US-12626598-B2 - Method, internet of things system and storage medium for street cleaning in smart city

US12626598B2US 12626598 B2US12626598 B2US 12626598B2US-12626598-B2

Abstract

Some embodiments of the present disclosure provide a method, an Internet of Things system, and a storage medium for street cleaning in a smart city. The method may include obtaining street monitoring information of a target area; determining distribution of fallen leaves on the street; determining at least one particle according to at least one fallen leaf pile; determining a central position of the at least one particle, and designating the central position as a center of mass of the at least one particle; determining a dispersion degree of fallen leaves; determining cleaning difficulty of each street in the target area according to the dispersion degree of fallen leaves or wind strength; determining at least one street to be cleaned from the target area; and determining, based on the at least one street to be cleaned, a fallen leaf cleaning route of the target area.

Inventors

Zehua Shao
Haitang XIANG
Bin Liu
Xiaojun Wei
Lei Zhang

Assignees

CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD.

Dates

Publication Date: 20260512
Application Date: 20230816
Priority Date: 20221024

Claims (5)

1 . A method for street cleaning in a smart city implemented based on an Internet of Things system for street cleaning in a smart city, wherein the Internet of Things system for street management in a smart city includes a management platform, a sensor network platform, an object platform, a user platform, and a service platform, the management platform includes at least one management sub-platform, and the sensor network platform includes at least one sensor network sub-platform; one of the at least one sensor network sub-platform corresponds to a target area; one of the at least one management sub-platform corresponds to one of the at least one sensor network sub-platforms; street monitoring information of the target area is obtained based on the object platform and transmitted to the management sub-platform corresponding to the sensor network sub-platform based on the sensor network sub-platform corresponding to the target area; the sensor network platform is configured as a communication network and gateway; the object platform is configured as a monitoring device, a cleaning vehicle, and a relevant device of each target area; the user platform is configured as a terminal device, which feedbacks a fallen leaf cleaning route and related information of the target area to a user; the method is executed by the management platform, and the method comprises: obtaining, based on the object platform, the street monitoring information of the target area through the sensor network platform; training an object identification model by training data labelled with fallen leaf piles, and determining fallen leaves of the street monitoring information by processing the street monitoring information through the object identification model; determining the fallen leaf piles by processing the fallen leaves of the street monitoring information based on a clustering algorithm; determining distribution of fallen leaves on a street, the distribution of fallen leaves including a total amount of fallen leaves and a count of the fallen leaf piles; determining at least one particle according to at least one fallen leaf pile, the at least one fallen leaf pile being in one-to-one correspondence with each particle of the at least one particle, a position of the particle being a position of the at least one fallen leaf pile corresponding to the particle, and a mass of the at least one particle being related to a size of the at least one fallen leaf pile corresponding to the particle; constructing a mapping space of the street based on an actual geographical condition of the street, and forming a center-of-mass system according to a mapping relationship between spaces and corresponding particles of the fallen leaf piles on a street pavement in the mapping space; determining a point in the mapping space from which a sum of distances to a position of the each particle in the center-of-mass system is minimum as a center of mass; determining, according to a distance from each particle of the at least one particle to the center of mass, a dispersion degree of fallen leaves, including: determining, according to the mass of the at least one particle, a weight of the each particle of the at least one particle; and determining the dispersion degree of fallen leaves by weighting the distance from the each particle to the center of mass according to the weight of the each particle of the at least one particle; determining a wind condition during a period of time in a future period after the current moment based on a wind condition before the current moment through a wind speed prediction model, wherein the wind condition includes wind strength, the wind speed prediction model is a Long Short-Term Memory, and the wind speed prediction model is obtained through training; determining cleaning difficulty of each street in the target area according to the dispersion degree of fallen leaves or the wind strength; determining, based on the total amount of fallen leaves and the cleaning difficulty, at least one street to be cleaned that meets preset cleaning conditions from the target area, wherein the preset cleaning conditions include a threshold for the total amount of fallen leaves and a cleaning difficulty threshold; determining, based on the at least one street to be cleaned through a route planning algorithm, a fallen leaf cleaning route of the target area, including: determining, based on the at least one street to be cleaned, at least one continuous action sequence, the continuous action sequence including cleaning actions for each of the at least one street to be cleaned; for any continuous action sequence of the at least one continuous action sequence, determining a reward value of each cleaning action of the continuous action sequence by processing the continuous action sequence based on a preset evaluation function, and determining a return value of each continuous action sequence of the at least one continuous action sequence by recording a total reward value of each cleaning action of the continuous action sequence as a return value of the continuous actions; determining, according to each continuous action sequence of the at least one continuous action sequence and the return value of each continuous action sequence, the fallen leaf cleaning route of the target area, wherein the cleaning actions characterize a cleaning process of a certain street by the cleaning vehicle, and the cleaning actions correspond to each street to be cleaned; and when performing the cleaning actions, controlling the cleaning vehicle to go to the street to be cleaned corresponding to the cleaning actions and clean the street to be cleaned; sending the fallen leaf cleaning route to each cleaning vehicle in the object platform through the sensor network sub-platform corresponding to the management sub-platform to enable the each cleaning vehicle to perform cleaning automatically; receiving a fallen leaf cleaning route query instruction issued by the user platform through the service platform; and sending the fallen leaf cleaning route to the user platform through the service platform, including: storing the fallen leaf cleaning route of each target area on the service platform; and in response to determining that the fallen leaf cleaning route query instruction is received, sending the fallen leaf cleaning route to the user platform by calling the fallen leaf cleaning route according to a target area where the user is located through the service platform.
