CN116911481B

CN116911481B - Garbage collection and transportation system and method based on big data processing

Info

Publication number: CN116911481B
Application number: CN202310956114.2A
Authority: CN
Inventors: 黄玉群
Original assignee: Shenzhen Xinzhang Environmental Protection Technology Co ltd
Current assignee: Shenzhen Xinzhang Environmental Protection Technology Co ltd
Priority date: 2023-07-31
Filing date: 2023-07-31
Publication date: 2024-05-28
Anticipated expiration: 2043-07-31
Also published as: CN116911481A

Abstract

The invention relates to the technical field of big data, in particular to a garbage collection and transportation system and method based on big data processing. The method comprises the following steps: obtaining garbage point location distribution data; extracting feature data of the garbage point location distribution data, so as to obtain garbage point filling emergency degree feature data and garbage point relative distance feature data; the shortest garbage collection and transportation route data are obtained according to the garbage point relative distance characteristic data mining, and the shortest garbage collection and transportation route data are optimized according to the garbage point filling emergency degree characteristic data, so that optimized garbage collection and transportation route data are obtained; and carrying out real-time scheduling optimization on the optimized garbage collection and transportation route data, thereby acquiring real-time scheduling feedback data, and sending the real-time scheduling feedback data to a garbage collection and transportation system based on big data processing so as to execute real-time garbage collection and transportation processing. The invention is beneficial to realizing accurate garbage collection and transportation scheduling and avoiding low collection and transportation efficiency or resource waste caused by misjudgment.

Description

Garbage collection and transportation system and method based on big data processing

Technical Field

The invention relates to the technical field of big data, in particular to a garbage collection and transportation system and method based on big data processing.

Background

The garbage collection and transportation method refers to a series of technical and operational steps taken to effectively and efficiently collect and dispose of garbage. These methods aim to collect and transport urban, community or personal generated waste to a waste disposal facility for proper disposal to maintain environmental and public health. In the conventional garbage collection method, garbage collection vehicles generally collect according to a fixed route, resulting in underutilization of resources. Some areas may have less garbage, but still need to be fixedly collected and transported, so that resource waste is caused.

Disclosure of Invention

The invention provides a garbage collection and transportation system and method based on big data processing to solve at least one technical problem.

The application provides a garbage collection and transportation method based on big data processing, which comprises the following steps:

Step S1: the method comprises the steps of obtaining garbage point position distribution data, wherein the garbage point position distribution data comprise garbage point position data, garbage point capacity data and garbage point historical filling data, and the garbage point historical filling data comprise garbage point historical filling data and garbage point historical filling put-in data;

Step S2: extracting feature data of the garbage point location distribution data, so as to obtain garbage point filling emergency degree feature data and garbage point relative distance feature data;

step S3: the shortest garbage collection and transportation route data are obtained according to the garbage point relative distance characteristic data mining, and the shortest garbage collection and transportation route data are optimized according to the garbage point filling emergency degree characteristic data, so that optimized garbage collection and transportation route data are obtained;

Step S4: and carrying out real-time scheduling optimization on the optimized garbage collection and transportation route data, thereby acquiring real-time scheduling feedback data, and sending the real-time scheduling feedback data to a garbage collection and transportation system based on big data processing so as to execute real-time garbage collection and transportation processing.

According to the method, the garbage point location distribution data is obtained, the characteristic data is extracted, and the garbage collection and transportation route data is optimized, so that the garbage collection and transportation route can be optimized, and garbage can be collected more efficiently by a garbage collection and transportation vehicle. The optimized garbage collection and transportation route can reduce the driving distance and time of the vehicle, thereby improving the garbage collection and transportation efficiency. By optimizing the garbage collection and transportation route, the driving mileage and the oil consumption of the vehicle can be reduced, thereby reducing the garbage collection and transportation cost. In addition, through real-time scheduling optimization, the resources of the garbage collection and transportation vehicle can be better utilized, and the operation cost is further reduced. The filling state and the distance information of the garbage point are accurately judged by acquiring the filling emergency degree characteristic data and the relative distance characteristic data of the garbage point. The method is favorable for realizing accurate garbage collection and transportation scheduling, and low collection and transportation efficiency or resource waste caused by misjudgment is avoided. The method based on big data processing can analyze and mine a large amount of garbage point location distribution data, obtain key characteristic information of garbage collection and transportation from the garbage point location distribution data, and further optimize collection and transportation routes and scheduling. Such an intelligent garbage collection and transportation system helps to improve overall garbage management level and efficiency. By optimizing the garbage collection and transportation route and scheduling, the running of garbage vehicles on urban roads is reduced, and the traffic jam and tail gas emission can be reduced, so that the adverse effect on the environment is reduced, and the urban environment quality is improved.

Preferably, step S1 is specifically:

step S11: collecting position data of the garbage point by using GPS equipment so as to obtain position original data of the garbage point;

Step S12: collecting capacity data of the garbage point through the embedded intelligent sensing equipment, so as to obtain capacity original data of the garbage point;

Step S13: acquiring historical filling data of a garbage point through Internet of things equipment so as to acquire historical filling raw data, wherein the garbage point raw data comprises garbage point position raw data, garbage point capacity raw data and historical filling raw data;

step S14: the method comprises the steps of cleaning original data of garbage points, so as to obtain preprocessing data of the garbage points, wherein the original data of the garbage points comprise original data of positions of the garbage points, original data of capacities of the garbage points and original data of historical fillers;

Step S15: and carrying out security verification on the garbage point preprocessing data so as to obtain garbage point distribution data.

According to the method, the position data and the capacity data of the garbage point can be accurately obtained by utilizing the GPS equipment and the embedded intelligent sensing equipment. Meanwhile, the historical filling data of the garbage points are collected through the Internet of things equipment, and the historical record of the filling state of the garbage points can be obtained. Accurate acquisition of the data is helpful for accurately knowing the actual condition and filling state of the garbage point. In step S1, the original data of the garbage point is cleaned, which is helpful to remove noise, outliers and repeated information in the data, and improve the quality and accuracy of the data. The data preprocessing process can provide clean and complete data, and provides a more reliable basis for extracting subsequent characteristic data and optimizing a route.

Preferably, the cleaning of the raw data is performed by a garbage point raw data cleaning calculation formula, wherein the garbage point raw data cleaning calculation formula specifically comprises:

P'(t)＝{P(t),f(P(t))≥θP_avg,f(P(t))<θ}；

P' (t) is garbage point preprocessing data, P (t) is garbage point original data, f (P (t)) is an outlier probability distribution function of the garbage point original data, θ is outlier threshold data, P _avg is average position data of the garbage point, f (x) is an outlier probability distribution function, x is specific item data of the garbage point, μ is specific item average length data of the garbage point, σ is specific item standard deviation data of the garbage point, t is garbage point time sequence data, and α is a function form adjustment item.

The invention constructs a garbage point original data cleaning calculation formula, which carries out abnormal value detection on the garbage point original data through a probability distribution function f (P (t)) and judges whether the garbage point data is an abnormal value or not according to an abnormal threshold value theta. When the anomaly probability f (P (t)) of the original data of the garbage point is larger than or equal to the threshold value theta, the original data P (t) is reserved, otherwise, the original data P (t) is replaced by a specific value P' (t), and therefore data cleaning and processing are conducted. Through a calculation formula, the garbage point original data P (t) is converted into the preprocessing data P' (t), and the data preprocessing is helpful for removing abnormal values, so that the preprocessing data is cleaner and more accurate. The parameters in the formula influence the shape and position of the anomaly probability distribution function f (P (t)) with respect to each other by a function morphology adjustment term α (t- μ). Where μ is term-specific average length data of the garbage point, σ is term-specific standard deviation data of the garbage point, and α is a parameter for controlling the morphological adjustment of the function. By adjusting the parameters, the method can flexibly adapt to the abnormal detection requirements of different garbage point data, so that the abnormal value detection effect is more accurate. In the calculation formula, the influence of the function morphology adjustment term α (t- μ) on the probability distribution function f (P (t)) is nonlinear. By adjusting μ and σ, the center position and shape of the function can be controlled, thereby affecting the sensitivity of outlier detection. The anomaly threshold value θ is a threshold value for setting the anomaly probability, and determines which data are considered to be anomaly values. The average position data P _avg of the garbage points is used for comparing the difference between the garbage point data and the average position, and further determining whether the garbage point data is abnormal. The garbage point original data cleaning calculation formula can realize detection and processing of abnormal values in the garbage point original data through probability distribution functions and parameter adjustment, the preprocessed data is cleaner and more accurate, and a more reliable data basis is provided for subsequent feature data extraction and garbage collection and transportation route optimization. By reasonably selecting parameters, the formula can be suitable for the processing requirements of different garbage point data, and the efficiency and the precision of a garbage collection and transportation system are effectively improved.

Preferably, step S2 is specifically:

Step S21: performing differential calculation on the garbage point location distribution data so as to obtain filling change degree characteristic data;

Step S22: marking the filling change degree characteristic data by using a preset filling change degree marking mode, so as to obtain filling emergency degree characteristic data;

step S23: extracting relative distance characteristics from the garbage point location distribution data so as to obtain relative distance characteristic data;

Step S24: and selecting relevant characteristics of the garbage points from the filling emergency degree characteristic data and the relative distance characteristic data, thereby acquiring the filling emergency degree characteristic data of the garbage points and the relative distance characteristic data of the garbage points.

According to the invention, the characteristic data of the filling change degree of the garbage point location distribution data can be obtained through the differential calculation in the step S21. These data will reflect the trend of the filling of the point of waste, including the increase or decrease of the filling, helping to identify the filling urgency of the point of waste. In step S22, the filling change degree feature data is marked by a preset filling change degree marking mode, so as to obtain filling emergency degree feature data. These data will classify the fill urgency of the point of waste, e.g. marking it as urgent fill, general fill or not, to reflect the shipping priority of the point of waste. In step S23, the relative distance feature extraction is performed on the garbage point location distribution data, so that the relative distance feature data between the garbage points can be obtained. The data show the spatial distribution relation among different garbage points, and are helpful for searching the shortest garbage collection and transportation route. Through step S24, garbage point related feature selection is performed on the filling emergency degree feature data and the relative distance feature data, so that filling emergency degree feature data and relative distance feature data of the garbage point can be obtained. The characteristic data can be used as an important basis for optimizing the garbage collection and transportation route, and helps to select the optimal collection and transportation route.

Preferably, step S21 is specifically:

step S211: performing time sequence detection on the garbage point history filling data in the garbage point distribution data so as to obtain time sequence garbage point history filling data;

step S212: performing optimized time sequence data smoothing processing on time sequence garbage point historical filler data so as to obtain smoothed garbage point historical filler data;

step S213: and carrying out differential calculation on the historical filler data of the smooth garbage points so as to obtain characteristic data of the filling change degree.

According to the invention, through the time sequence detection in the step S211, the historical filler data of the garbage points can be extracted from the garbage point distribution data. These data are records of the time-dependent filling of the landfill site, and are important for subsequent data processing and analysis. In step S212, the historical filler data of the garbage point is smoothed by optimizing the time series data smoothing method. The smoothed data can remove noise and abnormal values, reduce data fluctuation, enable the data to be more stable and reliable, and provide a more accurate basis for calculation of the subsequent filling change degree. The filling change degree characteristic data is obtained by the differential calculation in step S213. The data show the change trend and the change rate of the filling of the garbage points, and help judge the filling emergency degree of the garbage points. The filling change degree characteristic data is key information for optimizing the garbage collection and transportation route.

Preferably, the optimizing time series data smoothing process in step S212 performs smoothing processing by optimizing a time series data smoothing calculation formula, wherein the optimizing time series data smoothing calculation formula is specifically:

For smoothing the historical filler data of the garbage points, H _smooth[t] is the historical filler data of the smooth garbage points corresponding to the t-th time point, H _smooth[t-1] is the historical filler data of the smooth garbage points corresponding to the t-1 th time point, H _smooth[t+1] is the historical filler data of the smooth garbage points corresponding to the t+1th time point, f (x, y, z) is an optimized time sequence data smoothing calculation function, x is a first variable item, y is a second variable item, z is a third variable item, M is a smoothing constant adjustment item, delta is a smoothing step length parameter item, alpha is a smoothing parameter,/> The sign is calculated for the partial derivative, β is the noise suppression parameter, and t is the time data.

The invention constructs an optimized time sequence data smoothing calculation formula, which optimizes and smoothes historical filler data of garbage points. The smoothed data can remove noise, outliers and data fluctuations, making the data smoother and more reliable. Such data smoothing helps to improve data quality and reduce data volatility, thereby providing a more accurate data basis for the calculation of subsequent fill change levels. In the calculation formula, parameters M, delta, alpha and beta influence the data smoothing effect. Wherein M is a smoothing constant adjustment term for controlling the smoothing degree, and adjusting the size of M can affect the smoothness of the smoothed data. Delta is a smoothing step size parameter term used to control the step size of the smoothing, and proper adjustment of delta balances the smoothing effect and the calculation speed. Alpha and beta are smoothing parameters and noise suppression parameters, respectively, and by adjusting these two parameters, the shape of the smoothing function and the effect of suppressing noise can be controlled. In the optimized time series data smoothing calculation function f (x, y, z), x, y, z represent the first, second and third variable terms, respectively, which are the smoothed garbage point history filler data corresponding to the previous, current and subsequent times. By substituting these variables into the function f (x, y, z), smoothed data can be obtainedWherein the method comprises the steps ofRepresenting the partial derivative calculation symbol for calculating the rate of change of the data, i.e. the trend of the filler over time. The function f (x, y, z) integrates the data of the previous time, the current time, and the subsequent time, thereby realizing the smoothing process. The invention realizes the optimized smooth processing of the historical filler data of the garbage point by adjusting the parameters M, delta, alpha, beta and calculating the change rate of the data. By reasonably adjusting parameters, smoother and more reliable historical filler data of the garbage points can be obtained, and a more accurate and reliable data basis is provided for calculation of the subsequent filling change degree and optimization of garbage collection and transportation routes.

Preferably, step S24 is specifically:

Step S241: acquiring historical garbage point characteristic data, and carrying out characteristic importance assessment on filling emergency degree characteristic data and relative distance characteristic data by utilizing the historical garbage point characteristic data so as to acquire characteristic importance data;

step S242: characteristic sorting is carried out on the filling emergency degree characteristic data and the relative distance characteristic data by utilizing characteristic importance data distribution, so that characteristic sorting data are obtained;

Step S243: and carrying out recursive feature elimination on the feature ordering data so as to obtain the feature data of the filling emergency degree of the garbage points and the feature data of the relative distance of the garbage points.

According to the invention, the characteristic importance evaluation is carried out on the filling emergency degree characteristic data and the relative distance characteristic data by acquiring the historical garbage point characteristic data and utilizing the data. The feature importance evaluation can determine which features have the greatest influence on garbage collection and transportation route optimization, and is helpful for screening out the features with the most decision significance. In step S24, the filling emergency degree feature data and the relative distance feature data are feature-ordered by using the feature importance data distribution. Such ordering may rank the data according to the importance level of the features so that the important features are ranked ahead, providing a valuable ordering basis for subsequent recursive feature elimination. By performing recursive feature elimination on the feature ordering data, features of the feature data that contribute less to garbage collection and transportation route optimization can be gradually removed. In the recursive feature elimination process, feature selection and model training are repeated until an optimal feature set is selected. The method can help to remove redundant features, reduce data dimension and improve model efficiency and accuracy. The feature importance assessment, feature ordering and recursive feature elimination in the invention provide important support for the selection and optimization of the garbage point filling emergency degree feature data and the relative distance feature data. By the method, the characteristic with the greatest contribution to the garbage collection and transportation route optimization can be selected, and redundant characteristics are removed, so that the precision and efficiency of the garbage collection and transportation route optimization are improved, and an intelligent and efficient garbage collection and transportation system is realized.

Preferably, step S3 is specifically:

Step S31: performing node conversion according to the relative distance characteristic data of the garbage points, thereby obtaining the node data of the garbage points;

step S32: carrying out road travel time edge weight calculation on the node data of the garbage point map so as to obtain relative distance edge weight data;

step S33: constructing a graph structure according to the node data of the garbage point map and the relative distance edge weight data, so as to acquire the data of the garbage point map;

step S34: carrying out shortest path search on the garbage dot diagram data so as to obtain shortest path data;

step S35: path optimization is carried out on the shortest path data, so that optimized shortest path data are obtained;

step S36: carrying out path backtracking on the optimized shortest path data so as to obtain shortest garbage collection and transportation route data;

Step S37: and optimizing the shortest garbage collection and transportation route data by utilizing the garbage point filling emergency degree characteristic data, thereby obtaining optimized garbage collection and transportation route data.

In the invention, through steps S31 to S34, the garbage point diagram data is constructed according to the garbage point relative distance characteristic data, and the shortest path is calculated. The path planning can ensure that the distance travelled by the garbage truck is shortest, thereby saving time and energy and improving garbage collection and transportation efficiency. And (3) performing path optimization on the shortest path data through steps S35 to S37, and performing path optimization by utilizing the characteristic data of the emergency degree of filling the garbage points to obtain optimized garbage collection and transportation route data. The route optimization considers the filling emergency degree of the garbage points, so that the garbage truck can preferentially collect and transport the garbage points which are filled in an emergency manner, and the garbage collection and transport efficiency and response speed are further improved. The invention utilizes the feature data of the garbage points and the relative distance information, and realizes the intelligent garbage collection and transportation route planning through the calculation of the graph structure construction, the shortest path search and the like. The filling emergency degree of the garbage points is considered in the route optimization process, so that the garbage collection and transportation system can make intelligent decisions according to actual conditions, and the overall garbage collection and transportation efficiency and the resource utilization rate are improved. And the path planning, the route optimization and the intelligent decision in the step S3 provide important support for optimizing the garbage collection and transportation route. By the method, intelligent planning and optimization of the garbage collection and transportation route can be realized, garbage collection and transportation efficiency and response speed are improved, resource waste is reduced, and therefore a more intelligent, efficient and environment-friendly garbage collection and transportation system is realized.

Preferably, step S4 is specifically:

Step S41: detecting the garbage points in real time through terminal equipment, so as to obtain real-time garbage filler data;

Step S42: performing garbage filler shape feature data extraction and garbage filler volume feature data extraction on real-time garbage filler image data in the real-time garbage filler data, so as to obtain real-time garbage filler shape feature data and real-time garbage filler volume feature data;

step S43: the method comprises the steps of utilizing real-time garbage filler weight data in real-time garbage filler data and a real-time garbage filler dangerous degree identification model preset locally to carry out identification calculation on real-time garbage filler shape characteristic data and real-time garbage filler volume characteristic data, so as to obtain real-time garbage filler dangerous degree data;

step S44: and generating real-time scheduling feedback data according to the real-time garbage filler risk degree data, and sending the real-time scheduling feedback data to a garbage collection and transportation system based on big data processing for real-time processing.

In the invention, the terminal equipment is used for detecting the garbage points in real time to acquire real-time garbage filler data. The real-time monitoring and data acquisition can timely acquire the actual filling condition of the garbage points, and the timeliness and the accuracy of the data are ensured. And extracting shape characteristic data and volume characteristic data of the real-time garbage filler image data to obtain the shape and volume information of the real-time garbage filler. Such feature extraction facilitates further analysis and identification of the trash fill. And identifying and calculating the shape characteristics and the volume characteristics of the real-time garbage filler by using the real-time garbage filler weight data and a preset dangerous degree identification model, so as to obtain the dangerous degree data of the real-time garbage filler. Such identification calculations can help determine if there is a hazard with the landfill, thereby taking appropriate action to ensure safe and environmentally friendly garbage collection and transportation. And generating real-time scheduling feedback data according to the real-time garbage filler risk degree data, and sending the real-time scheduling feedback data to a garbage collection and transportation system based on big data processing for real-time processing. The real-time scheduling feedback can guide the running path and operation of the garbage collection and transportation vehicle in time, optimize the garbage collection and transportation route and improve the garbage collection and transportation efficiency and response capability.

Preferably, the invention also provides a garbage collection and transportation system based on big data processing, which comprises:

the garbage point location distribution data module is used for acquiring garbage point location distribution data, wherein the garbage point location distribution data comprises garbage point position data, garbage point capacity data and garbage point history filling data, and the garbage point history filling data comprises garbage point history filling data and garbage point history filling material throwing data;

The feature data extraction module is used for extracting feature data of the garbage point location distribution data so as to obtain the garbage point filling emergency degree feature data and the garbage point relative distance feature data;

The optimized garbage collection and transportation route data acquisition module is used for generating shortest garbage collection and transportation route data according to the garbage point relative distance characteristic data, and optimizing the shortest garbage collection and transportation route data by utilizing the garbage point filling emergency degree characteristic data so as to acquire optimized garbage collection and transportation route data;

And the real-time scheduling and scheduling optimization module is used for performing real-time scheduling optimization on the optimized garbage collection and transportation route data so as to acquire real-time scheduling feedback data, and transmitting the real-time scheduling feedback data to a garbage collection and transportation system based on big data processing so as to execute real-time garbage collection and transportation processing.

The invention has the beneficial effects that: and comprehensively analyzing and mining the filling emergency degree characteristic data and the relative distance characteristic data of the garbage points, thereby realizing the intelligent planning of the shortest garbage collection and transportation route. In the step, the optimal garbage collection and transportation route is selected through big data processing and algorithm optimization, so that the garbage collection and transportation vehicle can efficiently collect garbage and complete tasks in the shortest time. The generation of the garbage collection and transportation route is optimized, so that the operation cost of the garbage collection and transportation vehicle can be saved, and the garbage collection can be performed by utilizing the existing resources to the greatest extent. Through real-time scheduling optimization, the garbage collection and transportation vehicle can flexibly adjust the route according to the filling condition and road condition change of the real-time garbage points, improve the utilization efficiency of resources, reduce the fuel consumption and emission, and have positive influence on the environment. The method enables the garbage collection and transportation system to have real-time monitoring and response capability through real-time scheduling of feedback data. Once new garbage points are generated or filling conditions are changed, the system can quickly make adjustment, optimize garbage collection and transportation routes, ensure timely collection and transportation and avoid environmental problems caused by excessive filling of the garbage points. The invention fully utilizes the big data processing technology to comprehensively analyze and mine the garbage point location distribution data, and realizes the intelligent management of garbage collection and transportation through data-driven decision. Through historical filling data and real-time data of the garbage points, the system can deeply understand filling conditions and filling trends of the garbage points, so that a garbage collection and transportation strategy is scientifically decided, and garbage collection and transportation efficiency is improved. Optimizing the garbage collection and transportation route and real-time scheduling can reduce the travel distance and time of the garbage collection and transportation vehicle, reduce the exhaust emission and noise pollution of the vehicle, and have less influence on the environment. In addition, through more reasonable route planning and resource utilization, the method is also beneficial to reducing the generation of garbage point overflow and open-air garbage, and has positive effects on urban environment protection.

Drawings

Other features, objects and advantages of the application will become more apparent upon reading of the detailed description of a non-limiting implementation, made with reference to the accompanying drawings in which:

FIG. 1 shows a flow chart of steps of a big data processing based garbage collection method of an embodiment;

FIG. 2 shows a step flow diagram of step S1 of an embodiment;

FIG. 3 shows a step flow diagram of step S2 of an embodiment;

FIG. 4 shows a step flow diagram of step S21 of an embodiment;

FIG. 5 shows a step flow diagram of step S24 of an embodiment;

FIG. 6 shows a step flow diagram of step S3 of an embodiment;

fig. 7 shows a step flow diagram of step S4 of an embodiment.

Detailed Description

The following is a clear and complete description of the technical method of the present patent in conjunction with the accompanying drawings, and it is evident that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, are intended to fall within the scope of the present invention.

Furthermore, the drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. The functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor methods and/or microcontroller methods.

It will be understood that, although the terms "first," "second," etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of example embodiments. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.

Referring to fig. 1 to 7, the application provides a garbage collection and transportation method based on big data processing, which comprises the following steps:

Specifically, for example, a GPS device is installed on a garbage site in a city or community, and position data of the garbage site is recorded periodically to obtain raw data of the garbage site. And installing an embedded intelligent sensing device on each garbage point, wherein the embedded intelligent sensing device is used for monitoring the capacity condition of the garbage point in real time and recording the capacity raw data of the garbage point. And establishing an Internet of things system, and acquiring filling conditions and throwing historical data of the garbage can in real time through sensor equipment connected with the garbage can so as to acquire historical filler data of the garbage point.

specifically, the filling change degree characteristic data of each garbage point is calculated, for example, by a statistical method, such as calculating an average rate of increase of the filler or an average filler change amplitude. The relative distance characteristic data between each garbage point is calculated using geometric and mathematical methods, such as calculating the euclidean distance or manhattan distance between two garbage points.

Specifically, a graph theory algorithm, such as Dijkstra algorithm or a-x algorithm, is used to construct a network graph between garbage points according to the garbage point relative distance characteristic data, and the shortest garbage collection and transportation route data is calculated. And (3) taking actual road conditions and traffic jam conditions into consideration, and using a dynamic path planning algorithm to find the optimal shortest garbage collection and transportation route data.

Specifically, for example, the optimized garbage collection and transportation route data is updated by using the real-time garbage point filler data, so that the accuracy and the real-time performance of the route are ensured. And scheduling the garbage collection and transportation route through an optimization algorithm based on the real-time traffic data and the garbage point filling emergency degree characteristic data so as to optimize the garbage collection and transportation efficiency to the greatest extent. And designing a feedback mechanism, and sending the real-time scheduling feedback data to a garbage collection and transportation system based on big data processing so as to perform real-time processing and monitoring.

Preferably, step S1 is specifically:

specifically, for example, a GPS device is installed on each garbage point, and longitude and latitude coordinates of the garbage point are recorded periodically to obtain the raw data of the garbage point. And collecting the position information of the garbage point by using a GPS positioning mobile phone APP or a GPS data collector, and storing the position information as the original data of the garbage point.

Specifically, for example, an embedded intelligent sensing device is installed in the garbage can of each garbage point and is used for monitoring the capacity condition of the garbage can in real time and recording the capacity raw data of the garbage point. The embedded intelligent sensing equipment can be a weighing sensor or a capacity sensor, and the capacity raw data of the garbage point can be obtained by collecting the weight or capacity information of the garbage can in real time.

Specifically, for example, an internet of things system is established, and filling conditions and historical throwing data of the garbage can are obtained in real time through sensor equipment connected with the garbage can, so that historical filling data of garbage points are obtained. The internet of things equipment can record the time, filling amount, types and the like of garbage put in the garbage can each time and is used for generating historical filler original data.

Specifically, for example, data deduplication and outlier processing are performed to ensure accuracy and integrity of data, so as to obtain clean garbage point original data.

Specifically, for example, the garbage point position data is formatted and normalized.

Specifically, for example, the garbage point capacity data and the history filler data are subjected to cleaning and normalization processing.

Specifically, for example, the safety verification is performed on the preprocessed junk point data, so that the credibility and the integrity of the data are ensured, and the influence of errors or abnormal data on the subsequent analysis is avoided. The data is verified by using a data verification algorithm or an anomaly detection algorithm, such as hash verification or anomaly detection, so as to ensure the reliability and the safety of the data. The method ensures that the garbage site distribution data can be correctly used and applied to the subsequent garbage collection and transportation method.

P'(t)＝{P(t),f(P(t))≥θP_avg,f(P(t))<θ}；

Preferably, step S2 is specifically:

Specifically, for example, the historical filler data of each garbage point is subjected to time series analysis, and the filler variation, i.e., the difference, at adjacent time points is calculated. The difference can be expressed by the following formula: differential value = current time point filler amount-last time point filler amount. And obtaining characteristic data of the filling change degree through differential calculation, wherein the characteristic data is used for representing the change condition of the garbage point filling.

Specifically, for example, a set of marking modes or rules are preset for marking the filling emergency degree of the garbage points according to the filling change degree characteristic data. For example, the filling emergency degree of the garbage points can be classified into three levels of low, medium and high according to the magnitude of the differential value. And marking the filling change degree characteristic data according to a preset marking mode, so as to obtain filling emergency degree characteristic data which is used for representing the filling emergency degree of the garbage point.

Specifically, for example, the distance between each pair of garbage points is calculated to obtain the relative distance between the garbage points. The distance between garbage points may be calculated using Euclidean distance, manhattan distance, or other distance metrics. And obtaining relative distance characteristic data for representing the distance relation between the garbage points through relative distance characteristic extraction.

Specifically, the filling emergency degree feature data and the relative distance feature data are evaluated and screened using, for example, a feature selection algorithm (e.g., variance selection method, chi-square test, information gain). Selecting key features which have important influence on the garbage collection and transportation route optimization, and removing features which have little influence on the garbage collection and transportation route optimization, so as to obtain the garbage point filling emergency degree feature data and the garbage point relative distance feature data, and using the data for the subsequent shortest route generation and the garbage collection and transportation route optimization.

Preferably, step S21 is specifically:

Specifically, for example, the historical filler data of each garbage point is subjected to time series analysis, and arranged in time series. And detecting the time characteristics of trend, seasonality and periodicity in the time sequence data by using a statistical method or a machine learning algorithm. And obtaining time sequence garbage point historical filler data according to the time sequence detection result, wherein the time sequence garbage point historical filler data is used for representing the time change condition of the garbage point historical filler.

Specifically, for example, a time sequence smoothing algorithm is used to smooth the time sequence garbage point history filler data so as to eliminate noise and abnormal values in the data and make the data smoother. Common smoothing algorithms include moving average, exponential smoothing, weighted moving average. And (3) obtaining smooth garbage point historical filler data by optimizing time sequence data smoothing processing, wherein the smooth garbage point historical filler data is used for more accurately reflecting the trend and change of garbage point fillers.

Specifically, for example, the difference calculation is performed on the historical filler data of the smooth garbage points, so as to obtain the variation, namely the difference, of the fillers at adjacent time points. The difference can be expressed by the following formula: differential value = current time point filler amount-last time point filler amount. And the characteristic data of the filling change degree can be obtained through differential calculation and is used for representing the change condition of the filling material of the garbage point, so that a basis is provided for subsequent filling emergency degree evaluation and shortest path generation.

Preferably, step S24 is specifically:

Specifically, for example, historical garbage point feature data is acquired: the filling emergency degree characteristic data and the relative distance characteristic data obtained in the previous steps S21 and S22 are combined with the historical filling data and capacity data of the garbage points to form a historical garbage point characteristic data set. Feature importance assessment: training and analyzing the historical garbage point feature data set by utilizing a feature importance assessment method such as random forest, gradient lifting tree and feature importance ranking to obtain importance scores of filling emergency degree feature data and relative distance feature data. Acquiring feature importance data: the importance scores of the filling emergency degree feature data and the relative distance feature data are sorted into feature importance data.

Specifically, the filling emergency degree feature data and the relative distance feature data are ordered, for example, according to the feature importance data. And sorting the feature data in a descending order according to the feature importance, so as to obtain feature sorting data. The feature ordering data may help determine which features have a greater impact on filling urgency and relative distance during garbage collection, thereby prioritizing the use of more important feature data in subsequent steps.

In particular, less important feature data is gradually removed in combination with feature ordering data, for example using a recursive feature elimination (Recursive Feature Elimination, RFE) algorithm. In each step, some feature data with the lowest current rank is removed by utilizing feature importance information in the feature ranking data. Repeating the steps until the required characteristic data of the filling emergency degree of the garbage points and the characteristic data of the relative distance of the garbage points are obtained, wherein the characteristic data plays an important role in optimizing the route planning and the dispatching in the garbage collection and transportation process.

Preferably, step S3 is specifically:

Specifically, for example, each garbage point is used as a node according to the acquired relative distance characteristic data, and a relative distance relation between the garbage points is established. The garbage point map can be represented by using an undirected graph or a directed graph, wherein nodes of the graph are the garbage points, and edges of the graph represent the relative distance relation between the garbage points.

specifically, for example, the road travel time between the garbage points is calculated from the obtained garbage point map node data in combination with the map data and the traffic information. The travel time on the way may be used as a weight of the edge, representing travel time or distance between garbage points, for shortest path search in the subsequent step S34.

specifically, for example, the garbage dot pattern node data and the relative distance edge weight data are combined to construct a complete garbage dot pattern structure. The garbage map is a map structure containing garbage nodes and relative distance edge weights and is used for representing the spatial relationship between the garbage nodes and the running time information.

Specifically, for example, using the garbage map data, a shortest path search algorithm, such as Dijkstra algorithm, floyd-Warshall algorithm, is performed in the map to find the shortest path between two garbage points. The shortest path represents the shortest travel route from one refuse point to another, taking into account travel time or distance.

Specifically, for example, on the basis of the shortest path data, a path optimization algorithm, such as a genetic algorithm, a simulated annealing algorithm, and the like, may be performed to further optimize path planning. The path optimization considers the filling emergency degree characteristic data among the garbage points and the factors of possible traffic jams to obtain a more optimized path planning result.

Specifically, for example, path backtracking is performed on the basis of optimizing shortest path data, and the path backtracking is gradually performed from an end point garbage point to a start point garbage point, so that complete shortest garbage collection and transportation route data is obtained. The shortest garbage collection route data represents the travel route of the garbage truck, including passing garbage points and the sequence of travel.

Specifically, for example, the shortest garbage collection route data obtained in step S36 is optimized in combination with the garbage point filling emergency degree feature data obtained in step S24. The optimization aim is to adjust the garbage collection and transportation route according to the filling emergency degree characteristic data of the garbage points, and to preferentially collect and transport the filling emergency garbage points, so that the collection and transportation efficiency and the response speed are improved.

Preferably, step S4 is specifically:

In particular, for example, a sensor device, such as a pressure sensor, a weight sensor, is installed on each refuse site for monitoring the filling of the refuse site in real time. The sensor device may transmit filler data of the point of waste to the waste collection system periodically or in real time.

specifically, for example, a camera or other equipment is used for carrying out image acquisition on the garbage points, so as to acquire image data of the real-time garbage filler. And (3) performing image processing and calculation on the real-time image data of the garbage filler, and extracting shape characteristic data of the garbage filler, such as the outline and the area of the filler. And acquiring the volume data of the real-time garbage filler through devices such as a sensor.

Specifically, for example, the real-time garbage filler shape characteristic data and the volume characteristic data are identified and calculated by utilizing a pre-established local hazard degree identification model in combination with the acquired real-time garbage filler weight data. The dangerous degree recognition model can judge the dangerous degree of the garbage according to the shape, the volume and other characteristics of the filler, for example, whether the dangerous degree exceeds the upper capacity limit or whether dangerous substances exist. Building a local risk degree identification model: a local dangerous degree identification model is built in advance in the garbage collection and transportation system. The model is a machine learning model, and is trained according to historical data to learn the relation between the shape and the volume characteristics of the garbage filler and the dangerous degree. Real-time garbage filler hazard degree identification and calculation: and inputting the shape characteristic data, the volume characteristic data and the weight data of the real-time garbage filler into a local dangerous degree identification model for identification calculation. The model can judge according to the real-time data to obtain the dangerous degree of the garbage filler, such as whether the capacity upper limit is exceeded or not and whether dangerous substances are contained or not.

Specifically, the real-time scheduling feedback data is generated according to the acquired real-time garbage filler risk degree data, for example. The real-time scheduling feedback data can comprise information such as the receiving and transporting priority, receiving and transporting time and the like of the garbage points, so that the garbage receiving and transporting system can perform real-time scheduling, and the garbage receiving and transporting route is optimized.

Preferably, the present invention also provides a big data processing based garbage collection and transportation system for executing the big data processing based garbage collection and transportation method as described above, the big data processing based garbage collection and transportation system comprising:

The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.

The foregoing is only a specific embodiment of the invention to enable those skilled in the art to understand or practice the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. The garbage collection and transportation method based on big data processing is characterized by comprising the following steps of:

step S2: extracting feature data of the garbage point location distribution data, so as to obtain garbage point filling emergency degree feature data and garbage point relative distance feature data; the step S2 specifically comprises the following steps:

step S21: performing differential calculation on the garbage point location distribution data so as to obtain filling change degree characteristic data; the step S21 specifically includes:

Step S212: performing optimized time sequence data smoothing processing on time sequence garbage point historical filler data so as to obtain smoothed garbage point historical filler data; in step S212, the optimizing time series data smoothing process performs smoothing process by optimizing a time series data smoothing calculation formula, where the optimizing time series data smoothing calculation formula specifically includes:

；

To smooth garbage point historical filler data,/> For/>Smooth garbage point history filler data corresponding to each time point,/>For/>Smooth garbage point history filler data corresponding to the individual time points,For/>Smooth garbage point history filler data corresponding to each time point,/>Smoothing the computation function for optimizing time series data,/>For the first variable term,/>For the second variable term,/>For the third variable term,/>For smoothing constant adjustment term,/>For smoothing step size parameter term,/>For smoothing parameters,/>Calculating sign for partial derivative,/>Is a noise suppression parameter,/>Is time data;

Step S213: carrying out differential calculation on the historical filler data of the smooth garbage points so as to obtain characteristic data of filling change degree;

step S24: selecting relevant characteristics of the garbage points from the filling emergency degree characteristic data and the relative distance characteristic data, so as to obtain filling emergency degree characteristic data of the garbage points and the relative distance characteristic data of the garbage points; the step S24 specifically includes:

step S243: performing recursive feature elimination on the feature ordering data so as to obtain feature data of the filling emergency degree of the garbage points and feature data of the relative distance of the garbage points;

2. The method according to claim 1, wherein step S1 is specifically:

3. The method according to claim 2, wherein the raw data cleaning is performed by a garbage point raw data cleaning calculation formula, wherein the garbage point raw data cleaning calculation formula is specifically:

；

Preprocessing data for garbage points,/> Is garbage point original data,/>Is an outlier probability distribution function of the original data of the garbage points,/>Is abnormal threshold data,/>Is the average position data of garbage points,/>As an outlier probability distribution function,/>For specific item data of garbage points,/>For specific item average length data of garbage points,/>For specific item standard deviation data of garbage points,/>Is garbage point time sequence data,/>The term is adjusted for the function morphology.

4. The method according to claim 1, wherein step S3 is specifically:

5. The method according to claim 1, wherein step S4 is specifically:

6. A big data processing based garbage collection and transportation system for performing the big data processing based garbage collection and transportation method of claim 1, the big data processing based garbage collection and transportation system comprising: