CN110929693A - Intelligent garbage classification method and system - Google Patents
Intelligent garbage classification method and system Download PDFInfo
- Publication number
- CN110929693A CN110929693A CN201911272663.8A CN201911272663A CN110929693A CN 110929693 A CN110929693 A CN 110929693A CN 201911272663 A CN201911272663 A CN 201911272663A CN 110929693 A CN110929693 A CN 110929693A
- Authority
- CN
- China
- Prior art keywords
- garbage
- information
- thrown
- server
- classification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000010813 municipal solid waste Substances 0.000 title claims abstract description 428
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004064 recycling Methods 0.000 claims abstract description 44
- 238000004891 communication Methods 0.000 claims abstract description 40
- 238000011084 recovery Methods 0.000 claims abstract description 26
- 230000008569 process Effects 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims description 49
- 238000012549 training Methods 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 14
- 238000010586 diagram Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 4
- 239000002699 waste material Substances 0.000 claims 1
- 238000012423 maintenance Methods 0.000 abstract description 4
- 230000002349 favourable effect Effects 0.000 abstract description 2
- 238000005070 sampling Methods 0.000 description 6
- 238000013459 approach Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000977 initiatory effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Educational Administration (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an intelligent garbage classification method and system.A user acquires garbage information to be thrown through a mobile intelligent terminal, the mobile intelligent terminal is provided with a client, and the client sends user identification information and the garbage information to be thrown to a server; the server identifies and processes the garbage information to be put in, obtains garbage classification information, and sends the garbage classification information to the corresponding client according to the user identification information; when garbage to be thrown is thrown into the garbage recycling device, the mobile intelligent terminal sends a communication establishment request to the garbage recycling device, wherein the communication establishment request carries garbage classification information; the garbage recycling device identifies garbage classification information and controls the classification device to place the garbage to be thrown into the accommodating areas of the corresponding categories. The user can also accomplish the categorised recovery of rubbish under client and rubbish recovery unit help even do not know rubbish classification knowledge, and rubbish recovery unit structure is more simplified, puts in and the maintenance cost is lower, is favorable to using widely on a large scale.
Description
Technical Field
The invention relates to the technical field of garbage classification, in particular to an intelligent garbage classification method and system.
Background
Along with the rapid development of economy, the daily garbage generated by people is increased day by day, the garbage classification can reduce the garbage treatment amount and treatment equipment, reduce the treatment cost and reduce the consumption of land resources, has social, economic and ecological benefits, is an important measure for improving human living environment, promoting fine city management and guaranteeing sustainable development, and forcibly performs garbage classification in some major cities in China.
In the prior art, various garbage recycling devices capable of realizing automatic classification exist, for example, garbage cans capable of realizing automatic classification based on image recognition, the working principle of the garbage cans is that when a resident puts garbage into the garbage can, a shooting device is adopted to collect garbage images, the garbage images are recognized based on the image recognition technology to judge the garbage types, and the garbage cans are put into corresponding garbage cans according to the image recognition result, but in order to facilitate the resident to throw the garbage, the garbage cans are generally arranged in public places, the resident generally packs the garbage and then takes the garbage can to throw the garbage, and the garbage cans based on the image recognition are difficult to recognize the garbage types wrapped in plastic bags or other packages, so that the classification effect is poor; partial rubbish recovery unit then requires the resident to paste label or two-dimensional code that shows its classification on the rubbish wrapping bag after the packing, scan label or two-dimensional code through the scanner in the garbage bin and classify after, this type of device then has higher requirement to the rubbish classification knowledge level that the resident mastered, and complex operation, it is inconvenient to use, above-mentioned mode all requires garbage bin itself to have image acquisition in addition, discernment, automatic classification, functions such as remote communication, lead to this type of garbage bin structure complicacy, input and maintenance cost height.
Disclosure of Invention
The invention aims to provide an intelligent garbage classification method and system, and aims to solve the problems that a garbage recovery device in the prior art is poor in classification effect, complex in overall structure and high in investment and maintenance cost.
The invention provides an intelligent garbage classification method in a first aspect, which comprises the following steps:
a user collects information of garbage to be thrown in through a mobile intelligent terminal, the mobile intelligent terminal is provided with a client side, and the client side sends user identification information and the information of the garbage to be thrown in to a server;
the server identifies and processes the garbage information to be put in, obtains garbage classification information, and sends the garbage classification information to the corresponding client according to the user identification information;
when garbage to be thrown is thrown into the garbage recycling device, a client sends a communication establishment request to the garbage recycling device, wherein the communication establishment request carries garbage classification information;
the garbage recycling device identifies garbage classification information and controls the classification device to place the garbage to be thrown into the accommodating areas of the corresponding categories.
Further, after the garbage recycling device puts the garbage to be thrown into the accommodating area of the corresponding category, the garbage recycling device sends the garbage recycling device identification information, the accommodating information and the throwing success identification information to the mobile intelligent terminal, and the client sends the garbage recycling device identification information, the accommodating information and the throwing success identification information to the server.
Further, the user gathers through mobile intelligent terminal and waits to put in the rubbish information, specifically includes:
collecting a garbage image to be thrown in, identifying the garbage image to be thrown in by a client, and judging whether the garbage image to be thrown in is matched with a historical analysis image or not;
if the images of the garbage to be thrown are matched with the historical analysis images, the client side obtains garbage classification information corresponding to the matched historical analysis images;
if the garbage image to be thrown is not matched with the historical analysis image, the client sends the user identification information and the garbage information to be thrown to the server for recognition processing, stores the garbage image to be thrown into the historical analysis image library, and establishes a mapping relation between the garbage classification information and the corresponding image after the server feeds back the garbage classification information.
Further, the server identifies and processes the garbage information to be thrown in, and obtains garbage classification information, which specifically includes:
performing feature extraction on the garbage image to be thrown in through a first preset network to output a feature map;
and identifying the feature map through a second preset network, judging the matching degree of the feature map and the training sample, classifying the training sample into a plurality of categories according to garbage classification, and outputting garbage classification information of the corresponding category if the matching degree is higher than a preset threshold value.
Further, after the server sends the garbage classification information to the client according to the user identification information, the user can feed back whether the garbage classification is accurate through the client, the client sends the feedback information to the server, and when the server identifies that the feedback information is accurate, the corresponding garbage image to be thrown is added into the training sample of the corresponding category; and when the feedback information is identified to be inaccurate in garbage classification, counting the feedback times of the feedback information through a counter, and retraining the training samples of the corresponding classes when the feedback times exceed a preset threshold value.
A second aspect of the present invention provides an intelligent garbage classification system for implementing the method of the first aspect, including:
the system comprises a mobile intelligent terminal, a server and a communication recovery device, wherein the mobile intelligent terminal is used for acquiring garbage information to be thrown in, is provided with a client, and is used for sending user identification information and the garbage information to be thrown in to the server and sending a communication establishment request to the garbage recovery device, wherein the communication establishment request carries garbage classification information;
the server is used for identifying and processing the garbage information to be thrown in, acquiring garbage classification information and sending the garbage classification information to the corresponding client according to the user identification information;
garbage recycling device, including the device body, this internal master control module, sorter and a plurality of holding are regional to be equipped with of device, the holding is regional to be used for accomodating different types of rubbish, master control module is used for discerning rubbish classification information, controls sorter and will treat that the holding of putting into corresponding classification is regional.
The garbage recycling device further comprises a first communication module, wherein the first communication module is used for sending the identification information of the garbage recycling device, the containing information and the successful throwing identification information to the mobile intelligent terminal after the garbage to be thrown is put into the containing areas of the corresponding categories; the client further comprises a second communication module used for sending the received identification information of the garbage recycling device, the receiving information and the successful delivery identification information to the server.
Further, the client includes:
the first identification module is used for identifying the garbage image to be thrown, which is acquired by the mobile intelligent terminal, and judging whether the garbage image to be thrown is matched with the historical analysis image or not;
the acquisition submodule is used for acquiring the garbage classification information corresponding to the matched historical analysis image when the garbage image to be thrown is matched with the historical analysis image;
the sending submodule is used for sending the user identification information and the garbage information to be thrown to a server for recognition processing when the garbage image to be thrown is not matched with the historical analysis image, and storing the garbage image to be thrown into a historical analysis image library;
and the historical analysis image library is used for storing historical garbage images to be thrown in and establishing a mapping relation between the garbage classification information and the corresponding historical garbage images to be thrown in after the server feeds back the garbage classification information.
Further, the server includes:
the first preset network is used for extracting the features of the garbage image to be thrown in and outputting a feature map;
and the second preset network is used for identifying the characteristic diagram, judging the matching degree of the characteristic diagram and the training sample, classifying the training sample into a plurality of categories according to garbage classification, and outputting garbage classification information of the corresponding category when the matching degree is higher than a preset threshold value.
Further, the client is also provided with a feedback submodule for sending feedback information to the server after the client receives the garbage classification information sent by the server so as to feed back whether the garbage classification information is accurate or not,
the server is also provided with a second identification module for identifying the feedback information, and when the feedback information is accurate in garbage classification, the corresponding garbage image to be thrown is added into the training sample of the corresponding category; and when the feedback information is that the garbage classification is not accurate, counting the feedback times of the feedback information through a counter, and retraining the training samples of the corresponding categories when the feedback times exceed a preset threshold value.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides an intelligent garbage classification method and system, before throwing garbage, a user collects the garbage information to be thrown in through a mobile intelligent terminal, a client uploads the garbage information to be thrown in to a server for identification and analysis, and feeds back the garbage classification information to the client, when the user packs the garbage and approaches the garbage recycling device, the mobile intelligent terminal automatically sends a communication establishment request carrying the garbage classification information to the garbage recycling device, the garbage recycling device can directly put the garbage into a corresponding accommodating area according to the garbage classification information to realize classification, by the invention, the user can complete the classification and recovery of the garbage with the assistance of the client and the garbage recovery device even if the user does not know the garbage classification knowledge, and the garbage recycling device is simpler in structure, lower in putting and maintaining cost and beneficial to large-scale popularization and use.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is apparent that the drawings in the following description are only preferred embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without inventive efforts.
Fig. 1 is a schematic overall flow chart of an intelligent garbage classification method according to an embodiment of the present invention.
Fig. 2 is a schematic view of a collection process of spam to be delivered according to another embodiment of the present invention.
Fig. 3 is a schematic flow chart of identifying and processing spam to be delivered by a server according to another embodiment of the present invention.
Fig. 4 is a schematic diagram of the overall structure of the intelligent garbage classification system according to another embodiment of the present invention.
Fig. 5 is a schematic structural diagram of a garbage recycling device according to another embodiment of the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, the illustrated embodiments are provided to illustrate the invention and not to limit the scope of the invention.
Fig. 1 is a schematic overall flow chart of an intelligent garbage classification method according to an embodiment of the present invention. The mobile intelligent terminal in the method can be a smart phone, a tablet computer, intelligent wearable equipment and other equipment, and the server can be a computer, a server and other equipment.
