CN115640937A

CN115640937A - Garbage classification index evaluation method and device, electronic equipment and storage medium

Info

Publication number: CN115640937A
Application number: CN202211095902.9A
Authority: CN
Inventors: 赵骥; 齐晓锐; 吴教丰
Original assignee: Yangtze Delta Region Institute of Tsinghua University Zhejiang
Current assignee: Yangtze Delta Region Institute of Tsinghua University Zhejiang
Priority date: 2022-09-08
Filing date: 2022-09-08
Publication date: 2023-01-24

Abstract

The application provides a method and a device for evaluating a garbage classification index, an electronic device and a storage medium, wherein the method comprises the following steps: the method comprises the steps of obtaining garbage collection and transportation data, preprocessing data and a preprocessing mode of an object to be evaluated, wherein the garbage collection and transportation data are data obtained when garbage is collected and transported, the preprocessing data are data obtained when the garbage is sorted in a processing plant, and the preprocessing mode is a mode adopted for sorting wrongly-sorted garbage from the garbage; and inputting the garbage collection and transportation data and the preprocessed data into a corresponding classification index evaluation model according to a preprocessing mode to obtain a garbage classification index of the object to be evaluated, wherein the classification index evaluation model is used for evaluating the garbage classification index of the object to be evaluated. Through the method and the device, the problem that the kitchen waste cannot be effectively classified and supervised in the related technology is solved, and catering merchants are stimulated to improve source classification quality.

Description

Garbage classification index evaluation method and device, electronic equipment and storage medium

Technical Field

The present invention relates to the field of garbage classification processing technologies, and in particular, to a method and an apparatus for evaluating a garbage classification index, an electronic device, and a storage medium.

Background

The rapid development of the catering industry and the continuous improvement of the living standard of residents effectively promote the explosive growth of the production amount of kitchen waste, and the environmental and ecological problems brought by the kitchen waste are increasingly obvious. The kitchen waste treatment mainly comprises three links of waste collection and transportation, pretreatment and resource utilization. Poor source classification of the kitchen waste is a key factor causing problems of high pretreatment cost, large equipment damage and the like. When the separation effect of the inert substances such as plastics, chopsticks, bottle caps and the like in the kitchen waste is poor, the damage to the three-phase separation equipment is aggravated, and the biogas yield and the operation stability of an anaerobic system are influenced. In the prior art, in order to effectively remove inert substances in kitchen waste, a pretreatment process link is long, equipment investment, occupied area and operation cost in a pretreatment stage are increased, and organic matters are lost too much in a screening process. Therefore, realizing effective classification of the sources of the kitchen waste is the best method for effectively removing inert substances.

The kitchen waste and the kitchen waste of the residential community have large difference in the form and composition, the kitchen waste is bagged waste of residential communities and has low water content, and the kitchen waste is barreled waste generated in restaurants, restaurants or dining halls and has high water content (80-90%). When the kitchen garbage of the community is classified, some communities specially distribute garbage classification supervisors, and some communities adopt an integral reward mechanism, so that the kitchen garbage classification enthusiasm of residents of the community is strong, and the classification quality is high. However, restaurant and catering enterprises have low awareness of classifying the kitchen waste, so that a large amount of impurities are mixed in the kitchen waste. Due to the great difference in form and composition between the kitchen waste and the kitchen waste, the classification and supervision method for the kitchen waste is not suitable for the kitchen waste, and the related technologies cannot effectively classify and supervise the kitchen waste.

Therefore, it is necessary to research and develop a method for evaluating a source classification index of kitchen waste, so as to evaluate a source classification effect through the classification index and effectively mobilize the classification enthusiasm of the kitchen waste in the catering industry.

Disclosure of Invention

The application provides a method and a device for evaluating a garbage classification index, electronic equipment and a storage medium, which are used for solving the problem that the kitchen garbage cannot be effectively classified and supervised in the related technology.

According to an aspect of an embodiment of the present application, there is provided a method for evaluating a garbage classification index, the method including:

the method comprises the steps of obtaining garbage collection and transportation data, preprocessing data and a preprocessing mode of an object to be evaluated, wherein the garbage collection and transportation data are obtained when garbage is collected and transported, the preprocessing data are obtained when the garbage is sorted in a processing plant, and the preprocessing mode is a mode adopted for sorting wrongly-sorted garbage from the garbage;

and inputting the garbage collection and transportation data and the preprocessed data into a corresponding classification index evaluation model according to the preprocessing mode to obtain a garbage classification index of the object to be evaluated, wherein the classification index evaluation model is used for evaluating the garbage classification index of the object to be evaluated.

According to another aspect of the embodiments of the present application, there is also provided a device for evaluating a garbage classification index, the device including:

the system comprises an acquisition module, a pre-processing module and a pre-processing module, wherein the acquisition module is used for acquiring garbage collection and transportation data, pre-processing data and a pre-processing mode of an object to be evaluated, the garbage collection and transportation data is acquired when garbage is collected and transported, the pre-processing data is acquired when the garbage is sorted in a processing plant, and the pre-processing mode is a mode adopted for sorting the garbage with wrong classification from the garbage;

and the obtaining module is used for inputting the garbage collection and transportation data and the preprocessed data into a corresponding classification index evaluation model according to the preprocessing mode to obtain a garbage classification index of the object to be evaluated, wherein the classification index evaluation model is used for evaluating the garbage classification index of the object to be evaluated.

Optionally, the obtaining module includes:

a first judgment unit configured to judge whether or not a foreign matter weight of a foreign matter belonging to the object to be evaluated can be acquired from the preprocessing data if the preprocessing mode is rough sorting, wherein the foreign matter is the misclassified garbage;

a first acquisition unit configured to acquire a foreign matter weight of a foreign matter belonging to the object to be evaluated from the preprocessing data and acquire a trash weight belonging to the object to be evaluated from the trash collection and transportation data, in a case where the foreign matter weight can be acquired from the preprocessing data;

the first generation unit is used for generating a first preset formula according to the weight of the garbage and the weight of the foreign matters;

the first obtaining unit is used for obtaining a first classification index evaluation model according to the first preset formula, wherein the first classification index evaluation model is a sub-model of the classification index evaluation model.

A second judging unit, configured to judge whether a foreign matter weight of a foreign matter belonging to the object to be evaluated can be obtained from the pre-processing data, if so, input the garbage collection and transportation data and the pre-processing data into the first classification index evaluation model to obtain an evaluation index belonging to the object to be evaluated, and if not, input the garbage collection and transportation data and the pre-processing data into the second classification index evaluation model to obtain an evaluation index belonging to the object to be evaluated;

the second obtaining unit is used for obtaining a first preset number of historical evaluation indexes belonging to the object to be evaluated, wherein the historical evaluation indexes are evaluation indexes of other batches of garbage belonging to the object to be evaluated;

and the second obtaining unit is used for obtaining the garbage classification index according to the evaluation index, the historical evaluation index and a third preset formula.

