Intelligent control method for environment-friendly garbage can

Abstract

The invention relates to the technical field of garbage can cleaning and transportation control, in particular to an intelligent control method for an environment-friendly garbage can. The method comprises the steps of obtaining a time difference characterization value between a current garbage filling amount sequence and a target reference sequence according to a DDTW matching data pair between the current garbage filling amount sequence and the target reference sequence, and aligning the current garbage filling amount sequence with the target reference sequence according to the time difference characterization value, according to the alignment result and the difference between the current garbage filling amount sequence and the target reference sequence, the target predicted overflow duration of the intelligent garbage can at the current monitoring moment is obtained; and according to the target predicted overflow duration, garbage clearance of the intelligent garbage can is controlled. And the garbage clearance of the intelligent garbage can is controlled according to the result of predicting the duration of reaching the overflow of the intelligent garbage can, so that the clearance timeliness and the clearance effect of the intelligent garbage can can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of trash can cleaning control, and particularly relates to an intelligent control method for an environmental protection trash can. Background Art

[0002] Currently, with the acceleration of the urbanization process, intelligent trash cans are gradually replacing traditional trash cans and are applied to urban public areas and residential communities. And intelligent trash cans usually use the Internet of Things (IoT), wireless communication, and big data analysis to achieve overflow detection, remote management, and intelligent scheduling of trash cans. Although the current intelligent trash cans have the performance of detecting trash can overflow, that is, the current intelligent trash cans will give an alarm when the remaining capacity reaches a preset threshold to remind relevant staff to carry out trash cleaning, this method does not consider the trash input volume during the time when the cleaning vehicle travels to the intelligent trash can, resulting in problems such as untimely cleaning or poor cleaning effect of the intelligent trash can, that is, it will cause the intelligent trash can to reach the overflow state before it is cleaned, which will further cause a series of problems such as environmental pollution and health hazards. Therefore, how to improve the timeliness or cleaning effect of the intelligent trash can has become an urgent problem to be solved. Summary of the Invention

[0003] In order to solve the above problems, the present invention provides an intelligent control method for an environmental protection trash can, and the specific technical solution adopted is as follows: An embodiment of the present invention provides an intelligent control method for an environmental protection trash can, including the following steps: Obtain the reference sequence corresponding to each historical unit monitoring time period of the intelligent trash can and the current trash filling amount sequence corresponding to the current monitoring moment; According to the DDTW distance between any two reference sequences, cluster all the reference sequences to obtain each cluster, and obtain the reference cluster according to the distance between the current trash filling amount sequence and each cluster. According to the DDTW matching data pair between the current trash filling amount sequence and the target reference sequence, obtain the time difference characterization value between the current trash filling amount sequence and the target reference sequence. The sequences in the reference cluster are all target reference sequences. Align the current trash filling amount sequence and the target reference sequence according to the time difference characterization value, and obtain the target predicted overflow duration of the intelligent trash can at the current monitoring moment according to the alignment result and the difference between the current trash filling amount sequence and the target reference sequence; Control the trash cleaning of the intelligent trash can according to the target predicted overflow duration.

[0004] Beneficial effects: The present invention first obtains the reference sequence corresponding to each historical unit monitoring time period of the smart trash can and the current garbage filling amount sequence corresponding to the current monitoring moment; then, according to the DDTW distance between any two reference sequences, all the reference sequences are clustered to obtain various cluster clusters, and according to the distance between the current garbage filling amount sequence and each cluster cluster, the reference cluster cluster is obtained, and according to the DDTW matching data pair between the current garbage filling amount sequence and the target reference sequence, the time difference characterization value between the current garbage filling amount sequence and the target reference sequence is obtained, and according to the time difference characterization value, the current garbage filling amount sequence and the target reference sequence are aligned, and according to the alignment result and the difference between the current garbage filling amount sequence and the target reference sequence, the target predicted overflow duration of the smart trash can at the current monitoring moment is obtained; finally, according to the target predicted overflow duration, the garbage removal of the smart trash can is controlled. The present invention controls the garbage removal of the smart trash can by predicting the time it takes for the smart trash can to overflow, thereby improving the timeliness and effect of garbage removal from the smart trash can, that is, it can avoid as much as possible the phenomenon of not clearing the garbage in time when the trash can is overflowing. BRIEF DESCRIPTION OF THE DRAWINGS

[0005] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0006] Figure 1 The present invention is a flow chart of an intelligent control method for an environmentally friendly trash can. DETAILED DESCRIPTION

[0007] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the embodiments of the present invention.

[0008] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0009] This embodiment provides an intelligent control method for an environmentally friendly trash can, which is described in detail as follows: like Figure 1 As shown, the intelligent control method of the environmentally friendly trash can includes the following steps: Step S001: Obtain the reference sequence corresponding to each historical unit monitoring time period of the intelligent trash can and the current garbage filling amount sequence corresponding to the current monitoring moment.

[0010] The main purpose of this embodiment is to improve the timeliness and effect of the garbage removal of the intelligent trash can by predicting the duration when the intelligent trash can reaches full capacity. In this embodiment, sensors are arranged inside the intelligent trash can, and the arranged sensors can send the real-time remaining capacity data and positioning information inside the trash can to the remote terminal through the Internet of Things module arranged inside it. The remote terminal predicts the duration when the intelligent trash can reaches full capacity through analysis and calculation. In addition, for the convenience of understanding in this embodiment, the control process of the garbage removal of the intelligent trash cans on any one garbage removal route in any city will be used as an example for description later, and this garbage removal route will be recorded as the garbage removal route to be analyzed, that is, all the garbage removal routes that appear later belong to the same garbage removal route, and all the intelligent trash cans that appear later are the intelligent trash cans on the same garbage removal route. Moreover, a garbage removal route generally consists of multiple trash cans, and the intelligent trash can that is more forward in the garbage removal route is removed first.

[0011] In the following, this embodiment will predict the duration when each intelligent trash can on the garbage removal route to be analyzed reaches full capacity. Since the methods for predicting the duration when each intelligent trash can on the garbage removal route to be analyzed reaches full capacity are the same, in the following, the prediction process of the duration when any intelligent trash can A on the garbage removal route to be analyzed reaches full capacity will be used as an example for description. That is, the purpose of the following of this embodiment is to obtain the target predicted full capacity duration of the intelligent trash can A at the current monitoring moment. Before obtaining the target predicted full capacity duration of the intelligent trash can A at the current monitoring moment, it is necessary to first obtain the reference sequence corresponding to each historical unit monitoring time period of the intelligent trash can A and the current garbage filling amount sequence corresponding to the current monitoring moment of the intelligent trash can A. In the following, the prediction of the full capacity duration will be realized based on the reference sequence and the current garbage filling amount sequence. Then, the specific obtaining process of the reference sequence corresponding to each historical unit monitoring time period of the intelligent trash can A and the current garbage filling amount sequence corresponding to the current monitoring moment of the intelligent trash can A is as follows: First, obtain each complete day before the current monitoring moment, and regard each complete day before the current monitoring moment as a historical unit monitoring time period, that is, the time period from the start moment of a certain day to the end moment of that day is a historical unit monitoring time period, and the time length of a historical unit monitoring time period is 24 hours. For any historical unit monitoring time period, obtain the garbage filling amounts corresponding to each monitoring moment in this historical unit monitoring time period, and record the time series formed by the garbage filling amounts corresponding to all monitoring moments in this historical unit monitoring time period as the reference sequence corresponding to the intelligent trash can A in this historical unit monitoring time period, that is, the reference sequence corresponding to the intelligent trash can A in this historical unit monitoring time period is composed of all the garbage filling amounts obtained in this historical unit monitoring time period.

[0012] After that, record the current day as the current unit monitoring time period, obtain the garbage filling amounts corresponding to each monitoring moment in the time period from the start moment of the current unit monitoring time period to the current monitoring moment, and record the time series formed by the garbage filling amounts corresponding to all monitoring moments in the time period from the start moment of the current unit monitoring time period to the current monitoring moment as the current garbage filling amount sequence corresponding to the intelligent trash can A at the current monitoring moment. The current monitoring moment belongs to the current day, that is, the current garbage filling amount sequence corresponding to the intelligent trash can A at the current monitoring moment is composed of all the garbage filling amounts obtained in the time period from the start moment of the current unit monitoring time period to the current monitoring moment.

[0013] In this embodiment, the method for obtaining the garbage filling amount corresponding to each monitoring moment is as follows: for any monitoring moment: first, a monitoring moment adjacent to this monitoring moment and preceding it in time is denoted as the adjacent historical monitoring moment of this monitoring moment, and then the remaining capacity in the intelligent trash can A at this monitoring moment and the remaining capacity in the intelligent trash can A at the adjacent historical monitoring moment of this monitoring moment are obtained; if the intelligent trash can A has not been cleared between the adjacent historical monitoring moment of this monitoring moment and this monitoring moment, then the result of subtracting the remaining capacity in the intelligent trash can A at this monitoring moment from the remaining capacity in the intelligent trash can A at the adjacent historical monitoring moment of this monitoring moment is taken as the garbage filling amount corresponding to this monitoring moment; if there is a clearing behavior of the intelligent trash can A between the adjacent historical monitoring moment of this monitoring moment and this monitoring moment, then the remaining capacity in the intelligent trash can A before clearing is obtained, and the sum of the first filling amount difference and the second filling amount difference is denoted as the garbage filling amount corresponding to this monitoring moment. The first filling amount difference is the result of subtracting the remaining capacity in the intelligent trash can A before clearing from the remaining capacity in the intelligent trash can A at the adjacent historical monitoring moment of this monitoring moment, and the first filling amount difference is the result of subtracting the remaining capacity in the intelligent trash can A at this monitoring moment from the total capacity of the intelligent trash can A; and if there is no adjacent historical monitoring moment for this monitoring moment, then the result of subtracting the remaining capacity in the intelligent trash can A at this monitoring moment from the total capacity of the intelligent trash can A is also taken as the garbage filling amount corresponding to this monitoring moment; in addition, the method for obtaining the remaining capacity in the intelligent trash can A is a well-known technology, so it will not be described in detail in this embodiment.

[0014] In addition, in this embodiment, the time interval between adjacent monitoring moments is set according to the monitoring frequency usually set for intelligent trash cans applied in different scenarios. For example, if the intelligent trash can in this embodiment belongs to an urban public trash can, generally the time interval between adjacent monitoring moments is set between 15 minutes and 30 minutes, but it is required that the time intervals between all adjacent monitoring moments in this embodiment are the same, and the times corresponding to the monitoring moments on different days are also the same. For example, if 9 am is a monitoring moment, then a garbage filling amount needs to be obtained at 9 am every day.

[0015] Therefore, through the above process, this embodiment can obtain the reference sequence corresponding to each historical unit monitoring time period of the intelligent trash can A and the current garbage filling amount sequence corresponding to the current monitoring moment.

[0016] Step S002: Cluster all reference sequences based on the DDTW distance between any two reference sequences to obtain respective clusters, and obtain a reference cluster according to the distance between the current garbage filling amount sequence and each cluster. Obtain a time difference characterization value between the current garbage filling amount sequence and the target reference sequence according to the DDTW matching data pair between the current garbage filling amount sequence and the target reference sequence. Sequences in the reference cluster are all target reference sequences. Align the current garbage filling amount sequence and the target reference sequence according to the time difference characterization value, and obtain the target predicted overflow duration of the intelligent trash can at the current monitoring moment according to the alignment result and the difference between the current garbage filling amount sequence and the target reference sequence.

[0017] After obtaining the reference sequence corresponding to each historical unit monitoring time period of the intelligent trash can A and the current garbage filling amount sequence corresponding to the current monitoring moment in this embodiment, the target predicted overflow duration of the intelligent trash can A at the current monitoring moment is obtained by analyzing the reference sequence and the current garbage filling amount sequence. Before obtaining the target predicted overflow duration of the intelligent trash can A at the current monitoring moment, it is necessary to first cluster according to the similarity between the reference sequences, and obtain the target reference cluster corresponding to the current monitoring moment according to the clustering result. That is, in this embodiment, the DDTW distance between any two reference sequences will be obtained by using the Derivative Dynamic Time Warping (DDTW) algorithm. The smaller the DDTW distance between the reference sequences, the higher the similarity between the two reference sequences, and the easier it is to be divided into the same cluster during subsequent clustering. Moreover, the DDTW distance between any two reference sequences in this embodiment is the DDTW distance between the normalized sequences of any two reference sequences, that is, the DDTW distance between reference sequence 1 and reference sequence 2 is the DDTW distance between the normalized sequence of reference sequence 1 and the normalized sequence of reference sequence 2. The process of calculating the DDTW distance between any two sequences is a well-known technology, so it will not be described in this embodiment. In addition, the normalized sequence of a reference sequence refers to the sequence formed by the data obtained after normalizing all the data in the reference sequence. In this embodiment, the y-th data in the normalized sequence of any sequence is the result of normalizing the y-th data in the sequence. For example, the y-th data in the normalized sequence of a certain sequence is Norm(C), where C is the y-th data in the sequence, that is, Norm(C) is the normalized value of the y-th data in the sequence, and Norm() is the normalization function. The purpose of normalizing the obtained garbage filling amount is to avoid deviation in subsequent prediction analysis due to the similar delivery rules but different delivery amounts of garbage at different times.

[0018] After obtaining the DDTW distance between any two reference sequences, the mean shift clustering algorithm is used to cluster all the reference sequences to obtain each cluster. Then, according to the distance between the current garbage filling amount sequence and each cluster, the reference cluster corresponding to the current monitoring moment is obtained. Subsequently, prediction will be realized through the sequences in the reference cluster. The specific process of obtaining the reference cluster corresponding to the current monitoring moment is as follows: First, obtain the cluster center of each cluster, and record the sequence corresponding to the cluster center of each cluster as the center sequence of the corresponding cluster. Then, calculate the DDTW distance between the normalized sequence of the center sequence of each cluster and the normalized sequence of the current garbage filling amount sequence, and take the cluster corresponding to the minimum DDTW distance as the reference cluster corresponding to the current monitoring moment. All the reference sequences in the reference cluster are recorded as target reference sequences; and the new sequence generated by averaging all the reference sequences in the cluster using the DBA algorithm is the center sequence of the corresponding cluster. In addition, the reason for obtaining the reference cluster is that there are differences in the garbage disposal amounts in the trash cans at different locations on different days. For example, there is a trash can placed downstairs of an office building. During its working hours, such as on Monday and Friday, the number of office workers is relatively large, and the garbage disposal amount or disposal frequency may be relatively high. While on Saturday and Sunday, the number of office workers may be relatively small, and the garbage disposal amount or disposal frequency may be relatively low. Clustering can group the reference sequences corresponding to the historical unit monitoring time periods with similar disposal rules together. The historical unit monitoring time periods corresponding to the sequences in the reference cluster and the unit monitoring time period to which the current garbage filling amount sequence belongs are sequences with similar disposal rules. Then, based on the sequences in the reference cluster, the difference between the time when the intelligent trash can A reaches full overflow and the current monitoring moment can be accurately predicted, that is, the target predicted full overflow duration of the intelligent trash can A at the current monitoring moment can be accurately obtained.

[0019] After obtaining the reference clustering clusters, all DDTW matching data pairs between the current waste filling amount sequence and each target reference sequence in the reference clustering clusters are obtained. The DDTW matching data pair between any two sequences refers to the matching data pair generated by backtracking the path after finding the optimal path when calculating the DDTW distance between any two sequences. Since the process of obtaining the DDTW matching data pair when calculating the DDTW distance between any two sequences is well-known, it will not be described in this embodiment. However, since the DDTW distance between the normalized sequences is calculated in this embodiment, if, when backtracking the path, the k-th data in the normalized sequence of the current waste filling amount sequence and the z-th data in the normalized sequence of a certain target reference sequence form a matching data pair, then the combination of the k-th data in the current waste filling amount sequence and the z-th data in the target reference sequence is a DDTW matching data pair between the current waste filling amount sequence and the target reference sequence. Then, according to all the DDTW matching data pairs between the current waste filling amount sequence and any target reference sequence G in the reference clustering clusters, the time difference characterization value between the current waste filling amount sequence and the target reference sequence G is obtained. That is, the process of obtaining the time difference characterization value between the current waste filling amount sequence and the target reference sequence G is as follows: First, obtain all DDTW matching data pairs between the current garbage filling amount sequence and the target reference sequence G, and denote the set constructed by all DDTW matching data pairs between the current garbage filling amount sequence and the target reference sequence G as the matching data pair set corresponding to the target reference sequence G. Then, obtain the time difference corresponding to each DDTW matching data pair in the matching data pair set, and take the mean of the time differences corresponding to all DDTW matching data pairs in the matching data pair set as the time difference characterization value between the current garbage filling amount sequence and the target reference sequence G. Moreover, the time difference corresponding to any DDTW matching data pair in the matching data pair set corresponding to the target reference sequence G is the result of subtracting the monitoring time corresponding to the second data in the corresponding DDTW matching data pair from the monitoring time corresponding to the first data in the DDTW matching data pair. The first data in the DDTW matching data pairs in the matching data pair set corresponding to the target reference sequence G all belong to the current garbage filling amount sequence, and the second data in the DDTW matching data pairs in the matching data pair set corresponding to the target reference sequence G all belong to the target reference sequence G. Additionally, when calculating the time difference, the date is not considered. That is, if the monitoring time corresponding to the first data in a certain DDTW matching data pair is 7:00 in the morning and the monitoring time corresponding to the second data is 6:00 in the morning, then the time difference corresponding to the DDTW matching data pair is the result of subtracting 6:00 from 7:00. The reason for calculating the time difference is that although the overall garbage delivery pattern or delivery characteristics between the current unit monitoring time period to which the current garbage filling amount sequence belongs and the historical unit monitoring time period corresponding to the target reference sequence G are relatively similar, in actual delivery, it may be affected by natural factors such as weather, resulting in a certain time deviation or dislocation in the garbage delivery pattern in the current unit monitoring time period compared to the garbage delivery pattern in the historical unit monitoring time period corresponding to the target reference sequence G. For example, if in the historical unit monitoring time period corresponding to the target reference sequence G, 8:00 in the morning is the garbage delivery peak period, but in the current unit monitoring time period, due to rain, the delivery peak period is postponed to 8:30 in the morning. However, both of these peak periods belong to the early delivery peak period, that is, the attributes of these two peak periods are the same. Then, there is a time difference or dislocation between these two peak periods with the same attributes on different dates. The existence of this time difference or deviation will lead to a prediction deviation problem when using the target reference sequence G to predict the time remaining until the intelligent trash can A is full. Therefore, subsequent time alignment needs to be performed through the calculated time difference characterization value, and prediction is based on the aligned result.

[0020] In addition, if the time difference characterization value between the current garbage filling amount sequence and the target reference sequence G is equal to 0, it indicates that the garbage disposal change pattern within the current unit monitoring time period corresponding to the current garbage filling amount sequence is consistent in time with the garbage disposal change pattern within the historical unit monitoring time period corresponding to the target reference sequence G, and no alignment is required. For example, if the time difference characterization value between the current garbage filling amount sequence and the target reference sequence G is equal to 0, and the first peak disposal period within the historical unit monitoring time period corresponding to the target reference sequence G is 9:00 am, then the first peak disposal period within the current unit monitoring time period is generally also 9:00 am. If the time difference characterization value between the current garbage filling amount sequence and the target reference sequence G is greater than 0, it indicates that the garbage disposal change pattern within the current unit monitoring time period lags behind the garbage disposal change pattern within the historical unit monitoring time period corresponding to the target reference sequence G in time, and alignment is required. For example, if the time difference characterization value between the current garbage filling amount sequence and the target reference sequence G is greater than 0, the time difference characterization value between the current garbage filling amount sequence and the target reference sequence G is 30 minutes, and the first peak disposal period within the historical unit monitoring time period corresponding to the target reference sequence G is 9:00 am, then the first peak disposal period within the current unit monitoring time period may be 9:30 am. If the time difference characterization value between the current garbage filling amount sequence and the target reference sequence G is less than 0, it indicates that the garbage disposal change pattern within the historical unit monitoring time period corresponding to the target reference sequence G lags behind the garbage disposal change pattern within the current unit monitoring time period in time, and alignment is required. For example, if the time difference characterization value between the current garbage filling amount sequence and the target reference sequence G is less than 0, the time difference characterization value between the current garbage filling amount sequence and the target reference sequence G is 30 minutes, and the first peak disposal period within the historical unit monitoring time period corresponding to the target reference sequence G is 9:00 am, then the first peak disposal period within the current unit monitoring time period may be 8:30 am.

[0021] After obtaining the time difference characterization value, the current garbage filling amount sequence is aligned with the target reference sequence according to the obtained time difference characterization value. Based on the alignment result and the difference between the current garbage filling amount sequence and the target reference sequence, the target predicted overflow duration of the intelligent trash can A at the current monitoring moment is obtained. The specific acquisition process of the target predicted overflow duration of the intelligent trash can A at the current monitoring moment is as follows: First, based on the DDTW distances between the current garbage filling amount sequence and each target reference sequence, as well as the set of matching data pairs corresponding to the current garbage filling amount sequence and each target reference sequence, the difference eigenvalue between the current garbage filling amount sequence and each target reference sequence is obtained; then, a negative correlation mapping is performed on the difference eigenvalues between the current garbage filling amount sequence and each target reference sequence, and the mapping result is used as the initial prediction credibility under the corresponding target reference sequence, that is, the result obtained by performing a negative correlation mapping on the difference eigenvalue between the current garbage filling amount sequence and any target reference sequence is the initial prediction credibility under that target reference sequence, and the initial prediction credibility under any target reference sequence is exp(-L), where L is the difference eigenvalue between the current garbage filling amount sequence and that target reference sequence, and exp() is the exponential function with the constant e as the base; then, the sum of the initial prediction credibilities under all target reference sequences in the reference clustering cluster is obtained and denoted as the comprehensive prediction credibility, and the ratio of the initial prediction credibility under each target reference sequence to the comprehensive prediction credibility is obtained and denoted as the target prediction credibility under the corresponding target reference sequence; and the greater the target prediction credibility under the target reference sequence, the higher the credibility of the initial predicted overflow duration obtained subsequently based on the corresponding target reference sequence. Then, the higher the credibility of the initial predicted overflow duration, the higher the participation degree in obtaining the initial predicted overflow duration.

[0022] Immediately afterwards, according to the time difference characterization values between the current garbage filling amount sequence and each target reference sequence, the current garbage filling amount sequence is aligned with each target reference sequence respectively, and the initial predicted overflow duration under each target reference sequence is obtained according to the alignment result; then, the product of the initial predicted overflow duration under each target reference sequence and the target prediction credibility under the corresponding target reference sequence is obtained and used as the weighted predicted overflow duration under the corresponding target reference sequence, that is, the weighted predicted overflow duration under any target reference sequence is the product of the initial predicted overflow duration under that target reference sequence and the target prediction credibility under that target reference sequence; then, the sum of the weighted predicted overflow durations under all target reference sequences in the reference clustering cluster is obtained and denoted as the target predicted overflow duration of the intelligent trash can A at the current monitoring moment.

[0023] In this embodiment, the specific process of obtaining the difference eigenvalue between the current garbage filling amount sequence and each target reference sequence based on the DDTW distances between the current garbage filling amount sequence and each target reference sequence, as well as the set of matching data pairs corresponding to the current garbage filling amount sequence and each target reference sequence is as follows: For any target reference sequence G, first, obtain the absolute value of the difference between the normalized values of the two data in each DDTW matching data pair in the set of matching data pairs corresponding to the target reference sequence G, and denote it as the data difference value corresponding to the corresponding DDTW matching data pair. That is, the data difference value corresponding to any DDTW matching data pair is the absolute value of the difference between the normalized value of the first data and the normalized value of the second data in this DDTW matching data pair. The function used for normalization here is the Norm() function. Then, obtain the mean value of the data difference values corresponding to all DDTW matching data pairs in the set of matching data pairs corresponding to the target reference sequence G, and use it as the data difference mean. Then, obtain the absolute value of the difference between the data difference value corresponding to each DDTW matching data pair in the set of matching data pairs corresponding to the target reference sequence G and the data difference mean, and denote it as the first difference value corresponding to the corresponding DDTW matching data pair. Obtain the mean value of the first difference values corresponding to all DDTW matching data in the set of matching data pairs corresponding to the target reference sequence G, and denote it as the feature mean. Immediately afterwards, obtain the result of multiplying the DDTW distance between the current garbage filling amount sequence and the target reference sequence G by the feature mean, and use it as the difference feature value between the current garbage filling amount sequence and the target reference sequence G. That is, the difference feature value between the current garbage filling amount sequence and the target reference sequence G is , where is the DDTW distance between the current garbage filling amount sequence and the target reference sequence G, M is the total number of DDTW matching data pairs in the set of matching data pairs corresponding to the target reference sequence G, is the data difference value corresponding to the m-th DDTW matching data pair in the set of matching data pairs corresponding to the target reference sequence G, is the data difference mean.

[0024] In addition, when is smaller, it indicates that the similarity between the current garbage filling amount sequence and the target reference sequence G is higher. Then, the duration of the predicted distance to overflow based on the target reference sequence G, that is, the credibility and accuracy of the initial predicted overflow duration under the obtained target reference sequence G should be higher. When is smaller, it indicates that the data differences in all DDTW matching data pairs obtained based on the current garbage filling amount sequence and the target reference sequence G are smaller or the stability between all DDTW matching data pairs obtained based on the current garbage filling amount sequence and the target reference sequence G is better. Then, the duration of the predicted distance to overflow based on the target reference sequence G, that is, the credibility and accuracy of the initial predicted overflow duration under the obtained target reference sequence G should be higher. And since and The smaller it is, the smaller the difference eigenvalue between the current garbage filling amount sequence and the target reference sequence G. Therefore, if the difference eigenvalue between the current garbage filling amount sequence and the target reference sequence G is smaller, it indicates that the credibility and accuracy of the initially predicted overflow duration under the obtained target reference sequence G should be higher. On the contrary, if the difference eigenvalue between the current garbage filling amount sequence and the target reference sequence G is larger, it indicates that the credibility and accuracy of the initially predicted overflow duration under the obtained target reference sequence G should be lower.

[0025] In this embodiment, according to the time difference characterization value between the current garbage filling amount sequence and each target reference sequence, the current garbage filling amount sequence is aligned with each target reference sequence respectively, and the specific process of obtaining the initially predicted overflow duration under each target reference sequence according to the alignment result is as follows: For any target reference sequence G: According to the time difference characterization value between the current garbage filling amount sequence and the target reference sequence G, align the current garbage filling amount sequence with the target reference sequence G, and obtain the subsequence to be analyzed corresponding to the target reference sequence G. Denote the subsequence to be analyzed corresponding to the target reference sequence G as the subsequence to be analyzed H. The subsequence to be analyzed H is the predicted garbage filling amount corresponding to the future monitoring moment in the current unit monitoring time period. Moreover, in the current unit monitoring time period, all monitoring moments after the current monitoring moment are future monitoring moments in the current unit monitoring time period. Then, record the remaining capacity in the intelligent trash can at the current monitoring moment as the current remaining capacity. After that, judge whether the result of subtracting the second cumulative value from the current remaining capacity is not greater than the preset remaining capacity threshold, and whether the result of subtracting the first cumulative value from the current remaining capacity is greater than the preset remaining capacity threshold. If it is judged that the result of subtracting the second cumulative value from the current remaining capacity is not greater than the preset remaining capacity threshold but the result of subtracting the first cumulative value from the current remaining capacity is greater than the preset remaining capacity threshold, then use the time span value between the monitoring moment corresponding to the first data in the subsequence to be analyzed H and the monitoring moment corresponding to the bth data as the initial predicted overflow duration under the target reference sequence G. The initial predicted overflow duration refers to the predicted duration from the current monitoring moment when the intelligent trash can reaches full capacity. The first cumulative value is the cumulative result of the first b - 1 data in the subsequence to be analyzed H, and the second cumulative value is the cumulative result of the first b data in the subsequence to be analyzed H. b is greater than 1, and the preset remaining capacity threshold is generally set to 0, that is, when the remaining capacity in the trash can is 0, it indicates that the trash can reaches the full capacity state. For example, if the monitoring moment corresponding to the first data in the subsequence to be analyzed H is 9:00 am in the historical unit monitoring time period corresponding to the target reference sequence G, and the monitoring moment corresponding to the bth data in the subsequence to be analyzed H is 10:00 am in the historical unit monitoring time period corresponding to the target reference sequence G, then the time span value between the monitoring moment corresponding to the first data in the subsequence to be analyzed H and the monitoring moment corresponding to the bth data is 1 hour, indicating that the initial predicted overflow duration obtained based on the target reference sequence G is 1 hour. Moreover, if the current monitoring moment is 3:00 pm in the current unit monitoring time period, then the prediction result obtained based on the target reference sequence G is that the intelligent trash can may reach full capacity at 4:00 pm in the current unit monitoring time period.

[0026] In this embodiment, the specific process of aligning the current garbage filling amount sequence with the target reference sequence G according to the time difference characterization value between the current garbage filling amount sequence and the target reference sequence G and obtaining the subsequence to be analyzed corresponding to the target reference sequence G is as follows: First, denote the time corresponding to the current monitoring moment as T, and denote the value representing the time difference between the current garbage filling volume sequence and the target reference sequence G as t. Then, determine whether the value representing the time difference between the current garbage filling volume sequence and the target reference sequence G is 0. If it is, it indicates that there is no need to perform time alignment between the current garbage filling volume sequence and the target reference sequence G, and it also indicates that the garbage filling volumes corresponding to the monitoring moments in the target reference sequence G that are after time T are all the predicted garbage filling volumes corresponding to the future monitoring moments in the current unit monitoring time period. Then, at this time, obtain the moment with time T in the historical unit monitoring time period corresponding to the target reference sequence G, and denote it as the characteristic monitoring moment in the historical unit monitoring time period corresponding to the target reference sequence G. Continue to determine whether the value representing the time difference between the current garbage filling volume sequence and the target reference sequence G is less than 0. If it is, it indicates that the current garbage filling volume sequence needs to be shifted to the right by a time length of t relative to the target reference sequence G, and it also indicates that the garbage filling volumes corresponding to the monitoring moments in the target reference sequence G that are after (T + t) are all the predicted garbage filling volumes corresponding to the future monitoring moments in the current unit monitoring time period. Then, at this time, obtain the moment with time (T + t) in the historical unit monitoring time period corresponding to the target reference sequence G, and denote it as the characteristic monitoring moment in the historical unit monitoring time period corresponding to the target reference sequence G. Continue to determine whether the value representing the time difference between the current garbage filling volume sequence and the target reference sequence G is greater than 0. If it is, it indicates that the current garbage filling volume sequence needs to be shifted to the left by a time length of t relative to the target reference sequence G, and it also indicates that the garbage filling volumes corresponding to the monitoring moments in the target reference sequence G that are after (T - t) are all the predicted garbage filling volumes corresponding to the future monitoring moments in the current unit monitoring time period. Then, at this time, obtain the moment with time (T - t) in the historical unit monitoring time period corresponding to the target reference sequence G, and denote it as the characteristic monitoring moment in the historical unit monitoring time period corresponding to the target reference sequence G. And if the value representing the time difference between the current garbage filling volume sequence and the target reference sequence G is less than 0, the time corresponding to the current monitoring moment is 8:00 am, and t is 30 minutes, then the characteristic monitoring moment in the historical unit monitoring time period corresponding to the target reference sequence G is 8:30 am.

[0027] Then, in the historical unit monitoring time period corresponding to the target reference sequence G, denote the sequence composed of the garbage filling volumes corresponding to all the monitoring moments that are after the characteristic monitoring moment in terms of time as the subsequence to be analyzed corresponding to the target reference sequence G.

[0028] For example, if t is 30 minutes, the time interval between adjacent monitoring times is 10 minutes, and the time corresponding to the current monitoring time is 8:00 am, then after moving the current garbage filling amount sequence to the left by a time length of t relative to the target reference sequence G, the v-th data in the current garbage filling amount sequence is aligned with the (v - 3)-th data in the target reference sequence G. If the garbage filling amount corresponding to 8:00 am in the historical unit monitoring time period corresponding to the target reference sequence G is the U-th data in the target reference sequence G, then the (U - 3 + x)-th data in the target reference sequence G is the predicted data corresponding to the x-th future monitoring time in the current unit monitoring time period. That is, if the time corresponding to the current monitoring time is 8:00 am and the time interval between adjacent monitoring times is 10 minutes, then the first future monitoring time in the current unit monitoring time period is 8:10 am, and the garbage filling amount corresponding to the time 7:40 am in the target reference sequence G is the predicted garbage filling amount corresponding to the first future monitoring time in the current unit monitoring time period. Or, if in the historical unit monitoring time period corresponding to the target reference sequence G, the characteristic monitoring time is 6:00 pm, then the sequence formed by the garbage filling amounts corresponding to all monitoring times that belong to the historical unit monitoring time period corresponding to the target reference sequence G but after 6:00 pm in the historical unit monitoring time period corresponding to the target reference sequence G is denoted as the subsequence to be analyzed corresponding to the target reference sequence G. That is, if the monitoring time corresponding to the J-th data in the target reference sequence G is the characteristic monitoring time, then the time series sequence formed by the remaining data that are behind the J-th data in the target reference sequence G and belong to the target reference sequence G is the subsequence to be analyzed corresponding to the target reference sequence G.

[0029] Therefore, through the above process, the target predicted full overflow duration of the intelligent trash can A at the current monitoring time is obtained in this embodiment.

[0030] Step S003, control the garbage collection of the intelligent trash can according to the target predicted full overflow duration.

[0031] In the following, this embodiment will control the garbage collection of the intelligent trash cans on the collection route according to the target predicted full overflow durations of all the intelligent trash cans on the collection route to be analyzed at the current monitoring time. The specific process is as follows: First, obtain the garbage truck responsible for the garbage collection of the garbage collection route to be analyzed, and record it as the target garbage truck. Then, obtain the estimated time for the target garbage truck to reach each intelligent garbage bin on the garbage collection route to be analyzed, and determine whether the estimated time for the target garbage truck to reach each intelligent garbage bin on the garbage collection route to be analyzed is less than the target predicted overflow duration of the corresponding intelligent garbage bin at the current monitoring moment. If so, it is determined that the target garbage truck does not need to depart immediately to collect the garbage from the intelligent garbage bins on the garbage collection route to be analyzed at the current monitoring moment. Otherwise, an overflow warning needs to be issued, and it is determined that the target garbage truck needs to depart immediately to collect the garbage from the intelligent garbage bins on the garbage collection route to be analyzed in sequence. That is, if the estimated time for the garbage truck to reach any intelligent garbage bin on the garbage collection route to be analyzed is not less than the target predicted overflow duration of the corresponding intelligent garbage bin at the current monitoring moment, then it is determined that the target garbage truck needs to depart immediately to collect the garbage from the intelligent garbage bins on the garbage collection route to be analyzed in sequence. And the garbage collection process is as follows: If the intelligent garbage bins on the garbage collection route to be analyzed are W1, W2, W3, and W4 in sequence, then the target garbage truck will first arrive at W1 for garbage collection, then depart from W1 to arrive at W2 for garbage collection, then depart from W2 to arrive at W3 for garbage collection, and then depart from W3 to arrive at W4 for garbage collection. After the garbage collection is completed, the garbage truck will generally be transported to a landfill, a waste incineration plant, a composting plant, etc. for treatment.

[0032] In this embodiment, the process of obtaining the estimated time for the target garbage truck to travel to each intelligent garbage bin on the garbage collection route to be analyzed is as follows: Each time the target garbage truck collects garbage from the intelligent garbage bins on the garbage collection route to be analyzed, obtain the time taken for the target garbage truck to reach the f-th intelligent garbage bin on the garbage collection route to be analyzed for garbage collection, and record it as the historical time corresponding to the f-th intelligent garbage bin. Denote the set constructed by all the historical times corresponding to the f-th intelligent garbage bin as the set of times to be analyzed corresponding to the f-th intelligent garbage bin, and take the median of the set of times to be analyzed as the estimated time for the target garbage truck to reach the f-th intelligent garbage bin on the garbage collection route to be analyzed. As another implementation method, the mean of the set of times to be analyzed corresponding to the f-th intelligent garbage bin can also be taken as the estimated time for the target garbage truck to reach the f-th intelligent garbage bin on the garbage collection route to be analyzed. For example: If the number of times of garbage collection on the garbage collection route to be analyzed before the current monitoring moment is 3 times, and the intelligent garbage bins on the garbage collection route to be analyzed are W1, W2, W3, W4 in sequence, the time taken for the target garbage truck to reach the intelligent garbage bin W2 during the first garbage collection on the garbage collection route to be analyzed is 30 minutes, the time taken for the target garbage truck to reach the intelligent garbage bin W2 during the second garbage collection on the garbage collection route to be analyzed is 30 minutes, and the time taken for the target garbage truck to reach the intelligent garbage bin W2 during the third garbage collection on the garbage collection route to be analyzed is 32 minutes, then the estimated time for the target garbage truck to reach the intelligent garbage bin W2 is 30 minutes. Moreover, the time taken for the target garbage truck to reach W3 during garbage collection refers to the time taken for the target garbage truck to start from the departure point, reach W1, finish collecting the garbage in W1, then start from W1 and reach W2, finish collecting the garbage in W1, and then start from W2 and reach W3.

[0033] So far, this embodiment has completed the control of garbage collection from the intelligent garbage bins on the garbage collection route to be analyzed.

[0034] To summarize, this embodiment first obtains the reference sequence corresponding to each historical unit monitoring time period of the smart trash can and the current garbage filling amount sequence corresponding to the current monitoring moment; then, according to the DDTW distance between any two reference sequences, all the reference sequences are clustered to obtain various cluster clusters, and according to the distance between the current garbage filling amount sequence and each cluster cluster, a reference cluster cluster is obtained, and according to the DDTW matching data pair between the current garbage filling amount sequence and the target reference sequence, the time difference characterization value between the current garbage filling amount sequence and the target reference sequence is obtained, and according to the time difference characterization value, the current garbage filling amount sequence and the target reference sequence are aligned, and according to the alignment result and the difference between the current garbage filling amount sequence and the target reference sequence, the target predicted overflow duration of the smart trash can at the current monitoring moment is obtained; finally, according to the target predicted overflow duration, the garbage removal of the smart trash can is controlled. Moreover, this embodiment controls the garbage removal of the smart trash can by predicting the time it takes for the smart trash can to overflow, which can improve the timeliness and effect of garbage removal from the smart trash can, that is, it can avoid as much as possible the phenomenon that the garbage can is not removed in time when it is overflowing.

[0035] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An intelligent control method for an environmentally friendly trash can, characterized in that, The method includes the following steps: Obtain the reference sequence corresponding to each historical unit monitoring time period of the intelligent trash can and the current garbage filling amount sequence corresponding to the current monitoring moment; According to the DDTW distance between any two reference sequences, cluster all the reference sequences to obtain each cluster, and obtain the reference cluster according to the distance between the current garbage filling amount sequence and each cluster. According to the DDTW matching data pair between the current garbage filling amount sequence and the target reference sequence, obtain the time difference characterization value between the current garbage filling amount sequence and the target reference sequence. The sequences in the reference cluster are all target reference sequences. Align the current garbage filling amount sequence and the target reference sequence according to the time difference characterization value, and obtain the target predicted overflow duration of the intelligent trash can at the current monitoring moment according to the alignment result and the difference between the current garbage filling amount sequence and the target reference sequence; Control the garbage collection of the intelligent trash can according to the target predicted overflow duration.

2. The intelligent control method of an environmentally friendly trash can according to claim 1, characterized in that, The method for obtaining the reference sequence and the current garbage filling amount sequence includes: Regard each complete day before the current monitoring moment as a historical unit monitoring time period; for any historical unit monitoring time period, record the sequence composed of the garbage filling amounts corresponding to all monitoring moments in the historical unit monitoring time period as the reference sequence of the intelligent trash can corresponding to the historical unit monitoring time period; Regard the current day as the current unit monitoring time period, and record the sequence composed of the garbage filling amounts corresponding to each monitoring moment in the time period formed from the start moment of the current unit monitoring time period to the current monitoring moment as the current garbage filling amount sequence of the intelligent trash can corresponding to the current monitoring moment. The current monitoring moment belongs to the current day; the garbage filling amount corresponding to the monitoring moment refers to the result of subtracting the remaining capacity in the intelligent trash can at the monitoring moment from the remaining capacity in the intelligent trash can at the adjacent historical monitoring moment of the monitoring moment. The adjacent historical monitoring moment of the monitoring moment refers to a monitoring moment adjacent to the monitoring moment and preceding the monitoring moment in time.

3. The intelligent control method of an environmental protection trash can according to claim 2, characterized in that, The method for obtaining the reference cluster includes: Record the sequence corresponding to the cluster center of each cluster as the center sequence of the corresponding cluster, calculate the DDTW distance between the normalized sequence of the center sequence of each cluster and the normalized sequence of the current garbage filling amount sequence, and use the cluster corresponding to the smallest DDTW distance as the reference cluster.

4. The intelligent control method of an environmentally friendly trash can according to claim 3, characterized in that, The method for obtaining the time difference characterization value between the current garbage filling amount sequence and the target reference sequence includes: For any target reference sequence, the set constructed by all DDTW matching data pairs between the current garbage filling amount sequence and the target reference sequence is denoted as the matching data pair set corresponding to the target reference sequence, and the time difference corresponding to each DDTW matching data pair in the matching data pair set is obtained. The mean value of the time differences corresponding to all DDTW matching data pairs in the matching data pair set is used as the time difference characterization value between the current garbage filling amount sequence and the target reference sequence. The time difference corresponding to the DDTW matching data pair is the result of subtracting the monitoring time corresponding to the second data in the corresponding DDTW matching data pair from the monitoring time corresponding to the first data in the corresponding DDTW matching data pair. The first data in the DDTW matching data pair all belong to the current garbage filling amount sequence, and the second data in the DDTW matching data pair all belong to the target reference sequence.

