CN117575635B - Carbon index tracing method and system - Google Patents
Carbon index tracing method and system Download PDFInfo
- Publication number
- CN117575635B CN117575635B CN202410059605.1A CN202410059605A CN117575635B CN 117575635 B CN117575635 B CN 117575635B CN 202410059605 A CN202410059605 A CN 202410059605A CN 117575635 B CN117575635 B CN 117575635B
- Authority
- CN
- China
- Prior art keywords
- recycle
- auxiliary code
- model
- type
- carbon index
- 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.)
- Active
Links
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 165
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 165
- 238000000034 method Methods 0.000 title claims abstract description 54
- 239000000463 material Substances 0.000 claims abstract description 34
- 238000013145 classification model Methods 0.000 claims abstract description 25
- 238000004364 calculation method Methods 0.000 claims abstract description 21
- 238000011084 recovery Methods 0.000 claims abstract description 13
- 238000013507 mapping Methods 0.000 claims description 33
- 238000007781 pre-processing Methods 0.000 claims description 17
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000009792 diffusion process Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 description 18
- 239000000047 product Substances 0.000 description 10
- 239000010813 municipal solid waste Substances 0.000 description 9
- 239000004033 plastic Substances 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 239000005431 greenhouse gas Substances 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000011960 computer-aided design Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 238000002939 conjugate gradient method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 239000002920 hazardous waste Substances 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000010806 kitchen waste Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000000123 paper Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000004064 recycling Methods 0.000 description 1
- 238000012958 reprocessing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a carbon index tracing method and a system, wherein the method comprises the following steps: acquiring an original image of the recycled material and the weight of the recycled material; based on the original image, obtaining a recycle type and a two-dimensional mask of the recycle through a classification model; generating an auxiliary code of the recycled material, wherein the auxiliary code is used for representing information of the recycled material; based on the type and weight of the recycled material, performing carbon index calculation on the recycled material to obtain a converted carbon index; based on the original image, the two-dimensional mask and the auxiliary code, a digital model of the recovery is generated through a depth estimation model, wherein the digital model is a two-dimensional digital twin body, and the two-dimensional digital twin body is used for tracing the carbon index based on the auxiliary code. According to the carbon index tracing method and system provided by the invention, the two-dimensional digital twin body is taken as the main body, and the tracing of the carbon index can be realized by searching and retrieving the auxiliary code through the main body, so that the accuracy and the execution efficiency of the tracing of the carbon index are improved.
Description
Technical Field
The invention relates to the technical field of carbon index tracing, in particular to a carbon index tracing method and system.
Background
With the rapid development of industrialization and city, a large amount of greenhouse gas emissions cause global climate warming, and climate change poses serious threat to human society and ecological environment. In order to cope with climate change, international society has adopted a series of emission reduction actions including measures of reducing greenhouse gas emissions and improving energy efficiency.
The carbon index is an index measuring carbon emissions or carbon footprint, and is used to evaluate the carbon emissions level of an individual, organization, city or country, while it may represent the carbon emissions per unit time or per unit yield or consumption. The carbon index can be traded, and whether the reliability of carbon trade or the accuracy of carbon index evaluation is based on the carbon index, the carbon index should have traceability.
For carbon assessment, carbon index traceability can provide accurate and reliable data support, and helps related parties know and assess sources and emissions of greenhouse gas emissions. Through carbon traceability analysis, carbon emission of each process and activity can be tracked, key fields and key links can be determined, and accordingly more accurate and effective emission reduction policies and measures can be formulated.
For carbon index transaction, the reliability of carbon index transaction can be ensured by tracing the carbon index, and when abnormal conditions of the carbon index occur in the transaction process, tracing investigation can be timely performed to check each link of the carbon index.
Therefore, how to trace the carbon index is a problem to be solved in the carbon trade and carbon evaluation process.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a carbon index tracing method and a system.
In a first aspect, the present invention provides a carbon indicator tracing method, including: acquiring an original image of the recycled material and the weight of the recycled material; based on the original image, obtaining a recycle type and a two-dimensional mask of the recycle through a classification model; generating an auxiliary code of the recycle, the auxiliary code being generated based on the recycle type, the recycle weight, the sorting machine number, the operator execution time, the operation step number; based on the type and weight of the recycled material, performing carbon index calculation on the recycled material to obtain a converted carbon index; based on the original image, the two-dimensional mask and the auxiliary code, a digital model of the recovery is generated through a depth estimation model, wherein the digital model is a two-dimensional digital twin body, and the two-dimensional digital twin body is used for tracing the carbon index based on the auxiliary code.
In a possible implementation manner of the first aspect, the classification model includes a preprocessing layer, a first classification layer and a second classification layer, an input of the preprocessing layer includes an original image, an output includes a two-dimensional mask, an input of the first classification layer includes a two-dimensional mask, an output includes a recycle category, an input of the second classification layer includes a recycle category, an output includes a recycle category, the first classification layer is a semantic segmentation model based on deep learning, and the second classification layer is a logic classification model based on a knowledge graph.
In a possible implementation manner of the first aspect, the input of the second classification layer further includes a recycle knowledge graph, a node of the recycle knowledge graph includes a recycle category and a recycle type, and an edge of the recycle knowledge graph includes a correspondence between the recycle category and the recycle type.
In one possible implementation manner of the first aspect, generating a digital model of the recycle by a depth estimation model based on the original image, the two-dimensional mask and the auxiliary code includes: inputting the original image into a depth estimation model to obtain a depth estimation image and a depth estimation value; based on each pixel value of the depth estimation image, performing equal proportion conversion on the depth estimation image to obtain a height estimation value; based on the two-dimensional mask and the height estimation value, obtaining the length, the width and the height of the recycled object; obtaining a main body image of the recycled object based on the two-dimensional mask, the original image, the length, the width and the height, wherein the attribute of the main body image comprises the length, the width, the height and the type; based on the body and the ancillary code, a two-dimensional digital twin is generated.
In one possible implementation manner of the first aspect, the depth estimation model is a diffusion model, and an input of the diffusion model is 4 channels and an output of the diffusion model is 1 channel.
