KR102535185B1 - Method and apparatus for providing waste plastic recycling service - Google Patents

Abstract

The present disclosure relates to a method and apparatus for providing a waste plastic collection service. According to an embodiment, a method of providing a waste plastic collection service by an electronic device includes obtaining waste plastic collection request information from an external device connected to the electronic device; identifying the type of the collection requester who has transmitted the collection request information; obtaining collection plan information based on the identified type of collection requester; acquiring collection route information for each collection vehicle based on the acquired collection plan information; and transmitting the collection route information to a terminal for each collection vehicle connected to the electronic device. can include

Description

Method and apparatus for providing waste plastic recycling service {METHOD AND APPARATUS FOR PROVIDING WASTE PLASTIC RECYCLING SERVICE}

The present disclosure relates to a method and apparatus for providing a waste plastic recycling service. More specifically, it relates to a system for collecting waste toy plastic and recycling the collected waste toy plastic and an operating method thereof.

Social issues are being raised as the amount of waste plastic is rapidly increasing, and technologies for realizing carbon neutrality through recycling of waste plastic waste are being developed. In addition, in accordance with Article 19 of the Framework Act on Resource Circulation, companies are required to order improvement in product design according to the results of circular usability evaluation, and accordingly, corporate demand for recycled plastic resources is also increasing.

However, despite various attempts to recycle waste plastics, in the case of the currently running resource circulation system, the entire process is managed manually, and the efficiency of the waste plastic collection and classification process for business advancement against the growing market demand is very low. As a result, it is difficult for companies to meet the demand for recycling waste plastics.

Therefore, it is required to develop a technology for establishing a circulation system of recycled plastic materials by effectively collecting and classifying high-quality recycled plastic materials.

Korea Patent No. 1763729

According to an embodiment, a method for providing a waste plastic collection service and an electronic device performing the same may be provided.

More specifically, an apparatus and method for performing a waste plastic recycling service that collects waste plastic at a low cost based on an artificial intelligence model, tracks and records the entire process from producing recycled plastic materials by classifying the waste plastic with labor. this can be provided.

As a technical means for achieving the above technical problem, according to an embodiment, a method for providing a waste plastic collection service by an electronic device includes obtaining waste plastic collection request information from an external device connected to the electronic device; identifying the type of the collection requester who has transmitted the collection request information; obtaining collection plan information based on the identified type of collection requester; acquiring collection route information for each collection vehicle based on the acquired collection plan information; and transmitting the collection route information to a terminal for each collection vehicle connected to the electronic device. Including, a method may be provided.

According to another embodiment for achieving the above-described technical problem, an electronic device providing a waste plastic collection service includes a network interface; a memory that stores one or more instructions; and a plurality of processors executing the one or more instructions; wherein the plurality of processors obtain waste plastic collection request information from an external device connected to the electronic device by executing the one or more instructions, identify a type of a collection requester who has transmitted the collection request information, and Acquiring collection plan information based on the identified type of collection requester, obtaining collection route information for each collection vehicle based on the acquired collection plan information, and transmitting the collection route information to a terminal for each collection vehicle connected to the electronic device. An electronic device that transmits may be provided.

As a technical means for achieving the above-described technical problem, according to another embodiment, in a method for providing a waste plastic collection service by an electronic device, obtaining waste plastic collection request information from an external device connected to the electronic device. ; identifying the type of the collection requester who has transmitted the collection request information; obtaining collection plan information based on the identified type of collection requester; acquiring collection route information for each collection vehicle based on the acquired collection plan information; and transmitting the collection route information to a terminal for each collection vehicle connected to the electronic device. A computer-readable recording medium in which a program for performing the method including, may be provided.

According to an embodiment, carbon neutrality can be realized by performing a waste plastic recycling process at a low cost.

According to one embodiment, it is possible to mass-produce high-quality waste plastic recycling materials at low cost.

1 is a diagram schematically illustrating a waste plastic recycling process including a waste plastic collection process according to an embodiment.
2 is a diagram for explaining a waste plastic collection process according to another embodiment.
3 is a flowchart of a method of providing a waste plastic collection service according to an embodiment.
4 is a diagram for explaining a process of generating collection plan information according to an exemplary embodiment.
5 is a diagram for explaining a process of generating collection route information according to an exemplary embodiment.
6 is a diagram for explaining a detailed process of generating collection plan information and collection schedule information for each vehicle by an electronic device according to an exemplary embodiment.
7 is a diagram for explaining a process of defining collection plan information and optimizing the defined collection plan information by an electronic device according to another embodiment.
8 is a diagram for specifically describing collection request information, collection plan information, and collection schedule information for each vehicle used by an electronic device according to an exemplary embodiment.
9 is a diagram for comparing and describing collection schedule information for each vehicle and collection route information for each vehicle according to an exemplary embodiment.
10 is a diagram for explaining an example of a genetic algorithm used by an electronic device to learn an artificial intelligence model according to an embodiment.
11 is a diagram for explaining a process of tracking and recording inventory information according to collection of waste plastics by an electronic device according to an exemplary embodiment.
12 is a diagram for explaining a classification process for each plastic material through a classification system connected to an electronic device according to an embodiment.
13 is a block diagram of an electronic device according to an embodiment.
14 is a block diagram of an electronic device according to another embodiment.
15 is a block diagram of a server according to an embodiment.
16 is a diagram for explaining a process of performing a waste plastic recycling method by interworking a collection requester terminal, a service providing server, a collection vehicle terminal, and a classification system according to an embodiment.

Terms used in this specification will be briefly described, and the present disclosure will be described in detail.

The terms used in the present disclosure have been selected from general terms that are currently widely used as much as possible while considering the functions in the present disclosure, but they may vary according to the intention or precedent of a person skilled in the art, the emergence of new technologies, and the like. In addition, in a specific case, there is also a term arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the invention. Therefore, terms used in the present disclosure should be defined based on the meaning of the term and the general content of the present disclosure, not simply the name of the term.

When it is said that a certain part "includes" a certain component throughout the specification, it means that it may further include other components without excluding other components unless otherwise stated. In addition, terms such as "...unit" and "module" described in the specification mean a unit that processes at least one function or operation, which may be implemented as hardware or software or a combination of hardware and software. .

Hereinafter, with reference to the accompanying drawings, embodiments of the present disclosure will be described in detail so that those skilled in the art can easily carry out the present disclosure. However, the present disclosure may be implemented in many different forms and is not limited to the embodiments described herein. And in order to clearly describe the present disclosure in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

1 is a diagram schematically illustrating a waste plastic recycling process including a waste plastic collection process according to an embodiment.

According to an embodiment, the resource circulation system 10 may include a collection requester terminal 110, a server 2000, an electronic device 1000, a collector terminal 130, a collection vehicle terminal 140, and a classification system. there is. However, it is not limited to the above example, and may include more components required for recycling waste plastics, or may be provided with fewer components. The resource circulation system 10 accurately predicts the demand for discarded toys and, based on the predicted results, can perform a toy plastic resource circulation platform (TCMP: Toy Circulation Management Platform) function leading to a recycling process through waste plastic recycling. .

In the present specification, waste plastic may include waste of plastic materials. Also, according to one embodiment, the waste plastic recycled by the resource recycling system 10 in this specification may include toys or plastic materials used for toys. However, it is not limited to the above examples, and may include waste mixed with one or more plastic materials such as ABS, PP, and PE in addition to toys.

The resource circulation system 10 can predict waste plastic collection demand and collect waste plastic at a low cost. The resource circulation system 10 generates the results of the entire process from the collection of waste plastics to the production of recycled plastic materials through recycling of waste plastics into a ledger, and the resource circulation system 10 and the resource circulation system 10 ) can be managed as a blockchain network in which connected external devices participate.

The resource circulation system 10 generates point information based on inventory information generated in the process of recycling waste plastic discharged by a waste plastic collection requester, and rewards tokens equivalent to the generated point information. ) can be paid to the collection requester.

According to an embodiment, the electronic device 1000 may provide a plastic recycling or plastic collection service by being connected to the server 2000. According to an embodiment, the electronic device 1000 may correspond to a service providing server providing a plastic recycling or plastic collection service. In addition, in this specification, the plastic recycling service may include a plastic collection service, and the plastic recycling service receives a plastic collection request, collects the plastic for which the collection request has been received, extracts plastic recycling materials from the collected plastic, , It may include a process of providing predetermined point information according to the extracted reproduction material as a reward.

In addition, the plastic collection service obtains a waste plastic collection request from the collection requester terminal 110, collects the waste plastic by providing a collection vehicle in response to the obtained waste plastic collection request, and recycle materials extracted from the collected waste plastic. A process of paying points corresponding to the value as a reward may be included.

According to an embodiment, the collection requester terminal 110 may be an electronic device used by the individual 102 or the administrator of the child care institution 104 . Also, according to an embodiment, the collection requester terminal 110 may be a terminal used by a manager of another institution or company that has a plastic waste discharge demand. The collection requester terminal 110 may transmit collection request information to the electronic device 1000 based on a user input to the collection requester terminal. In addition, the collection requester terminal 110 may transmit collection request information to the electronic device 1000 and obtain point information from the electronic device 1000 as a reward for discharging waste plastic.

The electronic device 1000 includes a memory 122 storing one or more instructions for providing a waste plastic recycling or waste plastic collection service, at least one processor 124 executing the one or more instructions, and a network interface 126. ) may be included. The electronic device 1000 may correspond to a service providing server providing a plastic collection service. The electronic device 1000 receives collection request information from the collection requester terminal 110 or generates collection plan information based on collection demand prediction information obtained from a collection prediction model, and collects each vehicle according to the generated collection plan information. Route information can be created. The electronic device 1000 may transmit collection route information for each vehicle to at least one of the collector terminal 130 and the collection vehicle terminal 140 . Also, according to an embodiment, the electronic device 1000 may be connected to the sorting system 3000 including a hyperspectral sorter, and may obtain information related to the waste plastic recycling treatment result collected from the sorting system 3000. there is.

According to an embodiment, the collector terminal 130 may provide one or more services for the collector among waste plastic collection services. The collector terminal 130 may be a separate electronic device connected to the collection vehicle terminal 140 or may correspond to the collection vehicle terminal 140 mounted inside the collection vehicle. The collector terminal 130 and the collection vehicle terminal 140 may output collection route information for each collection vehicle that minimizes collection cost, and enables the collector to collect waste plastics through the path with the least cost according to the collection route information. can provide information.

The classification system 3000 may produce a recycled plastic material from the waste plastic by recycling the collected waste plastic. For example, the sorting system 3000 may collect waste plastic from collection vehicles in S162 and first classify the recovered waste plastic in S164. For example, the classification system 3000 may classify the collected plastic waste into a waste object and a circulation object. According to an embodiment, the waste plastic classified as a recycling target may be further classified into those that can be reused immediately and those that require repair.

In operation S166, the classification system 3000 may repair the waste plastic by transferring the waste plastic identified as requiring repair among the waste plastic classified as a circulation object to a repair point. In S166, the classification system 3000 may pre-treat the waste plastic by separating non-plastic materials such as rubber, metal, and electronic circuits included in the primarily classified waste plastic.

In operation S168, the classification system 3000 may extract recycled plastic materials (eg, flakes) for each material (ABS, PP, PE) by pulverizing the pretreated waste plastic. In S170, the classification system 3000 may extract flakes classified by material, color, and flammability/flame retardancy characteristics by providing the extracted plastic recycled material to an artificial intelligence-based hyperspectral sorter. The classification system 3000 repeatedly performs the secondary classification process on the pulverized waste plastic until a predetermined flake purity value is reached, thereby producing a high-quality recycled plastic material. In S172 , the classification system 3000 may generate information on the result of recycling the waste plastic from S162 to S172 as inventory information, and manage the generated inventory information in the ledger 153 .

According to an embodiment, the plastic inventory information generated by the classification system 3000 includes a collection location of waste plastics to be extracted for waste plastic recycling materials, types of waste plastic recycling materials (eg flakes), colors of waste plastic recycling materials, Information on at least one of flammability/flame retardancy characteristics of recycled waste plastic materials, purity of recycled waste plastic materials, weight of recycled waste plastic materials, or price of recycled waste plastic materials may be included. However, according to another embodiment, the plastic inventory information generated by the classification system 3000 includes the type, weight, color, and combustibility of waste plastic recycling materials extracted from waste plastic products discharged by predetermined collection requesters for a predetermined period of time. / Of course, information on flame retardant properties and purity may be further included.

The classification system 3000 may generate recycled plastic inventory information for each collection requester, and may generate point information for each collection requester based on the plastic inventory information generated for each collection requester. For example, the point information may include blockchain-based token information as reward information corresponding to the price of recycled plastic materials. The classification system 3000 generates a ledger including the processing results of the entire process for recycling waste plastics, plastic inventory information finally generated for each collection requester, and point information determined according to the plastic inventory information, A blockchain network in which the electronic device 1000, the server 2000, the classification system 3000, the collector terminal 130, the collection vehicle terminal 140, the collection requester terminal 110, and other external devices participate in the ledger information. It is possible to transparently manage the waste plastic recycling and compensation system by recording in

According to an embodiment, the electronic device 1000 randomly connects a ledger including plastic inventory information for each collection requester from the classification system 3000 and point information determined based on the plastic inventory information to the electronic device 1000. It can be transmitted to a blockchain network device. The electronic device 1000 according to the present disclosure has an advantage of producing a large amount of recycled plastic material at low waste plastic collection cost by providing optimized collection plan information and collection route information for each vehicle.

2 is a diagram for explaining a waste plastic collection process according to another embodiment.

In S212 , the electronic device 1000 may identify application log-in states of the individual 202 or administrator or users of the child care institution 204 . In S214, the electronic device 1000 may obtain waste plastic collection request information acquired through the collector terminal. According to another embodiment, the electronic device 1000 may obtain disinfection service request information from the individual 202 or child care institution 204 together with waste plastic collection request information. According to another embodiment, the electronic device 1000 may obtain only disinfection service request information from the individual 202 or child care institution 204 .

In S216, when the reception of the waste plastic or waste toy collection request is completed, the electronic device 1000 may transmit confirmation completion information confirming that the waste plastic collection request information has been received to the collection requester terminal. In S218, the electronic device 1000 may check whether the subject transmitting the collection request information is an individual or an institution. In S220, when the subject who has transmitted the collection request information is identified as an individual, the electronic device 1000 may obtain delivery address information from the terminal of the collection requester. In S222, when the delivery address information is obtained from the collection requester's terminal, the electronic device 1000 may transmit reception completion notification information confirming that the delivery address information has been obtained to the collection requester's terminal. In S224, the electronic device 1000 may obtain parcel delivery information from the collection requester terminal. In S226, when waste plastic or waste toy products arrive at the collection point, the electronic device 1000 may transmit notification information confirming that the waste toy courier has arrived to the collection requester terminal.

Further, according to an embodiment, in S218, the electronic device 1000 checks whether the subject transmitting the collection request information is an individual or an institution, and when the subject transmitting the collection request information is identified as an institution, S228 At , a collection schedule can be established. For example, the electronic device 1000 may generate collection plan information based on the type of the collection requester. In S230, the electronic device 1000 may determine a collection schedule plan by determining collection route information for each collection vehicle based on the collection plan information.

In operation S232, the electronic device 1000 may transmit collection schedule information including collection route information for each collection vehicle for each collection vehicle. In operation S234, the electronic device 1000 may transmit collection schedule notification information to a terminal for each vehicle to be collected or a terminal for the collector based on the collection schedule displayed on the collection route information for each vehicle. In S236, the electronic device 1000 may optimize the collection plan information by using an artificial intelligence model learned based on the collection childcare institution selection optimization algorithm. In operation S238, the electronic device 1000 may optimize collection route information based on an artificial intelligence model that outputs a traffic line for each collection vehicle as a solution so that an output value of a predetermined collection cost function becomes small. In S240, the electronic device 1000 may optimize the collection route for each collection vehicle by using another artificial intelligence model used in S236 to S238 that optimizes the selection of child care institutions to be collected based on the characteristics of each collection driver. .

In S242, the electronic device 1000 may check whether or not the collection vehicles arrive at the location of the collection requester according to the preset collection schedule. In S244, the electronic device 1000 may obtain information about whether disinfection or waste toy collection has been completed from the collection vehicle terminal. In step S246, the electronic device 1000 may transmit collection completion notification information to the collection requester terminal when waste toys or waste plastics collected from individuals or child care institutions reach a predetermined collection point.

In S247, the electronic device 1000 acquires information on whether the collected waste plastics are to be discarded or circulated from the classification system, and matches the obtained classification result with information on the type and weight of the waste plastics to obtain information on the blockchain network. can be stored in For example, in S248, the electronic device 1000 acquires the waste plastic primary classification result from the classification system 3000, and when it is determined that the obtained waste plastic product is a circulation target and requires repair, the waste plastic product can be identified as a target for repair. In S250, when the repair of the repaired waste plastic or waste toy product is completed, the electronic device 1000 may generate inventory information including information about the state and price of the waste plastic or waste toy product.

In S252, when the electronic device 1000 obtains a primary classification result indicating that the waste plastic collected from the classification system 3000 is to be discarded as a result of performing S247, the electronic device 1000 transmits information indicating that the target waste plastic product is a product to be discarded. It can be put into the recycling process by recording and storing in the blockchain network and providing the waste plastic product to the classification system 3000. In S254, the electronic device 1000 inputs the waste plastic product identified as a waste into the classification system 3000, and when the waste plastic recycling material is classified through the recycling process of the classification system 3000, the waste plastic is recycled. Information on the material may be acquired from the classification system 3000, and inventory information may be generated according to the information on the waste plastic recycling material.

3 is a flowchart of a method of providing a waste plastic collection service according to an embodiment.

In S310, the electronic device 1000 may obtain waste plastic collection request information from an external device connected to the electronic device. According to an embodiment, the collection request information acquired by the electronic device 1000 includes collection requester identification information for identifying collection requesters requesting collection of the waste plastic from an external device connected to the electronic device, and waste plastics subject to the collection request. It may include at least one of type information, information on the weight of waste plastics subject to the collection request, or information on the date of receipt of the collection request.

In S320, the electronic device 1000 may identify the type of the collection requester who has transmitted the collection request information. For example, the electronic device 1000 may identify whether the collection person who has transmitted the collection request information is an individual or an institution. In S330, the electronic device 1000 may obtain collection plan information based on the identified type of collection requester. For example, when the collection requester is not identified as an individual but is identified as an institution, the electronic device 1000 may obtain collection plan information from an artificial intelligence model that outputs collection plan information when collection request information is input. .

In S340, the electronic device 1000 may obtain collection route information for each collection vehicle based on the collection plan information. For example, when the collection plan information determined according to the collection request information is input, the electronic device 1000 inputs the collection plan information to an artificial intelligence model that outputs collection route information for each collection vehicle, thereby providing optimized route information for each collection vehicle. By determining the waste plastic of a single material, it is possible to effectively collect waste plastic at a low cost. In S350, the electronic device 1000 may transmit the collection route information to a collection vehicle terminal connected to the electronic device or a collector terminal used by collectors boarding the collection vehicle.

In addition, although not shown in FIG. 3, in a method for providing a waste plastic collection service by an electronic device according to another embodiment, when the type of collection requester is identified as an individual, confirmation of receipt of the collection request indicating that the collection request information has been received The method may further include transmitting information to a terminal of the collection requester connected to the electronic device, and transmitting collection completion information to the terminal of the collection requester when the waste plastic to be collected is collected from the collection requester.

In addition, although not shown in FIG. 3, a method for providing a waste plastic collection service by an electronic device includes an identification result of whether waste plastic obtained from a collection requester from a sorting system connected to the electronic device is to be discarded or circulated; When the obtained waste plastic is a target for circulation, a primary classification result including an identification result regarding whether the obtained waste plastic is usable or needs repair is obtained, and from an external device connected to the electronic device, among the obtained waste plastic , By pre-processing the waste plastic identified as a waste plastic, extracting mixed flakes by crushing the pre-treated plastic, and inserting the extracted mixed flakes into an artificial intelligence-based spectroscopic sorter, the recycled flakes are separately extracted from the artificial intelligence-based spectroscopic sorter. Obtaining a secondary classification result for at least one of type information, weight information, or purity information, and generating recycled plastic inventory information for each collection requester based on the primary classification result and the secondary classification result You may.

According to an embodiment, the inventory information generated by the electronic device 1000 includes identification information of collection requesters, information on the date of receipt of the collection request on which the collection request was received, information on the type of waste plastic requested by the collection requesters, and information collected by the collection requesters. The requested waste plastic weight information, the type information of recycled flakes produced from the collected waste plastics, the weight information of the recycled flakes, and the purity information of the recycled flakes may be matched and stored in the electronic device.

In addition, according to an embodiment, when the recycled flakes (recycled plastic material extracted from waste plastic) are sold, the inventory information further includes sales price information of the recycled flakes and point information corresponding to the sales price of the recycled flakes. may also include

In addition, although not shown in FIG. 3, a method of providing a waste plastic collection service by an electronic device generates point information for each collection requester based on recycled plastic inventory information generated for each collection requester, and converts the generated point information to the collection requester. It can be transmitted to an external device connected to the electronic device. For example, the electronic device 1000 may transmit point information for each collection requester to the collection requester terminal.

According to an embodiment, the point information generated by the electronic device 1000 may be determined based on price information determined according to the purity, type, and weight information of the recycled plastic material finally extracted from the classification system 3000. According to an embodiment, point information may be packed in an Ethereum-based NFT (Not Fungible Token) and stored in each of the electronic device connected to a blockchain network and an external device connected to the electronic device.

4 is a diagram for explaining a process of generating collection plan information according to an exemplary embodiment.

In S410, when the collection request information is not obtained, the electronic device 1000 obtains collection demand prediction information from the collection demand prediction model according to a preset cycle, and generates collection plan information based on the obtained collection demand prediction information. may be In S420, the electronic device 1000 may generate collection plan information based on the collection demand prediction information. For example, the electronic device 1000 according to the present disclosure predicts the collection demand for a preset period from a pre-learned collection demand prediction model even if collection request information is not received from collection requestors, and predicts the predicted collection demand. By generating collection plan information based on the results, it is possible to improve plastic collection efficiency while lowering the cost of operating plastic collection services.

According to an embodiment, the collection demand prediction model, when the prediction target time information and the waste plastic collection requester identification information are input, the expected number of waste plastic collection requests per day, week, and month within the period indicated in the prediction target time information, and the expected waste plastic collection requester identification information. It may be an artificial intelligence model trained to output plastic weight information or expected waste plastic type information.

5 is a diagram for explaining a process of generating collection route information according to an exemplary embodiment.

According to an embodiment, the electronic device 1000, in S502, provides learning data related to location information (eg, GPS information) of child care institutions, work time required for disinfection/waste plastic collection at the child care institution, and travel time required to travel to the child care institution. can be obtained. In S504, the electronic device 1000 may pre-process the acquired learning data. For example, the electronic device 1000 identifies a missing value appearing in the learning data, supplements the identified missing value, or based on an available probability value representing the degree to which some of the learning data is suitable for the collection schedule among the acquired learning data. The learning data may be preprocessed by performing a process of removing some of the learning data.

In S506, the electronic device 1000 may train an artificial intelligence model based on the preprocessed training data. According to an embodiment, the artificial intelligence model used by the electronic device 1000 may be a recurrent neural network-based Long Short Term Memory (LSTM) model optimized for predicting time-series data. In S508, the electronic device 1000 may collect platform data. For example, the electronic device 1000 may obtain past plastic waste collection data received from individuals or institutions.

In operation S510, the electronic device 1000 may determine variables constituting a collection cost function for optimizing collection plan information or collection route information. According to an embodiment, the electronic device 1000 may determine reference variables used to determine the output value of the collection cost function, such as the departure point, destination, and maximum load of the collection cost function. According to an embodiment, the electronic device 1000 may set variables of a collection cost function used for optimizing collection plan information determined based on collection request information and variables of a collection cost function used for optimizing collection schedule information for each vehicle. By setting differently, waste plastic collection efficiency can be improved at a low collection cost, despite various variables that can occur for each collection vehicle.

In S512, the electronic device 1000 may optimize AI models based on a preset optimization algorithm. According to an embodiment, since the electronic device 1000 has a high computational complexity that is usually classified as NP-hard in the case of optimization modeling configured for collection plan scheduling, a solution is solved within a certain time (polynomial time) In order to overcome the limitation of not deriving , an approximate solution having the output value of the lowest cost function (eg, collection plan information, collection route information for each vehicle) may be determined by using a heuristic algorithm. According to another embodiment, the electronic device 1000 may train an artificial intelligence model to derive the lowest-cost or most suitable solution by applying a global optimization technique based on a genetic algorithm to training data. .

In S514, the electronic device 1000 may select a childcare center to be visited for each collection vehicle based on a result of applying an optimization algorithm to at least one artificial intelligence model. In operation S516 , the electronic device 1000 may recommend a schedule for visiting the child care institution by determining collection route information for each collection vehicle and transmitting the determined collection route information for each collection vehicle.

6 is a diagram for explaining a detailed process of generating collection plan information and collection schedule information for each vehicle by an electronic device according to an exemplary embodiment.

The electronic device 1000 may generate collection plan information and collection route information for each collection vehicle by using a plurality of artificial intelligence models. For example, the electronic device 1000 obtains collection request information 602 from a collection requester terminal, and inputs the obtained collection request information 602 to the first artificial intelligence model 610 to generate collection plan information 620. can be obtained. According to another embodiment, the electronic device 1000 may obtain the collection plan information by obtaining the demand prediction information 604 from the collection prediction model and inputting the obtained demand prediction information to the first artificial intelligence model. According to an embodiment, the demand prediction information may correspond to the collection request information and may be prepared in an item and format corresponding to the collection request information.

According to an embodiment, the first artificial intelligence model may be a model that outputs collection plan information that minimizes an output value of the first collection cost function when collection request information is input. According to an embodiment, the collection plan information 620 includes collection requester schedule information 622, collection vehicle identification information 623 and 625, and collection vehicle identification information 623 and 625 for which a waste plastic collection request has been received within a preset period. ) may include collection schedule information 624 and 626 for each collection vehicle.

In addition, according to an embodiment, the collection schedule information for each collection vehicle includes collection requester identification information for identifying collection requesters assigned to each collection vehicle, and first collection priority indicating collection priority among collection requesters assigned to each collection vehicle. The ranking information 647, information on the weight of waste plastic subject to the collection request requested by the collection requester according to the collection requester identification information, and information on the date of receipt of the collection request by the collection requestor may be included.

According to an embodiment, the first artificial intelligence model may include the total number of collection vehicles, total travel time of collection vehicles, total travel distance of collection vehicles, weight information of waste plastics subject to request for collection according to the collection request information, and waste plastics subject to request for collection according to the collection request information. A first collection cost function including plastic type information, the average time required for waste plastic collection after moving to the collection requester's location, and the average time required for waste plastic disinfection after moving to the collection requester's location as input variables. The output value of 612 can be learned to be minimized.

In more detail, although not shown in FIG. 6 , the electronic device 1000 learns the first artificial intelligence model based on a user input to the electronic device prior to acquiring collection request information from collection requesters. Collection plan learning data for processing may be obtained, and an available probability value for the collection plan learning data may be determined based on a correlation between the collection plan learning data. The electronic device 1000 preprocesses the collection plan learning data by converting some collection plan learning data from among the collection plan learning data into an input format of the first artificial intelligence model based on the determined available probability value, and preprocessing the collection plan learning data. The first artificial intelligence model may be trained based on collected collection plan learning data.

Hereinafter, a process in which the electronic device 1000 learns the first artificial intelligence model so that the output value of the first collection cost function is minimized will be described in detail. For example, the electronic device 1000 may determine optimization candidate models by applying a mixed-integer programming algorithm to preprocessed training data. The electronic device 1000 may determine a plurality of optimization candidate models that minimize collection-related costs based on mixed integer programming despite high computational complexity.

In addition, the electronic device 1000 first collects solutions output from the optimization model based on a heuristic algorithm in order to further reduce the high computational complexity of solutions output from the determined optimization candidate models. A solution can be identified that minimizes the output of the cost function. The electronic device 1000 may identify a solution that is close to the optimal solution within a certain period of time based on a heuristic algorithm. The electronic device 1000 learns the first artificial intelligence model by identifying an optimization candidate model that outputs a solution identified based on a heuristic algorithm and setting model information of the optimization candidate model as model information of the first artificial intelligence model. can make it

Also, according to an embodiment, the electronic device 1000 applies a genetic algorithm to solutions output from optimization candidate models, thereby minimizing output values of the collection cost function for solutions output from the optimization model. can also identify. A process in which the electronic device 1000 identifies a solution for which an output value of a collection cost function is minimized for solutions output from an optimization model based on a genetic algorithm will be described in detail with reference to FIG. 10 described later.

According to an embodiment, when the collection plan information 620 is input, the electronic device 1000 outputs the second collection schedule information 640 for each vehicle to minimize the output value of the second collection cost function 632. Collection schedule information for each vehicle may be obtained using an artificial intelligence model. According to an embodiment, the collection schedule information 640 for each vehicle includes collection requester identification information 649 for identifying a collection requester assigned to each collection vehicle, location information of collection requesters classified according to the collection requester identification information, and Second collection priority information 648 regarding collection priorities among collection requesters assigned to each collection vehicle, location information of a collection point allocated to each collection vehicle, and starting point location information for each collection vehicle for the waste plastic collection and destination location information for each collection vehicle.

According to an embodiment, the second artificial intelligence model 630 determines the current location of each collection vehicle, the total distance of combined paths generated by connecting location information of collection requesters assigned to each collection vehicle, and the current location of each collection vehicle. It may be learned to minimize an output value of the second collection cost function 632 including, as input variables, the travel time taken to travel the combined routes and the preset work capacity weight of the collector assigned to each fraudulent collection vehicle.

In more detail, although not shown in FIG. 6 , the electronic device 1000 learns the second artificial intelligence model based on a user input to the electronic device prior to obtaining collection request information from collection requesters. acquiring collection schedule learning data for processing, identifying a missing value (NULL) included in the generated collection schedule learning data, calculating a normal distribution of the identified collection schedule learning data, and calculating 3 to the calculated normal distribution. By applying the sigma rule, collection schedule learning data corresponding to a partial section formed in both directions from the center of the normal distribution map may be removed. The electronic device 1000 may train the second artificial intelligence model to minimize the second collection cost function based on the collection schedule learning data from which the collection schedule learning data is removed.

In the electronic device 1000 according to the present disclosure, a first artificial intelligence model learned to minimize a first collection cost function and collection plan information obtained from the first artificial intelligence model are learned to minimize a second collection cost function. By inputting into the second artificial intelligence model, there is an advantage in that plastics can be collected at an optimal collection cost according to variables that may vary for each vehicle. In addition, the electronic device 1000 sequentially utilizes artificial intelligence models learned using a plurality of cost functions in which input variables of the collection cost function are set differently to set optimal collection route information suitable for the current status of each collection vehicle. be able to

For example, the input variables of the first collection cost function used by the electronic device 1000 are the total number of collection vehicles, the total travel time of the collection vehicles, the total travel distance of the collection vehicles, and the location of the person requesting collection. The average time required for plastic collection is included as an input variable, but the second collection cost function includes the current location of each collection vehicle, the total distance of combined routes generated by connecting the location information of collection requesters assigned to each collection vehicle, and the collection vehicle Since the travel time taken to move the combination paths from the current location of each vehicle and the preset work capacity weight of the collector assigned to each collection vehicle are included as input variables, the reference variables used to derive the optimization solution may be set differently.

Accordingly, the electronic device 1000 according to the present disclosure quickly calculates optimal collection plan information on the entire collection schedule based on the first collection cost function, and then calculates optimal collection schedule information suitable for variable conditions for each vehicle. Therefore, there is an advantage in that waste plastic can be effectively collected at a low cost. It can be seen that the first collection priority in the collection schedule information for each vehicle of the collection plan information shown in Figure 624 is different from the second collection priority in the collection route information for each vehicle shown in Figure 642. Similarly, it can be confirmed that the first collection priority shown in Figure 626 is optimized to the second collection priority shown in Figure 644 through the second artificial intelligence model optimized according to the second collection cost function.

7 is a diagram for explaining a process of defining collection plan information and optimizing the defined collection plan information by an electronic device according to another embodiment.

According to an embodiment, the electronic device 1000 may obtain collection request information and generate collection requester schedule information 710 based on the obtained collection request information. The electronic device 1000 sets a time required for collection and a collection delay according to the collection request schedule appearing on the collection requester schedule information 710 as a cost criterion 720, and a cost function that outputs a cost value according to the set cost criterion value. can define The electronic device 1000 may generate collection route information for each vehicle shown in the figure 730 using an artificial intelligence model learned based on the cost function.

8 is a diagram for specifically describing collection request information, collection plan information, and collection schedule information for each vehicle used by an electronic device according to an exemplary embodiment.

The collection request information 810 acquired by the electronic device 1000 from the collection requester terminal includes collection requester identification information 812, waste plastic type information 814, waste plastic weight information 816, or collection request receipt date information 818. ) may include at least one of In addition, as the electronic device 1000 inputs the collection request information 810 to the first artificial intelligence model, the collection plan information 820 obtained from the first artificial intelligence model includes collection vehicle identification information 822, collection requester schedule Information 823 and collection schedule information 824 for each vehicle may be included. According to an embodiment, the collection schedule information 824 for each vehicle included in the collection plan information includes collection requester identification information 825 assigned to each vehicle, first collection priority information 826, and waste plastic weight information subject to a collection request. It may include at least one of 827, collection request reception date information 828, and collection request object waste plastic type information 829.

9 is a diagram for comparing and describing collection schedule information for each vehicle and collection route information for each vehicle according to an exemplary embodiment.

According to an embodiment, as described above with reference to FIG. 8 , the collection schedule information 824 for each vehicle in the collection plan information 820 includes collection requester identification information 825 and first collection priority information 826 assigned to each vehicle. , waste plastic weight information 827 subject to collection request, information on the date of receiving the collection request 828, and waste plastic type information 829 subject to collection request.

The electronic device 1000 may obtain collection route information 910 for each vehicle by inputting the collection plan information 820 including the collection schedule information 824 for each vehicle to the second artificial intelligence model. According to an embodiment, the collection route information 910 for each vehicle includes collection requester identification information 912 assigned to each vehicle, location information 914 of collection requesters, second collection priority information 916, and information assigned to each vehicle. Information on the location of the collection point (918), information on the type of waste plastic subject to request for collection (920), information on the weight of waste plastic subject to request for collection (922), information on the location of departure point for each vehicle (924), or information on the location of destination for each vehicle (926) may include at least one of them.

10 is a diagram for explaining an example of a genetic algorithm used by an electronic device to learn an artificial intelligence model according to an embodiment.

Referring to figure 1002, a process in which the electronic device 1000 applies a genetic algorithm to solutions output from optimization candidate models in order to identify a solution for which the output value of the collection cost function is minimized is shown. For example, the electronic device 1000 calculates the cost of various collection plan information using a cost function that outputs a predetermined cost value according to various constraint conditions defined according to input variables of the cost function, and calculates a predetermined specific cost value. After generating a population with chromosomes as an initial population, harvesting plan information that outputs a cost value that satisfies the condition is generated, harvesting plan information capable of surviving the next generation deficit in the generated population is identified, and among the identified collection plan information, the cost Optimal collection plan information may be determined by selecting collection plan information that satisfies the condition as surviving objects of the next generation.

For example, in S1004, the electronic device 1000 may generate an initial chromosome map representing one collection plan information as a solution. In operation S1006, when the initial chromosome map is generated, the electronic device 1000 may determine an initial population of guide chromosomes. For example, the electronic device 1000 may randomly select some guide chromosomes from among chromosomes appearing on the initial chromosome map, and generate an initial population including the selected some guide chromosomes.

In operation S1008, the electronic device 1000 may calculate fitness for initial chromosomes by applying the guide chromosome to the chromosome map. In S1010, the electronic device 1000 calculates the degree of fitness for the initial chromosome map, and when a predetermined terminal condition (eg, a target cost condition on the collection plan information) is satisfied, a chromosome appearing in the corresponding chromosome map is selected as a solution, , can terminate the application of the genetic algorithm. However, when it is identified that the predetermined terminal condition is not satisfied in S1010, the electronic device 1000 may select some chromosomes from the initial chromosome map as parent genes based on the degree of fitness.

In operation S1014, the electronic device 1000 may generate chromosomes that will survive the fittest in the next generation by modeling the offspring propagation process of the selected parent gene chromosomes. According to an embodiment, in S1014, the electronic device 1000 may generate next-generation chromosome objects of parent gene chromosomes by modeling a breeding process such as crossing over and CROSS OVER. In operation S1016, the electronic device 1000 removes some of the chromosomes that do not most match the cost condition among newly generated chromosome individuals of the next generation in order to maintain a population having the same size as the size of the initial population. Chromosomal individuals that will survive the generation can be determined.

The electronic device 1000 applies a genetic algorithm to solutions output from optimization candidate models, thereby identifying a solution in which an output value of a collection cost function for solutions output from an optimization model is minimized, and deriving the corresponding solution. Collection plan information corresponding to the optimization candidate model may be identified.

11 is a diagram for explaining a process of tracking and recording inventory information according to collection of waste plastics by an electronic device according to an exemplary embodiment.

In S1102, the electronic device 1000 may identify whether the collection vehicle has arrived at the collection point. In operation S1104, the electronic device 1000 may generate first inventory information according to collection requester identification information, waste plastic type, and weight information. For example, after the collection vehicle arrives at the collection point, the electronic device 1000 may obtain first inventory information according to the type and weight information of waste plastic discharged for each collection requester from the classification system 3000 . According to another embodiment, the electronic device 1000 generates first inventory information based on the type and weight information of waste plastic currently collected from the classification system 3000, and sends the generated first inventory information to a blockchain network. can be recorded and stored.

In operation S1106, the electronic device 1000 may generate second inventory information by applying the primary classification result to the first inventory information. For example, the electronic device 1000 may determine whether waste plastics collected from an external device (eg, the classification system 3000) connected to the electronic device 1000 are to be discarded or circulated, and the obtained When the waste plastic is a circulation target, a primary classification result including an identification result on whether the waste plastic is usable or repair is required is obtained, and the obtained primary classification result is added to the first inventory information, thereby providing second inventory information. can create The electronic device 1000 may record and store the second inventory information on a blockchain network in which the electronic device and the classification system participate.

In operation S1108, the electronic device 1000 may generate third inventory information by applying a secondary classification result to the second inventory information. For example, the electronic device 1000 may obtain a secondary classification result from an external device (eg, the classification system 3000) connected to the electronic device 1000. For example, the classification system 3000 pre-processes waste plastics classified as waste among the collected waste plastics, pulverizes the pre-treated plastics to extract mixed flakes, and puts the extracted mixed flakes into an artificial intelligence-based spectroscopic sorter. By inserting, it is possible to separate and extract flakes by color and type. The electronic device 1000 may obtain a secondary classification result regarding at least one of type information, weight information, and purity information of the reproduced flakes that are separately extracted through the artificial intelligence-based spectroscopic sorter from the classification system 3000 . The electronic device 1000 generates third inventory information by adding a secondary classification result to the second inventory information, and the electronic device, the collection requester terminal, the collector terminal, and the classification system 3000 generate third inventory information. It can be recorded and stored on participating blockchain networks.

The electronic device 1000 according to the present disclosure may generate recycled plastic inventory information for each collection requester based on the first classification result and the second classification result obtained from the classification system 3000 . For example, the electronic device 1000 relates to type, weight, or purity information of recycled plastic generated from waste plastic discharged for each collection requester based on the above-described first inventory information, second inventory information, and third inventory information. Recycled plastic inventory information can be created.

12 is a diagram for explaining a classification process for each plastic material through a classification system connected to an electronic device according to an embodiment.

The electronic device 1000 according to the present disclosure includes information on the collection location, type, color, flammability/flame retardancy characteristics, weight, and price of recycled plastic materials (eg, recycled pellets) extracted separately through the classification system 3000. Inventory information can be created, and the generated recycled plastic inventory information can be recorded and stored on a blockchain network. The classification system 3000 connected to the electronic device 1000 pulverizes the waste plastics classified as waste, so that when ABS and PP are mixed (1202), when PP, PE and ABS are mixed (1204), PP and PE are mixed. Mixed flakes corresponding to the mixed case (1206) and the mixed case of PP and ABS (1208) can be obtained, and by repeatedly feeding the mixed flakes into the artificial intelligence model-based spectroscopic sorter, As described above, it is possible to obtain recycled plastic materials having high purity by color and material. According to an embodiment, the electronic device 1000 calculates the average number of inputs into the classification system for each collection requester, which is required to extract all recycled plastic materials for each plastic material having a certain purity or higher from waste plastic products, and calculates the number of inputs according to the calculated number of inputs. Based on this, point information to be compensated for to the collection requester may be determined.

According to an embodiment, the electronic device 1000, since the smaller the number of inputs into the classification system, the smaller cost is consumed for the classification of waste plastics composed of plastic materials of a single material, relatively more point information, and the input into the classification system. It can be provided to requesters with a low average number of collections. Conversely, the electronic device 1000 may provide relatively less point information to collection requesters who discharge plastic waste products having a high average sorting system input count.

13 is a block diagram of an electronic device according to an embodiment.

14 is a block diagram of an electronic device according to another embodiment.

As shown in FIG. 13 , an electronic device 1000 according to an embodiment may include a processor 1300, a network interface 1500, and a memory 1700. However, not all illustrated components are essential components. The electronic device 1000 may be implemented with more components than those illustrated, or the electronic device 1000 may be implemented with fewer components.

For example, as shown in FIG. 14 , the electronic device 1000 includes a processor 1300, a network interface 1500, and a memory 1700, as well as a user input interface 1100, an output unit 1200, and a sensing unit. 1400, a network interface 1500, an A/V input unit 1600, and a memory 1700 may be further included.

The user input interface 1100 means a means through which a user inputs data for controlling the electronic device 1000 . For example, the user input interface 1100 includes a key pad, a dome switch, a touch pad (contact capacitive method, pressure resistive film method, infrared sensing method, surface ultrasonic conduction method, A spray tension measuring method, a piezo effect method, etc.), a jog wheel, a jog switch, and the like may be included, but are not limited thereto.

The user input interface 1100 may receive a user input for using a waste plastic collection service or recycling service. For example, the user input interface 1100 may generate one or more user interface screens for transmitting a message to a collection requester terminal by a collector terminal.

The output unit 1200 may output an audio signal, a video signal, or a vibration signal, and the output unit 1200 may include a display unit 1210, a sound output unit 1220, and a vibration motor 1230. there is. The display unit 1210 includes a screen for displaying and outputting information processed by the electronic device 1000 . The audio output unit 1220 outputs audio data received from the network interface 1500 or stored in the memory 1700 . Also, the sound output unit 1220 outputs sound signals related to functions performed by the electronic device 1000 (eg, a call signal reception sound, a message reception sound, and a notification sound).

The processor 1300 typically controls overall operations of the electronic device 1000 . For example, the processor 1300 executes programs stored in the memory 1700, thereby providing a user input interface 1100, an output unit 1200, a sensing unit 1400, a network interface 1500, and an A/V input unit. (1600) and the like can be controlled overall. Also, the processor 1300 may perform at least some of the functions for performing the plastic recycling or plastic collection service described in FIGS. 1 to 12 by executing programs stored in the memory 1700 .

According to an embodiment, the processor 1300 obtains waste plastic collection request information from an external device connected to the electronic device by executing the one or more instructions, and the collection requester who transmits the collection request information. is identified, collection plan information is obtained based on the identified collection requester type, collection route information for each collection vehicle is obtained based on the acquired collection plan information, and the collection route information is converted into the electronic device. It can be transmitted to the terminal for each collection vehicle connected to .

The sensing unit 1400 may detect a state of the electronic device 1000 or a state around the electronic device 1000 and transmit the sensed information to the processor 1300 . For example, the sensing unit 1400 includes a magnetic sensor 1410, an acceleration sensor 1420, a temperature/humidity sensor 1430, an infrared sensor 1440, and a gyroscope sensor 1450. ), a position sensor (eg, GPS) 1460, an air pressure sensor 1470, a proximity sensor 1480, and an RGB sensor (illuminance sensor) 1490, but may include at least one, but is not limited thereto. Since a person skilled in the art can intuitively infer the function of each sensor from its name, a detailed description thereof will be omitted.

The network interface 1500 may include one or more components allowing the electronic device 1000 to communicate with other devices (not shown) and the server 2000 . The other device (not shown) may be a computing device such as the electronic device 1000 or a computing device capable of data communication corresponding to a collection requester terminal, a collector terminal, or a collection vehicle terminal.

For example, the network interface 1500 may include a wireless communication interface 1510, a wired communication interface 1520, and a mobile communication unit 1530. The wireless communication interface 1510 includes a short-range wireless communication unit, a Bluetooth communication unit, a Bluetooth Low Energy (BLE) communication unit, a near field communication unit, a WLAN (Wi-Fi) communication unit, and a Zigbee communication unit. , an infrared data association (IrDA) communication unit, a Wi-Fi Direct (WFD) communication unit, and an ultra wideband (UWB) communication unit, but are not limited thereto.

The wired communication interface 1520 may include at least one wired interface for exchanging data with an external device connected to the electronic device through wired communication. The mobile communication unit 1520 transmits and receives a radio signal with at least one of a base station, an external terminal, and a server on a mobile communication network. Here, the radio signal may include a voice call signal, a video call signal, or various types of data according to text/multimedia message transmission/reception.

An audio/video (A/V) input unit 1600 is for inputting an audio signal or a video signal, and may include a camera 1610 and a microphone 1620. The camera 1610 may obtain an image frame such as a still image or a moving image through an image sensor in a video call mode or a photographing mode. An image captured through the image sensor may be processed through the processor 1300 or a separate image processing unit (not shown).

The microphone 1620 receives external sound signals and processes them into electrical voice data. For example, the microphone 1620 may receive a sound signal from an external device or a user. The microphone 1620 may receive a user's voice input. The microphone 1620 may use various noise cancellation algorithms to remove noise generated in the process of receiving an external sound signal.

The memory 1700 may store programs for processing and control of the processor 1300 and may store data input to or output from the electronic device 1000 . Also, the memory 1700 may store at least one artificial intelligence model used by the electronic device 1000, collection plan information, inventory information, and collection route information for each vehicle.

In addition, the memory 1700 may store information about an optimization algorithm such as at least one neural network model used by the electronic device 1000, a genetic algorithm used for learning an artificial intelligence model, and a heuristic algorithm. For example, the memory 1700 may store layers, nodes, and weight values related to connection strengths of the layers in at least one neural network model. In addition, the electronic device 1000 may further store learning data generated by the electronic device 1000 to learn the neural network model.

The memory 1700 may include a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (eg SD or XD memory, etc.), RAM (RAM, Random Access Memory) SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk , an optical disk, and at least one type of storage medium.

Programs stored in the memory 1700 may be classified into a plurality of modules according to their functions, such as a UI module 1710, a touch screen module 1720, and a notification module 1730. .

The UI module 1710 may provide a specialized UI, GUI, or the like that works with the electronic device 1000 for each application in order to provide a plastic recycling or plastic collection service. The touch screen module 1720 may detect a user's touch gesture on the touch screen and transmit information about the touch gesture to the processor 1300 . The touch screen module 1720 according to some embodiments may recognize and analyze the touch code. The touch screen module 1720 may be configured as separate hardware including a controller.

The notification module 1730 may generate a signal to notify occurrence of a predetermined event when collection request information is received, collection plan information is updated, or collection route information for each vehicle is updated. Examples of events according to an embodiment include call signal reception, message reception, key signal input, schedule notification, and the like. The notification module 1730 may output a notification signal in the form of a video signal through the display unit 1210, output a notification signal in the form of an audio signal through the sound output unit 1220, and may output a notification signal in the form of a vibration motor 1230. A notification signal may be output in the form of a vibration signal through

15 is a block diagram of a server according to an embodiment.

According to one embodiment, the server 2000 may include a network interface 2100, a database 2200 and a processor 2300. The configuration of the server 2000 shown in FIG. 15 may correspond to the configuration of the electronic device disclosed in FIGS. 13 and 14. In this case, the server 2000 further includes the configurations of the electronic device disclosed in FIGS. 13 and 14. may also include According to an embodiment, the server 2000 may be a computing device used by a service provider to provide a plastic collection service or a plastic recycling service.

The network interface 2100 interworks with a collection requester terminal, a collector terminal, a collection vehicle terminal, and a sorting system to transmit/receive data necessary for performing a plastic collection or recycling service.

According to another embodiment, the network interface 2100 transmits information on an artificial intelligence model learned in an electronic device or server, or information on a neural network model (eg, weight values related to layers and connection strengths between layers). Can transmit and receive. According to another embodiment, the network interface 2100 is information about an artificial intelligence model trained by a server, information about layers of an artificial neural network and nodes included in the layers, or weights related to connection strengths of layers in a neural network. Values may be transmitted to the electronic device 1000 .

Also, according to an embodiment, the database 2200 may correspond to the memory described above with reference to FIGS. 13 and 14 . For example, the database 2200 may store collection request information received from an external device connected to the server, collection plan information, collection route information, plastic inventory information, and information on artificial intelligence models.

According to an embodiment, the processor 2300 may control overall operations of the server 2000. For example, the processor 2300 may perform all or part of the electronic device operations illustrated in FIGS. 1 to 14 by controlling the network interface 2100 and the database 2200 .

16 is a diagram for explaining a process of performing a waste plastic recycling method by interworking a collection requester terminal, a service providing server, a collection vehicle terminal, and a classification system according to an embodiment.

In S1602, the service providing server 1640 may generate demand prediction information. According to an embodiment, the service providing server 1640 may generate demand prediction information according to a preset period. In S1604, the collection vehicle terminal 1650 may generate initial collection route information. For example, the collection vehicle terminal 1650 may generate initial collection route information using a navigation service initiated through the Internet. In S1606, the collection requester terminal 1630 may generate collection request information. In S1608, the collection requester terminal 1630 may transmit the generated collection request information to the service providing server 1640.

According to an embodiment, the service providing server 1640 may perform all or part of the operations performed by the electronic device described above with reference to FIGS. 1 to 14 . In operation S1609, the service providing server 1640 may generate collection plan information from the first artificial intelligence model by inputting the collection request information into the first artificial intelligence model. In S1610, the service providing server 1640 may generate collection path information for each collection vehicle. For example, the service providing server 1640 may generate collection route information for each collection vehicle by inputting collection plan information to the second artificial intelligence model.

In operation S1612, the service providing server 1640 may transmit collection route information to the collection vehicle terminal 1650. In operation S1614, the collection vehicle terminal 1650 may modify and update pre-stored initial collection route information based on the collection route information for each vehicle provided from the service providing server 1640. In S1616, when the waste plastic is collected, the collection vehicle terminal 1650 may generate first inventory information including waste plastic type and weight information. In S1618 , the collection vehicle terminal 1650 may transmit first inventory information to the classification system 1660 .

In S1620, the classification system 1660 classifies the waste plastic into whether it is to be discarded or circulated, and in the case of waste plastic identified as circulated, a primary classification result is generated regarding whether repair is required or whether it can be used immediately, Second stock information may be generated by additionally reflecting the primary classification result on the first stock information.

In S1622, the sorting system 1660 pre-processes the waste plastic identified as a waste object, extracts mixed flakes by crushing the pre-treated plastic, and inserts the extracted mixed flakes into an artificial intelligence-based spectroscopic sorter to analyze the artificial intelligence-based spectroscopy. Secondary classification results regarding at least one of type information, weight information, and purity information of the regenerated flakes separately extracted from the sorter may be generated. In operation S1624, the classification system 1660 may generate third inventory information by additionally reflecting the secondary classification result on the second inventory information.

In operation S1628, the classification system 1660 may transmit third inventory information to the service providing server 1640. In operation S1630, the classification system 1660 may generate point information for each collection requester based on the third inventory information. In S1632, the classification system may transmit the generated point information to the service providing server 1640 and the collection requester terminal 1630. However, according to another embodiment, the service providing server 1640 may obtain point information from the classification system and transmit the obtained point information to the collection requester terminal. In S1634, the collection requester terminal 1630 may output acquired point information.

The method for providing a waste plastic collection service according to the present disclosure may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the medium may be those specially designed and configured for the present invention or those known and usable to those skilled in computer software.

Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements made by those skilled in the art using the basic concept of the present invention defined in the following claims are also included in the scope of the present invention. fall within the scope of the right

Claims (20)

A method for providing a waste plastic collection service by an electronic device,
acquiring waste plastic collection request information from an external device connected to the electronic device;
identifying the type of collection requester who has transmitted the waste plastic collection request information;
obtaining collection plan information based on the identified type of collection requester;
acquiring collection route information for each collection vehicle based on the acquired collection plan information;
transmitting the collection route information to a terminal for each collection vehicle connected to the electronic device;
The identification result of whether the waste plastic obtained from the collection requester from the external device connected to the electronic device is a target for disposal or circulation, and if the obtained plastic waste is a target for circulation, whether it can be used immediately or needs repair. Obtaining a primary classification result including an identification result regarding whether or not;
From the external device connected to the electronic device, among the obtained waste plastics, waste plastics identified as waste plastics are pretreated, and mixed flakes are extracted by crushing the pretreated plastics, and the extracted mixed flakes are placed in an AI-based spectroscopy machine. obtaining a secondary classification result for at least one of type information, weight information, or purity information of the reproduced flakes classified and extracted from the artificial intelligence-based spectroscopic sorter by inserting; and
generating recycled plastic inventory information for each collection requester based on the first classification result and the second classification result; Including, method. The method of claim 1, wherein the method
when the type of the collection requester is identified as an individual, transmitting collection request acknowledgment information indicating that the waste plastic collection request information has been received to a terminal of the collection requester connected to the electronic device; and
transmitting collection completion information to a terminal of the collection requester when the waste plastic to be collected is collected from the collection requester; Including, method. The method of claim 1, wherein the method
obtaining collection demand prediction information from a collection demand prediction model according to a preset period when the waste plastic collection request information is not obtained; and
generating the collection plan information based on the collection demand prediction information; Further comprising a method. The method of claim 3, wherein the obtaining of the waste plastic collection request information
The waste plastic collection request including at least one of collection requester identification information for identifying collection requesters requesting collection of waste plastics from an external device connected to the electronic device, waste plastic weight information subject to collection request, or collection request receipt date information. obtaining information; Including, method. The method of claim 3, wherein the obtaining of the collection plan information
If the type of collection requester identified above is not identified as an individual,
When the waste plastic collection request information is input, the waste plastic collection request information is input to a first artificial intelligence model that outputs collection plan information so that the output value of the first collection cost function is minimized. obtaining the collection plan information from; Including, method. The method of claim 5, wherein the collection plan information
Includes collection vehicle identification information and collection schedule information for each collection vehicle classified according to the collection vehicle identification information;
The collection schedule information for each vehicle includes collection requester identification information for identifying collection requesters assigned to each collection vehicle, first collection priority information indicating a collection priority among collection requesters assigned to each collection vehicle, and the collection requester. The method characterized by including information on the weight of waste plastics subject to the collection request requested by the collection requester according to the identification information and information on the date of receipt of the collection request by the collection requester. The method of claim 6, wherein the obtaining of the collection route information
When the collection plan information is input, the collection plan information output from the first artificial intelligence model is input to a second artificial intelligence model that outputs collection route information for each collection vehicle so that the output value of the second collection cost function is minimized. obtaining collection route information for each collection vehicle from the second artificial intelligence model; Including, method. The method of claim 7, wherein the collection route information for each vehicle is
Collection requester identification information for identifying the collection requester assigned to each collection vehicle, location information of collection requesters classified according to the collection requester identification information, and collection priority among collection requesters assigned to each collection vehicle and collection priority information, location information of a collection point allocated for each collection vehicle, origin location information for each collection vehicle for the waste plastic collection, and destination location information for each collection vehicle. delete The method of claim 1, wherein the method
generating point information for each collection requester based on recycled plastic inventory information generated for each collection requester; and
transmitting the generated point information to an external device connected to the electronic device; Including, method. 11. The method of claim 10, wherein the point information
Characterized in that it is packed in an Ethereum-based NFT (Not Fungible Token) and stored in each of the electronic device connected to a blockchain network and an external device connected to the electronic device. The method of claim 5, wherein the first artificial intelligence model
Total number of collection vehicles, total travel time of collection vehicles, total travel distance of collection vehicles, information on the weight of waste plastic subject to request for collection according to the collection request information, information on the type of waste plastic subject to request for collection according to the collection request information, status of movement to the location of the collection requester Learning to minimize an output value of a first collection cost function including an average time required for waste plastic collection and an average time required for waste plastic disinfection while moving to the location of a collection requester as input variables. . The method of claim 7, wherein the second artificial intelligence model
The current location of each collection vehicle, the total distance of combined routes generated by connecting location information of collection requesters assigned to each collection vehicle, the travel time required to move the combined routes from the current location of each collection vehicle, and the and learning to minimize an output value of a second collection cost function including a predetermined work capability weight of the collector as an input variable. 6. The method of claim 5, wherein the method
obtaining collection plan learning data for learning the first artificial intelligence model based on a user input to the electronic device prior to acquiring the waste plastic collection request information;
determining an available probability value for the collection plan learning data based on a correlation between the collection plan learning data;
pre-processing the collection plan learning data by converting some collection plan learning data among the collection plan learning data into an input format of the first artificial intelligence model, based on the determined available probability value; and
learning the first artificial intelligence model based on the preprocessed collection plan learning data; Including, method. 15. The method of claim 14, wherein the step of training the first artificial intelligence model
determining optimization candidate models including model information settable as model information of the first artificial intelligence model by applying a mixed-integer programming algorithm to the preprocessed learning data;
In order to reduce the high computational complexity of solutions output from the determined optimization candidate models, output values of the first collection cost function for solutions output from the optimization candidate models are minimized based on a heuristic algorithm. identifying a solution to be; and
learning the first artificial intelligence model by setting model information of an optimization candidate model outputting the identified solution as model information of the first artificial intelligence model; Including, method. 16. The method of claim 15, wherein identifying the solution comprises
identifying a solution that minimizes an output value of a collection cost function for solutions output from the optimization candidate models by applying a genetic algorithm to solutions output from the optimization candidate models; Including, method. 8. The method of claim 7, wherein the method
obtaining collection schedule learning data for training the second artificial intelligence model prior to acquiring the waste plastic collection request information;
identifying a missing value included in the generated collection schedule learning data;
calculating a normal distribution of the identified collection schedule learning data;
removing collection schedule learning data corresponding to a partial section formed in both directions from the center of the normal distribution map by applying a 3 sigma rule to the calculated normal distribution map; and
learning the second artificial intelligence model to minimize the second collection cost function based on collection schedule learning data from which the collection schedule learning data has been removed; Further comprising a method. 11. The method of claim 10, wherein the inventory information
Identification information of the collection requesters, information on the date of receipt of the collection request, information on the type of waste plastic requested by the collection requesters, information on the weight of waste plastic requested by the collection requesters, recycling produced from the requested waste plastic stored in the electronic device by matching flake type information, weight information of the reclaimed flakes, and purity information of the reclaimed flakes with each other;
The method of claim 1 , wherein the inventory information further includes sales price information of the recycled flakes and point information corresponding to the sales price of the recycled flakes when the recycled flakes are sold. In an electronic device providing a waste plastic collection service,
network interface;
a memory that stores one or more instructions; and
a plurality of processors executing the one or more instructions; including,
By executing the one or more instructions, the plurality of processors:
Acquiring waste plastic collection request information from an external device connected to the electronic device;
Identifying the type of collection requester who has transmitted the waste plastic collection request information;
Obtaining collection plan information based on the identified type of collection requester;
Obtaining collection route information for each collection vehicle based on the obtained collection plan information;
Transmitting the collection route information to a terminal for each collection vehicle connected to the electronic device;
at least one of the processors
The identification result of whether the waste plastic obtained from the collection requester from the external device connected to the electronic device is a target for disposal or circulation, and if the obtained plastic waste is a target for circulation, whether it can be used immediately or needs repair. Obtaining a primary classification result including an identification result on whether
From the external device connected to the electronic device, among the obtained waste plastics, waste plastics identified as waste plastics are pretreated, and mixed flakes are extracted by crushing the pretreated plastics, and the extracted mixed flakes are placed in an AI-based spectroscopy machine. Obtaining a secondary classification result for at least one of type information, weight information, or purity information of the reproduced flakes separately extracted from the artificial intelligence-based spectroscopic sorter by inserting,
The electronic device generates recycled plastic inventory information for each collection requester based on the first classification result and the second classification result. A recording medium in which an electronic device provides a waste plastic collection service, comprising: acquiring waste plastic collection request information from an external device connected to the electronic device;
identifying the type of collection requester who has transmitted the waste plastic collection request information;
obtaining collection plan information based on the identified type of collection requester;
acquiring collection route information for each collection vehicle based on the acquired collection plan information;
transmitting the collection route information to a terminal for each collection vehicle connected to the electronic device;
The identification result of whether the waste plastic obtained from the collection requester from the external device connected to the electronic device is a target for disposal or circulation, and if the obtained plastic waste is a target for circulation, whether it can be used immediately or needs repair. Obtaining a primary classification result including an identification result regarding whether or not;
From the external device connected to the electronic device, among the obtained waste plastics, waste plastics identified as waste plastics are pretreated, and mixed flakes are extracted by crushing the pretreated plastics, and the extracted mixed flakes are placed in an AI-based spectroscopy machine. obtaining a secondary classification result for at least one of type information, weight information, or purity information of the reproduced flakes classified and extracted from the artificial intelligence-based spectroscopic sorter by inserting; and
A computer-readable recording medium storing a program for performing the method, comprising generating recycled plastic inventory information for each collection requester based on the first classification result and the second classification result.

Images