CN112347949A - Garbage classification recycling system based on internet - Google Patents

Garbage classification recycling system based on internet Download PDF

Info

Publication number
CN112347949A
CN112347949A CN202011248943.8A CN202011248943A CN112347949A CN 112347949 A CN112347949 A CN 112347949A CN 202011248943 A CN202011248943 A CN 202011248943A CN 112347949 A CN112347949 A CN 112347949A
Authority
CN
China
Prior art keywords
garbage
central control
control module
preset
matrix
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.)
Withdrawn
Application number
CN202011248943.8A
Other languages
Chinese (zh)
Inventor
方攀
方建
胡家蒙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Lanzhou Xuyang Xianghui Technology Co ltd
Original Assignee
Lanzhou Xuyang Xianghui Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Lanzhou Xuyang Xianghui Technology Co ltd filed Critical Lanzhou Xuyang Xianghui Technology Co ltd
Priority to CN202011248943.8A priority Critical patent/CN112347949A/en
Publication of CN112347949A publication Critical patent/CN112347949A/en
Withdrawn legal-status Critical Current

Links

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
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
    • B65F1/00—Refuse receptacles; Accessories therefor
    • B65F1/0033—Refuse receptacles; Accessories therefor specially adapted for segregated refuse collecting, e.g. receptacles with several compartments; Combination of receptacles
    • B65F1/0053—Combination of several receptacles
    • B65F1/006—Rigid receptacles stored in an enclosure or forming part of it
    • 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
    • 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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12—Fingerprints or palmprints
    • G06V40/13—Sensors therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
    • B65F2210/00—Equipment of refuse receptacles
    • B65F2210/138—Identification means
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
    • B65F2210/00—Equipment of refuse receptacles
    • B65F2210/176—Sorting means
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
    • Y02W30/00—Technologies for solid waste management
    • Y02W30/10—Waste collection, transportation, transfer or storage, e.g. segregated refuse collecting, electric or hybrid propulsion

Abstract

The invention relates to a garbage classification recycling system based on the Internet, which comprises a characteristic acquisition module, a central control module, a storage module, a communication module, an interaction module and a garbage putting module. According to the invention, the detection image of the garbage to be classified is acquired by using the characteristic acquisition module, the central control module identifies the garbage contour in the image by using the convolutional neural network model according to the detection image and accurately obtains the classification characteristic information of each garbage in the garbage to be classified, then the garbage to be classified is preliminarily judged and confirmed by aiming at the garbage number of the first four in the descending order of volume, and the classification characteristic distribution aggregation indexes of all the garbage thrown in the throwing main body are calculated when the judgment is incorrect so as to throw the garbage to be classified into the garbage cans of the corresponding category when the throwing main body classifies the garbage according to the standard, the accurate classification throwing is ensured by combining the interaction module, the garbage classification efficiency and the garbage classification accuracy are improved, and the monitoring efficiency aiming at the garbage throwing main body is effectively improved.

Description

Garbage classification recycling system based on internet
Technical Field
The invention relates to the technical field of garbage classification, in particular to a garbage classification recycling treatment system based on the Internet.
Background
According to the latest garbage classification standard, the garbage can be classified into recoverable garbage, kitchen garbage, harmful garbage, other garbage and the like. The recyclable materials mainly comprise five types of waste paper, plastic, glass, metal and cloth, and the recyclable garbage has good recycling value and is suitable for recycling; the kitchen waste comprises food wastes such as leftovers, bones, roots, leaves and peels of vegetables and the like, has a certain recovery value, but can be used for other purposes after being treated for a certain time; the harmful garbage contains heavy metals and harmful substances harmful to human health or wastes causing real harm or potential harm to the environment, and comprises batteries, fluorescent lamps, bulbs, mercury thermometers, paint buckets, partial household appliances, expired medicines and containers thereof, expired cosmetics and the like, the recovery value of the harmful garbage can be determined according to specific conditions, but the harmful garbage needs targeted treatment and harmless treatment, and the like, other garbage includes brick and tile ceramics, dregs, waste paper in toilet, paper towel and other wastes, dust and food bag (box), other garbage also has certain recycling value and needs to be determined according to specific conditions, so that the garbage with recycling value does not have recycling value and even causes harm to the environment if the garbage is not classified. Therefore, it is very important to classify and collect garbage.
With the increasing awareness of people about garbage classification and the implementation of relevant regulations, garbage classification has become an important issue for urban development. Due to the rapid development of social economy and the rapid improvement of the living standard of people, the garbage generated in the urban production and living process is rapidly increased, and the conditions that the household garbage occupies the land and pollutes the environment are more obvious. How to recover and process garbage more efficiently becomes a focus of attention of all circles, and in the process of recovering and processing garbage, it is important to classify and process the garbage. The garbage classification means that the garbage is classified and stored, classified and put in, and classified and carried according to certain rules or standards, so that the garbage is converted into public resources. Compared with the traditional garbage recycling method, the garbage classification is a more effective garbage recycling method, and has the advantages of reducing environmental pollution, changing waste into valuable, recycling resources and the like. In the prior art, garbage classification is difficult to implement in daily life of a city, on one hand, the classification of each kind of garbage is difficult to completely distinguish in a short time, on the other hand, in order to strengthen the classification effect, supervision and classification are required to be equipped for supervision and guidance, so that the garbage classification treatment cost can be greatly increased, and in places lacking in supervision, garbage is still not classified according to classification standards but is mixed together for random delivery, which brings great difficulty to the implementation of garbage classification.
Disclosure of Invention
Therefore, the invention provides a garbage classification recycling treatment system based on the internet, which is used for solving the problem of low garbage classification efficiency caused by the fact that the thrown garbage cannot be effectively classified and monitored in the prior art.
In order to achieve the above object, the present invention provides an internet-based garbage classification recycling system, comprising:
the characteristic acquisition module is used for acquiring garbage to be classified and image information of the garbage throwing main body;
the central control module is connected with the characteristic acquisition module and is used for extracting classification characteristic information of the garbage to be classified and biological characteristic information of the garbage throwing main body from the image information acquired by the characteristic acquisition module;
the storage module is connected with the central control module and used for storing a plurality of preset matrixes, and when the central control module runs, the central control module can call the corresponding matrixes from the storage module according to the requirements to sequentially acquire information for identification or judgment;
the communication module is connected with the central control module and is used for enabling the central control module to retrieve data from the cloud internet or send a notice to a communication terminal for throwing the garbage main body when the garbage thrown by the garbage main body does not accord with the classification standard;
the interaction module is connected with the central control module and used for outputting an analysis result of the central control module;
the garbage throwing module is connected with the central control module and used for throwing the garbage into the corresponding garbage can when the central control module finishes judging the garbage type;
the central control module can sequentially acquire classification characteristic information of four pieces of garbage with the volume ratio of four in descending order in the garbage to be classified from the acquired image of the garbage to be classified, and acquire characteristic information of each piece of garbage in the image by using a convolutional neural network to judge the type A of the garbage to which each piece of garbage belongs, when the types of the garbage to which more than three pieces of garbage belong are the same, the central control module preliminarily judges the type of the garbage to be classified as the type and selects a corresponding preset volume ratio critical value Lk to compare with the volume ratio of the garbage with the minimum volume in the type of the four pieces of garbage to confirm the preliminary judgment, and when the central control module finishes the confirmation and judges the preliminary judgment to be correct, the central control module controls the throwing module to throw the garbage into a corresponding garbage can;
when the central control module completes confirmation and judges that the primary judgment is incorrect or when the number of the garbage of the same garbage type in the four garbage is less than three, the central control module calculates the classification characteristic distribution aggregative index D of the garbage to be classified and selects a corresponding index Dij from a preset classification characteristic distribution aggregative index matrix D0 prestored in the storage module to compare so as to judge whether the classification of the garbage is completed; when the central control module judges that the garbage classification is finished, the central control module controls the throwing module to throw the garbage into the corresponding garbage can, and when the central control module judges that the garbage classification is not finished, the central control module does not start the throwing module and outputs a judgment result through the interaction module.
Further, a preset garbage category characteristic matrix group A0 and a preset volume proportion critical matrix L0 are arranged in the storage module; for the preset garbage category feature matrix groups A0, A0(A1, A2, A3, A4), wherein A1 is a first preset garbage category feature matrix belonging to recyclable garbage, A2 is a second preset garbage category feature matrix belonging to kitchen garbage, A3 is a third preset garbage category feature matrix belonging to harmful garbage, and A4 is a fourth preset garbage category feature matrix belonging to other garbage; for the ith preset garbage category feature matrix Ai, i is 1, 2, 3, 4, Ai (Ai1, Ai2, Ai3,. Ain), wherein Ai1 is the ith preset garbage category first feature, Ai2 is the ith preset garbage category second feature, Ai3 is the ith preset garbage category third feature, and Ain is the ith preset garbage category nth feature; for the preset volume ratio critical matrix L0, L0(L1, L2, L3, L4), wherein L1 is a first preset volume ratio critical value, L2 is a second preset volume ratio critical value, L3 is a third preset volume ratio critical value, and L4 is a fourth preset volume ratio critical value;
when the central control module judges the types of the four rubbishes before the descending order of the volume ratio in the image, the central control module sequentially detects the feature points in each piece of the rubbishes according to the descending order of the volume ratio; when the central control module judges the type of a single garbage, the central control module extracts the shape outline of the garbage and identifies all the characteristics in the outline, and after the identification is completed, the central control module counts a preset garbage type characteristic matrix to which each characteristic belongs so as to judge the type of the garbage:
when the number of the features belonging to the A1 matrix in the garbage is the largest, judging the garbage as recoverable garbage;
when the number of the features belonging to the A2 matrix in the garbage is the largest, judging the garbage as kitchen garbage;
when the number of the features belonging to the A3 matrix in the garbage is the largest, judging the garbage as harmful garbage;
when the number of the features belonging to the A4 matrix in the garbage is the largest, judging the garbage as other garbage;
when the central control module finishes the primary judgment of the type of the garbage to be thrown in, the central control module selects a corresponding preset volume ratio critical value from an L0 matrix according to the type of the garbage to be preliminarily judged:
when the central control module preliminarily judges that the garbage to be classified is the first garbage type of the recyclable garbage, the central control module selects L1 to confirm the preliminarily judged result;
when the central control module preliminarily determines that the garbage to be classified is the second garbage type of the kitchen garbage, the central control module selects L2 to confirm the preliminarily determined result;
when the central control module preliminarily judges that the garbage to be classified is a third garbage type of harmful garbage, the central control module selects L3 to confirm the preliminarily judged result;
when the central control module preliminarily determines that the garbage to be classified is a fourth garbage type of other garbage, the central control module selects L4 to confirm the preliminarily determined result;
when the central control module selects Lk to confirm the result of the preliminary judgment, k is 1, 2, 3, 4, the central control module compares the volume ratio L of the garbage with the lowest ratio of the kth type of the k-th type of the garbage in the four garbage to be classified with Lk to confirm the preliminary judgment of the central control module: when L is larger than or equal to Lk, the central control module completes one-time confirmation and judges that the primary judgment is correct; and when L is less than Lk, the central control module judges that the primary judgment is incorrect.
Further, for the preset classification feature distribution aggregative index matrix D0, D0(D12, D13, D14, D23, D24, D34), wherein D12 is a preset classification feature distribution aggregative index for the first type of garbage and the second type of garbage, D13 is a preset classification feature distribution aggregative index for the first type of garbage and the third type of garbage, D14 is a preset classification feature distribution aggregative index for the first type of garbage and the fourth type of garbage, D23 is a preset classification feature distribution aggregative index for the second type of garbage and the third type of garbage, D24 is a preset classification feature distribution aggregative index for the second type of garbage and the fourth type of garbage, and D34 is a preset classification feature distribution aggregative index for the third type of garbage and the fourth type of garbage;
when the central control module completes confirmation and judges that the primary judgment is incorrect or when the number of the garbage of the same garbage type in the four garbage with the descending volume ratio is less than three, the central control module selects a first calculation garbage type and a second calculation garbage type:
when the types of the two wastes in the four wastes are the same, the central control module takes the waste type as a first calculation waste type and selects a second calculation waste according to the waste types of the two remaining wastes; when the types of the garbage to which the two remaining garbage belong are the same and different from the types of the garbage to which the two garbage belong, the central control module takes the garbage of the type as a second calculation garbage type; when the types of the two residual garbage are different, selecting the type of the garbage with the largest volume ratio in the two garbage as a second calculation garbage type;
when the garbage types of the four garbage are different, the central control module selects the garbage type to which the garbage with the highest volume ratio belongs from the four garbage as a first calculation garbage type, and selects the garbage type to which the garbage with the highest volume ratio belongs from the remaining three garbage as a second calculation garbage type;
when the central control module selects the ith garbage type as a first calculation garbage type and the jth garbage type as a second calculation garbage type, i is 1, 2, 3, 4, j is 1, 2, 3, 4 and i is not equal to j, the central control module selects a corresponding parameter from a D0 matrix as an evaluation standard of the classification characteristic distribution aggregativity index according to the selected first calculation garbage type and the second calculation garbage type, when i is less than j, the central control module selects Dij from a D0 matrix as the evaluation standard, and when i is greater than j, the central control module selects Dji from a D0 matrix as the evaluation standard.
Further, when the central control module calculates the aggregation index of the distribution of the classification features, the central control module obtains a first calculation classification garbage feature vector according to the first calculation garbage category and a second calculation classification garbage feature vector according to the second calculation garbage category, and obtains the aggregation index of the distribution of the classification features of the first calculation garbage category and the second calculation garbage category by using the following formula:
Figure BDA0002770954580000051
wherein, betaijCalculating a co-factor sum sigma beta between the classified garbage feature vector for the first calculation and the classified garbage feature vector for the second calculationij＝1，RijThe pearson correlation coefficient between the first calculation classification garbage feature vector and the second calculation classification garbage feature vector is set as E, the mixed feature vector of the first calculation classification garbage feature vector and the second calculation classification garbage feature vector is set as E, and the total number of the feature vectors of the first calculation classification garbage feature vector and the second calculation classification garbage feature vector is set as n;
when the central control module selects Dij from the D0 matrix as an evaluation standard, the central control module compares the D which is calculated with the Dij, and when the D is larger than or equal to the Dij, the central control module judges that the classification of the garbage to be classified is finished and takes the first calculation garbage category as the category of the garbage to be classified; and when D is less than Dij, the central control module judges that the garbage to be classified is not classified.
Further, a preset quantity ratio matrix B0(B1, B2, B3, B4) is further provided in the central control module, where B1 is a first preset quantity ratio for the first type of garbage, B2 is a second preset quantity ratio for the second type of garbage, B3 is a third preset quantity ratio for the third type of garbage, and B4 is a fourth preset quantity ratio for the fourth type of garbage;
when the central control module judges that the primary judgment is correct, the central control module detects the garbage to be classified again, extracts the outline characteristics of all the garbage from the garbage to be classified to obtain the outline characteristics, sequentially judges the garbage types of the garbage, and after the judgment is finished, the central control module selects the corresponding preset number ratio from the B0 matrix according to the garbage types in the primary judgment result to perform secondary confirmation on the primary judgment of the central control module;
when the preliminary judgment result for the garbage to be classified is the ith type of garbage, i is 1, 2, 3 and 4, the central control module selects Bi as a confirmation standard of secondary confirmation, after the selection is completed, the central control module calculates the proportion B of the number of the ith type of garbage in the garbage to be classified to the total number of the garbage to be classified, and when the proportion B is the maximum value of the proportion of four types of garbage in the garbage to be classified to the total number of the garbage in the garbage to be classified and B is not less than Bi, the central control module completes the secondary confirmation, judges that the preliminary judgment is correct and starts the throwing module to throw the garbage to be classified into a corresponding garbage can; and when B is not the maximum value of the ratio of the four kinds of garbage to the total garbage in the garbage to be classified or B is less than Bi, the central control module judges that the initial judgment is incorrect, does not start the putting module and calculates the classification characteristic distribution aggregative index of the garbage to be classified.
Further, a preset facial feature matrix F0, a preset fingerprint feature matrix G0 and a preset certification information matrix H0 are also stored in the storage module; the facial features of the residents around the system are prestored in an F0 matrix, the fingerprint features of the residents around the system are prestored in a G0 matrix, and the certification information of the residents around the system is prestored in an H0 matrix; when the garbage throwing main body throws garbage into the system, the garbage throwing main body performs identity verification through the feature acquisition module and selects one from facial features, fingerprints and certificate information for identity verification;
for the facial feature verification, the feature acquisition module acquires facial features of the garbage throwing main body, the central control module sequentially compares the acquired facial features with the facial features in the F0 matrix, and when the similarity between the facial features of the garbage throwing main body and a single preset facial feature in the F0 matrix is greater than 90%, the central control module matches the garbage throwing main body with a user to which the preset facial feature belongs and controls the storage unit to store the garbage throwing process; when the similarity between the facial features of the garbage throwing main body and a plurality of preset facial features in the F0 matrix is larger than 90%, the central control module matches the user to which the preset facial features with the highest similarity with the garbage throwing main body belong with the garbage throwing main body; when the similarity between the facial features of the garbage throwing main body and all the facial features in the F0 matrix is lower than 90%, the central control module uses the communication module to retrieve information related to the facial features of the garbage throwing main body from the cloud internet so as to authenticate the identity of the garbage throwing main body, and controls the storage module to record the facial features to be reserved for a record;
for fingerprint feature verification, a finger is pressed on the feature acquisition module by the garbage throwing main body, the fingerprint features of the garbage throwing main body are acquired by the feature acquisition module, the acquired fingerprint features are sequentially compared with the facial features in the G0 matrix by the central control module, and when the fingerprint features of the garbage throwing main body are the same as the single preset fingerprint features in the G0 matrix, the central control module matches the garbage throwing main body with the user to which the preset fingerprint features belong and controls the storage unit to store the garbage throwing process; when the fingerprint characteristics of the garbage throwing main body are different from all the fingerprint characteristics in the G0 matrix, the central control module uses the communication module to retrieve information related to the fingerprint characteristics of the garbage throwing main body from the cloud internet so as to authenticate the identity of the garbage throwing main body, and meanwhile, the central control module controls the storage module to record the fingerprint characteristics so as to be reserved for recording;
for certification information verification, the garbage throwing main body places certification information on the characteristic acquisition module, the characteristic acquisition module acquires certification information data, the central control module compares the certification information data with parameters in an H0 matrix in sequence, and when the certification information data is the same as single preset certification information data in an H0 matrix, the central control module matches the garbage throwing main body with a user to which the preset certification information data belongs and controls the storage unit to store the garbage throwing process; when the certification information data is not the same as all the preset certification information data in the H0 matrix, the central control module selects facial feature authentication or fingerprint authentication to confirm the identity information of the garbage throwing main body;
when the central control module completes verification of the garbage throwing main body, the central control module controls the throwing module to unlock, the garbage throwing main body places garbage to be classified at the designated position of the throwing module, and the characteristic acquisition module judges whether the garbage to be classified is classified or not.
Further, when the number of records of the same facial features in the storage module reaches a preset number Nf, the central control module determines that the garbage throwing main body to which the facial features belong is a new user, and adds the recorded facial features to the F0 matrix; when the number of records of the same fingerprint features in the storage module reaches a preset number Ng, the central control module determines that the garbage throwing main body to which the fingerprint features belong is a new user, and adds the facial features of the records to the G0 matrix.
Further, a preset putting time matrix N0 and a preset adjusting coefficient matrix a0 are also arranged in the storage module; for the preset throwing frequency matrix N0(N1, N2, N3, N4), where N1 is a first preset throwing frequency, N2 is a second preset throwing frequency, N3 is a third preset throwing frequency, N4 is a fourth preset throwing frequency, and each preset throwing frequency is gradually increased in sequence; for the preset adjustment coefficient matrix a0, a0(a1, a2, a3, a4), wherein a1 is a first preset adjustment coefficient, a2 is a second preset adjustment coefficient, a3 is a third preset adjustment coefficient, a4 is a fourth preset adjustment coefficient, and 1 < a1 < a2 < a3 < a4 < 2;
when the central control module judges that the garbage to be classified put in by the garbage putting main body is not classified, the central control module sends out notification information that the classification of the garbage to be classified is completed through the interaction module, and simultaneously, the central control module can also control the storage module to record the number N of the putting times of the unclassified garbage of a user matched with the garbage putting main body, the central control module compares the N with the parameters in the N0 matrix and selects a corresponding amount adjusting coefficient from the a0 matrix according to the comparison result so as to carry out evaluation standard when the user puts the garbage to be classified subsequently:
when N is less than N1, the central control module does not adjust the evaluation standard of the user when the user subsequently puts the garbage to be classified;
when N1 is more than or equal to N2, the central control module adjusts the evaluation standard of the user when the user puts garbage to be classified subsequently by using a 1;
when N2 is more than or equal to N3, the central control module adjusts the evaluation standard of the user when the user puts garbage to be classified subsequently by using a 2;
when N3 is more than or equal to N4, the central control module adjusts the evaluation standard of the user when the user puts garbage to be classified subsequently by using a 3;
when N is larger than or equal to N4, the central control module adjusts the evaluation standard of the user for subsequently throwing the garbage to be classified by using a 4;
when the central control module uses am to adjust the evaluation standard when the user subsequently puts garbage to be classified, m is 1, 2, 3 and 4, the central control module adjusts each preset volume proportion critical value Lk in the preset volume proportion critical matrix L0 into Lk ', and Lk' is Lk multiplied by am; the central control module adjusts each classification characteristic distribution aggregative index Dij in the preset classification characteristic distribution aggregative index matrix D0 to Dij', Dij ═ Dij × am; and the central control module adjusts the preset number proportion of each item in the preset number proportion matrix B0 to Bi ', Bi' ═ Bi × am.
Further, when the system runs for a preset period T0, the central control module controls the communication module to perform data interaction with a cloud internet to update features in each preset spam feature matrix in the preset spam feature matrix group a0, where the updating includes: new features are added, features that do not meet the classification criteria are deleted, and no changes are made to the features within the matrix.
Compared with the prior art, the invention has the advantages that the invention collects the detection image of the garbage to be classified by using the characteristic collection module, the central control module identifies the garbage outline in the image by using the convolutional neural network model according to the detection image and accurately obtains the classification characteristic information of each garbage in the garbage to be classified, then the preliminary judgment and confirmation are carried out on the garbage to be classified according to the number of the garbage in the first four in the descending order of the volume, and when the judgment is incorrect, calculating the classification characteristic distribution aggregation indexes of all the garbage thrown by the throwing main body so as to throw the garbage to be classified into the garbage cans of corresponding classes when the throwing main body is ensured to classify the garbage according to the standard, ensuring the classified accurate throwing by combining the interaction module, when the garbage classification efficiency and the garbage classification accuracy are improved, the monitoring efficiency of the garbage throwing main body is effectively improved.
Further, the storage module of the present invention is provided with a preset garbage category feature matrix group a0 and a preset volume occupancy critical matrix L0, when the central control module determines the category to which a single garbage in the four garbage items before the descending order of volume belongs, the central control module extracts the shape profile of the garbage and identifies all the features in the profile, after the identification is completed, the central control module counts the preset garbage category feature matrix to which each feature belongs to determine the category to which the garbage belongs, selects a corresponding preset volume occupancy critical value Lk from the L0 matrix according to the preliminarily determined garbage category, confirms the preliminary determination according to the size relationship between the volume occupancy L and Lk of the garbage having the smallest occupancy of the kth category to which the k category belongs in the four garbage items before the descending order of volume occupancy in the garbage to be classified, intelligently sets the corresponding profile critical value to different types of garbage to confirm the preliminary determination of the system on the garbage to be classified, the garbage classification precision of the system can be further improved, and therefore the garbage classification efficiency of the system is further improved.
Further, for the preset classification characteristic distribution aggregative index matrixes D0, D0(D12, D13, D14, D23, D24, D34), when the central control module completes confirmation and determines that the preliminary determination is incorrect or when the number of the garbage of the same garbage type in the four garbage with the volume percentage descending order is less than three, the central control module selects the first calculation garbage type and the second calculation garbage type and selects the corresponding parameter from the D0 matrix according to the selected first calculation garbage type and the second calculation garbage type as the evaluation standard Dij of the classification characteristic distribution aggregative index, by combining the two different garbage types and respectively selecting the corresponding evaluation standard, the occurrence of erroneous determination caused by the error generated when the unified standard is used for evaluating the two different types of garbage can be effectively avoided, while the classification accuracy of the system for the garbage is further improved, the garbage classification efficiency of the system is further improved. Meanwhile, when the classification characteristic distribution aggregative index is smaller than a preset classification characteristic distribution aggregative index threshold value, the classification of the garbage to be thrown is not carried out, or the classification is not accurate enough or even wrong, the garbage throwing channels of all the classes are kept closed, and reminding information is generated, so that the garbage can be thrown into the throwing main body after the garbage is accurately classified conveniently, on one hand, the garbage classification guiding function is realized on the throwing main body, on the other hand, the garbage classification behavior of the throwing main body can be restrained, the mixed loading and random throwing of all the garbage can be avoided, and the garbage classification efficiency of the system is further improved.
Furthermore, the classification characteristic distribution aggregative index can integrally reflect the classification aggregation degrees of different garbage to be classified, so that whether the garbage is classified by the throwing main body or not and the classification accuracy can be judged according to the classification characteristic distribution aggregative index, and the garbage classification efficiency of the system is further improved.
Furthermore, a preset quantity ratio matrix B0 is also arranged in the central control module, when the central control module judges that the primary judgment is correct, the central control module detects the garbage to be classified again, extracts the outline characteristics of all the garbage from the garbage to be classified to obtain the outline characteristics, sequentially judges the garbage types of the garbage, after the judgment is finished, the central control module selects the corresponding preset quantity ratio from the B0 matrix according to the garbage types in the primary judgment result to carry out secondary confirmation on the primary judgment of the central control module, and after the confirmation on the volume ratio is finished, the primary judgment result of the confirmation is confirmed again by adopting the quantity ratio again, so that the condition that the primary judgment causes erroneous judgment due to the fact that large-volume garbage is mixed into different types of garbage can be effectively avoided, the classification precision of the system on the garbage is further improved, the garbage classification efficiency of the system is further improved.
Further, a preset facial feature matrix F0, a preset fingerprint feature matrix G0 and a preset certification information matrix H0 are also stored in the storage module, when the garbage throwing main body throws garbage into the system, the garbage throwing main body performs identity verification through the feature acquisition module, and selects one from the facial features, the fingerprints and the certification information to perform identity verification; through the biological characteristic information or the identity identification information of obtaining rubbish input main part, can conveniently compare with presetting input main part identity information database, the identity information of input main part is discerned accurately, and the follow-up rubbish rather than input is convenient like this carries out the relevance to remind or follow-up tracing when necessary, also can retrain the rubbish input action of input main part simultaneously, when improving the monitoring efficiency of rubbish input main part, further improved the rubbish classification efficiency of system.
Further, when the number of records of the same facial features in the storage module reaches a preset number Nf, the central control module determines that the garbage throwing main body to which the facial features belong is a new user, and adds the recorded facial features to the F0 matrix; when the number of records with the same fingerprint characteristics in the storage module reaches a preset number Ng, the central control module judges that the garbage throwing main body to which the fingerprint characteristics belong is a new user, adds the facial characteristics of the records to the G0 matrix, can gradually identify and update user information around the system through self-learning, monitors the updated user, improves the monitoring efficiency of the garbage throwing main body, and further improves the garbage classification efficiency of the system.
Furthermore, a preset throwing frequency matrix N0 and a preset adjusting coefficient matrix a0 are also arranged in the storage module, when the central control module judges that the garbage to be classified thrown by the garbage throwing main body is not classified, the central control module sends out notification information that the classification of the garbage to be classified is completed through the interaction module, and simultaneously, the central control module also controls the storage module to record the non-classified throwing frequency N of a user matched with the garbage throwing main body, compares the parameters in the N and N0 matrixes and selects a corresponding adjusting coefficient from the a0 matrix according to the comparison result so as to evaluate the standard when the user throws the garbage to be classified, the corresponding adjusting coefficient is selected for the throwing frequency of the classified garbage according to the statistics of a single user, the garbage classification habit of the user can be effectively monitored in a targeted manner, the monitoring efficiency of the garbage throwing main body is improved, the garbage classification efficiency of the system is further improved.
Further, when the system runs for a preset period T0, the central control module controls the communication module to perform data interaction with the cloud internet to update the features in each preset garbage type feature matrix in the preset garbage type feature matrix group a0, and the classification accuracy of the central control module when classifying garbage to be classified can be further improved by updating the features in each preset garbage type feature matrix in the preset garbage type feature matrix group a0 in real time, so that the garbage classification efficiency of the system is further improved.
Drawings
Fig. 1 is a block diagram of the internet-based garbage classification recycling system according to the present invention.
Detailed Description
In order that the objects and advantages of the invention will be more clearly understood, the invention is further described below with reference to examples; it should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and do not limit the scope of the present invention.
It should be noted that in the description of the present invention, the terms of direction or positional relationship indicated by the terms "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, which are only for convenience of description, and do not indicate or imply that the device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Fig. 1 is a block diagram of a garbage sorting and recycling system based on the internet according to the present invention. The invention discloses an internet-based garbage classification recycling system, which comprises:
the characteristic acquisition module is used for acquiring garbage to be classified and image information of the garbage throwing main body;
and the central control module is connected with the characteristic acquisition module and used for extracting the classification characteristic information of the garbage to be classified and the biological characteristic information of the garbage throwing main body from the image information acquired by the characteristic acquisition module.
And the storage module is connected with the central control module and is used for storing a plurality of preset matrixes, and when the central control module runs, the central control module can call the corresponding matrixes from the storage module according to the requirements to sequentially acquire information for identification or judgment.
And the communication module is connected with the central control module and is used for enabling the central control module to retrieve data from the cloud internet or send a notice to the communication terminal for throwing the garbage main body when the garbage thrown by the garbage main body does not accord with the classification standard.
And the interaction module is connected with the central control module and is used for outputting the analysis result of the central control module.
And the garbage throwing module is connected with the central control module and used for throwing the garbage into the corresponding garbage can when the central control module finishes judging the garbage type.
The central control module can sequentially acquire classification characteristic information of four pieces of garbage with the volume ratio of four in descending order in the garbage to be classified from the acquired image of the garbage to be classified, and acquire characteristic information of each piece of garbage in the image by using a convolutional neural network to judge the type A of the garbage to which each piece of garbage belongs, when the types of the garbage to which more than three pieces of garbage belong are the same, the central control module preliminarily judges the type of the garbage to be classified as the type and selects a corresponding preset volume ratio critical value Lk to compare with the volume ratio of the garbage with the minimum volume in the type of the four pieces of garbage to confirm the preliminary judgment, and when the central control module finishes the confirmation and judges the preliminary judgment to be correct, the central control module controls the throwing module to throw the garbage into a corresponding garbage can.
When the central control module completes confirmation and judges that the primary judgment is incorrect or when the number of the garbage of the same garbage type in the four garbage is less than three, the central control module calculates the classification characteristic distribution aggregative index D of the garbage to be classified and selects a corresponding index Dij from a preset classification characteristic distribution aggregative index matrix D0 prestored in the storage module to compare so as to judge whether the classification of the garbage is completed; when the central control module judges that the garbage classification is finished, the central control module controls the throwing module to throw the garbage into the corresponding garbage can, and when the central control module judges that the garbage classification is not finished, the central control module does not start the throwing module and outputs a judgment result through the interaction module.
Specifically, in the embodiment of the present invention, the process of identifying the detection image through the convolutional neural network specifically includes:
firstly, constructing a feature extraction part of a convolutional neural network model, aiming at the construction of the AlexNet network after removing an LRN layer, constructing the feature extraction part firstly, wherein the feature extraction part comprises 5 convolutional layers and 3 pooling layers, and a ReLU activation function layer is arranged behind each layer of convolution; the characteristic extraction part is used for extracting the characteristics in the detection image and transmitting the characteristics to the convolutional neural network;
then, a classifier part of the convolutional neural network model is constructed, wherein the classifier part is composed of 3 layers of fully-connected layers and a loss layer, each input node of the fully-connected layers is connected with all output nodes, the loss layer maps the output result of the last layer to probability distribution through a Softmax function, and negative log-likelihood loss is obtained through the probability distribution; taking the maximum value in the probability distribution as a classification result, and taking a loss function as the basis for updating the neural network parameters;
training through the constructed convolutional neural network, wherein the training process of the convolutional neural network comprises a forward propagation stage and a backward propagation stage; in the forward propagation stage, the convolutional neural network calculates a classification result according to the input detection image to obtain loss; in the back propagation stage, error gradients are calculated according to a chain rule, and iterative updating of weight parameters is performed by using a random gradient descent method;
optimizing the training process: optimization of training was performed using Dropout strategy: in the training process, the Dropout strategy discards hidden nodes in the neural network according to a set probability, so that part of neurons are inactivated, the complexity of a neural network model is reduced, and the over-fitting phenomenon of the neural network is inhibited; obtaining the trained category classifier and obtaining the trained category classifier,
and finally, identifying the preprocessed detection image through the trained convolutional neural network to obtain the classification characteristic information of the garbage to be classified.
Specifically, a preset garbage category characteristic matrix group A0 and a preset volume proportion critical matrix L0 are arranged in the storage module; for the preset garbage category feature matrix groups A0, A0(A1, A2, A3, A4), wherein A1 is a first preset garbage category feature matrix belonging to recyclable garbage, A2 is a second preset garbage category feature matrix belonging to kitchen garbage, A3 is a third preset garbage category feature matrix belonging to harmful garbage, and A4 is a fourth preset garbage category feature matrix belonging to other garbage; for the ith preset garbage category feature matrix Ai, i is 1, 2, 3, 4, Ai (Ai1, Ai2, Ai3,. Ain), wherein Ai1 is the ith preset garbage category first feature, Ai2 is the ith preset garbage category second feature, Ai3 is the ith preset garbage category third feature, and Ain is the ith preset garbage category nth feature; for the preset volume fraction critical matrix L0, L0(L1, L2, L3, L4), wherein L1 is a first preset volume fraction critical value, L2 is a second preset volume fraction critical value, L3 is a third preset volume fraction critical value, and L4 is a fourth preset volume fraction critical value.
When the central control module judges the types of the four rubbishes before the descending order of the volume ratio in the image, the central control module sequentially detects the feature points in each piece of the rubbishes according to the descending order of the volume ratio; when the central control module judges the type of a single garbage, the central control module extracts the shape outline of the garbage and identifies all the characteristics in the outline, and after the identification is completed, the central control module counts a preset garbage type characteristic matrix to which each characteristic belongs so as to judge the type of the garbage:
when the number of the features belonging to the A1 matrix in the garbage is the largest, judging the garbage as recoverable garbage;
when the number of the features belonging to the A2 matrix in the garbage is the largest, judging the garbage as kitchen garbage;
when the number of the features belonging to the A3 matrix in the garbage is the largest, judging the garbage as harmful garbage;
and when the number of the features belonging to the A4 matrix in the garbage is the largest, judging the garbage as other garbage.
When the central control module finishes the primary judgment of the type of the garbage to be thrown in, the central control module selects a corresponding preset volume ratio critical value from an L0 matrix according to the type of the garbage to be preliminarily judged:
when the central control module preliminarily judges that the garbage to be classified is the first garbage type of the recyclable garbage, the central control module selects L1 to confirm the preliminarily judged result;
when the central control module preliminarily determines that the garbage to be classified is the second garbage type of the kitchen garbage, the central control module selects L2 to confirm the preliminarily determined result;
when the central control module preliminarily judges that the garbage to be classified is a third garbage type of harmful garbage, the central control module selects L3 to confirm the preliminarily judged result;
when the central control module preliminarily determines that the garbage to be classified is the fourth garbage type of other garbage, the central control module selects L4 to confirm the preliminarily determined result.
When the central control module selects Lk to confirm the result of the preliminary judgment, k is 1, 2, 3, 4, the central control module compares the volume ratio L of the garbage with the lowest ratio of the kth type of the k-th type of the garbage in the four garbage to be classified with Lk to confirm the preliminary judgment of the central control module: when L is larger than or equal to Lk, the central control module completes one-time confirmation and judges that the primary judgment is correct; and when L is less than Lk, the central control module judges that the primary judgment is incorrect.
Specifically, for the preset classification feature distribution aggregative index matrix D0, D0(D12, D13, D14, D23, D24, D34), where D12 is a preset classification feature distribution aggregative index for between the first type of garbage and the second type of garbage, D13 is a preset classification feature distribution aggregative index for between the first type of garbage and the third type of garbage, D14 is a preset classification feature distribution aggregative index for between the first type of garbage and the fourth type of garbage, D23 is a preset classification feature distribution aggregative index for between the second type of garbage and the third type of garbage, D24 is a preset classification feature distribution aggregative index for between the second type of garbage and the fourth type of garbage, and D34 is a preset classification feature distribution aggregative index for between the third type of garbage and the fourth type of garbage.
And when the central control module completes confirmation and judges that the primary judgment is incorrect or when the number of the garbage belonging to the same garbage type in the four garbage with the descending volume ratio is less than three, the central control module selects a first calculation garbage type and a second calculation garbage type.
When the types of the two wastes in the four wastes are the same, the central control module takes the waste type as a first calculation waste type and selects a second calculation waste according to the waste types of the two remaining wastes; when the types of the garbage to which the two remaining garbage belong are the same and different from the types of the garbage to which the two garbage belong, the central control module takes the garbage of the type as a second calculation garbage type; and when the types of the remaining two pieces of garbage are different, selecting the type of the garbage with the largest volume ratio in the two pieces of garbage as a second calculation garbage type.
And when the garbage types of the four garbage are different, the central control module selects the garbage type to which the garbage with the highest volume ratio belongs from the four garbage as a first calculation garbage type, and selects the garbage type to which the garbage with the highest volume ratio belongs from the remaining three garbage as a second calculation garbage type.
When the central control module selects the ith garbage type as a first calculation garbage type and the jth garbage type as a second calculation garbage type, i is 1, 2, 3, 4, j is 1, 2, 3, 4 and i is not equal to j, the central control module selects a corresponding parameter from a D0 matrix as an evaluation standard of the classification characteristic distribution aggregativity index according to the selected first calculation garbage type and the second calculation garbage type, when i is less than j, the central control module selects Dij from a D0 matrix as the evaluation standard, and when i is greater than j, the central control module selects Dji from a D0 matrix as the evaluation standard.
Specifically, the specific method of the central control module in calculating the clustering index of the distribution of the classification features is as follows:
calculating classification characteristic information of a first calculation garbage type and a second calculation garbage type and calculating Euclidean distance between the corresponding classification characteristic information;
performing classification feature clustering processing according to the Euclidean distance to obtain a corresponding first calculation garbage category classification feature set and a second calculation garbage category classification feature set;
extracting features of each classification feature set to obtain corresponding classification feature vectors;
obtaining the classification feature distribution aggregative indexes of the first calculation garbage type and the second calculation garbage type according to the classification feature vector by using the following formula:
Figure BDA0002770954580000161
wherein, betaijCalculating a co-factor sum sigma beta between the classified garbage feature vector for the first calculation and the classified garbage feature vector for the second calculationij＝1，RijThe pearson correlation coefficient between the first calculation classification garbage feature vector and the second calculation classification garbage feature vector is calculated, E is a mixed feature vector of the first calculation classification garbage feature vector and the second calculation classification garbage feature vector, and n is the total number of feature vectors of the first calculation classification garbage feature vector and the second calculation classification garbage feature vector.
When the central control module selects Dij from the D0 matrix as an evaluation standard, the central control module compares the D which is calculated with the Dij, and when the D is larger than or equal to the Dij, the central control module judges that the classification of the garbage to be classified is finished and takes the first calculation garbage category as the category of the garbage to be classified; and when D is less than Dij, the central control module judges that the garbage to be classified is not classified.
Specifically, the central control module of the present invention is further provided with a preset number ratio matrix B0(B1, B2, B3, B4), where B1 is a first preset number ratio for the first type of garbage, B2 is a second preset number ratio for the second type of garbage, B3 is a third preset number ratio for the third type of garbage, and B4 is a fourth preset number ratio for the fourth type of garbage.
And when the central control module judges that the primary judgment is correct, the central control module detects the garbage to be classified again, extracts the outline characteristics of all the garbage from the garbage to be classified to obtain the outline characteristics, sequentially judges the garbage types of the garbage, and after the judgment is finished, the central control module selects the corresponding preset number ratio from the B0 matrix according to the garbage types in the primary judgment result to perform secondary confirmation on the primary judgment of the central control module.
When the preliminary judgment result for the garbage to be classified is the ith type of garbage, i is 1, 2, 3 and 4, the central control module selects Bi as a confirmation standard of secondary confirmation, after the selection is completed, the central control module calculates the proportion B of the number of the ith type of garbage in the garbage to be classified to the total number of the garbage to be classified, and when the proportion B is the maximum value of the proportion of four types of garbage in the garbage to be classified to the total number of the garbage in the garbage to be classified and B is not less than Bi, the central control module completes the secondary confirmation, judges that the preliminary judgment is correct and starts the throwing module to throw the garbage to be classified into a corresponding garbage can; and when B is not the maximum value of the ratio of the four kinds of garbage to the total garbage in the garbage to be classified or B is less than Bi, the central control module judges that the initial judgment is incorrect, does not start the putting module and calculates the classification characteristic distribution aggregative index of the garbage to be classified.
Specifically, the storage module of the present invention further stores a preset facial feature matrix F0, a preset fingerprint feature matrix G0, and a preset certification information matrix H0; the facial features of the residents around the system are prestored in an F0 matrix, the fingerprint features of the residents around the system are prestored in a G0 matrix, and the certification information of the residents around the system is prestored in an H0 matrix; when the garbage throwing main body throws garbage into the system, the garbage throwing main body performs identity verification through the feature acquisition module and selects one from the facial features, the fingerprints and the certificate information to perform identity verification.
For the facial feature verification, the feature acquisition module acquires facial features of the garbage throwing main body, the central control module sequentially compares the acquired facial features with the facial features in the F0 matrix, and when the similarity between the facial features of the garbage throwing main body and a single preset facial feature in the F0 matrix is greater than 90%, the central control module matches the garbage throwing main body with a user to which the preset facial feature belongs and controls the storage unit to store the garbage throwing process; when the similarity between the facial features of the garbage throwing main body and a plurality of preset facial features in the F0 matrix is larger than 90%, the central control module matches the user to which the preset facial features with the highest similarity with the garbage throwing main body belong with the garbage throwing main body; when the similarity between the facial features of the garbage throwing main body and all the facial features in the F0 matrix is lower than 90%, the central control module uses the communication module to retrieve information related to the facial features of the garbage throwing main body from the cloud internet so as to authenticate the identity of the garbage throwing main body, and meanwhile, the central control module controls the storage module to record the facial features so as to be reserved for a record.
For fingerprint feature verification, a finger is pressed on the feature acquisition module by the garbage throwing main body, the fingerprint features of the garbage throwing main body are acquired by the feature acquisition module, the acquired fingerprint features are sequentially compared with the facial features in the G0 matrix by the central control module, and when the fingerprint features of the garbage throwing main body are the same as the single preset fingerprint features in the G0 matrix, the central control module matches the garbage throwing main body with the user to which the preset fingerprint features belong and controls the storage unit to store the garbage throwing process; when the fingerprint characteristics of the garbage throwing main body are different from all the fingerprint characteristics in the G0 matrix, the central control module retrieves information related to the fingerprint characteristics of the garbage throwing main body from the cloud internet by using the communication module so as to authenticate the identity of the garbage throwing main body, and meanwhile, the central control module controls the storage module to record the fingerprint characteristics so as to be reserved for recording.
For certification information verification, the garbage throwing main body places certification information on the characteristic acquisition module, the characteristic acquisition module acquires certification information data, the central control module compares the certification information data with parameters in an H0 matrix in sequence, and when the certification information data is the same as single preset certification information data in an H0 matrix, the central control module matches the garbage throwing main body with a user to which the preset certification information data belongs and controls the storage unit to store the garbage throwing process; when the certification information data is different from all the preset certification information data in the H0 matrix, the central control module selects facial feature authentication or fingerprint authentication to confirm the identity information of the garbage throwing main body.
When the central control module completes verification of the garbage throwing main body, the central control module controls the throwing module to unlock, the garbage throwing main body places garbage to be classified at the designated position of the throwing module, and the characteristic acquisition module judges whether the garbage to be classified is classified or not.
Specifically, when the number of records of the same facial features in the storage module reaches a preset number Nf, the central control module determines that the garbage throwing main body to which the facial features belong is a new user, and adds the recorded facial features to the F0 matrix; when the number of records of the same fingerprint features in the storage module reaches a preset number Ng, the central control module determines that the garbage throwing main body to which the fingerprint features belong is a new user, and adds the facial features of the records to the G0 matrix.
Specifically, the storage module is further provided with a preset putting time matrix N0 and a preset adjustment coefficient matrix a 0; for the preset throwing frequency matrix N0(N1, N2, N3, N4), where N1 is a first preset throwing frequency, N2 is a second preset throwing frequency, N3 is a third preset throwing frequency, N4 is a fourth preset throwing frequency, and each preset throwing frequency is gradually increased in sequence; for the preset adjustment coefficient matrix a0, a0(a1, a2, a3, a4), where a1 is a first preset adjustment coefficient, a2 is a second preset adjustment coefficient, a3 is a third preset adjustment coefficient, a4 is a fourth preset adjustment coefficient, and 1 < a1 < a2 < a3 < a4 < 2.
When the central control module judges that the garbage to be classified put in by the garbage putting main body is not classified, the central control module sends out notification information that the classification of the garbage to be classified is completed through the interaction module, and simultaneously, the central control module can also control the storage module to record the number N of the putting times of the unclassified garbage of a user matched with the garbage putting main body, the central control module compares the N with the parameters in the N0 matrix and selects a corresponding amount adjusting coefficient from the a0 matrix according to the comparison result so as to carry out evaluation standard when the user puts the garbage to be classified subsequently:
when N is less than N1, the central control module does not adjust the evaluation standard of the user when the user subsequently puts the garbage to be classified;
when N1 is more than or equal to N2, the central control module adjusts the evaluation standard of the user when the user puts garbage to be classified subsequently by using a 1;
when N2 is more than or equal to N3, the central control module adjusts the evaluation standard of the user when the user puts garbage to be classified subsequently by using a 2;
when N3 is more than or equal to N4, the central control module adjusts the evaluation standard of the user when the user puts garbage to be classified subsequently by using a 3;
when N is larger than or equal to N4, the central control module uses a4 to adjust the evaluation standard when the user puts garbage to be classified later.
When the central control module uses am to adjust the evaluation standard when the user subsequently puts garbage to be classified, m is 1, 2, 3 and 4, the central control module adjusts each preset volume proportion critical value Lk in the preset volume proportion critical matrix L0 into Lk ', and Lk' is Lk multiplied by am; the central control module adjusts each classification characteristic distribution aggregative index Dij in the preset classification characteristic distribution aggregative index matrix D0 to Dij', Dij ═ Dij × am; and the central control module adjusts the preset number proportion of each item in the preset number proportion matrix B0 to Bi ', Bi' ═ Bi × am.
Specifically, when the system runs for a preset period T0, the central control module controls the communication module to perform data interaction with a cloud internet to update features in each preset spam feature matrix in the preset spam feature matrix group a0, where the updating includes: new features are added, features that do not meet the classification criteria are deleted, and no changes are made to the features within the matrix.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention; various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (9)

1. The utility model provides a waste classification recycling processing system based on internet which characterized in that includes:
the characteristic acquisition module is used for acquiring garbage to be classified and image information of the garbage throwing main body;
the central control module is connected with the characteristic acquisition module and is used for extracting classification characteristic information of the garbage to be classified and biological characteristic information of the garbage throwing main body from the image information acquired by the characteristic acquisition module;
the storage module is connected with the central control module and used for storing a plurality of preset matrixes, and when the central control module runs, the central control module can call the corresponding matrixes from the storage module according to the requirements to sequentially acquire information for identification or judgment;
the communication module is connected with the central control module and is used for enabling the central control module to retrieve data from the cloud internet or send a notice to a communication terminal for throwing the garbage main body when the garbage thrown by the garbage main body does not accord with the classification standard;
the interaction module is connected with the central control module and used for outputting an analysis result of the central control module;
the garbage throwing module is connected with the central control module and used for throwing the garbage into the corresponding garbage can when the central control module finishes judging the garbage type;
the central control module can sequentially acquire contour information of four pieces of garbage with the volume accounting for four times of descending order in the garbage to be classified and all classification characteristic information in the contour information from the acquired image of the garbage to be classified, and acquire the characteristic information of each piece of garbage in the image by using a convolutional neural network to judge the garbage type A to which each piece of garbage belongs, when the types of the four pieces of garbage are the same as the types of the three or more pieces of garbage, the central control module preliminarily determines the type of the garbage to be classified as the type, selects a corresponding preset volume ratio critical value Lk and compares the volume ratio of the garbage with the minimum volume of the type of the four pieces of garbage to confirm the preliminary determination, when the central control module completes the confirmation and judges that the primary judgment is correct, the central control module controls the throwing module to throw the garbage into the corresponding garbage can;
when the central control module completes confirmation and judges that the primary judgment is incorrect or when the number of the garbage of the same garbage type in the four garbage is less than three, the central control module calculates the classification characteristic distribution aggregative index D of the garbage to be classified and selects a corresponding index Dij from a preset classification characteristic distribution aggregative index matrix D0 prestored in the storage module to compare so as to judge whether the classification of the garbage is completed; when the central control module judges that the garbage classification is finished, the central control module controls the throwing module to throw the garbage into the corresponding garbage can, and when the central control module judges that the garbage classification is not finished, the central control module does not start the throwing module and outputs a judgment result through the interaction module.
2. The internet-based garbage classification and recycling system of claim 1, wherein the storage module is provided with a preset garbage category feature matrix group a0 and a preset volume-to-volume ratio critical matrix L0; for the preset garbage category feature matrix groups A0, A0(A1, A2, A3, A4), wherein A1 is a first preset garbage category feature matrix belonging to recyclable garbage, A2 is a second preset garbage category feature matrix belonging to kitchen garbage, A3 is a third preset garbage category feature matrix belonging to harmful garbage, and A4 is a fourth preset garbage category feature matrix belonging to other garbage; for the ith preset garbage category feature matrix Ai, i is 1, 2, 3, 4, Ai (Ai1, Ai2, Ai3,. Ain), wherein Ai1 is the ith preset garbage category first feature, Ai2 is the ith preset garbage category second feature, Ai3 is the ith preset garbage category third feature, and Ain is the ith preset garbage category nth feature; for the preset volume ratio critical matrix L0, L0(L1, L2, L3, L4), wherein L1 is a first preset volume ratio critical value, L2 is a second preset volume ratio critical value, L3 is a third preset volume ratio critical value, and L4 is a fourth preset volume ratio critical value;
when the central control module judges the types of the four garbage in the image in descending order of the volume ratio, the central control module sequentially detects the feature points in the garbage outlines according to the descending order of the volume ratio; when the central control module judges the type of a single garbage, the central control module extracts the shape outline of the garbage and identifies all the characteristics in the outline, and after the identification is completed, the central control module counts a preset garbage type characteristic matrix to which each characteristic belongs so as to judge the type of the garbage:
when the number of the features belonging to the A1 matrix in the garbage is the largest, judging the garbage as recoverable garbage;
when the number of the features belonging to the A2 matrix in the garbage is the largest, judging the garbage as kitchen garbage;
when the number of the features belonging to the A3 matrix in the garbage is the largest, judging the garbage as harmful garbage;
when the number of the features belonging to the A4 matrix in the garbage is the largest, judging the garbage as other garbage;
four pieces has three pieces
When the central control module finishes the primary judgment of the type of the garbage to be thrown in, the central control module selects a corresponding preset volume ratio critical value from an L0 matrix according to the type of the garbage to be preliminarily judged:
when the central control module preliminarily judges that the garbage to be classified is the first garbage type of the recyclable garbage, the central control module selects L1 to confirm the preliminarily judged result;
when the central control module preliminarily determines that the garbage to be classified is the second garbage type of the kitchen garbage, the central control module selects L2 to confirm the preliminarily determined result;
when the central control module preliminarily judges that the garbage to be classified is a third garbage type of harmful garbage, the central control module selects L3 to confirm the preliminarily judged result;
when the central control module preliminarily determines that the garbage to be classified is a fourth garbage type of other garbage, the central control module selects L4 to confirm the preliminarily determined result;
when the central control module selects Lk to confirm the result of the preliminary judgment, k is 1, 2, 3, 4, the central control module compares the volume ratio L of the garbage with the lowest ratio of the kth type of the k-th type of the garbage in the four garbage to be classified with Lk to confirm the preliminary judgment of the central control module: when L is larger than or equal to Lk, the central control module completes one-time confirmation and judges that the primary judgment is correct; and when L is less than Lk, the central control module judges that the primary judgment is incorrect.
3. The Internet-based garbage classification and recycling system of claim 2, distributing a aggregability index matrix D0, D0(D12, D13, D14, D23, D24, D34) for the preset classification features, d12 is a preset aggregation index of classification feature distribution between the first type of garbage and the second type of garbage, D13 is a preset aggregation index of classification feature distribution between the first type of garbage and the third type of garbage, D14 is a preset aggregation index of classification feature distribution between the first type of garbage and the fourth type of garbage, D23 is a preset aggregation index of classification feature distribution between the second type of garbage and the third type of garbage, D24 is a preset aggregation index of classification feature distribution between the second type of garbage and the fourth type of garbage, and D34 is a preset aggregation index of classification feature distribution between the third type of garbage and the fourth type of garbage;
when the central control module completes confirmation and judges that the primary judgment is incorrect or when the number of the garbage of the same garbage type in the four garbage with the descending volume ratio is less than three, the central control module selects a first calculation garbage type and a second calculation garbage type:
when the types of the two wastes in the four wastes are the same, the central control module takes the waste type as a first calculation waste type and selects a second calculation waste according to the waste types of the two remaining wastes; when the types of the garbage to which the two remaining garbage belong are the same and different from the types of the garbage to which the two garbage belong, the central control module takes the garbage of the type as a second calculation garbage type; when the types of the two residual garbage are different, selecting the type of the garbage with the largest volume ratio in the two garbage as a second calculation garbage type;
when the garbage types of the four garbage are different, the central control module selects the garbage type to which the garbage with the highest volume ratio belongs from the four garbage as a first calculation garbage type, and selects the garbage type to which the garbage with the highest volume ratio belongs from the remaining three garbage as a second calculation garbage type;
when the central control module selects the ith garbage type as a first calculation garbage type and the jth garbage type as a second calculation garbage type, i is 1, 2, 3, 4, j is 1, 2, 3, 4 and i is not equal to j, the central control module selects a corresponding parameter from a D0 matrix as an evaluation standard of the classification characteristic distribution aggregativity index according to the selected first calculation garbage type and the second calculation garbage type, when i is less than j, the central control module selects Dij from a D0 matrix as the evaluation standard, and when i is greater than j, the central control module selects Dji from a D0 matrix as the evaluation standard.
4. The internet-based garbage classification recycling system of claim 3, wherein when the central control module calculates the aggregation index of the classification feature distribution, the central control module obtains a first calculation classification garbage feature vector according to the first calculation garbage category, obtains a second calculation classification garbage feature vector according to the second calculation garbage category, and obtains the aggregation index of the classification feature distribution of the first calculation garbage category and the second calculation garbage category by using the following formula:
Figure FDA0002770954570000041
wherein, betaijCalculating a co-factor sum sigma beta between the classified garbage feature vector for the first calculation and the classified garbage feature vector for the second calculationij＝1，RijThe pearson correlation coefficient between the first calculation classification garbage feature vector and the second calculation classification garbage feature vector is set as E, the mixed feature vector of the first calculation classification garbage feature vector and the second calculation classification garbage feature vector is set as E, and the total number of the feature vectors of the first calculation classification garbage feature vector and the second calculation classification garbage feature vector is set as n;
when the central control module selects Dij from the D0 matrix as an evaluation standard, the central control module compares the D which is calculated with the Dij, and when the D is larger than or equal to the Dij, the central control module judges that the classification of the garbage to be classified is finished and takes the first calculation garbage category as the category of the garbage to be classified; and when D is less than Dij, the central control module judges that the garbage to be classified is not classified.
5. The internet-based garbage classification and recycling system according to claim 4, wherein a preset number ratio matrix B0(B1, B2, B3, B4) is further provided in the central control module, wherein B1 is a first preset number ratio for the first type of garbage, B2 is a second preset number ratio for the second type of garbage, B3 is a third preset number ratio for the third type of garbage, and B4 is a fourth preset number ratio for the fourth type of garbage;
when the central control module judges that the primary judgment is correct, the central control module detects the garbage to be classified again, extracts the outline characteristics of all the garbage from the garbage to be classified to obtain the outline characteristics, sequentially judges the garbage types of the garbage, and after the judgment is finished, the central control module selects the corresponding preset number ratio from the B0 matrix according to the garbage types in the primary judgment result to perform secondary confirmation on the primary judgment of the central control module;
when the preliminary judgment result for the garbage to be classified is the ith type of garbage, i is 1, 2, 3 and 4, the central control module selects Bi as a confirmation standard of secondary confirmation, after the selection is completed, the central control module calculates the proportion B of the number of the ith type of garbage in the garbage to be classified to the total number of the garbage to be classified, and when the proportion B is the maximum value of the proportion of four types of garbage in the garbage to be classified to the total number of the garbage in the garbage to be classified and B is not less than Bi, the central control module completes the secondary confirmation, judges that the preliminary judgment is correct and starts the throwing module to throw the garbage to be classified into a corresponding garbage can; and when B is not the maximum value of the ratio of the four kinds of garbage to the total garbage in the garbage to be classified or B is less than Bi, the central control module judges that the initial judgment is incorrect, does not start the putting module and calculates the classification characteristic distribution aggregative index of the garbage to be classified.
6. The internet-based garbage classification and recycling system of claim 5, wherein the storage module further stores a preset facial feature matrix F0, a preset fingerprint feature matrix G0 and a preset certification information matrix H0; the facial features of the residents around the system are prestored in an F0 matrix, the fingerprint features of the residents around the system are prestored in a G0 matrix, and the certification information of the residents around the system is prestored in an H0 matrix; when the garbage throwing main body throws garbage into the system, the garbage throwing main body performs identity verification through the feature acquisition module and selects one from facial features, fingerprints and certificate information for identity verification;
for the facial feature verification, the feature acquisition module acquires facial features of the garbage throwing main body, the central control module sequentially compares the acquired facial features with the facial features in the F0 matrix, and when the similarity between the facial features of the garbage throwing main body and a single preset facial feature in the F0 matrix is greater than 90%, the central control module matches the garbage throwing main body with a user to which the preset facial feature belongs and controls the storage unit to store the garbage throwing process; when the similarity between the facial features of the garbage throwing main body and a plurality of preset facial features in the F0 matrix is larger than 90%, the central control module matches the user to which the preset facial features with the highest similarity with the garbage throwing main body belong with the garbage throwing main body; when the similarity between the facial features of the garbage throwing main body and all the facial features in the F0 matrix is lower than 90%, the central control module uses the communication module to retrieve information related to the facial features of the garbage throwing main body from the cloud internet so as to authenticate the identity of the garbage throwing main body, and controls the storage module to record the facial features to be reserved for a record;
for fingerprint feature verification, a finger is pressed on the feature acquisition module by the garbage throwing main body, the fingerprint features of the garbage throwing main body are acquired by the feature acquisition module, the acquired fingerprint features are sequentially compared with the facial features in the G0 matrix by the central control module, and when the fingerprint features of the garbage throwing main body are the same as the single preset fingerprint features in the G0 matrix, the central control module matches the garbage throwing main body with the user to which the preset fingerprint features belong and controls the storage unit to store the garbage throwing process; when the fingerprint characteristics of the garbage throwing main body are different from all the fingerprint characteristics in the G0 matrix, the central control module uses the communication module to retrieve information related to the fingerprint characteristics of the garbage throwing main body from the cloud internet so as to authenticate the identity of the garbage throwing main body, and meanwhile, the central control module controls the storage module to record the fingerprint characteristics so as to be reserved for recording;
for certification information verification, the garbage throwing main body places certification information on the characteristic acquisition module, the characteristic acquisition module acquires certification information data, the central control module compares the certification information data with parameters in an H0 matrix in sequence, and when the certification information data is the same as single preset certification information data in an H0 matrix, the central control module matches the garbage throwing main body with a user to which the preset certification information data belongs and controls the storage unit to store the garbage throwing process; when the certification information data is not the same as all the preset certification information data in the H0 matrix, the central control module selects facial feature authentication or fingerprint authentication to confirm the identity information of the garbage throwing main body;
when the central control module completes verification of the garbage throwing main body, the central control module controls the throwing module to unlock, the garbage throwing main body places garbage to be classified at the designated position of the throwing module, and the characteristic acquisition module judges whether the garbage to be classified is classified or not.
7. The internet-based garbage classification and recycling system of claim 6, wherein when the number of records of the same facial features in the storage module reaches a preset number Nf, the central control module determines that the garbage throwing subject to which the facial features belong is a new user, and adds the recorded facial features to the F0 matrix; when the number of records of the same fingerprint features in the storage module reaches a preset number Ng, the central control module determines that the garbage throwing main body to which the fingerprint features belong is a new user, and adds the facial features of the records to the G0 matrix.
8. The internet-based garbage classification and recycling system of claim 7, wherein the storage module further comprises a preset throwing time matrix N0 and a preset adjustment coefficient matrix a 0; for the preset throwing frequency matrix N0(N1, N2, N3, N4), where N1 is a first preset throwing frequency, N2 is a second preset throwing frequency, N3 is a third preset throwing frequency, N4 is a fourth preset throwing frequency, and each preset throwing frequency is gradually increased in sequence; for the preset adjustment coefficient matrix a0, a0(a1, a2, a3, a4), wherein a1 is a first preset adjustment coefficient, a2 is a second preset adjustment coefficient, a3 is a third preset adjustment coefficient, a4 is a fourth preset adjustment coefficient, and 1 < a1 < a2 < a3 < a4 < 2;
when the central control module judges that the garbage to be classified put in by the garbage putting main body is not classified, the central control module sends out notification information that the classification of the garbage to be classified is completed through the interaction module, and simultaneously, the central control module can also control the storage module to record the number N of the putting times of the unclassified garbage of a user matched with the garbage putting main body, the central control module compares the N with the parameters in the N0 matrix and selects a corresponding amount adjusting coefficient from the a0 matrix according to the comparison result so as to carry out evaluation standard when the user puts the garbage to be classified subsequently:
when N is less than N1, the central control module does not adjust the evaluation standard of the user when the user subsequently puts the garbage to be classified;
when N1 is more than or equal to N2, the central control module adjusts the evaluation standard of the user when the user puts garbage to be classified subsequently by using a 1;
when N2 is more than or equal to N3, the central control module adjusts the evaluation standard of the user when the user puts garbage to be classified subsequently by using a 2;
when N3 is more than or equal to N4, the central control module adjusts the evaluation standard of the user when the user puts garbage to be classified subsequently by using a 3;
when N is larger than or equal to N4, the central control module adjusts the evaluation standard of the user for subsequently throwing the garbage to be classified by using a 4;
when the central control module uses am to adjust the evaluation standard when the user subsequently puts garbage to be classified, m is 1, 2, 3 and 4, the central control module adjusts each preset volume proportion critical value Lk in the preset volume proportion critical matrix L0 into Lk ', and Lk' is Lk multiplied by am; the central control module adjusts each classification characteristic distribution aggregative index Dij in the preset classification characteristic distribution aggregative index matrix D0 to Dij', Dij ═ Dij × am; and the central control module adjusts the preset number proportion of each item in the preset number proportion matrix B0 to Bi ', Bi' ═ Bi × am.
9. The internet-based garbage classification recycling system of claim 8, wherein when the system runs for a preset period T0, the central control module controls the communication module to perform data interaction with a cloud internet to update the features in each of the preset garbage category feature matrices in the preset garbage category feature matrix group a0, and the updating includes: new features are added, features that do not meet the classification criteria are deleted, and no changes are made to the features within the matrix.
CN202011248943.8A 2020-11-10 2020-11-10 Garbage classification recycling system based on internet Withdrawn CN112347949A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011248943.8A CN112347949A (en) 2020-11-10 2020-11-10 Garbage classification recycling system based on internet

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011248943.8A CN112347949A (en) 2020-11-10 2020-11-10 Garbage classification recycling system based on internet

Publications (1)

Publication Number Publication Date
CN112347949A true CN112347949A (en) 2021-02-09

Family

ID=74362426

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011248943.8A Withdrawn CN112347949A (en) 2020-11-10 2020-11-10 Garbage classification recycling system based on internet

Country Status (1)

Country Link
CN (1) CN112347949A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112906565A (en) * 2021-02-18 2021-06-04 陈星衍 Community garbage delivery traceability system based on smart city
CN113844785A (en) * 2021-09-10 2021-12-28 杭州道法环境科技有限公司 Multi-stage intelligent garbage classification management system and method
CN116329237A (en) * 2023-04-06 2023-06-27 广州拓源电子科技有限公司 Intelligent recycling system based on visual recognition

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112906565A (en) * 2021-02-18 2021-06-04 陈星衍 Community garbage delivery traceability system based on smart city
CN113844785A (en) * 2021-09-10 2021-12-28 杭州道法环境科技有限公司 Multi-stage intelligent garbage classification management system and method
CN113844785B (en) * 2021-09-10 2023-02-28 杭州道法环境科技有限公司 Multi-stage intelligent garbage classification management system and method
CN116329237A (en) * 2023-04-06 2023-06-27 广州拓源电子科技有限公司 Intelligent recycling system based on visual recognition
CN116329237B (en) * 2023-04-06 2023-11-03 广州拓源电子科技有限公司 Intelligent recycling system based on visual recognition

Similar Documents

Publication Publication Date Title
CN112347949A (en) Garbage classification recycling system based on internet
Antonie et al. Text document categorization by term association
CN105956184B (en) Collaborative and organized junk information issue the recognition methods of group in a kind of microblogging community network
CN112407653B (en) Garbage classification system based on Internet of things
CN110654739A (en) Machine vision-based automatic recyclable garbage classification recycling device and method
CN110442568A (en) Acquisition methods and device, storage medium, the electronic device of field label
CN111186656A (en) Target garbage classification method and intelligent garbage can
CN103166830A (en) Spam email filtering system and method capable of intelligently selecting training samples
CN109902953A (en) A kind of classification of power customers method based on adaptive population cluster
CN102915447A (en) Binary tree-based SVM (support vector machine) classification method
CN108228853A (en) A kind of microblogging rumour recognition methods and system
CN111498327B (en) System and method for improving garbage classification accuracy based on block chain technology
CN109902740A (en) It is a kind of based on more algorithm fusions it is parallel learn Industry Control intrusion detection method again
CN111242161B (en) Non-invasive non-resident user load identification method based on intelligent learning
CN103336771A (en) Data similarity detection method based on sliding window
CN108596637A (en) A kind of electric business service problem discovery system
CN110738131A (en) Garbage classification management method and device based on deep learning neural network
CN112478488B (en) Automatic garbage sorting and collecting system and method
CN111832749B (en) Garbage bag identification method and related device
CN113935398A (en) Network traffic classification method and system based on small sample learning in Internet of things environment
Chen et al. Evaluation of decision forests on text categorization
CN113705664B (en) Model, training method and surface electromyographic signal gesture recognition method
CN108763242A (en) Label generating method and device
CN111498326A (en) Automatic garbage classifier based on two-class recognition model
CN111311178A (en) Intelligent garbage classification transfer traceable system

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20210209

WW01 Invention patent application withdrawn after publication