As shown in fig. 1, the intelligent garbage classification method includes the following steps:
s11, the user collects the information of the garbage to be thrown in through the mobile intelligent terminal, the mobile intelligent terminal is provided with a client, and the client sends the user identification information and the information of the garbage to be thrown in to the server.
The information of the garbage to be thrown in can be images of the garbage to be thrown in collected by a user through a mobile intelligent terminal, and can also be description information of the type of the garbage to be thrown in input by the user through the mobile intelligent terminal, for example, the garbage to be thrown in is vegetable leaves, shells, clothes, electronic equipment, plastic bottles and the like. The to-be-released spam information is input into a client running in the mobile intelligent terminal, and the client sends the user identification information and the to-be-released spam information to the server through the wireless network.
In addition, the user identification information is unique identification information of a user corresponding to the mobile intelligent terminal. In some embodiments, the user identification information may be an identification code, and the client may perform a pre-operation on the user identification information before sending the user identification information to the server, where the pre-operation may be to encrypt the user identification information, to reorder the user identification information according to a preset algorithm, or to perform other processing on the user identification information.
And S12, the server identifies the garbage information to be thrown in, obtains garbage classification information, and sends the garbage classification information to the corresponding client according to the user identification information.
In the step, after receiving the to-be-thrown garbage information and the user identification information sent by the client, the server firstly identifies the to-be-thrown garbage information, and searches the corresponding garbage classification information according to the content of the to-be-thrown garbage information after identifying the garbage classification represented by the to-be-thrown garbage information, wherein the garbage classification information is used for describing which garbage classification the to-be-thrown garbage belongs to. And then, the server sends the garbage classification information to the user corresponding to the client according to the user identification information.
In some embodiments, after receiving the user identification information, the server performs a post operation on the user identification information subjected to the pre-operation, where the post operation corresponds to the pre-operation, and may be to decrypt the user identification information, or to restore the user identification information sequence according to a preset algorithm, or to perform other operations on the user identification information.
In addition, after the client receives the garbage classification information, the client can prompt the user that the garbage identification and classification are finished through the mobile intelligent terminal in a mode of displaying pictures, texts, sounds and the like, or mark the garbage information to be thrown to indicate classification categories corresponding to various garbage, and display the garbage classification information to the user through a human-computer interface, so that the user can know and learn the garbage classification knowledge conveniently.
And S13, when the garbage to be thrown in is thrown into the garbage collection device, the client sends a communication establishment request to the garbage collection device, wherein the communication establishment request carries the garbage classification information.
After the client receives the garbage classification information, the user can pack the garbage, and the garbage of different classifications can be separately packed according to the garbage classification information so as to be convenient for recycling. When a user carries garbage and approaches to the garbage recycling device, a client running on the mobile intelligent terminal sends a communication establishment request carrying garbage classification information to the garbage recycling device, when the garbage recycling device receives the communication establishment request sent by the client, the communication is established with the client, and meanwhile, the garbage recycling device opens a throwing port so that the user can conveniently throw the packaged garbage into the garbage recycling device. When the user leaves the garbage recycling device after completing garbage throwing, the communication between the client and the garbage recycling device can be automatically disconnected, and when the garbage recycling device is not communicated with any equipment, the throwing port is automatically closed.
In some embodiments, the client and the garbage recycling device can communicate with each other through Bluetooth, the maximum connection distance of the Bluetooth is set to be 10 meters, and as long as a user carries a mobile intelligent terminal and approaches the garbage recycling device within 10 meters, the client automatically sends a communication establishment request to the garbage recycling device; when the user leaves the rubbish recovery unit for more than 10 meters, the communication between the client and the rubbish recovery unit is automatically disconnected, the user does not need to manually operate the mobile intelligent terminal or the rubbish recovery unit in the whole rubbish throwing process, and only needs to put rubbish into the rubbish throwing port after the rubbish recovery unit is opened, so that the operation is very simple and convenient, and the user does not need to contact with the rubbish recovery unit, so that good sanitary feeling is brought to the user. In other embodiments, the client and the garbage collection device may communicate with each other through other short-range communication methods.
And S14, identifying the garbage classification information by the garbage recovery device, and controlling the classification device to place the garbage to be thrown into the accommodating areas of the corresponding categories.
In this embodiment, the garbage collection device identifies the garbage classification information carried in the communication establishment request sent by the client, and determines which classification the garbage to be thrown by the user belongs to according to the garbage classification information, and when the user throws the garbage into the throwing port, the garbage collection device controls the built-in classification device to throw the garbage thrown by the user into the accommodating area of the corresponding classification.
The garbage recycling device is provided with a plurality of accommodating areas, and each accommodating area corresponds to one garbage classification category and is used for accommodating garbage of the corresponding classification category.
In some embodiments, when the garbage collection device recognizes that the garbage classification information carried by the communication establishment request includes a plurality of garbage classification categories, it indicates that the user needs to put in garbage of a plurality of different classification categories, the garbage collection device may prompt the user to put in garbage of which category first through a built-in audio player, and after completing the category storage of the garbage put in advance through the control classification device, the garbage collection device prompts the user to continue to put in garbage of other categories through the audio player until completing the prompt of all garbage classification categories included in the garbage classification information.
By adopting the intelligent garbage classification method provided by the embodiment, even if the user does not know the garbage classification knowledge deeply enough, the user can acquire the garbage information to be thrown in through the mobile intelligent terminal in advance at home, the client uploads the garbage information to be thrown in to the server for identification, the server acquires the corresponding garbage classification information through identifying the garbage information to be thrown in and feeds back the corresponding garbage classification information to the user corresponding to the client, the user can classify and pack the garbage to be thrown in according to the fed-back garbage classification information and carry the garbage to be thrown in to the garbage recycling device, so that the garbage recycling device only needs to classify and store the garbage thrown in the user according to the garbage classification information sent by the client during throwing, on one hand, the garbage to be thrown in advance can be acquired through the mobile intelligent terminal which is quite popular at present and has stronger camera shooting function, and the server can better identify the garbage, the classification accuracy rate improves, and on the other hand makes rubbish recovery unit structure further simplify, reduces and puts in earlier stage and later maintenance cost, is favorable to using widely on a large scale.
Optionally, in the foregoing embodiment, after placing the to-be-dropped garbage into the accommodating area of the corresponding category, the garbage collection device sends the garbage collection device identification information, the accommodating information, and the successful-dropping identification information to the mobile intelligent terminal, and the client sends the garbage collection device identification information, the accommodating information, and the successful-dropping identification information to the server.
The garbage collection device identification information is used as a unique identification of each garbage collection device, and the containing information is used for describing whether the garbage contained in the garbage collection device reaches an upper limit or not. The server stores an identification information list of all garbage recovery devices in advance, and the identification information list stores identification information of all garbage recovery devices, corresponding position information and accommodating information. And after receiving the identification information of the garbage recovery device, the containing information and the successful putting identification information sent by the client, the server searches an identification information list according to the identification information of the garbage recovery device and updates the corresponding containing information. The server periodically checks the containing information of all the garbage recovery devices in the identification information list, and if the garbage recovery devices which contain garbage or are about to reach the upper limit are found, the position information of the garbage recovery devices is extracted and sent to a worker to prompt the worker to go to the place where the garbage recovery devices are located as soon as possible to recover the garbage. The successful garbage throwing mark information comprises user identification information used for counting the times of successfully throwing garbage by each user, and users with higher times of successfully throwing garbage can be rewarded to improve the enthusiasm of the users.
Fig. 2 is a schematic view of a collection process of spam to be delivered according to another embodiment of the present invention.
As shown in fig. 2, on the basis of the foregoing embodiment, the user acquires spam information to be delivered through the mobile intelligent terminal, which specifically includes the following steps:
and S21, collecting the garbage image to be thrown in, identifying the garbage image to be thrown in by the client, and judging whether the garbage image to be thrown in is matched with the historical analysis image.
In this embodiment, when the user selects the mode of collecting the spam image as the spam information to be delivered, the client identifies the spam image to be delivered first, so as to judge whether further identification is needed by the server according to the matching degree of the spam image to be delivered and the historical analysis image. The historical analysis image is a garbage image which is stored in a historical analysis image library and is collected by a user in the past. And the matching degree of the image of the garbage to be thrown in and the historical analysis image is judged by calculating the matching rate of the image of the garbage to be thrown in and the historical analysis image.
And S22, if the garbage image to be thrown is matched with the historical analysis image, the client acquires the garbage classification information corresponding to the matched historical analysis image.
When the matching rate of the image of the garbage to be thrown in and the historical analysis image reaches or exceeds a preset matching rate threshold value, the image of the garbage to be thrown in is matched with the historical analysis image, and the situation that the garbage which needs to be thrown away by a user at this time is the same as the garbage which is thrown away before is shown, the client does not send the information of the garbage to be thrown in to the server any more, but directly obtains the garbage classification information corresponding to the matched historical analysis image from the historical analysis image library, so that the situation that the user needs to identify through the server every time the image of the garbage to be thrown in is collected by the user is avoided, and the load of the server.
And S23, if the garbage image to be thrown is not matched with the historical analysis image, the client sends the user identification information and the garbage information to be thrown to the server for recognition processing, stores the garbage image to be thrown into the historical analysis image library, and establishes the mapping relation between the garbage classification information and the corresponding image after the server feeds back the garbage classification information.
And when the matching rate of the garbage image to be thrown and the historical analysis image does not reach a preset matching rate threshold value, the garbage image to be thrown and the historical analysis image are not matched. And the client stores the acquired garbage image to be thrown into the historical analysis image library as a historical analysis image. When the server feeds back the garbage classification information to the client, the historical analysis image library establishes a mapping relation between the garbage images to be thrown and the garbage classification information, which are stored in the library at this time, so as to be used for next recognition and matching.
Fig. 3 is a schematic flow chart of identifying and processing spam to be delivered by a server according to another embodiment of the present invention.
As shown in fig. 3, on the basis of the first embodiment, the server performs identification processing on spam to be delivered to obtain spam classification information, and specifically includes the following steps:
and S31, performing feature extraction on the garbage image to be thrown in through a first preset network and outputting a feature map.
In some embodiments, the first preset network may adopt a ResNet neural network model, an Xception neural network model, or a neural network model with another structure.
And S32, identifying the feature map through a second preset network, judging the matching degree of the feature map and the training sample, classifying the training sample into a plurality of categories according to garbage classification, and outputting garbage classification information of the corresponding category if the matching degree is higher than a preset threshold value.
In some embodiments, the second predetermined network may be implemented by an FPN network, where the FPN network includes a pre-computation module from a bottom layer to a top layer and a high-level feature sampling module from a top layer to a bottom layer, and the pre-computation module and the high-level feature sampling module are connected by a convolution kernel. The pre-calculation module is used for calculating the feature level of the feature map, the high-level feature sampling module is used for sampling the high-resolution feature map to obtain the features of the feature map, and the high-level feature sampling module is connected with the pre-calculation module through a convolution kernel to enhance the features obtained by sampling, so that the identification accuracy is improved. And the second preset network judges which garbage classification category the garbage to be thrown into belongs to by comparing the similarity of the characteristic graph and training samples of different categories, obtains corresponding garbage classification information, and feeds the corresponding garbage classification information back to the client according to the user identification information.
Optionally, after the server sends the garbage classification information to the client according to the user identification information, the user can feed back whether the garbage classification is accurate through the client, the client sends the feedback information to the server, and when the server identifies that the feedback information is accurate, the server adds the corresponding garbage image to be thrown into the training sample of the corresponding category; when the feedback information is recognized to be inaccurate in garbage classification, the feedback times of the feedback information are counted through the counter, when the feedback times exceed a preset threshold value, the training samples of corresponding categories are retrained, so that the server can dynamically adjust the training samples according to the feedback of the user, the recognition accuracy is guaranteed, and the training samples can be adjusted only when the feedback of the user is accumulated to a certain degree, so that the training samples are prevented from being maliciously interfered, and the recognition accuracy is reduced.
Based on the same inventive concept as the previous embodiment, another embodiment of the present invention provides an intelligent garbage classification system.
As shown in fig. 4, in this embodiment, the system includes a mobile intelligent terminal 1, a server 2, and a garbage collection apparatus 3.
The mobile intelligent terminal 1 is used for collecting garbage information to be thrown in, the mobile intelligent terminal 1 is provided with a client 4, the client 4 is used for sending user identification information and the garbage information to be thrown in to the server 2, and is also used for sending a communication establishment request to the garbage recycling device 3, and the communication establishment request carries garbage classification information.
The server 2 is used for identifying and processing the garbage information to be thrown in, acquiring garbage classification information and sending the garbage classification information to the corresponding client 4 according to the user identification information;
garbage recycling device 3, including the device body, this internal master control module, sorter and a plurality of holding area of being equipped with of device, the holding is regional to be used for accomodating different types of rubbish, master control module is used for discerning rubbish classification information, controls sorter and will treat to put into in rubbish and put into the holding of corresponding classification in the region.
Fig. 5 is a schematic view of the overall structure of the garbage recycling device provided in this embodiment. As shown in fig. 5, the garbage recycling device 3 includes a device body 31, a feeding opening 32 is provided at a left end of a top of the device body 31, and a first sensor is provided at the feeding opening 32 for detecting whether garbage is fed. The inside sorter that is equipped with of device body 31, sorter includes electronic pivot 33, the left and right lateral wall of device body 31 is connected respectively at the both ends of electronic pivot 33, is provided with conveyer belt 34 on the electronic pivot 33, the initiating terminal of conveyer belt 34 is located puts in mouthful 32 below for can fall the initiating terminal of conveyer belt 34 from putting in the rubbish of putting in mouthful 32 department and putting in, its end is located the right-hand member of device body 31. A plurality of barrel bodies 35 serving as accommodating regions are arranged below one side of the electric rotating shaft 33, and the upper end of each barrel body 35 is open and used for accommodating different types of garbage. The electric rotating shaft 33 and the conveyor belt 34 are controlled by a main control module 36, the first sensor is electrically connected with the main control module 36, the main control module 36 communicates with the mobile intelligent terminal through wireless communication, and the main control module 36 can be realized by an industrial personal computer.
Under initial condition, conveyer belt 34 is horizontal gesture and motionless, receive the rubbish classification information that the client sent through wireless communication when main control module 36, and when first sensor detected that there is rubbish to put into, main control module 36 at first controls conveyer belt 34 and rotates, transport rubbish and deposit the staving 35 top back conveyer belt 34 stall of corresponding classification rubbish, electronic pivot 33 is behind conveyer belt 34 stall, rotate toward the one side that is arranged with staving 35, make conveyer belt 34 slope, rubbish falls into corresponding staving 35, electronic pivot 33 rethread rotates conveyer belt 34 to horizontal position afterwards.
In some embodiments, a second sensor is disposed inside the barrel 35 near the opening at the upper end, and the second sensor is electrically connected to the main control module 36 for detecting whether the barrel 35 can further store garbage.
Optionally, the garbage collection device 3 further includes a first communication module, where the first communication module is configured to send the garbage collection device identification information, the containing information, and the successful garbage collection device identification information to the mobile intelligent terminal 1 after the garbage to be thrown is placed in the containing area of the corresponding category; the client 4 further includes a second communication module, configured to send the received identifier information of the garbage collection device, the receiving information, and the identifier information of the successful placement to the server 2.
Optionally, the client 4 includes a first recognition module, an obtaining sub-module, a sending sub-module, and a historical analysis image library.
The first identification module is used for identifying a to-be-thrown garbage image acquired by the mobile intelligent terminal and judging whether the to-be-thrown garbage image is matched with a historical analysis image or not;
the acquisition submodule is used for acquiring the garbage classification information corresponding to the matched historical analysis image when the garbage image to be thrown is matched with the historical analysis image;
the sending submodule is used for sending the user identification information and the garbage information to be thrown to a server for recognition processing when the garbage image to be thrown is not matched with the historical analysis image, and storing the garbage image to be thrown into a historical analysis image library;
the historical analysis image library is used for storing historical garbage images to be thrown in and establishing a mapping relation between the garbage classification information and the corresponding historical garbage images to be thrown in after the server feeds back the garbage classification information.
