Intelligent garbage recycling system based on Internet integrated dispatching platform

Abstract

The invention provides an intelligent garbage collection system based on an Internet integrated scheduling platform, and belongs to the technical field of garbage data processing. Through the application of data processing technologies such as building of a collection prediction model and an anomaly detection mechanism, abnormal data in a period of time can be predicted and fed back to the Internet integrated scheduling platform, so that the garbage collection efficiency is improved. According to the method and the system, the data are used as reference data for garbage recycling resource scheduling to provide a recycling scheme, so that the garbage recycling efficiency is effectively improved, the resource configuration is optimized, abnormal changes of the garbage amount, the accumulation state or the throwing behavior are responded and processed in time, and powerful support is provided for formulating a more scientific and reasonable recycling scheme for an internet integrated scheduling platform.

Description

Technical Field

[0001] The present invention relates to the technical field of garbage data processing, and in particular to an intelligent garbage collection system based on an Internet integrated scheduling platform. Background Art

[0002] Traditional waste collection methods often rely on fixed recycling frequencies and routes, which can lead to a waste of resources. For example, in some areas, the trash bins may not be full, but the recycling vehicles still collect and transport the trash frequently as planned, resulting in increased fuel consumption and increased operating costs. The collected data, such as the amount and type of trash, is usually not fully utilized, which can be used to optimize recycling routes and predict future trends in waste generation. Due to the lack of data analysis capabilities, a lot of valuable information has not been effectively utilized, and the lack of effective prediction methods makes it impossible for the waste collection department to plan ahead.

[0003] Therefore, it is necessary to provide an intelligent garbage collection system based on an Internet integrated scheduling platform to solve the above technical problems. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides an intelligent garbage collection system based on an Internet integrated scheduling platform to solve the problem that the collected data cannot be fully utilized and there is a lack of effective prediction means, which makes it impossible for the garbage collection department to plan in advance.

[0005] The present invention provides an intelligent garbage collection system based on an Internet integrated scheduling platform, comprising: The data processing module is used to collect and pre-process the historical garbage collection data from each garbage site to obtain a processed historical garbage collection data set, wherein the historical garbage collection data specifically includes garbage quantity, garbage type, and recycling behavior information; A model building module is used to model the historical data based on the processed historical garbage collection data set using the ARIMA model in the time series analysis technology to obtain a recycling prediction model; The detection definition module is used to build an anomaly detection mechanism by setting anomaly thresholds, where the anomaly thresholds specifically include an anomaly threshold for the total amount of garbage, an anomaly threshold for changes in garbage accumulation, and an anomaly threshold for garbage placement behavior; The data collection module is used to obtain the garbage collection data of each garbage station according to the preset collection cycle and perform preprocessing to obtain the current garbage collection data; Model analysis module, used to extract the features of current garbage collection data and input them into the collection prediction model, and output the prediction data; The data feedback module is used to identify abnormal data that deviates significantly from normal data based on the predicted data through the set anomaly detection mechanism, and feed back the abnormal data to the Internet integrated scheduling platform to provide data for scheduling resource decisions for distributing garbage collection.

[0006] Preferably, the historical garbage collection data is collected from each garbage site and pre-processed to obtain a processed historical garbage collection data set, and the specific steps are: Collect historical garbage collection data from each garbage site, including garbage volume, garbage type, and recycling behavior information; The collected historical garbage collection data is preprocessed, specifically including cleaning, sorting and formatting, to form a processed historical garbage collection data set after the preprocessing.

[0007] Preferably, based on the processed historical garbage collection data set, the ARIMA model in the time series analysis technology is used to model the historical data to obtain the recycling prediction model, and the specific steps are: Based on the processed historical garbage collection data set, the ARIMA model in the time series analysis technology is selected for modeling; The processed historical garbage collection data set is used as a training set. The parameters of the ARIMA model are determined by inputting it into the training set to obtain a recycling prediction model, in which the parameters specifically include autoregressive terms, difference orders, and moving average terms.

[0008] Preferably, the anomaly detection mechanism is constructed by setting an anomaly threshold, and the specific steps are: According to the processed historical garbage collection data set, the standard deviation method or the quartile method is used to set the abnormal threshold of the total amount of garbage. Specifically, suppose the historical total amount of garbage data , where n is the number of observations, and the mean is calculated using the standard deviation method (for normally distributed garbage collection data) and standard deviation The expressions are:

[0009]

[0010] Next, set the abnormal threshold to and , among which, using or as a threshold; Using the quartile method (for non-normally distributed garbage collection data), calculate the first quartile , the third quartile , and the interquartile range ,in, = 25th percentile, = 75th percentile, ; Then, the anomaly threshold The calculation formula is set as:

[0011] ; Using image recognition technology, we can identify garbage images in the processed historical garbage collection dataset and set abnormal thresholds for garbage accumulation changes; Based on the garbage disposal behavior data in the processed historical garbage collection data set, an abnormal threshold is set for the garbage disposal behavior; Configure the judgment tool based on the abnormal threshold of total garbage amount, abnormal threshold of garbage accumulation change, and abnormal threshold of garbage disposal behavior.

[0012] Preferably, the judgment tool is configured based on the abnormal threshold of the total amount of garbage, the abnormal threshold of the change of garbage accumulation and the abnormal threshold of the garbage delivery behavior, and the specific steps are: Select the data monitoring and analysis script, and define the total amount of garbage, garbage accumulation changes, and garbage disposal behavior data as the data input type of the data monitoring and analysis script; Define the abnormal threshold of total garbage volume, abnormal threshold of garbage accumulation change, and abnormal threshold of garbage disposal behavior as the judgment threshold of data monitoring and analysis scripts; Set judgment logic: When it is identified that the total amount of garbage, changes in garbage accumulation, and garbage disposal behavior exceed the corresponding abnormal threshold, the identified abnormal data will be marked.

[0013] Preferably, the garbage collection data of each current garbage site is obtained and preprocessed according to a preset collection cycle to obtain the current garbage collection data, and the specific steps are: According to the preset collection cycle, regularly obtain the garbage collection data of each current garbage site; The garbage collection data of each current garbage site is cleaned, sorted and formatted to form the current garbage collection data set.

[0014] Preferably, the steps of extracting the features of the current garbage collection data and inputting them into a collection prediction model and outputting prediction data are as follows: Extract relevant features from the current waste collection dataset to input into the recycling prediction model, including waste volume, waste type, and recycling behavior; The extracted features are input into the recycling prediction model, and the prediction results are output, including data on the amount of garbage recycled and the distribution of garbage types over a period of time.

[0015] Preferably, the method of identifying abnormal data that deviates significantly from normal data based on the predicted data through a set abnormality detection mechanism, and feeding back the abnormal data to the Internet integrated scheduling platform, specifically comprises the following steps: The obtained predicted data is input into the pre-set anomaly detection mechanism, and the judgment tool is configured through the anomaly detection mechanism to predict the abnormal data; Identify the predicted abnormal data, and generate the corresponding data point deviation degree and change according to the identified data, and organize them into an abnormality identification report; The anomaly identification report is fed back to the Internet integrated scheduling platform as reference data for garbage collection resource scheduling and for proposing recycling plans.

[0016] Compared with the related art, the intelligent garbage collection system based on the Internet integrated scheduling platform provided by the present invention has the following beneficial effects: The present invention constructs a recycling prediction model and anomaly detection mechanism and other data processing technologies, and can predict abnormal data for a period of time and feed it back to the Internet integrated scheduling platform, which can be used as reference data for garbage recycling resource scheduling to propose recycling plans, effectively improving garbage recycling efficiency, optimizing resource allocation, and promptly responding to and processing abnormal changes in garbage volume, accumulation status or delivery behavior, providing strong support for the Internet integrated scheduling platform to formulate more scientific and reasonable recycling plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A module schematic diagram of an intelligent garbage collection system based on an Internet integrated scheduling platform provided by the present invention. DETAILED DESCRIPTION

[0018] The present invention will be further described below in conjunction with the accompanying drawings and implementation modes.

[0019] Embodiment 1 like Figure 1 As shown, an intelligent garbage collection system based on an Internet integrated scheduling platform includes: The data processing module is used to collect and pre-process the historical garbage collection data from each garbage site to obtain a processed historical garbage collection data set, wherein the historical garbage collection data specifically includes garbage quantity, garbage type, and recycling behavior information; In the specific implementation process, the specific steps are: Collect historical garbage collection data from each garbage site, including garbage volume, garbage type, and recycling behavior information; Specifically, the total amount of garbage at each garbage station over a period of time is collected, and the data is collected by weighing using electronic scales, usually in kilograms or tons; according to the garbage classification standards, the quantity or proportion of each type of garbage, such as recyclables, hazardous waste, wet garbage (kitchen waste), dry garbage (other garbage), etc., is collected through monitoring equipment such as cameras or other sensor devices; relevant behavioral data in the garbage recycling process is recorded, specifically the amount and time of delivery.

[0020] Preprocessing the collected historical garbage collection data, including cleaning, sorting and formatting, to form a processed historical garbage collection data set after preprocessing; Specifically, the collected historical garbage collection data are preprocessed through existing data processing tools, including checking and deleting duplicate records, processing missing data through interpolation, averaging or deletion, and classifying and unifying information such as garbage types and recycling behaviors to form a processed historical garbage collection data set for subsequent analysis.

[0021] A model building module is used to model the historical data based on the processed historical garbage collection data set using the ARIMA model in the time series analysis technology to obtain a recycling prediction model; In the specific implementation process, the specific steps are: S201. Based on the processed historical garbage collection data set, an ARIMA model in the time series analysis technology is selected for modeling; S202, using the processed historical garbage collection data set as a training set, inputting it into an ARIMA model for training, determining the parameters of the ARIMA model, and obtaining a recycling prediction model, wherein the parameters specifically include an autoregressive term p, a difference order d, and a moving average term q; Specifically, in this embodiment, the garbage volume data of a garbage site in the past year is predicted, and preliminary parameters are set through the autocorrelation function (ACF) and partial autocorrelation function (PACF) diagrams, specifically autoregressive term p=2, difference order d=1, and moving average term q=2. The processed historical garbage collection data set is used as a training set and input into the ARIMA model for training. During the training process, the model fits the data according to the set preliminary parameters such as autoregressive term p=2, difference order d=1, and moving average term q=2, and outputs the prediction results. After verification, the recycling prediction model is obtained.

[0022] The detection definition module is used to build an anomaly detection mechanism by setting anomaly thresholds, where the anomaly thresholds specifically include an anomaly threshold for the total amount of garbage, an anomaly threshold for changes in garbage accumulation, and an anomaly threshold for garbage placement behavior; In the specific implementation process, the specific steps are: S301. According to the processed historical garbage collection data set, use the standard deviation method or the quartile method to set the abnormal threshold of the total amount of garbage. Specifically, when the identified data follows a normal distribution, use ±2σ (2 standard deviations) or ±3σ (3 standard deviations) as the threshold. Specifically, the Shapiro-Wilk test or Kolmogorov-Smirnov test in the statistical method is used to test whether the data obeys the normal distribution. If the data obeys the normal distribution, the standard deviation method is used to set the abnormal threshold, and ±2σ (2 standard deviations) or ±3σ (3 standard deviations) is selected as the threshold; If the data does not follow a normal distribution, the quartile method is used to set the abnormal threshold. The lower quartile Q1, upper quartile Q3 and interquartile range IQR (Q3-Q1) of the data are calculated. Then, the abnormal value is defined as a value less than Q1-1.5IQR or greater than Q3+1.5IQR. For example, if the Q1 of a garbage station is 300 kg / day, Q3 is 700 kg / day, and IQR is 400 kg / day, the abnormal threshold is less than 100 kg / day or greater than 1300 kg / day.

[0023] S302, using image recognition technology to identify garbage images in the processed historical garbage collection data set, and setting an abnormal threshold for garbage accumulation changes; Specifically, the convolutional neural network (CNN), an existing tool in image recognition technology, is used to identify the preprocessed image, extract the characteristic information of garbage accumulation, and set the abnormal threshold of garbage accumulation change. Specifically, the threshold range is determined by comparing the garbage accumulation conditions in historical image data. In this embodiment, the abnormal threshold is set when the garbage accumulation amount exceeds 80% of the capacity of the standard collection device of the garbage station or the accumulation speed exceeds 50% per hour.

[0024] S303, setting an abnormal threshold for the garbage placement behavior based on the garbage placement behavior data in the processed historical garbage collection data set; Specifically, the cluster analysis algorithm in the existing data analysis technology is used to analyze the extracted data to find out the patterns of surge in delivery volume and abnormal delivery time, and according to the analysis results, the abnormal threshold of garbage delivery behavior is set. In this embodiment, it is set that when the delivery volume on a certain day exceeds twice the average delivery volume of the past week, the delivery volume abnormality is triggered, and when the delivery time of a certain day deviates significantly from the normal delivery time period (late at night or early morning), the delivery time abnormality is triggered.

[0025] Based on the abnormal threshold of total garbage volume, the abnormal threshold of garbage accumulation change, and the abnormal threshold of garbage disposal behavior, a judgment tool is configured. The specific steps of configuring the judgment tool are as follows: Select the data monitoring and analysis script, and define the total amount of garbage, garbage accumulation changes, and garbage disposal behavior data as the data input type of the data monitoring and analysis script; Define the abnormal threshold of total garbage volume, the abnormal threshold of garbage accumulation change, and the abnormal threshold of garbage disposal behavior as the judgment threshold of the data monitoring and analysis script; Set judgment logic: When it is identified that the total amount of garbage, changes in garbage accumulation, and garbage disposal behavior exceed the corresponding abnormal threshold, the identified abnormal data will be marked.

[0026] The data collection module is used to obtain the garbage collection data of each garbage station according to the preset collection cycle and perform preprocessing to obtain the current garbage collection data; In the specific implementation process, the specific steps are: S401, regularly obtaining garbage collection data of each current garbage site according to a preset collection cycle; Specifically, the corresponding collection cycle is set according to the scale of the garbage site. In this embodiment, for large garbage sites, data is collected once a day; and for small garbage sites, data is collected once a week or a month. Based on the set collection cycle, the existing automated data collection tools are used to regularly obtain garbage collection data from the data system of each garbage site.

[0027] S402, cleaning, sorting and formatting the garbage collection data of each current garbage site to form a current garbage collection data set; Specifically, the garbage collection data of each current garbage site is cleaned to remove duplicate, erroneous or invalid data. Specifically, for duplicate records, only one record needs to be retained; for obviously erroneous data (such as negative quantities or exceeding a reasonable range), they need to be corrected or deleted, and the cleaned data should be organized into a unified format.

[0028] Model analysis module, used to extract the features of current garbage collection data and input them into the collection prediction model, and output the prediction data; In the specific implementation process, the specific steps are: S501, extracting relevant features input into the recycling prediction model from the current garbage collection data set, specifically including garbage quantity, garbage type and recycling behavior; S502: Input the extracted features into a recycling prediction model, and output prediction results, specifically including data on the amount of garbage recycled and the distribution of garbage types within a period of time.

[0029] The data feedback module is used to identify abnormal data that deviates significantly from normal data based on the predicted data through the set anomaly detection mechanism, and feed the abnormal data back to the Internet integrated scheduling platform to provide data for the scheduling resource decision of the garbage collection distribution; In the specific implementation process, the specific steps are: S601, input the obtained prediction data into a pre-set anomaly detection mechanism, configure a judgment tool through the anomaly detection mechanism, and predict the abnormal data; Specifically, the predicted data is input into the anomaly detection mechanism through an automated data transmission system or an API interface. The anomaly detection mechanism uses a configured judgment tool to perform real-time analysis on the predicted data, by checking whether each data point in the predicted data exceeds a preset anomaly threshold. If a data point exceeds the threshold, it is considered to be abnormal data. In this embodiment, the abnormal threshold is when the garbage accumulation exceeds 80% of the capacity of the standard collection device of the garbage station or the accumulation rate exceeds 50% per hour.

[0030] S602, identifying the predicted abnormal data, and generating corresponding data point deviation and change according to the identified data, and arranging them into an abnormality identification report; Specifically, the predicted abnormal data is marked, specifically by color or label, to indicate the existence of abnormal data. For each data point marked as abnormal, the degree of deviation from the normal value is calculated by calculating the difference between the data point and the normal value, and a corresponding data point change graph is generated according to the abnormal data and its degree of deviation; S603, feeding back the abnormal identification report to the Internet integrated scheduling platform as reference data for garbage collection resource scheduling to propose a recycling plan; Specifically, the abnormal identification report is fed back to the Internet integrated scheduling platform through an automated system or manually. After receiving the abnormal data, the staff associated with the Internet integrated scheduling platform will conduct further analysis and decision-making. In this embodiment, it is identified according to the predicted abnormal identification report that the abnormal garbage recovery volume is caused by insufficient processing capacity of a certain garbage site. Then, the following recycling decisions are proposed: increase the recycling vehicles and personnel configuration of the site to improve processing capacity; or adjust and reduce the recycling plans of other sites to share the pressure of the site.

[0031] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0032] Embodiment 2 An intelligent garbage collection system based on an Internet integrated scheduling platform, comprising: A data processing module is used to collect historical garbage collection data from each garbage site and perform preprocessing to obtain a processed historical garbage collection data set, wherein the historical garbage collection data specifically includes garbage quantity, garbage type, and recycling behavior information; A model building module is used to model the historical data based on the processed historical garbage collection data set using the ARIMA model in the time series analysis technology to obtain a recycling prediction model; The detection definition module is used to build an anomaly detection mechanism by setting anomaly thresholds, where the anomaly thresholds specifically include an anomaly threshold for the total amount of garbage, an anomaly threshold for changes in garbage accumulation, and an anomaly threshold for garbage placement behavior. The specific steps for setting an anomaly threshold for the total amount of garbage are as follows: Set the total amount of historical garbage data , where n is the number of observations, and the mean is calculated using the standard deviation method (for normally distributed garbage collection data) and standard deviation The expressions are:

[0033]

[0034] Next, set the abnormal threshold to and , among which, using As the threshold, is 2, using As the threshold, It is 3; Using the quartile method (for non-normally distributed garbage collection data), calculate the first quartile , the third quartile , and the interquartile range ,in, = 25th percentile, = 75th percentile, ; Then, the anomaly threshold The expression to be set is:

[0035] .

[0036] The data collection module is used to obtain the garbage collection data of each garbage station according to the preset collection cycle and perform preprocessing to obtain the current garbage collection data; Model analysis module, used to extract the features of current garbage collection data and input them into the collection prediction model, and output the prediction data; The data feedback module is used to identify abnormal data that deviates significantly from normal data based on the predicted data through the set anomaly detection mechanism, and feed back the abnormal data to the Internet integrated scheduling platform to provide data for scheduling resource decisions for distributing garbage collection.

[0037] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0038] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. An intelligent garbage collection system based on an Internet integrated scheduling platform, characterized in that: include: A data processing module is used to collect historical garbage collection data from each garbage site and perform preprocessing to obtain a processed historical garbage collection data set, wherein the historical garbage collection data specifically includes garbage quantity, garbage type, and recycling behavior information; A model building module is used to model the historical data based on the processed historical garbage collection data set using the ARIMA model in the time series analysis technology to obtain a recycling prediction model; The detection definition module is used to build an anomaly detection mechanism by setting anomaly thresholds, where the anomaly thresholds specifically include an anomaly threshold for the total amount of garbage, an anomaly threshold for changes in garbage accumulation, and an anomaly threshold for garbage placement behavior; The data collection module is used to obtain the garbage collection data of each garbage station according to the preset collection cycle and perform preprocessing to obtain the current garbage collection data; Model analysis module, used to extract the features of current garbage collection data and input them into the collection prediction model, and output the prediction data; The data feedback module is used to identify abnormal data that deviates significantly from normal data based on the predicted data through the set anomaly detection mechanism, and feed back the abnormal data to the Internet integrated scheduling platform to provide data for scheduling resource decisions for distributing garbage collection.

2. The intelligent garbage collection system based on the Internet integrated scheduling platform according to claim 1 is characterized in that: The specific steps of collecting historical garbage collection data from each garbage site and preprocessing it to obtain a processed historical garbage collection data set are as follows: Collect historical garbage collection data from each garbage site, including garbage volume, garbage type, and recycling behavior information; The collected historical garbage collection data is preprocessed, specifically including cleaning, sorting and formatting, to form a processed historical garbage collection data set after the preprocessing.

3. The intelligent garbage collection system based on the Internet integrated scheduling platform according to claim 1 is characterized in that: Based on the processed historical garbage collection data set, the ARIMA model in the time series analysis technology is used to model the historical data to obtain the recycling prediction model, and the specific steps are as follows: Based on the processed historical garbage collection data set, the ARIMA model in the time series analysis technology is selected for modeling; The processed historical garbage collection data set is used as a training set. The parameters of the ARIMA model are determined by inputting it into the training set to obtain a recycling prediction model, in which the parameters specifically include autoregressive terms, difference orders, and moving average terms.

4. The intelligent garbage collection system based on the Internet integrated scheduling platform according to claim 1 is characterized in that: The specific steps of constructing an anomaly detection mechanism by setting an anomaly threshold are as follows: According to the processed historical garbage collection data set, the standard deviation method or the quartile method is used to set the abnormal threshold of the total amount of garbage. Specifically, suppose the historical total amount of garbage data , where n is the number of observations, and the mean is calculated using the standard deviation method (for normally distributed garbage collection data) and standard deviation The expressions are: Next, set the abnormal threshold to and , among which, using or as a threshold; Using the quartile method (for non-normally distributed garbage collection data), calculate the first quartile , the third quartile , and the interquartile range ,in, = 25th percentile, = 75th percentile, ; Then, the anomaly threshold The calculation formula is set as: ； Using image recognition technology, we can identify garbage images in the processed historical garbage collection dataset and set abnormal thresholds for garbage accumulation changes; Based on the garbage disposal behavior data in the processed historical garbage collection data set, an abnormal threshold is set for the garbage disposal behavior; Configure the judgment tool based on the abnormal threshold of total garbage amount, abnormal threshold of garbage accumulation change, and abnormal threshold of garbage disposal behavior.

5. The intelligent garbage collection system based on the Internet integrated scheduling platform according to claim 4 is characterized in that: The judgment tool is configured based on the abnormal threshold of the total amount of garbage, the abnormal threshold of the change of garbage accumulation and the abnormal threshold of the garbage delivery behavior, and the specific steps are: Select the data monitoring and analysis script, and define the total amount of garbage, garbage accumulation changes, and garbage disposal behavior data as the data input type of the data monitoring and analysis script; Define the abnormal threshold of total garbage volume, abnormal threshold of garbage accumulation change, and abnormal threshold of garbage disposal behavior as the judgment threshold of data monitoring and analysis scripts; Set judgment logic: When it is identified that the total amount of garbage, changes in garbage accumulation, and garbage disposal behavior exceed the corresponding abnormal threshold, the identified abnormal data will be marked.

6. The intelligent garbage collection system based on the Internet integrated scheduling platform according to claim 1 is characterized in that: The specific steps of obtaining the garbage collection data of each garbage station according to the preset collection cycle and preprocessing to obtain the current garbage collection data are as follows: According to the preset collection cycle, regularly obtain the garbage collection data of each current garbage site; The garbage collection data of each current garbage site is cleaned, sorted and formatted to form the current garbage collection data set.

7. The intelligent garbage collection system based on the Internet integrated scheduling platform according to claim 1 is characterized in that: The specific steps of extracting the features of the current garbage collection data and inputting them into the recycling prediction model and outputting the prediction data are as follows: Extract relevant features from the current waste collection dataset to input into the recycling prediction model, including waste volume, waste type, and recycling behavior; The extracted features are input into the recycling prediction model, and the prediction results are output, including data on the amount of garbage recycled and the distribution of garbage types over a period of time.

8. The intelligent garbage collection system based on the Internet integrated scheduling platform according to claim 1 is characterized in that: Based on the predicted data, the abnormal data that deviates significantly from the normal data is identified through the set anomaly detection mechanism, and the abnormal data is fed back to the Internet integrated scheduling platform. The specific steps are: The obtained predicted data is input into the pre-set anomaly detection mechanism, and the judgment tool is configured through the anomaly detection mechanism to predict the abnormal data; Identify the predicted abnormal data, and generate the corresponding data point deviation degree and change according to the identified data, and organize them into an abnormality identification report; The anomaly identification report is fed back to the Internet integrated scheduling platform as reference data for garbage collection resource scheduling and for proposing recycling plans.

Images