Intelligent digital park management method and system based on ant colony algorithm

Abstract

The invention relates to a smart digital park management method based on an ant colony algorithm, and the method comprises the following steps: 110, obtaining the transmission data of a target park; 120, processing any source data in the transmission data through a pre-constructed redundancy elimination algorithm model to obtain optimized transmission data; wherein any source data refers to data of the same type acquired by the same sensor or data acquisition equipment; step 130, preprocessing the optimized transmission data to obtain to-be-analyzed data in a preset format; step 140, acquiring a specific task and a target of target park management; 150, according to a specific task and a target, processing is carried out based on the to-be-analyzed data through an ant colony algorithm engine, and an optimal solution is obtained; and step 160, responding to specific tasks and targets based on the optimal solution. According to the method, mass data of the park can be well handled, and the obtained management scheme can be more optimized and is closer to the solving requirements of actual problems.

Description

Technical Field

[0001] This invention relates to the field of smart park technology, and in particular to a smart digital park management method and system based on ant colony algorithm. Background Technology

[0002] A smart park is a modern industrial or residential cluster that integrates next-generation information technology with park management services. Its core is to achieve efficient operation, high-quality services and sustainable development of the park through digital and intelligent means.

[0003] Existing smart park management methods often involve collecting data through relevant data acquisition devices, then combining this data with preset judgment thresholds to determine corresponding events, or processing data according to preset classic algorithms based on specific park management tasks and objectives such as resource allocation, path planning, and equipment scheduling.

[0004] The above processing has the following problems: On the one hand, the "massive" multi-source heterogeneous park data contains a lot of redundant and noisy data. If it is processed directly, the computing power is obviously insufficient, and the server cannot handle park management affairs well. On the other hand, although existing classic algorithms are applied when managing the park, the algorithm optimization problem is not considered, and the resulting management solution has poor application effect. Summary of the Invention

[0005] The purpose of this invention is to at least address one of the shortcomings of the prior art and provide a smart digital park management method based on ant colony algorithm.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: Specifically, a smart digital park management method based on ant colony algorithm is proposed, including the following: Step 110: Obtain the transmission data of the target park; Step 120: For any source data in the transmitted data, the optimized transmitted data is obtained by processing it through a pre-built redundancy removal algorithm model; wherein, any source data refers to the same type of data collected by the same sensor or data acquisition device. Step 130: Preprocess the optimized transmission data to obtain data to be analyzed in a preset format; Step 140: Obtain the specific tasks and objectives for the management of the target park; Step 150: Based on the specific task and objective, the ant colony algorithm engine processes the data to be analyzed to obtain the optimal solution; Step 160: Respond to specific tasks and objectives based on the optimal solution.

[0007] Furthermore, specifically, the process of obtaining optimized transmission data by processing any source data in the transmitted data using a pre-built redundancy removal algorithm model includes: For any source data in the transmitted data, let the transmitted dataset be [SJ_1, SJ_2, ..., SJ_N], with a preset scale value M, independent variable i and independent variable j, and i and j initialized to 1; Step 121: Define SJ_i as the transmitted data to be judged for the i-th sample, and the variable c, the value range of c is [1, i]; Step 122: Determine the relationship between i and M. If i is less than M, calculate the average value from SJ_1 to SJ_i as the threshold. If i is not less than M, use the value of SJ_c+1 as the threshold. Step 123: Perform redundancy removal based on the judgment threshold Threshold; Step 124: When j ≤ M, increment the value of j by 1 and proceed to step 121; when j > M, set j = 1 and proceed to step 125. Step 125: When c ≤ i, increment the value of c by M and proceed to step 121; when c > i, proceed to step 126. Step 126: Determine if i is equal to N. If yes, output the processed dataset as the optimized transmission data of the current source data. Otherwise, increment i by 1 and proceed to step 121.

[0008] Furthermore, specifically, the process of redundancy removal based on the judgment threshold (Threshold) includes: Calculate the upper limit of change value SJ_max and the lower limit of change value SJ_min, where, ; ; In the formula, This indicates the operation of retrieving the median value from the data. This indicates taking the maximum value of the data. This indicates taking the minimum value of the data; calculate The difference between the first difference and the threshold is denoted as the first difference. Calculate... The difference from Threshold is denoted as the second difference. If there is only one negative value between the first and second differences, calculate them separately. SJ_c+1, and The absolute values ​​of the differences are P, P1, and P2, and only the data corresponding to the intermediate value among P, P1, and P2 is retained; If either the first difference or the second difference contains two negative values ​​or zero negative values, calculate separately. SJ_c+1, and The numerical differences are obtained by taking the absolute values ​​of the differences, namely P', P1', and P2'. At this point, only the data corresponding to the maximum value among P', P1', and P2' is retained.

[0009] Furthermore, specifically, the preprocessing includes removing noise from the optimized transmitted data, and then uniformly converting data of different formats and sources into a preset format that is easy to process, thereby obtaining the data to be analyzed in the preset format.

[0010] Furthermore, specifically, the ant colony algorithm engine processes the data to be analyzed to obtain the optimal solution, including: Initializing the ant positions involves randomly distributing m ants within the feasible region of the solution space. The feasible region refers to the area that satisfies preset constraints. The pheromone concentration of all paths or positions is set to... Record the objective function values ​​corresponding to the solutions of all ants in the initial iteration to determine the initial global optimal solution. and local optimal solution ; The ants calculate the transition probability based on pheromone concentration and a heuristic function as follows: ; in Here, `allowed` is the heuristic function, and `allowed` is the set of nodes that the ant has not visited. The next node is selected using a roulette wheel method, and candidate solutions are generated using a probability density function. The range of candidate solution generation is adjusted in conjunction with pheromone concentration to ensure that the search is concentrated in high-quality regions. Pheromone Update: Pheromone concentration at all paths or locations is updated by... To evaporate, after the ant completes one step of movement, it... Update pheromones sparingly along the current path to enhance local search. After the iteration, only allow the ant that found the global optimum to update pheromones along its path. Strengthen the guiding role of high-quality pathways; If the number of iterations reaches , or continuous If the global optimal solution does not improve in the next iteration, the algorithm terminates; otherwise, it continues to iterate. Finally, after the iteration is complete, the globally optimal solution is output. and its corresponding objective function value .

[0011] Furthermore, the method also includes visually displaying the obtained optimal solution according to a preset template for users to view.

[0012] This invention also proposes a smart digital park management system based on ant colony algorithm, including the following: The data acquisition module is used to acquire the transmission data of the target park; The data optimization module is used to process any source data in the transmitted data using a pre-built redundancy removal algorithm model to obtain optimized transmitted data; wherein, any source data refers to the same type of data collected by the same sensor or data acquisition device; The data preprocessing module is used to preprocess the optimized transmitted data to obtain data to be analyzed in a preset format; The task acquisition module is used to acquire the specific tasks and objectives of the target park management. The optimization module is used to process the data to be analyzed using the ant colony algorithm engine according to the specific task and objective to obtain the optimal solution. The task response module is used to respond to specific tasks and objectives based on the optimal solution.

[0013] Furthermore, the system also includes, The visualization module is used to visually display the best solution obtained according to a preset template for users to view.

[0014] The beneficial effects of this invention are as follows: This invention proposes a smart digital park management method and device based on ant colony optimization. On the one hand, for the massive data in the smart digital park, a pre-constructed redundancy removal algorithm model is used to remove redundancy, eliminating data that is not sensitive enough to anomaly detection or event identification, thereby reducing the pressure on data storage and computation. Then, preprocessing operations are used to remove noise and unify data of different formats and sources into a format that is easy to process, and store it in a distributed database or data lake, providing a high-quality data foundation for subsequent in-depth analysis. On the other hand, the ant colony optimization algorithm is applied to the park management, which can make the obtained management solution more optimized and closer to the actual problem-solving needs. Attached Figure Description

