CN118179958A - Garbage sorting device and method - Google Patents

Abstract

The scheme discloses a rubbish sorting device and method, wherein, this device includes: the garbage image acquisition unit acquires garbage image data of a target area; the identifying unit is used for identifying the garbage type in the garbage image data to obtain the garbage type in the target area; and the sorting unit is used for collecting garbage of corresponding types according to the scheduling instruction. According to the technical scheme, the automatic garbage type identification strategy is introduced in the medical garbage sorting process, so that the types of garbage can be automatically identified and sorted, the type and weighing of garbage for each bearing container are not needed to be manually selected, the labor cost can be greatly reduced, garbage collection is reasonably scheduled by using a load balancing algorithm, the collection pressure of a collection road junction is reduced, and the garbage sorting efficiency is improved.

Description

Garbage sorting device and method

Technical Field

The scheme relates to the technical field of garbage sorting. And more particularly to an apparatus and method for automatic identification and sorting collection of hospital household and medical waste.

Background

A large number of household garbage and medical garbage can be produced in a large hospital every day, the hospital can spend a large amount of manpower and material resources to collect and transport the household garbage and the medical garbage every day, if the management is improper, the garbage can be discharged and discarded at will and be treated at will to cause serious environmental pollution, in order to purify the environment, strict classified collection regulations are respectively formulated for the household garbage and the medical garbage by the government, the garbage generation mechanism must carry out classified collection and treatment on the garbage under strict regulation, and the main mechanism for generating the garbage is heavy burden. Hospitals are used as main body mechanisms for classifying and collecting garbage, and the garbage generated in the hospitals every day is required to be collected, sorted and treated by invested funds and manpower, and the garbage is generally collected and sorted manually together in a manual collection and sorting mode and collected and sorted in a semi-automatic system.

In recent years, the treatment modes of hospital waste are generally as follows:

1. designating a garbage type on an interactive system at a garbage sending point and binding a loaded box number;

2. manually weighing garbage at a garbage sending point;

3. installing a box number scanner at each of a plurality of sorting crossings;

4. when the garbage container passes through each crossing, the system performs code scanning identification on the box once to judge whether the box can be collected at the current crossing;

5. if yes, sending an instruction to conduct import collection, and if not, continuing to the next crossing.

Disclosure of Invention

The invention aims to provide a device and a method for automatically identifying, sorting and collecting household garbage and medical garbage in hospitals, so as to solve the problems of high equipment cost, high manpower consumption, low treatment efficiency and the like of medical garbage classification in the prior art.

In order to achieve the above purpose, the present solution adopts the following technical scheme:

in a first aspect, the present disclosure provides a waste sorting apparatus, the apparatus comprising:

The garbage image acquisition unit acquires garbage image data of a target area;

the identifying unit is used for identifying the garbage type in the garbage image data to obtain the garbage type in the target area;

and the sorting unit is used for collecting garbage of corresponding types according to the scheduling instruction.

In a preferred embodiment, the acquisition unit comprises: at least one image acquisition device arranged at a predetermined position on the garbage transmission line.

In a preferred embodiment, the apparatus comprises: the scheduling unit generates scheduling instructions according to the current collection state of the sorting unit.

In a preferred embodiment, the scheduling unit comprises:

The acquisition module acquires at least one of the current garbage collection queuing quantity, the garbage quantity to be collected, the state data of a collection road junction and the garbage weight to collect state information;

The calculation module is used for calculating a scheduling scheme of each garbage sent to the sorting unit based on a load balancing algorithm by utilizing the collected state information;

and the scheduling module is used for generating scheduling instructions for collecting and scheduling garbage according to the scheduling scheme.

In a preferred embodiment, the sorting unit comprises a plurality of refuse collection gates;

And the garbage collection road junction collects garbage of corresponding types according to the scheduling instruction.

In a preferred embodiment, the apparatus comprises: and the weighing unit is used for weighing the garbage to be collected to obtain the weight data of the garbage.

In a preferred embodiment, the apparatus comprises: and the fault monitoring unit is used for monitoring the state of each garbage collection road junction in the sorting unit to obtain road junction state data.

In a preferred embodiment, the identifying unit identifies the garbage type in the garbage image data by using a pre-constructed garbage classification identifying model, and obtains the garbage type in the target area.

In a second aspect, the present disclosure provides a method for sorting waste, the method comprising:

Collecting garbage image data of a target area;

Based on a pre-constructed garbage classification and identification model, identifying garbage types in the garbage image data to obtain the garbage types in the target area;

and collecting garbage of corresponding types according to the scheduling instruction.

In a preferred embodiment, the step of obtaining the scheduling instruction includes:

acquiring at least one of the current garbage collection queuing quantity, the garbage quantity to be collected, the state data of a collection road junction and the garbage weight to collect state information;

Calculating a scheduling scheme of each garbage sent to the sorting unit based on a load balancing algorithm by utilizing the collection state information;

and generating a scheduling instruction for collecting and scheduling garbage according to the scheduling scheme.

The beneficial effects of the invention are as follows:

According to the technical scheme, the automatic garbage type identification strategy is introduced in the medical garbage sorting process, so that the types of garbage can be automatically identified and sorted, the type and weighing of garbage for each bearing container are not needed to be manually selected, the labor cost can be greatly reduced, garbage collection is reasonably scheduled by using a load balancing algorithm, the collection pressure of a collection road junction is reduced, and the garbage sorting efficiency is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 shows a schematic view of a refuse sorting apparatus according to the present solution;

fig. 2 shows a schematic diagram of the method for sorting waste according to the present solution;

FIG. 3 is a schematic diagram showing an example of a garbage classification model training method according to the present embodiment;

Fig. 4 shows a schematic diagram of an example of a garbage sorting process according to the present solution;

Fig. 5 shows a schematic view of an example of the refuse sorting apparatus according to the present solution.

Reference numerals and signs

1. An acquisition unit; 2. an identification unit; 3. a sorting unit; 4. a scheduling unit; 5. a fault monitoring unit; 6. and a weighing unit.

Detailed Description

In order to make the technical scheme and advantages of the present application more apparent, embodiments of the present application will be described in further detail with reference to the accompanying drawings. It will be apparent that the described embodiments are only some of the embodiments of the present application and are not exhaustive of all embodiments. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other.

Through analysis and research on the prior art, garbage type selection is needed to be performed manually through an interactive system in a garbage sending link, box number binding is performed, garbage weighing actions are performed, and human resources are wasted. In the garbage sorting link, a box number identifier is required to be added to each sorting crossing, equipment cost is increased, meanwhile, after each crossing identifies the box number each time, a system is required to conduct calculation processing of whether to conduct importing or not, and drainage and arrangement sorting containers cannot be conducted through overall flow and equipment state balanced scheduling, so that efficiency is low.

Therefore, the scheme aims to provide the garbage sorting device, the device introduces an automatic system in a collecting and sorting link of a large-scale hospital, realizes automation of collecting and sorting garbage in the hospital, introduces AI identification in a sorting link of garbage to confirm the type of the garbage, and performs automatic weighing. And reasonably distributing garbage collection sequences through a load balancing algorithm. Before sorting, the sending end only needs to sort and bin the garbage of different categories, does not need to do any input operation on the system, directly sends the boxes to the sorting end, and the sorting end carries out automatic sorting according to the AI identification result. Through the load balancing algorithm, flow adjustment can be performed according to the flow of equipment and the state of the equipment during garbage sorting, and sorting efficiency is improved. The multiple-sorting road junction can be sorted only by once identifying the total sorting point, the system can automatically calculate the real-time position of each box on the line body, and the sorter is sprung to turn and sort after reaching the preset road junction.

The device for automatically identifying, sorting and collecting household garbage and medical garbage in hospitals, which is provided by the scheme, is described in detail below with reference to the accompanying drawings. Specifically, as shown in fig. 1, the apparatus includes: the device comprises an acquisition unit 1, an identification unit 2, a scheduling unit 4 and a sorting unit 3. The method comprises the steps that an acquisition unit 1 acquires garbage image data of a target area; and identifying the garbage type in the garbage image data by using an identification unit 2 to obtain the garbage type in the target area. Then, a scheduling instruction is generated by the scheduling unit 4 according to the current collection state of the sorting unit 3. Finally, the sorting unit 3 is used for collecting the garbage of the corresponding type according to the scheduling instruction.

In this scheme, the acquisition unit 1 can be an image acquisition device, and is arranged at a preset position of a garbage transmission line. The image acquisition device can acquire image data of the garbage in the transmission box when the transmission box carrying the medical garbage passes through the image acquisition area, and then, the image data is transmitted to the identification unit 2. In one example, the acquisition unit 1 may comprise at least one camera. The camera is arranged near an image acquisition area of the garbage transmission line. When the transmission box carrying garbage passes through the image acquisition area, the camera sends acquired video images or images to a cloud server, a control center and the like for subsequent analysis and processing.

In this scheme, the recognition unit 2 may be disposed in a control center, a cloud server, an AI analysis scheduling system, and other devices, and uses a pre-trained classification model to recognize the type of garbage in the garbage image data, so as to determine the type of garbage in the transmission box. In one example, the garbage classification model is obtained by marking a garbage image prepared in advance, performing training for a plurality of times by using a deep learning neural network or machine learning as a training sample. And embedding the pre-trained garbage classification model into a system, and identifying the garbage type in the image data when the garbage image data is acquired, so as to determine the garbage type in the transmission box in the current image acquisition area.

In this solution, after determining the type of refuse, a scheduling instruction may be issued to the sorting unit 3 by a control center or an AI analysis scheduling system. The sorting unit 3 collects different types of waste according to the scheduling instructions. In one example, the sorting unit 3 may comprise a plurality of refuse collection gates. The garbage can be conveniently collected in the transmission box by arranging auxiliary collecting devices such as a manipulator, sorting, overturning and dumping at the garbage port. The auxiliary collection device carries and collects garbage of corresponding collection types at different garbage collection ports under the control of a dispatching instruction.

In this scheme, in order to be better orderly, more efficient collect rubbish, can further set up dispatch unit 4 at the device, dispatch unit 4 can be according to the current collection state of letter sorting unit 3, generates the scheduling instruction. Specifically, the scheduling unit 4 may include: the device comprises an acquisition module, a calculation module and a scheduling module. The acquisition module acquires at least one of the current garbage collection queuing quantity, the garbage quantity to be collected, the state data of a collection road junction and the garbage weight to collect state information; then, the calculation module calculates a scheduling scheme of each garbage sent to the sorting unit 3 based on a load balancing algorithm by using the collected state information; and the scheduling module generates scheduling instructions for collecting and scheduling garbage according to the scheduling scheme. The sorting unit 3 can finally distribute different types of garbage more reasonably according to the scheduling instruction, so that the collection efficiency is improved.

In addition, in order to facilitate the implementation of the scheduling instruction, the control of the auxiliary collecting device can be performed by utilizing a PLC controller to perform comprehensive scheduling and control.

In this solution, a weighing unit 6 and/or a guard length recognition unit 2 are further provided. The weighing unit 6 can weigh the garbage to be collected to obtain the weight data of the garbage. The fault detection unit 5 may monitor the status of each garbage collection crossing in the classification unit 3 to obtain crossing status data. The weight data, the road junction state data and other auxiliary analysis data can be used as the basis for the scheduling unit 4 to formulate a scheduling scheme, namely as the analysis parameters of a load balancing algorithm.

In the process of sorting and collecting the medical waste in a large hospital, when the transmission box carrying the medical waste passes through the total sorting point, the total sorting point is used as an image acquisition area for target identification, the camera is used for acquiring image data, and the waste in the transmission box is automatically weighed. And classifying the types of the garbage by using an AI garbage classification model, and recording the types and the weights of the garbage in the transmission box in the image acquisition area. The device is matched and bound with the corresponding garbage collection road junction according to the type of garbage. At this time, the status of the equipment at the collection level crossing may be obtained, for example, the number of queues of the dustbin at each collection level crossing is collected, and the number of dustbin expected to reach the level crossing is calculated. Then, the most suitable collection road junction is calculated by utilizing a load balancing algorithm, a dispatching instruction of sorting road junction is issued, and the garbage transmission box is sent to a suitable collection road junction to be matched with an auxiliary collection device for collecting garbage. All the garbage conveying boxes only need to be identified by one box number at a total sorting point, after sorting scheduling instructions are issued, the system can calculate the position of the current garbage conveying box according to the running speed of a transmission line and the starting point of the garbage conveying box, and when the current garbage conveying box reaches a preset collecting crossing, the garbage conveying box can be guided to the preset crossing by using a sorter and then is matched with an auxiliary collecting device to collect garbage.

The operation process of the garbage sorting device comprises the following steps: when the garbage transmission box is transmitted on the horizontal conveying belt, video picture data of garbage in the transmission box are collected at a preset position through the camera, and meanwhile, the weighing equipment can collect the weight of the garbage in the container, and the data are reported to the control center. The dispatching unit 4 collects the equipment state data of the collection crossing and counts the number of queuing transmission boxes of each collection crossing and the number of expected garbage transmission boxes. Then, based on a load balancing algorithm, an optimal allocation scheme is calculated to schedule and collect the crossing. Specifically, the garbage container passes through the camera, the acquired video image data is uploaded to the control center, and the recognition unit 2 in the control center classifies garbage in the image data based on the garbage classification model to confirm the garbage type. Meanwhile, the image acquisition area is provided with a weighing unit 6 for weighing the garbage and uploading the weight of the garbage to the control center. The queuing garbage can data of the collection road junction, the garbage can data expected to arrive at the collection road junction and the fault condition of the collection road junction are taken as the basis of scheduling calculation. And calculating the most suitable road junction collecting scheduling scheme by using a load balancing algorithm. Finally, based on a scheduling scheme, a sorter, an auxiliary collecting device and the like at the collecting crossing are actually controlled through a PLC (programmable logic controller) at the collecting crossing to cooperate with different garbage collection.

The existing hospital garbage collection mode is that when garbage is sent, garbage is classified and boxed, then classified through a manual marking classification mode, then bound with the box number of a garbage transmission box, finally weighed through a manual mode, and then garbage weight information is recorded into a system. Each collecting road mouth needs to be provided with a code scanning device for identifying the box number, when garbage is sorted to the collecting road mouth, whether the road mouth is full in a queuing way is judged once before each garbage enters the road mouth, and if the road mouth is full, the garbage is sent to the next road mouth. However, the AI identification and scheduling are introduced in the garbage sorting process, the type of garbage can be automatically identified, and the automatic scheduling sorting is completed by combining the flow of each road junction and the equipment loading state through a load balancing algorithm to issue instructions, so that the cost is greatly saved, the sorting efficiency is improved, and the type of garbage loading for each bearing container is not needed to be manually selected. In addition, automatic weighing is added, weighing data of garbage in each bin can be automatically recorded, manual weighing is not needed, the garbage sorting device is added in a sorting link, and after a plurality of road ports are only required to be subjected to one-time code scanning identification and AI identification, a household instruction issuing is carried out by combining the flow of each road port and the equipment loading state, so that the cost is saved, and the sorting efficiency is optimized.

On the basis of the garbage sorting device, the scheme further provides a garbage sorting method. As shown in fig. 2, the method includes:

Step S201, garbage image data of a target area are collected;

Step S202, identifying the garbage type in the garbage image data based on a pre-constructed garbage classification and identification model to obtain the garbage type in the target area;

Step S203, collecting garbage of corresponding types according to the scheduling instruction.

In this scheme, the step of obtaining the scheduling instruction includes: acquiring at least one of the current garbage collection queuing quantity, the garbage quantity to be collected, the state data of a collection road junction and the garbage weight to collect state information; calculating a scheduling scheme of each garbage sent to the sorting unit 3 based on a load balancing algorithm by using the collection state information; and generating a scheduling instruction for collecting and scheduling garbage according to the scheduling scheme.

In the prior art, image data is input for medical waste (later called medical waste) types which need artificial intelligence detection, model training is carried out, cover opening detection is carried out on a container box filled with medical waste in a medical waste dumping and discarding treatment link, the artificial intelligence carries out identification judgment on medical waste forms in the container, and if an empty box or a box cover is not opened, a warning prompt is given; if medical waste with non-compliance discarding is identified, the medical waste is not allowed to be dumped, for example, if a syringe with a needle is identified, the dumping process is not allowed, and a warning prompt is given. However, the scheme is that the garbage in the bag and the transmission box filled with medical wastes is automatically identified through image acquisition and AI detection and identification, and is sorted to the corresponding dumping treatment crossing for collection treatment. Medical waste is generally classified into four types. Medical waste is manually classified and bagged in a department, different types of medical waste bags are different, the medical waste bags are placed in boxes and are transmitted to a total collecting area through a lifter and a horizontal line, weighing records are carried out on the medical waste bags of each box in the area, the types of the medical waste bags in the conveying boxes are identified by using AI, and after the types are identified, the system can send the medical waste boxes to corresponding sorting material pouring ports and pour the medical waste bags into a larger garbage compartment, and the compartment is pulled to a treatment plant by a vehicle to be destroyed. In the process of sending out the material pouring opening, the equipment state and the flow of the material pouring opening can be judged, and the effect of balancing the loads of all the wire bodies is achieved.

As shown in fig. 3 and fig. 4, the present solution is further described by taking a specific process of garbage sorting as an example.

As shown in fig. 3, medical waste is generated in a hospital department, and generally divided into four types: pathological, damaging, pharmaceutical, chemical; the system can carry out image input on the packaging bag filled with medical wastes as a training sample, and determines training characteristics according to the operations of sample size, pixelation, characteristic extraction and the like. And then, training and evaluating through the classification model to obtain the garbage classification model.

After medical wastes are generated in a hospital department, the wastes can be classified, bagged and boxed to form a transmission box carrying the garbage bags. And (3) placing the transmission box carrying the medical waste garbage bags at a lifting machine station, and lifting the opportunity to send the transmission box of the medical waste garbage bags to a medical waste classified collection temporary storage station, namely an image collection area. In the process that the medical waste box is sent to the temporary storage station, weighing is firstly carried out when the medical waste box reaches the horizontal line of the temporary storage station, and weighing information is recorded by the system. Then, the camera shoots images of the medical waste garbage bags in the box, and the type of garbage is identified through the garbage classification model to determine the medical waste garbage bags. A comparison and identification mode of garbage classification can be as follows: the medical waste category in the inventory box is the category corresponding to the model with the highest similarity, and the comparison probability algorithm adopts the model with the highest entropy:

h (P) = - Σxp (x) log P (x), where x is a discrete random variable and P (x) is a probability distribution.

As shown in fig. 4, after identifying the type of medical waste, the system matches two crossing (2 pouring openings are set for each type of medical waste) to be poured, determines the fault condition of the matched 2 crossing devices, and finally obtains the target pouring opening according to the load balancing method according to the respective flow condition on the 2 lines: loading the matched medical waste pouring port of the type into d i ctLane structures comprises l aneCode (crossing code), boxCount (the number of the garbage can is being processed by the crossing), l aneStatus (the crossing equipment state); according to the traffic flow load balancing algorithm, the crossing with the abnormal equipment state is eliminated firstly, and then the sequence is carried out according to the number of boxes being processed, and the formula is as follows:

d i ctLane＝d i ctLane.OrderBy(o＝>o.Va l ue).ThenByDescend i ng(p＝>p.boxCount).ToD i ct i onary(o＝>o.Key,p＝>

p.Va l ue).Where(p＝>p.Status<>’bad’)；

taking the crossing with the minimum task number: l aneCode = d i ctlane.e l ementAt (0) Key.

The medical waste garbage transmission box reaches the target material pouring port to pour materials, and the empty box after material pouring is cleaned by the cleaning machine and is sent back to the material pouring department by the lifting machine. The material pouring and collecting carriage can be pulled up by an automobile through a direct hooking arm of the automobile to be transported to a medical waste treatment company for treatment; the medical waste system can check medical waste collection information, including information of a department, medical waste type, medical waste weight, treatment time and the like.

On the basis of the garbage sorting method embodiment, the scheme further provides a computer readable storage medium. The computer readable storage medium is a program product for implementing the garbage sorting method described above, which may employ a portable compact disc read-only memory (CD-ROM) and comprise program code, and may be run on a device, such as a personal computer. However, the program product of the present aspect is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable storage 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.

Program code for carrying out operations of the present scheme may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

On the basis of the garbage sorting method, the scheme further provides electronic equipment. The electronic device shown in fig. 5 is only an example, and should not impose any limitation on the functions and the scope of use of the embodiment of the present invention.

As shown in fig. 5, the electronic device 301 is in the form of a general purpose computing device. Components of electronic device 301 may include, but are not limited to: at least one memory unit 302, at least one processing unit 303, a display unit 304 and a bus 305 for connecting the different system components.

Wherein the storage unit 302 stores program code that is executable by the processing unit 303 such that the processing unit 303 performs the steps of the various exemplary embodiments described in the garbage sorting method described above. For example, the processing unit 303 may perform the steps as shown in fig. 2.

The memory unit 302 may include volatile memory units, such as Random Access Memory (RAM) and/or cache memory units, and may further include Read Only Memory (ROM).

The storage unit 302 may also include programs/utilities having program modules including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.

Bus 305 may include a data bus, an address bus, and a control bus.

The electronic device 301 may also communicate with one or more external devices 307 (e.g., keyboard, pointing device, bluetooth device, etc.) via an input/output (I/O) interface 306. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 301, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

It should be understood that the foregoing examples of the present invention are provided merely for clearly illustrating the present invention and are not intended to limit the embodiments of the present invention, and that various other changes and modifications may be made therein by one skilled in the art without departing from the spirit and scope of the present invention as defined by the appended claims.

Claims (10)

1. A waste sorting apparatus, the apparatus comprising:

The garbage image acquisition unit acquires garbage image data of a target area;

the identifying unit is used for identifying the garbage type in the garbage image data to obtain the garbage type in the target area;

and the sorting unit is used for collecting garbage of corresponding types according to the scheduling instruction.

2. The trash sorting device according to claim 1, characterized in that the collection unit comprises: at least one image acquisition device arranged at a predetermined position on the garbage transmission line.

3. The waste sorting device of claim 1, characterized in that it comprises: the scheduling unit generates scheduling instructions according to the current collection state of the sorting unit.

4. A waste sorting device according to claim 3, wherein the scheduling unit comprises:

The acquisition module acquires at least one of the current garbage collection queuing quantity, the garbage quantity to be collected, the state data of a collection road junction and the garbage weight to collect state information;

The calculation module is used for calculating a scheduling scheme of each garbage sent to the sorting unit based on a load balancing algorithm by utilizing the collected state information;

and the scheduling module is used for generating scheduling instructions for collecting and scheduling garbage according to the scheduling scheme.

5. The waste sorting device of claim 3 or 4, wherein the sorting unit comprises a plurality of waste collection gates;

And the garbage collection road junction collects garbage of corresponding types according to the scheduling instruction.

6. The waste sorting device of claim 1, characterized in that it comprises: and the weighing unit is used for weighing the garbage to be collected to obtain the weight data of the garbage.

7. The waste sorting device of claim 5, wherein the device comprises: and the fault monitoring unit is used for monitoring the state of each garbage collection road junction in the sorting unit to obtain road junction state data.

8. The trash sorting device according to claim 1, wherein the identifying unit identifies the trash type in the trash image data by using a trash classification identifying model constructed in advance, to obtain the trash type in the target area.

9. A method of sorting waste, the method comprising the steps of:

Collecting garbage image data of a target area;

Based on a pre-constructed garbage classification and identification model, identifying garbage types in the garbage image data to obtain the garbage types in the target area;

and collecting garbage of corresponding types according to the scheduling instruction.

10. The method of trash sorting according to claim 9, characterized in that the step of acquiring scheduling instructions comprises:

acquiring at least one of the current garbage collection queuing quantity, the garbage quantity to be collected, the state data of a collection road junction and the garbage weight to collect state information;

Calculating a scheduling scheme of each garbage sent to the sorting unit based on a load balancing algorithm by utilizing the collection state information;

and generating a scheduling instruction for collecting and scheduling garbage according to the scheduling scheme.