A third determination unit configured to, if the preprocessing mode is fine sorting, obtain foreign substance categories of all the foreign substances from the preprocessing data, and determine whether or not a foreign substance quantity of each of the foreign substance categories belonging to the object to be evaluated can be obtained from the preprocessing data;

a third obtaining unit, configured to obtain the amount of the foreign substances according to the waste collection and transportation data, the pre-processing data, and a first preset method if the amount of the foreign substances cannot be obtained, and directly obtain the amount of the foreign substances from the pre-processing data if the amount of the foreign substances can be obtained;

a fourth obtaining unit, configured to perform damage level division on the foreign matter category to obtain a damage level corresponding to the foreign matter category;

and the second generation unit is used for generating an initial evaluation network by taking the foreign matter category as a leaf node, taking the damage level as a middle layer node and taking the classification index as a root node.

The third acquisition unit is used for acquiring historical data from a historical database, wherein the historical data comprises historical foreign matter categories, historical foreign matter quantity and corresponding historical classification indexes;

the training unit is used for training the initial evaluation network through the historical data to obtain a target evaluation network;

and a fifth obtaining unit, configured to obtain a third classification index evaluation model based on the target evaluation network, where the third classification index evaluation model is a sub-model of the classification index evaluation model.

A sixth obtaining unit, configured to obtain, according to the quantity of the alien substances, a leaf node probability that the leaf node is in each preset quantity state, where the preset quantity state is used to indicate the quantity of the alien substances of the alien substance category corresponding to the node;

a seventh obtaining unit, configured to obtain an intermediate layer probability of the intermediate layer node according to a second preset number of the leaf node probabilities corresponding to the intermediate layer node, where the intermediate layer probability is a probability of the preset number of the intermediate layer node when the preset number of the second preset number of the leaf nodes is determined;

an eighth obtaining unit, configured to obtain probabilities of a third preset number of classification indexes according to the intermediate layer probability and a second preset method;

and the unit is used for taking the classification index with the maximum probability as the garbage classification index.

Optionally, the first judging unit includes:

a first obtaining sub-module configured to obtain, when a foreign matter weight of a foreign matter belonging to the object to be evaluated cannot be obtained from the pre-processing data, a total weight of trash of a corresponding lot from the garbage collection and transportation data, and obtain a total weight of the foreign matter of the corresponding lot from the pre-processing data;

the generation submodule is used for generating a second preset formula according to the total weight of the garbage and the total weight of the foreign matters;

and the first obtaining submodule is used for obtaining a second classification index evaluation model according to the second preset formula, wherein the second classification index evaluation model is a submodel of the classification index evaluation model.

Optionally, the third obtaining unit includes:

a second obtaining sub-module, configured to obtain the weight of the garbage belonging to the object to be evaluated and the total weight of the garbage of a corresponding batch from the garbage collection and transportation data, and obtain the total amount of the foreign substances of each foreign substance category of the corresponding batch from the pre-processing data;

and the second obtaining submodule is used for respectively obtaining the foreign matter quantity of each foreign matter category belonging to the object to be evaluated according to the garbage weight, the garbage total weight, the total foreign matter quantity and a fourth preset formula.

According to another aspect of the embodiments of the present application, there is also provided an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory communicate with each other through the communication bus; wherein the memory is used for storing the computer program; a processor for performing the method steps in any of the above embodiments by running the computer program stored on the memory.

According to a further aspect of the embodiments of the present application, there is also provided a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to perform the method steps of any of the above embodiments when the computer program is executed.

In the embodiment of the application, garbage collection and transportation data, preprocessing data and a preprocessing mode of an object to be evaluated are obtained, wherein the garbage collection and transportation data are data obtained when garbage is collected and transported, the preprocessing data are data obtained when the garbage is sorted in a processing plant, and the preprocessing mode is a mode adopted for sorting wrongly-sorted garbage from the garbage; and inputting the garbage collection and transportation data and the preprocessed data into a corresponding classification index evaluation model according to a preprocessing mode to obtain a garbage classification index of the object to be evaluated, wherein the classification index evaluation model is used for evaluating the garbage classification index of the object to be evaluated. According to the method and the device for evaluating the garbage classification indexes of the objects to be evaluated, the receiving and transporting data and the preprocessing data of the objects to be evaluated are obtained, and then the garbage classification indexes of the objects to be evaluated are evaluated through the corresponding classification index evaluation models according to the preprocessing mode. On one hand, the garbage classification condition of the object to be evaluated can be accurately reflected through the garbage classification index, and on the other hand, different classification index evaluation models are built according to different preprocessing modes, so that the application range is wider, and the obtained garbage classification index is more accurate. The problem that the kitchen waste cannot be effectively classified and supervised in the related technology is solved, and catering merchants are stimulated to improve source classification quality.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.

FIG. 1 is a schematic flow chart diagram illustrating an alternative method for evaluating a garbage classification index according to an embodiment of the present application;

fig. 2 is a flowchart of an alternative kitchen waste source classification index evaluation method according to an embodiment of the application;

fig. 3 is a detailed flowchart of an alternative kitchen waste source classification index evaluation method according to an embodiment of the present application;

FIG. 4 is a diagram of an alternative Bayesian network model according to an embodiment of the present application;

fig. 5 is a structural diagram of an optional kitchen waste source classification index evaluation system according to an embodiment of the present application;

FIG. 6 is a block diagram of an alternative garbage classification index evaluation apparatus according to an embodiment of the present application;

fig. 7 is a block diagram of an alternative electronic device according to an embodiment of the application.

Detailed Description

In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

The method has the advantages that data of the kitchen waste collection and transportation and pretreatment processes are collected, the classification effect of the kitchen waste source is evaluated according to the data, the classification of the kitchen waste source is objectively and truly reflected, and the kitchen waste source is conveniently supervised. Through the garbage classification index, not only can the classified source of kitchen waste be traced back, but also the punishment excitation mechanism of the classified kitchen waste source can be determined as a reference, the garbage classification enthusiasm of the catering industry is effectively mobilized, and the classification quality of the garbage source is improved, so that the kitchen waste pretreatment time is shortened, and the efficient recycling of organic matters is improved.

According to an aspect of an embodiment of the present application, there is provided a method for evaluating a garbage classification index, as shown in fig. 1, the method may include the following steps:

step S101, garbage collection and transportation data, preprocessing data and a preprocessing mode of an object to be evaluated are obtained, wherein the garbage collection and transportation data are data obtained when garbage is collected and transported, the preprocessing data are data obtained when the garbage is sorted in a processing plant, and the preprocessing mode is a mode adopted for sorting wrongly-sorted garbage from the garbage.

Alternatively, the object to be evaluated may be a specific merchant, such as dining merchant i (merchant i). When the kitchen waste is collected and transported, the waste collection and transportation data of a merchant are obtained, namely the waste weight w of a catering merchant i is obtained by weighing the waste bin in the process of collection and transportation _ki And the garbage collection and transportation truck is delivered to the factory and is weighed and returned to the factory to obtain the total weight W of the kitchen garbage of the number k of the trucks _k And collecting the information of the collecting and transporting vehicle and the information of the collecting and transporting personnel.

The pretreatment mode is required to be considered when the pretreatment data is acquired, the pretreatment mode comprises extensive type separation and fine type separation, and when the pretreatment mode is extensive type separation, the total weight W of the kitchen waste in the same train number can be considered _k The total foreign matter weight wy of the kitchen waste in the same train number _k The weight of the kitchen waste of the merchant and the weight y of the foreign matter of the merchant obtained by the formula (2) _ki Formula (1) represents wy _k Is the total foreign matter weight. Wherein k represents the kth train numberAnd i represents the ith merchant. At this time, the preprocessed data includes wy _k Then, y is obtained from the formula (2) _ki 。

wy _k ＝∑ _i y _ki (1)

When the pretreatment mode is also rough sorting, the other one obtains y _ki The method is characterized in that gridding is carried out, each merchant is separated during transportation, and the foreign matter weight y of each merchant can be obtained through separate treatment during sorting by pretreatment _ki . At this time, the preprocessed data includes y _ki 。

When the pretreatment mode is fine sorting, such as manual sorting and intelligent sorting, the foreign matter category of the merchant and the number of foreign matters under each foreign matter category are obtained: n is a radical of an alkyl radical _ki1 ，n _ki2 ，…，n _kim ，n _kim The number of the foreign matters is expressed as the m-th foreign matter category corresponding to the ith merchant of the kth train number. Classifying the foreign matters according to the sorting quantity of the foreign matters of each class, wherein the class is c ₀ ,c ₁ ,c ₂ ,…,c _c The categories are incremented by the number of sorts, indicated by the numbers 0,1,2, \ 8230;, c. Performing preliminary evaluation on the classification index according to the influence degree of the foreign matters, wherein the classification index evaluation is decreased according to the satisfaction degree, and symbols s are respectively used _a ,s _b ,…,s _s Indicating the corresponding letter a, b, \8230;, s.

When the pretreatment mode is fine sorting, one method for obtaining the number of the foreign matters in each foreign matter category is grid management, and the method is fine sorting for each merchant independently. If the grid management cannot be carried out on each merchant, all merchants of the train are identical, the number of the foreign matters of each merchant is calculated according to the ratio of the weight of the kitchen waste of the merchant to the total weight, and at the moment, the preprocessing data comprise the foreign matter category of the train and the total number of the foreign matters under each foreign matter category.

And S102, inputting the garbage collection and transportation data and the preprocessed data into a corresponding classification index evaluation model according to a preprocessing mode to obtain a garbage classification index of the object to be evaluated, wherein the classification index evaluation model is used for evaluating the garbage classification index of the object to be evaluated.

Optionally, three classification index evaluation models are constructed by combining a pretreatment mode and whether the foreign matter information belonging to the catering merchant i can be definitely obtained. The corresponding pretreatment mode is extensive sorting, and the foreign matter weight y of the restaurant merchant i can be obtained _ki . The corresponding pretreatment mode is extensive sorting, but the weight y of foreign matters of the restaurant merchant i cannot be obtained _ki . The other corresponding preprocessing mode is fine sorting, and a classification index evaluation model based on the Bayesian network is constructed. And then, when the classification index of the object to be evaluated is evaluated, judging which classification index evaluation model is applicable, and inputting the garbage collection and transportation data and the preprocessed data into the applicable classification index evaluation model to obtain the garbage classification index of the catering merchant i.

In the embodiment of the application, garbage collection and transportation data, preprocessing data and a preprocessing mode of an object to be evaluated are obtained, wherein the garbage collection and transportation data are data obtained when garbage is collected and transported, the preprocessing data are data obtained when the garbage is sorted in a processing plant, and the preprocessing mode is a mode adopted for sorting wrongly-sorted garbage from the garbage; and inputting the garbage collection and transportation data and the preprocessed data into a corresponding classification index evaluation model according to a preprocessing mode to obtain a garbage classification index of the object to be evaluated, wherein the classification index evaluation model is used for evaluating the garbage classification index of the object to be evaluated. According to the method and the device for evaluating the garbage classification indexes of the objects to be evaluated, the receiving and transporting data and the preprocessing data of the objects to be evaluated are obtained, and then the garbage classification indexes of the objects to be evaluated are evaluated through the corresponding classification index evaluation models according to the preprocessing mode. On one hand, the garbage classification condition of the object to be evaluated can be accurately reflected through the garbage classification index, and on the other hand, different classification index evaluation models are constructed according to different preprocessing modes, so that the application range is wider, and the obtained garbage classification index is more accurate. The problem that the kitchen waste cannot be effectively classified and supervised in the related technology is solved, and catering merchants are stimulated to improve source classification quality.

As an alternative embodiment, before inputting the garbage collection and transportation data and the preprocessed data into the corresponding classification index assessment model according to the preprocessing mode, the method further comprises:

if the pretreatment mode is extensive sorting, judging whether the weight of foreign matters belonging to the object to be evaluated can be obtained from the pretreatment data, wherein the foreign matters are garbage with wrong classification;

acquiring the foreign matter weight and the garbage weight of the object to be evaluated from the garbage collection and transportation data under the condition that the foreign matter weight of the foreign matter belonging to the object to be evaluated can be acquired from the preprocessing data;

generating a first preset formula according to the weight of the garbage and the weight of the foreign matters;

and obtaining a first classification index evaluation model according to a first preset formula, wherein the first classification index evaluation model is a sub-model of the classification index evaluation model.

Alternatively, in the case where the pretreatment is extensive sorting, the weight y of the foreign matter belonging to the restaurant i is clearly obtained if it is possible to obtain the weight y of the foreign matter _ki Then pass y _ki Garbage weight w belonging to catering trade company i _ki And equation (3), i.e. the first predetermined equation, to obtain the evaluation index Q _ki Comprises the following steps:

and (4) constructing a first classification index evaluation model based on the formula (3).

In the embodiment of the application, the preliminary evaluation index can be directly obtained through the weight of the garbage and the weight of the foreign matters of the catering trade company, the method is suitable for the existing generally-adopted kitchen garbage collection and transportation and pretreatment method, the convenience and the rapidness are realized, and the evaluation efficiency is higher.

As an alternative embodiment, the judging whether the foreign substance weight of the foreign substance belonging to the object to be evaluated can be acquired from the preprocessed data includes:

under the condition that the foreign matter weight of the foreign matters belonging to the object to be evaluated cannot be obtained from the pretreatment data, obtaining the total weight of the garbage of a corresponding batch from the garbage collection and transportation data, and obtaining the total weight of the foreign matters of the corresponding batch from the pretreatment data;

generating a second preset formula according to the total weight of the garbage and the total weight of the foreign matters;

and obtaining a second classification index evaluation model according to a second preset formula, wherein the second classification index evaluation model is a sub-model of the classification index evaluation model.

Alternatively, in the case where the pretreatment is extensive sorting, the weight y of the foreign matter belonging to the restaurant house i is not obtained if it is not clear _ki And the total weight wy of the foreign matters in the kitchen waste passing through the kth train number _k And the total weight W of the kitchen waste of the kth train number _k And equation (4), i.e., a second predetermined equation, to obtain the evaluation index Q _ki Comprises the following steps:

and (4) constructing a second classification index evaluation model based on the formula (4).

In the embodiment of the application, under the condition that the weight of the foreign matters cannot be directly obtained, the weight of the foreign matters is obtained through calculation in the steps, so that the application scene of the application is wider.

As an optional embodiment, according to a preprocessing mode, inputting the garbage collection and transportation data and the preprocessed data into a corresponding classification index evaluation model, and obtaining the garbage classification index of the object to be evaluated includes:

judging whether the foreign matter weight of the foreign matters belonging to the object to be evaluated can be obtained from the preprocessed data, if so, inputting the garbage collection and transportation data and the preprocessed data into a first classification index evaluation model to obtain an evaluation index belonging to the object to be evaluated, and if not, inputting the garbage collection and transportation data and the preprocessed data into a second classification index evaluation model to obtain the evaluation index belonging to the object to be evaluated;

acquiring a first preset number of historical evaluation indexes belonging to an object to be evaluated, wherein the historical evaluation indexes are evaluation indexes of other batches of garbage belonging to the object to be evaluated;

and obtaining the garbage classification index according to the evaluation index, the historical evaluation index and a third preset formula.

Alternatively, in the case where the pretreatment is extensive sorting, the weight y of the foreign matter belonging to the restaurant i is clearly obtained if it is possible to obtain the weight y of the foreign matter _ki Then, a first classification index evaluation model is adopted, and if the weight y of the foreign matters belonging to the catering merchant i cannot be definitely obtained _ki The model is evaluated using the second classification index.

Obtaining an evaluation index Q according to an applicable classification index evaluation model _ki Then, combining the evaluation indexes obtained by catering merchants i in different delivery vehicle numbers, firstly carrying out Q treatment on a plurality of vehicle numbers according to a formula (5) _ki Averaging to obtain Q _i And obtaining the final value of the garbage classification index Q according to a formula (6), namely a third preset formula.

Wherein sum (k) represents the total number of the train numbers, and the garbage classification indexes a, b, c and d are decreased progressively according to the satisfaction degree, and sequentially represent: very satisfactory, unsatisfactory, very unsatisfactory.

In the embodiment of the application, the evaluation indexes of a plurality of vehicle numbers are averaged, and a final classification index is obtained based on the average, wherein the classification index can reflect the classification quality of merchants more truly.

if the pretreatment mode is fine sorting, acquiring the foreign matter categories of all foreign matters from the pretreatment data, and judging whether the foreign matter quality quantity of each foreign matter category belonging to the object to be evaluated can be acquired from the pretreatment data;

if the quantity of the foreign matters cannot be obtained, obtaining the quantity of the foreign matters according to the garbage collection and transportation data, the pretreatment data and a first preset method, and if the quantity of the foreign matters can be obtained, directly obtaining the quantity of the foreign matters from the pretreatment data;

carrying out damage grade division on the foreign matter types to obtain damage grades corresponding to the foreign matter types;

and (4) generating an initial evaluation network by taking the foreign matter category as a leaf node, taking the damage level as an intermediate layer node and taking the classification index as a root node.

Acquiring historical data from a historical database, wherein the historical data comprises historical foreign matter categories, historical foreign matter quantity and corresponding historical classification indexes;

training the initial evaluation network through historical data to obtain a target evaluation network;

and obtaining a third classification index evaluation model based on the target evaluation network, wherein the third classification index evaluation model is a sub-model of the classification index evaluation model.

Optionally, in the case that the pretreatment mode is fine sorting, the foreign matter category and the corresponding foreign matter quantity are obtained, and if the foreign matter quantity cannot be directly obtained, the foreign matter quantity is obtained according to the garbage collection and transportation data, the pretreatment data and the first preset method.

The damage grades of the foreign matters are divided, so that in the efficient utilization of kitchen waste resources, the damage influence of a stainless steel cutter and a stainless steel spoon fork on the three-phase separation equipment is large, and the influence of ropes, beer bottle caps and the like is small. Therefore, the class of the foreign matters is divided into a damage level 1, a damage level 2 and a damage level 3 according to the damage degree of the machine equipment, the larger the level number is, the larger the damage influence of the foreign matters on the equipment is, for example, a stainless steel tool, and if the foreign matters occur in a treatment process link, the larger damage of the equipment can be caused. In this embodiment, there are six kinds of foreign matter categories including stainless steel spoon fork, stainless steel knife, plastic bag, plastic bottle, rope, beer bottle lid, and wherein, the wearing and tearing influence of stainless steel knife, stainless steel spoon fork to three-phase splitter is bigger, divides it into damage 3 level node, divides plastic bottle and plastic bag into damage 2 level node, because influence such as rope, beer bottle lid is less, divides it into damage 1 level node. Which together determine the index of classification of the kitchen waste.

An initial evaluation network is generated through a bayesian network, as shown in fig. 4, fig. 4 is an alternative bayesian network model diagram according to the embodiment of the present application, and the kitchen waste classification index is taken as a result node, i.e. a root node, and the state of the kitchen waste classification index is very satisfactory, unsatisfactory, and very unsatisfactory, which is denoted by a, b, c, and d. The foreign matter category is used as an influence node, namely a leaf node, the states of the foreign matter category are small, medium and large, and are respectively represented by 0,1,2, and the damage level is an intermediate layer node.

And then, training the structural parameters of the Bayesian network according to historical data acquired by kitchen garbage collection and transportation and pretreatment. And taking the trained Bayesian network as a target evaluation network, and obtaining a third classification index evaluation model.

In addition, the embodiment only provides a network structure, actually, the kitchen waste has a plurality of different types of foreign substances, different processing plants and different receiving and transporting sources, when a bayesian network structure is constructed, the considered influence nodes have respective emphasis, the corresponding dimensionalities of further division are different, and cross and interdependence relationships also exist among the bayesian network nodes. For example, the spoon fork category is used as a node and comprises a stainless steel spoon fork and a plastic spoon fork, and the node belongs to a damage level 3 node and a damage level 2 node. Each node can be modified according to the use requirement.

In the embodiment of the application, a classification index evaluation model is built based on a Bayesian network, the foreign matter categories are used as leaf nodes, the damage levels are used as middle level nodes, and the classification indexes are used as root nodes, so that the classification indexes obtained by the classification index evaluation model are more accurate, a plurality of influence factors can be comprehensively considered, and the evaluation efficiency is higher.

As an alternative example, if the foreign matter amount cannot be acquired, obtaining the foreign matter amount according to the garbage collection and transportation data, the preprocessing data and the first preset method comprises:

acquiring the weight of the garbage belonging to the object to be evaluated and the total weight of the garbage of a corresponding batch from the garbage collection and transportation data, and acquiring the total foreign matter quantity of each foreign matter category of the corresponding batch from the pretreatment data;

and respectively obtaining the foreign matter quantity of each foreign matter category belonging to the object to be evaluated according to the garbage weight, the garbage total weight, the total foreign matter quantity and a fourth preset formula.

Optionally, when the pretreatment mode is fine sorting, if each merchant cannot be managed in a gridding mode, all merchants of the train are equal, the number of the foreign matters of each merchant is calculated according to the ratio of the weight of the kitchen waste of the merchant to the total weight, and the kth train corresponds to the number n of the mth foreign matters of the i merchants _kim Comprises the following steps:

wherein n is _km For the total number of foreign matters in the mth foreign matter category of the kth train number, the calculation processes of the total number of foreign matters in other foreign matter categories are similar, and are not described again here.

In the embodiment of the application, under the condition that the foreign matter prime number cannot be directly obtained, the foreign matter number is obtained through the calculation of the steps, so that the application scene of the application is wider.

As an optional embodiment, according to the preprocessing mode, inputting the garbage collection and transportation data and the preprocessed data into a corresponding classification index evaluation model, and obtaining the garbage classification index of the object to be evaluated includes:

obtaining leaf node probabilities of the leaf nodes in each preset number state according to the number of the foreign matters, wherein the preset number state is used for representing the number of the foreign matters of the foreign matter type corresponding to the node;

obtaining the intermediate layer probability of the intermediate layer node according to the second preset number of leaf node probabilities corresponding to the intermediate layer node, wherein the intermediate layer probability is the probability of the intermediate layer node in the preset number state respectively under the condition that the preset number state of the second preset number of leaf nodes is determined;

obtaining the probability of a third preset number of classification indexes according to the intermediate layer probability and a second preset method;

and taking the classification index with the maximum probability as the garbage classification index.

Optionally, the category of the foreign matter of the merchant to be evaluated and the corresponding foreign matter prime number are obtained to obtain a leaf probability table of the leaf node, and the leaf probability is a prior probability of the bayesian network.

Wherein 0,1,2 represents the foreign matter category number state of the leaf node, and the state is small, medium or large. Taking stainless steel knives-category 0-0.9 as an example, the probability that the number of stainless steel knives is small is 0.9.

And then, obtaining the probability of the intermediate layer node according to the leaf node probabilities of the leaf nodes corresponding to different intermediate layer nodes. Taking the damage level 3 node as an example, the middle layer probability table of the corresponding damage level 3 node is obtained according to the leaf node probability of the stainless steel knife and the stainless steel spoon fork, and the middle layer probability is the conditional probability of the bayesian network.

State of state	0	1	2
				00	0.9	0.05	0.05
01	0.65	0.32	0.03
				02	0.01	0.45	0.54
10	0.35	0.62	0.03
				11	0.04	0.95	0.01
12	0.07	0.8	0.13
				20	1	0	0
21	0	1	0
				22	0.0	0	1

The states 0,1, and 2 represent the foreign substance type number states representing the intermediate level nodes, and the states are small, medium, and large. Taking 01-1 as 0.32 as an example, it shows that when the number state of the stainless steel knife is 0 (small amount), and the state of the stainless steel spoon/fork is 1 (medium), the probability of damaging the state corresponding to the tertiary node is 1 (medium) is 0.32. In addition, the value of each row is added to 1, and the probability values are calculated according to the statistical data. The process of obtaining the probability of other intermediate layer nodes is similar to the above process, and is not described herein again.

And calculating to obtain a result of the kitchen waste source classification index according to the intermediate layer probability and a Bayesian inference method, such as an accurate inference or a elimination method. The result is not an exact value, but a probability value of different classification indexes is obtained, and the classification index with the highest occurrence probability is the desired garbage classification index, as shown in the following table:

classification index evaluation	Probability p
		a	0.8815
b	0.0255
		c	0.0450
d	0.0481

Wherein a, b, c, d represent very satisfactory, unsatisfactory, very unsatisfactory, respectively. And taking the classification index a with the probability P of 0.8815 as a garbage classification index, namely, the classification state of the kitchen garbage of the object to be evaluated is very satisfactory.

In the embodiment of the application, the prior probability of the leaf node is calculated firstly, the conditional probability of the intermediate node is calculated through the prior probability, the probability values of different classification indexes are obtained according to the conditional probability, the maximum probability is the garbage classification index, the garbage classification index obtained in the way can accurately reflect the kitchen waste classification condition of each merchant, and the problem that the kitchen waste cannot be effectively classified and supervised in the related technology is solved.

As an alternative embodiment, fig. 2 is a flowchart of an alternative kitchen waste source classification index evaluation method according to an embodiment of the present application, where the steps of the flowchart are as follows:

step S201, collecting data of the kitchen waste collection and transportation-pretreatment stage.

And S202, constructing a source kitchen waste classification index evaluation model based on the kitchen waste collection data.

And S203, performing source kitchen waste classification index evaluation on the merchant to be evaluated based on the index evaluation model.

Alternatively, taking a kitchen waste collection and transportation-pretreatment production line of an environmental protection science and technology company as an example, before the waste collection and transportation vehicle departs from a treatment plant, the collected data includes: basic information of the vehicle, information of the receiving and transporting personnel, and initial weight of the receiving and transporting vehicle. And when the kitchen waste is received and transported, recording the weight of the catering trade company and the kitchen waste received and transported, and calculating according to 240L of each garbage can if the catering trade company has no weighing condition.

After the garbage collection and transportation vehicle returns to the treatment plant, the collected data comprise: basic information of the vehicle, information of the receiving and transporting personnel, the current weight of the receiving and transporting vehicle, the tracing back of a closed loop and the determination of the total received and transported garbage weight. And after weighing for multiple times, the weight of the kitchen waste is within an allowable error, otherwise, the weight of the kitchen waste of each catering merchant is finely adjusted.

In the pretreatment link of a treatment plant, foreign matters in the kitchen waste are sorted, wherein the foreign matters refer to impurities which are difficult to enter the next process link in solid materials formed by dehydrating the kitchen waste.

When the separation process is extensive separation, such as automatic separation equipment, the foreign matters are mixed together to obtain the weight y of the foreign matters _ki Total foreign matter weight wy _k . Wherein y is _ki Represents the foreign matter weight, wy, of the ith merchant of the kth train _k The total weight of foreign matters of the kth train is the sum of the weights of foreign matters of all merchants collected and transported by the kth train, and the formula is as follows:

wy _k ＝∑ _i y _ki (8)

when the sorting process is fine sorting, the category and the number of the foreign matters are obtained at the moment. There are many different kinds of foreign substances, such as stainless steel, porcelain, plastic, metal, bamboo, and the like. The foreign matter that will select separately in this embodiment divides into 6 types, is stainless steel sword, plastic bottle, plastic bag, ladle fork, rope, beer bottle lid respectively. The foreign matters are classified into small, medium and large quantities according to the sorting quantity of each type of foreign matters, and the numbers are 0,1,2. The classification index evaluation is progressively decreased according to the satisfaction degree, and the classification is as follows: very satisfactory, unsatisfactory, very unsatisfactory, denoted a, b, c, d.

And after the final source classification index is obtained, filling information such as the number, quantity category, weight, source classification index, receiving and transporting vehicles, receiving and transporting personnel, receiving and transporting merchants and the like of the stainless steel bars, plastics and other foreign matters into corresponding tables.

The step of constructing a source kitchen waste classification index evaluation model based on the kitchen waste collection data refers to the steps of constructing a first classification index evaluation model based on the formula (3), constructing a second classification index evaluation model based on the formula (4), taking the trained Bayesian network as a target evaluation network, obtaining a third classification index evaluation model and the like, and is not repeated here.

Based on the index evaluation model, performing source kitchen waste classification index evaluation on the merchant to be evaluated, wherein the detailed steps refer to step S102, which is not described herein again.

In the embodiment of the application, data of the kitchen waste collection, transportation and pretreatment stages are collected firstly, a kitchen waste classification index evaluation model is established based on the data, the kitchen waste classification index is evaluated through the model, the classification effect of each merchant on the kitchen waste is reflected through the waste classification index, and the problem that the kitchen waste cannot be classified and supervised effectively in the related art is solved.

As an alternative embodiment, fig. 3 is a detailed flowchart of an alternative kitchen waste source classification index evaluation method according to an embodiment of the present application, where the steps of the flowchart are as follows:

collecting data of the kitchen waste collection and transportation stage, collecting data of the kitchen waste pretreatment stage, judging whether the pretreatment mode is extensive sorting, if so, collecting weight of foreign matters corresponding to a merchant, constructing a kitchen waste source classification index evaluation model, evaluating the source classification index, and finally putting an obtained classification index result into a historical database, for example, counting the classification quality of a certain merchant according to historical data, wherein the result is taken as the historical data in the next counting, and after multiple times of counting, the classification index evaluation can more and more truly reflect the classification quality of the merchant. If the sorting is not extensive, acquiring the number of the foreign matter categories corresponding to the merchants, constructing a Bayesian network structure, counting Bayesian network node variables and calculating classification indexes by an inference method to construct a Bayesian network structure-based kitchen waste source classification index evaluation model, then performing source classification index evaluation according to the model, and finally putting the obtained classification index result into a historical database.

In the embodiment of the application, two ways are adopted to evaluate the classification index of the merchant according to whether the sorting is extensive, so that the application scene of the method is wider, and the obtained classification index of the kitchen waste source is more accurate.

As an alternative embodiment, fig. 5 is a structural diagram of an alternative kitchen waste source classification index evaluation system according to an embodiment of the present application, where the system includes:

the kitchen waste source classification index evaluation and tracing system comprises: the system comprises a data acquisition and management function module, a source classification index evaluation module and an operation management module. Several functional blocks are described in detail below.

And the data acquisition and management functional module is used for acquiring and managing data in the kitchen waste collection and transportation-pretreatment process. The data acquisition and management function module comprises a merchant information management unit, a receiving and transporting data acquisition management unit and a preprocessing data acquisition management unit.

And the merchant information management unit is used for performing basic information management on merchants associated with the kitchen waste treatment enterprise, and comprises merchant names, merchant categories, merchant positions, and a receiving and transporting garbage can corresponding to the merchants and the like.

And the collecting and transporting data collecting and managing unit is used for collecting and managing the data of the collecting and transporting vehicles, the collecting and transporting personnel and the garbage collecting and transporting weight.

And the pretreatment data acquisition and management unit is used for carrying out data acquisition and management on the sorting of the foreign matters pretreated by the kitchen waste.

And the source classification index evaluation module is used for evaluating the source merchant kitchen waste classification index. The source classification index evaluation module comprises a Bayesian network construction unit, a parameter learning unit and a Bayesian network reasoning unit.

And the Bayesian network construction unit is used for constructing a Bayesian network structure according to the foreign matter categories and the dependency relationship among the foreign matter categories.

And the parameter learning unit is used for performing data training according to the data acquired by the data acquisition and management function module to obtain a probability table of each node of the Bayesian network structure.

And the Bayesian network reasoning unit is used for evaluating the kitchen waste classification index of the source merchant according to a reasoning method.

And the operation management module is used for managing results, publishing information, collecting and transporting statistics and the like.

In the embodiment of the application, a kitchen waste source classification index evaluation system composed of modules and units is designed, and the kitchen waste source classification index evaluation method is implemented. Each module and each unit are designed to execute corresponding tasks respectively, so that the efficiency and the accuracy of evaluating the classification index of the kitchen waste source are improved, and the problem that the kitchen waste cannot be effectively classified and supervised in the related technology is solved.

According to another aspect of the embodiment of the present application, there is also provided an apparatus for evaluating a garbage classification index, which is used for implementing the above method for evaluating a garbage classification index. Fig. 6 is a block diagram of an alternative apparatus for evaluating a garbage classification index according to an embodiment of the present application, and as shown in fig. 6, the apparatus may include:

the obtaining module 601 is configured to obtain garbage collection and transportation data, preprocessing data and a preprocessing mode of an object to be evaluated, where the garbage collection and transportation data is obtained when garbage is collected and transported, the preprocessing data is obtained when garbage is sorted in a processing plant, and the preprocessing mode is a mode used for sorting out wrongly-sorted garbage from garbage;

the obtaining module 602 is configured to input the garbage collection and transportation data and the preprocessed data into a corresponding classification index evaluation model according to a preprocessing mode, so as to obtain a garbage classification index of the object to be evaluated, where the classification index evaluation model is used to evaluate the garbage classification index of the object to be evaluated.

Through the modules, the receiving and transporting data and the preprocessing data of the object to be evaluated are obtained firstly, and then the garbage classification index of the object to be evaluated is evaluated through the corresponding classification index evaluation model according to the preprocessing mode. On one hand, the garbage classification condition of the object to be evaluated can be accurately reflected through the garbage classification index, and on the other hand, different classification index evaluation models are constructed according to different preprocessing modes, so that the application range is wider, and the obtained garbage classification index is more accurate. The problem that the kitchen waste cannot be effectively classified and supervised in the related technology is solved, and catering merchants are stimulated to improve source classification quality.

As an alternative embodiment, the obtaining module includes:

a first judging unit configured to judge whether a foreign matter weight of a foreign matter belonging to an object to be evaluated can be acquired from the preprocessed data if the preprocessing mode is rough sorting, wherein the foreign matter is garbage with a wrong classification;

a first acquisition unit configured to acquire a foreign matter weight of foreign matter belonging to an object to be evaluated from the pre-processing data and acquire a trash weight belonging to the object to be evaluated from the trash collection and transportation data, in a case where the foreign matter weight of the foreign matter belonging to the object to be evaluated can be acquired from the pre-processing data;

the first obtaining unit is used for obtaining a first classification index evaluation model according to a first preset formula, wherein the first classification index evaluation model is a sub-model of the classification index evaluation model.

The second judging unit is used for judging whether the foreign matter weight of the foreign matters belonging to the object to be evaluated can be obtained from the preprocessed data, if so, the garbage collection and transportation data and the preprocessed data are input into the first classification index evaluation model to obtain an evaluation index belonging to the object to be evaluated, and if not, the garbage collection and transportation data and the preprocessed data are input into the second classification index evaluation model to obtain the evaluation index belonging to the object to be evaluated;

A third judging unit configured to acquire the foreign matter categories of all the foreign matters from the preprocessed data and judge whether the foreign matter quality quantity of each foreign matter category belonging to the object to be evaluated can be acquired from the preprocessed data, if the preprocessing mode is the fine sorting;

a third obtaining unit, configured to obtain the quantity of the foreign substances according to the garbage collection and transportation data, the preprocessing data, and the first preset method if the quantity of the foreign substances cannot be obtained, and directly obtain the quantity of the foreign substances from the preprocessing data if the quantity of the foreign substances can be obtained;

a fourth obtaining unit, configured to perform damage level division on the foreign matter categories to obtain damage levels corresponding to the foreign matter categories;

and the second generation unit is used for generating an initial evaluation network by taking the foreign matter category as a leaf node, the damage level as an intermediate layer node and the classification index as a root node.

The third acquisition unit is used for acquiring historical data from the historical database, wherein the historical data comprises historical foreign matter categories, historical foreign matter quantity and corresponding historical classification indexes;

the training unit is used for training the initial evaluation network through historical data to obtain a target evaluation network;

and the fifth obtaining unit is used for obtaining a third classification index evaluation model based on the target evaluation network, wherein the third classification index evaluation model is a sub-model of the classification index evaluation model.

A sixth obtaining unit, configured to obtain, according to the number of the alien substances, a leaf node probability that a leaf node is in each preset number state, where the preset number state is used to indicate the number of the alien substances of the alien substance category corresponding to the node;

a seventh obtaining unit, configured to obtain an intermediate layer probability of the intermediate layer node according to a second preset number of leaf node probabilities corresponding to the intermediate layer node, where the intermediate layer probability is a probability that the intermediate layer nodes are in a preset number state respectively when a preset number state of the second preset number of leaf nodes is determined;

As an alternative embodiment, the first judging unit includes:

a first obtaining sub-module, configured to obtain, from the garbage collection and transportation data, a total weight of garbage of a corresponding batch, and obtain, from the pre-processing data, a total weight of foreign matter of the corresponding batch, in a case where the weight of foreign matter belonging to the object to be evaluated cannot be obtained from the pre-processing data;

and the first obtaining submodule is used for obtaining a second classification index evaluation model according to a second preset formula, wherein the second classification index evaluation model is a submodel of the classification index evaluation model.

As an alternative embodiment, the third obtaining unit includes:

the second acquisition submodule is used for acquiring the weight of the garbage belonging to the object to be evaluated and the total weight of the garbage of a corresponding batch from the garbage collection and transportation data and acquiring the total foreign matter quantity of each foreign matter category of the corresponding batch from the pretreatment data;

It should be noted that the modules described above are the same as examples and application scenarios realized by corresponding steps, but are not limited to what is disclosed in the foregoing embodiments.

Fig. 7 is a block diagram of an alternative electronic device according to an embodiment of the present application, as shown in fig. 7, including a processor 701, a communication interface 702, a memory 703 and a communication bus 704, where the processor 701, the communication interface 702 and the memory 703 complete communication with each other through the communication bus 704, where,

a memory 703 for storing a computer program;

the processor 701 is configured to implement the following steps when executing the computer program stored in the memory 703:

the method comprises the steps of obtaining garbage collection and transportation data, preprocessing data and a preprocessing mode of an object to be evaluated, wherein the garbage collection and transportation data are data obtained when garbage is collected and transported, the preprocessing data are data obtained when the garbage is sorted in a processing plant, and the preprocessing mode is a mode adopted for sorting wrongly-sorted garbage from the garbage;

and inputting the garbage collection and transportation data and the preprocessed data into a corresponding classification index evaluation model according to a preprocessing mode to obtain a garbage classification index of the object to be evaluated, wherein the classification index evaluation model is used for evaluating the garbage classification index of the object to be evaluated.

Alternatively, in this embodiment, the communication bus may be a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 7, but that does not indicate only one bus or one type of bus.

The communication interface is used for communication between the electronic equipment and other equipment.

The memory may include RAM, and may also include non-volatile memory, such as at least one disk memory. Alternatively, the memory may be at least one memory device located remotely from the processor.

As an example, as shown in fig. 7, the memory 703 may include, but is not limited to, an obtaining module 601 and an obtaining module 602 in the evaluation apparatus for the garbage classification index. In addition, the evaluation apparatus may further include, but is not limited to, other module units in the evaluation apparatus for the garbage classification index, which is not described in detail in this example.

The processor may be a general-purpose processor, and may include but is not limited to: a CPU (Central Processing Unit), an NP (Network Processor), and the like; but also a DSP (Digital Signal Processing), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component.

Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment is not described herein again.

It can be understood by those skilled in the art that the structure shown in fig. 7 is only an illustration, and the device implementing the above method for evaluating a garbage classification index may be a terminal device, and the terminal device may be a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a Mobile Internet Device (MID), a PAD, and the like. Fig. 7 does not limit the structure of the electronic device. For example, the terminal device may also include more or fewer components (e.g., network interfaces, display devices, etc.) than shown in FIG. 7, or have a different configuration than shown in FIG. 7.

Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by a program instructing hardware associated with the terminal device, where the program may be stored in a computer-readable storage medium, and the storage medium may include: flash disk, ROM, RAM, magnetic or optical disk, and the like.

According to still another aspect of an embodiment of the present application, there is also provided a storage medium. Optionally, in this embodiment, the storage medium may be configured to store a program code for performing an evaluation method of a garbage classification index.

Optionally, in this embodiment, the storage medium may be located on at least one of a plurality of network devices in a network shown in the above embodiment.

Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps:

Optionally, the specific example in this embodiment may refer to the example described in the above embodiment, which is not described again in this embodiment.

Optionally, in this embodiment, the storage medium may include, but is not limited to: a U disk, a ROM, a RAM, a removable hard disk, a magnetic disk, or an optical disk.

In the description of the present specification, reference to the description of the terms "this embodiment," "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction. In the description of the present disclosure, "a plurality" means at least two, e.g., two, three, etc., unless explicitly specifically limited otherwise.

It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications derived therefrom are intended to be within the scope of the invention.

Claims

1. A method for evaluating a garbage classification index, the method comprising:

2. The method of claim 1, wherein prior to said inputting the garbage collection and transportation data and the preprocessed data into the corresponding classification index assessment model according to the preprocessing mode, the method further comprises:

if the pretreatment mode is extensive sorting, judging whether the weight of the foreign matters belonging to the foreign matters of the object to be evaluated can be acquired from the pretreatment data, wherein the foreign matters are the garbage with wrong classification;

in a case where a foreign matter weight of a foreign matter belonging to the object to be evaluated can be acquired from the preprocessing data, acquiring the foreign matter weight and acquiring a trash weight belonging to the object to be evaluated from the trash collection and transportation data;

and obtaining a first classification index evaluation model according to the first preset formula, wherein the first classification index evaluation model is a sub-model of the classification index evaluation model.

3. The method according to claim 2, wherein the determining whether or not a foreign matter weight of a foreign matter belonging to the object to be evaluated can be acquired from the preprocessed data includes:

in the case where the weight of foreign matter belonging to the foreign matter of the object to be evaluated cannot be obtained from the pretreatment data, obtaining the total weight of trash of a corresponding lot from the trash collection and transportation data, and obtaining the total weight of foreign matter of a corresponding lot from the pretreatment data;

and obtaining a second classification index evaluation model according to the second preset formula, wherein the second classification index evaluation model is a sub-model of the classification index evaluation model.

4. The method according to claim 3, wherein the step of inputting the garbage collection and transportation data and the preprocessed data into corresponding classification index evaluation models according to the preprocessing mode to obtain the garbage classification index of the object to be evaluated comprises the following steps:

judging whether the weight of the foreign matter belonging to the foreign matter of the object to be evaluated can be obtained from the preprocessed data, if so, inputting the garbage collection and transportation data and the preprocessed data into the first classification index evaluation model to obtain an evaluation index belonging to the object to be evaluated, and if not, inputting the garbage collection and transportation data and the preprocessed data into the second classification index evaluation model to obtain an evaluation index belonging to the object to be evaluated;

acquiring a first preset number of historical evaluation indexes belonging to the object to be evaluated, wherein the historical evaluation indexes are evaluation indexes of other batches of garbage belonging to the object to be evaluated;

5. The method of claim 1, wherein prior to said entering the garbage collection and transportation data and the pre-processed data into corresponding classification index assessment models according to the pre-processing mode, the method further comprises:

if the pretreatment mode is fine sorting, acquiring foreign matter categories of all foreign matters from the pretreatment data, and judging whether the foreign matter quality quantity of each foreign matter category belonging to the object to be evaluated can be acquired from the pretreatment data;

if the quantity of the foreign matters cannot be obtained, obtaining the quantity of the foreign matters according to the waste collection and transportation data, the pretreatment data and a first preset method, and if the quantity of the foreign matters can be obtained, directly obtaining the quantity of the foreign matters from the pretreatment data;

taking the foreign matter categories as leaf nodes, the damage levels as middle layer nodes and the classification indexes as root nodes to generate an initial evaluation network;

training the initial evaluation network through the historical data to obtain a target evaluation network;

6. The method of claim 5, wherein if the quantity of foreign matter is unavailable, obtaining the quantity of foreign matter based on the waste collection and transportation data, the pre-treatment data, and a first predetermined method comprises:

acquiring the weight of the garbage belonging to the object to be evaluated and the total weight of the garbage of the corresponding batch from the garbage collection and transportation data, and acquiring the total foreign matter quantity of each foreign matter category of the corresponding batch from the pretreatment data;

7. The method according to claim 6, wherein the step of inputting the garbage collection and transportation data and the preprocessed data into corresponding classification index evaluation models according to the preprocessing mode to obtain the garbage classification index of the object to be evaluated comprises the following steps:

obtaining leaf node probabilities that the leaf nodes are in each preset number state according to the quantity of the foreign matters, wherein the preset number states are used for representing the quantity of the foreign matters of the foreign matter type corresponding to the nodes;

obtaining the intermediate layer probability of the intermediate layer node according to a second preset number of leaf node probabilities corresponding to the intermediate layer node, wherein the intermediate layer probability is the probability of the preset number states of the intermediate layer node respectively under the condition that the preset number states of the second preset number of leaf nodes are determined;

8. An apparatus for evaluating a garbage classification index, comprising:

the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring garbage collection and transportation data, preprocessing data and a preprocessing mode of an object to be evaluated, the garbage collection and transportation data is data acquired when garbage is collected and transported, the preprocessing data is data acquired when the garbage is sorted in a processing plant, and the preprocessing mode is a mode adopted for sorting wrongly-sorted garbage from the garbage;

9. An electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein said processor, said communication interface and said memory communicate with each other via said communication bus,

the memory for storing a computer program;

the processor for performing the method steps of any one of claims 1 to 7 by running the computer program stored on the memory.

10. A computer-readable storage medium, in which a computer program is stored, wherein the computer program realizes the method steps of any one of claims 1 to 7 when executed by a processor.