[0015] The above and other features of this disclosure will become more apparent from the detailed description of the embodiments illustrated in conjunction with the accompanying drawings. In the accompanying drawings, the same reference numerals denote the same or similar elements. Obviously, the drawings described below are merely some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained from these drawings without any creative effort. In the drawings: Figure 1 The flowchart shown is a process for the intelligent digital park management method based on the ant colony algorithm of the present invention. Detailed Implementation

[0016] The following will provide a clear and complete description of the concept, specific structure, and technical effects of the present invention in conjunction with embodiments and accompanying drawings, so as to fully understand the purpose, solution, and effects of the present invention. It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The same reference numerals used throughout the accompanying drawings indicate the same or similar parts.

[0017] Example 1, referring to Figure 1 This invention proposes a smart digital park management method based on ant colony algorithm, including the following: Step 110: Obtain the transmission data of the target park; Step 120: For any source data in the transmitted data, the optimized transmitted data is obtained by processing it through a pre-built redundancy removal algorithm model; wherein, any source data refers to the same type of data collected by the same sensor or data acquisition device. Step 130: Preprocess the optimized transmission data to obtain data to be analyzed in a preset format; Step 140: Obtain the specific tasks and objectives for the management of the target park; Step 150: Based on the specific task and objective, the ant colony algorithm engine processes the data to be analyzed to obtain the optimal solution; Step 160: Respond to specific tasks and objectives based on the optimal solution.

[0018] In this embodiment 1, on the one hand, for the massive data in the smart digital park, redundancy removal is performed through a pre-built redundancy removal algorithm model to remove data that is not sensitive enough to anomaly detection or event identification, thereby reducing the pressure on data storage and computation. Then, through preprocessing operations to remove noise, data of different formats and sources are uniformly converted into a format that is easy to process and stored in a distributed database or data lake, providing a high-quality data foundation for subsequent in-depth analysis. On the other hand, ant colony optimization is applied when managing the park, which can make the obtained management solution more optimized and closer to the actual problem-solving needs.

[0019] In a preferred embodiment of the present invention, specifically, the process of obtaining optimized transmission data by processing any source data in the transmitted data using a pre-built redundancy removal algorithm model includes: For any source data in the transmitted data, let the transmitted dataset be [SJ_1, SJ_2, ..., SJ_N], with a preset scale value M, independent variable i and independent variable j, and i and j initialized to 1; Step 121: Define SJ_i as the transmitted data to be judged for the i-th sample, and the variable c, the value range of c is [1, i]; Step 122: Determine the relationship between i and M. If i is less than M, calculate the average value from SJ_1 to SJ_i as the threshold. If i is not less than M, use the value of SJ_c+1 as the threshold. Step 123: Perform redundancy removal based on the judgment threshold Threshold; Step 124: When j ≤ M, increment the value of j by 1 and proceed to step 121; when j > M, set j = 1 and proceed to step 125. Step 125: When c ≤ i, increment the value of c by M and proceed to step 121; when c > i, proceed to step 126. Step 126: Determine if i is equal to N. If yes, output the processed dataset as the optimized transmission data of the current source data. Otherwise, increment i by 1 and proceed to step 121.

[0020] In this preferred embodiment, considering the large amount of data in the smart digital park, each transmission of data for the same sensor or data acquisition device involves multiple samplings. If less sensitive sampled data in each transmission can be removed, a large amount of storage space can be saved. Furthermore, since more sensitive data is retained, the amount of data processing is greatly reduced, and the accuracy of the calculation results is also improved.

[0021] In a preferred embodiment of the present invention, the redundancy removal process based on the judgment threshold Threshold specifically includes: Calculate the upper limit of change value SJ_max and the lower limit of change value SJ_min, where, ; ; In the formula, This indicates the operation of retrieving the median value from the data. This indicates taking the maximum value of the data. This indicates taking the minimum value of the data; calculate The difference between the first difference and the threshold is denoted as the first difference. Calculate... The difference from Threshold is denoted as the second difference. If there is only one negative value between the first and second differences, calculate them separately. SJ_c+1, and The absolute values ​​of the differences are P, P1, and P2, and only the data corresponding to the intermediate value among P, P1, and P2 is retained; If either the first difference or the second difference contains two negative values ​​or zero negative values, calculate separately. SJ_c+1, and The numerical differences are obtained by taking the absolute values ​​of the differences, namely P', P1', and P2'. At this point, only the data corresponding to the maximum value among P', P1', and P2' is retained.

[0022] In a preferred embodiment of the present invention, the preprocessing specifically includes removing noise from the optimized transmitted data, and then converting data of different formats and sources into a preset format that is easy to process, thereby obtaining the data to be analyzed in the preset format.

[0023] In this preferred embodiment, data preprocessing in the above manner can further facilitate subsequent ant colony algorithm processing.

[0024] In a preferred embodiment of the present invention, specifically, an ant colony algorithm engine processes the data to be analyzed to obtain an optimal solution, including... 1. Initialization: Initialize the ant positions by randomly distributing m ants within the feasible region of the solution space (satisfying the constraints). The feasible region refers to the area that satisfies the preset constraints. Set the pheromone concentration of all paths or positions to... Record the objective function values ​​corresponding to the solutions of all ants in the initial iteration to determine the initial global optimal solution. and local optimal solution ; 2. Ant Pathfinding (Solution Construction): Discrete Problems (such as TSP): Ants calculate the transition probabilities based on pheromone concentration and heuristic function as follows: ; in Here, `allowed` is the heuristic function, and `allowed` is the set of nodes that the ant has not visited. The next node is selected using a roulette wheel method. When encountering continuous problems (such as function extrema), a probability density function (such as Gaussian distribution) is used to generate candidate solutions. The range of candidate solution generation is adjusted in combination with pheromone concentration to ensure that the search is concentrated in high-quality regions. 3. Pheromone Update: Global Evaporation: Pheromone concentration at all paths or locations is updated according to... Evaporation and localized updates (optional): After an ant completes one step of movement, it... A small amount of pheromone is updated on the current path to enhance local search; global update: after the iteration ends, only the ant that found the global optimum updates the pheromone on its path. Strengthen the guiding role of high-quality pathways; If the number of iterations reaches (Preferably 100-500), or continuous If the global optimal solution does not improve after 20-50 iterations (preferably), the algorithm terminates; otherwise, iteration continues. Finally, after the iteration is complete, the globally optimal solution is output. and its corresponding objective function value .

[0025] Result verification: By repeatedly running the algorithm (e.g., 10-20 times), the mean and variance of the optimal solution are statistically analyzed to verify the stability of the results; if the results fluctuate significantly, the completeness of the data cleaning or the rationality of the parameter settings needs to be checked. Parameter tuning: Use the control variable method (fix other parameters and adjust a single parameter) or response surface methodology to optimize key parameters (such as α and β). The goal is to improve the convergence speed of the algorithm while ensuring the accuracy of the optimization.

[0026] Where α represents the importance that ants attach to pheromone concentration. The larger α is, the more likely ants are to follow known pheromone paths. The smaller α is, the stronger the random search behavior. β represents the importance that ants attach to heuristic information (the heuristic function is usually the reciprocal of the objective function or the fitness function. The larger β is, the more likely ants are to choose the local optimum and the faster the convergence speed. The smaller β is, the stronger the global search ability).

[0027] In this preferred embodiment, by applying the classic ant colony algorithm to calculate the management scheme for the smart data park, an optimal solution that better suits the application scenario can be obtained.

[0028] In a preferred embodiment of the present invention, the method further includes visually displaying the obtained optimal solution according to a preset template for users to view.

[0029] In this preferred embodiment, the optimal solution is visualized using a preset template, which makes it convenient for users to view the results.

[0030] Example 2: This invention also proposes a smart digital park management system based on ant colony algorithm, including the following: The data acquisition module is used to acquire the transmission data of the target park; The data optimization module is used to process any source data in the transmitted data using a pre-built redundancy removal algorithm model to obtain optimized transmitted data; wherein, any source data refers to the same type of data collected by the same sensor or data acquisition device; The data preprocessing module is used to preprocess the optimized transmitted data to obtain data to be analyzed in a preset format; The task acquisition module is used to acquire the specific tasks and objectives of the target park management. The optimization module is used to process the data to be analyzed using the ant colony algorithm engine according to the specific task and objective to obtain the optimal solution. The task response module is used to respond to specific tasks and objectives based on the optimal solution.

[0031] In a preferred embodiment of the present invention, the system further includes, The visualization module is used to visually display the best solution obtained according to a preset template for users to view.

[0032] In application, the method proposed in this invention can be extended in the following ways: The application layer serves as the window for interaction between the system and users. A series of rich application function modules have been developed based on the needs of different roles within the park (park managers, enterprise users, property management personnel, etc.). For park managers, a comprehensive management platform is provided, covering functions such as park planning and decision-making, resource management, and operational monitoring, enabling them to fully grasp the overall operation of the park and make scientific and reasonable management decisions. Enterprise users can conveniently obtain services such as policy consultation, business processing, and resource sharing through the enterprise service platform, helping enterprises operate efficiently. Property management personnel, through the property management module, can achieve informatization and intelligentization of daily work such as maintenance and management of park facilities and equipment, inspection and repair processing, and environmental cleaning and greening management, improving the efficiency and quality of property services.

[0033] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0034] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or system capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0035] Although the description of the invention has been quite detailed and particularly of several described embodiments, it is not intended to limit it to any of these details or embodiments or any particular embodiment, but should be considered as providing a broad possible interpretation of the claims by referring to the appended claims and taking into account the prior art, thereby effectively covering the intended scope of the invention. Furthermore, the invention has been described above with respect to embodiments foreseeable by the inventors in order to provide a useful description, and non-substantial modifications to the invention that have not yet been foreseen may still represent equivalent modifications.

[0036] The above description is merely a preferred embodiment of the present invention. The present invention is not limited to the above-described embodiments. Any embodiment that achieves the technical effects of the present invention using the same means should fall within the protection scope of the present invention. Within the protection scope of the present invention, various modifications and variations can be made to the technical solutions and / or implementation methods.

Claims

1. A smart digital park management method based on ant colony algorithm, characterized in that, Including the following: Step 110: Obtain the transmission data of the target park; Step 120: For any source data in the transmitted data, the optimized transmitted data is obtained by processing it through a pre-built redundancy removal algorithm model; wherein, any source data refers to the same type of data collected by the same sensor or data acquisition device. Step 130: Preprocess the optimized transmission data to obtain data to be analyzed in a preset format; Step 140: Obtain the specific tasks and objectives for the management of the target park; Step 150: Based on the specific task and objective, the ant colony algorithm engine processes the data to be analyzed to obtain the optimal solution; Step 160: Respond to specific tasks and objectives based on the optimal solution.

2. The intelligent digital park management method based on ant colony algorithm according to claim 1, characterized in that, Specifically, the process of obtaining optimized transmission data by processing any source data in the transmitted data using a pre-built redundancy removal algorithm model includes: For any source data in the transmitted data, let the transmitted dataset be [SJ_1, SJ_2, ..., SJ_N], with a preset scale value M, independent variable i and independent variable j, and i and j initialized to 1; Step 121: Define SJ_i as the transmitted data to be judged for the i-th sample, and the variable c, the value range of c is [1, i]; Step 122: Determine the relationship between i and M. If i is less than M, calculate the average value from SJ_1 to SJ_i as the threshold. If i is not less than M, use the value of SJ_c+1 as the threshold. Step 123: Perform redundancy removal based on the judgment threshold Threshold; Step 124: When j ≤ M, increment the value of j by 1 and proceed to step 121; when j > M, set j = 1 and proceed to step 125. Step 125: When c ≤ i, increment the value of c by M and proceed to step 121; when c > i, proceed to step 126. Step 126: Determine if i is equal to N. If yes, output the processed dataset as the optimized transmission data of the current source data. Otherwise, increment i by 1 and proceed to step 121.

3. The intelligent digital park management method based on ant colony algorithm according to claim 2, characterized in that, Specifically, the redundancy removal process based on the threshold (Threshold) includes: Calculate the upper limit of change value SJ_max and the lower limit of change value SJ_min, where, ； ； In the formula, This indicates the operation of retrieving the median value from the data. This indicates taking the maximum value of the data. This indicates taking the minimum value of the data; calculate The difference between the first difference and the threshold is denoted as the first difference. Calculate... The difference from Threshold is denoted as the second difference. If there is only one negative value between the first and second differences, calculate them separately. SJ_c+1, and The absolute values ​​of the differences are P, P1, and P2, and only the data corresponding to the intermediate value among P, P1, and P2 is retained; If either the first difference or the second difference contains two negative values ​​or zero negative values, calculate separately. SJ_c+1, and The numerical differences are obtained by taking the absolute values ​​of the differences, namely P', P1', and P2'. At this point, only the data corresponding to the maximum value among P', P1', and P2' is retained.

4. The intelligent digital park management method based on ant colony algorithm according to claim 1, characterized in that, Specifically, the preprocessing includes removing noise from the optimized transmitted data, and then converting data of different formats and sources into a preset format that is easy to process, thereby obtaining the data to be analyzed in the preset format.

5. The intelligent digital park management method based on ant colony algorithm according to claim 1, characterized in that, Specifically, the ant colony algorithm engine processes the data to be analyzed to obtain the optimal solution, including: Initializing the ant positions involves randomly distributing m ants within the feasible region of the solution space. The feasible region refers to the area that satisfies preset constraints. The pheromone concentration of all paths or positions is set to... Record the objective function values ​​corresponding to the solutions of all ants in the initial iteration to determine the initial global optimal solution. and local optimal solution ; The ants calculate the transition probability based on pheromone concentration and a heuristic function as follows: ； in Here, `allowed` is the heuristic function, `allowed` is the set of nodes not visited by the ants, and `k∈[1,m]` is the ant number. The next node is selected using a roulette wheel method, and candidate solutions are generated using a probability density function. The range of candidate solution generation is adjusted in conjunction with pheromone concentration to ensure that the search is concentrated in high-quality regions. Pheromone Update: Pheromone concentration at all paths or locations is updated by... To evaporate, after the ant completes one step of movement, it... Update pheromones sparingly along the current path to enhance local search. After the iteration, only allow the ant that found the global optimum to update pheromones along its path. Strengthen the guiding role of high-quality pathways; If the number of iterations reaches , or continuous If the global optimal solution does not improve in the next iteration, the algorithm terminates; otherwise, it continues to iterate. Finally, after the iteration is complete, the globally optimal solution is output. and its corresponding objective function value .

6. The intelligent digital park management method based on ant colony algorithm according to claim 1, characterized in that, The method also includes visually displaying the obtained optimal solution according to a preset template for users to view.

7. A smart digital park management system based on ant colony algorithm, characterized in that, Including the following: The data acquisition module is used to acquire the transmission data of the target park; The data optimization module is used to process any source data in the transmitted data using a pre-built redundancy removal algorithm model to obtain optimized transmitted data; wherein, any source data refers to the same type of data collected by the same sensor or data acquisition device; The data preprocessing module is used to preprocess the optimized transmitted data to obtain data to be analyzed in a preset format; The task acquisition module is used to acquire the specific tasks and objectives of the target park management. The optimization module is used to process the data to be analyzed using the ant colony algorithm engine according to the specific task and objective to obtain the optimal solution. The task response module is used to respond to specific tasks and objectives based on the optimal solution.

8. The intelligent digital park management system based on ant colony algorithm according to claim 7, characterized in that, The system also includes, The visualization module is used to visually display the best solution obtained according to a preset template for users to view.

Images