A garbage collection method and system

Abstract

The application relates to the field of data processing, in particular to a garbage collection method and system, the method comprising: calculating periodicity of garbage disposal in a preset time interval; calculating a weight according to the periodicity of garbage disposal and the time interval, and performing disposal prediction by using a weighted moving average method; the periodicity calculation method comprising: clustering disposal time of historical garbage disposal data by using a density peak value clustering algorithm to obtain multiple clustering clusters, and taking a clustering center of the clustering clusters as a mean value of all disposal times in the clustering clusters; taking a clustering cluster of the clustering center in the time interval as a clustering cluster in the time interval; calculating stability of the time interval according to disposal time and garbage disposal quantity of all clustering clusters in the time interval; and calculating periodicity of the time interval according to time distribution and garbage disposal quantity of all clustering clusters in the time interval in consecutive days. The application has the effect of improving garbage disposal prediction accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of data processing, in particular to a garbage collection method and system. BACKGROUND

[0002] The fixed garbage station as the core node of garbage collection undertakes a large amount of centralized storage and transfer of garbage. The traditional garbage collection method mostly relies on manual scheduling and inspection, and the arrangement of collection tasks lacks scientificity and accuracy, resulting in low collection efficiency and garbage accumulation.

[0003] The prior art predicts the garbage disposal behavior of the user (the overflow condition of the garbage station) by arranging sensors at the garbage station to monitor the garbage quantity of the garbage station in real time and by using the historical data of the user's garbage disposal. For example, the garbage classification resource optimization management method based on a cloud platform disclosed in the Chinese patent with the patent number CN118585852B includes the following steps: predicting and analyzing the overflow state of the garbage station according to the real-time monitoring data and the historical monitoring data of the garbage station.

[0004] The garbage weight of the garbage station can be predicted using the weighted moving average method to prompt the staff to collect the garbage in time. The traditional weighted moving average method is a statistical method for smoothing time series data, and its working principle is to give different weights to different data points within the time window when calculating the average value at each time point, rather than simply assigning equal weights to all data points. The traditional method gives higher weights to the more recent data to better reflect the latest trend of the data.

[0005] However, for the user's garbage disposal data, the user's garbage disposal time is usually concentrated before and after breakfast and dinner, and if the traditional weighted moving average method is used to predict the garbage weight, a higher weight will be given to the value, the reference value is low and the prediction result is inaccurate. SUMMARY

[0006] To solve the technical problem of how to accurately predict garbage disposal according to the user's garbage disposal habits based on the weighted moving average method, the present application provides a garbage collection method and system.

[0007] In the first aspect, the present application provides a garbage collection method, which adopts the following technical solution:

[0008] A waste collection method includes the following steps: setting time intervals and calculating the periodicity of waste disposal in any time interval; calculating the weights based on the periodicity of waste disposal and the time intervals, using a weighted moving average method to predict disposal, and generating waste collection reminders based on the prediction results; the periodicity calculation method includes: obtaining the disposal times of historical waste disposal data, clustering the disposal times using a density peak clustering algorithm to obtain multiple clusters, with the cluster center of each cluster being the mean of all disposal times in the cluster; selecting clusters whose cluster centers are within a time interval as the clusters within that time interval; for any time interval, calculating the stability of that time interval based on the disposal times of all clusters within that time interval and the amount of waste disposed of; and calculating the periodicity of that time interval based on the time distribution of all clusters within the same time interval over consecutive days and the amount of waste disposed of.

[0009] By analyzing waste disposal patterns across different time intervals, the periodicity within each time interval is calculated. Specifically, the time of waste disposal is clustered, and clusters are created based on these time intervals. The periodicity of each time interval is then calculated based on all the clusters within that interval, making the periodicity calculation results for any given time interval more accurate. Weights are then assigned to each time interval based on its periodicity, further improving the accuracy of waste disposal predictions.

[0010] Alternatively, the formula for calculating stability can also be: In the formula, Indicates the first Heavenly Stability over time intervals; Indicates the first Heavenly The total number of clusters in each time interval; Indicates the first Heavenly In the nth time interval The standard deviation of each cluster; Represented by natural constant An exponential function with base 1.

[0011] The stability of a time interval is quantified by combining the fluctuation of clusters within the time interval with the total number of clusters. This represents the degree of fluctuation of all clusters within the given time interval. The larger the value, the greater the fluctuation and the weaker the stability within the given time interval; conversely, the smaller the value, the stronger the stability within the given time interval. This represents the total number of clusters within a given time interval. The smaller the value, the closer the data in that cluster are, indicating stronger stability within that time interval. Conversely, the larger the value, the weaker the stability of that time interval.

[0012] Alternatively, the formula for calculating stability can also be:

[0013] In the formula, Indicates the first Heavenly Stability over time intervals; Indicates the first Heavenly The total number of clusters in each time interval; Represented by natural constant An exponential function with base 1.

[0014] The stability of data quantification is achieved by using the total number of clusters within a time interval as a single dimension. This method requires minimal computation and is suitable for applications that require relatively low computational resources.

[0015] Optional, periodic calculation formula: In the formula, Indicates the first Periodicity of time intervals; Indicates the total number of days; Indicates the first Heavenly The weight of waste disposed of in all clusters within a given time interval; This indicates the number of days in the total number of days. The average weight of waste disposed of in all clusters within a given time interval; Indicates the first Heavenly Stability over time intervals; Represented by natural constant An exponential function with base 1.

[0016] This represents the difference between the weight of garbage disposed of each day within a given time interval and the average level within a consecutive number of days. The smaller the value, the more consistent the weight of garbage disposed of within that time interval, and the stronger the periodicity of that time interval. This indicates the stability of the time interval; the larger the value, the stronger the periodicity of the time interval. This embodiment focuses more on evaluating the consistency and stability of waste disposal volume over consecutive days.

[0017] Optional, In the formula, Indicates the first Periodicity of time intervals; Indicates the total number of days; Indicates the first Heavenly The weight of waste disposed of in all clusters within a given time interval; Indicates the first Heavenly The weight of waste disposed of in all clusters within a given time interval; Indicates the first Heavenly Stability over time intervals; Represented by natural constant An exponential function with base 1.

[0018] This represents the difference between the weight of waste disposed of on adjacent days within the same time interval and the average level. This embodiment focuses more on assessing the periodic changes in waste disposal volume over shorter time intervals (between days).

[0019] Optionally, the weights are calculated based on the periodicity and time intervals of waste disposal, including the following steps: pre-setting a sliding window, calculating the weights corresponding to all time intervals within the sliding window; the formula for calculating the weights is: In the formula, Indicates the first [number]th ... The weight of each time interval; Indicates the index of the time interval within the sliding window; Indicates the first [number]th ... Periodicity of time intervals; Indicates the first [number]th ... The start time of each time interval; Indicates the start time of the time interval to be predicted; This represents the standard normalization function.

[0020] Waste disposal data from time intervals with stronger periodicity are more stable, so they should be given higher weights for more reliable predictions. Conversely, time intervals with weak periodicity may contain noisy data points, and should be given lower weights.

[0021] Optionally, the weighted moving average method can be used to predict the value. The expression for the predicted value is: In the formula, This represents the predicted weight of waste to be disposed of at the next moment. Indicates the size of the sliding window; Indicates the first [number]th ... The weight of each time interval; Indicates the first in the sliding window The weight of garbage disposed of within a given time interval.

[0022] Secondly, this application provides a waste collection system, which adopts the following technical solution:

[0023] The garbage collection system comprises a processor and a memory, and the memory stores computer program instructions which, when executed by the processor, implement the garbage collection method described above.

[0024] The garbage collection method described above is generated into a computer program and stored in the memory to be loaded and executed by the processor, so that the system is convenient to use.

[0025] The present application has the following technical effects:

[0026] By analyzing the garbage disposal situation in different time intervals, the periodicity in each time interval is calculated. Specifically, the time when the user disposes of the garbage is clustered, and the clusters are divided according to the time interval. The periodicity of each time interval is calculated according to all the clusters in the time interval, so that the periodicity calculation result of any time interval is more accurate. According to the periodicity in different time intervals, a value is assigned to the time interval, so that the prediction result of garbage disposal is more accurate. BRIEF DESCRIPTION OF DRAWINGS

[0027] The above and other objects, features and advantages of the example embodiments of the present application will be more apparent from the following detailed description read in conjunction with the accompanying drawings, in which several embodiments of the present application are shown by way of example, and wherein the same reference numerals refer to the same or similar parts throughout several views.

[0028] Figure 1 is a method flowchart of a garbage collection method according to an embodiment of the present application.

[0029] Figure 2 is a method flowchart of step S1 in a garbage collection method according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0031] It should be understood that when the terms "first", "second" and the like are used in the claims, the specification and the drawings of the application, these terms are only used to distinguish different objects, and are not used to describe a particular order. The terms "include" and "contain" used in the specification and claims of the present application indicate the presence of the described features, whole, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, whole, steps, operations, elements, components and / or sets thereof.

[0032] The embodiments of the present application disclose a garbage collection method, referring to Figure 1 , comprising steps S1-S2, as follows:

[0033] S1: Set the time interval, calculate the periodicity of garbage disposal at any time interval.

[0034] Collect garbage disposal data of garbage sites; garbage disposal data refers to the quantity of garbage disposed by users such as residents and businesses, and the time of disposal and other information at fixed garbage sites. The monitoring of garbage disposal data helps the management personnel to understand the garbage disposal quantity of each site, so as to reasonably allocate resources, reduce the situation of garbage overflow or early cleaning, and improve the garbage disposal efficiency.

[0035] In one embodiment, when the weight of garbage in the garbage site changes (when the user disposes garbage), the current disposal time and the increment of garbage weight are collected as the garbage disposal time and the garbage disposal quantity of the data point. The user records once every time.

[0036] At this point, the garbage disposal data collection of the garbage site is completed.

[0037] Most people's lives have certain regularity, and the generation of garbage is often closely related to daily activities. For example, the garbage generation quantity of a general family may be the most in the morning and evening peak period, especially after breakfast and dinner, the garbage quantity is large, resulting in a significant periodicity of disposal frequency. By understanding the periodicity of garbage disposal at different time intervals, it is helpful to better predict the peak and trough of garbage quantity, and then the disposal of garbage can be arranged according to the prediction result.

[0038] Specifically, referring to Figure 2 , the periodicity calculation method comprises steps S10-S12, as follows:

[0039] S10: Obtain the disposal time of the historical garbage disposal data, and cluster the disposal time by using a density peak value clustering algorithm to obtain a plurality of clustering clusters, the clustering center of the clustering cluster being the mean value of all disposal times in the clustering cluster; the clustering center of the clustering cluster in the time interval is the clustering cluster in the time interval.

[0040] The clustering algorithm of the present application adopts a density peak clustering algorithm, which is an unsupervised learning algorithm based on the density of data points, aiming to adaptively determine the centers of clustering clusters by finding the "density peaks" in the data space, and classify data points into different clustering clusters according to the centers of clustering clusters.

[0041] Since garbage disposal usually has certain periodicity and regularity, for example, the garbage quantity has a higher disposal frequency at a certain period of the day (such as after breakfast and dinner). By using the density peak clustering algorithm for clustering, these time intervals in the data can be classified into different clusters, so as to identify the peak period and the trough period of garbage disposal.

[0042] By clustering the data samples, "isolated data points" in the garbage disposal data can be identified, that is, individual data points that do not conform to the overall trend. These data points are separated out to avoid the accuracy of predicting the garbage weight result.

[0043] For example, starting from 0:00, every two hours is taken as a time interval. For any time interval, if the clustering center of a clustering cluster is within the time interval, the clustering cluster is taken as the clustering cluster within the time interval. Repeat the above steps to obtain each time interval in the continuous days. The experience value is taken as 7 consecutive days.

[0044] S11: For any time interval, calculate the stability of the time interval according to the disposal time and the garbage disposal quantity of all clustering clusters within the time interval.

[0045] In one embodiment, the calculation formula of stability is:

[0046] , wherein, represents the stability of the th time interval on the th day; represents the total number of clustering clusters in the th time interval on the th day; represents the standard deviation of the th clustering cluster in the th time interval on the th day; represents the exponential function with the natural constant as the base number.

[0047] wherein the stability of the time interval is quantified comprehensively by the fluctuation degree of the clustering cluster within the time interval and the total number of clustering clusters, This represents the degree of fluctuation of all clusters within the given time interval. The larger the value, the greater the fluctuation and the weaker the stability within the given time interval; conversely, the smaller the value, the stronger the stability within the given time interval. This represents the total number of clusters within a given time interval. The smaller the value, the closer the data in that cluster are, indicating stronger stability within that time interval. Conversely, the larger the value, the weaker the stability of that time interval.

[0048] In one embodiment, the formula for calculating stability can also be:

[0049] In the formula, Indicates the first Heavenly Stability over time intervals; Indicates the first Heavenly The total number of clusters in each time interval; Represented by natural constant It is an exponential function with base 1. It quantifies stability using the total number of clusters within a time interval as a single dimension, requiring minimal computation and making it suitable for applications with lower computational demands.

[0050] S12: Calculate the periodicity of the time interval based on the time distribution of all clusters within the same time interval of consecutive days and the amount of waste disposed of.

[0051] In one embodiment, the periodicity calculation formula is as follows: In the formula, Indicates the first Periodicity of time intervals; Indicates the total number of days; Indicates the first Heavenly The weight of waste disposed of in all clusters within a given time interval; This indicates the number of days in the total number of days. The average weight of waste disposed of in all clusters within a given time interval; Indicates the first Heavenly Stability over time intervals; Represented by natural constant An exponential function with base 1.

[0052] in, This represents the difference between the weight of garbage disposed of each day within a given time interval and the average level within a consecutive number of days. The smaller the value, the more consistent the weight of garbage disposed of within that time interval, and the stronger the periodicity of that time interval. The stability of the time interval is represented, and the greater the value, the stronger the periodicity of the time interval. The embodiment focuses more on evaluating the consistency and stability of the garbage disposal amount on consecutive days.

[0053] In one embodiment, the calculation formula of periodicity is: , wherein, represents the periodicity of the i-th time interval on the j-th day; represents the total number of consecutive days; represents the i-th time interval on the j-th day; represents the garbage disposal weight of all clustering clusters in the i-th time interval on the j-th day; represents the garbage disposal weight of all clustering clusters in the i-th time interval on the j-th day; represents the stability of the i-th time interval on the j-th day; represents the exponential function with the natural constant e as the base number. represents the difference between the garbage disposal weight in the same time interval of adjacent days and the average level. The embodiment focuses more on evaluating the periodic change of garbage disposal amount in a short time interval (day to day). S2: Use the weighted moving average method to make disposal prediction according to the periodicity of garbage disposal, and generate garbage collection reminders according to the prediction results. The weighted moving average method is a statistical method for smoothing time series data. Its working principle is to give different weights to different data points in the time window when calculating the average value of each time point, instead of simply assigning equal weights to all data points. The traditional method gives higher weight to the more recent data to better reflect the latest trend of the data.

[0054] As for the user's garbage disposal data, since the periodicity of the user in different time intervals is different, the garbage disposal data in the time interval with stronger periodicity is more stable, and the reliability is higher when using it for prediction. On the contrary, the garbage disposal data in the time interval with weaker periodicity is less stable, and it may be a noise data point. Therefore, the application needs to calculate the weight of any time interval according to the periodicity of different time intervals.

[0055] S2: Use the weighted moving average method to make disposal prediction according to the periodicity of garbage disposal, and generate garbage collection reminders according to the prediction results.

[0056] The weighted moving average method is a statistical method for smoothing time series data. Its working principle is to give different weights to different data points in the time window when calculating the average value of each time point, instead of simply assigning equal weights to all data points. The traditional method gives higher weight to the more recent data to better reflect the latest trend of the data.

[0057] As for the user's garbage disposal data, since the periodicity of the user in different time intervals is different, the garbage disposal data in the time interval with stronger periodicity is more stable, and the reliability is higher when using it for prediction. On the contrary, the garbage disposal data in the time interval with weaker periodicity is less stable, and it may be a noise data point. Therefore, the application needs to calculate the weight of any time interval according to the periodicity of different time intervals.

[0058] ​​​​A weighted moving average method with a preset sliding window is used to calculate the weight of any time interval within the sliding window. In one embodiment, a prediction is made every two hours to forecast the weight of waste disposal at the next time interval. The preset sliding window for the weighted moving average method is 5, which can be set by the implementer according to the specific implementation situation.

[0059] The predicted value is obtained by using a weighted moving average method based on the weights corresponding to all time intervals within the sliding window. In one embodiment, the predicted value is expressed as: In the formula, This represents the predicted weight of waste to be disposed of at the next moment. Indicates the index of the time interval within the sliding window; Indicates the size of the sliding window; Indicates the first [number]th ... The weight of each time interval; Indicates the first in the sliding window The weight of garbage disposed of within a given time interval.

[0060] For any data point to be predicted, the five data points closest to the corresponding time point are used as the data points within the sliding window to predict the data. The weight calculation formula for any time interval within the sliding window is as follows: In the formula, Indicates the first [number]th ... The weight of each time interval; Indicates the index of the time interval within the sliding window; Indicates the first [number]th ... Periodicity of time intervals; Indicates the first [number]th ... The start time of each time interval; Indicates the start time of the time interval to be predicted; This represents the standard normalization function.

[0061] Waste disposal data from time intervals with stronger periodicity are more stable, so they should be given higher weights for more reliable predictions. Conversely, time intervals with weak periodicity may contain noisy data points, and should be given lower weights.

[0062] In one embodiment, the sum of the total weight of garbage at the current garbage station and the predicted weight of garbage to be disposed of at the next moment is taken as the total weight of garbage at the garbage station at the next moment. If the value exceeds 80% of the total weight that the garbage station is allowed to carry, staff are reminded that garbage collection is required.

[0063] The embodiments of the present application also disclose a garbage collection system, comprising a processor and a memory, and the memory stores computer program instructions, which realize the garbage collection method according to the present application when executed by the processor.

[0064] The system also includes communication buses and communication interfaces and other components known to those skilled in the art, the settings and functions of which are known in the art, and thus will not be described here.

[0065] In the present application, the aforementioned memory can be any tangible medium containing or storing a program, which can be used or combined with an instruction execution system, device or apparatus. For example, the computer readable storage medium can be any appropriate magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high bandwidth memory (HBM), hybrid memory cube (HMC) and the like, or any other medium that can be used to store desired information and can be accessed by an application, module or both. Any such computer storage medium can be part of a device or accessible or connectable to the device.

[0066] Although the present specification has shown and described multiple embodiments of the present application, it will be apparent to those skilled in the art that many changes, modifications and alterations to the embodiments described herein can be made without departing from the spirit and scope of the present application. It should be understood that in the process of practicing the present application, various alternatives to the embodiments of the present application described herein can be employed.

[0067] The above are the preferred embodiments of the present application, which do not limit the protection scope of the present application, therefore: any equivalent changes made on the structure, shape, principle of the present application should be covered within the protection scope of the present application.

Claims

1. A method of waste collection, characterized by, The method comprises the steps of: setting a time interval, calculating the periodicity of garbage disposal at any time interval; calculating the weight according to the periodicity of garbage disposal and the time interval, using the weighted moving average method for disposal prediction, and generating a garbage collection reminder according to the prediction result; The calculation method of the periodicity comprises: obtaining the disposal time of historical garbage disposal data, and using a density peak clustering algorithm to cluster the disposal time to obtain a plurality of clustering clusters, the clustering center of the clustering cluster being the mean of all disposal times in the clustering cluster; Clusters whose cluster centers fall within a given time interval are considered as clusters within that time interval. For any given time interval, the stability of that time interval is calculated based on the disposal times and waste disposal amounts of all clusters within that time interval. The formula for calculating stability is: In the formula, Indicates the first Heavenly Stability over time intervals; Indicates the first Heavenly The total number of clusters in each time interval; Indicates the first Heavenly In the nth time interval The standard deviation of each cluster; Represented by natural constant An exponential function with base 1; According to the time distribution and garbage disposal amount of all clustering clusters in the same time interval of consecutive days, the periodicity of the time interval is calculated; The periodicity is calculated by the formula: wherein denotes the periodicity of the time interval of the th day; denotes the total number of days; denotes the total weight of the cluster of the th time interval of the th day; denotes the average of the total weight of the cluster of the th time interval over the total number of days; denotes the stability of the th time interval of the th day; denotes the exponential function with the natural constant as the base. The weights are calculated based on the periodicity and time intervals of waste disposal, including the following steps: a sliding window is preset, and the weights corresponding to all time intervals within the sliding window are calculated. The formula for calculating the weights is: In the formula, Indicates the first [number]th ... The weight of each time interval; Indicates the index of the time interval within the sliding window; Indicates the first [number]th ... Periodicity of time intervals; Indicates the first [number]th ... The start time of each time interval; Indicates the start time of the time interval to be predicted; This represents the standard normalization function; By clustering the data samples, the isolated data points in the garbage disposal data are identified, that is, the individual data points that do not conform to the overall trend, and these data points are separated out to avoid the accuracy of the garbage weight result prediction; The predicted value is obtained using the weighted moving average method. The expression for the predicted value is: In the formula, This represents the predicted weight of waste to be disposed of at the next moment. Indicates the size of the sliding window; Indicates the first [number]th ... The weight of each time interval; Indicates the first in the sliding window The weight of waste disposed of within a given time interval; The sum of the total weight of the current garbage station and the garbage disposal weight prediction value of the next time is taken as the total weight of the garbage station at the next time, and if the value exceeds 80% of the total weight of the garbage station, the staff is reminded to collect and transport.

2. The waste collection method according to claim 1, characterized in that, The calculation formula of stability can also be: , wherein, represents the stability of the first time interval on the first day; represents the total number of clustering clusters in the first time interval on the first day; represents an exponential function with a natural constant as the base number.

3. The waste collection method according to claim 1, characterized in that, The formula for calculating periodicity can also be: In the formula, Indicates the first Periodicity of time intervals; Indicates the total number of days; Indicates the first Heavenly The weight of waste disposed of in all clusters within a given time interval; Indicates the first Heavenly The weight of waste disposed of in all clusters within a given time interval; Indicates the first Heavenly Stability over time intervals; Represented by natural constant An exponential function with base 1.

4. A waste collection system, characterized in that It comprises: a processor and a memory, the memory storing computer program instructions, when the computer program instructions are executed by the processor, the garbage collection method according to any one of claims 1-3 is realized.

Images