2 . A non-transitory computer-readable storage medium storing computer instructions, wherein when the computer instructions are executed by a processor, the method for street cleaning in the smart city of claim 1 is implemented.
3 . The method of claim 1 , the wind speed prediction model being trained based on a historical wind condition, wherein a wind condition before a certain historical moment is used as a training sample of the wind speed prediction model, a wind condition after the certain historical moment is used as a training label of the wind speed prediction model; after the training sample is input into the wind speed prediction model, a model output is compared with the training label to construct a loss function pair; and based on the loss function pair, parameters in the wind speed prediction model are iteratively updated.
4 . The method of claim 3 , wherein the object identification model is a trained convolutional neural network or an object detection algorithm with set parameters; training data of the object identification model includes a training sample and a sample label; the training sample is a historical monitoring image containing fallen leaves on a ground, the sample label is a fallen leaf pile that is labelled in the historical monitoring image.
5 . An Internet of Things system for street cleaning in a smart city including a management platform, a sensor network platform, an object platform, a user platform, and a service platform, the management platform includes at least one management sub-platform, and the sensor network platform includes at least one sensor network sub-platform; one of the at least one sensor network sub-platform corresponds to a target area; one of the at least one management sub-platform corresponds to one of the at least one sensor network sub-platforms; street monitoring information of the target area is obtained based on the object platform and transmitted to the management sub-platform corresponding to the sensor network sub-platform based on the sensor network sub-platform corresponding to the target area; the sensor network platform is configured as a communication network and gateway; the object platform is configured as a monitoring device, a cleaning vehicle, and a relevant device of each target area; the user platform is configured as a terminal device, which feedbacks a fallen leaf cleaning route and related information of the target area to a user; wherein the management platform is configured to: obtain, based on the object platform, the street monitoring information of the target area through the sensor network platform; train an object identification model by training data labelled with fallen leaf piles, and determine fallen leaves of the street monitoring information by processing the street monitoring information through the object identification model; determine the fallen leaf piles by processing the fallen leaves of the street monitoring information based on a clustering algorithm; determine distribution of fallen leaves on a street, the distribution of fallen leaves including a total amount of fallen leaves and a count of the fallen leaf piles; determine at least one particle according to at least one fallen leaf pile, the at least one fallen leaf pile being in one-to-one correspondence with each particle of the at least one particle, a position of the particle being a position of a fallen leaf pile corresponding to the particle, and a mass of the at least one particle being related to a size of the at least one fallen leaf pile corresponding to the particle; construct a mapping space of the street based on an actual geographical condition of the street, and forming a center-of-mass system according to a mapping relationship between spaces and corresponding particles of the fallen leaf piles on a street pavement in the mapping space; determine a point in the mapping space from which a sum of distances to a position of the each particle in the center-of-mass system is minimum as a center of mass; determine, according to a distance from each particle of the at least one particle to the center of mass, a dispersion degree of fallen leaves; wherein to determine, according to a distance from each particle of the at least one particle to the center of mass, a dispersion degree of fallen leaves, the management platform is further configured to: determine, according to the mass of the at least one particle, a weight of the each particle of the at least one particle; and determine the dispersion degree of fallen leaves by weighting the distance from the each particle to the center of mass according to the weight of the each particle of the at least one particle; determine a wind condition during a period of time in a future period after the current moment based on a wind condition before the current moment through a wind speed prediction model, wherein the wind condition includes wind strength, the wind speed prediction model is a Long Short-Term Memory, and the wind speed prediction model is obtained through training; determine cleaning difficulty of each street in the target area according to the dispersion degree of fallen leaves or the wind strength; determine, based on the total amount of fallen leaves and the cleaning difficulty, at least one street to be cleaned that meets preset cleaning conditions from the target area, wherein the preset cleaning conditions include a threshold for the total amount of fallen leaves and a cleaning difficulty threshold; determine, based on the at least one street to be cleaned through a route planning algorithm, a fallen leaf cleaning route of the target area, wherein to determine, based on the at least one street to be cleaned through a route planning algorithm, a fallen leaf cleaning route of the target area, the management platform is further configured to: determine, based on the at least one street to be cleaned, at least one continuous action sequence, the continuous action sequence including cleaning actions for each of the at least one street to be cleaned; for any continuous action sequence of the at least one continuous action sequence, determine a reward value of each cleaning action of the continuous action sequence by processing the continuous action sequence based on a preset evaluation function, and determine a return value of each continuous action sequence of the at least one continuous action sequence by recording a total reward value of each cleaning action of the continuous action sequence as a return value of the continuous actions: determine, according to each continuous action sequence of the at least one continuous action sequence and the return value of each continuous action sequence, the fallen leaf cleaning route of the target area, wherein the cleaning actions characterize a cleaning process of a certain street by the cleaning vehicle, and the cleaning actions correspond to each street to be cleaned; and when perform the cleaning actions, control the cleaning vehicle to go to the street to be cleaned corresponding to the cleaning actions and clean the street to be cleaned; send the fallen leaf cleaning route to each cleaning vehicle in the object platform through the sensor network sub-platform corresponding to the management sub-platform to enable the each cleaning vehicle to perform cleaning automatically; receive a fallen leaf cleaning route query instruction issued by the user platform through the service platform; and send the fallen leaf cleaning route to the user platform through the service platform, wherein to send the fallen leaf cleaning route to the user platform through the service platform, the management platform is further configured to: store the fallen leaf cleaning route of each target area on the service platform; and in response to determining that the fallen leaf cleaning route query instruction is received, send the fallen leaf cleaning route to the user platform by calling the fallen leaf cleaning route according to a target area where the user is located through the service platform.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application is a continuation of U.S. application Ser. No. 18/063,642, filed on Dec. 8, 2022, which claims priority of Chinese Patent Application No. 202211307812.1, filed on Oct. 24, 2022, the entire contents of each of which are hereby incorporated by reference. TECHNICAL FIELD The present disclosure relates to the field of smart cities, and in particular to, a method, an Internet of Things system, and a storage medium for street cleaning in a smart city. BACKGROUND With full promotion of carbon neutrality goals, the density of trees in cities (especially street trees on both sides of streets) is gradually increasing. In an annual fallen leaf season, a large number of fallen leaves are scattered on pavements of streets, affecting an appearance of a city and normal passage of vehicles or citizens. Therefore, how to plan a cleaning route of fallen leaves and improve the cleaning efficiency of the street surface is an urgent technical problem to be solved in the art. SUMMARY One or more embodiments of the present disclosure provide a method for street cleaning in a smart city implemented based on an Internet of Things system for street cleaning in a smart city. The Internet of Things system for street cleaning in a smart city may include a management platform, a sensor network platform, and an object platform. The method may be executed by the management platform. The method may include: obtaining, based on the object platform, street monitoring information of a target area through the sensor network platform; determining, according to the street monitoring information, distribution of fallen leaves on the street, the distribution of fallen leaves including a total amount of fallen leaves and a count of fallen leaf piles; determining at least one particle according to at least one fallen leaf pile; determining, according to a position of the at least one particle, a central position of the at least one particle, and designating the central position of the at least one particle as a center of mass of the at least one particle; determining, according to a distance from each particle of the at least one particle to the center of mass, a dispersion degree of fallen leaves; determining cleaning difficulty of each street in the target area according to the dispersion degree of fallen leaves or wind strength; wherein the wind strength is determined based on a wind speed prediction model, and an input of the wind speed prediction model is a wind condition before a current moment, an output is a wind condition during a period of time in a future after the current moment, and the wind condition includes the wind strength; the wind speed prediction model is a machine learning model, and the wind speed prediction model is obtained through training; determining, based on the total amount of fallen leaves and the cleaning difficulty, at least one street to be cleaned from the target area; and determining, based on the at least one street to be cleaned, a fallen leaf cleaning route of the target area. In some embodiments, the Internet of Things system for street cleaning in a smart city may further include a user platform and a service platform. The management platform may include at least one management sub-platform. The sensor network platform may include at least one sensor network platform. One of the at least one sensor network sub-platform may correspond to one of the target areas. One of the at least one management sub-platform may correspond to one of the sensor network sub-platforms. The street monitoring information of the target area may be obtained based on the object platform and transmitted to the management sub-platform corresponding to the sensor network sub-platform based on the sensor network sub-platform corresponding to the target area. The method may further include: sending the fallen leaf cleaning route to the user platform through the service platform. One or more embodiments of the present disclosure provide an Internet of Things system for street cleaning in a smart city. The Internet of Things system for street cleaning in a smart city may include a management platform, a sensor network platform, and an object platform. The management platform may be configured to: obtain, based on the object platform, street monitoring information of a target area through the sensor network platform; determine, according to the street monitoring information, distribution of fallen leaves on the street, the distribution of fallen leaves including a total amount of fallen leaves and a count of fallen leaf piles; determine at least one particle according to at least one fallen leaf pile; determine, according to a position of the at least one particle, a central position of the at least one particle, and designate the central position of the at least one particle as a center of mass of the at least one particle; determine, according to a distance from each particle of the