In one possible implementation manner of the first aspect, the auxiliary code includes a first auxiliary code, and the generating the auxiliary code of the recycle includes: generating a first auxiliary code based on the recycle type, wherein the first auxiliary code and the recycle type have a first mapping relation; based on the type and weight of the recycle, performing a carbon index calculation on the recycle to obtain a converted carbon index, comprising: and responding to the first auxiliary code and the recycle class to have a first mapping relation, and calculating the carbon index of the recycle based on the type and the weight of the recycle to obtain a converted carbon index.
In a possible implementation manner of the first aspect, the auxiliary code further includes a second auxiliary code, and based on the original image, the two-dimensional mask, and the auxiliary code, generating a digital model of the recycle through the depth estimation model includes: generating a second auxiliary code based on the converted carbon index, wherein the second auxiliary code has a second mapping relation with the type of the recycled material; a digital model of the recycle is generated by a depth estimation model based on the original image, the two-dimensional mask, and the second auxiliary code.
In a possible implementation manner of the first aspect, generating the auxiliary code of the recycle based on the recycle type further includes: determining a first mapping relation based on a first preset rule; tracing the carbon index based on the auxiliary code comprises the following steps: and tracing the carbon index through the two-dimensional digital twin body based on a first preset rule, the recycle class and the first auxiliary code.
In a possible implementation manner of the first aspect, generating the auxiliary code of the recycle based on the recycle type further includes: determining a second mapping relation based on a second preset rule; tracing the carbon index based on the auxiliary code, and further comprising: and tracing the carbon index through the two-dimensional digital twin body based on a second preset rule and a second auxiliary code.
In a second aspect, the present invention provides a carbon indicator tracing system, including: the acquisition module is used for acquiring an original image of the recycled object and the weight of the recycled object; the recycle classification module is used for obtaining the type of the recycle and a two-dimensional mask of the recycle through a classification model based on the original image; the auxiliary code generation module is used for generating an auxiliary code of the recycled object based on the type of the recycled object, and the auxiliary code is used for representing information of the recycled object; the carbon index calculation module is used for calculating the carbon index of the recycled material based on the type and the weight of the recycled material to obtain a converted carbon index; the digital model generation module is used for generating a digital model of the recovery through a depth estimation model based on the original image, the two-dimensional mask and the auxiliary code, wherein the digital model is a two-dimensional digital twin body; and the traceability information recording module is used for recording the two-dimensional digital twin body and tracing the carbon index based on the auxiliary code.
In a third aspect, the present invention provides a computer readable storage medium storing computer instructions, where when the computer reads the computer instructions in the storage medium, the computer performs a carbon indicator tracing method according to any one of the first aspects.
In a fourth aspect, the present invention provides an electronic device comprising a processor and a memory, wherein the memory is configured to store a computer program; the processor is configured to load and execute a computer program to cause the electronic device to perform a carbon indicator tracing method according to any one of the first aspects.
The carbon index tracing method and system provided by the invention have the beneficial effects that the two-dimensional digital twin body is taken as a main body, and the tracing of the carbon index can be realized by searching and retrieving the auxiliary code through the main body, so that the accuracy and the execution efficiency of the carbon index tracing are improved.
Drawings
Fig. 1 is a schematic structural diagram of an electronic device provided by the present invention.
Fig. 2 is a flowchart of a carbon indicator tracing method provided by the invention.
Fig. 3 is a schematic structural diagram of a classification model according to the present invention.
Fig. 4 is a schematic structural diagram of the knowledge graph of the recovered matters provided by the invention.
Fig. 5 is a flowchart of generating a digital model according to the present invention.
Fig. 6 is a schematic structural diagram of a carbon indicator tracing system provided by the present invention.
Reference numerals: processor-101, communication bus-102, network interface-103, user interface-104, memory-105, classification model 300, raw image 301, preprocessing layer 310, two-dimensional mask 311, first classification layer 320, recycle category 321, recycle knowledge graph 322, second classification layer 330, recycle category 331.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The applicant finds that in the process of researching the carbon index tracing, the existing carbon tracing method mainly aims at tracing the production or the technological process of the product and is mainly divided into a direct tracing method and a digital tracing method, wherein the direct tracing method is used for manually recording all links in the production or the technological process of the product in a manual recording mode, and the method has the advantages of high information accurate tracing accuracy, but high labor cost and low tracing speed so that the method is not suitable for large-scale tracing. The digital tracing method is to scan specific identification codes on product parts or process machines through special equipment to realize automatic recording and data storage of links, and has high speed, but the accuracy is lower than that of a direct tracing method, and the identification codes are used as tracing media and can only be used for products or processes with the same attribute.
The carbon index generation process is various, such as green planting, renewable product manufacturing, etc. The garbage (recycled material) recovery is an important way for generating carbon indexes, and in the garbage recovery process, corresponding carbon index conversion can be performed according to the type and the weight of garbage. However, because the garbage is of a large variety and large quantity, the direct tracing method based on manual recording is not preferable, and individuals of the same garbage are large in distinguishability, each time the carbon index is generated, a plurality of individuals are contained, and the individual sources are uncertain, so that the digital tracing through a specific identification mode not only needs to be manually identified and pasted, but also different shapes of the individuals can lead to different pasting positions, and the existing automatic identification technology of digital tracing cannot be applied.
Aiming at the problems existing in the prior art when the carbon index tracing method using garbage recovery as the carbon index production mode is applied, the invention provides the carbon index tracing method and system, which take a two-dimensional digital twin body as a main body, and can realize the tracing of the carbon index by searching and retrieving auxiliary codes through the main body, thereby improving the accuracy and efficiency of the carbon index tracing.
Fig. 1 is a schematic structural diagram of an electronic device provided by the present invention. Referring to fig. 1, fig. 1 is a schematic structural diagram of an electronic device of a hardware running environment according to an embodiment of the present invention, where the electronic device may include: a processor 101, such as a central processing unit (Central Processing Unit, CPU), a communication bus 102, a user interface 104, a network interface 103, a memory 105. Wherein the communication bus 102 is used to enable connected communication between these components. The user interface 104 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 104 may also include standard wired, wireless interfaces. The network interface 103 may alternatively comprise a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 105 may alternatively be a storage device independent of the foregoing processor 101, where the Memory 105 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or may be a stable Non-Volatile Memory (NVM), such as at least one magnetic disk Memory; the processor 101 may be a general purpose processor including a central processing unit, a network processor, etc., as well as a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 is not limiting of the electronic device and may include more or fewer components than shown, or may combine certain components, or may be arranged in different components.
As shown in fig. 1, the memory 105, which is a storage medium, may include an operating system, a network communication module, a user interface module, and a carbon indicator tracing system.
In the electronic device shown in fig. 1, the network interface 103 is mainly used for data communication with a network server; the user interface 104 is mainly used for data interaction with a user; the processor 101 and the memory 105 in the invention can be arranged in the electronic equipment, and the electronic equipment calls the carbon index tracing system in the memory 105 through the processor 101 and executes the carbon index tracing method provided by the embodiment of the invention.
Fig. 2 is a flowchart of a carbon indicator tracing method provided by the present invention, including:
s210: an original image of the recycle is obtained, and the weight of the recycle is obtained.
Recyclates (also called trash) are intended to be used by the user but can be reused by reprocessing, for example recyclates can include waste clothing, plastic bottles or paper shells. The user recovers the recovered matters to enter a recycling link, thereby being beneficial to environmental protection and reducing carbon emission.
In some embodiments, the raw image of the recycle and the weight of the recycle may be acquired by an acquisition module that includes an image sensor and a weight sensor. The original image may be a three-dimensional color image containing the recycle.
S220: based on the original image, obtaining the type of the recycle and the two-dimensional mask of the recycle through a classification model.
The type of recycle refers to the specific form of recycle. For example, the recycle types may include paper, plastic, glass, metal, cloth, batteries, and the like.
The two-dimensional mask of the recycle means dividing the original image into a number of small grid cells and assigning each cell an image of two-dimensional coordinates. Each grid cell corresponds to a pixel in the original image and may contain information about the pixel, such as color, texture, shape, etc. The two-dimensional mask may represent the position and shape of the recycle in the original image.
In some embodiments, the classification model includes a pre-processing layer, a first classification layer, and a second classification layer, the input of the pre-processing layer includes an original image, the output includes a two-dimensional mask, the input of the first classification layer includes a two-dimensional mask, the output includes a recycle category, the input of the second classification layer includes a garbage category, the output includes a recycle category, and the first classification layer and the second classification layer are machine learning models. For more on the classification model, see the relevant description in fig. 3.
S230: based on the type of recycle, an ancillary code for the recycle is generated, the ancillary code being used to represent information for the recycle.
The auxiliary code refers to a medium representing information about the recycle. For example, the auxiliary code may be a 1 x 25-dimensional vector containing 4-bit prescaler codes, specifically:
0001|202310111756|01|001|0004
bits 17-18 of the vector may represent the step actor type, e.g., 01 for machine prescreening, 02 for manual review, etc.; bits 1-4 may represent the number of a machine or person; bits 5-16 may represent the time at which the operation was performed; bits 19-21 may represent the type of recycle, e.g., 001 represents a plastic article, 002 represents a metal article, etc.; the last 4 bits may represent the weight of the recycle.
In some embodiments, the ancillary code may be generated by an ancillary code generation module. The auxiliary code generation module may generate corresponding auxiliary codes in each step, respectively. For example, the ancillary code generation module may generate a first ancillary code based on the recycle type, the first ancillary code having a first mapping relationship with the recycle type. The auxiliary code generation module may also generate a second auxiliary code based on the converted carbon indicator, the second auxiliary code having a second mapping relationship with the recycle type. For more on the first auxiliary code, the second auxiliary code, see the relevant description in the embodiments described below.
S240: and (3) based on the type and the weight of the recycled material, performing carbon index calculation on the recycled material to obtain a converted carbon index.
In some embodiments, the carbon indicator calculation may be performed by a carbon indicator calculation module. The carbon index conversion can be performed based on the related international standard of carbon tracing. For example, PAS2050, ISO14067, ISO21930, and the like. ISO14067, which is developed by the international organization for standardization (ISO) according to the PAS2050 standard, is collectively referred to as "product carbon footprint", provides the most basic requirements and guidelines for accounting for product carbon footprint, and is considered to be a more universal standard. PAS2050 is a set of evaluation criteria for Carbon Footprint (Carbon print) of products, officially released by the British Standards Institute (BSI) in 2008, which is mainly used for evaluating greenhouse gas emissions generated by products throughout their life cycle (from raw materials, production, transportation to final disposal). ISO21930 is a carbon footprint evaluation standard for renewable energy products (e.g., solar panels, wind power generation, etc.), which is intended to help manufacturers and consumers understand the carbon emissions of renewable energy products, thereby providing a basis for selecting more environmentally friendly renewable energy sources.
S250: based on the original image, the two-dimensional mask and the auxiliary code, a digital model of the recovery is generated through a depth estimation model, wherein the digital model is a two-dimensional digital twin body, and the two-dimensional digital twin body is used for tracing the carbon index based on the auxiliary code. S250 may be performed by a digital model generation module.
In some embodiments, the depth estimation model may be a diffusion model, the structure of which may be a common neural network structure, such as Transformer, resnet, etc. The diffusion model may also be constructed as a modified U-Net model (U-Net: convolutional Networks for Biomedical Image Segmentation) with a loss function of:
wherein,4 channels for input and 1 channel for output +.>Model (S)>For the target image +.>For the original image entered, ++>Is the noise level index>For regularization coefficients, the preferred value is +.>，/>Is noise (I)>Representing the introduction of different variables and regularization. The parameter conduction in the model training process can be performed by using a gradient descent method, a Newton method, a conjugate gradient method and the like according to the loss function until a preset condition is met, so that better model performance is obtained.
In some embodiments, the digital model generation module inputs the original image into a depth estimation model to obtain a depth estimation image and a depth estimation value; based on each pixel value of the depth estimation image, performing equal proportion conversion on the depth estimation image to obtain a height estimation value; based on the two-dimensional mask and the height estimation value, obtaining the length, the width and the height of the recycled object; obtaining a main body image of the recycled object based on the two-dimensional mask, the original image, the length, the width and the height, wherein the attribute of the main body image comprises the length, the width, the height and the type; based on the subject image and the auxiliary code, a two-dimensional digital twin is generated. For more on generating the digital model, see the relevant description in fig. 5.
