Garbage Collection System

Abstract

This garbage collection system (1) comprises: a data acquisition unit (11) that acquires population change data for each district demarcated in advance and actual garbage amount data for each district and each type of garbage; and a garbage amount prediction unit (12) that predicts the amount of garbage for each district and for each garbage type on the basis of the population change data for each district and the actual garbage amount data for each district and each type of garbage acquired by the data acquisition unit (11).

Description

[Technical field]

[0001] This disclosure provides a system that has the function of predicting the amount of garbage for each pre-defined district. Regarding the garbage collection system Furthermore, the waste collection system can also be equipped with a function for optimizing waste collection routes according to predicted amounts of waste in each area. [Background technology]

[0002] There has been a problem of how to collect garbage generated in daily life more efficiently. In addition, the amount of garbage generated from households is increasing due to the dramatic increase in the number of people working from home in response to the recent spread of the new coronavirus. For this reason, technology has been proposed to efficiently collect the increasing amount of garbage (see Patent Document 1 below). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-004076 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, Patent Document 1 does not describe any technology that accurately predicts the amount of garbage for each type of garbage in each collection area, as a prerequisite for efficient garbage collection, and thus technology that can accurately predict the amount of garbage for each type of garbage in each collection area is desired.

[0005] The present disclosure has been made to solve the above-mentioned problem, and aims to accurately predict the amount of garbage for each garbage type in each area subject to collection. [Means for solving the problem]

[0006] There is a technology that uses a wireless network mechanism used by a user's mobile terminal to obtain population trend data that shows the population trend for each pre-defined district. Based on the knowledge that the amount of garbage generated (i.e., the amount of garbage to be collected (hereinafter referred to as "garbage amount")) varies according to population change, the applicant has invented a technology that utilizes the population trend data and accurately predicts the amount of garbage for each district by garbage type, as follows:

[0007] The garbage collection system according to the present disclosure includes a data acquisition unit that acquires population trend data for each pre-divided district, as well as actual garbage volume data for each district and for each garbage type, and a garbage volume prediction unit that predicts the garbage volume for each district for each garbage type, based on the population trend data for each district and the actual garbage volume data for each district and for each garbage type acquired by the data acquisition unit.

[0008] In the above garbage collection system, the data acquisition unit acquires population transition data for each district and actual garbage volume data for each district and each garbage type, and the garbage volume prediction unit predicts the garbage volume for each district for each garbage type based on the acquired population transition data for each district and actual garbage volume data for each district and each garbage type. As an example of the "garbage volume prediction" here, a garbage volume prediction model for predicting the garbage volume for each district may be generated for each garbage type by machine learning, and the generated garbage volume prediction model may be used to predict the garbage volume for each district for each garbage type. As described above, the "garbage volume for each district," which varies according to the population transition represented by the population transition data, can be accurately predicted for each garbage type. Effect of the Invention

[0009] According to the present disclosure, it is possible to accurately predict the amount of garbage to be collected in each area by garbage type. [Brief description of the drawings]

[0010] [Figure 1] FIG. 2 is a functional block diagram of the waste collection system. [Diagram 2] FIG. 4 is a flow diagram showing a process executed in the waste collection system. [Diagram 3] FIG. 1A is a diagram for explaining the generation of a waste amount prediction model by machine learning, and FIG. 1B is a diagram for explaining waste amount prediction using the waste amount prediction model. [Figure 4] 11A and 11B are diagrams for explaining a process for determining a dust collection route. [Diagram 5] FIG. 13 is a diagram showing an example of determining a garbage collection route that optimizes both the total travel distance and the total number of vehicles. [Figure 6] FIG. 13 is a diagram showing an example of determining a garbage collection route that optimizes only the total number of vehicles. [Figure 7] FIG. 13 is a diagram showing an example of a garbage collection route in which both the total travel distance and the total number of vehicles are not optimized. [Figure 8] FIG. 4 is a functional block diagram of a garbage collection system according to a first modified example. [Figure 9] FIG. 1A is a diagram for explaining the generation of a trash collection route determination model by machine learning, and FIG. 1B is a diagram for explaining the determination of a trash collection route using the trash collection route determination model. [Figure 10] FIG. 11 is a flowchart showing a process for determining a garbage collection route in the first modified example. [Figure 11] FIG. 11 is a functional block diagram of a garbage collection system according to a second modified example. [Figure 12] FIG. 2 is a diagram illustrating an example of the hardware configuration of each device included in the waste collection system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of a dirt collection system according to the present disclosure will be described with reference to the accompanying drawings.

[0012] As shown in FIG. 1, the garbage collection system 1 includes a garbage amount prediction device 10 that predicts the amount of garbage, and a garbage collection route determination device 20 that determines the garbage collection route. In addition, as peripheral devices of the garbage collection system 1, there are a demographics server 30, a garbage collection amount performance history server 40, and a management server 50. The demographics server 30 is a server that acquires and provides population transition data that indicates the transition of population for each district that has been divided in advance, using a wireless network mechanism or the like used by a user's mobile terminal. Note that this embodiment will be described using an example in which districts that have been divided in advance into a mesh shape with boundaries along the east-west, north-south, and south directions (hereinafter referred to as "meshes") are used as the pre-divided districts. However, it is not essential to use meshes, and other divided districts such as towns and districts in administrative districts may be used. The garbage collection amount performance history server 40 is a server that acquires and provides garbage amount performance data for each mesh and for each garbage type, and is deployed, for example, for each mesh. The management server 50 is a server that manages and provides various management information (for example, location information regarding the departure point, destination, and garbage collection location of each garbage collection truck, information on the amount of garbage that can be collected by each garbage collection truck (hereinafter referred to as "capacity"), and information on the number of personnel and vehicles that can be dispatched).

[0013] In the waste collection system 1, the waste amount prediction device 10 includes a data acquisition unit 11, a waste amount prediction unit 12, and an information transmission unit 13, and the waste collection route determination device 20 includes an information acquisition unit 21, a collection route determination unit 22, and an information output unit 23. The function of each unit will be described below.

[0014] The data acquisition unit 11 is a functional unit that acquires population transition data for each predefined mesh from the demographic statistics server 30, and acquires garbage volume data for each mesh and for each garbage type from the garbage collection volume record server 40. Note that "garbage type" refers to the type of garbage, such as burnable garbage, non-burnable garbage, recyclable garbage, and bulky garbage.

[0015] The waste amount prediction unit 12 is a functional unit that predicts the amount of waste for each mesh by waste type based on population transition data for each mesh and actual waste amount data for each mesh and for each waste type acquired by the data acquisition unit 11. Details of the prediction process by the waste amount prediction unit 12 will be described later with reference to FIG.

[0016] The information transmission unit 13 is a functional unit that transmits information on the predicted value of the amount of dust for each mesh and for each type of dust obtained by the prediction process performed by the dust amount prediction unit 12 to the dust collection route determination device 20 .

[0017] The information acquisition unit 21 is a functional unit that acquires various information necessary for determining a garbage collection route. For example, the information acquisition unit 21 acquires information on the predicted garbage amount for each mesh and each garbage type from the information transmission unit 13, acquires location information on the departure point, destination, and garbage collection location for each mesh of the garbage collection truck used for garbage collection, information on the collection amount (capacity) for each garbage collection truck, and information on the number of personnel and vehicles that can be dispatched from the management server 50, and further acquires information on rules determined in advance for determining the number of personnel required depending on the amount of garbage to be collected from the garbage collection amount performance history server 40. Note that the above rule information does not need to be acquired every time, and may be acquired each time there is a revision.

[0018] The collection route determination unit 22 is a functional unit that determines the garbage collection route for each garbage collection vehicle and the personnel allocation for each garbage collection vehicle for each garbage type. The garbage collection route determination process by the collection route determination unit 22 includes (a) a method of determining a garbage collection route for each garbage collection vehicle by solving an optimization problem that minimizes an evaluation function whose output values ​​are the total travel distance of the garbage collection vehicles and the total number of garbage collection vehicles, and (b) a method of generating a garbage collection route determination model for determining a garbage collection route for each garbage collection vehicle by machine learning and determining a garbage collection route for each garbage collection vehicle using the garbage collection route determination model. Note that the "total number" of garbage collection vehicles means the number of vehicles obtained by counting the number of vehicles until one garbage collection vehicle reaches the destination (garbage processing plant) as "total number 1 vehicle," and then moving from there to a garbage collection site again to collect garbage, and counting the number of vehicles as "total number 2 vehicles" when the garbage collection vehicle reaches the destination (garbage processing plant) again.

[0019] In this embodiment, the above method (a) will be described, while the above method (b) will be described later in Modification 1. The collection route determination unit 22 further determines the amount of garbage to be collected for each garbage collection truck, which is determined according to the determined garbage collection route for each garbage type, and the allocation of personnel to each garbage collection truck, based on predetermined rules for determining the number of personnel required according to the amount of garbage to be collected.

[0020] The information output unit 23 is a functional unit that outputs information on the garbage collection route for each garbage collection truck and the staff allocation for each garbage collection truck determined by the collection route determination unit 22. The "output" here can take various forms, such as display on a display, audio output from a speaker, printing on a printer, and data output to an external device.

[0021] Next, the process executed in the waste collection system 1 will be described with reference to the flow diagram in Fig. 2. The execution timing of this process is arbitrary, and various patterns can be adopted, such as the timing at which a pre-scheduled time arrives, or the timing at which the operator of the waste amount prediction device 10 inputs a start command.

[0022] First, the demographics server 30 provides population transition data for each mesh to the waste amount prediction device 10 (step S1), and the data acquisition unit 11 of the waste amount prediction device 10 acquires the provided data. In addition, the waste collection amount performance history server 40 provides waste amount performance data for each mesh and each waste type to the waste amount prediction device 10 (step S2), and the data acquisition unit 11 of the waste amount prediction device 10 acquires the provided data.

[0023] Next, the waste amount prediction unit 12 generates and stores a waste amount prediction model 12A for each waste type as follows (step S3). For example, as shown in Fig. 3(a), the waste amount prediction unit 12 uses population transition data for each mesh in a predetermined past period (for example, from the previous garbage collection date to the current garbage collection date) as an explanatory variable, and the garbage amount record data for each mesh and garbage type in the above-mentioned predetermined period as an objective variable, and performs machine learning for each garbage type to generate a waste amount prediction model 12A for each garbage type to predict the garbage amount for each mesh.

[0024] Generally, the garbage collection timing (day of the week) differs for each garbage type, so the process from step S4 onward in Fig. 2 is executed at different times for each garbage type. In the following, an example in which burnable garbage is the target garbage type will be described, but the same process will be applied to garbage types other than burnable garbage.

[0025] When the garbage collection date for the target garbage type (here, for example, combustible garbage) arrives and it is time to perform garbage amount prediction for the target garbage type, the demographics server 30 provides the garbage amount prediction device 10 with population transition data for each mesh during the prediction target period (for example, from the previous garbage collection date to the garbage collection date) (step S4), the data acquisition unit 11 of the garbage amount prediction device 10 acquires the population transition data for each mesh provided, and the garbage amount prediction unit 12 predicts the garbage amount for each mesh related to the target garbage type (combustible garbage) by inputting the population transition data for each mesh during the prediction target period into the garbage amount prediction model 12A for the target garbage type (combustible garbage) as shown in FIG. 3(b). Information on the predicted garbage amount for each mesh and the target garbage type obtained by this prediction is transferred from the garbage amount prediction unit 12 to the information transmission unit 13, and the information transmission unit 13 transmits the information on the predicted garbage amount for each mesh and the target garbage type to the garbage collection route determination device 20 (step S6). Similarly, the management server 50 transmits to the garbage collection route determination device 20 position information relating to the departure point, destination, and garbage collection location for each mesh of the garbage collection truck used for garbage collection, information on the amount of garbage that can be collected (capacity) for each garbage collection truck, and information on the number of personnel and vehicles that can be dispatched (step S7), and the garbage collection amount performance history server 40 transmits information on rules relating to the number of personnel required depending on the amount of garbage to be collected to the garbage collection route determination device 20 (step S8). Note that step S8 does not need to be performed every time, and can be performed each time the above rules are revised.

[0026] The information acquisition unit 21 of the garbage collection route determination device 20 acquires the above various information and transfers it to the collection route determination unit 22, which determines the garbage collection route for each garbage collection vehicle and the personnel allocation for each garbage collection vehicle for the target garbage type (burnable garbage) as follows (step S9). For example, the collection route determination unit 22 determines the garbage collection route for each garbage collection vehicle to be dispatched by solving an optimization problem that minimizes an evaluation function in which the garbage collection route for each garbage collection vehicle to be dispatched is a variable, and the total travel distance of the garbage collection vehicles to be dispatched and the total number of garbage collection vehicles to be dispatched are output values, based on the predicted garbage amount for each mesh and each garbage type (here, burnable garbage) on the garbage collection day, the location information of the garbage collection vehicle's departure point, the location information of the garbage collection point, and the location information of the garbage collection vehicle's destination (garbage processing plant), and the information on the number of vehicles and personnel available on the garbage collection day, as shown on the left side of Fig. 4. The collection route determination unit 22 also determines the allocation of personnel to each garbage collection vehicle based on the amount of garbage collected by each garbage collection vehicle based on the determined garbage collection route and rule information on the number of personnel required according to the amount of garbage collected, within the range of the upper limit of the number of personnel that can be dispatched. Then, the determined information on the garbage collection route and personnel allocation for each garbage collection vehicle is transferred from the collection route determination unit 22 to the information output unit 23, and the information output unit 23 outputs the information on the garbage collection route and personnel allocation for each garbage collection vehicle (step S10). For example, the information is displayed and output on an operator terminal (not shown) of the garbage collection route determination device 20, and the operator can recognize the optimized garbage collection route and personnel allocation for each garbage collection vehicle as exemplified in FIG. 5, and garbage collection can be operated with the optimal personnel allocation and the optimal garbage collection route.

[0027] Here, an example of determining a garbage collection route will be outlined with reference to Figs. 5 to 7. The collection route determination unit 22 determines a garbage collection route that minimizes the total travel distance and total number of garbage collection vehicles. The example of determining a garbage collection route shown in Fig. 5 is a garbage collection route optimized so that each garbage collection vehicle collects garbage within the range of the collection amount (capacity) and minimizes both the total travel distance and the total number of garbage collection vehicles. In contrast, the example of determining a garbage collection route shown in Fig. 6 is a garbage collection route that is optimized so that the total number of garbage collection vehicles is the same as in Fig. 5, "3 vehicles", but the total travel distance is large and it is not optimized. In addition, the example of determining a garbage collection route shown in Fig. 7 is a garbage collection route in which the second garbage collection vehicle reaches the destination (garbage processing plant) twice, so the total number is "4 vehicles", which is higher than in Figs. 5 and 6, and it is not optimized, and the total travel distance is not optimized either.

[0028] (Effects of this embodiment) In the waste collection system 1 of this embodiment, the "amount of waste per mesh" which varies according to the population transition represented by the population transition data can be predicted with high accuracy for each type of waste.

[0029] In addition, by solving an optimization problem for minimizing the total travel distance and total number of garbage collection trucks based on the accurately predicted garbage amount prediction value for each mesh, it is possible to determine a garbage collection route that optimizes both the total travel distance and the total number of trucks as shown in Fig. 5 out of the three examples shown in Fig. 5 to Fig. 7. In addition, it is possible to appropriately determine the allocation of personnel to each garbage collection truck based on the amount of garbage collected by each garbage collection truck based on the determined garbage collection route and information on the number of personnel required according to the amount of garbage collected that is determined in advance as a rule.

[0030] (Variation 1) Variation example 1 is an example in which the collection route determination unit 22 adopts the above-mentioned method (b) “a method of generating a garbage collection route determination model for determining a garbage collection route for each garbage collection truck through machine learning, and determining a garbage collection route for each garbage collection truck using the garbage collection route determination model” when determining a garbage collection route.

[0031] As shown in FIG. 8, in the garbage collection system 1 according to the first modification, the collection route determination unit 22 generates and stores a garbage collection route determination model 22A for determining a garbage collection route as follows. More specifically, as shown in FIG. 9(a) and FIG. 10, the collection route determination unit 22 performs machine learning using the location information at the time of past collection route determination, the information on the collectable amount for each garbage truck, and the predicted garbage amount for each mesh as explanatory variables for each garbage type, and the garbage collection route for each garbage truck determined at the time of the collection route determination as the objective variable, to generate a garbage collection route determination model 22A for determining a garbage collection route for each garbage truck (step S9A in FIG. 10). Then, as shown in FIG. 9(b) and FIG. 10, the collection route determination unit 22 inputs the location information, the information on the collectable amount for each garbage truck, and the predicted garbage amount for each mesh to the generated garbage collection route determination model 22A, thereby determining a garbage collection route for each garbage truck (step S9B in FIG. 10). Furthermore, the collection route determination unit 22 determines the allocation of personnel to each garbage collection truck based on the amount of garbage to be collected for each garbage collection truck based on the determined garbage collection route and on rule information regarding the number of personnel required according to the amount of garbage to be collected (step S9C in FIG. 10).

[0032] According to the above-described first modification, a garbage collection route determination model for determining a garbage collection route is generated based on the accurately predicted garbage amount prediction value for each mesh, and by using the generated garbage collection route determination model, it is possible to determine a garbage collection route that optimizes both the total travel distance and the total number of vehicles as shown in Fig. 5, out of the three examples shown in Figs. 5 to 7 described above. In addition, it is possible to appropriately determine the allocation of personnel to each garbage collection truck based on the amount of garbage collected for each garbage collection truck based on the determined garbage collection route and information on the number of personnel required according to the amount of garbage collected that is set as a rule in advance.

[0033] (Variation 2) It is not essential that the waste collection system 1 includes the waste amount prediction device 10 and the waste collection route determination device 20 as shown in Figures 1 and 8, and the waste collection system 1 may be configured as a single device as shown in Figure 11. In that case, the information transmission unit 13 and information acquisition unit 21, which transmit and receive information between the devices, may be omitted, and the collection route determination unit 22 may acquire information directly from the waste amount prediction unit 12, the waste collection amount performance history server 40, and the management server 50. A waste collection system 1 configured in this way can also execute the same processes as the waste collection system 1 shown in Figures 1 and 8, and obtain the same effects.

[0034] (Explanation of terms, explanation of hardware configuration (Fig. 12), etc.) The waste amount prediction model 12A (FIGS. 1, 8, 11) and the waste collection route determination model 22A (FIG. 8) are both so-called trained models, and are expected to be used as program modules that are part of artificial intelligence software. That is, these trained models are "instructions for a computer" used in a computer equipped with a processor (CPU) and memory as shown in FIG. 12 described later, and are combined to obtain a certain result (to execute a predetermined process), that is, a computer program that makes the computer function. In other words, the trained model is a combination of a neural network structure and a parameter (weighting coefficient) that is the strength of the connection between each neuron of the neural network. Specifically, the computer's processor (CPU) operates in accordance with instructions from the waste amount prediction model 12A stored in the memory to output a waste amount prediction value for each mesh of the target waste type using population transition data for each mesh during the prediction target period as an input value. In addition, the computer processor (CPU) operates in accordance with instructions from the garbage collection route determination model 22A stored in the memory to output garbage collection routes for each garbage collection truck of the target garbage type, using as input values ​​the predicted garbage amount for the target garbage type on the garbage collection day, the starting point, destination, and location information regarding the garbage collection location for each district for the garbage collection truck, and information on the collectable amount for each garbage collection truck.

[0035] Moreover, the block diagrams used to explain the above embodiments and modified examples show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. Furthermore, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one device that is physically or logically combined, or may be realized using two or more devices that are physically or logically separated and directly or indirectly connected (for example, using wires, wirelessly, etc.) and these multiple devices. The functional blocks may be realized by combining the one device or the multiple devices with software.

[0036] Functions include, but are not limited to, judgment, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, selection, establishment, comparison, assumption, expectation, consideration, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs the function of transmission is called a transmitting unit or a transmitter. As described above, there is no particular limitation on the method of realization of each of these.

[0037] For example, the waste amount prediction device in the waste collection system of the present disclosure may function as a computer that performs the processing in this embodiment. Fig. 12 is a diagram showing an example of the hardware configuration of the waste amount prediction device 10. The above-mentioned waste amount prediction device 10 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like. Below, the waste amount prediction device 10 will be described as an example, but the same applies to other devices (such as the waste collection route determination device 20) that configure the waste collection system.

[0038] In the following description, the term "apparatus" may be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the waste amount prediction apparatus 10 may be configured to include one or more of the devices shown in the drawings, or may be configured to exclude some of the devices.

[0039] Each function in the waste amount prediction device 10 is realized by loading a specific software (program) onto hardware such as a processor 1001, a memory 1002, etc., so that the processor 1001 performs calculations, controls communications via a communication device 1004, and controls at least one of the reading and writing of data in the memory 1002 and the storage 1003.

[0040] The processor 1001 controls the entire computer by running, for example, an operating system. The processor 1001 may be configured with a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, and the like.

[0041] Furthermore, the processor 1001 reads out programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes according to these. As the programs, those that cause a computer to execute at least a part of the operations described in the above-mentioned embodiments are used. Although the above-mentioned various processes have been described as being executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may be transmitted from a network via a telecommunications line.

[0042] The memory 1002 is a computer-readable recording medium, and may be configured by at least one of, for example, a Read Only Memory (ROM), an Erasable Programmable ROM (EPROM), an Electrically Erasable Programmable ROM (EEPROM), a Random Access Memory (RAM), etc. The memory 1002 may be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store a program (program code), software modules, etc. that are executable to implement a wireless communication method according to an embodiment of the present disclosure.

[0043] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, and the like. Storage 1003 may be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database including at least one of memory 1002 and storage 1003, or other suitable medium.

[0044] The communication device 1004 is hardware (transmission / reception device) for performing communication between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0045] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that accepts input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that performs output to the outside. The input device 1005 and the output device 1006 may be integrated (e.g., a touch panel). Each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0046] Each aspect / embodiment described in this disclosure may be used alone, in combination, or switched according to execution. In addition, notification of specific information (e.g., notification that "X is the case") is not limited to being done explicitly, but may be done implicitly (e.g., not notifying the specific information).

[0047] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described in the present disclosure. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0048] The order of the steps, sequences, flow charts, etc. of each aspect / embodiment described in this disclosure may be changed unless inconsistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0049] The input and output information may be stored in a specific location (e.g., memory) or may be managed using a management table. The input and output information may be overwritten, updated, or added to. The output information may be deleted. The input information may be transmitted to another device.

[0050] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0051] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Further, when used in this disclosure, the term "or" is not intended to be an exclusive or.

[0052] In this disclosure, where articles have been added due to translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are in the plural form.

[0053] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different." [Explanation of symbols]

[0054] 1...garbage collection system, 10...garbage amount prediction device, 11...data acquisition unit, 12...garbage amount prediction unit, 12A...garbage amount prediction model, 13...information transmission unit, 20...garbage collection route determination device, 21...information acquisition unit, 22...collection route determination unit, 22A...garbage collection route determination model, 23...information output unit, 30...demographic statistics server, 40...garbage collection amount performance history server, 50...management server, 1001...processor, 1002...memory, 1003...storage, 1004...communication device, 1005...input device, 1006...output device, 1007...bus.

Claims

1. A data acquisition unit that acquires population transition data for each predefined district and waste amount data for each district and for each type of waste; a waste amount prediction unit that predicts the amount of waste for each district for each waste type based on the population transition data for each district and the waste amount actual data for each district and each waste type acquired by the data acquisition unit; a collection route determination unit that determines a garbage collection route for each garbage collection vehicle based on at least location information on a starting point, a destination, and a garbage collection location for each district of a garbage collection vehicle used for garbage collection, information on a collectable amount for each garbage collection vehicle, and a garbage amount prediction value for each district obtained by prediction by the garbage amount prediction unit; and Equipped with The dust amount prediction unit Using population transition data for each of the districts in a specified period of time in the past as explanatory variables, and using actual data on the amount of garbage for each of the districts and each of the garbage types in the specified period as objective variables, machine learning is performed for each of the garbage types to generate a garbage amount prediction model for predicting the amount of garbage for each of the districts, The population transition data for each district during a prediction period is inputted into the generated waste amount prediction model for each waste type, thereby predicting the waste amount for each district during the prediction period for each waste type; The collection route determination unit, for each of the waste types, Solving an optimization problem for minimizing an evaluation function having a garbage collection route for each garbage collection vehicle as a variable, a total travel distance of the garbage collection vehicles as an output value, and a total number of the garbage collection vehicles as an output value, determining a garbage collection route for each garbage collection vehicle by solving, as constraint conditions, location information on a starting point, a destination, and a garbage collection location for each district of the garbage collection vehicle, information on a collectable amount for each garbage collection vehicle, and a predicted value of a garbage amount for each district; Garbage collection system.

2. The collection route determination unit further determines, for each of the waste types, 2. The garbage collection system according to claim 1, wherein the allocation of personnel to each garbage collection truck is determined based on the amount of garbage to be collected for each garbage collection truck, which is determined according to the determined garbage collection route, and on information on the number of personnel required according to the amount of garbage to be collected, which is determined according to a predetermined rule.

3. A data acquisition unit that acquires population transition data for each predefined district and garbage amount actual data for each district and each garbage type; a waste amount prediction unit that predicts the amount of waste for each district for each waste type based on the population transition data for each district and the waste amount actual data for each district and each waste type acquired by the data acquisition unit; a collection route determination unit that determines a garbage collection route for each garbage collection vehicle based on at least location information on a starting point, a destination, and a garbage collection location for each district of a garbage collection vehicle used for garbage collection, information on a collectable amount for each garbage collection vehicle, and a garbage amount prediction value for each district obtained by prediction by the garbage amount prediction unit; and Equipped with The dust amount prediction unit Using population transition data for each of the districts in a specified period of time in the past as explanatory variables, and using actual data on the amount of garbage for each of the districts and each of the garbage types in the specified period as objective variables, machine learning is performed for each of the garbage types to generate a garbage amount prediction model for predicting the amount of garbage for each of the districts, The population transition data for each district during a prediction period is inputted into the generated waste amount prediction model for each waste type, thereby predicting the waste amount for each district during the prediction period for each waste type; The collection route determination unit, for each of the waste types, a garbage collection route determination model for determining a garbage collection route for each garbage collection truck is generated by performing machine learning using the location information, the information on the collectable amount for each garbage collection truck, and the predicted garbage amount for each district at the time of past collection route determination as explanatory variables, and the garbage collection route for each garbage collection truck determined at the time of the collection route determination as a target variable, and the current location information, the information on the collectable amount for each garbage collection truck, and the predicted garbage amount for each district are input into the generated garbage collection route determination model to determine a garbage collection route for each garbage collection truck; Garbage collection system.

4. The collection route determination unit further determines, for each of the waste types, The garbage collection system according to claim 3, further comprising: determining a staffing level for each garbage collection truck based on information on a garbage collection amount for each garbage collection truck determined according to the determined garbage collection route and a number of staff required according to a garbage collection amount that is determined in advance according to a rule.

Images