CN111222949A - Community waste resource sharing method and system based on deep learning - Google Patents
Community waste resource sharing method and system based on deep learning Download PDFInfo
- Publication number
- CN111222949A CN111222949A CN202010006331.1A CN202010006331A CN111222949A CN 111222949 A CN111222949 A CN 111222949A CN 202010006331 A CN202010006331 A CN 202010006331A CN 111222949 A CN111222949 A CN 111222949A
- Authority
- CN
- China
- Prior art keywords
- waste
- user
- article
- condition
- waste material
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0645—Rental transactions; Leasing transactions
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
- G07F17/0042—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for hiring of objects
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F7/00—Mechanisms actuated by objects other than coins to free or to actuate vending, hiring, coin or paper currency dispensing or refunding apparatus
- G07F7/06—Mechanisms actuated by objects other than coins to free or to actuate vending, hiring, coin or paper currency dispensing or refunding apparatus by returnable containers, i.e. reverse vending systems in which a user is rewarded for returning a container that serves as a token of value, e.g. bottles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F7/00—Mechanisms actuated by objects other than coins to free or to actuate vending, hiring, coin or paper currency dispensing or refunding apparatus
- G07F7/06—Mechanisms actuated by objects other than coins to free or to actuate vending, hiring, coin or paper currency dispensing or refunding apparatus by returnable containers, i.e. reverse vending systems in which a user is rewarded for returning a container that serves as a token of value, e.g. bottles
- G07F7/0609—Mechanisms actuated by objects other than coins to free or to actuate vending, hiring, coin or paper currency dispensing or refunding apparatus by returnable containers, i.e. reverse vending systems in which a user is rewarded for returning a container that serves as a token of value, e.g. bottles by fluid containers, e.g. bottles, cups, gas containers
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F7/00—Mechanisms actuated by objects other than coins to free or to actuate vending, hiring, coin or paper currency dispensing or refunding apparatus
- G07F7/06—Mechanisms actuated by objects other than coins to free or to actuate vending, hiring, coin or paper currency dispensing or refunding apparatus by returnable containers, i.e. reverse vending systems in which a user is rewarded for returning a container that serves as a token of value, e.g. bottles
- G07F7/069—Mechanisms actuated by objects other than coins to free or to actuate vending, hiring, coin or paper currency dispensing or refunding apparatus by returnable containers, i.e. reverse vending systems in which a user is rewarded for returning a container that serves as a token of value, e.g. bottles by box-like containers, e.g. videocassettes, books
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Molecular Biology (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a community waste resource sharing method based on deep learning, which comprises a waste material type selection step, a waste material image acquisition step, a waste material condition detection step and a waste material identification step, wherein the waste material type selection step selects a waste material type, the waste material image acquisition step acquires an image of the waste material, the waste material condition detection step detects the condition of the waste material when the waste material image is judged to be in accordance with the waste material type in the waste material type verification step, and the waste material type selection step supplements other information of the waste material; controlling the opening of the branch box in the waste throwing control step; and the waste data sharing step is used for matching the waste for the user and sending the description data of the waste to a mobile phone or a computer terminal of the user. The invention realizes the cyclic utilization of the matching of the waste and old materials and the user requirements; the deep learning technology is used for detecting the condition of the waste, and description data is imported into the system by combining with other information of the waste so as to match the requirements of the user, so that the forward guidance of the cyclic application is formed for the user.
Description
Technical Field
The invention relates to the technical field of resource sharing, in particular to a community waste resource sharing method and system based on deep learning.
Background
With the improvement of the consumption level of people, particularly the rise of new modes such as online shopping and takeaway, the waste and old matters generated in the life of people are increased day by day, so that the resource and environmental pressure are increased, and a large load is brought to the garbage storage and clearing work of communities.
At present, a lot of wastes all have cyclic utilization's value, for example express delivery packing carton, old clothing, plastic bottle and old electronic product etc. though there is the chain that waste classification retrieved and recycled, this cyclic process is long, need pass through many intermediate links, not only is unfavorable for the waste's quick digestion and recycle, has also caused the waste of middle transportation, letter sorting and processing cost. In addition, the configuration required in the circulation process is difficult to meet the requirements of high efficiency and economy, for example, a solid paper box can be used as express package for repeated use, and a plurality of new solid paper boxes serving as waste paper in the current garbage recycling process are directly crushed, pulped and used for papermaking again in the subsequent treatment process; electronic products such as chargers, earphones, toys and the like which are eliminated due to product updating do not have faults, can be completely continuously used, but are directly used for electronic garbage treatment, so that the electronic garbage treatment method has the advantages that not only is the best use of the products avoided, but also the subsequent harmless treatment is difficult; it can be seen that the existing garbage classification and recycling does not achieve the most economical and efficient recycling application mode, which is a great waste.
In conclusion, the invention provides a method and a system for sharing community waste resources based on deep learning, which can realize nearby shared utilization of waste articles such as express packaging cartons, old clothes, plastic bottles and old electronic products in the community range, accelerate the circulation speed of the waste articles and reduce unnecessary intermediate links; and a cyclic utilization mode which is more accurate and efficient and is more matched with the condition of the waste and the user requirement is realized.
Disclosure of Invention
Objects of the invention
In order to overcome at least one defect in the prior art, the invention provides a method and a system for sharing the waste resources of the community based on deep learning, which can realize the nearby sharing and utilization of the waste in the community range; a more accurate and efficient cyclic utilization mode which is more matched with the condition of the waste and the user requirement can be realized; the condition detection of the waste can be realized by applying a deep learning technology, the description data of the waste is imported into the system by combining the input information of the waste, so that the resource requirements of the user are matched, and forward incentive guidance of waste cyclic application is formed for the user.
(II) technical scheme
As a first aspect of the invention, the invention discloses a community waste resource sharing method based on deep learning, which comprises the following steps:
selecting waste articles, namely selecting input waste articles and displaying and guiding a user to execute a waste image acquisition step; when the waste article type verification step judges that the types of the waste articles collected in the waste article image collection step are not consistent with the waste article types selected to be input and put, error reporting is carried out; prompting the user to supplement other information of the waste when the waste condition detection step detects the condition of the waste;
a waste image acquisition step, wherein the waste is subjected to image acquisition;
a waste article type verifying step of judging whether the types of the waste articles collected in the waste article image collecting step are consistent with the waste articles selected in the waste article type selecting step, if so, executing the waste article condition detecting step, and if not, executing error reporting through the waste article type selecting step;
a waste condition detection step of detecting the external condition of the waste according to the image acquired in the waste image acquisition step to detect the condition of the waste;
a waste material throwing control step of controlling corresponding boxes to open the box covers thereof, throwing the waste materials and executing a waste material data generation step according to the detection result of the waste material condition detection step and the information supplemented by the user in the waste material class selection step;
a waste data generation step of generating description data of the waste according to the image acquired in the waste image acquisition step, the detection result of the waste condition detection step, and the information supplemented by the user in the waste class selection step;
the Internet of things communication step, namely uploading the description data to the waste sharing step;
and a waste sharing step, namely matching the waste meeting the user requirements for the user according to the waste and the description data retrieved by the user by utilizing a mobile phone or a computer terminal, and sending the description data corresponding to the waste to the mobile phone or the computer terminal.
In one possible embodiment, the discarded article type selection step selects the discarded article type by inputting a personal community account and a password or logging in by face recognition.
In a possible embodiment, the step of verifying the used article class includes: a plurality of deeply learned convolutional neural network models; and the deep learning convolutional neural network model identifies the types of the waste through the images acquired in the waste image acquisition step.
In one possible embodiment, the step of detecting the condition of the used article calls the convolutional neural network model corresponding to the used article class when the step of verifying the used article class judges that the used article class collected in the step of collecting the used article image matches the used article class selected in the step of selecting the used article class, so as to detect the external condition of the used article according to the convolutional neural network model corresponding to the used article class.
In one possible embodiment, the junk sharing step adds a credit corresponding to the credit to the user according to the junk type and the status of the junk put by the user; the points are redeemed by the user for the junk.
As a second aspect of the present invention, the present invention discloses a deep learning-based community waste resource sharing system, which includes:
the touch display is used for selecting and inputting the thrown waste and old articles and displaying and guiding the user to display the waste and old articles in front of the camera; when the waste article type verification module judges that the types of the waste articles collected by the camera are inconsistent with the waste article types selected and input to be released, error reporting is executed; when the condition of the waste is detected by a waste condition detection module, prompting the user to supplement other information of the waste;
the camera is used for acquiring images of the waste;
the arithmetic processor includes: the waste article type verification module and the waste article condition detection module; the used article type verification module is used for judging whether the types of the used articles collected by the camera are consistent with the used article types selected by the touch display, if so, the used article condition detection module is executed, and if not, an error is reported through the touch display; the waste condition detection module is used for detecting the external condition of the waste according to the image acquired by the camera so as to detect the condition of the waste;
the shared cabinet control interface is used for controlling corresponding boxes to open the box covers of the shared cabinet according to the detection result of the waste object condition detection module and the information supplemented by the user in the touch display, throwing the waste objects and executing a waste object data generation module;
the arithmetic processor further includes: the junk data generation module is used for generating description data of the junk according to the image acquired by the camera, the detection result of the junk condition detection module and the information supplemented by the user in the touch display;
the Internet of things communication module is used for uploading the description data to a background server;
and the background server is used for matching the obsolete materials meeting the user requirements for the user according to the obsolete materials and the description data retrieved by the user by using a mobile phone or a computer terminal, and sending the description data corresponding to the obsolete materials to the mobile phone or the computer terminal.
In a possible implementation, the touch display is configured to select the discarded article class to be delivered by inputting a personal community account and a password or logging in by face recognition.
In one possible embodiment, the used article class verification module includes: a plurality of deeply learned convolutional neural network models; and the deep learning convolutional neural network model is used for identifying the categories of the waste materials through the images collected by the camera.
In a possible embodiment, the used article condition detecting module is configured to, when the used article type verifying module determines that the type of the used article collected by the camera matches the used article type selected in the touch display, call the convolutional neural network model corresponding to the used article type, so as to perform external condition detection on the used article according to the convolutional neural network model corresponding to the used article type.
In a possible implementation manner, the background server is configured to add a credit corresponding to a credit to the user according to the type of the obsolete goods released by the user and the condition of the obsolete goods; the points are redeemed by the user for the junk.
(III) advantageous effects
The invention provides a community waste resource sharing method and system based on deep learning, wherein waste materials are selected and input through a waste material selection step, images of the waste materials are acquired through a waste material image acquisition step, a waste material verification step is used for judging whether the images of the waste materials are consistent with the waste materials selected and input, if not, error reporting is carried out through the waste material selection step, if so, the waste material condition detection step is used for detecting the condition of the waste materials according to the images of the waste materials, and the waste material selection step is used for supplementing other information of the waste materials; at this time, the waste throwing control step may control the corresponding box separation to open the box cover according to the condition of the waste and other information of the waste and throw the waste; the method comprises the steps of generating waste data, uploading the description data to a waste sharing step through an internet of things communication step, matching the waste meeting user requirements for a user according to the waste retrieved by the user and the description data, and sending the description data corresponding to the waste to a mobile phone or a computer terminal of the user. The community can not only realize the nearby sharing and utilization of the waste in the community range, but also realize a more accurate and efficient cyclic utilization mode which is more matched with the conditions of the waste and the user requirements; in addition, the condition detection of the waste is realized by applying a deep learning technology, and the description data of the waste is imported into the system by combining with other information of the waste so as to match the resource requirement of the user, thereby forming forward incentive guidance of the waste cyclic application for the user.
Drawings
The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining and illustrating the present invention and should not be construed as limiting the scope of the present invention.
Fig. 1 is a flowchart of a community waste resource sharing method based on deep learning according to the present invention.
Fig. 2 is a schematic structural diagram of a community waste resource sharing system based on deep learning provided by the invention.
Detailed Description
In order to make the implementation objects, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be described in more detail below with reference to the accompanying drawings in the embodiments of the present invention.
It should be noted that: in the drawings, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described are some embodiments of the present invention, not all embodiments, and features in embodiments and embodiments in the present application may be combined with each other without conflict. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like are used in the orientation or positional relationship indicated in the drawings, which are used for convenience in describing the invention and for simplicity in description, and are not intended to indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and are not to be considered limiting of the scope of the invention.
The first embodiment of the community waste resource sharing method based on deep learning provided by the invention is described in detail below with reference to fig. 1. As shown in fig. 1, the method for sharing community waste resources provided in this embodiment mainly includes: the method comprises the steps of selecting waste articles, collecting images of the waste articles, verifying the waste articles, detecting the conditions of the waste articles, putting and controlling the waste articles, generating waste article data, communicating the Internet of things and sharing the waste articles. The waste articles can be paper boxes, waste clothes, plastic bottles, electronic products and the like; the invention can continuously use the self-solid usable paper box as express package, and use the damaged unusable paper box as waste paper for recycling; and old electronic products without damage and faults can be continuously put into use instead of being treated as electronic garbage. The invention can set up the waste resource sharing cabinet in the appropriate place of the community (such as the entrance and exit of the community), and carry out the method through the background server in the form of full-flow self-service, thereby realizing the recycling and sharing of the waste resources for the residents of the community in a low operation cost, convenient and fast way. The using process of the waste resource sharing cabinet can comprise a waste article type selecting step, a waste article image collecting step, a waste article type verifying step, a waste article condition detecting step, a waste article data generating step, a waste article putting control step and an internet of things communication step.
Selecting waste articles, namely selecting input waste articles and displaying and guiding a user to execute a waste image acquisition step; when the waste article type verification step judges that the types of the waste articles collected in the waste article image collection step are not consistent with the waste article types selected to be input and put, error reporting is carried out; and prompting the user to supplement other information of the waste when the waste condition detection step detects the condition of the waste.
In the waste item class selection step, the user may directly select a waste item class of waste items to be released through a menu displayed on the touch display, where the waste item class may include: cartons, old clothes, plastic bottles, electronic products, and the like; the user can also select various conventional sizes of the waste in a next grade menu; when the user selects the waste article as an electronic product, the user can select the waste article as an earphone, a charger, a toy or the like in a next-level article menu. After the user finishes selecting the waste articles, the waste article selection step can guide the user to display the waste articles by displaying a guide instruction through the touch display, so that the waste article image acquisition step can acquire the images of the waste articles.
The step of selecting the waste and old articles can be used for performing error reporting through the touch display when the step of verifying the waste and old articles selected and input by the user is verified to be incorrect, and at the moment, the user can also reselect the corresponding waste and old articles. When the condition of the waste is detected in the waste condition detection step, the touch display can also display a further menu to prompt the user to supplement other information of the waste; the other information of the waste can be whether the electronic product can be normally used, an interface matched with a charger and an earphone, and the like.
A waste image acquisition step, wherein the waste is subjected to image acquisition; in the waste image collection step, image collection can be performed on each side of the carton displayed by the user, and image collection can be performed on the front side, the back side, the inside and the like of the old clothes displayed by the user.