Optionally, the server 2 includes a first preset network and a second preset network,
the first preset network is used for performing feature extraction on the garbage image to be thrown in and outputting a feature map;
the second preset network is used for identifying the characteristic diagram, judging the matching degree of the characteristic diagram and the training sample, dividing the training sample into a plurality of categories according to garbage classification, and outputting garbage classification information of the corresponding category when the matching degree is higher than a preset threshold value.
Optionally, the client is further provided with a feedback sub-module, configured to send feedback information to the server after the client receives the garbage classification information sent by the server to feed back whether the garbage classification information is accurate,
the server is also provided with a second identification module for identifying the feedback information, and when the feedback information is accurate in garbage classification, the corresponding garbage image to be thrown is added into the training sample of the corresponding category; and when the feedback information is that the garbage classification is not accurate, counting the feedback times of the feedback information through a counter, and retraining the training samples of the corresponding categories when the feedback times exceed a preset threshold value.
The intelligent garbage classification system is used for executing the method embodiments, and the implementation principle and the technical effect of the intelligent garbage classification system can refer to the method embodiments, which are not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. An intelligent garbage classification method is characterized by comprising the following steps:
a user collects information of garbage to be thrown in through a mobile intelligent terminal, the mobile intelligent terminal is provided with a client side, and the client side sends user identification information and the information of the garbage to be thrown in to a server;
the server identifies and processes the garbage information to be put in, obtains garbage classification information, and sends the garbage classification information to the corresponding client according to the user identification information;
when garbage to be thrown is thrown into the garbage recycling device, a client sends a communication establishment request to the garbage recycling device, wherein the communication establishment request carries garbage classification information;
the garbage recycling device identifies garbage classification information and controls the classification device to place the garbage to be thrown into the accommodating areas of the corresponding categories.
2. The intelligent garbage classification method according to claim 1, wherein the garbage collection device sends garbage collection device identification information, collection information and successful delivery identification information to the mobile intelligent terminal after placing the garbage to be delivered into the collection area of the corresponding category, and the client sends the garbage collection device identification information, collection information and successful delivery identification information to the server.
3. The intelligent garbage classification method according to claim 1, wherein the user collects the garbage information to be thrown through a mobile intelligent terminal, and the method specifically comprises the following steps:
collecting a garbage image to be thrown in, identifying the garbage image to be thrown in by a client, and judging whether the garbage image to be thrown in is matched with a historical analysis image or not;
if the images of the garbage to be thrown are matched with the historical analysis images, the client side obtains garbage classification information corresponding to the matched historical analysis images;
if the garbage image to be thrown is not matched with the historical analysis image, the client sends the user identification information and the garbage information to be thrown to the server for recognition processing, stores the garbage image to be thrown into the historical analysis image library, and establishes a mapping relation between the garbage classification information and the corresponding image after the server feeds back the garbage classification information.
4. The intelligent garbage classification method according to claim 1, wherein the server performs recognition processing on the garbage information to be delivered to obtain the garbage classification information, and specifically comprises:
performing feature extraction on the garbage image to be thrown in through a first preset network to output a feature map;
and identifying the feature map through a second preset network, judging the matching degree of the feature map and the training sample, classifying the training sample into a plurality of categories according to garbage classification, and outputting garbage classification information of the corresponding category if the matching degree is higher than a preset threshold value.
5. The intelligent garbage classification method according to claim 4, characterized in that after the server sends garbage classification information to the client according to the user identification information, the user can feed back whether the garbage classification is accurate through the client, the client sends the feedback information to the server, and when the server recognizes that the feedback information is accurate, the server adds the corresponding garbage image to be thrown into the training sample of the corresponding category; and when the feedback information is identified to be inaccurate in garbage classification, counting the feedback times of the feedback information through a counter, and retraining the training samples of the corresponding classes when the feedback times exceed a preset threshold value.
6. An intelligent waste classification system, the system comprising:
the system comprises a mobile intelligent terminal, a server and a communication recovery device, wherein the mobile intelligent terminal is used for acquiring garbage information to be thrown in, is provided with a client, and is used for sending user identification information and the garbage information to be thrown in to the server and sending a communication establishment request to the garbage recovery device, wherein the communication establishment request carries garbage classification information;
the server is used for identifying and processing the garbage information to be thrown in, acquiring garbage classification information and sending the garbage classification information to the corresponding client according to the user identification information;
garbage recycling device, including the device body, this internal master control module, sorter and a plurality of holding are regional to be equipped with of device, the holding is regional to be used for accomodating different types of rubbish, master control module is used for discerning rubbish classification information, controls sorter and will treat that the holding of putting into corresponding classification is regional.
7. The intelligent garbage classification system according to claim 6, wherein the garbage collection device further comprises a first communication module, and the first communication module is configured to send the garbage collection device identification information, the containing information, and the successful garbage collection device identification information to the mobile intelligent terminal after the garbage to be thrown is placed in the containing area of the corresponding category; the client further comprises a second communication module used for sending the received identification information of the garbage recycling device, the receiving information and the successful delivery identification information to the server.
8. The intelligent garbage classification system of claim 6, wherein the client comprises:
the first identification module is used for identifying the garbage image to be thrown, which is acquired by the mobile intelligent terminal, and judging whether the garbage image to be thrown is matched with the historical analysis image or not;
the acquisition submodule is used for acquiring the garbage classification information corresponding to the matched historical analysis image when the garbage image to be thrown is matched with the historical analysis image;
the sending submodule is used for sending the user identification information and the garbage information to be thrown to a server for recognition processing when the garbage image to be thrown is not matched with the historical analysis image, and storing the garbage image to be thrown into a historical analysis image library;
and the historical analysis image library is used for storing historical garbage images to be thrown in and establishing a mapping relation between the garbage classification information and the corresponding historical garbage images to be thrown in after the server feeds back the garbage classification information.
9. The intelligent garbage classification system of claim 6, wherein the server comprises:
the first preset network is used for extracting the features of the garbage image to be thrown in and outputting a feature map;
and the second preset network is used for identifying the characteristic diagram, judging the matching degree of the characteristic diagram and the training sample, classifying the training sample into a plurality of categories according to garbage classification, and outputting garbage classification information of the corresponding category when the matching degree is higher than a preset threshold value.
10. The intelligent garbage classification system of claim 9, wherein the client is further provided with a feedback sub-module for sending feedback information to the server after the client receives the garbage classification information sent by the server to feed back whether the garbage classification information is accurate or not,
the server is also provided with a second identification module for identifying the feedback information, and when the feedback information is accurate in garbage classification, the corresponding garbage image to be thrown is added into the training sample of the corresponding category; and when the feedback information is that the garbage classification is not accurate, counting the feedback times of the feedback information through a counter, and retraining the training samples of the corresponding categories when the feedback times exceed a preset threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911272663.8A CN110929693A (en) | 2019-12-12 | 2019-12-12 | Intelligent garbage classification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911272663.8A CN110929693A (en) | 2019-12-12 | 2019-12-12 | Intelligent garbage classification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110929693A true CN110929693A (en) | 2020-03-27 |
Family
ID=69859143
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911272663.8A Pending CN110929693A (en) | 2019-12-12 | 2019-12-12 | Intelligent garbage classification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110929693A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112348447A (en) * | 2020-11-30 | 2021-02-09 | 王俊杰 | Intelligent recovery bin-dividing compression control method and system based on data analysis |
| CN112591333A (en) * | 2020-12-11 | 2021-04-02 | 江西理工大学 | Automatic garbage classification device and method based on artificial intelligence |
| CN112620165A (en) * | 2020-12-11 | 2021-04-09 | 江西理工大学 | Garbage classification method |
| CN112758552A (en) * | 2021-01-11 | 2021-05-07 | 江苏地风环卫有限公司 | Intelligent garbage collection system and collection method thereof |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103394499A (en) * | 2013-07-27 | 2013-11-20 | 邱泽国 | Automatic classified collection and direct regeneration engineering for full-automatic garbage standard classification pipelines |
| CN103440607A (en) * | 2013-08-09 | 2013-12-11 | 杭州朗盾科技有限公司 | Service platform and method for classifying and intelligently recycling waste and old materials and garbage |
| CN105096451A (en) * | 2015-06-25 | 2015-11-25 | 英华达（上海）科技有限公司 | Resource recovery and classification system |
| CN106022980A (en) * | 2016-05-16 | 2016-10-12 | 深圳市德立信环境工程有限公司 | Garbage dumping and recycling system |
| CN206580119U (en) * | 2017-02-21 | 2017-10-24 | 厦门大学嘉庚学院 | Home automation garbage classification device |
| US20180065155A1 (en) * | 2015-12-16 | 2018-03-08 | Waste Repurposing International, Inc. | Waste Recovery Systems and Methods |
| CN107983755A (en) * | 2017-12-28 | 2018-05-04 | 朱子昕 | Refuse classification method and retrospective printing bar code system of the bar code for core |
| CN108665616A (en) * | 2018-05-15 | 2018-10-16 | 刘晓东 | A kind of recovery method and retracting device of rubbish |
| CN109147159A (en) * | 2018-07-26 | 2019-01-04 | 珠海市云筒环保科技有限公司 | A kind of environmental-protection box terminal and control method |
| CN109703943A (en) * | 2019-03-06 | 2019-05-03 | 北京鼎恒泰科技有限公司 | Rubbish recovering method, client and garbage recycling bin |
| CN110092112A (en) * | 2019-05-28 | 2019-08-06 | 中国联合网络通信集团有限公司 | Garbage classification management method, platform and dustbin equipment |
| CN110217511A (en) * | 2019-05-31 | 2019-09-10 | 广州普慧环保科技股份有限公司 | Duct type separate waste collection system and its application method |
| CN110428352A (en) * | 2019-08-09 | 2019-11-08 | 绵阳德川鸿丰环保科技有限公司 | The method and modularization garbage classification system of wearable device intelligent classification rubbish |
| CN110482080A (en) * | 2019-09-23 | 2019-11-22 | 北京迈奥腾科技有限公司 | The method, apparatus of garbage reclamation and the equipment for applying it |
| CN110489489A (en) * | 2019-08-21 | 2019-11-22 | 腾讯科技（深圳）有限公司 | A kind of method and relevant apparatus of object classification |
| CN110490246A (en) * | 2019-08-15 | 2019-11-22 | 中云信安（深圳）科技有限公司 | Rubbish classification determines method, apparatus, storage medium and electronic equipment |
| CN110516768A (en) * | 2019-08-29 | 2019-11-29 | 中新智擎科技有限公司 | A kind of method, apparatus and artificial intelligence robot of garbage classification management |
-
2019
- 2019-12-12 CN CN201911272663.8A patent/CN110929693A/en active Pending
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103394499A (en) * | 2013-07-27 | 2013-11-20 | 邱泽国 | Automatic classified collection and direct regeneration engineering for full-automatic garbage standard classification pipelines |
| CN103440607A (en) * | 2013-08-09 | 2013-12-11 | 杭州朗盾科技有限公司 | Service platform and method for classifying and intelligently recycling waste and old materials and garbage |
| CN105096451A (en) * | 2015-06-25 | 2015-11-25 | 英华达（上海）科技有限公司 | Resource recovery and classification system |
| TW201701228A (en) * | 2015-06-25 | 2017-01-01 | 英華達股份有限公司 | Recycling classification system |
| US20180065155A1 (en) * | 2015-12-16 | 2018-03-08 | Waste Repurposing International, Inc. | Waste Recovery Systems and Methods |
| CN106022980A (en) * | 2016-05-16 | 2016-10-12 | 深圳市德立信环境工程有限公司 | Garbage dumping and recycling system |
| CN206580119U (en) * | 2017-02-21 | 2017-10-24 | 厦门大学嘉庚学院 | Home automation garbage classification device |
| CN107983755A (en) * | 2017-12-28 | 2018-05-04 | 朱子昕 | Refuse classification method and retrospective printing bar code system of the bar code for core |
| CN108665616A (en) * | 2018-05-15 | 2018-10-16 | 刘晓东 | A kind of recovery method and retracting device of rubbish |
| CN109147159A (en) * | 2018-07-26 | 2019-01-04 | 珠海市云筒环保科技有限公司 | A kind of environmental-protection box terminal and control method |
| CN109703943A (en) * | 2019-03-06 | 2019-05-03 | 北京鼎恒泰科技有限公司 | Rubbish recovering method, client and garbage recycling bin |
| CN110092112A (en) * | 2019-05-28 | 2019-08-06 | 中国联合网络通信集团有限公司 | Garbage classification management method, platform and dustbin equipment |
| CN110217511A (en) * | 2019-05-31 | 2019-09-10 | 广州普慧环保科技股份有限公司 | Duct type separate waste collection system and its application method |
| CN110428352A (en) * | 2019-08-09 | 2019-11-08 | 绵阳德川鸿丰环保科技有限公司 | The method and modularization garbage classification system of wearable device intelligent classification rubbish |
| CN110490246A (en) * | 2019-08-15 | 2019-11-22 | 中云信安（深圳）科技有限公司 | Rubbish classification determines method, apparatus, storage medium and electronic equipment |
| CN110489489A (en) * | 2019-08-21 | 2019-11-22 | 腾讯科技（深圳）有限公司 | A kind of method and relevant apparatus of object classification |
| CN110516768A (en) * | 2019-08-29 | 2019-11-29 | 中新智擎科技有限公司 | A kind of method, apparatus and artificial intelligence robot of garbage classification management |
| CN110482080A (en) * | 2019-09-23 | 2019-11-22 | 北京迈奥腾科技有限公司 | The method, apparatus of garbage reclamation and the equipment for applying it |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112348447A (en) * | 2020-11-30 | 2021-02-09 | 王俊杰 | Intelligent recovery bin-dividing compression control method and system based on data analysis |
| CN112591333A (en) * | 2020-12-11 | 2021-04-02 | 江西理工大学 | Automatic garbage classification device and method based on artificial intelligence |
| CN112620165A (en) * | 2020-12-11 | 2021-04-09 | 江西理工大学 | Garbage classification method |
| CN112758552A (en) * | 2021-01-11 | 2021-05-07 | 江苏地风环卫有限公司 | Intelligent garbage collection system and collection method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110929693A (en) | Intelligent garbage classification method and system | |
| CN109201514B (en) | Waste sorting recycle method, garbage classification device and classified-refuse recovery system | |
| CN110294236A (en) | A kind of garbage classification monitoring apparatus, method and server system | |
| CN110428352B (en) | Intelligent garbage classification method for wearable equipment and modularized garbage classification system | |
| CN110087193A (en) | Information uploading method, device, electronic equipment and the readable storage medium storing program for executing of dustbin | |
| CN206546593U (en) | House refuse intelligent classification reclaims cloud identifying system | |
| CN113158956A (en) | Garbage detection and identification method based on improved yolov5 network | |
| CN111661508B (en) | Intelligent garbage classification recycling device based on interaction of Internet and Internet of things | |
| CN208326334U (en) | A kind of intelligent classification case based on two-dimensional barcode information identification | |
| CN108877083A (en) | Intelligent takeaway box system based on neural network recognization | |
| CN114275416B (en) | Kitchen waste classification method, device, equipment and medium based on image recognition | |
| CN111680650A (en) | Garbage classification recycling excitation method and system | |
| CN111907959A (en) | Intelligent garbage recycling system based on artificial intelligence and big data technology | |
| CN111099205A (en) | Intelligent garbage classification method and system based on AI technology | |
| CN113128397A (en) | Garbage classification throwing monitoring method, system and device and storage medium | |
| CN110838202A (en) | Method, system and device for rewarding delivery of dry garbage | |
| CN116682098A (en) | Automatic urban household garbage identification and classification system and method | |
| KR20210074929A (en) | deep learning based garbage distribution system | |
| CN113371363A (en) | Classified garbage can, intelligent classified garbage can based on deep learning and classification method | |
| CN209922092U (en) | Material recycling bin capable of automatically identifying human face and garbage types | |
| CN214297580U (en) | Intelligent garbage recognition and classification device based on internet | |
| CN111977214A (en) | Intelligent garbage classification throwing station capable of being remotely and manually monitored and using method thereof | |
| CN111661509B (en) | Garbage recycling and classifying management system based on interaction of Internet and Internet of things | |
| CN111422527A (en) | Categorised recovery plant of double-deck cutlery box | |
| CN217576626U (en) | Classification garbage can |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20240419 |
|
| AD01 | Patent right deemed abandoned |