Sorting processing support system, sorting processing support method, program, and storage medium

Abstract

A sorting processing support system comprises: an interface capable of receiving a question sentence from a user; a server that generates an answer sentence to the question sentence by using generative AI and displays the answer sentence on the interface; and a user-specific information storage unit in which user-specific information including at least one from among sorting premise information that serves as the premise for sorting processing using a sorting device and device operation information collected during operation of the sorting device. If it has been determined that content related to the question sentence is included in the user-specific information, the server generates the answer sentence with reference to the user-specific information.

Description

Sorting process support system, sorting process support method, program, and storage medium

[0001] The present disclosure relates to a sorting process support system, a sorting process support method, a program, and a storage medium. This application claims priority based on Japanese Patent Application No. 2025-026640 filed in Japan on February 21, 2025, and incorporates its content herein by reference.

[0002] Patent Document 1 discloses a sorting device that sorts a mixture containing multiple types of plastics by type of plastic.

[0003] International Publication No. 2024 / 176323

[0004] In such a sorting device, in order to accurately sort plastics, it is necessary to appropriately set sorting conditions and the like. However, it may be difficult for users to appropriately operate the sorting device.

[0005] The present disclosure has been made in consideration of such circumstances, and an object thereof is to provide a sorting process support system, a sorting process support method, a program, and a storage medium that can assist a user in operating a sorting device.

[0006] To solve the above problems, an aspect 1 of the present disclosure is a sorting process support system for assisting the operation of a sorting device that sorts a mixture containing multiple types of plastics by type of plastic, including an interface capable of receiving a question sentence from a user, a server that uses a generation AI to generate an answer sentence for the question sentence and displays the answer sentence on the interface, and a user-specific information storage unit that stores user-specific information including at least any one of sorting prerequisite information that is a prerequisite for the sorting process by the sorting device and device operation information collected during the operation of the sorting device; the server generates the answer sentence by referring to the user-specific information when it is determined that the content related to the question sentence is included in the user-specific information.

[0007] Aspect 2 of the present disclosure is a sorting process support method that supports the operation of a sorting apparatus for sorting a mixture containing multiple types of plastics according to the type of plastic, comprising the steps of: receiving a question from a user; and, if it is determined that the content related to the question is included in user-specific information, referring to the user-specific information and generating an answer using a generation AI.

[0008] Aspect 3 of the present disclosure is a program that supports the operation of a sorting apparatus for sorting a mixture containing multiple types of plastics according to the type of plastic, and causes a computer to perform the steps of receiving a question from a user, and if it is determined that the content related to the question is included in user-specific information, referring to the user-specific information and generating an answer using a generation AI.

[0009] Aspect 4 of the present disclosure is a storage medium storing a program that supports the operation of a sorting apparatus for sorting a mixture containing multiple types of plastics according to the type of plastic, wherein the program causes a computer to perform the steps of receiving a question from a user, and, if it is determined that the content related to the question is included in user-specific information, to refer to the user-specific information and generate an answer using a generating AI.

[0010] According to the above aspects of this disclosure, a sorting process support system, a sorting process support method, a program, and a storage medium can be provided that can assist a user in operating a sorting device.

[0011] This figure shows an example configuration of a sorting support system according to an embodiment. This block diagram shows an example of the functional configuration of a sorting device according to an embodiment. This figure illustrates the support functions provided by the support unit according to an embodiment. This is a flowchart of the processing in the support unit according to an embodiment. This is an example of an interface screen display showing a response generated by referencing user-specific information. This is an example of an interface screen display showing a response generated without referencing user-specific information.

[0012] Embodiments of this disclosure will be described below with reference to the drawings. The scope of this disclosure is not limited to the embodiments described below, and can be arbitrarily modified within the scope of the technical concept of this disclosure. Figure 1 is a diagram illustrating an example of the configuration of the sorting support system 1. The sorting support system 1 comprises a sorting device 100 and a support unit 4.

[0013] The sorting device 100 is configured to sort a mixture containing multiple types of objects according to the type of object. In this embodiment, a group of plastic pieces P is used as an example of a "mixture containing multiple types of objects". In the example in Figure 1, the group of plastic pieces P contains two types of plastic pieces p1 and p2 made of different materials. In this specification, the materials of the plastic pieces p1 and p2 may not be distinguished and they may be referred to as "granules". Three or more types of plastic pieces may be included in the group of plastic pieces P.

[0014] In the following explanation, we will use the example where plastic piece p1 is ABS (Acrylonitrile-butadiene-styrene) and plastic piece p2 is PS (Polystyrene). Plastic pieces p1 and p2 are obtained, for example, by crushing and drying the casing of an electrical appliance using a crusher. Plastic pieces p1 and p2 are formed to a size of, for example, about 10 mm square.

[0015] The sorting device 100 can electrostatically separate a group of plastic pieces P, which consists of multiple types of plastic pieces p1 and p2 with different electrostatic properties, into plastic pieces p1 and plastic pieces p2. In the example shown in Figure 1, the sorting device 100 includes an input unit 121, a charging cylinder 122, a vibrating feeder 123, a first electrode 124, a second electrode 125, a DC power supply 126, a collection box 127, and partition plates 128 and 129. The sorting device 100 also includes a raw material detection unit 11, a calculation unit 12, a control unit 13, a recovered material detection unit 14, etc. However, the configuration of the sorting device 100 in Figure 1 is merely an example and can be changed.

[0016] The input section 121 includes a hopper 121a and an input feeder 121b. Dried plastic pieces P are supplied to the hopper 121a. The hopper 121a supplies a predetermined amount of plastic pieces P per unit time to the input feeder 121b. The input feeder 121b supplies the plastic pieces P fed from the hopper 121a into the electrostatic cylinder 122.

[0017] The charging cylinder 122 and the vibrating feeder 123 constitute the charging unit 2. The charging unit 2 charges each of the plastic pieces p1 and p2 and then drops them. Specifically, the charging cylinder 122 agitates the group of plastic pieces P by rotating. Inside the charging cylinder 122, multiple types of plastic pieces p1 and p2 mixed in the group of plastic pieces P become charged by friction with each other. Each of the charged plastic pieces p1 and p2 has a charge amount of polarity (positive or negative) according to the triboelectric series. In this example, the plastic piece p1, which is ABS, becomes positively charged, and the plastic piece p2, which is PS, becomes negatively charged.

[0018] The charged plastic pieces p1 and p2 are supplied to the rear end of the upper surface of the vibrating feeder 123. The positively charged plastic piece p1 and the negatively charged plastic piece p2 may attract each other due to electrostatic force and pair up. The vibrating feeder 123 pushes the plastic pieces p1 and p2 forward while vibrating them up and down. This disengages the pairing of the plastic pieces p1 and p2, and the plastic pieces p1 and p2 move in the X direction in the figure. The plastic pieces p1 and p2 also fall from the vibrating feeder 123.

[0019] Electrodes 124, 125 and a DC power supply 126 constitute the electric field generating unit 3. The electric field generating unit 3 applies an electrostatic field to each charged plastic piece p1, p2. As a result, each plastic piece p1, p2 falls to a position corresponding to its respective charge state. Specifically, electrodes 124 and 125 are formed in a flat plate shape. Electrodes 124 and 125 are arranged in the X direction in the figure. Electrodes 124 and 125 are positioned facing each other, straddling the path through which the plastic pieces p1 and p2 fall. A ground voltage GND is applied to the first electrode 124. The DC power supply 126 applies a predetermined DC voltage between the first electrode 124 and the second electrode 125, generating an electrostatic field between the first electrode 124 and the second electrode 125.

[0020] When the plastic pieces p1 and p2, whose pairing has been broken by the vibrating feeder 123, are dropped between electrodes 124 and 125, each plastic piece falls while being attracted to either electrode 124 or electrode 125 by an electrostatic force corresponding to its charge state (polarity, amount of charge). In other words, each plastic piece p1 and p2 traces a parabolic trajectory corresponding to its charge state and falls to a different position. In this example, since plastic piece p1 is positively charged, it falls towards the first electrode 124. On the other hand, since plastic piece p2 is negatively charged, it falls towards the second electrode 125.

[0021] The collection box 127 is located below the electrodes 124 and 125 and collects the plastic pieces p1 and p2 that have fallen from the vibrating feeder 123 through the space between the electrodes 124 and 125. The top of the collection box 127 is open. The opening of the collection box 127 is formed, for example, in a rectangular shape, with its long side facing the X direction in the figure.

[0022] Each of the partition plates 128 and 129 is also referred to as a partition member. The partition plates 128 and 129 are arranged parallel to the YZ plane in the figure within the collection box 127 and are movable in the X direction in the figure. The position of each of the partition plates 128 and 129 in the X direction is controlled by the control unit 13. Partition plate 128 is located on the first electrode 124 side, and partition plate 129 is located on the second electrode 125 side. The collection box 127 is divided by the partition plates 128 and 129 into a collection chamber 127a on the first electrode 124 side, a collection chamber 127b on the second electrode 125 side, and an intermediate collection chamber 127c.

[0023] Each plastic piece p1, p2 that falls from the vibrating feeder 123 through the electrodes 124, 125 is collected in one of the three collection chambers 127a to 127c according to its charge state. In this example, plastic piece p1 is positively charged and is collected in collection chamber 127a. On the other hand, plastic piece p2 is negatively charged and is collected in collection chamber 127b. Plastic pieces p1 and p2 that are not sufficiently charged are collected in collection chamber 127c. The collected material in collection chamber 127c may, for example, pass through a circulation path (not shown) and be fed back into the input section 121.

[0024] The raw material detection unit 11 acquires raw material information. "Raw material information" refers to information about the raw materials fed into the input unit 121, i.e., the mixture before sorting. The recovered material detection unit 14 detects recovered material information. "Recovered material information" refers to information about the granular material recovered in the recovery box 127, i.e., the mixture after sorting. The raw material information and recovered material information are used to set the sorting conditions. The setting of sorting conditions will be explained below using Figure 2. Figure 2 is a block diagram showing an example of the functional configuration of the sorting device 100. The sorting device 100 includes, for example, a data processing unit 261, an input amount conversion unit 262, a data processing unit 263, and image processing units 264, 265, 266, and 267.

[0025] The raw material detection unit 11 includes, for example, a granular sensor, a charge sensor, a near-infrared camera, and a visible light camera. The raw material detection unit 11 may include only some of these components. The granular sensor is a sensor capable of detecting the number of granular particles passing through. The information regarding the number of granular particles detected by the granular sensor is output to the input amount conversion unit 262 as granular particle passage information. Based on the granular particle passage information, the input amount conversion unit 262 generates input amount data indicating the amount of mixture to be input and transmits the input amount data to the calculation unit 12.

[0026] The charge sensor is a sensor capable of detecting the charge amount of granular material. The charge amount information detected by the charge sensor is output to the data processing unit 263 as charge amount information. Based on the charge amount information, the data processing unit 263 generates charge amount data indicating the charge amount of the mixture and transmits the charge amount data to the calculation unit 12. The near-infrared camera outputs the captured near-infrared image to the image processing unit 264. Based on the near-infrared image, the image processing unit 264 generates composition ratio data of the mixture and transmits the composition ratio data to the calculation unit 12. The visible light camera outputs the captured visible image to the image processing unit 265. Based on the visible image, the image processing unit 265 generates particle size and foreign matter data indicating the particle size and foreign matter contained in the mixture and transmits the particle size and foreign matter data to the calculation unit 12.

[0027] The control unit 13 outputs operating condition information, such as partition plate position information, voltage information, MID circulation information, charging cylinder information, and feeder speed information, to the data processing unit 261. Partition plate position information indicates the positions of partition plates 128 and 129. Voltage information indicates the voltage between electrodes 124 and 125. MID circulation information indicates the amount of plastic pieces circulated from the collection chamber 127c to the input unit 121. Charging cylinder information indicates the rotation speed of the charging cylinder 122. Feeder speed information indicates the vibration speed of the vibrating feeder 123. The data processing unit 261 performs predetermined data processing to generate operating condition data. The operating condition data is, for example, data in which partition plate position information, voltage information, MID circulation information, charging cylinder information, and feeder speed information are linked for each time period. The data processing unit 261 transmits the generated operating condition data to the calculation unit 12.

[0028] The recovered material detection unit 14 includes, for example, a visible light camera, an optical sensor, and a near-infrared camera. The recovered material detection unit 14 outputs a visible image detected by the visible light camera or optical sensor of the plastic pieces collected in the collection box 127 to the image processing unit 266. The image processing unit 266 generates recovery rate data for each plastic piece p1, p2 based on the visible image and transmits the recovery rate data to the calculation unit 12. The recovered material detection unit 14 also outputs a near-infrared image detected by the near-infrared camera of the plastic pieces (recovered materials) collected in the collection box 127 to the image processing unit 267. The image processing unit 267 generates purity data of the recovered materials based on the near-infrared image and transmits the purity data to the calculation unit 12.

[0029] The calculation unit 12 may create and update a trained model using raw material information, operating condition data, and recovery results. Raw material information may include, for example, input amount data, charge amount data, composition ratio data, and particle size / foreign matter data. Recovery results may include, for example, recovery rate data and purity data.

[0030] The calculation unit 12 uses a trained model to calculate set values ​​for sorting conditions based on raw material information, etc. The calculation unit 12 outputs the set values, which are the result of the calculation, to the control unit 13. The control unit 13 controls the sorting conditions of the sorting device 100 based on the set values ​​input from the calculation unit 12. For example, the control unit 13 may control the positions of the partition plates 128 and 129 in the X direction. Alternatively, the control unit 13 may control the rotation speed or tilt of the charged cylinder 122, the voltage applied by the DC power supply 126 to the second electrode 125, etc. In other words, the "set values" are the positions of the partition plates 128 and 129 in the X direction, the rotation speed or tilt of the charged cylinder 122, the voltage of the DC power supply 126, etc. The "set values" may include multiple of these parameters. The calculation unit 12 may perform feedback control based on the recovery rate data, etc., detected by the recovered material detection unit 14 and calculate the set values.

[0031] However, control based solely on calculations by the calculation unit 12 may not yield desirable sorting results. Specific examples include cases where the user operates the sorting device 100 improperly, or where the state of the plastic piece group P fed into the input unit 121 is undesirable. Therefore, the sorting processing support system 1 of this embodiment includes a support unit 4 to assist the user in operating the sorting device 100. The support unit 4 will be described below.

[0032] As shown in Figure 1, the support unit 4 includes an interface 15, a server 16, and a memory 17. The support unit 4 is connected to the sorting device 100 by wire or wireless connection and can communicate with each other. In Figure 1, the support unit 4 is connected to the control unit 13, but the support unit 4 may also be connected to other components of the sorting device 100. The components included in the support unit 4 are also connected to each other by wire or wireless connection and can communicate with each other.

[0033] Interface 15 is capable of receiving user-submitted questions. Interface 15 may be integrated with, for example, the arithmetic unit 12 or the control unit 13. Interface 15 may be a PC (personal computer), smartphone, tablet terminal, etc. Interface 15 has a display unit visible to the user and an operation unit used for user operation. The display unit and the operation unit may be integrated, such as a touch panel. Alternatively, the operation unit may be a keyboard or mouse, and the operation unit and the display unit may be separate.

[0034] Server 16 generates an answer sentence using a generative AI in response to a question sentence entered by the user via interface 15. Server 16 also displays the generated answer sentence on interface 15. The generative AI used by server 16 may, for example, have pre-learned the relationship between question sentences and answer sentences based on training data. In this case, by using training data related to the sorting process of plastic pieces, it is possible to generate more accurate answer sentences to the user's questions about the sorting process. The generative AI used by server 16 may also be a so-called language model. Examples of language models include large-scale language models such as GPT-4 (registered trademark), Llama2, and PaLM2.

[0035] The memory 17 includes a user-specific information storage unit 17a and a determination information storage unit 17b. The memory 17 may be composed of multiple hardware components. Examples of hardware components of the memory 17 include RAM (Random Access Memory), HDD (hard disk drive), and flash memory. The user-specific information storage unit 17a and the determination information storage unit 17b may be composed of different hardware components. User-specific information is stored in the user-specific information storage unit 17a. User-specific information includes, for example, sorting prerequisite information and device operation information.

[0036] <Prerequisite Information for Sorting> Prerequisite information for sorting is information that serves as a prerequisite for sorting in the sorting device 100. Prerequisite information for sorting is pre-entered by the user and stored in the user-specific information storage unit 17a. The interface for the user to input prerequisite information for sorting may be the same as the interface 15 for inputting the question text, or it may be different. Prerequisite information for sorting may be pre-entered by the user when the sorting device 100 is installed. Prerequisite information for sorting may be entered by the user at the same time as the input of the question text, or immediately before or after the input of the question text.

[0037] For example, the sorting prerequisite information may include the origin product of the input raw material, crushing size, pre- and post-processing information, and installation environment information. The origin product is the product from which the input raw material was derived, such as an automobile or home appliance. Crushing size is an indicator of the size of the granules, such as the average particle size. As an example, the average particle size is about 10 mm.

[0038] Pre- and post-processing information refers to information about processes before or after sorting by the sorting device 100. For example, preliminary sorting may be performed before sorting by the sorting device 100. The method of preliminary sorting can be selected as appropriate, but for example, electrostatic sorting or specific gravity sorting may be used. Specific gravity sorting is a sorting method that utilizes the fact that different types of plastic pieces have different specific gravities. Furthermore, optical sorting may be performed after sorting by the sorting device 100. Optical sorting is a sorting method that utilizes the fact that different types of plastic pieces have different light reflectivity. In optical sorting, detection light is shone onto a group of plastic pieces, and the reflected light is detected. Various wavelengths of light, such as infrared or X-rays, can be used as the detection light. By detecting the spectrum of reflected light or Raman scattered light, plastic pieces can be distinguished by type. After such distinction, the plastic pieces may be sorted by air blowing or the like.

[0039] Installation environment information refers to information about the environment in which the sorting device 100 is installed. For example, the installation environment information may include whether the sorting device 100 is installed outdoors or indoors. Information about the country, region, or coordinates where the sorting device 100 is installed may also be included in the installation environment information. In some cases, predictions regarding temperature or humidity may be possible based on the installation environment information. By using the installation environment information, the support unit 4 may be able to generate a more appropriate response. Similarly, by using sorting prerequisite information other than the installation environment information, the support unit 4 may be able to generate a more appropriate response.

[0040] <Equipment Operation Information> Equipment operation information refers to information relating to the operation of the sorting device 100. For example, the equipment operation information may include fluid passage information, charge amount information, partition plate position information, voltage information, MID circulation information, charging cylinder information, feeder speed information, etc., as shown in Figure 2. Alternatively, the equipment operation information may include input amount data, charge amount data, composition ratio data, particle size / impurity data, operating condition data, recovery rate data, purity data, etc., as shown in Figure 2. The equipment operation information is collected automatically or manually while the sorting device 100 is operating and stored in the memory 17.

[0041] <Decision Information> The decision information storage unit 17b stores decision information used for decisions made by the server 16. Here, "decision" refers to a determination of whether or not the content related to the question entered by the user is included in the user-specific information. If the server 16 determines that the content related to the question is included in the user-specific information, it refers to the user-specific information storage unit 17a in order to generate an answer to the question. If the sorting device 100 uses an electrostatic sorting method, the decision information is, for example, specific words such as "composition ratio," "temperature," "humidity," "recovery rate," "purity," "specific charge," and "charge amount." The general outline of the processing in the server 16 will be explained below using Figure 3.

[0042] As shown in Figure 3, when a user inputs a question via the interface 15, the information in the question is converted into a format that the server 16 can process. This information conversion may be performed by the server 16 or by a PC or other device acting as the interface 15. Based on the question, the server 16 determines whether or not to refer to the user-specific information storage unit 17a for generating an answer. This determination is made by referring to the determination information storage unit 17b.

[0043] For example, server 16 determines to refer to user-specific information storage unit 17a if the above word, which is used as judgment information, is included in the question. Also, server 16 determines not to refer to user-specific information storage unit 17a if the above word, which is used as judgment information, is not included in the question.

[0044] Figure 4 is a flowchart for explaining the flow of the process executed by the support unit 4. As shown in Figure 4, in step S1, a question sentence is received. Specifically, the question sentence input by the user to the interface 15 is information-converted and analyzed by the server 16. In step S2, the server 16 accesses the determination information storage unit 17b. In step S3, the server 16 determines whether to refer to the user-specific information storage unit 17a for generating a response sentence. Specifically, the server 16 collates the question sentence and the determination information, and if a predetermined condition is satisfied, determines to refer to the user-specific information storage unit 17a (step S3: YES). In this case, the process proceeds to step S4.

[0045] In step S4, the server 16 generates a response sentence using the user-specific information and the language model. In step S3, the server 16 collates the question sentence and the determination information, and if a predetermined condition is not satisfied, determines not to refer to the user-specific information storage unit 17a (step S3: NO). In this case, the process proceeds to step S5. In step S5, the server 16 generates a response sentence using only the language model without using the user-specific information.

[0046] Figures 5 and 6 show an example of the screen display on the interface 15. As shown in Figures 5 and 6, the interface 15 may have a question sentence display section 15a and a response sentence display section 15b. The question sentence input by the user is displayed in the question sentence display section 15a. The response sentence generated by the generation AI is displayed in the response sentence display section 15b. In Figure 5, since the word "purity", which is an example of determination information, is included in the question sentence, the server 16 determines to use the user-specific information (step S3 in Figure 4: YES). As a result, the accuracy of the response is improved, and a more effective solution means considered to be suitable for the situation of the user is presented in the response sentence display section 15b.

[0047] Figure 6 shows an example of a response sentence generated without using user-specific information. Since it is a response sentence generated without using user-specific information, it shows general content common to all users. Note that when generating the response sentence in Figure 6, user-specific information is not referenced, so there is an advantage that the time required for the response generation process can be shortened compared to the case of referencing user-specific information.

[0048] Each function such as the above-described support unit 4, arithmetic unit 12, control unit 13, etc. is realized, for example, when a processor such as a CPU executes a program stored in a storage medium not shown, that is, software. Note that at least a part of each function may be realized by hardware including circuit units such as, for example, LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), and GPU (Graphics Processing Unit), or may be realized by cooperation between software and hardware. As a storage medium for storing the program, for example, RAM (Random Access Memory), ROM (Read Only Memory), HDD (hard disk drive), and flash memory can be adopted.

[0049] As described above, the sorting support system 1 according to this embodiment supports the operation of a sorting device 100 that sorts a mixture containing multiple types of plastics according to the type of plastic. The sorting support system 1 comprises an interface 15, a server 16, and a user-specific information storage unit 17a. The interface 15 is capable of receiving questions from the user. The server 16 generates answers to the questions using generation AI and displays the answers on the interface 15. The user-specific information storage unit 17a stores user-specific information that includes at least one of sorting prerequisite information that is the basis for the sorting process by the sorting device 100, and device operation information collected when the sorting device 100 is in operation. When the server 16 determines that content related to the question is included in the user-specific information, it generates an answer by referring to the user-specific information.

[0050] The sorting process support method according to this embodiment includes the steps of receiving a question and, if it is determined that the content related to the question is included in the user-specific information, referring to the user-specific information and generating an answer using a generation AI. The program according to this embodiment causes the computer to perform the steps of receiving a question and, if it is determined that the content related to the question is included in the user-specific information, referring to the user-specific information and generating an answer using a generation AI.

[0051] According to the above-described sorting support system 1, sorting support method, or program, if the generating AI generates a response by referring to user-specific information, it can provide the user with more accurate solutions, etc. Furthermore, if the generating AI generates a response without referring to user-specific information, it can provide the user with a general response in a short time. Therefore, it is possible to suitably support the user's operation of the sorting device 100.

[0052] Furthermore, the sorting prerequisite information may include any of the following: the origin product of the input raw materials, the crushing size, the processes before and after the sorting process by the sorting device 100, and the installation environment of the sorting device 100. In addition, the device operation information may include any of the following: the raw material composition ratio, the recovery rate, the purity, and the sorting conditions. In these cases, it becomes possible to generate more appropriate responses tailored to the specific circumstances of each user.

[0053] Furthermore, when the server 16 generates a response by referring to user-specific information, it may calculate statistical values ​​for the data included in the equipment operation information and generate the response based on these statistical values. Here, "data included in the equipment operation information" includes, for example, input amount data, charge amount data, composition ratio data, particle size / foreign matter data, operating condition data, etc. Statistical values ​​include, for example, standard deviation, mean, etc. By generating a response based on these statistical values, more specific support can be provided to the user. The statistical values ​​themselves may also be included in the response.

[0054] Furthermore, the generation AI used by server 16 may be a large-scale language model. In this case, it becomes possible to generate answers to both general questions and specialized questions regarding plastic sorting. Therefore, it is possible to provide users with a wider range of support.

[0055] The technical scope of this disclosure is not limited to the embodiments described above, and various modifications can be made without departing from the spirit of this disclosure.

[0056] For example, the sorting device 100 in the above embodiment employs an electrostatic sorting method. However, the sorting method in the sorting device 100 is not limited, and may be, for example, specific gravity sorting or optical sorting.

[0057] If the sorting method of the sorting device 100 is optical sorting or specific gravity sorting, words corresponding to the sorting method may be stored in the judgment information storage unit 17b. Examples of words corresponding to optical sorting or specific gravity sorting include "composition ratio," "temperature," "humidity," "recovery rate," and "purity."

[0058] Furthermore, it is possible to replace the components in the above-described embodiments with well-known components as appropriate, without departing from the spirit of this disclosure, and the above-described embodiments and modifications may be combined as appropriate.

[0059] 1... Sorting processing support system 2... Charging unit 3... Electric field generation unit 15... Interface 16... Server 17a... User-specific information storage unit 100... Sorting device

Claims

1. A sorting process support system that assists the operation of a sorting apparatus for sorting a mixture containing multiple types of plastics according to the type of plastic, comprising: an interface capable of receiving questions from a user; a server that generates answers to the questions using generation AI and displays the answers on the interface; and a user-specific information storage unit that stores user-specific information including at least one of sorting prerequisite information that is a prerequisite for sorting processing by the sorting apparatus, and apparatus operation information collected when the sorting apparatus is in operation, wherein the server generates the answer by referring to the user-specific information when it determines that the content related to the question is included in the user-specific information.

2. The sorting support system according to claim 1, wherein the sorting prerequisite information includes any of the following: the origin product of the input raw material, the crushing size, the processes before and after the sorting process by the sorting device, and the installation environment of the sorting device.

3. The sorting process support system according to claim 1 or 2, wherein the apparatus operation information includes any of the raw material composition ratio, recovery rate, purity, and sorting conditions.

4. The sorting processing support system according to any one of claims 1 to 3, wherein when the server generates the response text by referring to the user-specific information, it obtains statistical data from the device operation information and generates the response text based on the statistical data.

5. The sorting processing support system according to any one of claims 1 to 4, wherein the generating AI is a large-scale language model.

6. The sorting device comprises a charging unit for charging the mixture before sorting, and an electric field generating unit for applying an electrostatic field to the charged mixture, the sorting processing support system according to any one of claims 1 to 5.

7. A sorting process support method for assisting the operation of a sorting apparatus that sorts a mixture containing multiple types of plastics according to the type of plastic, comprising the steps of: receiving a question from a user; and, if it is determined that the content related to the question is included in user-specific information, referring to the user-specific information and generating an answer using a generation AI.

8. A program that assists the operation of a sorting apparatus for sorting a mixture containing multiple types of plastics according to the type of plastic, the program causing a computer to perform the steps of: receiving a question from a user; and, if it is determined that the content related to the question is included in user-specific information, referring to the user-specific information and generating an answer using a generation AI.

9. A storage medium storing a program that supports the operation of a sorting device for sorting a mixture containing multiple types of plastics according to the type of plastic, wherein the program causes a computer to perform the steps of: receiving a question from a user; and, if it is determined that the content related to the question is included in user-specific information, referring to the user-specific information and generating an answer using a generating AI.

Images