A waste article type verifying step of judging whether the types of the waste articles collected in the waste article image collecting step are consistent with the waste articles selected in the waste article type selecting step, if so, executing the waste article condition detecting step, and if not, executing error reporting through the waste article type selecting step; the waste article type verifying step can judge whether the waste article types selected and input by the user are correct or not according to the collected images of the waste articles, such that the error is reported through the waste article type selecting step when the waste article types selected and input by the user are incorrect.
A waste condition detection step of detecting the external condition of the waste according to the image acquired in the waste image acquisition step to detect the condition of the waste; in the step of detecting the waste condition, the external condition of the waste can be detected according to the image of the waste so as to judge the integrity, cleanliness and the like of the waste and further judge whether the waste can be reused. The waste external condition detecting step may further include: a humidity sensor, etc., by which the humidity of the used waste can be judged in an intact state. When the waste to be put into the cabinet by the user is the waste which can not be used or stored continuously in a wet state such as a paper box and old clothes, the user can use a humidity sensor arranged on the waste resource sharing cabinet to detect whether the waste is affected with damp or not.
The condition of the carton can be divided into a carton with good condition and capable of being recycled and a carton which is damaged or wetted and can not be recycled; the conditions of the old clothes can comprise the old clothes with good conditions and can be recycled, and the old clothes with damaged stains and can not be recycled; the condition of the plastic bottles can be divided into plastic bottles with high complete cleanliness and reusability and plastic bottles with dirty and non-recyclable property; the status of electronic products can be classified into electronic products that have good status and can be used continuously and electronic products that have been damaged and cannot be used continuously.
A waste material throwing control step of controlling corresponding boxes to open the box covers thereof, throwing the waste materials and executing a waste material data generation step according to the detection result of the waste material condition detection step and the information supplemented by the user in the waste material class selection step; corresponding recycling boxes can be arranged on the waste resource sharing cabinet for waste materials of different waste material types, and the recycling boxes can comprise a paper box recycling box, a waste clothes recycling box, a plastic bottle recycling box, an electronic product recycling box and the like; the recycling boxes of the same waste article type can be provided with different boxes according to different conditions of the waste articles, for example, the carton recycling boxes can be divided into carton boxes with good conditions and can be recycled, and carton boxes which are damaged or cannot be recycled after being affected with damp; the old clothes recycling box can comprise a clothes branch box which is good in condition and can be recycled, and a clothes branch box which is damaged and polluted and can not be recycled; the plastic bottle recycling box can be divided into a bottle body sub-box which is complete, high in cleanliness and capable of being recycled and a bottle body sub-box which is dirty and incapable of being recycled; the electronic product recycling bin can be divided into an electronic product recycling bin which has good product condition and can be used continuously and an electronic product recycling bin which is damaged and can not be used continuously.
A waste data generation step of generating description data of the waste according to the image acquired in the waste image acquisition step, the detection result of the waste condition detection step, and the information supplemented by the user in the waste class selection step; in the junk data generation step, for junk that can be reused, description data of the junk is generated. The description data can include the waste article class of the waste article, the condition of the waste article, the image of the waste article, the position of the waste resource sharing cabinet where the waste article is located, the box division of the waste resource sharing cabinet, the grid number and the like.
The Internet of things communication step, namely uploading the description data to the waste sharing step;
and a waste sharing step, namely matching the waste meeting the user requirements for the user according to the waste and the description data retrieved by the user by utilizing a mobile phone or a computer terminal, and sending the description data corresponding to the waste to the mobile phone or the computer terminal. In the waste sharing step, a user can connect to a background server by using a mobile phone or a computer terminal; the user can search the waste needed by the user by using the mobile phone or the computer terminal, for example, the user can input the waste class of the waste needed, then the background server matches the waste which is closest to the user position and meets the user requirement according to the description data, and sends the waste resource sharing cabinet position corresponding to the waste, the sub-box of the waste resource sharing cabinet position, the grid number and the like to the mobile phone or the computer terminal of the user.
When the user is an enterprise (such as an express delivery company and a plastic recycling enterprise) specialized in recycling of waste, the user can go to each waste resource sharing cabinet periodically to pick up the required waste.
And the waste and old article type selection step is to select the released waste and old article type by inputting a personal community account and a password or logging in by face recognition. The user can operate the touch display to input the personal community account and the personal password to log in or log in by face recognition, and the user can select the waste article type of the waste article to be released through the menu after logging in successfully. The face or personal community account number and the password of each user correspond to a unique ID, so that the discarded object put by each user can be recorded and monitored conveniently.
The method comprises the following steps of: a plurality of deeply learned convolutional neural network models; and the deep learning convolutional neural network model identifies the types of the waste through the images acquired in the waste image acquisition step. In the step of verifying the waste and old articles, each convolutional neural network model is trained through a large sample of each waste and old article, so as to obtain the trained convolutional neural network model, wherein the convolutional neural network model can be a paper box model or a plastic bottle model.
