Information processing device, information processing program and information processing method

Abstract

To provide an information processing device capable of identifying types of waste in a waste pit.SOLUTION: An information processing device includes a type identification section that has an identification algorithm generated by learning teacher data in which types of waste are labelled with past image data obtained by imaging inside of a waste pit for storing waste and that identifies the type of the waste stored in the waste pit by inputting new image data obtained by imaging inside of the waste pit.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing program, and an information processing method for identifying the types of waste.

Background Art

[0002] Conventionally, in a waste treatment plant, various types of waste with different qualities, such as household waste, bulky crushed waste, pruning branches, and sludge, are put into a waste pit. These various types of waste are stored in the waste pit and then together fed into an incinerator for treatment in the incinerator. The quality of the waste fed into the incinerator is determined by the ratio of various types of waste contained in the waste, which affects combustion. In order to stabilize combustion, the waste in the waste pit is stirred by a crane to homogenize the quality of the waste.

[0003] However, if the waste fed into the incinerator contains a certain amount or more of waste such as bulky crushed waste or sludge, the temperature inside the incinerator may change rapidly, generating harmful gases and substances such as dioxins, which may have an adverse impact on the surrounding environment. In addition, there is also waste that is a cause of trouble for each device related to the waste treatment plant, not only affecting the combustion state. For example, if the waste fed into the incinerator contains a large amount of pruning branches, it may cause clogging in the hopper that supplies the waste into the incinerator.

[0004] On the other hand, waste such as general waste is basically put into the waste pit in a bag and stirred by a crane. However, when the degree of bag breakage is low, that is, when the breakage of the garbage bag is small and a large amount of waste remains in the garbage bag, it is empirically known that the state of the garbage bag also contributes to the stability of combustion, such as affecting the combustion state.

[0005] For example, Patent Document 1 discloses a method for operating an automatic crane using a control device for an automatic crane at a waste treatment plant, in which general waste and different types of waste are distinguished from each other by color tone when they are dumped into a waste pit, and the crane is controlled based on the distinguishing results, thereby standardizing the quality of the waste.

[0006] Furthermore, Patent Document 2 discloses a garbage agitation state detection device and method that detects the garbage agitation state, that is, the degree of tearing of the garbage bag, based on the brightness value of a captured image. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] JP 2007-126246 A [Patent Document 2] JP 2015-124955 A Summary of the Invention [Problem to be solved by the invention]

[0008] However, in the method of operating an automatic crane using the control device for an automatic crane for a waste treatment plant in Patent Document 1, general waste and heterogeneous waste are distinguished by color, but it is difficult to identify the type of waste simply by color, and for example, even if some coarse crushed waste is mixed in, it may be determined that the waste as a whole is general waste. Therefore, there is a risk that more than a certain amount of heterogeneous waste that affects the combustion state or waste that causes troubles in each equipment will be put into the incinerator.

[0009] In addition, the garbage agitation state detection device and garbage agitation state detection method of Patent Document 2 detect the degree of tearing of the garbage bag from the brightness value, but this method can only detect garbage bags. In an actual garbage pit, various types of waste such as pruning branches and futons may be thrown in addition to garbage bags, so it was difficult to apply the above method to such an actual garbage pit.

[0010] The present invention has been made in consideration of the above points, and an object of the present invention is to provide an information processing device, an information processing program, and an information processing method that can identify the type of waste in a garbage pit. [Means for solving the problem]

[0011] An information processing device according to a first aspect of the present invention includes: The system is provided with a type identification unit that uses an identification algorithm that has been trained on training data in which the type of waste is labeled to past image data obtained by capturing images of the inside of a garbage pit where waste is stored, and that uses new image data of the inside of the garbage pit as input to identify the type of waste stored in the garbage pit. An information processing device according to a first aspect of the present invention includes: The system may further include an identification algorithm generation unit that generates the identification algorithm by learning training data in which the type of waste is labeled from past image data captured inside a garbage pit where waste is stored.

[0012] According to this embodiment, the type of waste stored in the waste pit is identified using a trained identification algorithm generated by machine learning with image data obtained by capturing an image of the inside of the waste pit as input, making it possible to identify waste that will affect the combustion state if a certain amount or more is added, or waste that will cause trouble in each piece of equipment. This makes it possible to prevent the erroneous addition of a certain amount or more of such special waste, and to achieve stable processing without affecting the combustion state or each piece of equipment.

[0013] An information processing device according to a second aspect of the present invention is the information processing device according to the first aspect, The identification algorithm includes one or more of linear regression, Boltzmann machine, neural network, support vector machine, Bayesian network, sparse regression, decision tree, statistical estimation using random forest, reinforcement learning, and deep learning.

[0014] The information processing apparatus according to the third aspect of the present invention is the information processing apparatus according to the first or second aspect, The image data includes one or more of shape and color image data of waste imaged by an RGB camera, near-infrared image data of waste imaged by a near-infrared camera, and three-dimensional image data of waste imaged by a 3D camera or an RGB-D camera.

[0015] The information processing apparatus according to the fourth aspect of the present invention is the information processing apparatus according to any one of the first to third aspects, The types of the waste include one or more of unopened garbage bag waste, paper waste, pruning branches, futons, sludge, coarsely crushed waste, cardboard, gunny bags, paper bags, and bottom waste.

[0016] The information processing apparatus according to the fifth aspect of the present invention is the information processing apparatus according to any one of the first to fourth aspects, a plant control unit that controls a waste treatment plant based on the identification result of the type identification unit; and further includes.

[0017] The information processing apparatus according to the sixth aspect of the present invention is the information processing apparatus according to the fifth aspect, The plant control unit includes one or both of a crane control unit that transmits the identification result of the type identification unit to a crane control device that controls a crane that stirs or transports the waste, and a combustion control unit that transmits the identification result of the type identification unit to a combustion control device that controls the combustion of the waste.

[0018] The information processing apparatus according to the seventh aspect of the present invention is the information processing apparatus according to any one of the first to sixth aspects, the identification algorithm has learned training data in which the type of waste is labeled on image data obtained by capturing an image of the inside of the waste pit and objects to be identified other than the waste are labeled by type; The type identification unit uses the identification algorithm with new image data of the inside of the waste pit as input to identify the type of waste stored in the waste pit as well as the type of identification object other than waste.

[0019] The present inventors have actually verified that such an embodiment can significantly improve the accuracy of waste identification. This is believed to be because, according to the inventors' study, the type identification unit can suppress the type identification unit from being confused about an object to be identified other than waste and identifying it as some kind of waste, for example, being confused about the side wall of a garbage pit and identifying it as sludge.

[0020] An information processing device according to an eighth aspect of the present invention is the information processing device according to the seventh aspect, The types of identification objects other than waste include one or more of the following: beams of a waste treatment plant, side walls of a garbage pit, cliffs of piles of waste stored in a garbage pit, and cranes used to mix or transport the waste.

[0021] An information processing device according to a ninth aspect of the present invention is the information processing device according to the seventh aspect, The types of identification objects other than the waste include one or more of the following: beams of a waste treatment plant, side walls of a garbage pit, cliffs of piles of waste stored in a garbage pit, cranes that mix or transport the waste, walls, pillars, floors, windows, ceilings, doors, stairs, girders, walkways of a waste treatment plant, partition walls of a garbage pit, garbage hoppers, loading doors, workers, and loading vehicles.

[0022] An information processing device according to a tenth aspect of the present invention is an information processing device according to any one of the first to ninth aspects, a foreign object input detection unit that detects abnormal objects input into the garbage pit based on the identification result of the type identification unit; It further comprises:

[0023] An information processing device according to an eleventh aspect of the present invention is the information processing device according to the tenth aspect, The foreign object input detection unit transmits the identification result of the type identification unit to a foreign object detection device that detects abnormal objects input into a garbage pit in which the waste is stored.

[0024] An information processing device according to a twelfth aspect of the present invention is an information processing device according to any one of the first to eleventh aspects, a fall detection unit that detects a fall of a worker or a transport vehicle into the waste pit based on the identification result of the type identification unit; It further comprises:

[0025] An information processing device according to a thirteenth aspect of the present invention is the information processing device according to the twelfth aspect, The fall detection unit transmits the identification result of the type identification unit to a fall detection device that detects the presence of a worker or an input vehicle in a garbage pit where the waste is stored.

[0026] An information processing device according to a 14th aspect of the present invention is the information processing device according to any one of the first to 13th aspects, The types of waste include one or more of the following: unbroken garbage bags, paper waste, pruning branches, futons, sludge, bulky crushed garbage, cardboard, burlap bags, paper bags, bottom waste, wood chips, textile waste, clothing waste, plastic waste, animal residues, animal carcasses, kitchen waste, vegetation, soil, medical waste, incineration ash, bicycles, chests of drawers, beds, shelves, desks, chairs, agricultural vinyl products, plastic bottles, styrofoam, meat and bone meal, agricultural crops, pottery, scrap glass, scrap metal, rubble, scrap concrete, tatami mats, bamboo, straw, and activated carbon.

[0027] An information processing program according to a fifteenth aspect of the present invention comprises: Computer, The system functions as a type identification unit that uses a learning identification algorithm to identify the type of waste stored in a garbage pit by inputting new image data of the garbage pit and labeling the type of waste from past image data obtained by capturing images of the inside of the garbage pit where waste is stored. An information processing program according to a fifteenth aspect of the present invention comprises: The computer further comprises: The device may also function as an identification algorithm generation unit that generates the identification algorithm by learning training data in which the type of waste is labeled from past image data taken inside a garbage pit where waste is stored.

[0028] An information processing method according to a sixteenth aspect of the present invention comprises: The method includes a step of identifying the type of waste stored in a garbage pit by inputting new image data of the garbage pit using an identification algorithm that has been trained on training data in which the type of waste is labeled to past image data obtained by capturing images of the inside of the garbage pit where waste is stored. An information processing method according to a sixteenth aspect of the present invention comprises: The method may further include a step of generating the identification algorithm by learning training data in which the type of waste is labeled from past image data captured inside a garbage pit where waste is stored.

[0029] An information processing device according to a seventeenth aspect of the present invention comprises: The system is provided with a type identification unit that uses an identification algorithm that has been trained on training data in which the type of waste is labeled to past image data obtained by capturing images of the waste storage area where waste is stored, and that inputs new image data of the waste storage area to identify the type of waste stored in the waste storage area. An information processing device according to a seventeenth aspect of the present invention comprises: The system may further include an identification algorithm generation unit that generates the identification algorithm by learning training data in which the type of waste is labeled from past image data captured inside a waste storage area where waste is stored.

[0030] An information processing program according to an eighteenth aspect of the present invention comprises: Computer, Past images obtained by capturing images of the waste storage area where waste is stored The training data, in which the type of waste is labeled, is used to function as a type identification unit that uses a learned identification algorithm to input new image data of the waste storage area and identify the type of waste stored in the waste storage area. An information processing program according to an eighteenth aspect of the present invention comprises: The computer further comprises: The device may also function as an identification algorithm generation unit that generates the identification algorithm by learning training data in which the type of waste is labeled from past image data captured inside a waste storage area where waste is stored.

[0031] An information processing method according to a nineteenth aspect of the present invention comprises: The method includes a step of identifying the type of waste stored in a waste storage area by inputting new image data of the waste storage area using an identification algorithm that has been trained on training data in which the type of waste is labeled on past image data obtained by capturing images of the waste storage area where waste is stored. An information processing method according to a nineteenth aspect of the present invention comprises: The method may further include a step of generating the identification algorithm by learning training data in which the type of waste is labeled on past image data captured within a waste storage area where waste is stored. Effect of the Invention

[0032] According to the present invention, the type of waste in a garbage pit can be identified. [Brief description of the drawings]

[0033] [Figure 1] FIG. 1 is a schematic diagram showing the configuration of a waste treatment plant according to one embodiment. [Diagram 2] FIG. 2 is a block diagram showing a configuration of an information processing device according to an embodiment. [Diagram 3] FIG. 3 is a flowchart illustrating an example of an information processing method performed by the information processing device according to an embodiment. [Figure 4] FIG. 4 is a diagram showing an example of image data obtained by capturing an image of the inside of a garbage pit. [Diagram 5] FIG. 5 is a diagram showing an example of training data in which image data obtained by capturing an image inside a garbage pit is labeled with the types of waste and objects to be identified other than waste. [Figure 6] FIG. 6 is a diagram showing an example of data in which the classification result by the type classification unit is superimposed on image data obtained by capturing an image of the inside of a garbage pit. [Figure 7] Figure 7 is a map showing the ratio of waste types in each area within the garbage pit. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0034] Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings. In the following description and the drawings used in the following description, the same reference numerals are used for parts that can be configured identically, and duplicated descriptions will be omitted.

[0035] FIG. 1 is a schematic diagram showing the configuration of a waste treatment plant 100 according to one embodiment.

[0036] As shown in FIG. 1, the waste treatment plant 100 comprises a platform 21 on which a transport vehicle (garbage truck) 22 carrying waste is parked, a garbage pit 3 in which the waste input from the platform 21 is stored, a crane 5 for mixing and transporting the waste stored in the garbage pit 3, a hopper 4 into which the waste transported by the crane 5 is input, an incinerator 1 for incinerating the waste input from the hopper 4, and a heat exchanger for recovering exhaust heat from exhaust gas generated in the incinerator 1. The incinerator 1 is equipped with a waste heat boiler 2 for burning waste materials and a waste heat generator 3 for heating and discharging the waste materials. The type of incinerator 1 is not limited to a stoker furnace as shown in Fig. 1, but also includes a fluidized furnace (also called a fluidized bed furnace). The structure of the garbage pit 3 is not limited to a single-tier pit as shown in Fig. 1, but also includes a two-tier pit. The waste treatment plant 100 is also provided with a crane control device 50 for controlling the operation of the crane 5, and a combustion control device 20 for controlling the combustion of waste in the incinerator 1.

[0037] Waste carried in on a transport vehicle 22 is dumped from a platform 21 into a garbage pit 3, where it is stored. The waste stored in the garbage pit 3 is stirred by a crane 5, and is transported by the crane 5 to a hopper 4, through which it is dumped into the incinerator 1, where it is incinerated and disposed of.

[0038] As shown in FIG. 1, the waste treatment plant 100 is provided with an imaging device 6 that captures images of the inside of a waste pit 3, and an information processing device 10 that identifies the type of waste in the waste pit 3.

[0039] The imaging device 6 is disposed above the garbage pit 3 and, in the illustrated example, is fixed to the rails of the crane 5 so as to be able to capture images of the waste stored in the garbage pit 3 from above the garbage pit 3. Fig. 4 is a diagram showing an example of image data obtained by capturing an image of the inside of the garbage pit 3 with the imaging device 6.

[0040] The imaging device 6 may be an RGB camera that outputs shape and color image data of the waste as the imaging result, a near-infrared camera that outputs near-infrared image data of the waste as the imaging result, a 3D camera or RGB-D camera that captures three-dimensional image data of the waste as the imaging result, or a combination of two or more of these.

[0041] Next, there will be described the configuration of the information processing device 10 that identifies the type of waste in the garbage pit 3. FIG.

[0042] 2, the information processing device 10 includes a control unit 11, a storage unit 12, and a communication unit 13. Each unit is connected to each other via a bus so as to be able to communicate with each other.

[0043] Of these, the communication unit 13 is a communication interface between each of the imaging device 6, the crane control device 50, and the combustion control device 20 and the information processing device 10. The communication unit 13 transmits and receives information between each of the imaging device 6, the crane control device 50, and the combustion control device 20 and the information processing device 10.

[0044] The storage unit 12 is a fixed data storage such as a hard disk. The storage unit 12 stores various data handled by the control unit 11. The storage unit 12 also stores a classification algorithm 12a generated by a classification algorithm generating unit 11a (to be described later) and image data 12b acquired by an image data acquiring unit 11b (to be described later).

[0045] The control unit 11 is a control means for performing various processes of the information processing device 10. As shown in Fig. 2, the control unit 11 has an identification algorithm generating unit 11a, an image data acquiring unit 11b, a type identifying unit 11c, a plant control unit 11d, a fall detecting unit 11e, and a foreign object insertion detecting unit 11f. Each of these units may be realized by a processor in the information processing device 10 executing a predetermined program, or may be implemented by hardware.

[0046] The identification algorithm generating unit 11a captures an image of the inside of a garbage pit where waste is stored. By learning training data in which the type of waste is labeled from past image data obtained by the above process, a trained identification algorithm 12a is generated that can identify the type of waste by inputting new image data of the waste pit.

[0047] The identification algorithm generation unit 11a may generate a trained identification algorithm 12a that uses past image data within the garbage pit as input to identify the types of waste as well as the types of identification objects other than waste by learning training data in which past image data within the garbage pit is labeled with the type of waste and in which identification objects other than waste are labeled by type.

[0048] The identification algorithm 12a specifically includes, for example, one or more of linear regression, Boltzmann machines, neural networks, support vector machines, Bayesian networks, sparse regression, decision trees, statistical estimation using random forests, reinforcement learning, and deep learning.

[0049] The teacher data is created, for example, by an experienced operator who operates the waste treatment plant 100 visually identifying waste and identification objects other than waste and labeling them by type from image data obtained by capturing an image of the inside of the garbage pit 3. The types of waste and identification objects other than waste are labeled, for example, by type layer superimposed on the image data.

[0050] The types of waste to be labeled in the training data may include one or more of the following: unbroken garbage bags, paper waste, pruning branches, futons, sludge, bulky crushed garbage, cardboard, burlap bags, paper bags, and bottom waste (waste that is present near the bottom of the garbage pit 3 and is compressed by the waste above and has a high moisture content). The types of waste to be labeled in the training data may also include unplanned waste (abnormal objects) that are not desired to enter the garbage pit 3 but may enter. Here, abnormal objects include, for example, objects that should not be incinerated, specifically, for example, fluorescent lights, garbage containing mercury, explosives such as cylinders, cans, and oil tanks. In addition, the types of waste to be labeled in the training data may include one or more of the following: wood chips, textile waste, clothing waste, plastic waste, animal residues, animal carcasses, kitchen waste, vegetation, soil, medical waste, incineration ash, bicycles, chests of drawers, beds, shelves, desks, chairs, agricultural vinyl products, plastic bottles, styrofoam, meat and bone meal, agricultural crops, pottery, scrap glass, scrap metal, rubble, scrap concrete, tatami mats, bamboo, straw, and activated carbon.

[0051] The types of identification objects other than waste that are labeled in the teacher data may include one or more of the following: beams of the waste treatment plant 100, side walls of the garbage pit 3, cliffs of the piles of waste stored in the garbage pit 3 (parts of the cliffs of the piles of waste that are dark enough that the type of waste cannot be visually identified), and the crane 5 that mixes or transports the waste. The types of identification objects other than waste that are labeled in the teacher data may include one or both of workers and delivery vehicles. The types of identification objects other than waste that are labeled in the teacher data may include one or more of the following: walls, pillars, floors, windows, ceilings, doors, stairs, girders (structures that move by suspending the crane 5), walkways, partition walls of the garbage pit, garbage input hoppers, delivery doors, workers, and delivery vehicles of the waste treatment plant 100.

[0052] Fig. 5 is a diagram showing an example of training data in which image data obtained by capturing an image inside a garbage pit is labeled with the types of waste and identification objects other than waste. In the example shown in Fig. 5, image data obtained by capturing an image inside a garbage pit is labeled with the types of waste, such as unbroken bags, pruning branches, and futons, and is labeled with the types of identification objects other than waste, such as a crane 5, a cliff of a waste mountain, a side wall of a garbage pit 3, and a plant 1. Each of the 00 floors is labeled according to type.

[0053] The image data acquisition unit 11b acquires new image data from the imaging device 6, which is obtained by capturing an image of the inside of the garbage pit 3. The new image data acquired by the image data acquisition unit 11b is stored in the storage unit 12.

[0054] The type identification unit 11c uses new image data acquired by the image data acquisition unit 11b as input and identifies the type of waste stored in the garbage pit 3 using the learned identification algorithm 12a generated by the identification algorithm generation unit 11a.

[0055] The type identification unit 11c may use the learned identification algorithm 12a with the new image data acquired by the image data acquisition unit 11b as input to identify the type of waste stored in the garbage pit 3 as well as the type of identification object other than waste. Fig. 6 is a diagram showing an example of data in which the identification result by the type identification unit 11c is superimposed on image data obtained by capturing an image of the inside of the garbage pit. In the example shown in Fig. 6, the waste (unbroken bag waste, pruning branches) identified by the type identification unit 11c and the identification objects other than waste (the crane 5, the cliff of the waste mountain, the side wall of the garbage pit 3, and the floor of the plant 100) are superimposed on the image data and displayed by type.

[0056] As shown in Fig. 7, the type identification unit 11c may generate a map that displays the ratio of the type of waste stored in the garbage pit 3 for each area based on the identification result. In the example shown in Fig. 7, the garbage pit 3 is divided into a 5 x 4 grid, and the ratio of the type of waste identified by the type identification unit 11c is displayed for each area.

[0057] The plant control unit 11d controls the waste treatment plant 100 based on the identification result of the type identification unit 11c.

[0058] In the example shown in Figure 1, the plant control unit 11d includes a crane control unit 11d1 that transmits the identification result of the type identification unit 11c (i.e., information on the type of waste identified from image data) to a crane control device 50 that controls a crane 5 that mixes or transports the waste, and a combustion control unit 11d2 that transmits the identification result of the type identification unit 11c (i.e., information on the type of waste identified from image data) to a combustion control device 20 that controls the combustion of the waste.

[0059] In the example shown in FIG. 1, the plant control unit 11d includes both the crane control unit 11d1 and the combustion control unit 11d2, but this is not limited to this and may include only one of the crane control unit 11d1 and the combustion control unit 11d2.

[0060] For example, the crane control unit 11d1 transmits a map (see FIG. 7) showing the ratio of waste types stored in the waste pit 3 for each area as the identification result of the type identification unit 11c to the crane control device 50. Based on the map received from the crane control unit 11d1, the crane control device 50 operates the crane 5 to stir up the waste in the waste pit 3 so that the ratio of waste types is equal in all areas.

[0061] For example, the combustion control unit 11d2 transmits a map (see FIG. 7) showing the ratio of the types of waste stored in the garbage pit 3 for each area as the identification result of the type identification unit 11c to the combustion control device 20. Based on the map received from the combustion control unit 11d2, the combustion control device 20 grasps the ratio of the types of waste grabbed by the crane 5 and transported together from the garbage pit 3 to the hopper 4, and controls the combustion of the waste in accordance with the ratio of the waste that is thrown into the incinerator 1 together via the hopper 4 (for example, controls the stoker feed speed or the amount of air supplied).

[0062] The fall detection unit 11e detects a fall of a worker or a transport vehicle from the platform 21 into the garbage pit 3 based on the identification result of the type identification unit 11c (i.e., information on the worker or the transport vehicle identified from the image data). The fall detection unit 11e may transmit the identification result of the type identification unit 11c (i.e., information on the worker or the transport vehicle identified from the image data) to a fall detection device (not shown) that detects the presence of a worker or an input vehicle in the garbage pit 3 where waste is stored. The fall detection device (not shown) issues an alarm or operates the crane 5 to rescue the worker based on the identification result of the type identification unit 11c transmitted from the fall detection unit 11e.

[0063] The foreign object input detection unit 11f detects abnormal objects input into the garbage pit 3 based on the identification result of the type identification unit 11c (i.e., information on the type of waste identified from the image data). Here, the term "abnormal objects" refers to unplanned waste that is not desired to enter the garbage pit 3 but may enter, such as objects that should not be incinerated, specifically, fluorescent lamps, mercury-containing waste, explosives such as cylinders, cans, and oil tanks. The foreign object input detection unit 11f may transmit the identification result of the type identification unit (i.e., information on the type of waste identified from the image data) to a foreign object detection device (not shown) that detects abnormal objects input into the garbage pit 3 where waste is stored. The foreign object detection device (not shown) refers to a database that stores the company or vehicle that input the waste into the garbage pit 3 together with time information, and identifies the company or vehicle that input the foreign object into the garbage pit 3 based on the identification result of the type identification unit 11c transmitted from the foreign object input detection unit 11f.

[0064] Next, an example of an information processing method by the information processing device 10 configured as above will be described below. Fig. 3 is a flowchart showing an example of the information processing method.

[0065] As shown in FIG. 3, first, the identification algorithm generation unit 11a learns training data in which the type of waste is labeled on past image data capturing an image inside the garbage pit 3, and generates a learned identification algorithm 12a that identifies the type of waste using new image data obtained by capturing an image inside the garbage pit 3 as input (step S11).

[0066] The identification algorithm generation unit 11a may generate a trained identification algorithm 12a that uses new image data obtained by capturing an image inside the garbage pit 3 as input and identifies the types of identification objects other than waste in addition to the types of waste, by learning training data (e.g., see Figure 5) in which past image data obtained by capturing an image inside the garbage pit 3 is labeled with the type of waste and identification objects other than waste are labeled by type.

[0067] Next, the image data acquisition unit 11b acquires new image data 12b (see FIG. 4, for example) obtained by capturing an image of the inside of the garbage pit 3 from the imaging device 6 (step S12). The new image data 12b acquired by the image data acquisition unit 11b is stored in the storage unit 12.

[0068] Next, the type identification unit 11c uses the new image data acquired by the image data acquisition unit 11b as input and identifies the type of waste stored in the garbage pit 3 using the learned identification algorithm 12a generated by the identification algorithm generation unit 11a (step S13).

[0069] The type identification unit 11c receives new image data (for example, see FIG. 4) acquired by the image data acquisition unit 11b as an input, and uses the learned classification algorithm generated by the classification algorithm generation unit 11a. The waste identification algorithm 12a may be used to identify the types of waste stored in the waste pit 3 as well as the types of objects to be identified other than waste (see, for example, FIG. 6). Furthermore, the type identification unit 11c may generate a map (see, for example, FIG. 7) that displays the ratio of the types of waste stored in the waste pit 3 for each region based on the results of identifying the types of waste.

[0070] Next, the plant control unit 11d controls the waste treatment plant based on the identification result by the type identification unit 11c.

[0071] Specifically, for example, the crane control unit 11d1 transmits a map showing the ratio of waste types for each area as shown in Fig. 7 as the identification result of the type identification unit 11c to the crane control device 50 that controls the crane 5 that mixes or transports the waste (step S14). Based on the map received from the crane control unit 11d1, the crane control device 50 operates the crane 5 to mix the waste in the garbage pit 3 so that the ratio of waste types is equal in all areas.

[0072] The combustion control unit 11d2 also transmits a map showing the ratio of waste types for each region as shown in Fig. 7 as the identification result of the type identification unit 11c to the combustion control device 20 that controls the combustion of the waste (step S15). Based on the map received from the combustion control unit 11d2, the combustion control device 20 grasps the ratio of the types of waste that are picked up by the crane 5 and transported together from the garbage pit 3 to the hopper 4, and controls the combustion of the waste according to the ratio of each type of waste that is thrown together into the incinerator 1 via the hopper 4 (for example, by controlling the stoker feed speed or the amount of air supplied).

[0073] In addition, when the type identification unit 11c identifies a worker or a transport vehicle from image data inside the garbage pit 3, the fall detection unit 11e may detect a fall of the worker or transport vehicle from the platform 21 into the garbage pit 3 based on the identification result of the type identification unit 11c, and transmit the identification result of the type identification unit 11c to a fall detection device (not shown).

[0074] In addition, if the type identification unit 11c detects an abnormal object from image data inside the garbage pit 3, the foreign object insertion detection unit 11f may detect the abnormal object that has been inserted into the garbage pit 3 based on the identification result of the type identification unit 11c, and transmit the identification result of the type identification unit 11c to a foreign object detection device (not shown).

[0075] Incidentally, as mentioned in the section on the problem to be solved by the invention, the method described in Patent Document 1 distinguishes between general waste and heterogeneous waste by color tone, but it is difficult to identify the type of waste simply by color tone, and for example, even if some coarse crushed waste is mixed in, it may be determined that the waste as a whole is general waste. Therefore, there is a risk that more than a certain amount of heterogeneous waste that affects the combustion state or waste that causes troubles in each equipment will be put into the incinerator.

[0076] In addition, the method described in Patent Document 2 detects the degree of tearing of the garbage bag based on the brightness value, but this method can only detect garbage bags. In an actual garbage pit, various types of waste such as pruning branches and futons may be thrown in addition to garbage bags, so it was difficult to apply the above method to such an actual garbage pit.

[0077] In contrast, according to the present embodiment, the type of waste stored in the waste pit 3 is identified using image data obtained by capturing an image of the inside of the waste pit 3 as an input and a trained identification algorithm 12a generated by machine learning. This identifies waste that will affect the combustion state if more than a certain amount is added (for example, unbroken bags of waste) and waste that will affect the combustion state if more than a certain amount is added, and the type of waste that will affect the combustion state if more than a certain amount is added. It is possible to identify waste that may cause problems (such as pruning branches), which will prevent the erroneous input of more than a certain amount of such special waste, enabling stable processing without affecting the combustion state or each piece of equipment.

[0078] According to the present embodiment, the identification algorithm generating unit 11a generates a learned identification algorithm 12a by learning teacher data in which the types of waste are labeled on past image data obtained by capturing an image inside the garbage pit 3 and the objects to be identified other than waste are labeled by type, and the type identification unit 11c uses the identification algorithm 12a with new image data acquired by the image data acquiring unit 11b as input to identify the types of waste stored in the garbage pit 3 as well as the types of objects to be identified other than waste. When the present inventors actually verified this, it was confirmed that such an embodiment can significantly improve the accuracy of identifying waste. According to the study by the present inventors, this is thought to be because the type identification unit 11c can be prevented from being confused about objects to be identified other than waste and identifying them as some kind of waste, for example, being confused about the side wall of the garbage pit 3 and identifying them as sludge.

[0079] The above-described embodiment can be modified in various ways. Modifications of the above-described embodiment will be described below.

[0080] In the above embodiment, the combustion control unit 11d2 transmits to the combustion control device 20, as the identification result of the type identification unit 11c, a map (see FIG. 7) showing the ratio of the type of waste stored in the garbage pit 3 for each region. However, the present invention is not limited to this. As the identification result of the type identification unit 11c, a map showing labels converted from the ratio of the type of waste into quality information, for example, input OK, input NG, calorie L (Low), M (Middle), H (High), etc., for each region may be transmitted to the combustion control device 20. In addition, the combustion control unit 11d2 may transmit to the combustion control device 20, as the identification result of the type identification unit 11c, a label indicating a large proportion that affects the combustion state (for example, unbroken bag waste, bottom waste, etc.). Similarly, the crane control unit 11d1 may transmit to the crane control device 50, as the identification result of the type identification unit 11c, a label indicating a large proportion that affects each device (for example, pruning branches, large crushed waste, etc.).

[0081] When the type identification unit 11c generates a map based on the identification results to display the ratio of waste types stored in the garbage pit 3 by region, the image data acquired by the image data acquisition unit 11b may simply be divided into regions to display the ratio of waste types, or the image data may be linked to the address division of the garbage pit 3 to display the ratio of waste types by address.

[0082] As a method of linking image data with a crane address, a mark is attached in advance to a crane 5 whose position relative to the garbage pit 3 can be measured, and the imaging device 6 captures the marked crane 5 in multiple images, and the type identification unit 11c estimates the relative position and direction of the imaging device 6 with respect to the garbage pit 3 based on the multiple images in which the marked crane 5 is captured, and estimates which address the pixel in the image data is located at from the estimated position and shooting direction of the imaging device 6. Alternatively, the imaging device 6 captures the crane 5 whose position relative to the garbage pit 3 can be measured in multiple images, and the type identification unit 11c marks the crane 5 in the images, and estimates the relative position and direction of the imaging device 6 with respect to the garbage pit 3 based on the multiple images in which the crane 5 is marked, and estimates which address the pixel in the image data is located at from the estimated position and shooting direction of the imaging device 6.

[0083] A part of the processing of the control unit 11 is not performed by the information processing device 10 but by a client separate from the information processing device 10. A part of the storage unit 12 may be located not in the information processing device 10 but in a cloud server separate from the information processing device 10.

[0084] For example, the processing of the discrimination algorithm generating unit 11a may be executed on a cloud server to generate the discrimination algorithm 12a. Also, the processing of the type discrimination unit 11c may be executed on the cloud server using the discrimination algorithm 12a generated on the cloud server by the discrimination algorithm generating unit 11a, or the discrimination algorithm 12a may be downloaded by the information processing device 10 from the cloud server and used within the information processing device 10 to execute the processing of the type discrimination unit 11c.

[0085] The control unit 11 may periodically monitor the classification result of the type classification unit 11c and determine whether or not the model of the classification algorithm 12a needs to be reviewed and updated.

[0086] For example, the control unit 11 uses an edge server to determine whether the identification results of the type identification unit 11c are normal or abnormal, and if an abnormality is detected, it determines whether the image data and the identification results pose a problem in the operation of the incinerator 1. If it is determined that there is an operational problem, an experienced operator re-labels the image data for which the abnormality was detected by waste type, prepares new training data, and the identification algorithm generation unit 11a learns the newly prepared training data to generate the identification algorithm 12a.

[0087] When a dumping request comes from the incinerator 1, the crane control device 50 may select garbage from the garbage pit 3 that meets the dumping criteria based on the ratio threshold for each garbage type based on the map received from the crane control unit 11d1, and operate the crane 5 to dump the garbage into the hopper 4.

[0088] In addition, when sorting out garbage that meets the disposal criteria from within the garbage pit 3, the crane control device 50 may sort the garbage so that the difference between the ratio of each type of garbage disposed of previously in the hopper 4 is small.

[0089] The crane control device 50 may use one or more ratio thresholds for the above-mentioned input criteria as the ratio thresholds. These ratio thresholds may include unbroken garbage bags, paper waste, pruning branches, futons, sludge, crushed bulky garbage, cardboard, gunny bags, paper bags, bottom waste, wood chips, textile waste, clothing waste, plastic waste, animal residues, animal carcasses, kitchen waste, vegetation, soil, medical waste, incineration ash, agricultural vinyl products, PET bottles, styrofoam, meat and bone meal, agricultural crops, pottery, scrap glass, scrap metal, rubble, scrap concrete, tatami mats, bamboo, straw, and activated carbon.

[0090] In addition, as a method of determining the above-mentioned throwing criteria, the crane control device 50 may determine the ratio threshold value for each type of waste that an experienced operator uses to determine whether or not it can be thrown in by comparing image data obtained by taking past footage of the inside of the waste pit 3, which the experienced operator has visually inspected to classify and label the waste quality shown in the image data as to whether or not it can be thrown in from the standpoint of combustion stability and its impact on equipment, with an image obtained by estimating the ratio of each type of waste using the type identification unit 11c.

[0091] In addition, the crane control device 50 may determine a ratio threshold for each type of waste by linking ratio data for each type of waste actually dumped into the hopper 4 with the process data of the incinerator 1 from a map received from the crane control unit 11d1, which shows the ratio of each type of waste stored in the waste pit 3 by area, or may link the two sets of data over time to dynamically change the ratio threshold.

[0092] In addition, the crane control device 50 may dynamically change the ratio threshold value based on weather information as well as the above process data. For example, the crane control device 50 may dynamically change the ratio threshold value based on weather information. If it is raining, the input criteria based on the ratio threshold is changed, for example, by lowering the ratio threshold for unbroken garbage bags or by raising the ratio threshold for crushed bulky garbage.

[0093] The crane control device 50 may dynamically change the ratio threshold based on the day of the week information. For example, the crane control device 50 changes the input amount standard based on the ratio threshold, such as increasing the ratio threshold of unbroken garbage bags in order to reduce the amount of garbage incinerated on Sundays, when there is less garbage in the garbage pit 3 based on the day of the week information.

[0094] The crane control device 50 may dynamically change the ratio threshold value based on the operation plan value of the waste treatment plant 100. For example, if the amount of evaporation falls from the current evaporation amount setting value, the crane control device 50 changes the input criteria based on the ratio threshold value, such as lowering the ratio threshold value for unbroken garbage bags or raising the ratio threshold value for crushed bulky garbage.

[0095] When a dumping request comes from the incinerator 1, if there is no garbage that meets the dumping criteria based on the ratio threshold for each type of garbage in the map received from the crane control 11d1, the crane control device 50 may operate the crane 5 to dump garbage that is close to the dumping criteria into the hopper 4, or it may stir the garbage that is close to the dumping criteria and create garbage that meets the dumping criteria.

[0096] The crane control device 50 may operate the crane 5 to pile up only the waste that meets the throwing criteria based on the ratio threshold for each type of waste in the map received from the crane control 11d1 at a specific location in the waste pit 3. In this way, the waste that meets the throwing criteria can be accumulated in the waste pit 3.

[0097] The crane control device 50 uses the ratio thresholds for each type of waste in the map received from the crane control 11d1 to detect waste (e.g., sludge) that may affect the combustion conditions in the waste pit 3 and waste (e.g., pruning branches) that may cause problems in each piece of equipment, and may operate the crane 5 to store the waste in a specific location in the waste pit 3 or scatter it in specific places.

[0098] When garbage that does not meet the mixing standard based on the ratio threshold for each garbage type is present in the garbage pit 3 in the map received from the crane control 11d1, the crane control device 50 may operate the crane 5 to mix the garbage. The mixing standard may be the same as or different from the input standard.

[0099] In addition, the crane control device 50 may dynamically change the mixing criteria using one or more of the following: process data for the incinerator 1, weather information, day of the week information, information on the waste delivery company, information on the amount of waste brought in (total amount or amount brought in by type of waste), waste delivery speed, information on the waste pit level (overall, specific area), information on the crane operation status (two units capable of operation, one unit only in operation, one unit currently in operation, two units currently in operation), and information on the collection route and collection area of ​​the waste collection vehicle.

[0100] The crane control device 50 may determine the mixing condition of the entire garbage pit 3 from the ratio of different types of garbage in each area in the map received from the crane control 11d1, determine whether or not it is necessary to operate two cranes 5, operate the crane 5, and start the operation of the second crane or store the second crane.

[0101] In the above example, the crane control device 50 operates the crane 5, but a crane operation judgment device (not shown) may be provided upstream of the crane control device 50, and the crane operation judgment device may determine the operation details of the crane 5, transmit a command for the operation details to the crane control device 50, and the crane control device 50 may operate the crane 5 based on the received command content. The crane operation determination device transmits and receives information to and from the information processing device 10. Alternatively, the crane operation determination device may be a part of the information processing device 10, that is, the information processing device 10 may include the crane operation determination device.

[0102] The crane operation judgment device may receive an input request signal from the crane control device 50 when an input request comes from the incinerator 1, and based on the map received from the crane control unit 11d1, select from the garbage pit 3 garbage in the map that meets the input criteria based on the ratio threshold for each garbage type, and send a command to the crane control device 50 to input the garbage into the hopper 4, and the crane control device 50 may operate the crane 5 based on the received command. Furthermore, when selecting garbage that meets the input criteria from the garbage pit, the crane operation judgment device may select the garbage so that the difference between the garbage type ratio and the garbage previously input into the hopper 4 is small.

[0103] When an input request comes from the incinerator 1, the crane operation judgment device receives an input request signal from the crane control device 50, and if there is no waste that meets the input criteria based on the ratio threshold for each waste type in the map received from the crane control 11d1, the crane operation judgment device sends a command to the crane control device 50 to input waste that is close to the input criteria into the hopper 4, or to mix the waste that is close to the input criteria and create waste that meets the input criteria, and the crane control device 50 may operate the crane 5.

[0104] The crane operation determination device may send a command to the crane control device 50 to pile up only the waste that meets the throwing criteria based on the ratio threshold value of the waste type in the map received from the crane control 11d1 at a specific location in the waste pit 3, and the crane control device 50 may operate the crane 5. In this way, the waste that meets the throwing criteria can be accumulated in the waste pit 3.

[0105] The crane operation judgment device detects waste (e.g., sludge) that may affect the combustion conditions and waste (e.g., pruning branches) that may cause problems in each piece of equipment in the map received from the crane control 11d1 based on the ratio threshold for each type of waste, and sends a command to the crane control device 50 to store the waste in a specific location in the waste pit 3 or to scatter it in a specific place, and the crane control device 50 may operate the crane 5.

[0106] When garbage that does not meet the mixing criteria based on the ratio threshold for each garbage type is present in the garbage pit 3 in the map received from the crane control 11d1, the crane operation determination device may send a command to the crane control device 50 to mix the garbage, and the crane control device 50 may operate the crane 5. The mixing criteria may be the same as or different from the input criteria.

[0107] The crane operation judgment device judges the mixing condition of the entire garbage pit 3 from the ratio of different garbage types in each area in the map received from the crane control 11d1, judges whether or not it is necessary to operate two cranes 5, and sends a command to the crane control device 50, which then operates the crane 5 and may start operating the second crane or store the second crane.

[0108] In the above-described embodiment, an example has been described in which the information processing device 10 that identifies the type of waste is used in the garbage pit 3 of the waste treatment plant 100. However, the place of use of the information processing device 10 is not limited to the garbage pit 3 of the waste treatment plant 100 as long as it is a waste storage place where waste is stored. For example, the information processing device 10 may be used in the receiving area of ​​a recycling facility.

[0109] Although the embodiment and the modified examples of the present invention have been described above by way of example, the scope of the present invention is not limited to these. The present invention is not limited to the above, and may be modified or altered according to the purpose within the scope of the claims. Furthermore, the embodiments and modifications may be combined as appropriate within the scope of the claims without causing any contradiction in the processing contents.

[0110] In addition, the information processing device 10 in this embodiment may be configured by one or more computers, but the program for realizing the information processing device 10 in one or more computers and the recording medium on which the program is recorded are also covered by the present invention. [Explanation of symbols]

[0111] 1 Incinerator 2 Combustion equipment 3. Garbage Pit 4 Hopper 5. Crane 6. Imaging device 10. Information processing device 11 Control section 11a Identification algorithm generation unit 11b Image data acquisition unit 11c Type identification part 11d Plant Control Section 11e Fall detection unit 11f Foreign object input detection unit 12 Storage section 12a Identification Algorithm 12b Image data 13. Communications Department 14 Display section 20 Combustion control device 21 Platform 22 Transport vehicle 50 Crane control device 100 Waste Treatment Plant

Claims

1. a type identification unit that uses an identification algorithm that has been trained with teacher data in which types of waste are labeled on past image data obtained by capturing an image of the inside of a garbage pit in which waste is stored, and that uses new image data of the inside of the garbage pit as input to identify the type of waste stored in the garbage pit; The waste whose type is identified by the type identification unit includes a first waste that affects a combustion state of a waste treatment plant, A plant control unit that controls the waste treatment plant based on the identification result of the type identification unit, The plant control unit includes a combustion control unit that transmits the identification result of the type identification unit to a combustion control device that controls the combustion of the waste, The combustion control unit transmits, as the identification result of the type identification unit, one or more of a label in which the ratio of the types of waste is converted into quality information, and a label indicating that a ratio of a first waste that affects the combustion state is high, to the combustion control device.

23. An information processing apparatus comprising:

2. The label obtained by converting the ratio of the types of waste into quality information includes one or more of the following: OK to throw, NG to throw, calorie L (Low), calorie M (Middle), and calorie H (High); 2. The information processing apparatus according to claim 1,

3. The first waste that affects the combustion state of the waste treatment plant includes one or more of unbroken garbage bags, bottom garbage, pruning branches, and coarse crushed garbage; 3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

4. The classification algorithm includes one or more of linear regression, Boltzmann machines, neural networks, support vector machines, Bayesian networks, sparse regression, decision trees, statistical inference using random forests, reinforcement learning, and deep learning; 4. The information processing device according to claim 1, wherein:

5. The image data includes one or more of the following: shape and color image data of the waste captured by an RGB camera, near-infrared image data of the waste captured by a near-infrared camera, and three-dimensional image data of the waste captured by a 3D camera or an RGB-D camera; 5. The information processing device according to claim 1,

6. The types of waste include one or more of the following: unbroken garbage bags, paper waste, pruning branches, futons, sludge, bulky crushed garbage, cardboard, burlap bags, paper bags, and bottom garbage; 6. The information processing device according to claim 1,

7. the identification algorithm has learned training data in which the type of waste is labeled on past image data obtained by capturing an image of the inside of the waste pit, and objects to be identified other than the waste are labeled by type; the type identification unit uses the identification algorithm with new image data of the waste pit as an input to identify the type of waste stored in the waste pit as well as the type of identification object other than waste; 7. The information processing apparatus according to claim 1,

8. The types of identification objects other than waste include one or more of the following: beams of a waste treatment plant, side walls of a garbage pit, cliffs of piles of waste stored in a garbage pit, and cranes for mixing or transporting the waste; 8. The information processing apparatus according to claim 7,

9. The identification results of the type identification unit are periodically monitored to determine whether the model of the identification algorithm needs to be revised and / or updated.

9. The information processing device according to claim 1,

10. and a discrimination algorithm generating unit that judges whether the discrimination result of the type discrimination unit is normal or abnormal, determines whether there is a problem in the operation of the incinerator, re-labels the image data for which an abnormality is detected according to the type of waste, prepares new teacher data, and generates a discrimination algorithm by learning the newly prepared teacher data.

10. The information processing apparatus according to claim 9,

11. The types of the identification objects other than the waste include one or more of the following: beams of a waste treatment plant, side walls of a waste pit, cliffs of piles of waste stored in a waste pit, cranes that mix or transport the waste, walls, columns, floors, windows, ceilings, doors, stairs, girders, walkways, partition walls of a waste pit, waste input hoppers, loading doors, workers, and loading vehicles.

9. The information processing apparatus according to claim 8,

12. The types of waste include one or more of the following: unbroken garbage bags, paper waste, pruning branches, futons, sludge, bulky crushed garbage, cardboard, gunny bags, paper bags, bottom waste, wood chips, textile waste, clothing waste, plastic waste, animal residues, animal carcasses, kitchen waste, vegetation, soil, medical waste, incineration ash, bicycles, chests of drawers, beds, shelves, desks, chairs, agricultural vinyl products, PET bottles, styrofoam, meat and bone meal, agricultural crops, pottery, glass waste, metal waste, rubble, concrete waste, tatami mats, bamboo, straw, and activated carbon.

12. The information processing device according to claim 1,

13. Computer, a type identification unit that uses an identification algorithm that has been trained with training data in which the types of waste are labeled on past image data obtained by capturing an image of the inside of a waste pit in which waste is stored, and that uses new image data of the inside of the waste pit as input to identify the type of waste stored in the waste pit; and A plant control unit that controls the waste treatment plant based on the identification result of the type identification unit. An information processing program that functions as The waste whose type is identified by the type identification unit includes a first waste that affects a combustion state of a waste treatment plant, The plant control unit includes a combustion control unit that transmits the identification result of the type identification unit to a combustion control device that controls the combustion of the waste, The combustion control unit transmits, as the identification result of the type identification unit, one or more of a label in which the ratio of the types of waste is converted into quality information, and a label indicating that a ratio of a first waste that affects the combustion state is high, to the combustion control device.

2. An information processing program comprising:

14. A step of identifying the type of waste stored in the waste pit by inputting new image data of the waste pit using a recognition algorithm that has been trained with training data in which the type of waste is labeled on past image data obtained by capturing an image of the inside of the waste pit where the waste is stored; and controlling the waste treatment plant based on the identification result in the identifying step. The waste type identified in the identifying step includes a first waste that affects a combustion state of the waste treatment plant; The step of controlling includes a step of transmitting the identification result in the identifying step to a combustion control device that controls the combustion of the waste, In the transmitting step, one or more of a label in which the ratio of the types of waste is converted into quality information and a label indicating that a ratio of a first waste that affects the combustion state is high is transmitted to the combustion control device as the identification result in the identifying step.

23. An information processing method comprising:

15. a type identification unit that uses an identification algorithm that has been trained with teacher data in which the types of waste are labeled on past image data obtained by capturing an image of the waste storage area where the waste is stored, and that uses new image data of the waste pit as input to identify the type of waste stored in the waste pit; The waste whose type is identified by the type identification unit includes a first waste that affects a combustion state of a waste treatment plant, A plant control unit that controls the waste treatment plant based on the identification result of the type identification unit, The plant control unit includes a combustion control unit that transmits the identification result of the type identification unit to a combustion control device that controls the combustion of the waste, The combustion control unit transmits, as the identification result of the type identification unit, one or more of a label in which the ratio of the types of waste is converted into quality information, and a label indicating that a ratio of a first waste that affects the combustion state is high, to the combustion control device.

23. An information processing apparatus comprising:

16. Computer, a type identification unit that uses an identification algorithm that has been trained with training data in which the types of waste are labeled on past image data obtained by capturing images of the waste storage area where the waste is stored, and that uses new image data of the waste pit as input to identify the type of waste stored in the waste pit; and A plant control unit that controls the waste treatment plant based on the identification result of the type identification unit. An information processing program that functions as The waste whose type is identified by the type identification unit includes a first waste that affects a combustion state of a waste treatment plant, The plant control unit includes a combustion control unit that transmits the identification result of the type identification unit to a combustion control device that controls the combustion of the waste, The combustion control unit transmits, as the identification result of the type identification unit, one or more of a label in which the ratio of the types of waste is converted into quality information, and a label indicating that a ratio of a first waste that affects the combustion state is high, to the combustion control device.

2. An information processing program comprising:

17. A step of identifying the type of waste stored in the waste pit by inputting new image data of the waste pit using an identification algorithm that has been trained with training data in which the type of waste is labeled on past image data obtained by capturing an image of the waste storage area where the waste is stored; and controlling the waste treatment plant based on the identification result in the identifying step. The waste type identified in the identifying step includes a first waste that affects a combustion state of the waste treatment plant; The step of controlling includes a step of transmitting the identification result in the identifying step to a combustion control device that controls the combustion of the waste, In the transmitting step, one or more of a label in which the ratio of the types of waste is converted into quality information and a label indicating that a ratio of a first waste that affects the combustion state is high is transmitted to the combustion control device as the identification result in the identifying step.

23. An information processing method comprising:

18. A discrimination algorithm generating unit that generates the discrimination algorithm by learning training data in which types of waste are labeled on past image data obtained by capturing an image of a garbage pit in which waste is stored and objects to be discriminated other than the waste are labeled by type.

2. The information processing apparatus according to claim 1, further comprising:

Images