A method and system for intelligent analysis and dynamic control of seedling environment

Abstract

This invention relates to the field of agricultural seedling technology, specifically to a method and system for intelligent analysis and dynamic control of the seedling environment. The method includes: establishing a communication network path optimization method to iteratively optimize the path of the seedling environment data monitoring and communication network, obtaining an optimized seedling environment data monitoring and communication network; obtaining an original seedling environment data set based on the optimized monitoring and communication network; detecting mutation points in the original seedling environment data set and obtaining the mutation point detection results; correcting the original seedling environment data set based on the mutation point detection results to obtain a target seedling environment data set; and obtaining evaluation and judgment results for different seedling environment parameters based on the seedling environment parameter judgment system and the target seedling environment data set, thereby achieving dynamic control of the seedling environment. This invention improves data quality through data correction processing, comprehensively considers multiple parameters for overall control of the seedling environment, and meets the actual needs of seedling growth.

Description

Technical Field

[0001] This invention relates to the field of agricultural seedling technology, specifically to a method and system for intelligent analysis and dynamic control of the seedling environment. Background Technology

[0002] Existing methods for monitoring the agricultural seedling environment have significant shortcomings. On the one hand, it is difficult to optimize and adjust the data acquisition system, resulting in a lack of assurance regarding the accuracy and effectiveness of the monitoring data. This hinders accurate monitoring and effective control of seedling environmental information, ultimately leading to unstable seedling data. On the other hand, environmental factors, including temperature, humidity, and light intensity, significantly impact seedling growth and development. Concentration and other factors are key influencing factors, but existing methods only use single comparison methods or simple combination comparisons when analyzing relevant environmental parameters, without comprehensively considering the degree of mutual influence and effect between different parameters. This results in insufficient comprehensiveness of environmental parameter analysis results, and the above-mentioned problems can easily lead to a series of adverse consequences, such as poor seedling growth and large-scale breeding of pests and diseases, which in turn affect the survival rate of seedlings and prolong their growth cycle.

[0003] Furthermore, traditional seedling environment analysis methods cannot dynamically monitor and regulate seedling environment parameters and actual seedling needs, further increasing seedling costs and hindering healthy seedling growth. Therefore, it is necessary to design a method with data monitoring and optimization capabilities and intelligent regulation of the seedling environment to further ensure the intelligent development of agricultural seedling technology. Summary of the Invention

[0004] To address the shortcomings of existing methods and the needs of practical applications, this paper aims to optimize the data monitoring and communication process, ensuring efficient transmission and effective collection of monitoring information. It also includes the detection and analysis of data anomalies to promptly identify and further guarantee data reliability. Simultaneously, a comprehensive seedling environment assessment system is constructed to comprehensively and systematically evaluate different seedling environment parameters, understanding the intrinsic relationships and influence mechanisms between these parameters. This allows for dynamic regulation of the seedling environment, ensuring it remains in an optimal state to meet the various needs of seedling growth and development, and promoting the intelligent transformation of agricultural seedling technology. On the one hand, this invention provides a method for intelligent analysis and dynamic control of the seedling environment. The method includes: establishing a communication network path optimization method; using the communication network path optimization method to iteratively optimize the path of the seedling environment data monitoring and communication network, and obtaining a path-optimized seedling environment data monitoring and communication network; obtaining an original seedling environment data set based on the path-optimized seedling environment data monitoring and communication network; detecting mutation points in the original seedling environment data set and obtaining data mutation point detection results; correcting the original seedling environment data set based on the data mutation point detection results to obtain a target seedling environment data set; constructing a seedling environment parameter judgment system; obtaining evaluation judgment results for different seedling environment parameters based on the target seedling environment data set and the seedling environment parameter judgment system; and dynamically controlling the seedling environment based on the evaluation judgment results.

[0005] This invention selects the optimal data transmission path through an iterative optimization algorithm, which helps reduce system data latency and packet loss rate; data mutation point detection and correction can ensure data quality; and dynamic control of the seedling environment can realize intelligent dynamic management of the seedling environment.

[0006] Optionally, the method for optimizing communication network paths includes: introducing an improved ant colony algorithm and monitoring the operational characteristics of the communication network; and combining the improved ant colony algorithm and the monitored operational characteristics of the communication network to construct a communication network path optimization method. Traditional ant colony algorithms are prone to getting trapped in local optima, but this invention enhances the algorithm's global search capability through improvements, ensuring that it finds the network path with the shortest latency or lowest energy consumption in complex networks.

[0007] Optionally, the method for optimizing communication network paths includes: obtaining network transmission delay, network queuing delay, and processing delay based on seedling environment data monitoring and communication network; setting a network delay evaluation function model in the communication network path optimization method based on the network transmission delay, the network queuing delay, and the processing delay; setting a local pheromone update expression in the communication network path optimization method according to the network delay evaluation function model; and setting a global pheromone update expression in the communication network path optimization method in combination with the local pheromone update expression.

[0008] This invention breaks down the total latency into transmission latency, queuing latency, and processing latency, covering the entire process of data transmission and reception, and providing reliable reference information for system adjustment and optimization.

[0009] Optionally, the step of using the communication network path optimization method to perform path iterative optimization on the seedling environment data monitoring and communication network and obtain the path-optimized seedling environment data monitoring and communication network includes: combining the network delay evaluation function model, the local pheromone update expression, and the global pheromone update expression to perform path iterative optimization on the seedling environment data monitoring and communication network to obtain the path-optimized seedling environment data monitoring and communication network.

[0010] This invention gradually reduces the total latency through multiple iterations, avoiding getting trapped in local optima in a single optimization, which is beneficial for locating the globally optimal path and reducing transmission delays caused by data detours.

[0011] Optionally, obtaining the original seedling environment data set based on the optimized seedling environment data monitoring and communication network includes: analyzing the path selection conditions of different paths in the seedling environment data monitoring and communication network using the network latency evaluation function model; introducing path selection conditions and combining the path selection conditions with the path selection conditions of different paths to obtain network path check results; updating the local pheromones in the seedling environment data monitoring and communication network based on the network path check results, the latency evaluation results of different paths, and the local pheromone update expression, and obtaining local pheromone update results; obtaining global pheromone update results through the local pheromone update results and the local pheromone update expression; and obtaining the original seedling environment data set of the seedling environment data monitoring and communication network based on the global pheromone update results.

[0012] This invention dynamically adjusts the pheromone concentration on the path based on network path inspection results and local pheromone update expressions, thereby enhancing the adaptability and effectiveness of the dynamic control method.

[0013] Optionally, the step of detecting mutation points in the original seedling environment data set and obtaining data mutation point detection results, and then correcting the original seedling environment data set based on the data mutation point detection results to obtain the target seedling environment data set, includes: defining parameters in the mutation point detection process based on the original seedling environment data set and obtaining detection parameter definition information; obtaining the time series reverse processing result of the original seedling environment data set by combining the detection parameter definition information; setting a seedling environment data threshold value; and obtaining the mutation point detection result of the original seedling environment data set based on the time series reverse processing result and the seedling environment data threshold value. This invention dynamically defines mutation point detection parameters based on the statistical characteristics of the original seedling environment data set, which helps this method adapt to the mutation detection needs of different seedling scenarios.

[0014] Optionally, the step of detecting mutation points in the original seedling environment data set and obtaining data mutation point detection results, and then correcting the original seedling environment data set based on the data mutation point detection results to obtain the target seedling environment data set, includes: determining the seedling environment baseline data in the seedling environment data monitoring and communication network; setting a time series segmented regression analysis mechanism; setting a weight analysis function based on the Bisquare function; and obtaining different time series weights through the time series segmented regression analysis mechanism and the weight analysis function.

[0015] This invention clarifies the baseline data for the seedling environment, providing an objective and accurate reference standard for subsequent data processing. This gives clear goals and directions for subsequent mutation point detection and correction, ensuring that the processed data conforms to the actual state of the seedling environment.

[0016] Optionally, the step of detecting mutation points in the original seedling environment data set and obtaining data mutation point detection results, and then correcting the original seedling environment data set based on the data mutation point detection results to obtain the target seedling environment data set, includes: correcting the mutation time data based on the mutation point detection results and the seedling environment baseline data to form new time series data; and obtaining the target seedling environment data set by combining a regression analysis function, the different time series weights, and the new time series data. This invention, by correcting the mutation time data based on mutation point detection results and seedling environment baseline data, can adjust abnormal data to values ​​that conform to normal trends, eliminate abnormal interference, and make the new time series data more coherent and stable, more realistically reflecting the changes in the seedling environment over time.

[0017] Optionally, the step of constructing a seedling environment parameter judgment system, obtaining evaluation judgment results for different seedling environment parameters based on the seedling environment target data set and the seedling environment parameter judgment system, and dynamically regulating the seedling environment based on the evaluation judgment results includes: setting a seedling environment parameter threshold judgment formula in the constructed seedling environment parameter judgment system; obtaining evaluation judgment results for different seedling environment parameters based on the seedling environment parameter threshold judgment formula and the seedling environment target data set; performing comprehensive calculation and analysis on the evaluation judgment results of the different seedling environment parameters, and obtaining a comprehensive evaluation and analysis result of the seedling environment; and dynamically regulating the seedling environment based on the comprehensive evaluation and analysis result and the evaluation judgment result.

[0018] The threshold judgment formula of this invention sets clear numerical limits for seedling environment parameters, transforming environmental requirements into specific and quantifiable indicators. This helps to ensure the objectivity and consistency of seedling environment assessment results and avoids errors and uncertainties caused by subjective judgment.

[0019] Secondly, to efficiently execute the intelligent analysis and dynamic control method for seedling environment provided by this invention, this invention also provides an intelligent analysis and dynamic control system for seedling environment. The system includes an input device, a processor, an output device, and a memory, wherein the input device, processor, output device, and memory are interconnected. The memory includes the intelligent analysis and dynamic control method for seedling environment as described in the first aspect of this invention. The memory stores a computer program, which includes program instructions. The processor is configured to call the program instructions. The intelligent analysis and dynamic control system for seedling environment provided by this invention has a compact structure, strong applicability, and greatly improves operating efficiency. Attached Figure Description

[0020] Figure 1 This is a flowchart of the intelligent analysis and dynamic control method for the seedling environment of the present invention;

[0021] Figure 2 This is a schematic diagram illustrating the detection and determination of mutation points in the original data set of the seedling environment in the intelligent analysis and dynamic control method for the seedling environment of the present invention.

[0022] Figure 3 This is a schematic diagram of the deflection effect curve of the target data set of the seedling environment in the intelligent analysis and dynamic control method of the seedling environment of the present invention;

[0023] Figure 4 This is a structural diagram of the intelligent analysis and dynamic control system for the seedling environment of the present invention. Detailed Implementation

[0024] Specific embodiments of the present invention will now be described in detail. It should be noted that the embodiments described herein are for illustrative purposes only and are not intended to limit the invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be apparent to those skilled in the art that these specific details are not necessary to practice the invention. In other instances, well-known circuits, software, or methods have not been specifically described to avoid obscuring the invention.

[0025] Throughout this specification, references to "an embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with that embodiment or example is included in at least one embodiment of the invention. Therefore, the phrases "in an embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily refer to the same embodiment or example. Furthermore, specific features, structures, or characteristics can be combined in one or more embodiments or examples in any suitable combination and / or sub-combination. Moreover, those skilled in the art will understand that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale.

[0026] Please see Figure 1 To optimize the data monitoring and communication pathways and ensure efficient transmission and effective collection of monitoring information, it is necessary to detect and analyze sudden changes in network data to enhance data reliability and accuracy. Furthermore, to evaluate and assess different seedling environment parameters and analyze the intrinsic relationships and influence mechanisms between these parameters, dynamic control of the seedling environment can be achieved to fully meet the growth and development needs of different seedlings and promote the intelligent transformation of agricultural seedling technology. This invention provides a method for intelligent analysis and dynamic control of the seedling environment, comprising the following steps:

[0027] S1. Establish a communication network path optimization method. This method iteratively optimizes the path of the seedling environment data monitoring and communication network, resulting in a path-optimized seedling environment data monitoring and communication network. The specific setup steps and implementation details are as follows:

[0028] First, it is necessary to introduce ant colony optimization algorithms and monitor the operational characteristics of communication networks, and then combine these algorithms to construct a communication network path optimization method.

[0029] Various sensors were scientifically and rationally deployed in advance within the seedling area, mainly including temperature sensors, humidity sensors, and light sensors. Concentration sensors and other components are strategically placed to ensure comprehensive and accurate collection of various parameters related to the seedling environment.

[0030] Based on the aforementioned different types of sensors, the monitoring and communication network can acquire real-time data on temperature, humidity, light intensity, and other parameters in the seedling environment. Key parameters such as concentration can be combined with meteorological data to comprehensively and accurately grasp the real-time status of the seedling environment. Simultaneously, the network connects to weather stations and online meteorological data platforms to obtain real-time meteorological information about the seedling environment, such as temperature, humidity, light intensity, and wind speed. This meteorological information will serve as an important reference for subsequent seedling environment control. All the aforementioned sensors and meteorological data acquisition equipment will transmit the collected seedling environment data to the central control system of the seedling environment data monitoring and communication network at pre-set time intervals.

[0031] However, some problems exist in the process of transmitting massive amounts of seedling environment data through the seedling environment data monitoring and communication network. The instantaneous queue length of the transmission within the network fluctuates frequently. This phenomenon not only prolongs the waiting time of data packets in the network and increases network latency, but also easily causes network congestion, leading to the loss of seedling environment data packets, thereby affecting the reliability and stability of the seedling environment data monitoring and communication network.

[0032] In a big data environment, the dynamic and uncertain nature of big data transmission processes exacerbates the complexity and severity of network congestion. Therefore, this embodiment presents an efficient and intelligent congestion optimization control method, which is of great significance for improving the transmission performance of seedling environment data monitoring and communication networks in a big data environment.

[0033] Based on the above, this embodiment introduces an improved ant colony algorithm to identify the congestion status of the seedling environment data monitoring and communication network, and makes targeted improvements to it. Combining the characteristics of the seedling environment data monitoring and communication network, a congestion identification method based on the time delay matrix is ​​constructed.

[0034] The first step involves monitoring seedling environment data and using the communication network to obtain network transmission latency, network queuing latency, and processing latency.

[0035] Based on the transmission delay that can be clearly obtained in the monitoring and communication network ( Queuing delay ) and processing latency ( Transmission latency represents the delay time of a fixed link; queuing latency reflects the delay caused by dynamic congestion; and processing latency refers to the time consumed by network nodes to process data. In particular, the processing latency indicator can further reflect the impact of the load status of different nodes in the network on path selection. The above network latency information is highly applicable in application scenarios such as multi-sensor environments and data transmission.

[0036] Next, appropriate weighting coefficients need to be assigned to different network latency levels. In this example, the priority of different network latency levels can be adjusted according to the seedling environment. For network latency data with high real-time requirements, the weighting coefficients can be adjusted specifically, i.e., the weighting coefficients... These represent transmission delays ( ) Queuing delay ) and processing latency ( The weighting coefficients can satisfy the priority requirements of data with different network latency. Furthermore, taking actual data types as an example, for real-time data, such as... Concentration data can increase The value of this can be increased, thus reducing the weight of transmission delay in the overall analysis; while for periodic data, such as soil pH data, the weight can be increased. The value is set to tolerate relatively long processing latency.

[0037] The second step involves setting up a network latency evaluation function model in the communication network path optimization method based on network transmission latency, network queuing latency, and processing latency.

[0038] The time delay evaluation function constructed in the seedling environment data monitoring and communication network follows a specific mathematical relationship, and its specific calculation formula is as follows:

[0039]

[0040] in, This indicates the path in the seedling environment data monitoring and communication network. The latency assessment results express The corresponding weighting coefficients, This indicates the transmission latency in the seedling environment data monitoring and communication network. express The corresponding weighting coefficients, This indicates the queuing delay in the seedling environment data monitoring and communication network. express The corresponding weighting coefficients, This indicates the processing latency in the seedling environment data monitoring and communication network.

[0041] Transmission latency reflects the time it takes for data to propagate through a fixed link and is a fundamental component of network latency; queuing latency reflects the delay caused by data waiting to be processed at network nodes, and it is closely related to network congestion and is a dynamically changing latency factor; processing latency represents the time required for network nodes to process data, and the load of different nodes will lead to differences in processing latency.

[0042] The aforementioned latency evaluation function model enables a comprehensive analysis of the impact of transmission latency, queuing latency, and processing latency on different path latency in the seedling environment data monitoring and communication network, thereby providing strong support for subsequent communication network path optimization.

[0043] The third step is to set the local pheromone update expression in the communication network path optimization method based on the network latency evaluation function model.

[0044] After completing the construction of the network latency evaluation function model, the next step of the communication network path optimization method is to set the local pheromone update expression based on the latency evaluation function model. The above steps guide the ants in the ant colony algorithm to choose paths with low latency and good performance by reasonably updating the pheromone concentration on the path, thereby gradually approaching the optimal path of the communication network.

[0045] In the context of seedling environment data monitoring and communication networks, the above local pheromone update expression follows a specific mathematical relationship, specifically satisfying the following relationship:

[0046]

[0047] in, express Time Path pheromone concentration, Indicates the initial pheromone residue level. express Time Path pheromone concentration, This indicates the initial pheromone concentration. Indicates the congestion penalty factor. This indicates the path in the seedling environment data monitoring and communication network. The latency assessment results.

[0048] The pheromone concentration mentioned above is an important basis for guiding ants to choose paths in the ant colony algorithm, and its level reflects the quality of the path.

[0049] The initial pheromone residue value range is: This parameter is mainly used to control the evaporation rate of pheromones, by adjusting... The size of the pheromone can balance the retention and evaporation of pheromones, avoiding excessive accumulation or rapid disappearance of pheromones, thereby ensuring the stability and effectiveness of the algorithm.

[0050] The pheromone concentration on different paths at different times reflects the selection and performance of different paths in the previous time step, providing a basic starting point for pheromone updates.

[0051] The congestion penalty factor is an important adjustment parameter.

[0052] Exponential decay term It plays a crucial role in the entire expression, enabling the imposition of penalties on high-latency paths. That is, when the path... Latency assessment results When the value is small, it means the path is clear. The pheromone increase is close to The pheromones along the path will increase relatively steadily; while when A larger value indicates path congestion. It will decay rapidly, and the increase in pheromones will decrease significantly. If The value is large enough that the pheromone increment can even approach 0, thus effectively suppressing ants from choosing congested links.

[0053] The aforementioned local pheromone update expression fully utilizes the reciprocal of pheromone increment and path delay, ensuring that paths with lower delays experience faster pheromone growth, thus attracting more ants to choose those paths. As the algorithm iterates, ants gradually concentrate on the optimal path, accelerating the algorithm's convergence speed and enabling more efficient discovery of the optimal path within the communication network. This meets the requirements of seedling environment data monitoring and communication networks for efficient and reliable data transmission.

[0054] The fourth step involves setting a global pheromone update expression in the communication network path optimization method, incorporating the local pheromone update expression.

[0055] After setting the local pheromone update expression, in order to further optimize the communication network path, it is necessary to set the global pheromone update expression in combination with the local pheromone update situation. The above global pheromone update aims to enhance the attractiveness of the optimal path from the overall level, while avoiding abnormal accumulation of pheromones due to network congestion, thereby guiding the ant algorithm to search for the global optimal path more efficiently.

[0056] In the scenario of path optimization for seedling environment data monitoring and communication networks, the update of global pheromones follows a specific mathematical relationship, the specific expression of which is as follows:

[0057]

[0058] in, Indicates in Time Path Global pheromone concentration on Indicates pheromone residue level, express Pheromone concentration values ​​at any given time Indicates the congestion penalty factor. This represents the shortest path delay that can be obtained in each iteration of the search.

[0059] The global pheromone concentration mentioned above reflects the overall performance of the path throughout the search process and is a key basis for guiding ants to make global path selections.

[0060] The range of values ​​for the congestion penalty factor is: It plays an important regulatory role in global pheromone updates.

[0061] Exponential decay term The introduction of this feature helps to address frequent network congestion. When the shortest path delay is obtained in each loop search... When the threshold is exceeded, it indicates that there may be a network congestion problem. Will follow The pheromone decays rapidly due to its effect, thereby enhancing the decay rate of pheromones and preventing excessive accumulation of pheromones that could cause the path to be locked on a congested path. This allows the algorithm to escape local optima and continue searching for better paths.

[0062] It represents the latency of the optimal path found during the current search process. In the example, it will be... By introducing a global pheromone update expression, the pheromone update becomes closely related to the performance of the optimal path. The optimal path (with the shortest latency) will receive more pheromone increments, thereby attracting more ants to choose this path and accelerating the algorithm to converge to the globally optimal path.

[0063] By combining the global pheromone update expression with the local pheromone update, the pheromone concentration on the path can be dynamically adjusted at both the local and global levels. This guides the ant colony algorithm to search for the optimal path more efficiently in the communication network, meeting the requirements of seedling environment data monitoring and communication networks for efficient and reliable data transmission.

[0064] In an optional embodiment, the above-described communication network path optimization method is used to perform iterative path optimization for the seedling environment data monitoring and communication network, ultimately obtaining the optimized network. The specific implementation process is as follows:

[0065] This study utilizes an improved ant colony algorithm to simulate ant search behavior and construct and optimize paths. Based on simulated ant search behavior within a seedling environment data monitoring and communication network, a path from the starting point to the destination is gradually built and optimized. During this process, the pheromone information output from local and global pheromone update expressions is fully utilized to guide ants and encourage them to choose low-latency paths. A detailed comparison between the optimal path set and the original paths is then performed. This comparative analysis accurately and effectively identifies congested areas within the seedling environment data monitoring and communication network, providing direction for subsequent network path optimization.

[0066] Based on the communication network path optimization method, key indicators and node settings are clearly defined. This method has a powerful optimization capability, enabling it to efficiently find the optimal path in complex seedling environment data monitoring and communication networks. In the network environment, each network node is considered a potential path point, and latency is used as the core indicator for evaluating path performance. The total latency of any path encompasses multiple aspects, including propagation latency, transmission latency, queuing latency, and processing latency. Lower total latency indicates better path performance, meeting the requirements for efficient data transmission.

[0067] Virtual ants are deployed to explore paths using a communication network path optimization method. A certain number of virtual ants are deployed into the network, and these ants will explore based on the current seedling environment data monitoring and the actual state of the communication network, i.e., the total latency. During their movement from the starting point to the destination, each ant releases pheromones. The presence of pheromones has a significant impact on the path selection of subsequent ants, making them more inclined to choose paths that have been proven to be low-latency by preceding ants. This forms a positive feedback mechanism that can accelerate the optimization and updating of the optimal path.

[0068] Path convergence is achieved through multiple iterations based on a communication network path optimization method. Through continuous iterations, the entire ant colony gradually converges to an optimal path. In this process, the original heuristic function is modified, shifting the objective from finding the shortest path to finding the shortest delay path. This modification not only simplifies the computation and improves the algorithm's efficiency but also constructs a more efficient improved ant colony algorithm, making it better suited to the actual needs of seedling environment data monitoring and communication networks.

[0069] Finally, path iteration optimization was completed. Based on the above communication network path optimization method and the correlation calculation expression, a series of path iteration optimization operations were performed to obtain the optimized seedling environment data monitoring and communication network. The optimized network can effectively reduce data transmission latency and improve network transmission efficiency, providing a strong guarantee for real-time and accurate monitoring of seedling environment data.

[0070] S2. Based on the optimized seedling environment data monitoring and communication network described above, the original seedling environment data set is obtained. The specific steps and implementation details are as follows:

[0071] First, the path selection conditions of different paths in the seedling environment data monitoring and communication network are analyzed using a network latency evaluation function model.

[0072] In the context of multi-source data on the seedling environment, this embodiment will Virtual ants are deployed into the seedling environment data monitoring and communication network. An improved ant colony algorithm is used to search for a specified network termination node within the total delay matrix of the network in which the ants reside. To complete the search task comprehensively and efficiently, the total number of ants needs to be adjusted. Perform traversal processing.

[0073] The first [project] was carried out in the seedling environment data monitoring and communication network. This is the second iteration, and the maximum number of iterations is set to [number]. The method involves several key parameters during its execution, among which the pheromone factor is used. In other words, the heuristic factor is used This indicates that the congestion penalty factor is used This indicates that, based on the content of this embodiment, considering that different types of seedling environment data have different priorities, separate settings are provided. express The corresponding weighting coefficients, express The corresponding weighting coefficients, express The corresponding weighting coefficients.

[0074] Based on the above settings and combined with the latency evaluation function in the seedling environment data monitoring and communication network, The time delay matrix in the seedling environment data monitoring and communication network can be further obtained through the aforementioned time delay evaluation function. Its expression is , This represents the time delay matrix of the seedling environment data monitoring and communication network. This indicates the path in the seedling environment data monitoring and communication network. The latency assessment results provide quantitative data support for subsequent path selection and optimization.

[0075] The path selection process needs to follow preset conditions, which specifically include a loop control mechanism and ant dispatch conditions.

[0076] Loop control mechanism; To ensure the method can perform a sufficient search within a reasonable range, a loop control mechanism is set up in the embodiment. If the current loop count is... Less than the maximum number of loops ,Right now Then execute The operation increments the loop count by 1 and proceeds to the next loop, continuing the search for the optimal path in the network; if the current loop count is... The maximum number of loops has been reached or exceeded. ,Right now If the loop terminates, it is considered that the relevant algorithm has completed a sufficient search and can output the optimal path found so far.

[0077] Ant dispatch conditions: In each round of the loop, ants need to be dispatched sequentially to perform pathfinding. If the current ant index... Less than the total number of ants ,Right now Then execute The operation increments the ant index by 1 and sends the next ant into the network to explore paths; if the current ant index... The total number of ants has been reached or exceeded. ,Right now If the condition is met, it indicates that all ants have completed the path search task in this round of the cycle. At this point, we can proceed to the global pheromone update step. Based on the pheromone left behind by the ants during their search, we can globally update the pheromones in the network to guide subsequent ants to search for the optimal path more effectively.

[0078] Next, path selection conditions are introduced, and network path inspection results are obtained by combining the path selection conditions and the path selection conditions of different paths.

[0079] In the ant colony algorithm, the probability of ant k migrating from node i to node j is... The following formula must be satisfied:

[0080]

[0081] in, Ants From node Migrate to The probability, express Pheromone concentration values ​​at any given time This indicates the path in the seedling environment data monitoring and communication network. The latency assessment results and These represent different nodes in the seedling environment data monitoring and communication network. Represents pheromone factor, Indicates the heuristic factor. This represents the set of possible paths for ant k to migrate from node i to node j.

[0082] The pheromone factor is mainly used to regulate the degree of influence of pheromones on ant path selection.

[0083] Heuristic factors are used to measure the guiding effect of latency assessment results on ant path selection.

[0084] The set of optional paths is the set of possible paths that ant k can take from node i to node j.

[0085] During the ant search process, it is necessary to check in real time whether the ant has reached the termination node. If the ant successfully reaches the termination node, it means that the ant has completed a complete path search. At this time, the path parameters need to be updated and a local pheromone update needs to be performed to record the performance of the path in the current search process. If the ant has not reached the termination node, it is guided to continue exploring along the path in the network.

[0086] Then, based on the network path inspection results, the latency evaluation results of different paths, and the local pheromone update expression, the local pheromone in the seedling environment data monitoring and communication network is updated, and the local pheromone update results are obtained.

[0087] The local pheromone update expression in the embodiment To perform a local pheromone update, the execution flow of the above local pheromone update expression satisfies the following code:

[0088] The following is a code example that satisfies the local pheromone update process:

[0089] def update_local_pheromone(t_ij, delta_t, forall_it, phi0, lambda):

[0090] evaporation = (1 - phi0) * t_ij

[0091] penalty = np.exp(-lambda * forall_it)

[0092] deposit = phi0 * (penalty / forall_it)

[0093] return evaporation + deposit

[0094] After completing the local pheromone update, you can return to continue sending ants for the next round of pathfinding.

[0095] Then, the global pheromone update result can be obtained through the local pheromone update result and the global pheromone update expression, so as to optimize the pheromone distribution in the network from the overall level.

[0096] The global pheromone update steps are as follows: First, compare the path delays of all ants, find the shortest path, and update the optimal path. The aforementioned optimal path represents the best-performing path found during the current search process, with the lowest latency. Then, based on the global pheromone update expression... Perform a global pheromone update.

[0097] After completing the global pheromone update, return to start the next round of the loop and continue sending ants to perform pathfinding. This indicates that all ants in this loop have been traversed, and the search process enters the next stage.

[0098] Finally, based on the global pheromone update results, the original data set of the seedling environment of the seedling environment monitoring and communication network is obtained.

[0099] In this embodiment, based on the global pheromone update results, the final set of raw seedling environment data for the seedling environment monitoring and communication network is obtained. The final output results include, but are not limited to, the optimal path and its total latency, and mark congested areas, i.e., links whose latency exceeds the threshold.

[0100] Based on the optimized seedling environment data monitoring and communication network, the seedling environment can be monitored and collected in real time efficiently and accurately, thereby obtaining a comprehensive and reliable set of raw seedling environment data, providing information for subsequent seedling environment analysis and decision management.

[0101] S3. Detect mutation points in the original seedling environment dataset and obtain the mutation point detection results. Based on the mutation point detection results, perform correction processing on the original seedling environment dataset to obtain the target seedling environment dataset. The specific implementation details are as follows:

[0102] After acquiring the original data set of the seedling environment, in order to deeply explore the data information and accurately grasp the dynamic changes of the seedling environment, the embodiment further used mutation point detection and baseline correction methods to systematically analyze the original data set of the seedling environment. The above process mainly focuses on the detection and analysis of time series change trends and mutation points, aiming to eliminate trend changes and abnormal fluctuations in the original data, thereby obtaining a target data set that can accurately reflect the real state of the seedling environment and effectively improve the reliability of the data.

[0103] First, the parameters in the mutation point detection process are defined based on the original data set of the seedling environment, and the detection parameter definition information is obtained.

[0104] Before detecting mutation points, relevant parameters need to be clearly defined based on the original dataset of the seedling environment after path optimization. This original dataset contains a total of [data missing]. There are time series samples, each sample has There are 1 time points, and different time series samples are denoted as _____. .

[0105] A standardized statistic was defined for each time series sample. The relevant calculation formulas are as follows:

[0106]

[0107] in, Standardized statistics representing different time series samples This represents the rank sum of the cumulative counts of samples from different time series. express The average value, express The variance.

[0108] The cumulative rank sum of different time series samples reflects the time series at the nodes The cumulative trend of change at that location.

[0109] At the same time, presidential measurement was defined. The calculation formula is as follows:

[0110]

[0111] in, This represents the sum of the defined statistics for different time series samples.

[0112] Then, by combining the information defined by the detection parameters, the time series reverse processing result of the original data set of the seedling environment is obtained.

[0113] To analyze time series data more comprehensively, it is necessary to analyze different time series samples. By performing reverse order processing, we can obtain the reverse order result, which satisfies the following relationship: .

[0114] The above reverse order processing flow satisfies the following conditions:

[0115]

[0116] in, Representing different time series samples, express The result of the reverse processing.

[0117] Next, a critical value for the seedling environment data is set, and the mutation point detection results of the original seedling environment data set are obtained based on the time series reverse processing results and the critical value of the seedling environment data.

[0118] Setting critical values ​​for seedling environment data includes setting auxiliary statistical quantities.

[0119] Set auxiliary statistics The following relationship must be satisfied:

[0120]

[0121] in, Indicates auxiliary statistics, Standardized statistics representing different time series samples express The starting point, Represents a time series.

[0122] The above auxiliary statistic series defines a specific starting point. When processing time series data, from arrive Auxiliary statistics were gradually constructed, providing a reference standard for the calculation and comparison of subsequent auxiliary statistics.

[0123] Setting critical values ​​for seedling environment data includes setting critical values.

[0124] At the significance level Below, the critical value is determined using the normal distribution. .

[0125] like and If the time series shows an upward trend, then the time series shows an upward trend; conversely, if the time series shows a downward trend, then the time series shows an upward trend.

[0126] like or If so, then the time series shows a significant trend change.

[0127] Mutation point location determination.

[0128] Standardized statistics for different time series samples and auxiliary statistics When time series curves intersect, the time node corresponding to the intersection point is the mutation moment, which is the moment when the time series sample in the original data set of the seedling environment undergoes a mutation.

[0129] This implementation employed the Manner-Kendall method for nonparametric testing, performing full-time, one-by-one detection of potential mutation points in the entire seedling environment raw data set. Specifically, following the aforementioned method, at a 95% significance level, the potential mutation points in the seedling environment raw data set were calculated. and The intersection of two statistical time series is used to determine the time point when a mutation occurs.

[0130] In the original data set of seedling environment and Please see the statistical value diagram. Figure 2 ,from Figure 2 It can be seen that there is a significant abrupt change in the processed monitoring data signal between 15:06 and 15:08, indicating that there is a data mutation point.

[0131] Meanwhile, the embodiments require determining the baseline data for the seedling environment within the seedling environment data monitoring and communication network. These embodiments determine the baseline data for the seedling environment within the seedling environment data monitoring and communication network to provide a benchmark reference for subsequent data analysis and processing.

[0132] Piecewise robust regression analysis mechanism.

[0133] After completing the analysis of all mutation points in the original data set of the seedling environment, regression analysis was performed on each segment of data using iterative weighted least squares (IRLS), with the mutation points as the segment points. That is, using the location of the mutation point as the segment point, regression analysis was performed on the monitoring data within each segment point using iterative weighted least squares to estimate the regression parameters between each segment point.

[0134] Weight analysis function settings.

[0135] To ensure the robustness of the regression, the Bisquare function is used to assign appropriate weights during the regression analysis, where the weights satisfy the following relationship:

[0136]

[0137] in, Indicates about residuals The weight function, Indicates the adjustment parameter. Represents the residual. This represents the critical value.

[0138] The residual refers to the difference between the observed value and the model prediction, which can reflect the degree of deviation between the data point and the regression model.

[0139] The adjustment parameter is a pre-set constant, mainly used to control the rate and shape of change of the weight function. Its value affects the weight distribution of the weight function under different residual values, thus affecting the results of robust regression. At that time, weight A value of 0 means that data points with residual absolute values ​​exceeding this critical value are not assigned weights in the regression analysis; that is, the impact of these points on the regression model is not considered. At that time, the weights are based on The rules are used for calculation.

[0140] Each data segment is based on a fitted linear model to obtain a segmented baseline. Specifically, a linear regression equation is established between each segment point based on the regression parameters between all mutation points. This equation is then plotted synchronously with the time-history curve of the original seedling environment data set, allowing for a direct observation of the baseline's effectiveness. Analysis shows that for each mutation point, the baseline determined by robust regression is consistent and corresponds to the monitoring time-history data. Different time-series weights can be obtained through the aforementioned time-series segmented regression analysis mechanism and weighting analysis function.

[0141] The weights of different time series can be quickly obtained using the time series segmented regression analysis mechanism and weight analysis function described above.

[0142] Next, based on the above mutation point detection results and seedling environment baseline data, the mutation time data were corrected to form new time series data.

[0143] After the mutation point detection and identification at the significance level are completed, the data at the mutation point is corrected based on the above mutation point determination results. In this embodiment, the data at the mutation time is uniformly corrected to the data at the previous time to form a new time series. The specific formula is as follows:

[0144]

[0145] Based on this, subsequent data mutation points are corrected and adjusted accordingly.

[0146] Finally, by combining regression analysis functions, different time series weights, and new time series data, a target data set for the seedling environment was obtained.

[0147] Subtracting the baseline data obtained from robust regression from the original seedling environment data set yields the target seedling environment data set, which satisfies the following relationship:

[0148]

[0149] in, This represents the target data set for the seedling environment. Indicating time series samples Data at specific points in time, Indicates the first The slope of the segment data, Indicates the first The intercept of the segment data.

[0150] Furthermore, the embodiment includes a schematic diagram of the deflection effect curve of the target data set of the seedling environment; please refer to [link / reference] for details. Figure 3 ,from Figure 3 It can be seen that the target data set of the seedling environment can be obtained better after baseline correction, which provides a better data foundation for monitoring, evaluating and analyzing the effects of key parameters in the seedling environment, and provides accurate and objective data basis.

[0151] This embodiment also includes the following content regarding the accuracy verification of the target dataset:

[0152] To further verify the accuracy of the seedling environment target dataset after mutation point detection and correction, the Manner-Kendall nonparametric test was performed again on the seedling environment target dataset. Analysis revealed that the seedling environment target dataset... and Both statistics are within the 95% confidence level, indicating that the target data set for the seedling environment no longer shows significant trend changes or abrupt changes.

[0153] By verifying the accuracy of the target data set and conducting non-parametric tests, the accuracy of the seedling environment target data set is ensured, effectively avoiding erroneous decisions and management adjustments due to inaccurate data. Furthermore, when dynamically controlling the seedling environment, the target data set facilitates the development of more scientific and rational management strategies. Environmental parameters such as temperature, humidity, and light can be precisely adjusted according to the seedling environment conditions, providing a more suitable growth environment for seedlings and thus improving the success rate and quality of seedling cultivation.

[0154] S4. Construct a seedling environment parameter judgment system. Based on the seedling environment target data set and the seedling environment parameter judgment system, obtain the evaluation and judgment results of different seedling environment parameters. Based on the evaluation and judgment results, dynamically regulate the seedling environment. The specific implementation content is as follows:

[0155] First, a threshold judgment formula for seedling environment parameters was set in the construction of the seedling environment parameter judgment system.

[0156] During the seedling cultivation process, different varieties of seedlings have unique growth characteristics and different sensitivities to environmental parameters. They have specific suitable ranges for various seedling environmental parameters. In order to create the most suitable growth environment for seedlings and improve seedling quality and efficiency, it is necessary to set the optimal parameter range for the growth of each seedling variety under different seedling environmental parameters.

[0157] Based on the target data set for the seedling environment, the seedling environment parameters in this embodiment are as follows:

[0158] concentration: It is an important raw material for plants to carry out photosynthesis, and different seedling varieties require it at different growth stages. The required concentration varies. Some rapidly growing seedlings may require relatively higher concentrations during periods of peak photosynthesis. Concentration is used to promote the synthesis of organic matter.

[0159] Humidity: Humidity directly affects the water balance and physiological metabolism of seedlings. Excessive humidity can lead to seedling diseases, while excessively low humidity can cause seedlings to lose water, affecting their normal growth. Different seedling varieties have different tolerance ranges for humidity. For example, some tropical plants prefer relatively humid conditions, while some drought-tolerant plants can grow in lower humidity environments.

[0160] Temperature: Temperature is one of the important environmental factors affecting seedling growth and development. Different seedling varieties have different temperature tolerance ranges; some seedlings are suitable for growth in warm environments, while others can survive in colder or hotter environments. At the same time, temperature also affects the physiological processes of seedlings, such as photosynthesis and respiration.

[0161] Light intensity: Light is the energy source for plants to carry out photosynthesis, and different seedling varieties have significantly different light intensity requirements. Sun-loving plants need strong light to carry out efficient photosynthesis, while shade-loving plants are suitable for growing under weak light conditions; excessive light may damage them.

[0162] Nitrogen, phosphorus, and potassium content: Nitrogen, phosphorus, and potassium are essential nutrients for plant growth, promoting root development, enhancing stress resistance, and optimizing growth structure. Nitrogen deficiency will result in slow plant growth, stunted growth, and in severe cases, yellowing of leaves. Excessive nitrogen may lead to excessive vegetative growth. Phosphorus deficiency results in stunted growth, stunted growth, and poor root development. Potassium deficiency causes leaves to wither and plants to easily fall over.

[0163] Soil pH: Soil pH affects the availability of nutrients and the activity of microorganisms in the soil, thus influencing seedlings' absorption and utilization of nutrients. Different seedling varieties have different tolerance ranges for soil pH. For example, some acid-loving soil plants are suitable for growing in soils with lower pH values, while alkaline soil plants are more tolerant of higher pH values.

[0164] Setting the threshold judgment formula for seedling environment parameters:

[0165] To monitor in real time whether different seedling environment parameters are within the optimal seedling range, so as to take timely seedling environment control measures, the seedling environment parameter threshold judgment formula is set to satisfy the following relationship:

[0166]

[0167] in, This represents the formula for determining the threshold values ​​of seedling environment parameters. Indicates the values ​​of seedling environment parameters. This indicates the lower limit of the seedling environment parameters. This indicates the upper limit of the seedling environment parameters.

[0168] when When this occurs, it indicates that the current seedling environment parameters have exceeded the set optimal threshold range, and the current seedling environment conditions will have an adverse effect on the growth of the seedlings, requiring timely adjustment of the environmental parameters.

[0169] when When the current environmental parameters are within the optimal threshold range, it indicates that the seedlings are growing and developing normally and that the current environmental conditions can be maintained.

[0170] By setting the optimal range of seedling environment parameters for different seedling varieties and applying the threshold judgment formula, we can provide a scientific basis for the intelligent analysis and dynamic control of the seedling environment, which will help to achieve scientific management and effective control of the seedling environment, thereby improving the success rate and quality of seedling cultivation.

[0171] Then, based on the seedling environment parameter threshold judgment formula and the seedling environment target data set, the evaluation judgment results of different seedling environment parameters are obtained.

[0172] In the process of seedling environment management, in order to accurately control the seedling growth environment, the seedling environment parameter threshold judgment formula and seedling environment target data set are used to conduct a comprehensive evaluation of different seedling environment parameters, so as to obtain the evaluation judgment results of different seedling environment parameters.

[0173] The following example uses a certain type of seedling to illustrate the evaluation process for different seedling environmental parameters. Combining seedling growth characteristics and the sensitivity of environmental parameters, the optimal threshold range for different seedling environmental parameters, and the evaluation and judgment process satisfying the following relationship:

[0174] best_params = {

[0175] 'CO2_concentration': {'lower':xxx, 'upper': xxx}, # ppm

[0176] 'humidity': {'lower': xxx, 'upper': xxx}, # %

[0177] 'temperature': {'lower': xxx, 'upper': xxx}, # °C

[0178] 'light_intensity': {'lower': xxx, 'upper': xxx}, # lux

[0179] 'soil_pH': {'lower': xxx, 'upper': xxx},

[0180] The formula for determining threshold values ​​for seedling environment parameters is used to assess whether the current seedling environment parameters meet safe range conditions. If a parameter exceeds the threshold, it will be automatically flagged, and the process will proceed to the next stage of control and decision-making.

[0181] In this embodiment, based on the seedling environment parameter threshold judgment formula, each parameter in the seedling environment target data set is compared with the pre-set optimal parameter range one by one. The threshold comparison method is used. For any parameter, if the current parameter value is less than the lower limit of the optimal parameter range or greater than the upper limit of the optimal parameter range, it is determined that the parameter exceeds the threshold. The system will automatically mark the parameters that exceed the threshold and include them in the next control decision stage.

[0182] If the current temperature value is less than best_params['temperature']['lower'] or greater than best_params['temperature']['upper'], then the temperature parameter is determined to be outside the threshold range.

[0183] Next, the evaluation results of different seedling environment parameters were comprehensively calculated and analyzed to obtain the comprehensive evaluation and analysis results of the seedling environment.

[0184] In addition to comparing each parameter individually, it is also necessary to consider the complex interrelationships and influences among the seedling environment parameters. In order to more comprehensively reflect the overall status of the seedling environment parameters, it is necessary to conduct a comprehensive evaluation of different seedling environment parameters. In this embodiment, a multi-parameter comprehensive evaluation method is adopted to integrate the comparison results of different seedling environment parameters to obtain a comprehensive evaluation index.

[0185] Suppose there are a total of There are several seedling environment parameters, and the weight of each seedling environment parameter satisfies the following relationship: Meanwhile, the membership degree of each seedling environment parameter is (This indicates the degree to which the current parameter value conforms to the optimal parameter range, where...) The calculation formulas for the above comprehensive evaluation indicators are as follows:

[0186]

[0187] in, This indicates the results of the comprehensive evaluation indicators. This represents the total number of environmental parameters for seedling cultivation. This indicates the weights of different seedling environment parameters. This indicates the membership degree of different seedling environment parameters.

[0188] The weights of different seedling environment parameters satisfy the following conditions:

[0189] weights = {

[0190] 'CO2_concentration': σCO2

[0191] 'humidity': σhumidity,

[0192] 'temperature': σtemperature

[0193] 'light_intensity': σlight_intensity

[0194] 'soil_pH': σsoil_pH

[0195] To calculate the comprehensive evaluation index, the following procedures must be followed:

[0196] membership_results = pd.DataFrame(index=df.index)

[0197] for param in best_params.keys():

[0198] lower = best_params[param]['lower']

[0199] upper = best_params[param]['upper']

[0200] membership_results[param] = df[param].apply(lambda x:calculate_membership(x, lower, upper))

[0201] comprehensive_evaluation = pd.Series(index=df.index)

[0202] for i in df.index:

[0203] z = 0

[0204] for param in best_params.keys():

[0205] z += weights[param] * membership_results.loc[i, param]

[0206] comprehensive_evaluation[i] = z

[0207] Finally, a comprehensive judgment is made and the results are output.

[0208] Comprehensive judgment rule setting: Based on the comparison and comprehensive evaluation results of seedling environment parameters one by one, the embodiment sets clear judgment rules to determine whether the parameter exceeds the threshold. That is, if the current value of a certain seedling environment parameter is not within the optimal parameter range, or the comprehensive evaluation index exceeds the preset threshold, the parameter is judged to exceed the threshold.

[0209] The following operational process will be used to make a comprehensive judgment and output the results:

[0210] comprehensive_threshold = xxx # Preset comprehensive evaluation index threshold

[0211] comprehensive_results = comprehensive_evaluation.apply(lambda x:1 if x < comprehensive_threshold else 0)

[0212] return

[0213] threshold_results, comprehensive_evaluation, comprehensive_results

[0214] The above evaluation system can comprehensively and accurately assess the status of seedling environment parameters, providing a reliable basis for subsequent seedling environment control and further realizing intelligent management of the seedling environment.

[0215] Finally, the seedling environment is dynamically regulated based on the comprehensive evaluation and analysis results and the evaluation judgment results.

[0216] After obtaining the comprehensive evaluation and analysis results and the assessment judgment results, in order to ensure that the seedlings are always in the most suitable growth environment, it is necessary to dynamically regulate the seedling environment based on the above results and target information. The specific regulation strategies and implementation steps are as follows:

[0217] I. Real-time parameter adjustment

[0218] Treatment of excessive environmental parameters in single seedling cultivation

[0219] When the assessment results show that a single seedling environment parameter exceeds the threshold range, the corresponding control mechanism should be triggered immediately.

[0220] Concentration exceeds limit: If If the concentration is below the lower limit of the optimal parameter range, it can be turned on. Supplemental devices to increase environmental [resources / resources]. Concentration; if If the concentration exceeds the upper limit, activate the ventilation system to increase air circulation and remove excess air. This reduces the concentration to a suitable range.

[0221] Humidity exceeding limits: When the humidity is too high, turn on the dehumidifier to reduce the ambient humidity; if the humidity is too low, use a humidifier to increase the moisture content in the air. At the same time, you can use a spray system to locally humidify the area around the seedlings to ensure that the humidity meets the growth needs of the seedlings.

[0222] Temperature exceeding limits: When the temperature is too low, the heating equipment will be activated to raise the ambient temperature; when the temperature is too high, the cooling equipment will be activated to lower the temperature and maintain a suitable temperature environment.

[0223] Excessive light intensity: When the light is too strong, the opening and closing degree of the shade curtain will be automatically adjusted to reduce the amount of light entering the seedling area; when the light is insufficient, artificial light sources such as LED plant growth lights will be turned on, and the light intensity and light time will also need to be adjusted according to the needs of different growth stages of the seedlings.

[0224] Treatment of multiple seedling environmental parameters exceeding limits

[0225] When multiple seedling environment parameters simultaneously exceed their threshold ranges, the system needs to comprehensively consider the interactions between these parameters and formulate a priority control strategy. If both temperature and humidity exceed their upper limits, temperature should be controlled first, as high temperatures accelerate moisture evaporation and further exacerbate humidity problems. While lowering the temperature, humidity should be adjusted appropriately to gradually restore both to their optimal ranges. When dealing with multiple parameters exceeding their limits, it is essential to ensure that control measures do not conflict, avoiding adjustments to a single parameter that could trigger larger fluctuations in other parameters.

[0226] II. Optimized Regulation Based on Comprehensive Evaluation Results

[0227] Comprehensive evaluation index and threshold comparison analysis

[0228] The comprehensive evaluation index is compared with the preset comprehensive evaluation index threshold. If the comprehensive evaluation index is lower than the threshold, it indicates that the overall seedling environment is poor, and there may be multiple parameters that, although not individually exceeding the threshold, have a combined effect on seedling growth. In this case, the membership degree of each parameter should be comprehensively analyzed to identify the key parameters that have a greater impact on the comprehensive evaluation index.

[0229] Targeted optimization and control measures should be implemented, and targeted optimization and control plans should be formulated based on the analysis results of key parameters. If the membership degree of light intensity is found to be low, significantly impacting the comprehensive evaluation indicators, the light duration can be appropriately adjusted, while fine-tuning can be made in conjunction with other parameters. During the implementation of optimization and control, a gradual adjustment method should be adopted to avoid causing stress to seedlings due to excessively large adjustments at once. After each adjustment, seedling environmental parameters and seedling growth should be continuously monitored, and control strategies should be adjusted promptly based on feedback information to ensure that the seedling environment is gradually optimized to its optimal state.

[0230] III. Continuous Monitoring and Feedback Adjustment of Dynamic Control

[0231] This method also establishes a real-time monitoring system to continuously monitor seedling environment parameters 24 hours a day. The relevant monitoring equipment features high precision, high stability, and rapid response, enabling timely and accurate acquisition of information on changes in environmental parameters. Simultaneously, sensor networks and wireless communication technologies are used to transmit monitoring data to the central control system in real time, allowing managers to monitor the dynamic changes in the seedling environment at any time.

[0232] Based on real-time monitoring data, the system can automatically compare and analyze the parameters with preset optimal ranges and comprehensive evaluation index thresholds. If parameters deviate from the normal range or comprehensive evaluation indicators are found to be abnormal, a feedback adjustment mechanism is immediately activated to dynamically adjust the seedling environment according to the aforementioned control strategies. During the adjustment process, new monitoring data can be continuously collected to evaluate the control effect, forming a closed-loop control system and achieving precise and dynamic management of the seedling environment.

[0233] Simultaneously, data recording and analysis are conducted. Detailed records are kept of each monitoring data point and control operation, establishing a comprehensive database. Historical data analysis allows for the summarization of seedling environmental parameter requirements at different seasons and growth stages, facilitating subsequent optimization of optimal parameter ranges and control strategies. Furthermore, data analysis techniques are used to predict environmental parameter trends, enabling proactive preventative control measures to further improve the stability and controllability of the seedling environment.

[0234] Through the above dynamic control measures, the seedling environment can be adjusted and optimized in a timely and effective manner based on the comprehensive evaluation and analysis results, providing a suitable growth environment for seedlings at all times, thereby improving the success rate and quality of seedling cultivation and realizing intelligent and scientific management of the seedling process.

[0235] Please see Figure 4 In an optional embodiment, to efficiently execute the intelligent analysis and dynamic control method for seedling environment provided by this invention, the present invention also provides an intelligent analysis and dynamic control system for seedling environment. The system includes a processor, an input device, an output device, and a memory, which are interconnected. The memory stores a computer program, which includes program instructions. The processor is configured to call the program instructions and execute the specific steps of the intelligent analysis and dynamic control method for seedling environment and related embodiments provided by this invention. The intelligent analysis and dynamic control system for seedling environment of this invention has a complete structure and is objectively stable.

[0236] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A method for intelligent analysis and dynamic control of seedling environment, characterized in that, The method includes: A communication network path optimization method is established, and the path of the seedling environment data monitoring and communication network is iteratively optimized using the communication network path optimization method to obtain the seedling environment data monitoring and communication network after path optimization. The original data set of the seedling environment is obtained based on the optimized seedling environment data monitoring and communication network described above; Mutation point detection is performed on the original data set of the seedling environment to obtain the data mutation point detection results. Based on the data mutation point detection results, the original data set of the seedling environment is corrected to obtain the target data set of the seedling environment. A seedling environment parameter judgment system is constructed. Based on the seedling environment target data set and the seedling environment parameter judgment system, the evaluation and judgment results of different seedling environment parameters are obtained. The seedling environment is dynamically regulated based on the evaluation and judgment results. The method for optimizing communication network paths includes: Introducing ant colony optimization algorithms and monitoring the operational characteristics of communication networks; A communication network path optimization method is constructed by combining the improved ant colony algorithm and the operational characteristics of the monitoring communication network. Based on seedling environment data monitoring and communication network, network transmission latency, network queuing latency, and processing latency are obtained; Based on the network transmission delay, the network queuing delay, and the processing delay, a network delay evaluation function model is set in the communication network path optimization method; Based on the network latency evaluation function model, a local pheromone update expression is set in the communication network path optimization method; In the context of seedling environment data monitoring and communication networks, the local pheromone update expression follows a specific mathematical relationship: ， in, express Time Path pheromone concentration, Indicates the initial pheromone residue level. express Time Path pheromone concentration, This indicates the initial pheromone concentration. Indicates the congestion penalty factor. This indicates the path in the seedling environment data monitoring and communication network. The latency assessment results; After completing the setting of the local pheromone update expression, the global pheromone update expression is set in the communication network path optimization method in conjunction with the local pheromone update expression; The global pheromone update expression enhances the attractiveness of the optimal path at the overall level, guiding the ant colony algorithm to search for the globally optimal path. In the path optimization scenario of seedling environment data monitoring and communication network, the global pheromone update expression is as follows: ， in, Indicates in Time Path Global pheromone concentration on Indicates pheromone residue level, express Pheromone concentration values ​​at any given time Indicates the congestion penalty factor. This represents the shortest path delay that can be obtained in each iteration of the search.

2. The intelligent analysis and dynamic control method for seedling environment according to claim 1, characterized in that, The method of using the communication network path optimization method to iteratively optimize the path of the seedling environment data monitoring and communication network, and to obtain the optimized seedling environment data monitoring and communication network, includes: The path iteration optimization of the seedling environment data monitoring and communication network is performed by combining the network latency evaluation function model, the local pheromone update expression, and the global pheromone update expression to obtain the path-optimized seedling environment data monitoring and communication network.

3. The intelligent analysis and dynamic control method for seedling environment according to claim 1, characterized in that, The seedling environment data set obtained by the seedling environment data monitoring and communication network optimized according to the path includes: The path selection conditions of different paths in the seedling environment data monitoring and communication network are analyzed using the network latency evaluation function model. By introducing path selection conditions and combining these conditions with the path selection conditions for different paths, network path inspection results are obtained. Based on the network path inspection results, the latency evaluation results of different paths, and the local pheromone update expression, the local pheromone in the seedling environment data monitoring and communication network is updated, and the local pheromone update results are obtained. The global pheromone update result is obtained by using the local pheromone update result and the local pheromone update expression; The original data set of the seedling environment of the seedling environment monitoring and communication network is obtained based on the global pheromone update results.

4. The intelligent analysis and dynamic control method for seedling environment according to claim 1, characterized in that, The process of detecting mutation points in the original seedling environment data set and obtaining data mutation point detection results, followed by correction processing of the original seedling environment data set based on the data mutation point detection results to obtain the target seedling environment data set, includes: Based on the original data set of the seedling environment, the parameters in the mutation point detection process are defined, and the detection parameter definition information is obtained; The time-series reverse processing result of the original seedling environment data set is obtained by combining the detection parameter definition information; A threshold value for the seedling environment data is set, and the mutation point detection result of the original seedling environment data set is obtained based on the reverse processing result of the time series and the threshold value of the seedling environment data.

5. The intelligent analysis and dynamic control method for seedling environment according to claim 4, characterized in that, The process of detecting mutation points in the original seedling environment data set and obtaining data mutation point detection results, followed by correction processing of the original seedling environment data set based on the data mutation point detection results to obtain the target seedling environment data set, includes: Determine the baseline data for the seedling environment in the seedling environment data monitoring and communication network; Set up a time series piecewise regression analysis mechanism; The weight analysis function is set based on the Bisquare function; Different time series weights are obtained through the time series segmented regression analysis mechanism and the weight analysis function.

6. The intelligent analysis and dynamic control method for seedling environment according to claim 5, characterized in that, The process of detecting mutation points in the original seedling environment data set and obtaining data mutation point detection results, followed by correction processing of the original seedling environment data set based on the data mutation point detection results to obtain the target seedling environment data set, includes: Based on the mutation point detection results and the seedling environment baseline data, the mutation time data are corrected to form new time series data; By combining the regression analysis function, the different time series weights, and the new time series data, a target data set for the seedling environment is obtained.

7. The intelligent analysis and dynamic control method for seedling environment according to claim 1, characterized in that, The construction of the seedling environment parameter judgment system, based on the seedling environment target data set and the seedling environment parameter judgment system, yields evaluation and judgment results for different seedling environment parameters, and dynamically regulates the seedling environment based on the evaluation and judgment results, including: In the constructed seedling environment parameter judgment system, a seedling environment parameter threshold judgment formula is set; Based on the threshold judgment formula for the seedling environment parameters and the target data set for the seedling environment, the evaluation and judgment results of different seedling environment parameters are obtained; The evaluation results of the different seedling environment parameters are comprehensively calculated and analyzed to obtain the comprehensive evaluation and analysis results of the seedling environment; The seedling environment is dynamically regulated based on the comprehensive evaluation and analysis results and the evaluation judgment results.

8. A seedling environment intelligent analysis and dynamic control system, characterized in that, The system includes a processor, an input device, an output device, and a memory, which are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to call the program instructions to execute the intelligent analysis and dynamic control method for seedling environment as described in any one of claims 1-7.

Images