Intelligent park comprehensive management system and method

Abstract

The application discloses a kind of wisdom park integrated management system and method, it is related to wisdom park technical field, by real-time collection garbage recycling area and the multidimensional data of garbage transport vehicle, and integrate and analyze each item of information, accurately assess the garbage classification efficiency of each garbage recycling area, predict garbage volume and optimize recycling path and frequency.In this process, data set D (t) play a key role, by the classification efficiency analysis of each garbage recycling area, obtain classification efficiency vector E, and predict garbage volume G in combination with historical record information, effectively reflect the garbage cleaning demand of each area.In addition, by optimizing recycling path and frequency, recycling path optimization vector C is obtained, which further reduces the recycling cost and improves the sustainability and efficiency of recycling.Finally, the system obtains the park garbage recycling efficiency index R by summarizing these data, providing a comprehensive decision basis for park managers.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart park, in particular to a smart park comprehensive management system and method. BACKGROUND

[0002] With the gradual popularization of the concept of smart city and green environmental protection, park management is gradually developing towards intelligence and automation. As a frontier of this trend, smart park covers multiple fields such as park resource management, environmental monitoring, security guarantee, etc. The goal of park management is not only to improve operational efficiency, but also to achieve efficient use of resources and sustainable development of the environment. Among many management fields, garbage classification and recycling, as a field closely related to the ecological environment of the park, is gradually being put on the agenda. In this field, traditional garbage classification and recycling methods usually rely on manual or semi-automatic means, which is difficult to achieve comprehensive and efficient management in large-scale parks.

[0003] In the existing park garbage management, there are many unsatisfactory places, especially in the monitoring and evaluation of garbage classification and recycling. Traditional garbage classification systems often rely on manual classification or single classification markers, which cannot monitor the types and quantities of garbage in real time, resulting in many garbage not being effectively classified, which in turn affects the recycling effect. At the same time, the path and frequency of garbage recycling are usually preset by manual, which is difficult to flexibly adjust according to the actual garbage generation situation of the park. Lack of intelligent data analysis and real-time feedback, leading to untimely or inaccurate garbage recycling, causing garbage accumulation, resource waste, etc. For example, some areas in the park may generate a large amount of garbage due to high population density, while other areas have less garbage. Traditional recycling methods often cannot accurately adjust the frequency and route of garbage collection, causing excessive consumption of resources in some areas and garbage accumulation in other areas. SUMMARY

[0004] In view of the deficiencies of the prior art, the present application provides a smart park comprehensive management system and method, which solves the problems mentioned in the background art.

[0005] To achieve the above purpose, the present application is realized by the following technical scheme: a smart park comprehensive management system and method, S1, by deploying sensor groups in the garbage recycling area and garbage transport vehicles, real-time collection of multi-dimensional data information, and through integration processing, obtaining data set D(t);

[0006] S2, by substituting the data set D(t) into the established garbage recycling area classification efficiency calculation formula, analyzing the garbage classification efficiency of each garbage recycling area, and through the integration of the garbage classification efficiency of each garbage recycling area, obtaining the classification efficiency vector E;

[0007] S3, obtain the density prediction garbage amount G of the garbage recycling area by associating the data set D and the historical record information of each garbage recycling area;

[0008] S4, obtain the recycling cost of the garbage recycling area by substituting the classification efficiency vector E and the density prediction garbage amount G into the analysis through the establishment of the garbage recycling path and frequency optimization model of the garbage recycling area, and obtain the recycling path optimization vector C by integrating the recycling cost of each garbage recycling area;

[0009] S5, obtain the park garbage recycling efficiency index R by summarizing the classification efficiency vector E, the density prediction garbage amount G and the recycling path optimization vector C, and analyze the optimization effect of the garbage recycling area in the park.

[0010] Preferably, S1 includes S11 and S12;

[0011] S11, by deploying a sensor group including ultrasonic sensors, pressure sensors, image recognition cameras, RFID sensors, GPS positioning sensors and acceleration sensors on each garbage recycling area and garbage transport vehicles, collecting the garbage filling degree Tc, the garbage can type Lx, the garbage weight Zl and the garbage classification state Fl of the garbage can in each garbage recycling area at a fixed period, and integrating the real-time collected path data Lj of the garbage transport vehicle, an initial data set Draw is formed, and the initial data set Draw is uploaded to the cloud data processing center through LoRa, 5G and Wi-Fi after marking time t for record analysis;

[0012] The initial data set Draw is reorganized into an initial data set Draw(t) with time t after marking time t, specifically Draw={Tc(t), Lx(t), Zl(t), Fl(t), Lj(t)};

[0013] Wherein, Tc(t) represents the garbage filling degree collected at time t, Lx(t) represents the garbage can type collected at time t, Zl(t) represents the garbage weight collected at time t, Fl(t) represents the garbage classification state collected at time t, and Lj(t) represents the path data collected at time t.

[0014] Preferably, S12, data cleaning preprocessing and data missing preprocessing are performed on the uploaded data initial data set Draw, the data cleaning preprocessing includes using moving average filter to smooth the data fluctuation of time series data, and using threshold algorithm to eliminate data that does not meet the predetermined classification standard;

[0015] The data missing preprocessing includes using linear interpolation method to fill the missing data points, and using path reconstruction algorithm to reconstruct the lost path information according to the existing path data;

[0016] Through data cleaning preprocessing and data filling preprocessing on the initial data set Draw, the data set D(t) of time t is formed after integration.

[0017] Preferably, S2 comprises S21 and S22.

[0018] S21, by substituting the data set D(t) into the established garbage can classification efficiency calculation formula in the garbage recycling area, analyzes the garbage classification efficiency of each garbage can in each garbage recycling area, and obtains the classification efficiency E(i,t) of the i-th garbage can in the garbage recycling area at time t.

[0019] The classification efficiency Ei(t) of the i-th garbage can is obtained by the following garbage can classification efficiency calculation formula:

[0020] ;

[0021] In the formula, Tc(i,t) represents the garbage filling degree of the i-th garbage can at time t, Tmax(i) represents the upper limit capacity of the i-th garbage can, Fl(i,t) represents the garbage classification state of the i-th garbage can at time t, Lx(i,t) represents the garbage can type of the i-th garbage can at time t, which is used to judge the relationship between the garbage in the i-th garbage can and the classification standard, and a represents the efficiency coefficient, and 0

[0022] Preferably, S22, by substituting the obtained classification efficiency E(i,t) of the i-th garbage can in the garbage recycling area at time t into the established garbage recycling area classification efficiency calculation formula, analyzes the garbage classification efficiency of each garbage recycling area, obtains the classification efficiency E(r,t) of the r-th garbage recycling area at time t, and integrates the classification efficiency E(r,t) of each garbage recycling area to form a classification efficiency vector E.

[0023] The classification efficiency E(r,t) of the r-th garbage recycling area at time t is calculated by the following garbage recycling area classification efficiency calculation formula:

[0024] ;

[0025] In the formula, N(r) represents the r-th garbage recycling area, and specifically represents the total number of garbage cans in the r-th garbage recycling area.

[0026] The classification efficiency vector E is specifically E={E(1,t), E(2,t), …, E(r,t)}.

[0027] Preferably, S3 comprises S31.

[0028] S31, obtaining the density prediction garbage amount G(r, t+1) of the rth garbage recycling area at time t+1 by associating the data set D and the historical record information of each garbage recycling area;

[0029] The density prediction garbage amount G(r, t) of the rth garbage recycling area at time t is obtained by the following association formula:

[0030] ;

[0031] In the formula, Graw(r, t) represents the preliminary prediction garbage amount of the rth garbage recycling area at time t, γ represents an adjustment coefficient, which is specifically used for adjusting the influence of the historical record information on the density prediction garbage amount G(r, t+1) of the rth garbage recycling area at time t+1, and Gavg(r) represents the historical average garbage amount of the rth garbage recycling area.

[0032] The preliminary prediction garbage amount Graw(r, t) of the rth garbage recycling area at time t is obtained by the following calculation formula:

[0033] ;

[0034] In the formula, G(i, t) represents the prediction garbage amount of the ith garbage can at time t.

[0035] The prediction garbage amount Gyc(i, t) of the ith garbage can at time t is obtained by the following calculation formula:

[0036] ;

[0037] In the formula, Zl(i, t-1) represents the garbage weight of the ith garbage can at time t-1, and β represents an influence coefficient.

[0038] Preferably, the S4 comprises S41 and S42.

[0039] S41, by establishing a garbage recycling path and frequency optimization model of the garbage recycling area, the classified efficiency vector E and the density prediction garbage amount G are substituted into analysis to obtain the recycling cost C(r, t) of the rth garbage recycling area at time t.

[0040] The recycling cost C(r, t) of the rth garbage recycling area at time t is obtained by the following calculation formula:

[0041] ;

[0042] In the formula, Emax represents the maximum classification efficiency in all garbage recycling areas, Lj(r, t) represents the path data of the rth garbage recycling area at time t, Lmax(r) represents the path maximum value of the rth garbage recycling area, and c1 represents a balance coefficient.

[0043] Preferably, S42, according to the obtained recycling cost C(r, t) of the rth garbage recycling area at time t, integrates the recycling cost C(r, t) of each garbage recycling area, calculates the recycling path optimization vector C of the whole park to reflect the cost status of the garbage recycling of the whole park, and optimizes the garbage recycling cost status in the park by executing the recycling path optimization vector C. Specifically, the recycling path optimization vector C of all garbage recycling areas is sorted to generate a garbage recycling area cleaning list, and the garbage recycling area cleaning list is sequentially processed.

[0044] Wherein, when generating the garbage recycling area cleaning list, the recycling path optimization vector C is compared with the preset path recycling threshold Cthe, and the elimination state of all garbage recycling areas is iteratively judged.

[0045] The elimination state is obtained by the following comparison method:

[0046] When the recycling path optimization vector C is less than the path recycling threshold Cthe, it is determined that the elimination state of the current garbage recycling area is execution elimination, and the current garbage recycling area is eliminated from the garbage recycling area cleaning list.

[0047] When the recycling path optimization vector C is greater than or equal to the path recycling threshold Cthe, it is determined that the elimination state of the current garbage recycling area is not execution elimination.

[0048] The recycling path optimization vector C is obtained by the following calculation formula:

[0049] ;

[0050] In the formula, C(t) represents the recycling path optimization vector at time t, M(r) represents the total number of garbage recycling areas in the park, and C(m, t) represents the recycling cost of the mth garbage recycling area at time t.

[0051] Preferably, the S5 comprises S51.

[0052] S51, obtain the park garbage recycling efficiency index R by summarizing the classification efficiency vector E, the density prediction garbage amount Gyc and the recycling path optimization vector C, mark it as the post-execution park garbage recycling efficiency index Rend, calculate the park garbage recycling efficiency index R by extracting the recycling path optimization vector C applied in the last time period, and mark it as the pre-execution park garbage recycling efficiency index Rbefore, analyze the optimization effect of the garbage recycling area in the park;

[0053] The park garbage recycling efficiency index R is obtained by the following calculation formula:

[0054] ;

[0055] In the formula, E(m, t) represents the classification efficiency vector of the mth garbage recycling area at time t, G(m, t) represents the density prediction garbage amount of the mth garbage recycling area at time t, C(m, t) represents the recycling path optimization vector of the mth garbage recycling area at time t, w1 represents the adjustment coefficient of the area garbage amount to the park garbage recycling efficiency index, w2 represents the adjustment coefficient of the predicted garbage amount to the park garbage recycling efficiency index, and exp represents the exponential decay function.

[0056] The optimization effect is obtained by the following comparison method:

[0057] When the pre-execution park garbage recycling efficiency index Rbefore≥the post-execution park garbage recycling efficiency index Rend, the optimization effect is obtained, the recycling path optimization vector C is generated again and applied;

[0058] When the pre-execution park garbage recycling efficiency index Rbefore<the post-execution park garbage recycling efficiency index Rend, the optimization effect is obtained, the recycling path optimization vector C and the park garbage recycling efficiency index R are stored.

[0059] A smart park comprehensive management system and method, comprising a park data acquisition module, a data classification efficiency module, a correlation analysis module, an optimization module and an optimization evaluation module;

[0060] The park data acquisition module acquires multi-dimensional data information in real time by deploying a sensor group in the garbage recycling area and the garbage transport vehicle, and obtains a data set D(t) by integration processing.

[0061] The data classification efficiency module analyzes the garbage classification efficiency of each garbage recycling area by substituting the data set D(t) into the established garbage recycling area classification efficiency calculation formula, and obtains a classification efficiency vector E by integrating the garbage classification efficiency of each garbage recycling area.

[0062] The correlation analysis module obtains the density prediction garbage amount G of the garbage recycling area by correlating the data set D and the historical record information of each garbage recycling area.

[0063] The optimization module obtains the recycling cost of the garbage recycling area by establishing the garbage recycling path and frequency optimization model of the garbage recycling area, and substituting the classification efficiency vector E and the density prediction garbage amount G into the analysis, and obtains the recycling path optimization vector C by integrating the recycling cost of each garbage recycling area.

[0064] The optimization evaluation module obtains the park garbage recycling efficiency index R by summarizing the classification efficiency vector E, the density prediction garbage amount G and the recycling path optimization vector C, and analyzes the optimization effect of the garbage recycling area in the park.

[0065] The present application provides a kind of wisdom park integrated management system and method, with the following beneficial effects:

[0066] (1) by real-time acquisition of multi-dimensional data of garbage recycling area and garbage transport vehicle, and integrating and analyzing various information, accurately evaluating the garbage classification efficiency, predicting the garbage amount and optimizing the recycling path and frequency of each garbage recycling area. In this process, the data set D (t) plays a key role, and by analyzing the classification efficiency of each garbage recycling area, the classification efficiency vector E is obtained, and the garbage amount G is predicted in combination with the historical record information, effectively reflecting the garbage cleaning demand of each area. In addition, by optimizing the recycling path and frequency, the recycling path optimization vector C is obtained, which further reduces the recycling cost and improves the sustainability and efficiency of recycling. Finally, the system summarizes these data to obtain the park garbage recycling efficiency index R, providing a comprehensive decision basis for park managers, which can effectively judge the effect of optimization measures and provide data support for future optimization, solving the problem of lack of effective monitoring, evaluation and optimization mechanism in traditional garbage recycling system. In the traditional mode, the problems of low garbage classification efficiency, inaccurate garbage quantity prediction, unreasonable recycling frequency and path often lead to resource waste and increase the difficulty of management.

[0067] (2) By calculating the recycling cost C(r, t) of each garbage recycling area, and generating the recycling path optimization vector C of the whole park by integrating the recycling cost, finally, by sorting and comparing the recycling cost of all garbage recycling areas, dynamically adjusting the optimized garbage recycling path, reducing unnecessary recycling frequency, reducing the burden of high-cost areas, realizing the cost and efficiency optimization of park garbage recycling, the intelligent optimization of garbage recycling path and frequency can be realized. Through real-time analysis of the classification efficiency, prediction of garbage quantity and recycling cost of each garbage recycling area, the system can accurately judge which areas need frequent cleaning and which areas can reduce the recycling frequency or optimize the path, so as to avoid unnecessary waste of resources. Compared with the traditional periodic recycling mode, this method not only can dynamically adjust the recycling strategy according to real-time data and historical records, but also can reduce the overall recycling cost of the park and improve the garbage recycling efficiency through detailed recycling path optimization. This flexible optimization strategy not only helps the park to realize more efficient garbage recycling management, but also brings more significant improvement in environmental protection and cost control, ensuring the maximum utilization of resources and the minimization of operating costs in the garbage disposal process.

[0068] (3) By implementing the park garbage recycling efficiency index R calculation model based on the classification efficiency vector E, the density prediction garbage quantity Gyc and the recycling path optimization vector C, the system can dynamically evaluate and compare the optimization effect of garbage recycling in the park. Specifically, by calculating the park garbage recycling efficiency index Rbefore before execution and the park garbage recycling efficiency index Rend after execution, the system can clearly identify whether the effect of recycling path optimization meets the expectation. When the park garbage recycling efficiency index Rend after execution is higher than Rbefore before execution, it means that the optimization is effective, and the system will store the new recycling path optimization vector C and the park garbage recycling efficiency index R, and further apply the optimization measures; when the efficiency index after execution is lower, it means that the optimization is not effective, and the system will generate and apply a new recycling path optimization vector, so that the efficiency of park garbage recycling can be continuously improved, so as to flexibly respond to the garbage recycling demand of different parks. BRIEF DESCRIPTION OF DRAWINGS

[0069] Figure 1 A smart park comprehensive management system and method steps schematic diagram of the present application;

[0070] Figure 2 A smart park comprehensive management system and method block diagram schematic diagram of the present application. DETAILED DESCRIPTION

[0071] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0072] Embodiment 1

[0073] The present application provides a smart park comprehensive management system and method, please refer to Figure 1 , comprising the following steps:

[0074] S1, by deploying a sensor group in the garbage recycling area and the garbage transport vehicle, real-time collection of multi-dimensional data information, and through integration processing, obtaining data set D(t);

[0075] S2, by substituting the data set D(t) into the established garbage recycling area classification efficiency calculation formula, analyzing the garbage classification efficiency of each garbage recycling area, and through the integration of the garbage classification efficiency of each garbage recycling area, obtaining the classification efficiency vector E;

[0076] S3, by associating the data set D and the historical record information of each garbage recycling area, obtaining the density prediction garbage amount G of the garbage recycling area;

[0077] S4, by establishing a garbage recycling path and frequency optimization model of the garbage recycling area, substituting the classification efficiency vector E and the density prediction garbage amount G into the analysis, obtaining the recycling cost of the garbage recycling area, and then integrating the recycling cost of each garbage recycling area, obtaining the recycling path optimization vector C;

[0078] S5, by summarizing the classification efficiency vector E, the density prediction garbage amount G and the recycling path optimization vector C, obtaining the park garbage recycling efficiency index R, and analyzing the optimization effect of the garbage recycling area in the park.

[0079] In this embodiment, by collecting multi-dimensional data of garbage recycling areas and garbage transport vehicles in real time, and integrating and analyzing various information, the garbage classification efficiency of each garbage recycling area is accurately evaluated, the garbage quantity is predicted, and the recycling path and frequency are optimized. In this process, the data set D(t) plays a key role, through the classification efficiency analysis of each garbage recycling area, the classification efficiency vector E is obtained, and the garbage quantity G is predicted combined with the historical record information, effectively reflecting the garbage cleaning demand of each area. In addition, by optimizing the recycling path and frequency, the recycling path optimization vector C is obtained, further reducing the recycling cost and improving the sustainability and efficiency of recycling. Finally, the system obtains the park garbage recycling efficiency index R by summarizing these data, providing a comprehensive decision basis for park managers, which can effectively judge the effect of optimization measures and provide data support for future optimization, solving the problem of lack of effective monitoring, evaluation and optimization mechanism in traditional garbage recycling system. In the traditional mode, low garbage classification efficiency, inaccurate garbage quantity prediction, unreasonable recycling frequency and path often lead to waste of resources and increase of management difficulty. The intelligent park management method realizes the fine management of the garbage recycling system through data and automation, effectively improves the recycling efficiency, reduces the cost, reduces the unnecessary recycling path and frequency, and ensures the accuracy of garbage recycling and efficient use of resources.

[0080] Embodiment 2

[0081] This embodiment is an explanation and description in embodiment 1, please refer to Figure 1 , specifically: the S1 includes S11 and S12;

[0082] S11, by deploying a sensor group including ultrasonic sensor, pressure sensor, image recognition camera, RFID sensor, GPS positioning sensor and acceleration sensor on each garbage recycling area and garbage transport vehicle, collecting the garbage filling degree Tc, garbage can type Lx, garbage weight Zl and garbage classification state Fl of the garbage can in the garbage recycling area at a fixed period, and integrating the path data Lj data of the garbage transport vehicle collected in real time, forming an initial data set Draw, and uploading the initial data set Draw to the cloud data processing center through LoRa, 5G and Wi-Fi mode after marking time t for record analysis;

[0083] The initial data set Draw is reorganized into an initial data set Draw(t) with time t after marking time t, specifically Draw={Tc(t), Lx(t), Zl(t), Fl(t), Lj(t)};

[0084] Wherein, Tc(t) represents the garbage filling degree collected at time t, Lx(t) represents the garbage can type collected at time t, Zl(t) represents the garbage weight collected at time t, Fl(t) represents the garbage classification state collected at time t, and Lj(t) represents the path data collected at time t.

[0085] S12, data cleaning preprocessing and data missing preprocessing are performed on the uploaded initial data set Draw, the data cleaning preprocessing includes using a moving average filter to smooth data fluctuations in time series data, and using a threshold algorithm to remove data that does not meet a predetermined classification standard, such as misclassified data generated by image recognition;

[0086] The data missing preprocessing includes using a linear interpolation method to fill in missing data points, and using a path reconstruction algorithm to reconstruct lost path information according to existing path data;

[0087] After data cleaning preprocessing and data missing preprocessing are performed on the initial data set Draw, the data set D(t) at time t is integrated.

[0088] Embodiment 3

[0089] This embodiment is an explanation and description in embodiment 2, please refer to Figure 1 , specifically: the S2 includes S21 and S22;

[0090] S21, by substituting the data set D(t) into the established garbage can classification efficiency calculation formula in the garbage recycling area, the garbage classification efficiency of each garbage can in each garbage recycling area is analyzed, and the classification efficiency E(i, t) of the i-th garbage can in the garbage recycling area at time t is obtained.

[0091] The classification efficiency Ei(t) of the i-th garbage can is obtained by the following garbage can classification efficiency calculation formula:

[0092] ;

[0093] In the formula, Tc(i, t) represents the garbage filling degree of the i-th garbage can at time t, Tmax(i) represents the upper limit capacity of the i-th garbage can, Fl(i, t) represents the garbage classification state of the i-th garbage can at time t, which is used to associate the garbage classification put into the garbage can with whether the type of the garbage can matches, Lx(i, t) represents the garbage can type of the i-th garbage can at time t, which is used to judge the relationship between the garbage in the i-th garbage can and the classification standard, specifically, 1 represents that the garbage in the i-th garbage can meets the classification standard, and 0 represents that the garbage in the i-th garbage can does not meet the classification standard, and a represents an efficiency coefficient, and 0

[0094] S22, by substituting the classification efficiency E(i, t) of the i-th garbage can in the obtained garbage recycling area at time t into the established garbage recycling area classification efficiency calculation formula, the classification efficiency of each garbage recycling area is analyzed, the classification efficiency E(r, t) of the r-th garbage recycling area at time t is obtained, and the classification efficiency vector E is formed by integrating the classification efficiency E(r, t) of each garbage recycling area;

[0095] The classification efficiency E(r, t) of the r-th garbage recycling area at time t is calculated by the following garbage recycling area classification efficiency calculation formula:

[0096] ;

[0097] In the formula, N(r) represents the r-th garbage recycling area, specifically the total number of garbage cans in the r-th garbage recycling area;

[0098] The classification efficiency vector E is specifically E={E(1, t), E(2, t), …, E(r, t)}.

[0099] In this embodiment, the classification efficiency E(i, t) of each garbage can is evaluated by the data set D(t) and the garbage can classification efficiency calculation formula, which specifically considers the garbage filling degree Tc(i, t), the classification state Fl(i, t) and the garbage can type Lx(i, t) of each garbage can. The overall classification efficiency E(r, t) of each garbage recycling area is further evaluated by the garbage recycling area classification efficiency calculation formula, and the classification efficiency vector E is formed by integration, which provides a quantitative basis for the overall effect of garbage recycling in the park. Through individual analysis of garbage cans and integrated evaluation of recycling areas, not only can the classification efficiency of each garbage can be accurately evaluated, but also the overall situation of garbage classification in the park can be comprehensively mastered from the regional level. Unlike traditional methods that often rely on overall or regional statistical data, this method reveals the potential problems of classification efficiency through detailed analysis at the level of garbage cans, especially in the case of garbage can filling degree and classification unqualified, which can flexibly reflect the actual effect of garbage recycling. In this way, by continuously monitoring and adjusting the classification efficiency of the garbage recycling area, garbage classification can be more effectively optimized, recycling quality can be improved, and real-time data support can be provided for the formulation and improvement of garbage classification standards. Therefore, this method significantly improves the intelligence and accuracy of park garbage recycling management, ensuring a more efficient and environmentally friendly garbage disposal mode.

[0100] Embodiment 4

[0101] This embodiment is an explanation and description in embodiment 3, please refer to Figure 1 , specifically: the S3 includes S31;

[0102] S31, obtaining the density prediction garbage amount G(r, t+1) of the rth garbage recycling area at time t+1 by associating the data set D and the historical record information of each garbage recycling area;

[0103] The density prediction garbage amount G(r, t) of the rth garbage recycling area at time t is obtained by the following association formula:

[0104] ;

[0105] In the formula, Graw(r, t) represents the preliminary prediction garbage amount of the rth garbage recycling area at time t, γ represents an adjustment coefficient, which is specifically used to adjust the influence of the historical record information on the density prediction garbage amount G(r, t) of the rth garbage recycling area at time t+1, and Gavg(r) represents the historical average garbage amount of the rth garbage recycling area, which is specifically obtained by counting the average value of the density prediction garbage amount G(r) of the rth garbage recycling area in a plurality of time periods stored;

[0106] The preliminary prediction garbage amount Graw(r, t) of the rth garbage recycling area at time t is obtained by the following calculation formula:

[0107] ;

[0108] In the formula, G(i, t) represents the prediction garbage amount of the ith garbage can at time t;

[0109] The prediction garbage amount Gyc(i, t) of the ith garbage can at time t is obtained by the following calculation formula:

[0110] ;

[0111] In the formula, Zl(i, t-1) represents the garbage weight of the ith garbage can at time t-1, and β represents an influence coefficient, which specifically represents the influence coefficient of the filling degree on the prediction garbage amount Gyc(i, t) of the ith garbage can at time t.

[0112] The S4 includes S41 and S42;

[0113] S41, by establishing a garbage recycling path and frequency optimization model of the garbage recycling area, the classification efficiency vector E and the density prediction garbage amount G are substituted into the analysis to obtain the recycling cost C(r, t) of the rth garbage recycling area at time t;

[0114] The recycling cost C(r, t) of the rth garbage recycling area at time t is obtained by the following calculation formula:

[0115] ;

[0116] In the formula, Emax represents the maximum classification efficiency in all garbage recycling areas, Lj(r, t) represents the path data of the rth garbage recycling area at time t, Lmax(r) represents the path maximum value of the rth garbage recycling area, c1 represents a balance coefficient, and is specifically used to balance the influence of the classification efficiency and the path data on the recycling cost C(r, t) of the rth garbage recycling area at time t.

[0117] S42, according to the obtained recycling cost C(r, t) of the rth garbage recycling area at time t, the recycling cost C(r, t) of each garbage recycling area is integrated again, the recycling path optimization vector C of the whole park is calculated, which reflects the cost condition of the whole park garbage recycling, and the garbage recycling cost condition in the park is optimized by executing the recycling path optimization vector C. Specifically, the recycling path optimization vector C of all garbage recycling areas is sorted to generate a garbage recycling area cleaning list, and the garbage recycling area cleaning list is sequentially processed;

[0118] Wherein, when generating the garbage recycling area cleaning list, the recycling path optimization vector C is compared with the preset path recycling threshold Cthe, and the elimination state of all garbage recycling areas is judged by traversal;

[0119] The elimination state is obtained by the following comparison method:

[0120] When the recycling path optimization vector C is less than the path recycling threshold Cthe, it is determined that the elimination state of the current garbage recycling area is execution elimination, and the current garbage recycling area is eliminated from the garbage recycling area cleaning list;

[0121] When the recycling path optimization vector C is greater than or equal to the path recycling threshold Cthe, it is determined that the elimination state of the current garbage recycling area is not execution elimination;

[0122] The recycling path optimization vector C is obtained by the following calculation formula:

[0123] ;

[0124] In the formula, C(t) represents the recycling path optimization vector at time t, M(r) represents the total number of garbage recycling areas in the park, and C(m, t) represents the recycling cost of the mth garbage recycling area at time t. The purpose of the formula is: a higher recycling path optimization vector C(t) indicates that the recycling cost in the park is higher, which may be due to the excessive amount of garbage in some recycling areas, the excessively long path, or the lower classification efficiency. At this time, the path optimization, frequency adjustment or recycling efficiency of these areas need to be improved; a lower recycling path optimization vector C(t) indicates that the recycling cost is lower, and the garbage recycling process is more efficient. The recycling path and frequency are already reasonable, and optimization may not be needed, or unnecessary frequency can be reduced.

[0125] In this embodiment, by associating the data set D(t) and the historical record information, the density prediction garbage amount G(r, t+1) of each garbage recycling area at time t+1 is obtained, the predicted garbage amount G(r, t) and the garbage weight data of the garbage can are combined, and the preliminary prediction garbage amount Graw(r, t) of each area is further calculated. By establishing the recycling path and frequency optimization model, the classification efficiency vector E and the density prediction garbage amount G are substituted into the recycling cost C(r, t) of each garbage recycling area, and the recycling path optimization vector C of the whole park is generated by integrating the recycling cost. Finally, by sorting and comparing the recycling costs of all garbage recycling areas, the garbage recycling path is dynamically adjusted and optimized, the unnecessary recycling frequency is reduced, the burden of high-cost areas is reduced, the cost and efficiency optimization of the park garbage recycling is realized, and the intelligent optimization of the garbage recycling path and frequency is realized. Through real-time analysis of the classification efficiency, predicted garbage amount and recycling cost of each garbage recycling area, the system can accurately determine which areas need frequent cleaning and which areas can reduce the recycling frequency or optimize the path, thereby avoiding unnecessary resource waste. Compared with the traditional periodic recycling mode, this method not only dynamically adjusts the recycling strategy according to real-time data and historical records, but also reduces the overall recycling cost of the park through detailed recycling path optimization, and improves the garbage recycling efficiency. This flexible optimization strategy not only helps the park to realize more efficient garbage recycling management, but also brings more significant improvement in environmental protection and cost control, ensuring the maximum utilization of resources and the minimization of operating costs in the garbage disposal process.

[0126] Embodiment 5

[0127] This embodiment is an explanation and description in embodiment 4, please refer to Figure 1 , in particular: the S5 includes S51;

[0128] S51, by summarizing the classification efficiency vector E, the density prediction garbage amount Gyc and the recycling path optimization vector C, the park garbage recycling efficiency index R is obtained, which is marked as the executed park garbage recycling efficiency index Rend, the park garbage recycling efficiency index R calculated by extracting the recycling path optimization vector C applied in the last time period is marked as the executed park garbage recycling efficiency index Rbefore, and the optimization effect of the garbage recycling area in the park is analyzed;

[0129] The park garbage recycling efficiency index R is obtained by the following calculation formula:

[0130]

[0131] ​In the formula, E(m, t) represents the classification efficiency vector of the mth garbage recycling area at time t, G(m, t) represents the density predicted garbage amount of the mth garbage recycling area at time t, C(m, t) represents the recycling path optimization vector of the mth garbage recycling area at time t, w1 represents the adjustment coefficient of the area garbage amount to the park garbage recycling efficiency index, w2 represents the adjustment coefficient of the predicted garbage amount to the park garbage recycling efficiency index, w1 is specifically used to control the relative importance between the classification efficiency and the garbage amount, when w1 is larger, the classification efficiency and the garbage amount have a greater influence on the recycling efficiency, w2 is specifically used to control the influence of the recycling path optimization on the recycling efficiency, if w2 is larger, it means that the optimization of the recycling path has a greater negative influence on the overall efficiency, and exp represents the exponential decay function.

[0132] The optimization effect is obtained by the following comparison mode:

[0133] When the park garbage recycling efficiency index Rbefore before execution is greater than the park garbage recycling efficiency index Rend after execution, the optimization effect is not obtained, the recycling path optimization vector C is generated again and applied;

[0134] When the park garbage recycling efficiency index Rbefore before execution is less than the park garbage recycling efficiency index Rend after execution, the optimization effect is obtained, and the recycling path optimization vector C and the park garbage recycling efficiency index R are stored.

[0135] In this embodiment, by implementing a model for calculating the park's waste recycling efficiency index R based on the classification efficiency vector E, density-predicted waste volume Gyc, and recycling path optimization vector C, the system can dynamically evaluate and compare the optimization effect of waste recycling within the park. Specifically, by calculating the park's waste recycling efficiency index Rbefore and Rend after execution, the system can clearly identify whether the optimization effect of the recycling path has met expectations. When the park's waste recycling efficiency index Rend after execution is higher than Rbefore before execution, it indicates that the optimization is effective, and the system will store a new recycling path optimization vector C and the park's waste recycling efficiency index R, and further apply optimization measures. When the efficiency index after execution is lower, it indicates that the optimization is ineffective, and the system will regenerate and apply a new recycling path optimization vector, so that the efficiency of waste recycling in the park can be continuously improved, thereby flexibly responding to the waste recycling needs of different parks. Especially when the recycling path optimization is insufficient, the system can provide timely feedback through changes in the efficiency index to ensure the effectiveness of the optimization measures. Compared with traditional static adjustment methods, this method can continuously improve the park's waste recycling efficiency through real-time tracking and adjustment, avoiding high costs and resource waste caused by improper recycling path planning. Therefore, implementing this method not only optimizes the path and frequency of waste collection, but also improves the overall collection efficiency, making park management more intelligent and dynamic, thereby achieving higher operational efficiency and cost-effectiveness.

[0136] Example 6

[0137] A smart park integrated management system and method, please refer to Figure 2 Specifically, it includes a park data acquisition module, a data classification efficiency module, a correlation analysis module, an optimization module, and an optimization evaluation module;

[0138] The park's data acquisition module collects multi-dimensional data in real time by deploying sensor groups in the waste recycling area and waste transport vehicles, and obtains the data set D(t) through integration and processing.

[0139] The data classification efficiency module analyzes the waste classification efficiency of each waste recycling area by substituting the data set D(t) into the established waste recycling area classification efficiency calculation formula, and obtains the classification efficiency vector E by integrating the waste classification efficiency of each waste recycling area.

[0140] The correlation analysis module obtains the density prediction of waste volume G for each waste recycling area by using the correlation data set D and the historical information of each waste recycling area.

[0141] The optimization module inputs the classification efficiency vector E and the density predicted garbage amount G into analysis by establishing a garbage recycling path and frequency optimization model of the garbage recycling area, obtains the recycling cost of the garbage recycling area, and then integrates the recycling cost of each garbage recycling area to obtain a recycling path optimization vector C;

[0142] The optimization evaluation module obtains a park garbage recycling efficiency index R by summarizing the classification efficiency vector E, the density predicted garbage amount G, and the recycling path optimization vector C, and analyzes the optimization effect of the garbage recycling area in the park.

[0143] Although embodiments of the present application have been shown and described, it is to be understood that various modifications, substitutions, replacements and changes can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A smart park integrated management method, characterized in that: The method comprises the following steps: S1, collecting multi-dimensional data information in real time by deploying a sensor group in the garbage recycling area and the garbage transport vehicle, and obtaining a data set D(t) through integrated processing; S2, analyzing the garbage classification efficiency of each garbage recycling area by substituting the data set D(t) into the established garbage recycling area classification efficiency calculation formula, and obtaining a classification efficiency vector E by integrating the garbage classification efficiency of each garbage recycling area; S3, obtaining the density prediction garbage amount G of the garbage recycling area by correlating the data set D(t) and the historical record information of each garbage recycling area; S4, substituting the classification efficiency vector E and the density prediction garbage amount G into analysis by establishing a garbage recycling path and frequency optimization model of the garbage recycling area, obtaining the recycling cost of the garbage recycling area, and obtaining a recycling path optimization vector C by integrating the recycling cost of each garbage recycling area; The S4 comprises S41 and S42; S41, substituting the classification efficiency vector E and the density prediction garbage amount G into analysis by establishing a garbage recycling path and frequency optimization model of the garbage recycling area, obtaining the recycling cost C(r, t) of the rth garbage recycling area at time t; The recycling cost C(r, t) of the rth garbage recycling area at time t is obtained by the following calculation formula: ； In the formula, Emax represents the maximum value of the classification efficiency in all garbage recycling areas, Lj(r, t) represents the path data of the rth garbage recycling area at time t, Lmax(r) represents the maximum value of the path of the rth garbage recycling area, c1 represents a balance coefficient; E(r, t) represents the classification efficiency of the rth garbage recycling area at time t, and G(r, t) represents the density prediction garbage amount of the rth garbage recycling area at time t; S42, according to the obtained recycling cost C(r, t) of the rth garbage recycling area at time t, integrating the recycling cost of each garbage recycling area, calculating the recycling path optimization vector C of the whole park to reflect the cost status of the whole park garbage recycling, and optimizing the garbage recycling cost status in the park by executing the recycling path optimization vector C, sorting processing the recycling path optimization vector C of all garbage recycling areas, and generating a garbage recycling area cleaning list, and sequentially processing the garbage recycling area cleaning list; When the recycling path optimization vector C is generated, the recycling path optimization vector C is compared with the preset path recycling threshold Cthe, and the elimination state of all garbage recycling areas is judged by traversal; The elimination state is obtained by the following comparison method: When the recycling path optimization vector C is less than the path recycling threshold Cthe, it is determined that the elimination state of the current garbage recycling area is execution elimination, and the current garbage recycling area is eliminated from the garbage recycling area cleaning list; When the recycling path optimization vector C is greater than or equal to the path recycling threshold Cthe, it is determined that the elimination state of the current garbage recycling area is not execution elimination; The recycling path optimization vector C is obtained by the following calculation formula: ； In the formula, C(t) represents the recycling path optimization vector at time t, M(r) represents the total number of garbage recycling areas in the park, and C(m, t) represents the recycling cost of the mth garbage recycling area at time t; S5, by summarizing the classification efficiency vector E, the density prediction garbage amount G and the recycling path optimization vector C, the garbage recycling efficiency index R of the park is obtained, and the optimization effect of the garbage recycling area in the park is analyzed. 2.The method according to claim 1, characterized in that: The S1 includes S11 and S12; S11, by deploying a sensor group including ultrasonic sensors, pressure sensors, image recognition cameras, RFID sensors, GPS positioning sensors and acceleration sensors on each garbage recycling area and garbage transport vehicles, collecting the garbage filling degree Tc, the garbage can type Lx, the garbage weight Zl and the garbage classification state Fl of the garbage can in each garbage recycling area at a fixed period, and integrating the real-time collected path data Lj data of the garbage transport vehicle, an initial data group Draw is formed, and the initial data group Draw is uploaded to the cloud data processing center through LoRa, 5G or Wi-Fi after marking time t for record analysis; The initial data group Draw is reorganized into an initial data group Draw(t) with time t after marking time t, and specifically Draw={Tc(t), Lx(t), Zl(t), Fl(t), Lj(t)}; Wherein, Tc(t) represents the garbage filling degree collected at time t, Lx(t) represents the garbage can type collected at time t, Zl(t) represents the garbage weight collected at time t, Fl(t) represents the garbage classification state collected at time t, and Lj(t) represents the path data collected at time t. 3.The method according to claim 2, characterized in that: S12, by performing data cleaning preprocessing and data missing preprocessing on the uploaded initial data group Draw, the data cleaning preprocessing includes using moving average filter to smooth the data fluctuation of time series data, and using threshold algorithm to eliminate data that does not meet the predetermined classification standard; The data missing preprocessing includes using linear interpolation method to fill the missing data points, and using path reconstruction algorithm to reconstruct the lost path information according to the existing path data; Through data cleaning preprocessing and data missing preprocessing on the initial data group Draw, the data set D(t) at time t is formed after integration. 4.The method according to claim 3, characterized in that: The S2 includes S21 and S22; S21, by substituting the data set D(t) into the established garbage can classification efficiency calculation formula in the garbage recycling area, the garbage classification efficiency of each garbage can in each garbage recycling area is analyzed, and the classification efficiency E(i, t) of the ith garbage can in the garbage recycling area at time t is obtained. The classification efficiency E(i, t) of the ith garbage can is obtained through the following garbage can classification efficiency calculation formula: ； In the formula, Tc(i, t) represents the garbage filling degree of the ith garbage can at time t, Tmax(i) represents the upper limit of the filling capacity of the ith garbage can, Fl(i, t) represents the garbage classification state of the ith garbage can at time t, Lx(i, t) represents the garbage can type of the ith garbage can at time t, which is used to judge the relationship between the garbage in the ith garbage can and the classification standard, and α represents the efficiency coefficient, and 0 < α < 1; 1 indicates that the garbage in the ith garbage can meets the classification standard, and 0 indicates that the garbage in the ith garbage can does not meet the classification standard. 5.The method according to claim 4, characterized in that: S22, by substituting the classification efficiency E(i, t) of the ith garbage can in the garbage recycling area at time t obtained into the established garbage recycling area classification efficiency calculation formula, the garbage classification efficiency of each garbage recycling area is analyzed, the classification efficiency E(r, t) of the rth garbage recycling area at time t is obtained, and the classification efficiency vector E is composed by integrating the classification efficiency of each garbage recycling area; The classification efficiency E(r, t) of the rth garbage recycling area at time t is calculated and obtained through the following garbage recycling area classification efficiency calculation formula: ； In the formula, N(r) represents the rth garbage recycling area. The classification efficiency vector E is specifically E={E(1, t), E(2, t), …, E(r, t)}.

6. The method according to claim 5, wherein: The S3 includes S31; S31, by associating the data set D and the historical record information of each garbage recycling area, the density prediction garbage amount G(r, t) of the rth garbage recycling area at time t is obtained; The density prediction garbage amount G(r, t) of the rth garbage recycling area at time t is obtained through the following association formula: ； In the formula, Graw(r, t) represents the preliminary prediction garbage amount of the rth garbage recycling area at time t, γ represents the adjustment coefficient, and Gavg(r) represents the historical average garbage amount of the rth garbage recycling area; The preliminary prediction garbage amount Graw(r, t) of the rth garbage recycling area at time t is obtained through the following calculation formula: ； In the formula, Gyc(i, t) represents the prediction garbage amount of the ith garbage can at time t; The prediction garbage amount Gyc(i, t) of the ith garbage can at time t is obtained through the following calculation formula: ； In the formula, Zl(i, t-1) represents the garbage weight of the ith garbage can at time t-1, and β represents the influence coefficient. 7.The method of claim 1, wherein: The S5 includes S51; S51, by summarizing the classification efficiency vector E, the density prediction garbage amount G and the recycling path optimization vector C, the park garbage recycling efficiency index R is obtained, which is marked as the park garbage recycling efficiency index Rend after execution, the park garbage recycling efficiency index R calculated when the recycling path optimization vector C applied in the last time period is extracted, and is marked as the park garbage recycling efficiency index Rbefore before execution, and the optimization effect of the garbage recycling area in the park is analyzed; The park garbage recycling efficiency index R is obtained through the following calculation formula: ； In the formula, E(m, t) represents the classification efficiency of the mth garbage recycling area at time t, G(m, t) represents the density predicted garbage amount of the mth garbage recycling area at time t, C(m, t) represents the recycling cost of the mth garbage recycling area at time t, w1 represents the adjustment coefficient of the area garbage amount to the park garbage recycling efficiency index, w2 represents the adjustment coefficient of the predicted garbage amount to the park garbage recycling efficiency index, and exp represents an exponential decay function. The optimization effect is obtained by the following comparison mode: When the park garbage recycling efficiency index Rbefore before execution is greater than the park garbage recycling efficiency index Rend after execution, an optimization effect not in effect result is obtained, the recycling path optimization vector C is generated again, and the recycling path optimization vector C is applied; When the park garbage recycling efficiency index Rbefore before execution is less than the park garbage recycling efficiency index Rend after execution, an optimization effect in effect result is obtained, and the recycling path optimization vector C and the park garbage recycling efficiency index R are stored.

8. A smart park integrated management system applied to execute the smart park integrated management method of any one of claims 1-7. The park data acquisition module, the data classification efficiency module, the correlation analysis module, the optimization module and the optimization evaluation module are included. The park data acquisition module acquires multi-dimensional data information in real time by deploying a sensor group in the garbage recycling area and the garbage transport vehicle, and obtains a data set D(t) through integration processing. The data classification efficiency module analyzes the garbage classification efficiency of each garbage recycling area by substituting the data set D(t) into the established garbage recycling area classification efficiency calculation formula, and obtains a classification efficiency vector E by integrating the garbage classification efficiency of each garbage recycling area. The correlation analysis module obtains the density predicted garbage amount G of the garbage recycling area by correlating the data set D(t) and the historical record information of each garbage recycling area. The optimization module obtains the recycling cost of the garbage recycling area by substituting the classification efficiency vector E and the density predicted garbage amount G into the analysis, and obtains a recycling path optimization vector C by integrating the recycling cost of each garbage recycling area. The optimization evaluation module obtains a park garbage recycling efficiency index R by summarizing the classification efficiency vector E, the density predicted garbage amount G and the recycling path optimization vector C, and analyzes the optimization effect of the garbage recycling area in the park.

Images