Intelligent control method and system for improving survival rate of aquatic animal transportation

Abstract

The application discloses an intelligent regulation method and system for improving survival rate of aquatic animals in transportation, which is applied to the field of food transportation, and the method comprises the following steps: collecting stress indexes by backtracking first transportation records, judging whether the first stress frequency and the first stress level meet corresponding threshold values, setting corresponding stress indexes as first isolated early warning indexes if the corresponding threshold values are met; performing hierarchical cluster analysis on the first isolated early warning indexes to generate a first cluster analysis result; generating a first damage prediction level; setting corresponding isolated early warning indexes as first hazard indexes if the first damage level threshold is met; generating a first coping strategy based on a coping strategy matching model, and performing transportation regulation. The technical problem that the prior art cannot accurately analyze indexes affecting the survival rate of aquatic animals and thus cannot accurately regulate transportation is solved. The technical effect of accurately predicting the influence degree of indexes affecting the survival rate of aquatic animals and improving the accuracy of transportation regulation is achieved.

Description

Technical Field

[0001] This application relates to the field of food transportation, and in particular to an intelligent control method and system for improving the survival rate of aquatic animals during transportation. Background Technology

[0002] With economic development and faster commodity circulation, people's demand for aquatic products is no longer just about quantity, but also about quality. Researching relevant technologies for transporting fresh aquatic products is of great significance for improving the utilization of aquatic resources in my country and enhancing our quality of life.

[0003] Currently, research on the stress responses and stress levels of aquatic animals during transportation aims to analyze the changes in their physiological functions and further investigate effective stress relief strategies. By analyzing factors affecting the survival rate of aquatic animals during transportation, appropriate relief strategies can be selected.

[0004] However, the analysis of the degree of influence of various influencing factors in the existing technology is not accurate enough. Judgments and adjustments are often made based on the experience of the staff, which leads to inaccurate adjustment results. As a result, the survival rate of aquatic animals during transportation is greatly reduced. There is a technical problem that it is impossible to accurately analyze the degree of influence of stress indicators and their interaction on the survival rate of aquatic animals, and thus impossible to accurately control the transportation process. Summary of the Invention

[0005] The purpose of this application is to provide an intelligent control method and system for improving the survival rate of aquatic animals during transportation, in order to solve the technical problem in the prior art that the influence of stress indicators and their interactions on the survival rate of aquatic animals cannot be accurately analyzed, and thus the transportation process cannot be accurately controlled.

[0006] In view of the above problems, this application provides an intelligent control method and system for improving the survival rate of aquatic animals during transportation.

[0007] In a first aspect, this application provides an intelligent regulation method for improving the survival rate of aquatic animals during transportation. The method is implemented through an intelligent regulation system for improving the survival rate of aquatic animals during transportation. The method includes: collecting stress indicators by retrospectively analyzing a first transportation record to obtain a first set of stress indicators, wherein the first stress indicators include a first stress frequency and a first stress level; determining whether the first stress frequency meets a first stress frequency threshold, and determining whether the first stress level meets a first stress level threshold; when the first stress frequency meets the first stress frequency threshold and / or the first stress level meets the first stress level threshold, setting the corresponding stress indicator as a first isolated early warning indicator; performing hierarchical cluster analysis on the first isolated early warning indicator to generate a first cluster analysis result; uploading a first preset transportation duration, traversing the first cluster analysis result to predict the damage level, and generating a first damage prediction level; when the first damage prediction level meets a first damage level threshold, setting the corresponding isolated early warning indicator as a first hazard indicator; inputting the first preset transportation duration and the first hazard indicator into a coping strategy matching model to generate a first coping strategy, and performing transportation regulation based on the first coping strategy.

[0008] On the other hand, this application also provides an intelligent control system for improving the survival rate of aquatic animals during transportation, used to execute an intelligent control method for improving the survival rate of aquatic animals during transportation as described in the first aspect, wherein the system includes: a first acquisition unit, the first acquisition unit being used to retrospectively collect stress indicators from a first transportation record to obtain a first set of stress indicators, wherein the first stress indicator includes a first stress frequency and a first stress level; a first judgment unit, the first judgment unit being used to judge whether the first stress frequency meets a first stress frequency threshold and whether the first stress level meets a first stress level threshold; and a first setting unit, the first setting unit being used to set the stress level when the first stress frequency meets the first stress frequency threshold and / or the first stress level meets the first stress level threshold. A stress level threshold is defined, and the corresponding stress indicator is set as a first isolated early warning indicator; a first generation unit is used to perform hierarchical cluster analysis on the first isolated early warning indicator to generate a first cluster analysis result; a second generation unit is used to upload a first preset transportation time, traverse the first cluster analysis result to predict the damage level, and generate a first damage prediction level; a second setting unit is used to set the corresponding isolated early warning indicator as a first hazard indicator when the first damage prediction level meets the first damage level threshold; a first control unit is used to input the first preset transportation time and the first hazard indicator into a response strategy matching model to generate a first response strategy, and perform transportation control based on the first response strategy.

[0009] Thirdly, a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in any one of the first aspects.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] This application embodiment collects stress indicators by retrospectively analyzing a first transportation record to obtain a first set of stress indicators, wherein the first stress indicators include a first stress frequency and a first stress level. It determines whether the first stress frequency meets a first stress frequency threshold and whether the first stress level meets a first stress level threshold. When the first stress frequency meets the first stress frequency threshold and / or the first stress level meets the first stress level threshold, the corresponding stress indicator is set as a first isolated early warning indicator. Hierarchical clustering analysis is performed on the first isolated early warning indicator to generate a first clustering analysis result. A first preset transportation time is uploaded, and the damage level is predicted by traversing the first clustering analysis result to generate a first damage prediction level. When the first damage prediction level meets the first damage level threshold, the corresponding isolated early warning indicator is set as a first hazard indicator. The first preset transportation time and the first hazard indicator are input into a coping strategy matching model to generate a first coping strategy, and transportation regulation is performed based on the first coping strategy. This achieves accurate prediction of the impact of indicators affecting the survival rate of aquatic animals, improves the accuracy of transportation regulation, and realizes the technical effect of improving the survival rate of aquatic animals.

[0012] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0014] Figure 1 This is a flowchart illustrating an intelligent control method for improving the survival rate of aquatic animals during transportation, as proposed in this application.

[0015] Figure 2This is a flowchart illustrating the process of determining whether the first stress frequency meets the first stress frequency threshold and whether the first stress level meets the first stress level threshold in the intelligent control method for improving the survival rate of aquatic animals during transportation, as described in this application.

[0016] Figure 3 This is a flowchart illustrating the process of generating the first cluster analysis result by performing hierarchical cluster analysis on the first isolated early warning indicator in the intelligent control method for improving the survival rate of aquatic animals during transportation, as described in this application.

[0017] Figure 4 This is a flowchart illustrating the process of uploading a first preset transportation time, traversing the first cluster analysis results to predict the damage level, and generating a first damage prediction level in the intelligent control method for improving the survival rate of aquatic animals during transportation, as described in this application.

[0018] Figure 5 This is a schematic diagram of the structure of an intelligent control system for improving the survival rate of aquatic animals during transportation, as proposed in this application.

[0019] Figure 6 This is a schematic diagram of the structure of an exemplary electronic device of this application.

[0020] Explanation of reference numerals in the attached drawings: First obtaining unit 11, first judging unit 12, first setting unit 13, first generating unit 14, second generating unit 15, second setting unit 16, first control unit 17, electronic device 300, memory 301, processor 302, communication interface 303, bus architecture 304. Detailed Implementation

[0021] This application provides an intelligent control method and system for improving the survival rate of aquatic animals during transportation. It solves the technical problem in existing technologies where the influence of stress indicators and their interactions on the survival rate of aquatic animals cannot be accurately analyzed, thus hindering accurate control of the transportation process. This method achieves the goal of accurately predicting the influence of indicators affecting the survival rate of aquatic animals, improving the accuracy of transportation control, and ultimately increasing the survival rate of aquatic animals.

[0022] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0023] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0024] This application provides an intelligent control method for improving the survival rate of aquatic animals during transportation. The method is applied to an intelligent control system for improving the survival rate of aquatic animals during transportation. The method includes: collecting stress indicators by retrospectively analyzing a first transportation record to obtain a first set of stress indicators, wherein the first stress indicators include a first stress frequency and a first stress level; determining whether the first stress frequency meets a first stress frequency threshold, and determining whether the first stress level meets a first stress level threshold; when the first stress frequency meets the first stress frequency threshold and / or the first stress level meets the first stress level threshold, setting the corresponding stress indicator as a first isolated early warning indicator; then performing hierarchical cluster analysis on the first isolated early warning indicator to generate a first cluster analysis result; uploading a first preset transportation duration, traversing the first cluster analysis result to predict the damage level, and generating a first damage prediction level; when the first damage prediction level meets a first damage level threshold, setting the corresponding isolated early warning indicator as a first hazard indicator; finally, inputting the first preset transportation duration and the first hazard indicator into a coping strategy matching model to generate a first coping strategy, and performing transportation control based on the first coping strategy.

[0025] After introducing the basic principles of this application, various non-limiting embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0026] Example 1

[0027] like Figure 1 As shown, this application provides an intelligent control method for improving the survival rate of aquatic animals during transportation. The method is applied to an intelligent control system for improving the survival rate of aquatic animals during transportation, and specifically includes the following steps:

[0028] Step S100: Backtrack the first transportation record to collect stress indicators and obtain a first set of stress indicators, wherein the first stress indicator includes a first stress frequency and a first stress level;

[0029] Specifically, by analyzing historical transportation records and collecting indicators affecting the survival rate of aquatic animals during transportation, influencing factors can be identified. For example, the aquatic animals can be fish, crustaceans (shrimp, crab), shellfish, and other aquatic animals. The first transportation record refers to historical data generated during the transportation process, recording relevant information such as the transportation environment, the type of aquatic product transported, and the transportation time. The first stress indicator is an indicator that causes stress responses in aquatic animals during transportation, affecting their normal physiological state. The first set of stress indicators refers to the set corresponding to the first stress indicator. The first stress indicator also includes the first stress frequency and the first stress level. The first stress frequency is the frequency of stress responses generated by aquatic animals due to the first stress indicator, and the first stress level is the level of influence corresponding to the stress responses generated by aquatic animals due to the first stress indicator. By obtaining the first stress indicator and its degree of influence, a technical effect is achieved by providing basic data for subsequent analysis of key indicators affecting the survival rate of aquatic animals during transportation and for regulating transportation.

[0030] For example, the first stress index may be tissue hypoxia stress, pH value in water, ammonia nitrogen content in water, salt concentration and temperature during transportation, transportation density, etc.

[0031] For example, when the transported aquatic animal is a fish, the corresponding first stress level can be divided into three levels. Level 1 is caused by changes in serum cortisol levels in the body, manifested as an increase in cortisol and adrenaline. Level 2 is caused by changes in proteins in the body, manifested as changes in blood physiological and biochemical parameters such as respiratory system energy metabolism and water-salt balance, as well as the beginning of immune regulation. Level 3 is a situation where, based on the Level 2 response, the physiological and biochemical parameters of the fish change even more, the immune capacity decreases, and the metabolic system is disordered.

[0032] Step S200: Determine whether the first stress frequency meets the first stress frequency threshold, and determine whether the first stress level meets the first stress level threshold;

[0033] Specifically, a first stress frequency threshold and a first stress level threshold are set to classify the first stress frequency and the first stress level, identifying stress indicators with a high correlation to the survival rate of aquatic animals during transportation. The first stress frequency threshold is the highest value of the stress response frequency that does not affect the normal physiological state of aquatic animals, and the first stress level threshold is the highest value of the stress response impact level that does not affect the normal physiological state of aquatic animals. This improves the efficiency of subsequent analysis of the first stress indicator, thereby enhancing the accuracy of regulation.

[0034] For example, the first stress frequency threshold can be 10 times per hour. The specific frequency threshold can be set by the staff according to the type of aquatic product, and there is no restriction here.

[0035] Step S300: When the first stress frequency meets the first stress frequency threshold and / or the first stress level meets the first stress level threshold, the corresponding stress indicator is set as the first isolated early warning indicator.

[0036] Specifically, when the first stress frequency meets the first stress frequency threshold (meaning the first stress frequency exceeds the highest value of the stress response frequency that does not affect the normal physiological state of the aquatic animal), and the first stress level meets the first stress level threshold (meaning the first stress level exceeds the highest value of the stress response impact level that does not affect the normal physiological state of the aquatic animal), and when both the first stress frequency and the first stress level meet the first stress level threshold (meaning both the first stress frequency and the first stress level exceed the range that does not affect the normal physiological state of the aquatic animal), it indicates that the first stress frequency and / or the first stress level corresponding to the first stress indicator can have a relatively serious impact on the normal physiological state of the aquatic animal on its own, and the first stress indicator needs to be given special attention. The first isolated warning indicator is an indicator that has a relatively serious impact on the aquatic animal and needs to be closely observed; it is a relatively dangerous indicator. This method achieves the technical effect of screening numerous stress indicators, providing indicators that have a relatively serious impact on the physiological state of aquatic animals for subsequent analysis, and improving the efficiency of analysis and the accuracy of regulation.

[0037] Step S400: Perform hierarchical cluster analysis on the first isolated early warning indicator to generate the first cluster analysis result;

[0038] Specifically, the hierarchical clustering analysis refers to grouping and analyzing the first isolated early warning indicators to explore and uncover potential differences and connections between them, analyzing intra-group similarities and inter-group differences. This hierarchical clustering analysis is an unsupervised learning method that does not require any form of labeling; cluster labels are inferred based on the data's inherent structure, and the first clustering analysis result is obtained through this process. The first clustering analysis result represents the association between the first isolated early warning indicators and the physiological state of aquatic animals, thereby achieving the technical effect of improving the accuracy of transportation regulation.

[0039] Step S500: Upload the first preset transportation time, traverse the first cluster analysis results to predict the damage level, and generate the first damage prediction level;

[0040] Specifically, the first preset transportation time is the preset transportation duration for aquatic animals. Within this transportation time, the possible damage levels predicted by the first clustering analysis are determined, and a first damage prediction level is generated. The first damage prediction level is a damage level obtained based on the predicted damage to the aquatic animals during transportation, and can be selected as: Level 1 is minor injury, Level 2 is serious injury, and Level 3 is death. Therefore, the degree of damage to aquatic animals within the transportation time can be predicted, further achieving the technical effect of providing analytical data for subsequent damage analysis.

[0041] Step S600: When the first damage prediction level meets the first damage level threshold, the corresponding isolated early warning indicator is set as the first hazard indicator.

[0042] Specifically, setting a first damage level threshold to filter the first damage prediction level is to identify factors that truly affect the survival rate of aquatic animals during transportation. The first damage level threshold is the maximum level at which damage to aquatic animals reaches the minor injury level; if the first damage level exceeds the threshold, it will cause serious injury to the aquatic animals. Furthermore, setting the corresponding isolated early warning indicator as the first hazard indicator achieves the technical effect of progressively filtering the first stress indicators to obtain the true hazard indicators, providing foundational data for subsequently generating corresponding response strategies.

[0043] Step S700: Input the first preset transportation time and the first hazard index into the response strategy matching model to generate a first response strategy, and perform transportation regulation based on the first response strategy.

[0044] Specifically, the response strategy matching model is a neural network containing multiple learnable parameters that takes the first preset transportation time and the first hazard index as input data to generate the first response strategy. Then, the accurate response strategy is used to regulate the transportation process of aquatic animals, thereby achieving the technical effect of improving the survival rate of aquatic animals.

[0045] Furthermore, such as Figure 2 As shown, in determining whether the first stress frequency meets the first stress frequency threshold and whether the first stress level meets the first stress level threshold, step S200 of this application embodiment further includes:

[0046] Step S210: When the first stress frequency does not meet the first stress frequency threshold or / and the first stress level does not meet the first stress level threshold, the corresponding stress index is set as the first interactive early warning index.

[0047] Step S220: Based on historical data, combine the first interactive early warning indicators to obtain a first combination result;

[0048] Step S230: Based on the first preset transportation time, traverse the first combination results to predict the damage level and generate a second damage prediction level.

[0049] Specifically, if the first stress frequency does not meet the first frequency threshold and / or the first stress level does not meet the first stress level threshold, it indicates that the corresponding stress indicators, when acting alone, do not have a significant impact on the physiological state of the aquatic animals. However, when multiple first interactive warning indicators are combined, they may cause the mortality of the aquatic animals. Combining the first interactive warning indicators with each other can obtain the first combination result, and then generate the second damage prediction level. Performing the same operation on the second damage prediction level as on the first damage prediction level can realize the prediction of the impact on the aquatic animal inventory based on the result of the combination of the first interactive warning indicators, and further generate corresponding coping strategies, making the coping strategies more complete and accurate, thereby achieving the technical effect of improving the accuracy and effectiveness of intelligent regulation.

[0050] Specifically, the first interactive early warning indicator is a stress indicator that, when used alone, cannot significantly impact the survival of aquatic animals. The first combined result is obtained by combining the first interactive early warning indicators, including the frequency and level of stress caused to aquatic animals after the combination.

[0051] For example, when the aquatic animal is a fish, the first interactive warning indicator can be the rate of apoptosis, the amount of immune protein synthesis, etc. Apoptosis is a normal phenomenon in fish when they are under stress in order to achieve homeostasis. However, if the rate of apoptosis reaches a certain level and the amount of immune protein synthesis decreases at the same time, it will lead to the death of the fish.

[0052] Furthermore, such as Figure 3 As shown, in the step of performing hierarchical cluster analysis on the first isolated early warning indicator to generate the first cluster analysis result, step S400 of this application embodiment further includes:

[0053] Step S410: Obtain the first-level clustering attributes, wherein the first-level clustering attributes include physical stress attributes and chemical stress attributes;

[0054] Step S420: Cluster the first isolated early warning indicator according to the first-level clustering attribute to generate a first-level clustering result;

[0055] Step S430: Traverse the first isolated early warning indicators to generate a second stress level;

[0056] Step S440: Perform serialization adjustment on the second stress level to generate a first serialization adjustment result;

[0057] Step S450: Based on the first serialization adjustment result, traverse the first-level clustering results to perform layering and generate the first directed clustering tree;

[0058] Step S460: Set the first directed clustering tree as the first clustering analysis result.

[0059] Specifically, the hierarchical clustering analysis of the first isolated early warning indicator firstly involves clustering it according to the primary clustering attributes to find the similarity between the physical stress attributes and chemical stress attributes of the first isolated early warning indicator. Optionally, the physical stress attributes include transport density, noise, vibration, and collisions between individuals during transport. The chemical stress attributes include ammonia nitrogen content in water, salt concentration in water, and pH value. The primary clustering result is the degree of similarity between the physical stress attributes and chemical stress attributes of the first isolated early warning indicator. Thus, the first isolated early warning indicator can be divided into two categories for separate analysis. Furthermore, the second stress level refers to the stress level generated by the effect of the first isolated early warning indicator (either the physical stress attribute or the chemical stress attribute) on aquatic animals.

[0060] Specifically, by sequentially adjusting the second stress level according to its descending order, the first sequential adjustment result is generated. Then, based on the adjustment result, the first-level clustering result is stratified according to the stress level, generating the first directed clustering tree. This first directed clustering tree provides a clear visual representation of the clustering results, making the impact of the first isolated early warning indicator on aquatic animals visible. This lays the technical foundation for establishing an accurate matching model for subsequent response strategies.

[0061] Furthermore, such as Figure 4 As shown, the step S500 of the embodiment of this application further includes: uploading the first preset transportation time, traversing the first clustering analysis results to predict the damage level, and generating a first damage prediction level.

[0062] Step S510: Obtain a first damage level prediction model, wherein the first damage level prediction model includes a first network layer and a second network layer;

[0063] Step S520: Based on the results of the first cluster analysis, generate the first directed set of physical stress indicators and the first directed set of chemical stress indicators;

[0064] Step S530: Based on the first preset transportation time, traverse the first directed set of physical stress indicators, input it into the first network layer, and generate the first physical stress damage level.

[0065] Step S540: Based on the first preset transportation time, traverse the first directed set of chemical stress indicators, input it into the second network layer, and generate the first chemical stress damage level;

[0066] Step S550: Add the first physical stress damage level and the first chemical stress damage level to the first damage prediction level.

[0067] Specifically, after obtaining the first clustering analysis results, the directed sets of the first physical stress indicators and the first chemical stress indicators can be obtained, with the direction from top to bottom, indicating that the impact on aquatic animals decreases. The first network layer is a neural network model that outputs the first physical stress damage level by using the damage caused to aquatic animals by the physical stress indicators obtained by traversing the first directed set of physical stress indicators according to the first preset transportation time as input data. The second network layer is a neural network model that outputs the first chemical stress damage level by using the damage caused to aquatic animals by the chemical stress indicators obtained by traversing the first directed set of chemical stress indicators according to the first preset transportation time as input data.

[0068] Specifically, adding the first physical stress damage level and the first chemical stress damage level to the first damage prediction level enriches the attributes of the first damage prediction level, improves its accuracy, and provides accurate and efficient analytical data for subsequent determination of whether the corresponding isolated early warning indicators are the first hazard indicators.

[0069] Furthermore, in the step of predicting the damage level by traversing the first combination results based on the first preset transportation time and generating a second damage prediction level, step S230 of this application embodiment further includes:

[0070] Step S231: Obtain the third network layer based on the first damage level prediction model;

[0071] Step S232: Based on the first preset transportation time, traverse the first combination result, input it into the third network layer, and generate the second damage prediction level.

[0072] Specifically, since both are based on the first stress index as fundamental data, the third network layer can be obtained by transferring the data from the first damage level prediction model. This third network layer is a neural network model that takes the damage caused to aquatic animals by the first interactive early warning index, obtained by traversing the first combination results based on the first preset transportation time, as input data and outputs the second damage prediction level. This can improve the completeness and accuracy of damage level prediction.

[0073] Specifically, the first, second, and third network layers are all simple three-layer neural networks consisting of an input layer, a hidden layer, and an output layer. These three layers are deployed as independent nodes in the hidden layer of the damage level prediction model, and are processed separately according to different types of information input from the model's input layer. This achieves the technical effect of efficiently and accurately predicting damage levels.

[0074] Furthermore, in obtaining the first damage level prediction model, step S510 of this application embodiment further includes:

[0075] Step S511: Construct the first input layer;

[0076] Step S512: Construct the first network layer based on the artificial neural network and the first historical data;

[0077] Step S513: Construct the second network layer based on the artificial neural network and the second historical data;

[0078] Step S514: Construct the third network layer based on the artificial neural network and the third historical data;

[0079] Step S515: Construct the first output layer;

[0080] Step S516: Merge the first input layer, the first network layer, the second network layer, the third network layer, and the first output layer to generate the first damage level prediction model.

[0081] Specifically, the first historical data is obtained by traversing the directed set of the first physical stress indicators based on the first preset transportation time; the second historical data is obtained by traversing the directed set of the first chemical stress indicators based on the first preset transportation time; and the third historical data is obtained by traversing the first combined result based on the first preset transportation time. The specific construction process of each network layer has been explained above and will not be repeated here. The first input layer is the channel used by the first damage level prediction model to receive input data and determine whether the data type belongs to physical stress indicators, chemical stress indicators, or combined indicators. It can input different types of data into subsequent network layers with different functions. The first output layer is the channel used to output the damage level prediction result. The first damage level prediction model is a neural network model obtained by merging the first input layer, the first network layer, the second network layer, the third network layer, and the first output layer, thereby achieving accurate prediction of the damage level of aquatic animals and improving the accuracy of intelligent regulation.

[0082] Furthermore, the step S700 of this embodiment further includes inputting the first preset transportation time and the first hazard index into the response strategy matching model to generate a first response strategy, and performing transportation regulation based on the first response strategy:

[0083] Step S710: Obtain the fourth historical data, wherein the fourth historical data includes multiple sets of: hazard indicators, transportation time and response strategy identification information;

[0084] Step S720: Divide the fourth historical data into a ratio of 9:0.5:0.5, set the 9 ratio as the training dataset, the 0.5 ratio as the iteration dataset, and the 0.5 ratio as the validation dataset.

[0085] Step S730: Construct the response strategy matching model based on the training dataset, the iterative dataset, and the validation dataset.

[0086] Specifically, the response strategy matching model is a neural network model that can be iteratively trained based on different weight parameters. It obtains multiple sets of the fourth historical data, including hazard indicators, transportation duration, and response strategy identification information. Then, it constructs a dataset based on this fourth historical data, which includes a training dataset, an iteration dataset, and a validation dataset. The training dataset is used to train and adjust the model parameters of the neural network model. The iteration dataset is used for iterative training based on different weight parameters. The validation dataset is used to verify the model's accuracy and adjust its parameters.

[0087] Specifically, by dividing the fourth historical data into different proportions to train and construct the strategy matching model, the performance of the strategy matching model can be made more accurate, the matching speed can be accelerated, and the efficiency and quality of intelligent control over the transportation process of aquatic animals can be improved.

[0088] Furthermore, in the embodiment of this application, step S730, which involves constructing the response strategy matching model based on the training dataset, the iterative dataset, and the validation dataset, further includes:

[0089] Step S731: Construct the first node sub-model based on the training dataset, the iterative dataset, and the validation dataset;

[0090] Step S732: Extract the first deviation data of the first node sub-model that does not meet the first preset accuracy, perform weight gain, and generate the second training dataset, the second iteration dataset, and the second validation dataset;

[0091] Step S733: Construct a second node sub-model based on the second training dataset, the second iteration dataset, and the second validation dataset;

[0092] Step S734: When the Mth deviation data meets the first preset quantity, merge the first node sub-model, the second node sub-model and the Mth node sub-model to generate the response strategy matching model.

[0093] Specifically, in constructing the response strategy matching model, the first node sub-model is first constructed according to the above training method. If the training results show first bias data that does not meet the first preset accuracy, it indicates that the weight of the first bias data in the dataset is too low to accurately predict its impact on aquatic animals. Therefore, its weight in the dataset is increased, generating the second training dataset, the second iteration dataset, and the second validation dataset, and establishing the second node sub-model. When the Mth bias data is lower than the first preset number, it indicates that the impact of the bias data on the accuracy of the prediction model is within the error range. The first node sub-model, the second node sub-model, and the Mth node sub-model can be merged to generate the response strategy matching model. The Mth bias data corresponds to the Mth sub-model, and the first preset number is a preset amount of bias data within an acceptable range. Optionally, this can be customized by the staff. By constructing multiple sub-models to continuously fit the output error, the technical effect of improving the model output accuracy is achieved.

[0094] In summary, the intelligent control method for improving the survival rate of aquatic animals during transportation provided in this application has the following technical effects:

[0095] 1. This application collects stress indicators by retrospectively analyzing the first transportation record, determines whether the first stress frequency and first stress level meet corresponding thresholds, and sets the corresponding stress indicator as the first isolated early warning indicator if the threshold is met; performs hierarchical cluster analysis on the first isolated early warning indicator to generate the first cluster analysis result; generates the first damage prediction level; if the first damage level threshold is met, sets the corresponding isolated early warning indicator as the first hazard indicator; and generates the first response strategy based on the response strategy matching model for transportation regulation. This achieves the technical effect of accurately predicting the impact of indicators affecting the survival rate of aquatic animals and improving the accuracy of transportation regulation.

[0096] 2. In this embodiment, the first interactive early warning indicators are combined to obtain the first combination result, which in turn generates the second damage prediction level. Performing the same operations on the second damage prediction level as on the first damage prediction level allows for the prediction of the impact on aquatic animal inventory based on the combined results of the first interactive early warning indicators. This further generates corresponding response strategies, making the response strategies more comprehensive and accurate, thereby improving the accuracy and effectiveness of intelligent regulation.

[0097] Example 2

[0098] Based on the same inventive concept as the intelligent control method for improving the survival rate of aquatic animals during transportation described in the foregoing embodiments, such as... Figure 5 As shown, this application also provides an intelligent control system for improving the survival rate of aquatic animals during transportation, the system comprising:

[0099] The first obtaining unit 11 is used to backtrack the first transportation record to collect stress indicators and obtain a first set of stress indicators, wherein the first stress indicators include a first stress frequency and a first stress level.

[0100] The first judgment unit 12 is used to determine whether the first stress frequency meets the first stress frequency threshold and whether the first stress level meets the first stress level threshold.

[0101] The first setting unit 13 is used to set the corresponding stress indicator as the first isolated early warning indicator when the first stress frequency meets the first stress frequency threshold and / or the first stress level meets the first stress level threshold.

[0102] The first generation unit 14 is used to perform hierarchical clustering analysis on the first isolated early warning indicator and generate the first clustering analysis result.

[0103] The second generation unit 15 is used to upload the first preset transportation time, traverse the first clustering analysis results to predict the damage level, and generate the first damage prediction level.

[0104] The second setting unit 16 is used to set the corresponding isolated early warning indicator as the first hazard indicator when the first damage prediction level meets the first damage level threshold.

[0105] The first control unit 17 is used to input the first preset transportation time and the first hazard index into the response strategy matching model, generate a first response strategy, and perform transportation control based on the first response strategy.

[0106] Furthermore, the system also includes:

[0107] The third setting unit is used to set the corresponding stress indicator as the first interactive early warning indicator when the first stress frequency does not meet the first stress frequency threshold or / and the first stress level does not meet the first stress level threshold.

[0108] The second obtaining unit is used to combine the first interactive early warning indicators based on historical data to obtain a first combination result;

[0109] The third generation unit is used to predict the damage level by traversing the first combination results based on the first preset transportation time, and generate a second damage prediction level.

[0110] Furthermore, the system also includes:

[0111] The third obtaining unit is used to obtain the first-level clustering attributes, wherein the first-level clustering attributes include physical stress attributes and chemical stress attributes;

[0112] The fourth generation unit is used to cluster the first isolated early warning indicator according to the first-level clustering attribute to generate a first-level clustering result;

[0113] The fifth generation unit is used to traverse the first isolated early warning indicators and generate a second stress level;

[0114] The sixth generation unit is used to perform serialization adjustment on the second stress level and generate a first serialization adjustment result;

[0115] The seventh generation unit is used to perform layering by traversing the first-level clustering results according to the first serialization adjustment result, and generate a first directed clustering tree.

[0116] The fourth setting unit is used to set the first directed clustering tree as the first clustering analysis result.

[0117] Furthermore, the system also includes:

[0118] The fourth obtaining unit is used to obtain a first damage level prediction model, wherein the first damage level prediction model includes a first network layer and a second network layer.

[0119] The eighth generation unit is used to generate a first directed set of physical stress indicators and a first directed set of chemical stress indicators based on the first clustering analysis results.

[0120] The ninth generation unit is used to traverse the first directed set of physical stress indicators according to the first preset transportation time, input it into the first network layer, and generate the first physical stress damage level.

[0121] The tenth generation unit is used to traverse the first chemical stress index directed set according to the first preset transportation time, input it into the second network layer, and generate the first chemical stress damage level.

[0122] The first adding unit is used to add the first physical stress damage level and the first chemical stress damage level to the first damage prediction level.

[0123] Furthermore, the system also includes:

[0124] The fifth obtaining unit is used to obtain the third network layer based on the first damage level prediction model;

[0125] The eleventh generation unit is used to generate the second damage prediction level by traversing the first combination result according to the first preset transportation time and inputting it into the third network layer.

[0126] Furthermore, the system also includes:

[0127] A first building unit, which is used to build a first input layer;

[0128] The second construction unit is used to construct the first network layer based on the artificial neural network and the first historical data;

[0129] The third building unit is used to build the second network layer based on the artificial neural network and the second historical data;

[0130] The fourth construction unit is used to construct the third network layer based on the artificial neural network and the third historical data;

[0131] The fifth building unit is used to build the first output layer;

[0132] The twelfth generation unit is used to merge the first input layer, the first network layer, the second network layer, the third network layer and the first output layer to generate the first damage level prediction model.

[0133] Furthermore, the system includes:

[0134] The sixth obtaining unit is used to obtain the first historical data, wherein the fourth historical data includes multiple sets of: hazard indicators, transportation time and response strategy identification information;

[0135] The fifth setting unit is used to divide the fourth historical data into a ratio of 9:0.5:0.5, setting the 9 ratio as the training dataset, the 0.5 ratio as the iteration dataset, and the 0.5 ratio as the validation dataset.

[0136] The sixth building unit is used to build the response strategy matching model based on the training dataset, the iterative dataset, and the validation dataset.

[0137] Furthermore, the system also includes:

[0138] The seventh building unit is used to build a first node sub-model based on the training dataset, the iterative dataset, and the validation dataset;

[0139] The thirteenth generation unit is used to extract the first deviation data of the first node sub-model that does not meet the first preset accuracy, perform weight gain, and generate the second training dataset, the second iteration dataset, and the second verification dataset.

[0140] The eighth building unit is used to build a second node sub-model based on the second training dataset, the second iteration dataset, and the second validation dataset;

[0141] The fourteenth generation unit is used to merge the first node sub-model, the second node sub-model and the Mth node sub-model to generate the response strategy matching model when the Mth deviation data meets the first preset quantity.

[0142] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Figure 1 The intelligent control method and specific examples for improving the survival rate of aquatic animals during transportation in Example 1 are also applicable to the intelligent control system for improving the survival rate of aquatic animals during transportation in this embodiment. Through the foregoing detailed description of the intelligent control method for improving the survival rate of aquatic animals during transportation, those skilled in the art can clearly understand the intelligent control system for improving the survival rate of aquatic animals during transportation in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here. As for the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant details can be found in the method section.

[0143] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0144] Example 3

[0145] Based on the same inventive concept as the intelligent control method for improving the survival rate of aquatic animals during transportation in the foregoing embodiments, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method as described in Embodiment 1.

[0146] Exemplary electronic devices

[0147] The following is for reference. Figure 6 To describe the electronic device of this application,

[0148] Based on the same inventive concept as the intelligent control method for improving the survival rate of aquatic animals during transportation in the foregoing embodiments, this application also provides an intelligent control system for improving the survival rate of aquatic animals during transportation, comprising: a processor coupled to a memory for storing a program, wherein when the program is executed by the processor, the system performs the steps of the method described in Embodiment 1.

[0149] The electronic device 300 includes a processor 302, a communication interface 303, and a memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. The communication interface 303, processor 302, and memory 301 can be interconnected via the bus architecture 304; the bus architecture 304 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus architecture 304 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0150] Processor 302 may be a CPU, microprocessor, ASIC, or one or more integrated circuits used to control the execution of programs according to the present application.

[0151] Communication interface 303 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), wired access network, etc.

[0152] Memory 301 can be ROM or other types of static storage devices capable of storing static information and instructions, RAM or other types of dynamic storage devices capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory can exist independently and be connected to the processor via bus architecture 304. Memory can also be integrated with the processor.

[0153] The memory 301 stores computer execution instructions for implementing the scheme of this application, and the processor 302 controls the execution. The processor 302 executes the computer execution instructions stored in the memory 301, thereby realizing the intelligent control method for improving the survival rate of aquatic animals during transportation provided by the above embodiments of this application.

[0154] Those skilled in the art will understand that the various numerical designations, such as "first," "second," etc., used in this application are merely for descriptive convenience and are not intended to limit the scope of this application, nor do they indicate a chronological order. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one" refers to one or more. "At least two" refers to two or more. "At least one," "any one," or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0155] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive (SSD)).

[0156] The various illustrative logic units and circuits described in this application may be implemented or operate the described functions using a general-purpose processor, digital signal processor, application-specific integrated circuit (ASIC), field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof. The general-purpose processor may be a microprocessor, and optionally, it may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented using a combination of computing devices, such as a digital signal processor and a microprocessor, multiple microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration.

[0157] The steps of the methods or algorithms described in this application can be directly embedded in hardware, a software unit executed by a processor, or a combination of both. The software unit can be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other storage medium of any form in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and storage medium can be disposed in an ASIC, which can be disposed in a terminal. Optionally, the processor and storage medium can also be disposed in different components within the terminal. These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0158] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely illustrative examples of this application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Thus, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. An intelligent control method for improving the survival rate of aquatic animal transportation, characterized in that, The method comprises: obtaining a first stress index set by backtracking a first transportation record, wherein the first stress index comprises a first stress frequency and a first stress level; determining whether the first stress frequency meets a first stress frequency threshold and whether the first stress level meets a first stress level threshold; setting a corresponding stress index as a first isolated early warning index when the first stress frequency meets the first stress frequency threshold or / and the first stress level meets the first stress level threshold; generating a first clustering analysis result by performing hierarchical clustering analysis on the first isolated early warning index; generating a first physical stress index directed set and a first chemical stress index directed set according to the first clustering analysis result; uploading a first preset transportation time length, traversing the first clustering analysis result to predict a damage level, and generating a first damage prediction level; setting a corresponding isolated early warning index as a first hazard index when the first damage prediction level meets a first damage level threshold; inputting the first preset transportation time length and the first hazard index into a coping strategy matching model to generate a first coping strategy, and performing transportation regulation based on the first coping strategy; setting a corresponding stress index as a first interactive early warning index when the first stress frequency does not meet the first stress frequency threshold or / and the first stress level does not meet the first stress level threshold; combining the first interactive early warning index based on historical data to obtain a first combination result; traversing the first combination result to predict a damage level according to the first preset transportation time length, and generating a second damage prediction level.

2. The method of claim 1, wherein, The method comprises: obtaining a first stress index set by backtracking a first transportation record, wherein the first stress index comprises a first stress frequency and a first stress level; determining whether the first stress frequency meets a first stress frequency threshold and whether the first stress level meets a first stress level threshold; setting a corresponding stress index as a first isolated early warning index when the first stress frequency meets the first stress frequency threshold or / and the first stress level meets the first stress level threshold; generating a first clustering analysis result by performing hierarchical clustering analysis on the first isolated early warning index; generating a first physical stress index directed set and a first chemical stress index directed set according to the first clustering analysis result; 3. The method of claim 1, wherein, uploading a first preset transportation time length, traversing the first clustering analysis result to predict a damage level, and generating a first damage prediction level; setting a corresponding isolated early warning index as a first hazard index when the first damage prediction level meets a first damage level threshold; inputting the first preset transportation time length and the first hazard index into a coping strategy matching model to generate a first coping strategy, and performing transportation regulation based on the first coping strategy; setting a corresponding stress index as a first interactive early warning index when the first stress frequency does not meet the first stress frequency threshold or / and the first stress level does not meet the first stress level threshold; combining the first interactive early warning index based on historical data to obtain a first combination result; traversing the first combination result to predict a damage level according to the first preset transportation time length, and generating a second damage prediction level. The method comprises: obtaining a first stress index set by backtracking a first transportation record, wherein the first stress index comprises a first stress frequency and a first stress level; determining whether the first stress frequency meets a first stress frequency threshold and whether the first stress level meets a first stress level threshold; setting a corresponding stress index as a first isolated early warning index when the first stress frequency meets the first stress frequency threshold or / and the first stress level meets the first stress level threshold; generating a first clustering analysis result by performing hierarchical clustering analysis on the first isolated early warning index; generating a first physical stress index directed set and a first chemical stress index directed set according to the first clustering analysis result; uploading a first preset transportation time length, traversing the first clustering analysis result to predict a damage level, and generating a first damage prediction level; setting a corresponding isolated early warning index as a first hazard index when the first damage prediction level meets a first damage level threshold; inputting the first preset transportation time length and the first hazard index into a coping strategy matching model to generate a first coping strategy, and performing transportation regulation based on the first coping strategy; setting a corresponding stress index as a first interactive early warning index when the first stress frequency does not meet the first stress frequency threshold or / and the first stress level does not meet the first stress level threshold; combining the first interactive early warning index based on historical data to obtain a first combination result; traversing the first combination result to predict a damage level according to the first preset transportation time length, and generating a second damage prediction level. The method comprises: obtaining a first stress index set by backtracking a first transportation record, wherein the first stress index comprises a first stress frequency and a first stress level; determining whether the first stress frequency meets a first stress frequency threshold and whether the first stress level meets a first stress level threshold; setting a corresponding stress index as a first isolated early warning index when the first stress frequency meets the first stress frequency threshold or / and the first stress level meets the first stress level threshold; generating a first clustering analysis result by performing hierarchical clustering analysis on the first isolated early warning index; generating a first physical stress index directed set and a first chemical stress index directed set according to the first clustering analysis result; uploading a first preset transportation time length, traversing the first clustering analysis result to predict a damage level, and generating a first damage prediction level; setting a corresponding isolated early warning index as a first hazard index when the first damage prediction level meets a first damage level threshold; inputting the first preset transportation time length and the first hazard index into a coping strategy matching model to generate a first coping strategy, and performing transportation regulation based on the first coping strategy; setting a corresponding stress index as a first interactive early warning index when the first stress frequency does not meet the first stress frequency threshold or / and the first stress level does not meet the first stress level threshold; combining the first interactive early warning index based on historical data to obtain a first combination result; traversing the first combination result to predict a damage level according to the first preset transportation time length, and generating a second damage prediction level.

4. The method of claim 3, wherein, The first combination result is traversed according to the first preset transportation time length to perform damage level prediction, and a second damage prediction level is generated. A third network layer is obtained according to the first damage level prediction model. The first combination result is traversed according to the first preset transportation time length, and the third network layer is input to generate the second damage prediction level.

5. The method of claim 4, wherein, The first damage level prediction model is obtained, including: A first input layer is constructed; The first network layer is constructed based on an artificial neural network and first historical data, wherein the first historical data is obtained by traversing the first physical stress indicator directed set according to the first preset transportation time length; The second network layer is constructed based on an artificial neural network and second historical data, wherein the second historical data is obtained by traversing the first chemical stress indicator directed set according to the first preset transportation time length; The third network layer is constructed based on an artificial neural network and third historical data, wherein the third historical data is obtained by traversing the first combination result according to the first preset transportation time length; A first output layer is constructed; The first input layer, the first network layer, the second network layer, the third network layer and the first output layer are combined to generate the first damage level prediction model.

6. The method of claim 1, wherein, The first preset transportation time length and the first damage indicator are input into a coping strategy matching model to generate a first coping strategy, and transportation regulation is performed based on the first coping strategy, including: Fourth historical data is obtained, wherein the fourth historical data includes multiple groups of damage indicators, transportation time lengths and coping strategy identification information; The fourth historical data is divided into 9:0.5:0.5 proportions, the 9 proportion is set as a training data set, the 0.5 proportion is set as an iteration data set, and the 0.5 proportion is set as a verification data set; The coping strategy matching model is constructed according to the training data set, the iteration data set and the verification data set.

7. The method of claim 6, wherein, The coping strategy matching model is constructed according to the training data set, the iteration data set and the verification data set, including: A first node sub-model is constructed according to the training data set, the iteration data set and the verification data set; First bias data that does not meet a first preset accuracy rate is extracted from the first node sub-model, and weight gain is performed to generate a second training data set, a second iteration data set and a second verification data set; A second node sub-model is constructed according to the second training data set, the second iteration data set and the second verification data set; When the Mth bias data meets the first preset number, the first node sub-model, the second node sub-model and the Mth node sub-model are combined to generate the coping strategy matching model.

8. An intelligent control system for improving survival rate of aquatic animals during transportation, characterized in that, The system is applied to the method of any one of claims 1 to 6, and the system includes: A first obtaining unit is configured to backtrack a first transportation record to collect stress indicators and obtain a first stress indicator set, wherein the first stress indicator includes a first stress frequency and a first stress level. A first determining unit is configured to determine whether the first stress frequency meets a first stress frequency threshold and whether the first stress level meets a first stress level threshold; A first setting unit is configured to set a corresponding stress indicator as a first isolated early warning indicator when the first stress frequency meets the first stress frequency threshold or / and the first stress level meets the first stress level threshold; A first generating unit is configured to perform hierarchical clustering analysis on the first isolated early warning indicator to generate a first clustering analysis result; A second generating unit is configured to upload a first preset transportation time length, traverse the first clustering analysis result to perform damage level prediction, and generate a first damage prediction level; A second setting unit is configured to set a corresponding isolated early warning indicator as a first hazard indicator when the first damage prediction level meets a first damage level threshold; A first regulating unit is configured to input the first preset transportation time length and the first hazard indicator into a coping strategy matching model to generate a first coping strategy, and perform transportation regulation based on the first coping strategy.

9. A computer program product, characterised in that, A storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the method in any one of claims 1 to 7.

Images