Aiming at the defects of high time cost and high calculation cost of the existing twin technology such as CAD (computer aided design), electric cloud reconstruction and the like for generating the three-dimensional model twin technology, the carbon index tracing method provided by the invention takes a two-dimensional digital twin body as a main body, and can realize tracing of the carbon index by searching and retrieving auxiliary codes through the main body, so that the accuracy and the execution efficiency of tracing of the carbon index are improved.
Fig. 3 is a schematic structural diagram of a classification model 300 according to the present invention. As shown in fig. 3, the classification model 300 includes a preprocessing layer 310, a first classification layer 320, and a second classification layer 330, the input of the preprocessing layer 310 includes an original image 301, the output includes a two-dimensional mask 311, the input of the first classification layer 320 includes a two-dimensional mask 311, the output includes a recycle category 321, the input of the second classification layer 330 includes a recycle category 321, the output includes a recycle category 331, the first classification layer is a deep learning-based semantic segmentation model, and the second classification layer is a knowledge-graph-based logic classification model.
The preprocessing layer 310 is used to preprocess the original image 301 so as to be better able to adapt to the subsequent first classification layer 320. The preprocessing layer 310 may include denoising, normalization, image enhancement, etc. operations to enhance the performance and generalization capability of the classification model. For example, the preprocessing layer 310 may include an input layer, a denoising layer (using denoising algorithms such as median filtering, gaussian filtering, etc.), a normalization layer (using normalization algorithms such as mean normalization, etc. to adjust the pixel value range of the image data to the same scale), an image enhancement layer (using image enhancement algorithms such as flipping, clipping, rotation, etc.), a feature extraction layer, an output layer, etc.
The first classification layer 320 is used to assign each pixel in the two-dimensional mask 311 to a particular recycle category 321. The recycle category 321 refers to different kinds of recyclates, for example, the recycle category 321 may include recyclables, kitchen recyclates, hazardous waste, and other waste. In some embodiments, the first classification layer may be a deep learning based semantic segmentation model.
The second classification layer 330 is used to correspond the recycle category 321 to the recycle category 331. In some embodiments, the second classification layer may be a knowledge-graph based logical classification model. The input of the second classification layer 330 may also include a two-dimensional mask 311. The preprocessing layer 310, the first classification layer 320, and the second classification layer 330 may be trained using a supervised learning approach, or may be trained in combination. The training sample is a recycle image labeled with classifications. The labels may be manually marked.
In the embodiment of the invention, the classification model is used for classifying the recovered matters, so that the problems of time and labor waste in the traditional manual classification are solved, the automation of the classification of the recovered matters is realized, the accuracy and the efficiency of the classification of the recovered matters are improved, and the accuracy and the efficiency of carbon tracing are further improved.
In some embodiments, the input to the second classification layer 330 further includes a recycle knowledge graph 322, the nodes of the recycle knowledge graph 322 including recycle categories and recycle types, the edges of the recycle knowledge graph 322 including correspondence between recycle categories and recycle types.
Fig. 4 is a schematic structural diagram of the knowledge graph of the recovered matters provided by the invention. As shown in fig. 4, A1, A2, A3, A4 represent different recycle categories, and B1, B2, B3 represent different recycle types. And establishing a corresponding relation between the types of the recyclates and the types of the recyclates to form a recyclate knowledge graph 322.
The recyclate knowledge graph 322 may be trained using machine learning methods. For example, a training dataset may be constructed first, the training dataset comprising a plurality of images labeled recycle categories, recycle types, and then a convolutional neural network model (CNN) is used to train the model, adjusting the model parameters until the accuracy meets the preset conditions.
In the embodiment of the invention, the recovery knowledge graph is used as the input of the second classification layer, so that the accuracy of classification of the second classification layer can be improved, the recovery processing strategy is optimized, the generalization capability of the classification model is enhanced, and the accuracy of carbon tracing is further improved.
Fig. 5 is a flowchart of generating a digital model according to the present invention. The process is performed by a digital model generation module, comprising:
s251: and inputting the original image into a depth estimation model to obtain a depth estimation image and a depth estimation value.
The depth estimation image refers to an image output by the depth estimation model. The depth estimation value refers to the object (recovered object) height obtained by converting the first depth image. The depth estimation value can be obtained through the distance between the camera and the shooting bottom plate. In the process of classifying the recycled objects, the distance between the camera and the shooting bottom plate used by the equipment can be obtained through manual calibration and is usually unchanged for a long time, so that the distance between the camera and the shooting bottom plate can be recorded as a depth estimated value。
S252: and carrying out equal proportion conversion on the depth estimation image based on each pixel value of the depth estimation image to obtain a height estimation value.
By depth estimationAs the maximum height value of the depth estimation image, the depth estimation image output by the depth estimation model is subjected to equal-scale conversion according to the pixel value, namely, the pixel value 255 represents the maximum height value +.>The pixel value 0 represents a height value of 0, and the height of the object in the converted image is taken as a height estimation value.
S253: based on the two-dimensional mask and the height estimate, the length, width, and height of the recycle are obtained.
The digital model generation module may extract an extracted image based on the two-dimensional mask 311 based on the height estimation value, calculate a difference between the maximum height and the minimum height in the extracted image, and use the difference as the height of the operated object (recovered object) and use the length and the width of the two-dimensional mask 311 as the length and the width of the operated object (recovered object).
S254: based on the two-dimensional mask, the original image, the length, the width, and the height, a subject image of the recycle is obtained, and attributes of the subject image include the length, the width, the height, and the type.
The digital model generation module may crop the original image 301 using the two-dimensional mask 311 to obtain a subject image of the recycle.
S255: based on the subject image and the auxiliary code, a two-dimensional digital twin is generated.
In some embodiments of the present invention, a depth estimation model is used to perform depth estimation on an original image, the height of an operated object is obtained through a height difference, and the length and width of the operated object are calculated by using a two-dimensional mask obtained by a classification model, so that a two-dimensional digital twin body with three-dimensional information is generated, and the operation efficiency of the digital twin process is improved.
In some embodiments, the depth estimation model is a machine learning model with an input channel number of 4 and an output channel number of 1. The input sample of the depth estimation model is a color image (the dimension is 3), and the output target image (the depth estimation image) is also a color image, and because the invention solves the depth estimation problem, the channel is changed to 4, namely the sample is a color image, the target image is a depth estimation image (the dimension is 1), and the accuracy and the universality of the depth estimation model in the aspect of tracing the recycled carbon are improved.
The applicant finds that in the process of researching carbon tracing, when abnormal conditions occur in carbon indexes in the carbon transaction process, the tracing and investigation of links with problems are difficult.
In view of this, in some embodiments provided herein, the ancillary codes may include a first ancillary code that generates an ancillary code for a recycle based on a recycle type, including: generating a first auxiliary code based on the recycle type, wherein the first auxiliary code and the recycle type have a first mapping relation; based on the type and weight of the recycle, performing a carbon index calculation on the recycle to obtain a converted carbon index, comprising: and responding to the first auxiliary code and the recycle class to have a first mapping relation, and calculating the carbon index of the recycle based on the type and the weight of the recycle to obtain a converted carbon index.
The first auxiliary code refers to the medium generated by the auxiliary code generating module after the second classifying layer 330 outputs the recycle type 331. For example, the first auxiliary code may be a 1 x 25-dimensional vector containing 4-bit prescaler codes, specifically:
0001|202310111756|01|001|0004
bits 17-18 of the vector may represent the step actor type, e.g., 01 for machine prescreening, 02 for manual review, etc.; bits 1-4 may represent the number of a machine or person; bits 5-16 may represent the time at which the operation was performed; bits 19-21 may represent the type of recycle, e.g., 001 represents a plastic article, 002 represents a metal article, etc.; the last 4 bits may represent the weight of the recycle.
The first mapping relationship is used for representing the correspondence relationship between the recycle type and the recycle type. The first mapping relationship may be represented based on a coded form. For example, the number of recoverable objects in the recovered object class is 1000 to 1999, the number of kitchen garbage is 2000 to 2999, and for a certain operated object (plastic), the number corresponding to the recovered object class is 1000 in the first auxiliary code of the plastic (1000 is recoverable object, and the description classification is correct). If the number corresponding to the type of the recycled material in the first auxiliary code of the plastic is 2222 (indicating a certain kitchen waste, such as pericarp), the first auxiliary code and the type of the recycled material do not have a first mapping relationship, and the problem link appears in the recycled material classification module. If the number corresponding to the recycle type in the first auxiliary code of the plastic is 1222 (representing the plastic), the recycle type and the first auxiliary code have a first mapping relationship.
In some embodiments, the ancillary code further comprises a second ancillary code that generates a digital model of the recycle by a depth estimation model based on the original image, the two-dimensional mask, and the ancillary code, comprising: generating a second auxiliary code based on the converted carbon index, wherein the second auxiliary code has a second mapping relation with the type of the recycled material; a digital model of the recycle is generated by a depth estimation model based on the original image, the two-dimensional mask, and the second auxiliary code.
The second auxiliary code refers to the medium generated by the auxiliary code generation module after the main body image of the operated object (recovered object) is generated by the index pattern generation module. For example, the second auxiliary code may be a 1 x 25-dimensional vector containing 4-bit prescaler codes, specifically:
0010|202310112307|03|001|0025
wherein the first 4 bits represent the number of the carbon index calculation device, the 5-16 bits represent the time of execution of the operation, the 17-18 bits represent the type of the executor of the step, the 03 is the step, the 19-21 is the type of the recovered material, and the last 4 bits represent the converted carbon index of the operated object (recovered material). The numbers of all devices are unique. After the carbon indicator calculation is completed, the carbon indicator calculation module may issue the converted carbon indicator in the form of an electronic payment to the electronic account of the recycler.
The second mapping relationship is used for representing the correspondence relationship between the recycle type and the converted carbon index. The second mapping relationship may be expressed based on the encoded form. For example, if the carbon index corresponding to the second auxiliary code is not within a reasonable range of the carbon index of the recycle type corresponding to the second auxiliary code (e.g., greater than a preset maximum carbon index of the recycle type or less than a preset minimum carbon index of the recycle type), the second auxiliary code and the recycle type do not have a second mapping relationship. The second auxiliary code is generated under the condition that the first auxiliary code and the recycled object type have a first mapping relation (namely, the recycled object classification module classifies correctly), so that if the second auxiliary code and the recycled object type do not have a second mapping relation, the description problem link appears in the carbon index calculation module.
In some embodiments of the invention, corresponding auxiliary codes are generated in the recovery classification process and the digital model generation process, and the problem links can be explored by searching and retrieving the auxiliary codes through the main body, so that the problems of difficult tracing and difficult investigation when the carbon index is abnormal are solved.
In some embodiments, generating the ancillary code of the recycle further comprises: determining a first mapping relation based on a first preset rule; tracing the carbon index based on the auxiliary code comprises the following steps: and tracing the carbon index through the two-dimensional digital twin body based on a first preset rule, the recycle class and the first auxiliary code.
In some embodiments, generating the ancillary code of the recycle further comprises: determining a second mapping relation based on a second preset rule; tracing the carbon index based on the auxiliary code, and further comprising: and tracing the carbon index through the two-dimensional digital twin body based on a second preset rule and a second auxiliary code.
Because of the differences of the carbon emission standards and the monitoring methods between different countries and regions, the method determines the first mapping relation between the types of the reclaimed materials and the types of the reclaimed materials based on the first preset rule and determines the second mapping relation between the types of the reclaimed materials and the carbon indexes based on the second preset rule, so that the carbon tracing system can adapt to the related regulations of carbon tracing or carbon emission between different countries and regions, and the universality of the carbon tracing system is improved.
The first preset rule may be a recycle classification mode of each country or region. For example, the first preset rule may be a recycle classification standard of the region a, and the recycle knowledge graph of the region a is constructed based on the recycle classification mode of the region a. In the carbon tracing system, a user selects different first preset rules to determine a corresponding first mapping relation, and based on the first preset rules and the retrieval of the first auxiliary codes of the main body, the carbon tracing of the main body recovery classification process can be realized.
The second preset rule may be an international standard related to carbon tracing of each country or region. For example, the second preset rule may be a calculation rule of PAS2050, ISO14067, ISO21930, and the like. The user selects different second preset rules to determine corresponding second mapping relations, and the carbon tracing of the main body carbon index conversion process can be realized based on the second preset rules and the retrieval of the second auxiliary codes of the main body.
The invention provides a carbon index traceability system, which comprises:
the acquisition module is used for acquiring an original image of the recycled object and the weight of the recycled object;
the recycle classification module is used for obtaining the type of the recycle and a two-dimensional mask of the recycle through a classification model based on the original image;
the auxiliary code generation module is used for generating an auxiliary code of the recycled material, and the auxiliary code is used for representing information of the recycled material;
the carbon index calculation module is used for calculating the carbon index of the recycled material based on the type and the weight of the recycled material to obtain a converted carbon index;
the digital model generation module is used for generating a digital model of the recovery through a depth estimation model based on the original image, the two-dimensional mask and the auxiliary code, wherein the digital model is a two-dimensional digital twin body;
And the traceability information recording module is used for recording the two-dimensional digital twin body and tracing the carbon index based on the auxiliary code.
According to the carbon index tracing system provided by the invention, the two-dimensional digital twin body is taken as the main body, and the tracing of the carbon index can be realized by searching and retrieving the auxiliary code through the main body, so that the accuracy and the execution efficiency of the tracing of the carbon index are improved.
The invention provides a computer readable storage medium, the storage medium stores computer instructions, and when the computer reads the computer instructions in the storage medium, the computer executes a carbon index tracing method according to any one of the above embodiments.
The invention provides an electronic device, which comprises a processor and a memory, wherein the memory is used for storing a computer program; the processor is configured to load and execute a computer program to cause the electronic device to perform a carbon indicator tracing method according to any one of the above embodiments.
In describing embodiments of the present invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "center", "top", "bottom", "inner", "outer", "inside", "outside", etc. indicate orientations or positional relationships based on the drawings are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Wherein "inside" refers to an interior or enclosed area or space. "peripheral" refers to the area surrounding a particular component or region.
In the description of embodiments of the present invention, the terms "first," "second," "third," "fourth" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first", "a second", "a third" and a fourth "may explicitly or implicitly include one or more such feature. In the description of the present invention, unless otherwise indicated, the meaning of "a plurality" is two or more.
In describing embodiments of the present invention, it should be noted that the terms "mounted," "connected," and "assembled" are to be construed broadly, as they may be fixedly connected, detachably connected, or integrally connected, unless otherwise specifically indicated and defined; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
In the description of embodiments of the invention, a particular feature, structure, material, or characteristic may be combined in any suitable manner in one or more embodiments or examples.
In describing embodiments of the present invention, it will be understood that the terms "-" and "-" are intended to be inclusive of the two numerical ranges, and that the ranges include the endpoints. For example: "A-B" means a range greater than or equal to A and less than or equal to B. "A-B" means a range of greater than or equal to A and less than or equal to B.
In the description of embodiments of the present invention, the term "and/or" is merely an association relationship describing an association object, meaning that three relationships may exist, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (6)
1. The carbon index tracing method is characterized by comprising the following steps of:
acquiring an original image of a recycled object and the weight of the recycled object;
Based on the original image, obtaining a recycle type and a two-dimensional mask of the recycle through a classification model;
generating an auxiliary code for the recycle based on the recycle type, the auxiliary code generated based on recycle type, recycle weight, sorting machine number, operator execution time, operational step number;
based on the type and the weight of the recycled material, performing carbon index calculation on the recycled material to obtain a converted carbon index;
generating a digital model of the recycle through a depth estimation model based on the original image, the two-dimensional mask and the auxiliary code, wherein the digital model is a two-dimensional digital twin body which is used for tracing the carbon index based on the auxiliary code,
the classification model comprises a preprocessing layer, a first classification layer and a second classification layer, wherein the input of the preprocessing layer comprises the original image, the output of the preprocessing layer comprises the two-dimensional mask, the input of the first classification layer comprises the two-dimensional mask, the output of the first classification layer comprises a recycle class, the input of the second classification layer comprises the recycle class, the output of the second classification layer comprises the recycle class, the first classification layer is a semantic segmentation model based on deep learning, and the second classification layer is a logic classification model based on a knowledge graph;
The generating a digital model of the recycle by a depth estimation model based on the original image, the two-dimensional mask, and the auxiliary code, comprising:
inputting the original image into a depth estimation model to obtain a depth estimation image and a depth estimation value;
based on each pixel value of the depth estimation image, carrying out equal proportion conversion on the depth estimation image to obtain a height estimation value;
obtaining the length, width and height of the recycle based on the two-dimensional mask and the height estimation value;
obtaining a main body image of the recycled object based on the two-dimensional mask, the original image, the length, the width and the height, wherein the attribute of the main body image comprises the length, the width, the height and the recycled object type;
generating the two-dimensional digital twin body based on the main body image and the auxiliary code;
the ancillary codes include a first ancillary code, the generating the ancillary code for the recycle based on the recycle type comprising:
generating the first auxiliary code based on the recycle type, wherein the first auxiliary code and the recycle category have a first mapping relation;
The carbon index calculation is performed on the recycle based on the recycle type and the weight to obtain a converted carbon index, including:
responding to the first auxiliary code and the recycle class to have a first mapping relation, and based on the recycle type and the weight, performing carbon index calculation on the recycle to obtain a converted carbon index;
the auxiliary code further includes a second auxiliary code, and the generating a digital model of the recycle by a depth estimation model based on the original image, the two-dimensional mask, and the auxiliary code includes:
generating the second auxiliary code based on the converted carbon indicator, the second auxiliary code having a second mapping relationship with the recyclate type;
and generating a digital model of the recycled object through a depth estimation model based on the original image, the two-dimensional mask and the second auxiliary code.
2. The method of claim 1, wherein the input of the second classification layer further comprises a recycle knowledge graph, wherein nodes of the recycle knowledge graph comprise the recycle category and the recycle type, and wherein edges of the recycle knowledge graph comprise a correspondence between the recycle category and the recycle type.
3. The carbon indicator tracing method according to claim 1, wherein the depth estimation model is a diffusion model, and the diffusion model has an input of 4 channels and an output of 1 channel.
4. The method of claim 1, wherein generating the auxiliary code for the recycle based on the recycle type, further comprises:
determining the first mapping relation based on a first preset rule;
tracing the carbon index based on the auxiliary code comprises the following steps:
and tracing the carbon index through the two-dimensional digital twin body based on the first preset rule, the recycle class and the first auxiliary code.
5. The method for tracing a carbon indicator according to claim 4, wherein,
the generating the auxiliary code of the recycle based on the recycle type further comprises:
determining the second mapping relation based on a second preset rule;
the tracing of the carbon index based on the auxiliary code further comprises:
and tracing the carbon index through the two-dimensional digital twin body based on the second preset rule and the second auxiliary code.
6. A carbon indicator traceability system, comprising:
the acquisition module is used for acquiring an original image of the recycled object and the weight of the recycled object;
the recycle classification module is used for obtaining the type of the recycle and the two-dimensional mask of the recycle through a classification model based on the original image;
an auxiliary code generation module for generating an auxiliary code of the recycle based on the recycle type, the auxiliary code being used to represent information of the recycle;
the carbon index calculation module is used for calculating the carbon index of the recycled material based on the type and the weight of the recycled material to obtain a converted carbon index;
the digital model generation module is used for generating a digital model of the recovery through a depth estimation model based on the original image, the two-dimensional mask and the auxiliary code, wherein the digital model is a two-dimensional digital twin body;
the traceability information recording module is used for recording the two-dimensional digital twin body and tracing the carbon index based on the auxiliary code,
the classification model comprises a preprocessing layer, a first classification layer and a second classification layer, wherein the input of the preprocessing layer comprises the original image, the output of the preprocessing layer comprises the two-dimensional mask, the input of the first classification layer comprises the two-dimensional mask, the output of the first classification layer comprises a recycle class, the input of the second classification layer comprises the recycle class, the output of the second classification layer comprises the recycle class, the first classification layer is a semantic segmentation model based on deep learning, and the second classification layer is a logic classification model based on a knowledge graph;
The generating a digital model of the recycle by a depth estimation model based on the original image, the two-dimensional mask, and the auxiliary code, comprising:
inputting the original image into a depth estimation model to obtain a depth estimation image and a depth estimation value;
based on each pixel value of the depth estimation image, carrying out equal proportion conversion on the depth estimation image to obtain a height estimation value;
obtaining the length, width and height of the recycle based on the two-dimensional mask and the height estimation value;
obtaining a main body image of the recycled object based on the two-dimensional mask, the original image, the length, the width and the height, wherein the attribute of the main body image comprises the length, the width, the height and the recycled object type;
generating the two-dimensional digital twin body based on the main body image and the auxiliary code;
the ancillary codes include a first ancillary code, the generating the ancillary code for the recycle based on the recycle type comprising:
generating the first auxiliary code based on the recycle type, wherein the first auxiliary code and the recycle category have a first mapping relation;
The carbon index calculation is performed on the recycle based on the recycle type and the weight to obtain a converted carbon index, including:
responding to the first auxiliary code and the recycle class to have a first mapping relation, and based on the recycle type and the weight, performing carbon index calculation on the recycle to obtain a converted carbon index;
the auxiliary code further includes a second auxiliary code, and the generating a digital model of the recycle by a depth estimation model based on the original image, the two-dimensional mask, and the auxiliary code includes:
generating the second auxiliary code based on the converted carbon indicator, the second auxiliary code having a second mapping relationship with the recyclate type;
and generating a digital model of the recycled object through a depth estimation model based on the original image, the two-dimensional mask and the second auxiliary code.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410059605.1A CN117575635B (en) | 2024-01-16 | 2024-01-16 | Carbon index tracing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410059605.1A CN117575635B (en) | 2024-01-16 | 2024-01-16 | Carbon index tracing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117575635A CN117575635A (en) | 2024-02-20 |
| CN117575635B true CN117575635B (en) | 2024-03-29 |
Family
ID=89862871
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410059605.1A Active CN117575635B (en) | 2024-01-16 | 2024-01-16 | Carbon index tracing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117575635B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117787575B (en) * | 2024-02-27 | 2024-05-03 | 四川绿豆芽信息技术有限公司 | Carbon monitoring method and device |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010191832A (en) * | 2009-02-20 | 2010-09-02 | Hitachi Ltd | Carbon traceability management system |
| CN110276147A (en) * | 2019-06-24 | 2019-09-24 | 广东工业大学 | A kind of manufacture system fault source tracing method, system based on the twin model of number |
| CN111967890A (en) * | 2020-09-21 | 2020-11-20 | 姚耀春 | Lithium ion battery full-life cycle monitoring traceability system and method |
| CN112926754A (en) * | 2021-03-23 | 2021-06-08 | 苏州耀天环保科技有限公司 | Traceable renewable solid waste resource recycling business model |
| CN113435054A (en) * | 2021-07-06 | 2021-09-24 | 天津水泥工业设计研究院有限公司 | Carbon emission assessment method and system based on digital twin model |
| CN114462133A (en) * | 2022-04-12 | 2022-05-10 | 天津水泥工业设计研究院有限公司 | Digital twin technology equipment product-based carbon footprint digital accounting method and system |
| CN114662780A (en) * | 2022-04-06 | 2022-06-24 | 国网冀北电力有限公司计量中心 | Carbon emission prediction method, carbon emission prediction device, electronic apparatus, and storage medium |
| CN115238529A (en) * | 2022-09-23 | 2022-10-25 | 北自所(北京)科技发展股份有限公司 | Chemical fiber filament process tracing method and device based on digital twinning and storage medium |
| CN115271994A (en) * | 2022-04-19 | 2022-11-01 | 国网冀北电力有限公司电力科学研究院 | Power industry carbon emission monitoring method and device based on digital twinning |
| CN116109089A (en) * | 2023-02-11 | 2023-05-12 | 新疆八一钢铁股份有限公司 | Digital monitoring management method for low-carbon transformation of steel mill |
| CN116127689A (en) * | 2022-10-09 | 2023-05-16 | 阿里云计算有限公司 | Digital twin space construction method and device and computing equipment |
| CN116362769A (en) * | 2023-03-06 | 2023-06-30 | 中国石油化工股份有限公司 | Method and system for tracing quality problem of finished oil, electronic equipment and storage medium |
| CN117197683A (en) * | 2023-09-05 | 2023-12-08 | 中南林业科技大学 | Country region remote sensing image carbon emission estimation system based on depth feature fusion |
-
2024
- 2024-01-16 CN CN202410059605.1A patent/CN117575635B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010191832A (en) * | 2009-02-20 | 2010-09-02 | Hitachi Ltd | Carbon traceability management system |
| CN110276147A (en) * | 2019-06-24 | 2019-09-24 | 广东工业大学 | A kind of manufacture system fault source tracing method, system based on the twin model of number |
| CN111967890A (en) * | 2020-09-21 | 2020-11-20 | 姚耀春 | Lithium ion battery full-life cycle monitoring traceability system and method |
| CN112926754A (en) * | 2021-03-23 | 2021-06-08 | 苏州耀天环保科技有限公司 | Traceable renewable solid waste resource recycling business model |
| CN113435054A (en) * | 2021-07-06 | 2021-09-24 | 天津水泥工业设计研究院有限公司 | Carbon emission assessment method and system based on digital twin model |
| CN114662780A (en) * | 2022-04-06 | 2022-06-24 | 国网冀北电力有限公司计量中心 | Carbon emission prediction method, carbon emission prediction device, electronic apparatus, and storage medium |
| CN114462133A (en) * | 2022-04-12 | 2022-05-10 | 天津水泥工业设计研究院有限公司 | Digital twin technology equipment product-based carbon footprint digital accounting method and system |
| CN115271994A (en) * | 2022-04-19 | 2022-11-01 | 国网冀北电力有限公司电力科学研究院 | Power industry carbon emission monitoring method and device based on digital twinning |
| CN115238529A (en) * | 2022-09-23 | 2022-10-25 | 北自所(北京)科技发展股份有限公司 | Chemical fiber filament process tracing method and device based on digital twinning and storage medium |
| CN116127689A (en) * | 2022-10-09 | 2023-05-16 | 阿里云计算有限公司 | Digital twin space construction method and device and computing equipment |
| CN116109089A (en) * | 2023-02-11 | 2023-05-12 | 新疆八一钢铁股份有限公司 | Digital monitoring management method for low-carbon transformation of steel mill |
| CN116362769A (en) * | 2023-03-06 | 2023-06-30 | 中国石油化工股份有限公司 | Method and system for tracing quality problem of finished oil, electronic equipment and storage medium |
| CN117197683A (en) * | 2023-09-05 | 2023-12-08 | 中南林业科技大学 | Country region remote sensing image carbon emission estimation system based on depth feature fusion |
Non-Patent Citations (4)
| Title |
|---|
| "Research on carbon flow traceability system for distribution network based on blockchain and power flow calculation";Sun Heyang 等;《 Frontiers in Energy Research》;20230203;第1-6页 * |
| "电力碳排放计量网络溯源方法及计量分析";王春妍 等;《电网技术》;20231031;第1-9页 * |
| "碳达峰碳中和背景下低碳制造研究现状与技术路径研究";李洪丞 等;《机械工程学报》;20230224;第59卷(第7期);第225-240页 * |
| 基于二维码的禽类肉产品安全溯源系统设计与实现;王华;李卫卫;吴怀广;白艳红;栗俊广;;计算机应用与软件;20201012(第10期);第7-11页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117575635A (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117575635B (en) | Carbon index tracing method and system | |
| CN102914545B (en) | Gear defect detection method and system based on computer vision | |
| Zheng et al. | HLU 2-Net: a residual U-structure embedded U-Net with hybrid loss for tire defect inspection | |
| CN105844602A (en) | Airborne LIDAR point cloud 3D filtering method based on volume elements | |
| CN115908424A (en) | Building health detection method, system and medium based on three-dimensional laser scanning | |
| CN102521624B (en) | Classification method for land use types and system | |
| CN106503178B (en) | Automatic method and device for evaluating land ecological quality | |
| CN112835570A (en) | Machine learning-based visual mathematical modeling method and system | |
| CN102565074B (en) | System and method for rechecking images of suspected defective products by small sheet sorter | |
| Jeong et al. | A systemic approach to exploring an essential patent linking standard and patent maps: Application of generative topographic mapping (GTM) | |
| CN115984662B (en) | Multi-mode data pre-training and identifying method, device, equipment and medium | |
| CN104217213A (en) | Medical image multi-stage classification method based on symmetry theory | |
| CN116186594B (en) | Method for realizing intelligent detection of environment change trend based on decision network combined with big data | |
| CN117115147A (en) | Textile detection method and system based on machine vision | |
| CN113254517A (en) | Service providing method based on internet big data | |
| CN111310611B (en) | Method for detecting cell view map and storage medium | |
| CN117197146A (en) | Automatic identification method for internal defects of castings | |
| CN109636194B (en) | Multi-source cooperative detection method and system for major change of power transmission and transformation project | |
| CN110264066A (en) | A kind of automobile industry transition and upgrade information monitoring system | |
| CN109785261A (en) | A kind of airborne LIDAR three-dimensional filtering method based on gray scale volume element model | |
| CN109739840A (en) | Data processing empty value method, apparatus and terminal device | |
| CN114283280A (en) | Water surface floating garbage identification method based on improved convolutional neural network | |
| CN109739839A (en) | Data processing empty value method, apparatus and terminal device | |
| Yao et al. | A pavement crack synthesis method based on conditional generative adversarial networks | |
| CN117787670B (en) | BIM data management method and system based on constructional engineering |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |