Garbage classification processing method, device and system, computer equipment and readable medium

Abstract

The present invention provides a method, device and system for garbage classification and processing, computer equipment and readable medium, and relates to the field of cloud computing. The method comprises: collecting characteristic information of garbage; the characteristic information of the garbage comprises at least one of the contour image, appearance image, text information on the appearance and component information of the garbage; and obtaining the classification of the garbage according to the characteristic information of the garbage and a pre-trained garbage classification model. The present invention can realize the classification of garbage intelligently and automatically by adopting the above technical solution, without manual participation in the whole process, and can effectively improve the efficiency of garbage classification and effectively ensure the accuracy of garbage classification.

Description

[Technical field]

[0001] The present invention relates to the field of computer application technology, and in particular to a garbage classification and processing method, device and system, computer equipment and readable medium. [Background technology]

[0002] With the rapid development of economy, the continuous growth of population and the improvement of people's living standards, the amount of domestic waste has also increased sharply, which has caused a great burden on the environment, affected the foundation of sustainable development and restricted the further development of the national economy. How to follow the principles and goals of harmlessness, reduction and resource utilization to deal with these wastes and fundamentally solve the harm of waste to the environment has become a problem of great concern to all sectors of society.

[0003] In the prior art, different garbage needs to be treated in different ways. For example, some garbage can be recycled, while some garbage needs to be landfilled or incinerated. If some chemical garbage that needs special treatment is mistaken for garbage that needs to be landfilled, it will cause very serious environmental pollution. Therefore, before garbage treatment, it is necessary to effectively classify the garbage. Therefore, garbage classification is a very important task in garbage treatment. In the prior art, the most common garbage classification method is to manually classify garbage items.

[0004] However, in the existing garbage sorting process, manual sorting is time-consuming and labor-intensive, the efficiency of garbage sorting is low, and the accuracy is also poor. [Summary of the invention]

[0005] The present invention provides a garbage classification processing method, device and system, computer equipment and readable medium, which are used to improve the efficiency and accuracy of garbage classification.

[0006] The present invention provides a garbage classification processing method, the method comprising:

[0007] Collecting characteristic information of the garbage; the characteristic information of the garbage includes at least one of an outline image, an appearance image, text information on the appearance, and composition information of the garbage;

[0008] The classification of the garbage is obtained according to the characteristic information of the garbage and a pre-trained garbage classification model.

[0009] The present invention provides a garbage classification processing device, the device comprising:

[0010] A collection module, used for collecting characteristic information of garbage; the characteristic information of garbage includes at least one of the outline image, appearance image, text information on the appearance and composition information of the garbage;

[0011] The classification module is used to obtain the classification of the garbage according to the characteristic information of the garbage and a pre-trained garbage classification model.

[0012] The present invention also provides a garbage classification system, the garbage classification system comprising the garbage classification device as described above; and further comprising at least one of an X-ray device, a camera, an OCR text recognition device, and a spectrum analyzer, and at least one communication module;

[0013] Each of the communication modules is used to send the characteristic information of the garbage collected by the corresponding X-ray device, the camera, the OCR text recognition instrument or the spectrometer to the garbage classification device.

[0014] The present invention also provides a computer device, the device comprising:

[0015] one or more processors;

[0016] A memory for storing one or more programs;

[0017] When the one or more programs are executed by the one or more processors, the one or more processors implement the garbage classification processing method as described above.

[0018] The present invention also provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the garbage classification processing method as described above is implemented.

[0019] The garbage classification processing method, device and system, computer equipment and readable medium of the present invention collect characteristic information of garbage; the characteristic information of garbage includes at least one of the outline image, appearance image, text information on the appearance and component information of the garbage; and obtains the classification of garbage according to the characteristic information of the garbage and the pre-trained garbage classification model. The technical solution of the present invention can realize the classification of garbage intelligently and automatically, without manual participation in the whole process, can effectively improve the efficiency of garbage classification, and can effectively ensure the accuracy of garbage classification.

Brief Description of the Drawings

[0020] Figure 1 This is a flow chart of Example 1 of the garbage classification and processing method of the present invention.

[0021] Figure 2 This is a flow chart of Embodiment 2 of the garbage classification and processing method of the present invention.

[0022] Figure 3 This is a flow chart of Example 3 of the garbage classification and processing method of the present invention.

[0023] Figure 4This is a flow chart of Embodiment 4 of the garbage classification and processing method of the present invention.

[0024] Figure 5 This is a structural diagram of the first embodiment of the garbage classification and processing device of the present invention.

[0025] Figure 6 This is a structural diagram of the second embodiment of the garbage classification and processing device of the present invention.

[0026] Figure 7 A structural diagram of an embodiment of a garbage classification system of the present invention.

[0027] Figure 8 It is a structural diagram of a computer device embodiment of the present invention.

[0028] Fig. 9 An exemplary diagram of a computer device provided by the present invention. [Specific implementation method]

[0029] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0030] Figure 1 This is a flow chart of the first embodiment of the garbage classification method of the present invention. Figure 1 As shown, the garbage classification processing method of this embodiment may specifically include the following steps:

[0031] S100, collecting characteristic information of garbage; the characteristic information of garbage includes at least one of an outline image, an appearance image, text information on the appearance, and composition information of the garbage;

[0032] S101. Obtaining garbage classification according to feature information of the garbage and a pre-trained garbage classification model.

[0033] The executor of the garbage classification and processing method of this embodiment is a garbage classification and processing device, which can be an electronic entity or a software-integrated application. When in use, the characteristic information of the garbage is input into the garbage classification and processing device, and the garbage classification and processing device can classify the garbage based on a pre-trained garbage classification model.

[0034] That is to say, the garbage classification processing device of this embodiment is embedded with a pre-trained garbage classification model, and the garbage classification model can classify the garbage based on the characteristic information of the collected garbage.

[0035] In this embodiment, the collected characteristic information of the garbage may include at least one of: an outline image, an appearance image, text information on the appearance, and composition information of the garbage.

[0036] The contour image of the collected garbage can be obtained by obtaining the contour image of the garbage scanned by an X-ray device;

[0037] The appearance image of the collected garbage can be obtained by acquiring the appearance image of the garbage taken by a camera;

[0038] The text information on the appearance of the garbage can be obtained by using an optical character recognition (OCR) text recognition device to identify the appearance of the garbage.

[0039] The composition information of the garbage can be obtained by obtaining the spectrum information of the garbage analyzed by the spectrum analyzer, and further analyzing the spectrum information of the garbage. The spectrum analyzer has different spectra based on different substances, and can analyze different substances such as elements included in the garbage, thereby analyzing the composition information of the garbage. Furthermore, the spectrum analyzer can also further infer the chemical molecular formula of the garbage based on other information.

[0040] The pre-trained garbage classification model in this embodiment can be trained using the characteristic information of several preset classifications of garbage during training. In this way, when in use, after the characteristic information of the garbage is input, the garbage classification model can output the probability that the garbage belongs to each classification. For example, if the number of preset classifications is N, then when in use, the garbage classification model outputs a 1*N vector based on the characteristic information of the garbage, where the value of each position in the vector is the probability of the garbage classification corresponding to the position. Where N is an arbitrary positive integer. For example, in actual applications, the classification of garbage can include textile garbage, paper garbage, chemical raw material garbage, flammable and explosive garbage, electronic garbage, catering garbage, etc. According to actual application requirements, it can be roughly classified according to the major categories of garbage, including only a few classifications, or it can be enriched to hundreds of classifications according to the detailed classification of garbage.

[0041] During specific use, the characteristic information of the garbage, including the contour image, appearance image, text information on the appearance and at least one of the component information of the garbage, is input into a pre-trained garbage classification model to obtain the classification with the highest probability predicted by the garbage classification model as the classification of the garbage.

[0042] It should be noted that the garbage classification model of this embodiment uses the garbage contour image, appearance image, text information on the appearance, and component information for training. When predicting the garbage classification, the corresponding type of information can be used for garbage classification prediction. In other words, the type of information used in training must be consistent with the type of information input during prediction.

[0043] Further optionally, in the garbage classification processing method of this embodiment, after step S101,

[0044] After obtaining the classification of garbage according to the characteristic information of garbage and the pre-trained garbage classification model, the following steps may also be included:

[0045] (a) Determine whether the classification of the garbage belongs to the preset first category of hazardous garbage; if so, execute step (b); otherwise, do not perform any operation for the time being.

[0046] (b) Sending an alarm message.

[0047] The first type of hazardous waste in this embodiment can be flammable and explosive waste, or chemically contaminated waste, etc. If the waste classification model predicts that the waste is the first type of hazardous waste, the waste classification and processing device can also be provided with an alarm module to send out an alarm message, so that the staff can handle the waste in time and avoid the harm caused by the waste.

[0048] Furthermore, the garbage classification processing method of this embodiment may further include displaying the classification of garbage after step S101. That is, the garbage classification processing device of this embodiment may also be provided with a display module to display the classification of the garbage, so that the staff can see the classification information of the garbage in time, and the dangerous garbage can be processed in time to avoid the harm caused by the garbage.

[0049] The garbage classification method of this embodiment collects characteristic information of the garbage; the characteristic information of the garbage includes at least one of the outline image, appearance image, text information on the appearance, and component information of the garbage; and obtains the classification of the garbage based on the characteristic information of the garbage and the pre-trained garbage classification model. The technical solution of this embodiment can realize the classification of garbage intelligently and automatically without manual participation in the whole process, which can effectively improve the efficiency of garbage classification and effectively ensure the accuracy of garbage classification.

[0050] Figure 2 This is a flow chart of Embodiment 2 of the garbage classification and processing method of the present invention. Figure 2 As shown, the garbage classification processing method of this embodiment may specifically include the following steps:

[0051] S200, collecting feature information of garbage; the feature information of garbage includes at least one of an outline image, an appearance image, and text information on the appearance of the garbage;

[0052] S201, obtaining the classification of garbage according to the characteristic information of the garbage and the pre-trained garbage classification model; and using it as the primary classification;

[0053] The implementation of step S200 and step S201 in this embodiment is the same as that in the above Figure 1 The difference between steps S100 and S101 in the embodiment shown is that the characteristic information of the garbage in this embodiment includes at least one of the outline image, appearance image and text information on the appearance of the garbage, but does not include the composition information of the garbage. The rest is the same as the above. Figure 1 Steps S100 and S101 of the embodiment shown are the same, and details can be referred to above. Figure 1 The relevant records of the illustrated embodiment will not be repeated here.

[0054] S202, determine whether the primary classification of the garbage is the preset second category of hazardous garbage; if so, execute step S203; otherwise, end.

[0055] The second category of hazardous waste in this embodiment may be drug waste, pharmaceutical waste or other hazardous waste, which may be further deeply identified to more accurately identify the primary classification of the waste.

[0056] That is to say, for the classification of hazardous waste that is not suitable for the second category, the classification results can be output after only primary classification.

[0057] S203, collecting spectral information of the garbage; and obtaining component information of the garbage based on the spectral information of the garbage; executing step S204;

[0058] The implementation of this step can refer to Figure 1 The explanation of the relevant steps shown will not be repeated here.

[0059] S204, obtaining a secondary classification of the garbage based on at least one of the contour image, the appearance image, and the text information on the appearance of the garbage, the component information of the garbage, the primary classification of the garbage, and a pre-trained deep garbage classification model.

[0060] This embodiment is different from the above Figure 1 The difference of the embodiment shown is that: Figure 1 In the embodiment shown, only one level of classification is performed when garbage is classified, and correspondingly only one garbage classification model is used. Figure 1 On the basis of the technical solution of the illustrated embodiment, for certain hazardous wastes such as drugs and medicines, a deep waste classification model can be used to perform secondary classification of the waste, thereby achieving more accurate classification of the hazardous waste, so as to facilitate accurate treatment of the hazardous waste and avoid the harm of the waste.

[0061] Similarly, the deep garbage classification model of this embodiment needs to be trained with several pieces of garbage feature information, each piece of garbage feature information includes at least one of the garbage contour image, appearance image and text information on the appearance, and the garbage component information and the primary classification of the garbage are trained together. Specifically, for at least one of the garbage contour image, appearance image and text information on the appearance, which ones are included during training, they also need to be included during garbage classification prediction.

[0062] The garbage classification and processing method of this embodiment, by adopting the above technical solution, can perform secondary classification of hazardous garbage, and can achieve more accurate classification of hazardous garbage, so as to facilitate accurate treatment of hazardous garbage and avoid the harm of garbage. Moreover, the technical solution of this embodiment can realize the classification of garbage intelligently and automatically, without the need for manual participation throughout the process, and can effectively improve the efficiency of garbage classification, and can perform secondary classification of hazardous garbage, further effectively ensuring the accuracy of garbage classification.

[0063] Figure 3 This is a flow chart of Embodiment 3 of the garbage classification and processing method of the present invention. Figure 3 As shown, the garbage classification processing method of this embodiment may specifically include the following steps:

[0064] S300, collecting a plurality of training data, characteristic information of training garbage in each training data and known classification of training garbage; the characteristic information of each training garbage includes at least one of the contour image, appearance image, text information on the appearance and component information of the training garbage;

[0065] S301: Train a garbage classification model based on the feature information of each piece of training garbage and the corresponding known classification.

[0066] Similarly, in this embodiment, each feature information of the training garbage includes at least one of the contour image, appearance image, text information on the appearance, and component information of the training garbage. When performing garbage classification prediction, the corresponding feature information can be used for prediction according to the features used in training.

[0067] During specific training, the feature information of each piece of training garbage is input into the garbage classification model. The garbage classification model can predict a garbage classification based on the existing parameters and the feature information of the input training garbage. Then, it is determined whether the predicted classification is consistent with the known classification. If not, the parameters of the garbage classification model are adjusted so that the classification predicted by the garbage classification model is consistent with the known classification. Using the feature information of several pieces of training garbage and the corresponding known classification, the garbage classification model is continuously trained in the above manner until the number of training times reaches a preset threshold, or the predicted classification in the continuous preset number of rounds of training is always consistent with the known classification. At this time, the training ends, the parameters of the garbage classification model are determined, and then the garbage classification model is determined.

[0068] The training garbage in this embodiment can be any garbage, such as textile garbage, paper garbage, chemical raw material garbage, flammable and explosive garbage, electronic garbage, restaurant garbage, etc.

[0069] The garbage classification model trained in this embodiment is used to achieve the above Figure 1 The garbage classification process of the illustrated embodiment.

[0070] The execution subject of the garbage classification processing method of this embodiment can be the same as the above Figure 1 The garbage classification processing device first trains the garbage classification model and the deep garbage classification model, and then uses the above-mentioned garbage classification processing device based on the trained garbage classification model. Figure 1 The technical solution of the illustrated embodiment realizes the primary classification of garbage.

[0071] Alternatively, the execution subject of the garbage classification processing method of this embodiment may be different from the above Figure 1 The execution subject of the embodiment shown is a training device for the garbage classification model that is independent of the garbage classification processing device. When in use, the training device for the garbage classification model first trains the garbage classification model and the deep garbage classification model, and then the garbage classification processing device directly calls the trained garbage classification model when classifying garbage. Figure 1 The technical solution of the illustrated embodiment realizes the classification of garbage.

[0072] The garbage classification method of this embodiment can realize garbage classification intelligently and automatically by adopting the garbage classification model trained by the above-mentioned scheme, without the need for human intervention in the whole process, and can effectively improve the efficiency of garbage classification and effectively ensure the accuracy of garbage classification.

[0073] Figure 4 This is a flow chart of Embodiment 4 of the garbage classification and processing method of the present invention. Figure 4As shown, the garbage classification processing method of this embodiment may specifically include the following steps:

[0074] S400, collecting a plurality of training data, each of which includes characteristic information of training garbage, primary classification of training garbage, and known secondary classification of training garbage; the characteristic information of training garbage includes at least one of a contour image, an appearance image, and text information on the appearance of the training garbage, and component information of the training garbage;

[0075] S401, training a deep garbage classification model according to the feature information of each training garbage, the corresponding primary classification and the known secondary classification.

[0076] Specifically, if the above Figure 3 In the embodiment shown, when training a garbage classification model, the characteristic information of each training garbage includes at least one of a contour image, an appearance image, and text information on the appearance of the training garbage. At this time, for hazardous waste such as drugs and medicines, the technical solution of this embodiment can be further adopted to train a deep garbage classification model to achieve secondary classification of the garbage.

[0077] That is, the range of training garbage in this embodiment is smaller than the above Figure 3 The scope of the training waste in the illustrated embodiment may be hazardous waste such as drugs and medicines.

[0078] During specific training, the feature information and primary classification of each piece of training garbage are input into the deep garbage classification model. The deep garbage classification model can predict the secondary classification of a piece of garbage based on the existing parameters and the feature information and primary classification of the input training garbage. Then determine whether the predicted secondary classification is consistent with the known secondary classification. If not, adjust the parameters of the deep garbage classification model so that the secondary classification predicted by the deep garbage classification model is consistent with the known secondary classification. Using the feature information, primary classification and corresponding secondary known classification of several pieces of training garbage, the deep garbage classification model is continuously trained in the above manner until the number of training times reaches a preset threshold, or the predicted secondary classification in the continuous preset number of rounds of training is always consistent with the known secondary classification. At this time, the training ends, the parameters of the deep garbage classification model are determined, and then the deep garbage classification model is determined.

[0079] If the above Figure 3 The characteristic information of each piece of training garbage in the embodiment shown does not include component information. Figure 3 The garbage classification model trained by the embodiment shown and Figure 4 The deep garbage classification model trained in the embodiment shown in the figure is implemented together Figure 2 The garbage classification process of the illustrated embodiment.

[0080] Similarly, the execution subject of the garbage classification processing method of this embodiment can be the same as the above Figure 2 That is, the garbage classification processing device first trains the garbage classification model and the deep garbage classification model, and then the garbage classification processing device can also use the above-mentioned Figure 2 The technical solution of the illustrated embodiment realizes the secondary classification of garbage.

[0081] Alternatively, the execution subject of the garbage classification processing method of this embodiment may be different from the above Figure 2 The execution subject of the embodiment shown is a training device for the garbage classification model that is independent of the garbage classification processing device. When in use, the training device for the garbage classification model first trains the garbage classification model and the deep garbage classification model, and then the garbage classification processing device directly calls the trained garbage classification model and the deep garbage classification model when classifying garbage. Figure 2 The technical solution of the illustrated embodiment realizes the secondary classification of garbage.

[0082] The garbage classification method of this embodiment can realize garbage classification intelligently and automatically by adopting the garbage classification model trained by the above-mentioned scheme, without the need for human intervention in the whole process, and can effectively improve the efficiency of garbage classification and effectively ensure the accuracy of garbage classification.

[0083] Figure 5 FIG. 1 is a structural diagram of a first embodiment of a garbage classification and processing device of the present invention. Figure 5 As shown, the garbage classification processing device of this embodiment may specifically include:

[0084] The collection module 10 is used to collect characteristic information of garbage; the characteristic information of garbage includes at least one of the outline image, appearance image, text information on the appearance and composition information of the garbage;

[0085] The classification module 11 is used to obtain the classification of garbage according to the feature information of the garbage collected by the collection module 10 and the pre-trained garbage classification model.

[0086] The garbage classification and processing device of this embodiment realizes garbage classification and processing by adopting the above-mentioned modules. The implementation principle and technical effect are the same as those of the above-mentioned related method embodiments. For details, please refer to the records of the above-mentioned related method embodiments, which will not be repeated here.

[0087] Figure 6 FIG. 2 is a structural diagram of the second embodiment of the garbage classification and processing device of the present invention. Figure 6 As shown, the garbage classification processing device of this embodiment, in the above Figure 5Based on the technical solution of the illustrated embodiment, the technical solution of the present invention is further described in more detail.

[0088] In the garbage classification processing device of this embodiment, the collection module 10 is used to perform at least one of the following:

[0089] Obtaining a contour image of the garbage scanned by an X-ray machine;

[0090] Obtaining the appearance image of the garbage captured by the camera;

[0091] Obtaining text information on the appearance of the garbage obtained by using an OCR text recognition device to recognize the appearance of the garbage; and

[0092] Spectral information of the garbage analyzed by the spectrum analyzer is obtained, and component information of the garbage is obtained based on the spectral information of the garbage.

[0093] Optionally, in the garbage classification processing device of this embodiment, the classification module 11 is used for:

[0094] Input the characteristic information of garbage into the pre-trained garbage classification model;

[0095] The classification with the highest probability predicted by the garbage classification model is obtained as the classification of the garbage.

[0096] Further optionally, if Figure 6 As shown, the garbage classification processing device of this embodiment also includes:

[0097] The judging module 12 is used to judge whether the classification of the garbage processed by the classification module 11 belongs to the preset first category of hazardous garbage;

[0098] The alarm module 13 is used to send out an alarm message if the judgment module 12 determines that the classification of the garbage is the first category of hazardous garbage.

[0099] Further optionally, if Figure 6 As shown, the garbage classification processing device of this embodiment also includes:

[0100] The display module 14 is used to display the classification of the garbage processed by the classification module 11.

[0101] Further optionally, if Figure 6 As shown, the garbage classification processing device of this embodiment further includes a training module 15;

[0102] The acquisition module 10 is also used to acquire a plurality of training data, characteristic information of training garbage in each training data and known classification of training garbage; the characteristic information of each training garbage includes at least one of the contour image, appearance image, text information on the appearance and component information of the training garbage;

[0103] The training module 15 is used to train a garbage classification model according to the feature information of each training garbage collected by the collection module 10 and the corresponding known classification.

[0104] Further optionally, in another scenario of the present embodiment, the judging module 12 is further configured to, if the characteristic information of the garbage collected by the collecting module 10 includes at least one of an outline image, an appearance image, and text information on the appearance of the garbage, use the classification of the garbage obtained by the classifying module 11 as a primary classification, and judge whether the primary classification is a preset second-class hazardous garbage classification;

[0105] The collection module 10 is also used to collect the spectrum information of the garbage if the primary classification is the classification of the second category of hazardous garbage; and obtain the composition information of the garbage based on the spectrum information of the garbage;

[0106] The classification module 11 is also used to obtain the secondary classification of garbage based on at least one of the contour image, appearance image and text information on the appearance of the garbage collected by the collection module 10, the composition information of the garbage, the primary classification and the pre-trained deep garbage classification model.

[0107] Correspondingly, the acquisition module 10 is also used to acquire a plurality of training data, each of which includes characteristic information of training garbage, primary classification of training garbage, and known secondary classification of training garbage; the characteristic information of training garbage includes at least one of the contour image, appearance image, and text information on the appearance of the training garbage, and the composition information of the training garbage;

[0108] The training module 11 is also used to train a deep garbage classification model according to the feature information of each training garbage, the corresponding primary classification and the known secondary classification.

[0109] Optionally, the collection module 10 and the training module 11 of this embodiment can also independently constitute a training device for a garbage classification model and can exist independently.

[0110] The garbage classification and processing device of this embodiment realizes garbage classification and processing by adopting the above-mentioned modules. The implementation principle and technical effect are the same as those of the above-mentioned related method embodiments. For details, please refer to the records of the above-mentioned related method embodiments, which will not be repeated here.

[0111] Figure 7 The structure diagram of the garbage classification system embodiment of the present invention. Figure 7 As shown, the garbage classification system of this embodiment includes the above Figure 5 or Figure 6 The garbage classification device 20 of the illustrated embodiment also includes at least one of an X-ray device 21, a camera 22, an OCR text recognition device 23, and a spectrum analyzer 24, and at least one communication module 25; Figure 7 The illustrated embodiment takes the X-ray device 21 , the camera 22 , the OCR text recognition device 23 and the spectrum analyzer 24 as an example.

[0112] Each communication module 25 is used to send the characteristic information of garbage collected by the corresponding X-ray device 21, camera 22, OCR text recognition device 23 or spectrum analyzer 24 to the garbage classification device.

[0113] Further optionally, if Figure 7 As shown, the garbage classification system of this embodiment further includes a transmission mechanism 26 and a processing box 27 for storing garbage of each classification;

[0114] The transport mechanism 26 is used to transport the garbage to the corresponding classification processing box 27 according to the classification of the garbage obtained by the garbage classification device 20; and / or

[0115] Further optionally, if Figure 7 As shown, the garbage classification system of this embodiment further includes a storage module 28, which is used to store the characteristic information of garbage collected by the X-ray device 21, the camera 22, the OCR text recognition device 23 and the spectrometer 24. At this time, correspondingly, each communication module 25 can transmit the characteristic information of garbage collected by the X-ray device 21, the camera 22, the OCR text recognition device 23 and the spectrometer 24 to the storage module 28 for storage. When performing garbage classification detection, the storage module 28 directly outputs the characteristic information of the collected garbage to the garbage classification device 20, so that the garbage classification device 20 adopts the steps of the above-mentioned related method embodiments to realize the classification of garbage.

[0116] The garbage classification system of this embodiment can effectively classify garbage and avoid the harm of garbage by adopting the above technical solution. Moreover, the technical solution of this embodiment can realize the classification of garbage intelligently and automatically without manual participation in the whole process, which can effectively improve the efficiency of garbage classification and effectively ensure the accuracy of garbage classification.

[0117] Figure 8 FIG. 1 is a structural diagram of a computer device embodiment of the present invention. Figure 8 As shown, the computer device of this embodiment includes: one or more processors 30, and a memory 40, the memory 40 is used to store one or more programs, when the one or more programs stored in the memory 40 are executed by the one or more processors 30, the one or more processors 30 implement the above Figure 1-Figure 4 The garbage classification and processing method of the illustrated embodiment. Figure 8 The embodiment shown in the figure takes a plurality of processors 30 as an example.

[0118] For example, Fig. 9 An exemplary diagram of a computer device provided by the present invention. Fig. 9 A block diagram of an exemplary computer device 12a suitable for use in implementing embodiments of the present invention is shown. Fig. 9 The computer device 12a shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0119] like Fig. 9 As shown, the computer device 12a is in the form of a general-purpose computing device. The components of the computer device 12a may include, but are not limited to: one or more processors 16a, a system memory 28a, and a bus 18a that connects different system components (including the system memory 28a and the processor 16a).

[0120] Bus 18a represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0121] The computer device 12a typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12a, including volatile and non-volatile media, removable and non-removable media.

[0122] The system memory 28a may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30a and / or cache memory 32a. The computer device 12a may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34a may be used to read and write non-removable, non-volatile magnetic media ( Fig. 9 not shown, usually called a "hard drive"). Although Fig. 9 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical media) may be provided. In these cases, each drive can be connected to the bus 18a via one or more data medium interfaces. The system memory 28a may include at least one program product, which has a set (such as at least one) of program modules, which are configured to execute the above-mentioned Figure 1-Figure 6 Functions of various embodiments.

[0123] A program / utility 40a having a set (at least one) of program modules 42a may be stored, for example, in system memory 28a, such program modules 42a including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may include the implementation of a network environment. Program modules 42a generally perform the above-described Figure 1-Figure 6 Functions and / or methods in each embodiment.

[0124] The computer device 12a can also communicate with one or more external devices 14a (e.g., keyboard, pointing device, display 24a, etc.), and can also communicate with one or more devices that enable users to interact with the computer device 12a, and / or communicate with any device that enables the computer device 12a to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be carried out through an input / output (I / O) interface 22a. In addition, the computer device 12a can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) through a network adapter 20a. As shown in the figure, the network adapter 20a communicates with other modules of the computer device 12a through a bus 18a. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the computer device 12a, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0125] The processor 16a executes various functional applications and data processing by running the programs stored in the system memory 28a, such as implementing the garbage classification processing method shown in the above embodiment.

[0126] The present invention also provides a computer-readable medium on which a computer program is stored. When the program is executed by a processor, the garbage classification processing method shown in the above embodiment is implemented.

[0127] The computer-readable medium of this embodiment may include the above Figure 7 RAM 30a, and / or cache memory 32a, and / or storage system 34a in system memory 28a in the illustrated embodiment.

[0128] With the development of science and technology, the dissemination of computer programs is no longer limited to tangible media, and can also be downloaded directly from the Internet or obtained in other ways. Therefore, the computer-readable medium in this embodiment can include not only tangible media, but also intangible media.

[0129] The computer-readable medium of the present embodiment can adopt any combination of one or more computer-readable media.Computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium.Computer-readable storage medium can be, for example, - but not limited to - a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above.More specific examples (non-exhaustive list) of computer-readable storage medium include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0130] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0131] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0132] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0133] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation.

[0134] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0136] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0137] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for waste classification and processing, characterized in that: The method comprises: Collecting characteristic information of the garbage; the characteristic information of the garbage includes at least one of an outline image, an appearance image, and text information on the appearance of the garbage; According to the characteristic information of the garbage and a pre-trained garbage classification model, the classification of the garbage is obtained as the primary classification of the garbage; Determining whether the primary classification is a preset second category of hazardous waste; If yes, collect spectrum information of the garbage; and obtain component information of the garbage based on the spectrum information of the garbage; The secondary classification of the garbage is obtained according to at least one of the contour image, the appearance image and the text information on the appearance of the garbage, the component information of the garbage, the primary classification and the pre-trained deep garbage classification model.

2. The method according to claim 1, characterized in that: The characteristic information of the collected garbage includes at least one of the following: Obtaining a contour image of the garbage scanned by an X-ray machine; Acquire an appearance image of the garbage captured by a camera; and The text information on the appearance of the garbage is obtained by an OCR text recognition device recognizing the appearance of the garbage.

3. The method according to claim 1, characterized in that According to the feature information of the garbage and the pre-trained garbage classification model, the classification of the garbage is obtained, including: Inputting the characteristic information of the garbage into a pre-trained garbage classification model; The classification with the highest probability predicted by the garbage classification model is obtained as the classification of the garbage.

4. The method according to claim 1, characterized in that: After obtaining the classification of the garbage according to the characteristic information of the garbage and the pre-trained garbage classification model, the method further includes: Determining whether the classification of the garbage belongs to the preset first category of hazardous garbage; If so, an alarm message is issued.

5. The method according to claim 1, characterized in that After obtaining the classification of the garbage according to the characteristic information of the garbage and the pre-trained garbage classification model, the method further includes: Displays the classification of the garbage.

6. The method according to claim 1, characterized in that Before obtaining the classification of the garbage according to the characteristic information of the garbage and the pre-trained garbage classification model, the method further includes: Collecting a plurality of training data, characteristic information of training garbage in each of the training data and known classification of the training garbage; the characteristic information of each of the training garbage includes at least one of the contour image, appearance image, text information on the appearance and component information of the training garbage; The garbage classification model is trained according to the feature information of each piece of the training garbage and the corresponding known classification.

7. The method according to claim 1, characterized in that Before obtaining the secondary classification of the garbage based on at least one of the contour image, the appearance image and the text information on the appearance of the garbage, the component information of the garbage, the primary classification and the pre-trained deep garbage classification model, the method further includes: Collecting a plurality of training data, each of which includes characteristic information of training garbage, primary classification of the training garbage, and known secondary classification of the training garbage; the characteristic information of the training garbage includes at least one of a contour image, an appearance image, and text information on the appearance of the training garbage, and component information of the training garbage; The deep garbage classification model is trained according to the feature information of each piece of the training garbage, the corresponding primary classification and the known secondary classification.

8. A garbage classification and processing device, characterized in that: The device comprises: A collection module, used for collecting characteristic information of garbage; the characteristic information of garbage includes at least one of an outline image, an appearance image, and text information on the appearance of the garbage; A classification module, used for obtaining the classification of the garbage as a primary classification of the garbage according to the characteristic information of the garbage and a pre-trained garbage classification model; A judgment module, used to judge whether the primary classification is a preset second category of hazardous waste; The acquisition module is further used for acquiring spectral information of the garbage if the primary classification is the classification of the second type of hazardous garbage; and acquiring component information of the garbage based on the spectral information of the garbage; The classification module is also used to obtain the secondary classification of the garbage based on at least one of the contour image, appearance image and text information on the appearance of the garbage, the component information of the garbage, the primary classification and a pre-trained deep garbage classification model.

9. The device according to claim 8, characterized in that The acquisition module is used to perform at least one of the following: Obtaining a contour image of the garbage scanned by an X-ray machine; Obtaining an appearance image of the garbage captured by a camera; and The text information on the appearance of the garbage is obtained by an OCR text recognition device recognizing the appearance of the garbage.

10. The device according to claim 8, characterized in that The classification module is used to: Inputting the characteristic information of the garbage into a pre-trained garbage classification model; The classification with the highest probability predicted by the garbage classification model is obtained as the classification of the garbage.

11. The device according to claim 8, characterized in that The device also includes: A judgment module, used to judge whether the classification of the garbage belongs to the preset first category of hazardous garbage; The alarm module is used to issue an alarm message if the classification of the garbage is the first category of hazardous garbage.

12. The device according to claim 8, characterized in that The device also includes: The display module is used to display the classification of the garbage.

13. The device according to claim 11, characterized in that The device also includes a training module; The acquisition module is further used to acquire a plurality of training data, feature information of training garbage in each of the training data and known classification of the training garbage; the feature information of each of the training garbage includes at least one of the contour image, appearance image, text information on the appearance and component information of the training garbage; The training module is used to train the garbage classification model according to the feature information of each piece of training garbage and the corresponding known classification.

14. The device according to claim 8, characterized in that: The acquisition module is further used to acquire a plurality of training data, each of which includes characteristic information of training garbage, primary classification of the training garbage, and known secondary classification of the training garbage; the characteristic information of the training garbage includes at least one of the contour image, appearance image, and text information on the appearance of the training garbage, and the composition information of the training garbage; The training module is also used to train the deep garbage classification model according to the feature information of each piece of training garbage, the corresponding primary classification and the known secondary classification.

15. A garbage classification system, characterized in that: The garbage classification system comprises the garbage classification device as described in any one of claims 8 to 14 above; and further comprises at least one of an X-ray device, a camera, an OCR text recognition device and a spectrum analyzer, and at least one communication module; Each of the communication modules is used to send the characteristic information of the garbage collected by the corresponding X-ray device, the camera, the OCR text recognition instrument or the spectrometer to the garbage classification device.

16. The system according to claim 15, characterized in that The system also includes a transmission mechanism and a processing box for storing each of the classified garbage; The transmission mechanism is used to transmit the garbage to the processing box corresponding to the classification according to the classification of the garbage; and / or The system also includes a storage module for storing feature information of garbage collected by the X-ray device, the camera, the OCR text recognition device and the spectrometer.

17. A computer device, characterized in that: The device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

18. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images