and reproduction of Hirudo nipponia are significantly affected by environmental factors such as water temperature, pH, and dissolved oxygen. Maintaining a suitable breeding environment is crucial for improving its growth efficiency. Water temperature, as a critical factor affecting Hirudo nipponia growth, must be monitored and controlled in real time. Traditional breeding management methods often rely on experience, making precise environmental control difficult. With technological advancements, utilizing sensors and data analysis techniques for real-time monitoring and intelligent adjustment of the breeding environment has become a new trend in improving breeding efficiency and biological health. By establishing a scientific water temperature monitoring system, not only can environmental changes be detected promptly, but breeding parameters can also be adjusted according to growth conditions, thus ensuring the sustainable development of Hirudo nipponia.

[0003] The existing technology has the following shortcomings:

[0004] In modern aquaculture, effectively assessing and monitoring the health status of farmed organisms is a pressing technical problem. Traditional health assessment methods often rely on visual observation or single indicators, which are not only highly subjective but also fail to comprehensively reflect the true health status of organisms in complex environments. With the expansion of aquaculture scale and the diversification of environmental factors, single indicators cannot meet the needs of comprehensive assessment of organism health. Therefore, a systematic health indicator system is urgently needed to identify and address potential problems in the aquaculture process in a timely manner.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to provide a method and device for real-time monitoring and control of water temperature in artificially bred Hirudo medicinalis, so as to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] A method for real-time monitoring and control of water temperature in artificially cultured Hirudo medicinalis, comprising the following steps:

[0009] Step 1: Randomly select multiple samples of leeches in the leech breeding pond, and obtain the weight, body length, body width, growth images and growth stages of the leeches at the current and previous collection times, as well as the environmental data in the leech breeding pond. Determine the growth rate of the leeches at the previous collection times based on their weight.

[0010] Step 2: Construct a growth rate prediction model with inputs of body weight, growth stage, and environmental data, and output of growth rate. Train the model based on data collected at previous times, and obtain the growth rate of the sample leeches at the current time based on the trained model.

[0011] Step 3: Analyze the growth rate, body length, and body width of the sample leeches at the current moment using the analytic hierarchy process (AHP) to comprehensively assess the health status of the leeches in the breeding pond at the current moment, and determine whether to adjust the temperature based on the health status.

[0012] Step 4: Based on the regulated temperature, obtain the regulated growth rate and health status of the sample leeches, and generate a comprehensive health index based on the regulated environmental data and health status to determine the regulated effect.

[0013] Furthermore, determining the growth rate of the sample *Hirudo medicinalis* specifically includes:

[0014] The growth stages of *Hirudo nipponia* are divided into juvenile, adult, and senile stages. The body width data refers to the width of the abdomen, and the body length data refers to the length from head to tail. Based on the body weight data of *Hirudo nipponia* samples from the breeding pond at the current and previous collection times, the growth rate of each sample was calculated using the following formula:

[0015] ;

[0016] in, For the i-th sample of Hirudo medicinalis Growth rate at any given time For the i-th sample of Hirudo medicinalis Weight at any given time For the i-th sample of Hirudo medicinalis Weight at any given time Let be the time interval between time t+1 and time t. This is the index for the time.

[0017] Furthermore, constructing the growth rate prediction model specifically includes:

[0018] The environmental data includes the temperature, pH value, and dissolved oxygen concentration of the water in the leech breeding pond. Temperature sensors, pH sensors, and dissolved oxygen sensors are arranged around and in the center of the breeding pond to collect the temperature, pH value, and dissolved oxygen concentration data of the water in the surrounding and center locations of the leech breeding pond. The average value is calculated and defined as the temperature, pH value, and dissolved oxygen concentration data of the water in the leech breeding pond.

[0019] After pre-treating the temperature, pH and dissolved oxygen concentration of the culture pond at multiple time points, the Pearson correlation coefficient between each environmental variable and the growth rate was calculated. Environmental variables with an absolute value of Pearson correlation coefficient greater than 0.5 were selected as strongly correlated environmental variables. The pre-treatment included removing outliers, filling missing values ​​and maximum-minimum normalization.

[0020] The weight, growth stage, and pre-processed strongly correlated environmental variables of the sample leeches were used as inputs, and the growth rate of the sample leeches was used as the label. Data from previous collection times were divided into training and testing sets. The weight, growth stage, and pre-processed strongly correlated environmental variables of the sample leeches in the training set were input, and the growth rate of the corresponding sample leeches was used as the label to train the growth rate prediction model. The data in the testing set were input into the trained model for testing.

[0021] Furthermore, a comprehensive assessment of the current health status of the sampled leeches specifically includes:

[0022] Collect environmental data of the water in the breeding pond of Hirudo nipponia at the current moment, input the environmental data into the trained growth rate prediction model, predict the growth rate of the Hirudo nipponia sample at the current moment, and then measure the body length and body width of the Hirudo nipponia sample at the current moment.

[0023] The growth rate, body length, and body width of the sample leeches were set as evaluation indicators. A scoring method was set, and the relative importance of each evaluation indicator was determined by expert scoring. A judgment matrix was constructed based on the expert scores, and the eigenvalues ​​and eigenvectors of the judgment matrix were calculated. Consistency was tested by calculating the consistency index and consistency ratio. If the consistency ratio was less than 0.1, the judgment matrix was considered consistent. The health index of the sample leeches at the current moment was then calculated to evaluate the health status of the sample leeches. If the consistency ratio was equal to or greater than 0.1, the judgment matrix was readjusted.

[0024] The health status of the leech is assessed by calculating its current health indicators. The formula is as follows:

[0025] ;

[0026] in, Let represent the health indicators of the i-th sample leech at the current moment. The growth rate prediction model outputs the growth rate of the i-th *Hirudo nipponia* at the current moment. These are the body length and width of the i-th sample leech at the current time. These represent the baseline growth rate, baseline body length, and baseline body width of the i-th sample leech at the current time, representing its growth stage. These are the weight coefficients of the corresponding terms, i.e., the values ​​of the first, second, and third terms in the eigenvectors involved in the analytic hierarchy process.

[0027] Furthermore, determining whether to adjust the temperature specifically includes:

[0028] Calculate the mean of the health indicators of the sample leeches at the current moment, and compare the mean with the preset health threshold. If the mean of the health indicators of the sample leeches at the current moment is higher than the health threshold, it indicates that the current environment has a promoting effect on the growth of leeches. If the mean of the health indicators of the sample leeches at the current moment is lower than the health threshold, it indicates that the current environment has an inhibitory effect on the growth of leeches. Then monitor the temperature data of the water in the breeding pond and regulate it.

[0029] The current temperature data in the leech farming pond is compared with the optimal temperature value to calculate the heat required for the temperature change within the system. The calculation formula is as follows:

[0030] ;in, The heat required for temperature changes within the system. For the quality of the water in the aquaculture pond, Let T be the specific heat capacity of the water in the aquaculture pond, and T be the current temperature of the water in the aquaculture pond. This represents the optimal temperature for the water in the aquaculture pond.

[0031] The formula for calculating the power required to calculate the change in heat is:

[0032] ;

[0033] in, The power required for the change in heat. Preset adjustment duration;

[0034] If the current water temperature in the aquaculture pond is higher than the optimal temperature, the calculated power value will be matched with the output power of the corresponding cooling equipment. If the current water temperature in the aquaculture pond is lower than the optimal temperature, the calculated power value will be matched with the output power of the corresponding heating equipment.

[0035] Furthermore, the analysis of the environmental data after regulation specifically includes:

[0036] Environmental data of the *Hirudo medicinalis* (horsehair) breeding ponds after regulation were obtained, and the regulated environmental data were analyzed to obtain the environmental impact index. The calculation formula is as follows:

[0037] ;

[0038] Where Ej is the environmental impact index corresponding to the j-th growth stage. Let be the comprehensive scoring function for the j-th growth stage, x be the environmental data index, and x = T, pH, DO, where T is the current temperature of the aquaculture pond water, pH is the current acidity / alkalinity of the aquaculture pond water, DO is the current dissolved oxygen concentration of the aquaculture pond water, a, b, and c are the weight coefficients of the corresponding items, and j is the growth stage index, j = 1, 2, 3, that is, E1, E2, and E3 correspond to the juvenile leech stage, adult leech stage, and old age stage, respectively.

[0039] ;

[0040] in, This represents the optimal value of the environmental data corresponding to the j-th growth stage. Let x be the comprehensive score coefficient for the xth environmental data item. Further, generating the comprehensive health index specifically includes:

[0041] The body weight data of the regulated sample of *Hirudo nipponia* was obtained. This body weight data, along with the corresponding growth stage of the leeches, was input into a growth rate prediction model. The growth rate of the regulated leeches was then obtained from the model's output. Combined with the growth rate, body length, and body width data of the regulated leeches, health indicators were obtained. Based on these health indicators and environmental data, the overall health status of the leeches at the current moment was analyzed using the following formula:

[0042] ;

[0043] in, This represents the comprehensive health index of the i-th sample of *Hirudo medicinalis* after the current regulation. The health indicators of the i-th sample of leeches after the current regulation are as follows: This represents the environmental impact index of the i-th sample of *Hirudo medicinalis* after regulation. ∈(E1, E2, E3), These are the weight coefficients for the corresponding items;

[0044] The overall health index of the sample leeches at the current moment is compared with a preset health threshold. If the overall health index of the sample leeches at the current moment is higher than the preset health threshold, the sample leeches are considered to be in a healthy state. If the overall health index of the sample leeches at the current moment is lower than the health threshold, the sample leeches are considered to be in an unhealthy state. The number of healthy and unhealthy sample leeches in each breeding pond is counted. If the number of unhealthy sample leeches in a breeding pond exceeds one-quarter of the total number of sample leeches in that breeding pond, the breeding pond is marked as an abnormal state, and the water temperature in the breeding pond in the abnormal state is monitored and adjusted.

[0045] The present invention also provides a real-time water temperature monitoring and control device for artificially bred leeches. This device is used to implement the above-mentioned real-time water temperature monitoring and control method for artificially bred leeches, comprising:

[0046] The data acquisition module is used to randomly select multiple samples of Hirudo nipponia from the Hirudo nipponia breeding pond, and obtain the weight, body length, body width, growth images and growth stages of the sample Hirudo nipponia at the current and previous collection times, as well as the environmental data in the Hirudo nipponia breeding pond, and determine the growth rate of the sample Hirudo nipponia at the previous collection times based on the weight.

[0047] The model building module is used to build a growth rate prediction model that takes weight, growth stage and environmental data as input and outputs growth rate. The model is trained based on data collected at previous times and the growth rate of the sample leeches is obtained based on the trained model at the current time.

[0048] The temperature control module is used to analyze the growth rate, body length and body width of the sample leeches at the current moment based on the analytic hierarchy process, so as to comprehensively assess the health status of the sample leeches in the breeding pond at the current moment, and determine whether to control the temperature based on the health status.

[0049] The comprehensive evaluation module is used to obtain the post-regulation growth rate and health status of the sample leeches based on the regulated temperature, and to generate a comprehensive health index based on the regulated environmental data and health status to determine the regulation effect.

[0050] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0051] The real-time water temperature monitoring and control method of this invention, by introducing automated monitoring and intelligent analysis, can promptly capture environmental changes and dynamically adjust the water temperature, thereby effectively addressing problems such as slow biological growth, increased disease incidence, and even economic losses caused by unsuitable environments. By comprehensively monitoring growth rate, body length, body width, and environmental data, a scientifically sound health assessment system is constructed. This method can reflect the health status of Hirudo medicinalis in real time, enabling farmers to quickly identify potential problems and take timely measures, thereby effectively reducing growth retardation and mortality caused by unsuitable environments.

[0052] Furthermore, this method incorporates advanced linear regression technology to monitor the growth rate of *Hirudo medicinalis* in the rearing ponds using a data-driven approach, thereby monitoring their health. By dynamically adjusting water temperature and other environmental factors, it not only improves the growth efficiency of *Hirudo medicinalis* but also enhances the sustainability of the rearing process. Overall, this method provides an efficient and intelligent management solution for the artificial rearing of *Hirudo medicinalis*, with significant economic and ecological benefits. Attached Figure Description

[0053] Figure 1 This is a schematic diagram of the overall method flow of the present invention;

[0054] Figure 2 This is a schematic diagram of the device structure of the present invention. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0056] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly. Example

[0057] Please see Figure 1 The present invention provides a technical solution:

[0058] A method for real-time monitoring and control of water temperature in artificially cultured Hirudo medicinalis, comprising the following steps:

[0059] Step 1: Randomly select multiple samples of leeches in the leech breeding pond, and obtain the weight, body length, body width, growth images and growth stages of the leeches at the current and previous collection times, as well as the environmental data in the leech breeding pond. Determine the growth rate of the leeches at the previous collection times based on their weight.

[0060] In this embodiment, determining the growth rate of the sample leech specifically includes:

[0061] The growth stages of *Hirudo nipponia* are divided into juvenile, adult, and senile stages. The body width data refers to the width of the abdomen, and the body length data refers to the length from head to tail. Based on the body weight data of *Hirudo nipponia* samples from the breeding pond at the current and previous collection times, the growth rate of each sample was calculated using the following formula: ;in, Let be the growth rate of the i-th sample of *Hirudo medicinalis* at time t. Let be the weight of the i-th sample leech at time t. Let be the weight of the i-th sample leech at time t+1. This represents the time interval between time t+1 and time t, where t is the index of the time.

[0062] By randomly selecting and collecting data from multiple samples of *Hirudo nipponia*, more comprehensive and accurate growth data can be obtained. This multi-sample design reduces the impact of individual differences on the results and improves the accuracy of growth rate calculation. Collecting body weight data at continuous time points allows for real-time monitoring of *Hirudo nipponia* growth changes. This dynamic analysis helps farmers better understand the growth patterns of *Hirudo nipponia*, providing data support for subsequent farming management. Dividing the growth stages of *Hirudo nipponia* into juvenile, adult, and senescent stages allows farmers to take corresponding management measures for different growth stages. The growth rate of *Hirudo nipponia* at different growth stages will certainly be different, providing reliable data for subsequently building a growth rate prediction model. The growth rate calculation formula is based on the biological concept of growth rate, which is usually defined as the change in body weight of an organism per unit time. The formula reflects the relationship between body weight change and time interval, conforming to the basic laws of biological growth. and Let represent the body weight of the i-th sample of *Hirudo medicinalis* at times t+1 and t, respectively. By calculating the difference in body weight between these two times, the growth change of the sample during this period can be directly quantified. By dividing *Hirudo medicinalis* into different growth stages (juvenile, adult, and senescent), the growth rate of different stages can be monitored in more detail. This segmentation method makes the application of the formula more reasonable and allows for management tailored to the needs of different growth stages.

[0063] Step 2: Construct a growth rate prediction model with inputs of body weight, growth stage, and environmental data, and output of growth rate. Train the model based on data collected at previous times, and obtain the growth rate of the sample leeches at the current time based on the trained model.

[0064] In this embodiment, constructing the growth rate prediction model specifically includes:

[0065] The environmental data includes the temperature, pH value, and dissolved oxygen concentration of the water in the leech breeding pond. Temperature sensors, pH sensors, and dissolved oxygen sensors are arranged around and in the center of the breeding pond to collect the temperature, pH value, and dissolved oxygen concentration data of the water in the surrounding and center locations of the leech breeding pond. The average value is calculated and defined as the temperature, pH value, and dissolved oxygen concentration data of the water in the leech breeding pond.

[0066] After pretreatment of the temperature, pH, and dissolved oxygen concentration of the culture pond at multiple consecutive time points, the Pearson correlation coefficients between each environmental variable and the growth rate were calculated, as shown in the following formula:

[0067] ;

[0068] in, r The Pearson correlation coefficient is used. X Let Y be the environmental variable and Y be the growth rate. These represent the mean values ​​of environmental variables and growth rate over the given time period;

[0069] Environmental variables with an absolute value of Pearson correlation coefficient greater than 0.5 were selected as strongly correlated environmental variables;

[0070] Preprocessing includes outlier removal, missing value imputation, and max-min normalization. The Z-score for each data point is calculated, and the absolute value of the Z-score is determined. When a value is missing, it is considered an outlier and removed. The value is then replaced by the average of the data from the previous and next time points. The same method is used to fill in missing values.

[0071] The weight, growth stage, and pre-processed strongly correlated environmental variables of the sample leeches were used as inputs, and the growth rate of the sample leeches was used as the label. Data from previous collection times were divided into training and test sets. The weight, growth stage, and pre-processed strongly correlated environmental variables of the sample leeches in the training set were input, and the growth rate of the corresponding sample leeches was used as the label. A growth rate prediction model was constructed based on a linear model and trained. The data in the test set were then input into the trained model for testing.

[0072] The parameters in the model were estimated using the body weight, growth stage, and pre-treated strongly correlated environmental variables of the *Hirudo medicinalis* samples in the test set, as well as the corresponding growth rate of the *Hirudo medicinalis* samples. Minimizing the mean squared error was chosen as the objective function, expressed as:

[0073] Where MSE is the mean squared error and N is the total sample size. Let be the growth rate of the i-th sample leech at time t. For the i-th sample leech predicted by the model t Growth rate at each moment;

[0074] The performance of the trained linear model is then evaluated using the test set, with the coefficient of determination used as the evaluation index. The formula is as follows:

[0075] ;

[0076] in, As the coefficient of determination, This represents the mean growth rate of the sample of Hirudo nipponia.

[0077] By arranging temperature, pH, and dissolved oxygen sensors around and in the center of the rearing pond, environmental changes in the water body can be monitored comprehensively and in real time. This layout ensures data representativeness, eliminates biases that may arise from data from a single location, and makes the environmental data more accurate. Preprocessing steps (such as outlier removal, missing value imputation, and max-min normalization) ensure data quality and consistency, providing a reliable foundation for subsequent analysis and avoiding analytical errors caused by data quality issues. Calculating the Pearson correlation coefficient between environmental variables and growth rate effectively identifies environmental variables that are significantly related to growth rate. Selecting correlation variables with absolute values ​​greater than 0.5 as strongly correlated variables helps to focus on the factors that have the greatest impact on growth, improving the relevance of the analysis. In addition, a linear regression model is chosen to describe the relationship between the body length, body width, and environmental data of the sample *Hirudo medicinalis* and its growth rate. This method is simple and easy to interpret, and the linear model can effectively capture the linear effect of input data on growth rate.

[0078] Linear models (such as linear regression) provide clear explanations of causal relationships. For example, a model can directly explain the impact of each unit change in body weight or growth stage on growth rate. This transparency allows researchers and breeders to intuitively understand the relationships between variables. Linear models typically require only a small number of parameters to estimate, and with limited data or features, simple models can effectively avoid overfitting. Furthermore, linear models are relatively simple, train quickly, and are suitable for rapid construction and debugging. This efficiency is crucial for real-time systems or scenarios requiring rapid feedback. Input data includes the body weight and growth stage (e.g., juvenile, adult, and mature leeches) of the sample leeches. These variables are potential factors affecting growth rate. Body weight reflects the rate of growth, while growth stage is used to eliminate differences in growth rate among leeches at different growth stages. Larger body weight may indicate stronger growth capacity and is a direct measure of the change in leech growth rate; leeches at different growth stages also show significant differences in growth rate, and different growth stages and environmental data also significantly affect their physiological activities and metabolic efficiency.

[0079] Step 3: Analyze the growth rate, body length, and body width of the sample leeches at the current moment using the analytic hierarchy process (AHP) to comprehensively assess the health status of the leeches in the breeding pond at the current moment, and determine whether to adjust the temperature based on the health status.

[0080] In this embodiment, the comprehensive assessment of the current health status of the sample leeches specifically includes:

[0081] Collect environmental data of the water in the breeding pond of Hirudo nipponia at the current moment, input the environmental data into the trained growth rate prediction model, predict the growth rate of the Hirudo nipponia sample at the current moment, and then measure the body length and body width of the Hirudo nipponia sample at the current moment.

[0082] The growth rate, body length, and body width of the sample leeches were set as evaluation indicators. A scoring method was set, specifically using a scale of 1-5 to score the relative importance of the two indicators. 1 indicates that the two indicators are equally important, 3 indicates that the two indicators are important, 5 indicates that the two indicators are extremely important, and 2 and 4 are values ​​between the two. The relative importance of each evaluation indicator was determined by an expert scoring method, which can be carried out through questionnaires or meetings.

[0083] Construct a judgment matrix based on expert ratings. For example, suppose the expert rating results are as follows:

[0084] ;

[0085] Where A is the judgment matrix, and the importance score in the x-th row and y-th column is represented as... , The matrix represents the importance score of indicator x relative to indicator y. Each row of the matrix represents the growth rate, body length, and body width of a certain leech, and each column represents the growth rate, body length, and body width of a certain leech.

[0086] For example, if experts believe that indicator A1 is more important than indicator A2, then... Therefore, we can conclude that For example, the importance relationship between growth rate and body length is 3, that is... Therefore, the importance of body length relative to growth rate is... , A value greater than 1 indicates that index i is more important. The reciprocal of the value indicates that the index y is relatively unimportant. The eigenvalues ​​and eigenvectors of the judgment matrix are calculated using the following formula:

[0087] ;in, To determine the eigenvalues ​​of a matrix, To determine the eigenvectors of a matrix, the eigenvectors are... Each element represents the weight of each indicator;

[0088] Consistency is verified by calculating the consistency index and the consistency ratio. The formula for calculating the consistency index is as follows:

[0089] ;

[0090] CI stands for Consistency Index. To determine the largest eigenvalue of a matrix, n is the dimension of the matrix;

[0091] The formula for calculating the consistency ratio is:

[0092] ;

[0093] Wherein, CR is the consistency ratio and RI is the random consistency index, which are obtained by looking up a table according to the matrix dimensions;

[0094] If the consistency ratio is less than 0.1, the judgment matrix is ​​considered consistent, and the comprehensive score of each evaluation indicator is calculated to assess the health status of the leeches. If the consistency ratio is equal to or greater than 0.1, the judgment matrix is ​​analyzed, and the eigenvectors are normalized to obtain the normalized weight vector, represented as follows: Based on the weight vector and the judgment matrix, the consistency matrix is ​​calculated using the following formula:

[0095] ;

[0096] Where C is the consistency matrix, It determines the element in the x-th row and y-th column of a matrix. and It is the corresponding element in the weight vector;

[0097] Calculate the consistency deviation matrix to represent the deviation of each rating from the ideal consistency. The calculation formula is as follows:

[0098] ;

[0099] in, Indicates rating The greater the deviation from the ideal consistency, the more likely the rating is to be disputed;

[0100] Therefore, calculate the average deviation of each row or column in the consistency deviation matrix, find the row or column with the largest average deviation, and then find the largest element in that row or column. The corresponding rating The score with the largest discrepancy is considered the largest score. Adjustments should be made to this score. This can be done by having experts re-evaluate the item, or by averaging the scores for that row or column, replacing the largest discrepancy score. When calculating the average score, this largest discrepancy score must be excluded. or The diagonal elements;

[0101] When choosing to replace the score with the largest difference using either the row average score or the column average score, first determine the number of scores with the largest difference in the row and column containing the score with the largest difference. If the number of scores with the largest difference in the row containing the score with the largest difference is greater than the number of scores with the largest difference in the column containing the score with the largest difference, then the column average score is used for replacement; otherwise, the row average score is used for replacement. If the number of scores with the largest difference in the row and column containing the score with the largest difference is the same, then either the row average score or the column average score can be used for replacement.

[0102] The Analytic Hierarchy Process (AHP) breaks down complex problems into multiple levels and indicators, enabling decision-makers to clearly identify the relationships and relative importance of various evaluation indicators. This systematic approach effectively integrates multiple aspects such as the growth rate, body length, and body width of *Hirudo medicinalis* into a comprehensive evaluation framework. AHP combines quantitative scoring with expert qualitative judgment. Using a 1-5 rating scale, experts can score the importance of each evaluation indicator based on their experience and expertise. This method quantifies subjective judgment, reduces the impact of uncertainty in the decision-making process, and thus makes the evaluation results more reliable and actionable.

[0103] The health status of the leech is assessed by calculating its current health indicators. The formula is as follows:

[0104] ;

[0105] in, Let represent the health indicators of the i-th sample leech at the current moment. The growth rate prediction model outputs the growth rate of the i-th *Hirudo nipponia* at the current moment. These are the body length and width of the i-th sample leech at the current time. These represent the baseline growth rate, baseline body length, and baseline body width of the i-th sample leech at the current time, representing its growth stage. These are the weight coefficients of the corresponding terms, i.e., the values ​​of the first, second, and third terms in the eigenvectors involved in the analytic hierarchy process.

[0106] Health indicators are a comprehensive assessment value that provides a quantitative evaluation of health status by combining multiple factors such as growth rate, body length, and body width. High health indicators generally indicate good health and growth, while low indicators may suggest health problems. Growth rate is usually positively correlated with health status. Healthy leeches have a faster growth rate, reflecting their good nutrient absorption and metabolic capacity. Body length and width are important indicators of individual growth and health. Generally, healthy individuals exhibit larger body length and width. These independent variables are interrelated and collectively influence health status. For example, a good growth rate usually indicates sufficient nutrient supply, which in turn promotes an increase in body length and width. Simultaneously, increased body length and width also indicate good growth status, reflecting a level of health. When growth rate increases, health indicators also increase, indicating better health. Similarly, when body length or width increases, health indicators also improve, indicating a better individual health status. Growth rate, body length, and body width are all positively correlated with health indicators. The growth rate, body length, and body width of samples of *Hirudo nipponia* (a type of leech) at different growth stages vary. Comparing the current growth rate, body length, and body width of a sample of *Hirudo nipponia* with the baseline growth rate, baseline body length, and baseline body width for the same growth stage provides a better reflection of the current health status of the sample and eliminates errors caused by significant data differences due to different growth stages. The baseline growth rate, baseline body length, and baseline body width can be obtained by analyzing historical data of healthy *Hirudo nipponia*, using the average of relevant data for each growth stage as the corresponding baseline value.

[0107] In this embodiment, determining whether to adjust the temperature specifically includes:

[0108] Calculate the mean of the health indicators of the sample leeches at the current moment, and compare the mean with the preset health threshold. If the mean of the health indicators of the sample leeches at the current moment is higher than the health threshold, it indicates that the current environment has a promoting effect on the growth of leeches. If the mean of the health indicators of the sample leeches at the current moment is lower than the health threshold, it indicates that the current environment has an inhibitory effect on the growth of leeches. Then monitor the temperature data of the water in the breeding pond and regulate it.

[0109] The current temperature data in the leech farming pond is compared with the optimal temperature value to calculate the heat required for the temperature change within the system. The calculation formula is as follows:

[0110] ;in, The heat required for temperature changes within the system. Let be the mass of the water in the aquaculture pond, be the specific heat capacity of the water in the aquaculture pond, and be the current temperature of the water in the aquaculture pond. This represents the optimal temperature for the water in the aquaculture pond.

[0111] The formula for calculating the power required to calculate the change in heat is: ;

[0112] in, The power required for the change in heat. Preset adjustment duration;

[0113] If the current water temperature in the aquaculture pond is higher than the optimal temperature, the calculated power value will be matched with the output power of the corresponding cooling equipment. If the current water temperature in the aquaculture pond is lower than the optimal temperature, the calculated power value will be matched with the output power of the corresponding heating equipment.

[0114] By comparing the current health indicators of the *Hirudo nipponia* samples with preset health thresholds, the impact of the growth environment on the *Hirudo nipponia* can be quickly determined. This real-time monitoring can promptly identify potential temperature risks to the normal growth of the *Hirudo nipponia* samples, allowing for timely intervention. By observing the temperature data of the water in the breeding pond and adjusting it according to changes in health indicators, precise environmental management can be achieved, promoting the healthy growth of the *Hirudo nipponia* samples. Appropriate temperature adjustments are made for different health states to maximize growth efficiency. Formulas are used to calculate the heat and power required for temperature changes within the system, making the adjustment process more scientific and precise. Calculations based on the water's mass and specific heat capacity ensure the rational use of energy required for heating or cooling, avoiding resource waste. Furthermore, through real-time monitoring and dynamic adjustment, a rapid response to water temperature changes is possible; whether the temperature rises or falls, appropriate measures can be taken promptly to help maintain the water temperature within the optimal range.

[0115] Step 4: Obtain the regulated growth rate and regulated health status of the sample Poecilobdella manillensis based on the regulated temperature, and generate a comprehensive health index based on the regulated environmental data and health status to judge the regulation effect;

[0116] In this embodiment, the analysis of the regulated environmental data specifically includes:

[0117] Obtain the environmental data of the Poecilobdella manillensis breeding pond after regulation, and analyze the regulated environmental data to obtain an environmental impact index. The calculation formula is:

[0118] ;

[0119] ;

[0120] ;

[0121] Among them, E1 is the environmental impact index in the juvenile leech stage, E2 is the environmental impact index in the adult leech stage, E3 is the environmental impact index in the old leech stage, is the comprehensive scoring function in the juvenile leech stage, is the comprehensive scoring function in the adult leech stage, is the comprehensive scoring function in the old leech stage, x is the environmental data index, and x = T, pH, DO, T is the temperature of the water body in the current breeding pond, pH is the acidity and alkalinity of the water body in the current breeding pond, DO is the dissolved oxygen concentration of the water body in the current breeding pond, a, b, c are the weight coefficients of the corresponding items, 0 < b < c < a < 1, and a + b + c = 1;

[0122] The environmental impact index comprehensively evaluates the overall impact of the temperature, pH value and dissolved oxygen concentration of the water body in the breeding pond on the growth of Poecilobdella manillensis. This index reflects the comprehensive suitability of the current environmental conditions for the health and growth of Poecilobdella manillensis. By calculating the environmental impact index, breeders can quickly understand the impact of the environment on organisms and make timely regulation measures, which helps to optimize the breeding environment, improve the growth environment and reduce losses caused by environmental discomfort. The impact of environmental data on Poecilobdella manillensis at different growth stages is also different, and the suitable values of water temperature, pH and dissolved oxygen concentration for Poecilobdella manillensis at different growth stages are also different. Therefore, it is reasonable to analyze the impact of environmental data on Poecilobdella manillensis at different growth stages separately.

[0123] Temperature, pH, and dissolved oxygen concentration are three key environmental factors affecting the growth of *Hirudo medicinalis*, and they are interconnected. For example, temperature affects the dissolved oxygen content in water, while pH may affect the efficiency of oxygen utilization by organisms. Therefore, these three independent variables jointly influence the environmental impact index, which in turn affects the growth of *Hirudo medicinalis*. The environmental impact index is a weighted sum of scores for temperature, pH, and dissolved oxygen. Appropriate temperature, pH, and dissolved oxygen concentrations will result in a more favorable scoring function. , , A higher environmental value leads to an increase in the value of E, indicating that a suitable environment promotes the growth of Hirudo nipponia. If any environmental indicator fails to meet the standard, the corresponding score will decrease, affecting the value of E and causing it to drop, reflecting the unsuitability of the environment.

[0124] Temperature is a key factor in the growth of aquatic organisms. Water temperature directly affects the metabolic rate, respiration, and growth rate of organisms. In the cultivation of most aquatic organisms, temperature changes have a significant impact on their growth and health; therefore, the weight 'a' is usually set to the maximum value. Dissolved oxygen is a basic element required for the respiration of aquatic organisms, especially during growth and reproduction; sufficient dissolved oxygen is crucial for aquatic organisms. Oxygen deficiency can lead to suffocation and reduced growth rate. Therefore, the weight 'c' is generally set relatively high, but slightly lower than the weight of temperature, because temperature changes indirectly affect dissolved oxygen levels. Although pH is also an important factor affecting organism growth, its influence is usually smaller compared to the direct effects of temperature and dissolved oxygen. The pH value of the water body affects many biochemical reactions and the availability of nutrients, but the suitable pH range is generally wide. Therefore, its weight 'b' is usually set to the minimum value. The constraint a+b+c=1 ensures that the environmental impact index is a normalized indicator, guaranteeing that the total contribution of the weighted combination of multiple factors is 100%.

[0125] The formula for calculating the comprehensive score function for various environmental data is as follows:

[0126] ;

[0127] in, This is a comprehensive temperature scoring function. This represents the optimal temperature for the water in the aquaculture pond. This is the overall scoring coefficient for temperature data, with a value range of [0.1, 1]. The larger the value, the more sensitive the scoring function is to temperature changes. In other words, the change in the scoring function will be more obvious when the temperature is close to the optimal value. Therefore, a relatively high value can be set in this range to reflect the greater influence of temperature.

[0128] This scoring function quantifies the deviation of the current water temperature from the optimal water temperature. Its value ranges from 0 to 1, with higher values ​​indicating that the water temperature is closer to the optimal state and suitable for growth. Through this comprehensive temperature scoring function, the impact of water temperature on leeches can be quantitatively assessed, helping breeders quickly identify the suitability of temperature for growth and adjust the water temperature in a timely manner. The scoring function is calculated based on the difference between the current temperature and the optimal temperature. As T moves... Approaching, rating Temperature increases and decreases. Changes in temperature directly affect the score, and thus the environmental impact index. The relationship with T is positive; that is, the closer the current temperature T is to the optimal temperature... The higher the score, the better; if T deviates... The score decreased, indicating the negative impact of temperature on the growth of Hirudo nipponia.

[0129] During the larval stage, the optimal temperature value If set to 29℃, then the corresponding This represents a comprehensive temperature score function for the juvenile leech stage; for the adult leech stage, it represents the optimal temperature value. If set to 26℃, then the corresponding The temperature comprehensive score function represents the leech stage, and in the old age stage, it represents the optimal temperature value. If set to 24℃, then the corresponding The temperature score function represents the overall temperature range in old age. Young leeches have a relatively high metabolic rate; suitable higher temperatures promote their growth and development, accelerate the conversion of food into energy, and support rapid growth. At this stage, young leeches have a weaker ability to adapt to temperature; higher temperatures help enhance their physiological activity, improve immunity, and promote healthy growth. Adult leeches experience a slower growth rate; suitable temperatures maintain their physiological activities while preventing excessive energy consumption due to excessively high temperatures, ensuring healthy development. The physiological needs of adult leeches tend to stabilize; lower temperatures can maintain their physiological functions and reduce stress caused by changes in the external environment. The metabolic rate of aged leeches further decreases; suitable lower temperatures help slow metabolism, avoiding excessive energy consumption and stress responses. As the physiological functions of elderly individuals gradually decline, suitable low temperatures can help reduce physiological burden, lower metabolic rate, and help extend their lifespan.

[0130] ;

[0131] in, For pH comprehensive scoring function, The optimal acid-base value, This is the comprehensive scoring coefficient for pH data, with a value range of [0.1, 0.5]. Changes in pH generally have a smaller impact on organisms compared to temperature and dissolved oxygen. The value is usually lower than and smaller The value can provide a smooth response curve, so that when the pH is close to the optimal value, the score does not change too drastically. This is suitable in actual breeding management because pH adjustment usually takes a certain amount of time and has a wide suitable range.

[0132] This scoring function assesses the difference between the current pH level and the optimal pH level of the water, reflecting the suitability of the water quality for the growth of *Hirudo medicinalis*. Through this function, farmers can promptly understand the suitability of the water's pH level and make corresponding adjustments to ensure the environment promotes the growth of *Hirudo medicinalis*. The scoring function reflects the relationship between the current pH and the optimal value. If the current pH level is close to the optimal value, the score... A higher value indicates a higher environmental impact index (E), while a lower value indicates a lower value, directly affecting the environmental impact index (E). The relationship with pH is positively correlated, meaning the closer the pH is to the optimum, the better. The higher the pH, the lower the score; if the pH deviates from the optimal value, the lower the score, indicating that the effect of pH on the growth of Hirudo nipponia becomes negative.

[0133] During the larval stage, the optimal pH value Setting it to 7 corresponds to The pH score function represents the overall pH value during the juvenile leech stage; in the adult leech stage, the optimal pH value is determined. Setting it to 7 corresponds to The pH comprehensive score function represents the adult leech stage, and in the old age stage, the optimal pH value is determined. Setting it to 6 will result in the corresponding This is a pH score function representing the aging stage. pH directly affects enzymatic reactions, nutrient absorption, and metabolic functions in leeches. Different growth stages have different requirements for enzyme activity and metabolic processes, thus the required pH varies: juvenile leeches have weaker environmental adaptability, and maintaining a neutral pH helps promote their growth and improve immunity. A neutral environment reduces the impact of acidity and alkalinity on the physiological activities of juvenile leeches, which is beneficial to the normal development of their organs and systems; juvenile leeches require a relatively neutral environment to maintain enzyme activity and promote digestion and absorption. The physiological needs of adult leeches tend to stabilize, and a suitable pH (still around 7.0) can maintain their physiological balance and promote nutrient absorption and metabolic activities. At this stage, slight changes in pH will not significantly affect their growth, but stability is needed to avoid stress. Adult leeches require a relatively stable pH to ensure efficient metabolic processes. The physiological functions of older individuals gradually decline, and a suitable pH range (e.g., 6.5) can help alleviate their physiological burden and reduce metabolic rate. A slightly lower pH level helps provide a more suitable ecological environment for older individuals, reducing stress responses. A moderate decrease in pH during old age helps promote certain physiological responses while reducing the burden on older individuals.

[0134] ;

[0135] in, This is a comprehensive scoring function for dissolved oxygen concentration. This represents the optimal value for dissolved oxygen concentration. This is the comprehensive scoring coefficient for dissolved oxygen concentration data, with a value range of [0.1, 1]. Dissolved oxygen is crucial for the survival of aquatic organisms, and a reasonable... The chosen value ensures the scoring function's sensitivity to changes in dissolved oxygen concentration, reflecting the direct impact of oxygen concentration on biological activity. Similar to temperature, a larger value... The value helps to bring the oxygen concentration close to the optimal value. In a timely manner, it can keenly reflect any deviations, thus providing farmers with an effective basis for regulation.

[0136] During the larval stage, the optimal dissolved oxygen concentration value is... If set to 6 mg / L, then the corresponding The comprehensive scoring function represents the dissolved oxygen concentration during the juvenile leech stage. During the adult leech stage, the optimal dissolved oxygen concentration value is... If set to 5 mg / L, then the corresponding The comprehensive score function representing dissolved oxygen concentration during the adult leech stage, and the optimal dissolved oxygen concentration value during the senescent stage. If set to 4 mg / L, then the corresponding This is a comprehensive scoring function representing dissolved oxygen concentration in older leeches. Young leeches grow rapidly and have a relatively high oxygen requirement. Optimal dissolved oxygen concentration helps meet their high metabolic rate, supporting rapid growth and development. Sufficient oxygen promotes cellular respiration, increases energy production, and supports the physiological activities of young leeches. Young leeches have poor adaptability to environmental changes, therefore requiring higher dissolved oxygen concentrations to enhance their physiological activity and immunity, and strengthen their adaptability. Adult leeches have a relatively stable metabolic rate, and a suitable dissolved oxygen concentration can meet their growth and activity needs. At this stage, excessively high oxygen concentrations may lead to stress, while excessively low concentrations may affect health. Therefore, maintaining a moderate oxygen concentration is crucial. Adult leeches have strong adaptability and can adapt to changes in oxygen concentration within a certain range, but it is still necessary to maintain them within the optimal range to ensure healthy growth. The metabolic needs of older individuals decrease, and a suitable dissolved oxygen concentration can reduce oxygen demand and lower the physiological burden on older individuals. Lower oxygen concentrations can avoid oxidative stress caused by excessive oxygen, helping older individuals maintain health. As individuals age, their adaptability gradually weakens. Lower dissolved oxygen concentrations can reduce stress responses, help them maintain physiological balance, and extend their lifespan.

[0137] In this embodiment, generating the comprehensive health index specifically includes:

[0138] The body weight data of the regulated sample of *Hirudo nipponia* was obtained. This body weight data, along with the corresponding growth stage of the leeches, was input into a growth rate prediction model. The growth rate of the regulated leeches was then obtained from the model's output. Combined with the growth rate, body length, and body width data of the regulated leeches, health indicators were obtained. Based on these health indicators and environmental data, the overall health status of the leeches at the current moment was analyzed using the following formula:

[0139] ;

[0140] in, This represents the comprehensive health index of the i-th sample of *Hirudo medicinalis* after the current regulation. The health indicators of the i-th sample of leeches after the current regulation are as follows: This represents the environmental impact index of the i-th sample of *Hirudo medicinalis* after regulation. ∈(E1, E2, E3), that is, the corresponding environmental impact index is calculated based on the growth stage of the sample leeches. These are the weight coefficients for the corresponding items. ,and ;

[0141] The overall health index of the sample leeches at the current moment is compared with a preset health threshold. If the overall health index of the sample leeches at the current moment is higher than the preset health threshold, the sample leeches are considered to be in a healthy state. If the overall health index of the sample leeches at the current moment is lower than the health threshold, the sample leeches are considered to be in an unhealthy state. The number of healthy and unhealthy sample leeches in each breeding pond is counted. If the number of unhealthy sample leeches in a breeding pond exceeds one-quarter of the total number of sample leeches in that breeding pond, the breeding pond is marked as an abnormal state, and the water temperature in the breeding pond in the abnormal state is monitored and adjusted.

[0142] Comprehensive Health Index This index reflects the overall health status of *Hirudo medicinalis* under current environmental conditions. It is a comprehensive indicator that considers both the organism's health status and environmental impact, aiming to provide a quantitative standard for farmers to understand the growth and health level of *Hirudo medicinalis*. By calculating the comprehensive health index, farmers can quickly determine the health status of *Hirudo medicinalis* and decide whether to adjust the water temperature in the rearing pond. It also provides a scientific and quantitative way to manage and optimize the rearing environment, helping to improve the growth efficiency and survival rate of *Hirudo medicinalis*. In the growth and health assessment of aquatic organisms, health indicators are core factors directly reflecting the organism's condition; therefore, providing... A higher weighting is reasonable, meaning that the health status of organisms occupies a more important position in the comprehensive health index. The environmental impact index E reflects the potential negative impact of the environment on the health of organisms. Although it is important, based on the impact on health indicators, it is generally desirable not to let environmental impacts excessively interfere with health assessments. Therefore, giving E a smaller weight is a way of reflecting its negative effects through subtraction. This format ensures that the calculation result of the comprehensive health index is within a relatively uniform range (e.g., 0 to 1), making... It can be understood and applied more intuitively. Through normalization, the comparison between health indicators and environmental impacts can be balanced, ensuring that both are assessed under the same standard.

[0143] Health-related indicators for leeches include growth rate, body length, and body width. Growth rate directly reflects the leech's growth speed and is an important indicator of its health. Body length and width are physical manifestations of biological growth; generally, increases in body length and width are positively correlated with health. A higher H value, i.e., a larger ratio, indicates that the leech is in good health, leading to an increase in the H value, and vice versa. Therefore There is a positive correlation between health indicators and the overall health index; as health indicators increase, the overall health index also increases, and vice versa. The environmental impact index is negatively correlated with E. If the current temperature, pH, or dissolved oxygen concentration is far from the optimal value and is not the most suitable environment for the growth of Hirudo medicinalis, the environmental impact index will increase, and the corresponding comprehensive health index will decrease. Conversely, the smaller the environmental impact index, the closer the environmental data is to the optimal value, and the more suitable it is for the growth of Hirudo medicinalis, the higher the comprehensive health index will be.

[0144] Please see Figure 2 The present invention also provides a real-time water temperature monitoring and control device for artificially bred leeches. This device is used to implement the above-mentioned real-time water temperature monitoring and control method for artificially bred leeches, comprising:

[0145] The data acquisition module is used to randomly select multiple samples of Hirudo nipponia from the Hirudo nipponia breeding pond, and obtain the weight, body length, body width, growth images and growth stages of the sample Hirudo nipponia at the current and previous collection times, as well as the environmental data in the Hirudo nipponia breeding pond, and determine the growth rate of the sample Hirudo nipponia at the previous collection times based on the weight.

[0146] The model building module is used to build a growth rate prediction model that takes weight, growth stage and environmental data as input and outputs growth rate. The model is trained based on data collected at previous times and the growth rate of the sample leeches is obtained based on the trained model at the current time.

[0147] The temperature control module is used to analyze the growth rate, body length and body width of the sample leeches at the current moment based on the analytic hierarchy process, so as to comprehensively assess the health status of the sample leeches in the breeding pond at the current moment, and determine whether to control the temperature based on the health status.

[0148] The comprehensive evaluation module is used to obtain the post-regulation growth rate and health status of the sample leeches based on the regulated temperature, and to generate a comprehensive health index based on the regulated environmental data and health status to determine the regulation effect.

[0149] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0150] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0151] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0152] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for real-time monitoring and control of water temperature in artificially cultured Hirudo medicinalis, characterized in that, The specific steps include: Step 1: Randomly select multiple samples of leeches in the leech breeding pond, and obtain the weight, body length, body width, growth images and growth stages of the leeches at the current and previous collection times, as well as the environmental data in the leech breeding pond. Determine the growth rate of the leeches at the previous collection times based on their weight. Step 2: Construct a growth rate prediction model with inputs of body weight, growth stage, and environmental data, and output of growth rate. Train the model based on data collected at previous times, and obtain the growth rate of the sample leeches at the current time based on the trained model. Step 3: Analyze the growth rate, body length, and body width of the sample leeches at the current moment using the analytic hierarchy process (AHP) to comprehensively assess the health status of the leeches in the breeding pond at the current moment, and determine whether to adjust the temperature based on the health status. Step 4: Based on the regulated temperature, obtain the regulated growth rate and health status of the sample leeches, and generate a comprehensive health index based on the regulated environmental data and health status to determine the regulated effect; The analysis of the environmental data after regulation specifically includes: Environmental data of the *Hirudo medicinalis* (horsehair) breeding ponds after regulation were obtained, and the regulated environmental data were analyzed to obtain the environmental impact index. The calculation formula is as follows: Where Ej is the environmental impact index corresponding to the j-th growth stage; Let be the comprehensive scoring function for the j-th growth stage, x be the environmental data index, and x = T, pH, DO, where T is the current temperature of the aquaculture pond water, pH is the current acidity / alkalinity of the aquaculture pond water, DO is the current dissolved oxygen concentration of the aquaculture pond water, a, b, and c are the weight coefficients of the corresponding items, and j is the growth stage index, j = 1, 2, 3, that is, E1, E2, and E3 correspond to the juvenile leech stage, adult leech stage, and old age stage, respectively. ； in, This represents the optimal value of the environmental data corresponding to the j-th growth stage. This represents the overall score coefficient for the xth environmental data item. The body weight data of the regulated sample of *Hirudo nipponia* was obtained. This body weight data, along with the corresponding growth stage of the leeches, was input into a growth rate prediction model. The growth rate of the regulated leeches was then obtained from the model's output. Combined with the growth rate, body length, and body width data of the regulated leeches, health indicators were obtained. Based on these health indicators and environmental data, the overall health status of the leeches at the current moment was analyzed using the following formula: ;in, This represents the comprehensive health index of the i-th sample of *Hirudo medicinalis* after the current regulation. The health indicators of the i-th sample of leeches after the current regulation are as follows: This represents the environmental impact index of the i-th sample of *Hirudo medicinalis* after regulation. ∈(E1, E2, E3), These are the weight coefficients for the corresponding items; The overall health index of the sample leeches at the current moment is compared with a preset health threshold. If the overall health index of the sample leeches at the current moment is higher than the preset health threshold, the sample leeches are considered to be in a healthy state. If the overall health index of the sample leeches at the current moment is lower than the health threshold, the sample leeches are considered to be in an unhealthy state. The number of healthy and unhealthy sample leeches in each breeding pond is counted. If the number of unhealthy sample leeches in a breeding pond exceeds one-quarter of the total number of sample leeches in that breeding pond, the breeding pond is marked as an abnormal state, and the water temperature in the breeding pond in the abnormal state is monitored and adjusted.

2. The method for real-time monitoring and control of water temperature in artificially bred Hirudo medicinalis according to claim 1, characterized in that, Determining the growth rate of the sample *Hirudo medicinalis* specifically includes: The growth stages of *Hirudo nipponia* are divided into juvenile, adult, and senile stages. The body width data refers to the width of the abdomen, and the body length data refers to the length from head to tail. Based on the body weight data of *Hirudo nipponia* samples from the breeding pond at the current and previous collection times, the growth rate of each sample was calculated using the following formula: ； in, For the i-th sample of Hirudo medicinalis Growth rate at any given time For the i-th sample of Hirudo medicinalis Weight at any given time For the i-th sample of Hirudo medicinalis Weight at any given time For time t and The time interval of time, This is the index for the time.

3. The method for real-time monitoring and control of water temperature in artificially bred Hirudo medicinalis according to claim 1, characterized in that, Constructing the growth rate prediction model specifically includes: The environmental data includes the temperature, pH value, and dissolved oxygen concentration of the water in the leech breeding pond. Temperature sensors, pH sensors, and dissolved oxygen sensors are arranged around and in the center of the breeding pond to collect the temperature, pH value, and dissolved oxygen concentration data of the water in the surrounding and center locations of the leech breeding pond. The average value is calculated and defined as the temperature, pH value, and dissolved oxygen concentration data of the water in the leech breeding pond. After pre-treating the temperature, pH and dissolved oxygen concentration of the culture pond at multiple time points, the Pearson correlation coefficient between each environmental variable and the growth rate was calculated. Environmental variables with an absolute value of Pearson correlation coefficient greater than 0.5 were selected as strongly correlated environmental variables. The pre-treatment included removing outliers, filling missing values ​​and maximum-minimum normalization. The weight, growth stage, and pre-processed strongly correlated environmental variables of the sample leeches were used as inputs, and the growth rate of the sample leeches was used as the label. Data from previous collection times were divided into training and testing sets. The weight, growth stage, and pre-processed strongly correlated environmental variables of the sample leeches in the training set were input, and the growth rate of the corresponding sample leeches was used as the label to train the growth rate prediction model. The data in the testing set were input into the trained model for testing.

4. The method for real-time monitoring and control of water temperature in artificially bred Hirudo medicinalis according to claim 1, characterized in that, A comprehensive assessment of the current health status of the sampled leeches includes: Collect the weight and growth stage of the sample leeches at the current moment and input them into the trained growth rate prediction model to obtain the growth rate data output by the model. The growth rate, body length, and body width of the sample leeches were set as evaluation indicators. A scoring method was set, and the relative importance of each evaluation indicator was determined by expert scoring. A judgment matrix was constructed based on the expert scores, and the eigenvalues ​​and eigenvectors of the judgment matrix were calculated. Consistency was tested by calculating the consistency index and consistency ratio. If the consistency ratio was less than 0.1, the judgment matrix was considered consistent. The health index of the sample leeches at the current moment was then calculated to evaluate the health status of the sample leeches. If the consistency ratio was equal to or greater than 0.1, the judgment matrix was readjusted. The health status of the leech is assessed by calculating its current health indicators. The formula is as follows: ； in, Let represent the health indicators of the i-th sample leech at the current moment. The growth rate prediction model outputs the growth rate of the i-th *Hirudo nipponia* at the current moment. These are the body length and width of the i-th sample leech at the current time. These represent the baseline growth rate, baseline body length, and baseline body width of the i-th sample leech at the current time, representing its growth stage. These are the weight coefficients of the corresponding terms, i.e., the values ​​of the first, second, and third terms in the eigenvectors involved in the analytic hierarchy process.

5. The method for real-time monitoring and control of water temperature in artificially bred Hirudo medicinalis according to claim 4, characterized in that, Determining whether to adjust the temperature specifically includes: Calculate the mean of the health indicators of the sample leeches at the current moment, and compare the mean with the preset health threshold. If the mean of the health indicators of the sample leeches at the current moment is higher than the health threshold, it indicates that the current environment has a promoting effect on the growth of leeches. If the mean of the health indicators of the sample leeches at the current moment is lower than the health threshold, it indicates that the current environment has an inhibitory effect on the growth of leeches. Then monitor the temperature data of the water in the breeding pond and regulate it. The current temperature data in the leech farming pond is compared with the optimal temperature value to calculate the heat required for the temperature change within the system. The calculation formula is as follows: ;in, The heat required for temperature changes within the system. For the quality of the water in the aquaculture pond, Let T be the specific heat capacity of the water in the aquaculture pond, and T be the current temperature of the water in the aquaculture pond. This represents the optimal temperature for the water in the aquaculture pond. The formula for calculating the power required to calculate the change in heat is: in, The power required for the change in heat. Preset adjustment duration; If the current water temperature in the aquaculture pond is higher than the optimal temperature, the calculated power value will be matched with the output power of the corresponding cooling equipment. If the current water temperature in the aquaculture pond is lower than the optimal temperature, the calculated power value will be matched with the output power of the corresponding heating equipment.

6. A real-time water temperature monitoring and control device for artificially bred Hirudo medicinalis, characterized in that, The aforementioned real-time water temperature monitoring and control device for artificially bred Hirudo medicinalis is used to implement the real-time water temperature monitoring and control method for artificially bred Hirudo medicinalis as described in any one of claims 1-5, comprising: The data acquisition module is used to randomly select multiple samples of Hirudo nipponia from the Hirudo nipponia breeding pond, and obtain the weight, body length, body width, growth images and growth stages of the sample Hirudo nipponia at the current and previous collection times, as well as the environmental data in the Hirudo nipponia breeding pond, and determine the growth rate of the sample Hirudo nipponia at the previous collection times based on the weight. The model building module is used to build a growth rate prediction model that takes weight, growth stage and environmental data as input and outputs growth rate. The model is trained based on data collected at previous times and the growth rate of the sample leeches is obtained based on the trained model at the current time. The temperature control module is used to analyze the growth rate, body length and body width of the sample leeches at the current moment based on the analytic hierarchy process, so as to comprehensively assess the health status of the sample leeches in the breeding pond at the current moment, and determine whether to control the temperature based on the health status. The comprehensive evaluation module is used to obtain the post-regulation growth rate and health status of the sample leeches based on the regulated temperature, and to generate a comprehensive health index based on the regulated environmental data and health status to determine the regulation effect.

Images