Search

CN-122022244-A - Intelligent digital park management method and system based on ant colony algorithm

CN122022244ACN 122022244 ACN122022244 ACN 122022244ACN-122022244-A

Abstract

The invention relates to an intelligent digital park management method based on an ant colony algorithm, which comprises the following steps of obtaining transmission data of a target park, processing any source data in the transmission data through a pre-built redundancy elimination algorithm model to obtain optimized transmission data, preprocessing the optimized transmission data to obtain data to be analyzed in a preset format, obtaining specific tasks and targets managed by the target park, processing the data to be analyzed through an ant colony algorithm engine according to the specific tasks and targets, and responding to the specific tasks and targets based on the optimal solution, wherein the arbitrary source data refer to the data of the same type collected through the same sensor or data collection equipment, and the step 130. The method and the system can not only well deal with mass data of the park, but also enable the obtained management scheme to be more optimized and be more close to the solving requirement of the actual problem.

Inventors

  • XU WANG
  • TAN HAIFENG

Assignees

  • 广东省广业创意产业园投资有限公司

Dates

Publication Date
20260512
Application Date
20251218

Claims (8)

  1. 1. The intelligent digital park management method based on the ant colony algorithm is characterized by comprising the following steps of: Step 110, obtaining transmission data of a target park; Step 120, processing any source data in the transmission data through a pre-constructed redundancy elimination algorithm model to obtain optimized transmission data, wherein the any source data refers to the same type of data acquired through the same sensor or data acquisition equipment; 130, preprocessing the optimized transmission data to obtain data to be analyzed in a preset format; Step 140, acquiring specific tasks and targets managed by the target park; Step 150, processing the data to be analyzed by an ant colony algorithm engine according to specific tasks and targets to obtain an optimal solution; step 160, responding to specific tasks and targets based on the optimal solution.
  2. 2. The intelligent digital park management method based on ant colony algorithm according to claim 1, wherein specifically, for any source data in the transmission data, the process of processing by the pre-constructed redundancy elimination algorithm model to obtain optimized transmission data includes, Recording the transmitted data set as [ SJ_1, SJ_2, ], SJ_N ], presetting a scale value M, an independent variable i and an independent variable j, and initializing i and j as 1 for any source data in the transmitted data; Step 121, defining sj_i as transmission data of the ith sample to be judged, wherein the value range of the variables c and c is [1, i ]; Step 122, determining the magnitude relation between i and M, if i is smaller than M, then obtaining the average value of SJ_1 to SJ_i as a determination Threshold, and if i is not smaller than M, then taking the value of SJ_c+1 as the determination Threshold; step 123, performing redundancy elimination processing based on a judgment Threshold; Step 124, when j is less than or equal to M, increasing the value of j by 1, and turning to step 121 for operation, and when j is more than M, turning to step 125 for operation, wherein j=1; Step 125, when c is less than or equal to i, increasing the value of c by M, and turning to step 121 for operation, and when c > i, turning to step 126 for operation; step 126, judging whether i is equal to N, if so, outputting the processed data set as optimized transmission data of the current source data, if not, increasing i by 1, and turning to step 121 to operate.
  3. 3. The intelligent digital park management method based on ant colony algorithm according to claim 2, wherein the process of performing redundancy elimination based on the judgment Threshold includes, The upper variation limit value SJ _ max and the lower variation limit value SJ _ min are calculated, wherein, ; ; In the formula, The median operation of the data is represented, Representing the maximum value of the taken data, Representing a minimum value of the fetch data; Calculation of The difference with Threshold is recorded as the first difference, and the calculation is performed Marking the difference with Threshold as a second difference value, if only 1 negative value exists in the first difference value and the second difference value, respectively calculating ,SJ_c+1, And (3) with The absolute value of the difference of P, P is obtained, and data corresponding to intermediate values in P, P and P2 are only reserved; If there are 2 negative values or 0 negative values in the first difference and the second difference, respectively calculating ,SJ_c+1, And (3) with The numerical value difference of (2) is taken as the absolute value to obtain P ', P1' and P2', and only the data corresponding to the maximum value in P', P1 'and P2' are reserved.
  4. 4. The ant colony algorithm-based intelligent digital park management method according to claim 1, wherein the preprocessing includes noise removal processing of the optimized transmission data, and then unifying the data with different formats and different sources into a preset format convenient to process, so as to obtain the data to be analyzed in the preset format.
  5. 5. The intelligent digital park management method based on ant colony algorithm according to claim 1, wherein specifically, the processing is performed by an ant colony algorithm engine based on the data to be analyzed to obtain an optimal solution, comprising, Initializing ant positions, namely immediately distributing m ants in a feasible region of a solution space, wherein the feasible region refers to a region meeting preset constraint conditions, and the pheromone concentration of all paths or positions is set as Recording objective function values corresponding to solutions of all ants in initial iteration, and determining initial global optimal solution And a locally optimal solution ; The ants calculate the transition probabilities according to the pheromone concentration and heuristic function as follows: ; Wherein the method comprises the steps of As heuristic function, allowed is node set not accessed by ant, k is [1, m ] is ant number; selecting the next node according to a roulette method, generating a candidate solution by adopting a probability density function, and adjusting the generation range of the candidate solution by combining with the concentration of the pheromone to ensure that the search is concentrated to a high-quality area; Pheromone updating, namely, the concentration of the pheromone of all paths or positions is according to Volatilizing, and after the ants complete one-step movement, passing Updating pheromone on the current path in a small amount, enhancing local search, and only enabling ants finding the globally optimal solution to update the pheromone on the path after iteration is finished Strengthening the guiding function of the high-quality path; If the iteration times reach Or continuously The global optimal solution of the secondary iteration is not improved, the algorithm is terminated, otherwise, the iteration is continued; finally, outputting the global optimal solution after iteration is completed Target function value corresponding to the target function value 。
  6. 6. The ant colony algorithm-based intelligent digital park management method according to claim 1, further comprising visually displaying the obtained optimal solution according to a preset template for the user to review.
  7. 7. Intelligent digital park management system based on ant colony algorithm, which is characterized by comprising the following steps: The data acquisition module is used for acquiring transmission data of the target park; The data optimization module is used for processing any source data in the transmission data through a pre-constructed redundancy elimination algorithm model to obtain optimized transmission data, wherein the any source data refers to the same type of data acquired through the same sensor or data acquisition equipment; The data preprocessing module is used for preprocessing the optimized transmission data to obtain data to be analyzed in a preset format; the task acquisition module is used for acquiring specific tasks and targets managed by the target park; the optimizing module is used for processing the data to be analyzed through an ant colony algorithm engine according to specific tasks and targets to obtain an optimal solution; And the task response module is used for responding to specific tasks and targets based on the optimal solution.
  8. 8. The intelligent digital park management system based on the ant colony algorithm according to claim 7, further comprising, And the visual display module is used for visually displaying the obtained optimal solution according to a preset template for the user to review.

Description

Intelligent digital park management method and system based on ant colony algorithm Technical Field The invention relates to the technical field of intelligent parks, in particular to an intelligent digital park management method and system based on an ant colony algorithm. Background The intelligent park is a modern industry or living gathering area integrating new generation information technology and park management service, and the core of the intelligent park is to realize efficient operation, high-quality service and sustainable development of the park through digital and intelligent means. The existing intelligent park management method is to perform data acquisition through related data acquisition equipment, then perform judgment of corresponding events by combining with a preset judgment threshold, or perform corresponding processing according to a preset classical algorithm according to specific tasks and targets of park management such as resource allocation, path planning, equipment scheduling and the like. The processing process has the problems that on one hand, massive multi-source heterogeneous park data have more redundant and noise data, if the data are directly processed, the computing power is obviously insufficient, a server cannot be used for processing park management transactions better, and on the other hand, the conventional classical algorithm is applied when park management is carried out, but the problem of algorithm optimization is not considered, and the application effect of the obtained management scheme is poor. Disclosure of Invention The invention aims to at least solve one of the defects in the prior art and provides an intelligent digital park management method based on an ant colony algorithm. In order to achieve the above purpose, the present invention adopts the following technical scheme: specifically, an intelligent digital park management method based on an ant colony algorithm is provided, which comprises the following steps: Step 110, obtaining transmission data of a target park; Step 120, processing any source data in the transmission data through a pre-constructed redundancy elimination algorithm model to obtain optimized transmission data, wherein the any source data refers to the same type of data acquired through the same sensor or data acquisition equipment; 130, preprocessing the optimized transmission data to obtain data to be analyzed in a preset format; Step 140, acquiring specific tasks and targets managed by the target park; Step 150, processing the data to be analyzed by an ant colony algorithm engine according to specific tasks and targets to obtain an optimal solution; step 160, responding to specific tasks and targets based on the optimal solution. Further, specifically, for any source data in the transmission data, the process of processing the transmission data through the pre-constructed redundancy elimination algorithm model to obtain optimized transmission data comprises, Recording the transmitted data set as [ SJ_1, SJ_2, ], SJ_N ], presetting a scale value M, an independent variable i and an independent variable j, and initializing i and j as 1 for any source data in the transmitted data; Step 121, defining sj_i as transmission data of the ith sample to be judged, wherein the value range of the variables c and c is [1, i ]; Step 122, determining the magnitude relation between i and M, if i is smaller than M, then obtaining the average value of SJ_1 to SJ_i as a determination Threshold, and if i is not smaller than M, then taking the value of SJ_c+1 as the determination Threshold; step 123, performing redundancy elimination processing based on a judgment Threshold; Step 124, when j is less than or equal to M, increasing the value of j by 1, and turning to step 121 for operation, and when j is more than M, turning to step 125 for operation, wherein j=1; Step 125, when c is less than or equal to i, increasing the value of c by M, and turning to step 121 for operation, and when c > i, turning to step 126 for operation; step 126, judging whether i is equal to N, if so, outputting the processed data set as optimized transmission data of the current source data, if not, increasing i by 1, and turning to step 121 to operate. Further, specifically, the process of performing redundancy elimination processing based on the judgment Threshold value Threshold includes, The upper variation limit value SJ _ max and the lower variation limit value SJ _ min are calculated, wherein, ; ; In the formula,The median operation of the data is represented,Representing the maximum value of the taken data,Representing a minimum value of the fetch data; Calculation of The difference with Threshold is recorded as the first difference, and the calculation is performedMarking the difference with Threshold as a second difference value, if only 1 negative value exists in the first difference value and the second difference value, respectively calculating,SJ_c+1,And (3) wi