5. The intelligent control method of an environmentally friendly trash can according to claim 4, characterized in that, The method for obtaining the target predicted overflow duration of the intelligent trash can at the current monitoring moment includes: According to the DDTW distance between the current garbage filling amount sequence and the target reference sequence and the matching data pair set corresponding to the target reference sequence, the difference characteristic value between the current garbage filling amount sequence and the target reference sequence is obtained, and the negative correlation mapping value of the difference characteristic value between the current garbage filling amount sequence and the target reference sequence is used as the initial prediction credibility under the corresponding target reference sequence. The sum of the initial prediction credibilities under all target reference sequences is denoted as the comprehensive prediction credibility, and the ratio of the initial prediction credibility under the target reference sequence to the comprehensive prediction credibility is denoted as the target prediction credibility under the corresponding target reference sequence; Align the current garbage filling amount sequence and the target reference sequence according to the time difference characterization value, and obtain the initial predicted overflow duration under each target reference sequence according to the alignment result. The product of the initial predicted overflow duration under the target reference sequence and the target prediction credibility under the corresponding target reference sequence is used as the weighted predicted overflow duration under the corresponding target reference sequence. The sum of the weighted predicted overflow durations under all target reference sequences is denoted as the target predicted overflow duration of the intelligent trash can at the current monitoring moment.

6. The intelligent control method of an environmentally friendly trash can according to claim 5, characterized in that, The method for obtaining the difference characteristic value between the current garbage filling amount sequence and the target reference sequence includes: For any target reference sequence, obtain the data difference value corresponding to each DDTW matching data pair in the set of matching data pairs corresponding to the target reference sequence. The data difference value corresponding to the DDTW matching data pair is the absolute value of the difference between the normalized value of the first data and the normalized value of the second data in the corresponding DDTW matching data pair. Take the mean of the data difference values corresponding to all DDTW matching data pairs in the set of matching data pairs as the data difference mean. Denote the absolute value of the difference between the data difference value corresponding to the DDTW matching data pair and the data difference mean as the first difference value corresponding to the DDTW matching data pair. Denote the mean of the first difference values corresponding to all DDTW matches in the set of matching data pairs as the feature mean. Take the result of multiplying the DDTW distance between the current garbage filling amount sequence and the target reference sequence by the feature mean as the difference feature value between the current garbage filling amount sequence and the target reference sequence.

7. The intelligent control method of an environmental protection trash can according to claim 5, characterized in that, A method for aligning the current garbage filling amount sequence with the target reference sequence according to the time difference characterization value and obtaining the initial predicted overflow duration under each target reference sequence based on the alignment result, includes: Denote the remaining capacity in the intelligent trash can at the current monitoring moment as the current remaining capacity; For any target reference sequence: According to the time difference characterization value between the current garbage filling amount sequence and the target reference sequence, obtain the sub-sequence to be analyzed corresponding to the target reference sequence, and denote the sub-sequence to be analyzed corresponding to the target reference sequence as the sub-sequence to be analyzed H; Denote the sum of the first b - 1 data in the sub-sequence to be analyzed H as the first cumulative value, and denote the sum of the first b data in the sub-sequence to be analyzed H as the second cumulative value, where b > 1; If the result of subtracting the second cumulative value from the current remaining capacity is not greater than the preset remaining capacity threshold, and the result of subtracting the first cumulative value from the current remaining capacity is greater than the preset remaining capacity threshold, then take the time span value between the monitoring moment corresponding to the first data and the monitoring moment corresponding to the bth data in the sub-sequence to be analyzed H as the initial predicted overflow duration under the target reference sequence G.

8. The intelligent control method of an environmentally friendly trash can according to claim 7, characterized in that, The method for obtaining the sub-sequence to be analyzed corresponding to the target reference sequence, includes: Let the time corresponding to the current monitoring moment be denoted as \(T\), and let the value characterizing the time difference between the current garbage filling amount sequence and the target reference sequence be denoted as \(t\). If the value characterizing the time difference between the current garbage filling amount sequence and the target reference sequence is \(0\), then in the historical unit monitoring time period corresponding to the target reference sequence, the moment with time \(T\) is denoted as the characteristic monitoring moment in the historical unit monitoring time period corresponding to the target reference sequence. If the value characterizing the time difference between the current garbage filling amount sequence and the target reference sequence is less than \(0\), then in the historical unit monitoring time period corresponding to the target reference sequence, the moment with time \((T + t)\) is denoted as the characteristic monitoring moment in the historical unit monitoring time period corresponding to the target reference sequence. If the value characterizing the time difference between the current garbage filling amount sequence and the target reference sequence is greater than \(0\), then in the historical unit monitoring time period corresponding to the target reference sequence, the moment with time \((T - t)\) is denoted as the characteristic monitoring moment in the historical unit monitoring time period corresponding to the target reference sequence. In the historical unit monitoring time period corresponding to the target reference sequence, the sequence formed by the garbage filling amounts corresponding to all monitoring moments that are temporally after the characteristic monitoring moment is denoted as the subsequence to be analyzed corresponding to the target reference sequence.

9. The intelligent control method of an environmentally friendly trash can according to claim 1, characterized in that, A method for controlling the garbage removal of the intelligent trash can according to the target predicted overflow duration, includes: Denote the garbage removal route where the intelligent trash can is located as the to-be-analyzed garbage removal route, and obtain the estimated time for the garbage truck to reach each intelligent trash can on the to-be-analyzed garbage removal route. If the estimated time for the garbage truck to reach any intelligent trash can on the to-be-analyzed garbage removal route is not less than the target predicted overflow duration of the corresponding intelligent trash can at the current monitoring moment, then it is determined that at the current monitoring moment, the garbage truck immediately departs to sequentially remove the garbage from the intelligent trash cans on the to-be-analyzed garbage removal route.

10. The intelligent control method of an environmentally friendly trash can according to claim 9, characterized in that, The method for obtaining the estimated time for the garbage truck to reach each intelligent trash can on the to-be-analyzed garbage removal route, includes: Each time the garbage truck removes the garbage from the intelligent trash cans on the to-be-analyzed garbage removal route, obtain the duration used by the garbage truck to reach the \(f\)-th intelligent trash can on the to-be-analyzed garbage removal route for garbage removal, and denote it as the historical driving duration corresponding to the \(f\)-th intelligent trash can. Denote the set constructed by all the historical driving durations corresponding to the \(f\)-th intelligent trash can as the historical driving duration set corresponding to the \(f\)-th intelligent trash can, and use the median of the historical driving duration set as the estimated time for the garbage truck to reach the \(f\)-th intelligent trash can on the to-be-analyzed garbage removal route.

Images