And a waste article type verifying step, namely judging whether the image of the waste article collected in the waste article image collecting step is matched with a convolutional neural network model, if so, indicating that the type of the waste article collected in the waste article image collecting step corresponds to the convolutional neural network model, and the waste article type corresponding to the convolutional neural network model is the type of the waste article, so that whether the type of the waste article is consistent with the waste article type selected by the user in the waste article type selecting step can be judged.
And a waste condition detection step of calling the convolutional neural network model corresponding to the waste image when the waste image is judged to be consistent with the waste selected in the waste image selection step in the waste image verification step, so as to detect the external condition of the waste according to the convolutional neural network model corresponding to the waste. For example, when the waste article verifying step verifies that the image of the waste article matches the carton model, the waste article condition detecting step detects the external condition of the waste article according to the image of the waste article in a carton detecting manner, and determines whether the carton to be put by the user is complete or not, and whether the carton is affected with damp and deformed or not. When the waste article type verification step verifies that the image of the waste article is consistent with the plastic bottle model, the waste article condition detection step detects the external condition of the waste article according to the image of the waste article in a plastic bottle detection mode, and judges the cleanliness of the plastic bottle and the like; the plastic bottle mold may include: when the image of the waste plastic object is consistent with a certain plastic bottle model, the appearance (color and the like) of the plastic bottle corresponding to the plastic bottle model can be known, and then the color of the plastic bottle is judged by comparing the image of the waste plastic object with the appearance of the plastic bottle corresponding to the plastic bottle model, and the cleanliness of the plastic bottle is known.
Wherein, the waste sharing step adds the integral of the corresponding credit for the user according to the waste type and the condition of the waste put by the user; the points are redeemed by the user for the junk. When the waste articles of the waste articles thrown by the user are cartons and the conditions of the waste articles are good in conditions and can be recycled, the user can obtain points, so that the user can exchange the cartons for the points when the cartons need to be used next time.
Selecting input waste materials by a waste material type selection step, carrying out image acquisition on the waste materials by a waste material image acquisition step, judging whether the images of the waste materials are consistent with the waste materials selected and input by a waste material type verification step, if not, carrying out error reporting by the waste material type selection step, if so, detecting the conditions of the waste materials by a waste material condition detection step according to the images of the waste materials, and supplementing other information of the waste materials by the waste material type selection step; at this time, the waste throwing control step may control the corresponding box separation to open the box cover according to the condition of the waste and other information of the waste and throw the waste; the method comprises the steps of generating waste data, uploading the description data to a waste sharing step through an internet of things communication step, matching the waste meeting user requirements for a user according to the waste retrieved by the user and the description data, and sending the description data corresponding to the waste to a mobile phone or a computer terminal of the user. The method for sharing the community waste resources based on deep learning can realize nearby sharing and utilization of the waste in the community range, accelerate the circulation speed of the waste and reduce unnecessary intermediate links; a more accurate and efficient cyclic utilization mode which is more matched with the condition of the waste and the user requirement can be realized; the condition detection of the waste can be realized by applying a deep learning technology, the description data of the waste is imported into the system by combining with other information of the waste, so that the resource requirements of the user are matched, and the forward incentive guidance of the waste cyclic application is formed for the user.
The following describes a first embodiment of the community waste resource sharing system based on deep learning in detail with reference to fig. 2. As shown in fig. 2, the community waste resource sharing system provided in this embodiment mainly includes: the system comprises a touch display, a camera, an old and useless article type verification module, an old and useless article condition detection module, a shared cabinet control interface, an old and useless article data generation module, an Internet of things communication module and a background server.
The touch display is used for selecting and inputting the thrown waste and old articles and displaying and guiding the user to display the waste and old articles in front of the camera; when the waste article type verification module judges that the types of the waste articles collected by the camera are inconsistent with the waste article types selected and input to be released, error reporting is executed; when the condition of the waste is detected by a waste condition detection module, prompting the user to supplement other information of the waste;
the camera is used for acquiring images of the waste;
the arithmetic processor includes: the waste article type verification module and the waste article condition detection module; the used article type verification module is used for judging whether the types of the used articles collected by the camera are consistent with the used article types selected by the touch display, if so, the used article condition detection module is executed, and if not, an error is reported through the touch display; the waste condition detection module is used for detecting the external condition of the waste according to the image acquired by the camera so as to detect the condition of the waste;
the shared cabinet control interface is used for controlling corresponding boxes to open the box covers of the shared cabinet according to the detection result of the waste object condition detection module and the information supplemented by the user in the touch display, throwing the waste objects and executing a waste object data generation module;
the arithmetic processor further includes: the junk data generation module is used for generating description data of the junk according to the image acquired by the camera, the detection result of the junk condition detection module and the information supplemented by the user in the touch display;
the Internet of things communication module is used for uploading the description data to a background server;
and the background server is used for matching the obsolete materials meeting the user requirements for the user according to the obsolete materials and the description data retrieved by the user by using a mobile phone or a computer terminal, and sending the description data corresponding to the obsolete materials to the mobile phone or the computer terminal.
The touch display is used for inputting a personal community account and a password or logging in by face recognition, so that the thrown-in waste article class is selected.
Wherein the used article class verification module comprises: a plurality of deeply learned convolutional neural network models; and the deep learning convolutional neural network model is used for identifying the categories of the waste materials through the images collected by the camera.
The waste article condition detection module is configured to, when the waste article type verification module determines that the types of the waste articles collected by the camera are consistent with the waste article type selected in the touch display, call the convolutional neural network model corresponding to the waste article type, so as to perform external condition detection on the waste articles according to the convolutional neural network model corresponding to the waste article type.
The background server is used for adding points of corresponding lines for the user according to the waste article types put by the user and the conditions of the waste articles; the points are redeemed by the user for the junk.
According to the invention, the touch display is used for selecting and inputting thrown-in waste articles, the camera is used for collecting images of the waste articles, the waste article verification module is used for judging whether the images of the waste articles are consistent with the waste articles selected and input, if not, the error reporting is carried out through the touch display, if so, the waste article condition detection module is used for detecting the condition of the waste articles according to the images of the waste articles, and the touch display is used for supplementing other information of the waste articles; at this time, the shared cabinet control interface can control the corresponding sub-box to open the box cover according to the condition of the waste and other information of the waste and old objects and put in the waste and old objects; the waste data generation module generates description data of the waste according to the image of the waste, the condition of the waste and other information of the waste, the internet of things communication module uploads the description data to the background server, the background server matches the waste meeting the requirements of the user for the user according to the waste and the description data retrieved by the user, and sends the description data corresponding to the waste to a mobile phone or a computer terminal of the user. The community waste resource sharing system based on deep learning can realize nearby sharing and utilization of waste in the community range, accelerate the circulation speed of the waste and reduce unnecessary intermediate links; a more accurate and efficient cyclic utilization mode which is more matched with the condition of the waste and the user requirement can be realized; the condition detection of the waste can be realized by applying a deep learning technology, the description data of the waste is imported into the system by combining with other information of the waste, so that the resource requirements of the user are matched, and the forward incentive guidance of the waste cyclic application is formed for the user.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A community waste resource sharing method based on deep learning is characterized by comprising the following steps:
selecting waste articles, namely selecting input waste articles and displaying and guiding a user to execute a waste image acquisition step; when the waste article type verification step judges that the types of the waste articles collected in the waste article image collection step are not consistent with the waste article types selected to be input and put, error reporting is carried out; prompting the user to supplement other information of the waste when the waste condition detection step detects the condition of the waste;
a waste image acquisition step, wherein the waste is subjected to image acquisition;
a waste article type verifying step of judging whether the types of the waste articles collected in the waste article image collecting step are consistent with the waste articles selected in the waste article type selecting step, if so, executing the waste article condition detecting step, and if not, executing error reporting through the waste article type selecting step;
a waste condition detection step of detecting the external condition of the waste according to the image acquired in the waste image acquisition step to detect the condition of the waste;
a waste material throwing control step of controlling corresponding boxes to open the box covers thereof, throwing the waste materials and executing a waste material data generation step according to the detection result of the waste material condition detection step and the information supplemented by the user in the waste material class selection step;
a waste data generation step of generating description data of the waste according to the image acquired in the waste image acquisition step, the detection result of the waste condition detection step, and the information supplemented by the user in the waste class selection step;
the Internet of things communication step, namely uploading the description data to the waste sharing step;
and a waste sharing step, namely matching the waste meeting the user requirements for the user according to the waste and the description data retrieved by the user by utilizing a mobile phone or a computer terminal, and sending the description data corresponding to the waste to the mobile phone or the computer terminal.
2. The method for sharing community waste resources according to claim 1, wherein the waste item class selection step selects the delivered waste item class by inputting a personal community account and password or logging in by face recognition.
3. The community waste resource sharing method according to claim 1, wherein the waste material class verification step comprises: a plurality of deeply learned convolutional neural network models; and the deep learning convolutional neural network model identifies the types of the waste through the images acquired in the waste image acquisition step.
4. The method according to claim 3, wherein the used-up condition detection step calls the convolutional neural network model corresponding to the used-up item when the used-up item verification step determines that the used-up item collected in the used-up item image collection step matches the used-up item selected in the used-up item selection step, so as to perform external condition detection on the used-up item according to the convolutional neural network model corresponding to the used-up item.
5. The community waste resource sharing method according to claim 1, wherein the waste sharing step adds points corresponding to the amount of the user according to the waste type and the condition of the waste thrown by the user; the points are redeemed by the user for the junk.
6. The utility model provides a old and useless resource sharing system of community based on deep learning which characterized in that includes:
the touch display is used for selecting and inputting the thrown waste and old articles and displaying and guiding the user to display the waste and old articles in front of the camera; when the waste article type verification module judges that the types of the waste articles collected by the camera are inconsistent with the waste article types selected and input to be released, error reporting is executed; when the condition of the waste is detected by a waste condition detection module, prompting the user to supplement other information of the waste;
the camera is used for acquiring images of the waste;
the arithmetic processor includes: the waste article type verification module and the waste article condition detection module; the used article type verification module is used for judging whether the types of the used articles collected by the camera are consistent with the used article types selected by the touch display, if so, the used article condition detection module is executed, and if not, an error is reported through the touch display; the waste condition detection module is used for detecting the external condition of the waste according to the image acquired by the camera so as to detect the condition of the waste;
the shared cabinet control interface is used for controlling corresponding boxes to open the box covers of the shared cabinet according to the detection result of the waste object condition detection module and the information supplemented by the user in the touch display, throwing the waste objects and executing a waste object data generation module;
the arithmetic processor further includes: the junk data generation module is used for generating description data of the junk according to the image acquired by the camera, the detection result of the junk condition detection module and the information supplemented by the user in the touch display;
the Internet of things communication module is used for uploading the description data to a background server;
and the background server is used for matching the obsolete materials meeting the user requirements for the user according to the obsolete materials and the description data retrieved by the user by using a mobile phone or a computer terminal, and sending the description data corresponding to the obsolete materials to the mobile phone or the computer terminal.
7. The community waste resource sharing system according to claim 6, wherein the touch display is configured to select the discarded waste object class by inputting a personal community account and a password or logging in by face recognition.
8. The community waste resource sharing system according to claim 6, wherein the waste article class verification module comprises: a plurality of deeply learned convolutional neural network models; and the deep learning convolutional neural network model is used for identifying the categories of the waste materials through the images collected by the camera.
9. The community waste resource sharing system according to claim 8, wherein the waste condition detecting module is configured to call the convolutional neural network model corresponding to the waste item when the waste item verifying module determines that the type of the waste collected by the camera matches the waste item selected in the touch display, so as to perform external condition detection on the waste according to the convolutional neural network model corresponding to the waste item.
10. The community waste resource sharing system according to claim 6, wherein the background server is configured to add points corresponding to the amount to the user according to the waste article class and the condition of the waste article released by the user; the points are redeemed by the user for the junk.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010006331.1A CN111222949B (en) | 2020-01-03 | 2020-01-03 | Community waste resource sharing method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010006331.1A CN111222949B (en) | 2020-01-03 | 2020-01-03 | Community waste resource sharing method and system based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111222949A true CN111222949A (en) | 2020-06-02 |
| CN111222949B CN111222949B (en) | 2021-06-04 |
Family
ID=70829454
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010006331.1A Active CN111222949B (en) | 2020-01-03 | 2020-01-03 | Community waste resource sharing method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111222949B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112052963A (en) * | 2020-07-16 | 2020-12-08 | 张洋 | Waste material classification and value evaluation device capable of conducting autonomous learning |
| CN112365197A (en) * | 2020-12-09 | 2021-02-12 | 重庆满惠网络科技有限公司 | Intelligent community resource sharing management system and method thereof |
| CN112418457A (en) * | 2020-12-07 | 2021-02-26 | 广州城市职业学院 | Novel intelligent Internet of things sharing method and device |
| CN112560821A (en) * | 2021-02-22 | 2021-03-26 | 浙江大胜达包装股份有限公司 | Automatic classifying and sorting system and method for detecting recycled corrugated paper raw material |
| CN112562174A (en) * | 2021-02-20 | 2021-03-26 | 浙江大胜达包装股份有限公司 | Self-service recycling system and method for renewable paper products |
| CN112561098A (en) * | 2021-02-19 | 2021-03-26 | 浙江大胜达包装股份有限公司 | Automatic recycling system and method based on express paper packaging box image analysis |
| CN112550524A (en) * | 2021-02-23 | 2021-03-26 | 浙江大胜达包装股份有限公司 | Unmanned express packaging type paper product recycling and transporting trailer and using method thereof |
| CN112718572A (en) * | 2021-04-02 | 2021-04-30 | 浙江大胜达包装股份有限公司 | Automatic management system and method for classification of recycled paper products |
| WO2022007123A1 (en) * | 2020-07-08 | 2022-01-13 | 谢超奇 | Overall humidity analysis system for carton |
| TWI754428B (en) * | 2020-09-25 | 2022-02-01 | 大陸商深圳富桂精密工業有限公司 | Carton recycling method, electronic device and storage medium |
| CN113998344A (en) * | 2020-07-28 | 2022-02-01 | 北京四维图新科技股份有限公司 | Express delivery box recovery method, system, server, terminal and storage medium |
| CN114220213A (en) * | 2021-11-30 | 2022-03-22 | 王晓华 | Terminal interconnection formula clothing recovery system based on thing networking |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20040029651A (en) * | 2002-10-01 | 2004-04-08 | 유명일 | Family crisis garbage can |
| CN108372126A (en) * | 2017-12-26 | 2018-08-07 | 刘利行 | A kind of Intelligent refuse classification system and its sorting technique |
| CN109201514A (en) * | 2017-06-30 | 2019-01-15 | 京东方科技集团股份有限公司 | Waste sorting recycle method, garbage classification device and classified-refuse recovery system |
| CN110210635A (en) * | 2019-06-05 | 2019-09-06 | 周皓冉 | A kind of intelligent classification recovery system that can identify waste |
-
2020
- 2020-01-03 CN CN202010006331.1A patent/CN111222949B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20040029651A (en) * | 2002-10-01 | 2004-04-08 | 유명일 | Family crisis garbage can |
| CN109201514A (en) * | 2017-06-30 | 2019-01-15 | 京东方科技集团股份有限公司 | Waste sorting recycle method, garbage classification device and classified-refuse recovery system |
| CN108372126A (en) * | 2017-12-26 | 2018-08-07 | 刘利行 | A kind of Intelligent refuse classification system and its sorting technique |
| CN110210635A (en) * | 2019-06-05 | 2019-09-06 | 周皓冉 | A kind of intelligent classification recovery system that can identify waste |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022007123A1 (en) * | 2020-07-08 | 2022-01-13 | 谢超奇 | Overall humidity analysis system for carton |
| CN112052963A (en) * | 2020-07-16 | 2020-12-08 | 张洋 | Waste material classification and value evaluation device capable of conducting autonomous learning |
| CN113998344A (en) * | 2020-07-28 | 2022-02-01 | 北京四维图新科技股份有限公司 | Express delivery box recovery method, system, server, terminal and storage medium |
| TWI754428B (en) * | 2020-09-25 | 2022-02-01 | 大陸商深圳富桂精密工業有限公司 | Carton recycling method, electronic device and storage medium |
| CN114333141A (en) * | 2020-09-25 | 2022-04-12 | 深圳富桂精密工业有限公司 | Carton recycling method, electronic device and storage medium |
| CN112418457A (en) * | 2020-12-07 | 2021-02-26 | 广州城市职业学院 | Novel intelligent Internet of things sharing method and device |
| CN112365197A (en) * | 2020-12-09 | 2021-02-12 | 重庆满惠网络科技有限公司 | Intelligent community resource sharing management system and method thereof |
| CN112561098A (en) * | 2021-02-19 | 2021-03-26 | 浙江大胜达包装股份有限公司 | Automatic recycling system and method based on express paper packaging box image analysis |
| CN112561098B (en) * | 2021-02-19 | 2021-05-25 | 浙江大胜达包装股份有限公司 | Automatic recycling system and method based on express paper packaging box image analysis |
| CN112562174A (en) * | 2021-02-20 | 2021-03-26 | 浙江大胜达包装股份有限公司 | Self-service recycling system and method for renewable paper products |
| CN112560821A (en) * | 2021-02-22 | 2021-03-26 | 浙江大胜达包装股份有限公司 | Automatic classifying and sorting system and method for detecting recycled corrugated paper raw material |
| CN112550524A (en) * | 2021-02-23 | 2021-03-26 | 浙江大胜达包装股份有限公司 | Unmanned express packaging type paper product recycling and transporting trailer and using method thereof |
| CN112718572B (en) * | 2021-04-02 | 2021-06-15 | 浙江大胜达包装股份有限公司 | Automatic management system and method for classification of recycled paper products |
| CN112718572A (en) * | 2021-04-02 | 2021-04-30 | 浙江大胜达包装股份有限公司 | Automatic management system and method for classification of recycled paper products |
| CN114220213A (en) * | 2021-11-30 | 2022-03-22 | 王晓华 | Terminal interconnection formula clothing recovery system based on thing networking |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111222949B (en) | 2021-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111222949B (en) | Community waste resource sharing method and system based on deep learning | |
| US20220297940A1 (en) | Systems and methods for learning to extrapolate optimal object routing and handling parameters | |
| US9707595B2 (en) | Household hazardous waste recovery | |
| US20220005002A1 (en) | Closed Loop Recycling Process and System | |
| US20200222943A1 (en) | Systems and Methods of Recovering Household Waste | |
| CN103052342A (en) | A Checkout Counter | |
| CN104318421A (en) | System and method for realizing reverse logistics in field of recycling of renewable resources | |
| Ji et al. | Automatic sorting of low-value recyclable waste: a comparative experimental study | |
| JP2022073649A (en) | Determination device, determination method, program and collection device | |
| CN114067488B (en) | Recovery system | |
| KR102432059B1 (en) | Method for separation and settlement of recyclable waste and electronic device thereof | |
| GB2616534A (en) | The technology of detecting the type of recyclable materials with sound processing | |
| US20140052646A1 (en) | Closed-Loop Recycling Process | |
| CN111882748A (en) | Can discern and detect recovery machine of accomodating payment | |
| CN109081002A (en) | A kind of cell distribution waste disposal method | |
| CN112777170B (en) | Garbage classification system | |
| Ríos-Zapata et al. | Can the attributes of a waste bin improve recycling? A literature review for sensors and actuators to define product design objectives | |
| Tamkhade et al. | Automated Garbage Separation Using Ai Based Robotic ARM | |
| CN113642839B (en) | Workflow self-adaptive renewable resource recycling system based on flow reconstruction | |
| CN217777467U (en) | Plastic classifying, sorting and recycling device | |
| US11998953B2 (en) | Recovery of higher volume and higher quality recyclables from a mixed stream | |
| CN212100396U (en) | Intelligent garbage can and intelligent garbage disposal system | |
| TWI636418B (en) | System and method for recycling products | |
| CN211077166U (en) | Intelligent sorting and recycling system suitable for community garbage | |
| CN114684508A (en) | Garbage classification method, electronic device and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |