CN116542380A - Power plant supply chain carbon footprint optimization method and device based on natural language - Google Patents
Power plant supply chain carbon footprint optimization method and device based on natural language Download PDFInfo
- Publication number
- CN116542380A CN116542380A CN202310517951.5A CN202310517951A CN116542380A CN 116542380 A CN116542380 A CN 116542380A CN 202310517951 A CN202310517951 A CN 202310517951A CN 116542380 A CN116542380 A CN 116542380A
- Authority
- CN
- China
- Prior art keywords
- supply chain
- information
- carbon footprint
- preset
- text data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 151
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 151
- 238000005457 optimization Methods 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000013178 mathematical model Methods 0.000 claims abstract description 51
- 238000004458 analytical method Methods 0.000 claims abstract description 50
- 230000007246 mechanism Effects 0.000 claims abstract description 35
- 238000007726 management method Methods 0.000 claims abstract description 15
- 238000010801 machine learning Methods 0.000 claims abstract description 8
- 230000006399 behavior Effects 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 34
- 239000013598 vector Substances 0.000 claims description 32
- 238000004364 calculation method Methods 0.000 claims description 26
- 238000000605 extraction Methods 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 18
- 238000012216 screening Methods 0.000 claims description 14
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 230000010354 integration Effects 0.000 claims description 7
- 239000000203 mixture Substances 0.000 claims description 7
- 238000007621 cluster analysis Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 239000002245 particle Substances 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000000116 mitigating effect Effects 0.000 claims description 2
- 238000003058 natural language processing Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000008901 benefit Effects 0.000 description 13
- 230000008569 process Effects 0.000 description 8
- 239000011159 matrix material Substances 0.000 description 6
- 238000012549 training Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 230000007774 longterm Effects 0.000 description 4
- 238000013439 planning Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002195 synergetic effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 125000002015 acyclic group Chemical group 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010921 in-depth analysis Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- 239000002699 waste material Substances 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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
- G06Q50/06—Energy or water supply
-
- 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)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Development Economics (AREA)
- Biomedical Technology (AREA)
- Educational Administration (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Operations Research (AREA)
- Public Health (AREA)
- Databases & Information Systems (AREA)
- Water Supply & Treatment (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a natural language-based power plant supply chain carbon footprint optimization method and device, comprising the steps of acquiring text data related to a power supply chain; performing natural language analysis on the text data to obtain supply chain structure information; obtaining cooperative mechanism information among the supply chain members according to the supply chain structure information and a preset power system analysis model, wherein the cooperative mechanism information comprises cooperative strategies and game behaviors among the supply chain members; obtaining a carbon footprint prediction result of each link of the power supply chain according to the cooperative mechanism information and a preset machine learning mathematical model; and obtaining an optimal carbon footprint slowing scheme according to the carbon footprint prediction result and a preset optimizing mathematical model. By utilizing the natural language processing technology to acquire key information such as supply chain structure information, collaboration mechanism information and the like from text data, more comprehensive and accurate data support is provided for carbon footprint management.
Description
Technical Field
The invention relates to the technical field of carbon neutralization, in particular to a power plant supply chain carbon footprint optimization method and device based on natural language processing.
Background
As global climate change and carbon emissions become more and more problematic, carbon footprint management of the power supply chain is becoming more and more of an issue. The existing carbon footprint management method mainly relies on manual collection and analysis of data, and is low in efficiency and easy to error. Furthermore, the prior art often lacks in-depth analysis of the synergistic mechanisms in the supply chain, resulting in limited implementation of carbon emission schemes.
Based on the drawbacks of the prior art, a need exists for a method that can optimize carbon emissions.
Disclosure of Invention
The invention aims to provide a natural language-based power plant supply chain carbon footprint optimization method and device, so as to solve the problems. In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
in one aspect, the present application provides a natural language based power plant supply chain carbon footprint optimization method, comprising:
acquiring text data related to a power supply chain;
performing natural language analysis on the text data to obtain supply chain structure information, wherein the supply chain structure information is used for representing the composition, the operation mode and the operation environment of an electric power supply chain;
obtaining cooperative mechanism information among the supply chain members according to the supply chain structure information and a preset power system analysis model, wherein the cooperative mechanism information comprises cooperative strategies and game behaviors among the supply chain members;
Obtaining a carbon footprint prediction result of each link of the power supply chain according to the cooperative mechanism information and a preset machine learning mathematical model;
and obtaining an optimal carbon footprint slowing scheme according to the carbon footprint predicting result and a preset optimizing mathematical model.
On the other hand, the application also provides a natural language-based power plant supply chain carbon footprint optimization device, which comprises:
the acquisition module is used for acquiring text data related to the power supply chain;
the analysis module is used for carrying out natural language analysis on the text data to obtain supply chain structure information, wherein the supply chain structure information is used for representing the composition, the operation mode and the operation environment of the power supply chain;
the processing module is used for obtaining cooperative mechanism information among the supply chain members according to the supply chain structure information and a preset power system analysis model, wherein the cooperative mechanism information comprises cooperative strategies and game behaviors among the supply chain members;
the prediction module is used for obtaining a carbon footprint prediction result of each link of the power supply chain according to the cooperative mechanism information and a preset machine learning mathematical model;
and the optimization module is used for obtaining an optimal carbon footprint slowing scheme according to the carbon footprint prediction result and a preset optimization mathematical model.
The beneficial effects of the invention are as follows:
the invention obtains key information such as the supply chain structure information, the collaboration mechanism information and the like from text data by utilizing a natural language processing technology, and provides more comprehensive and accurate data support for carbon footprint management. By automatically analyzing text data related to the power supply chain, inefficiency and errors of manually collecting and analyzing the data are avoided, and therefore analysis efficiency of carbon footprint optimization is remarkably improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a natural language-based power plant supply chain carbon footprint optimization method according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a natural language-based power plant supply chain carbon footprint optimization device according to an embodiment of the invention.
The marks in the figure: 1. an acquisition module; 2. an analysis module; 21. a first extraction unit; 211. a first processing unit; 212. a first identification unit; 2121. a first conversion unit; 2122. a second extraction unit; 2123. a second construction unit; 2124. a first judgment unit; 2125. a second screening unit; 213. a first sorting unit; 214. a first clustering unit; 215. a first screening unit; 22. a first building unit; 23. a first calculation unit; 24. a second calculation unit; 25. a first integration unit; 3. a processing module; 31. a second sorting unit; 32. a first analysis unit; 33. a second analysis unit; 34. a third analysis unit; 35. a fourth analysis unit; 4. a prediction module; 41. a third extraction unit; 42. a first training unit; 43. a third calculation unit; 44. a second processing unit; 45. a first contrast unit; 5. an optimization module; 51. a second integration unit; 52. a third processing unit; 53. a fourth processing unit; 54. a fourth calculation unit; 55. and a fifth processing unit.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. 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 noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1:
the embodiment provides a power plant supply chain carbon footprint optimization method based on natural language processing.
Referring to fig. 1, the method is shown to include steps S100, S200, S300, S400, and S500.
Step S100, acquiring text data related to a power supply chain.
Text data relating to the power supply chain is collected at this step and includes policy regulations, industry reports, business annual reports, research papers, news reports, etc. The text data covers information about the composition, manner of operation, operating environment and carbon emissions of the power supply chain. In the step, the actual condition of the power supply chain can be comprehensively known by acquiring text data from various sources, and abundant data support is provided for subsequent analysis.
Step 200, performing natural language analysis on the text data to obtain supply chain structure information, wherein the supply chain structure information is used for representing the composition, operation mode and operation environment of the power supply chain.
The step S200 includes a step S210, a step S220, a step S230, a step S240, and a step S250.
And step S210, carrying out entity identification and keyword extraction on the text data to obtain the member information of the supply chain.
The step carries out entity identification and keyword extraction on the acquired text data to obtain the member information of the supply chain, and the entity identification and keyword extraction can mine core information in the text and provide a key basis for subsequent analysis. Step S210 includes step S211, step S212, step S213, step S214, and step S215.
Step S211, preprocessing the text data to obtain pure text data with noise and irrelevant information removed.
The preprocessing process comprises the steps of removing formatting symbols, deleting redundant blank spaces, converting text codes and the like, and the preprocessing of the original text data is helpful for improving the accuracy and efficiency in the subsequent natural language processing and analysis process, so that the related information of the power supply chain can be better mined.
Step S212, obtaining an entity list of the power supply chain according to the pure text data and a preset entity identification mathematical model, wherein the entity identification mathematical model comprises a dictionary in the power supply chain and carbon emission management field.
In the step, the entity identification mathematical model identifies key entities in the pure text data by using a professional dictionary in the field of power supply chain and carbon emission management, thereby obtaining an entity list of the power supply chain. The entities include participants, equipment, modes of operation, environmental factors, etc. of the links of the supply chain. The method is helpful for further analyzing the structure, the operation mode and the environmental factors of the supply chain by accurately identifying and extracting the entity information related to the power supply chain, and providing key information about carbon emission for enterprises and government departments, thereby making more effective policies and measures and reducing the carbon footprint of the whole power supply chain. Step S212 includes step S2121, step S2122, step S2123, step S2124, and step S2125.
Step S2121, performing word vector conversion processing on the clean text data to obtain vector representation of the clean text data.
Word vectors are a technique that maps words in natural language to a numerical vector space. By converting words in the plain text data into word vectors, a vector representation of the plain text data may be obtained. Such vector representations facilitate more efficient understanding and processing of natural language data by a computer for subsequent entity recognition and relationship extraction.
And step S2122, extracting the characteristics of the text according to the vector representation and a preset convolutional neural network mathematical model to obtain a characteristic vector.
The convolutional neural network is a deep learning model, has the characteristics of local perception and weight sharing, and can effectively extract local features in text data. By inputting the text of the vector representation into a pre-trained convolutional neural network model, higher level abstract features can be obtained. The convolutional neural network can extract the text characteristics so as to mine out the potential information which is difficult to be directly observed in the text, and provide richer and deeper characteristic representation for the subsequent entity identification and relation extraction tasks. Through extracting the feature vector, more accurate analysis of text data can be realized, and the accuracy of entity identification and relation extraction is improved. Meanwhile, the parallel computing capability of the convolutional neural network enables the feature extraction process to have higher computing efficiency, and is beneficial to improving the performance of the whole power supply chain analysis system.
And step S2123, performing sequence modeling on the feature vector according to the feature vector and a preset long-short-time memory network mathematical model to obtain sequence information.
The long-short time memory network is a special cyclic neural network and has the capability of capturing long-distance dependence. The feature vector extracted by the convolutional neural network is input into a long-short-time memory network model, so that the sequence modeling can be carried out on the entities and the relations in the text, and the sequence information and the context relations in the text are further captured. In the step, long-distance dependency relationship in the text can be effectively captured by using sequence modeling of long-time and short-time memory network, so that accuracy of entity identification and relationship extraction tasks is improved.
Step S2124, performing entity boundary detection and category judgment according to the sequence information and a preset entity identification mathematical model to obtain an entity candidate list.
The step inputs the sequence information into a Conditional Random Field (CRF) model, can detect entity boundaries in the text, judges the category of the entity, and finally obtains an entity candidate list. The accuracy of entity boundary detection and class determination is critical to the overall effectiveness of the power supply chain analysis, as relationships between entities can only be further mined if the entities are correctly identified.
Step S2125, the entity candidate list is subjected to correlation and context information screening to obtain an entity list of the power supply chain.
In this step, the entity candidate list may contain some entities not related to the power supply chain and carbon emission management field, and thus screening is required. By analyzing the context information of the entities in the text and the association degree of the entities with known power supply chains and carbon emission management related entities, the entities in the entity candidate list can be screened, irrelevant entities are removed, and finally the entity list of the power supply chain is obtained. The relevance and context information screening can improve the accuracy and reliability of the entity list, and ensure that the entities in the entity list are closely related to the power supply chain and the carbon emission management field. In addition, the calculation complexity of subsequent analysis can be reduced through the electric power supply chain entity list obtained through screening, and the efficiency and performance of the whole system are improved.
And S213, carrying out weight calculation and sequencing on the keywords in the entity list to obtain a keyword weight list.
In order to better understand the importance of each entity in the power supply chain and carbon emission management fields, the keywords in the entity list need to be weighted, and the keywords with higher importance in the power supply chain and carbon emission management fields can be identified through weight calculation and sequencing, so that valuable information is provided for subsequent relation extraction and supply chain structure analysis. The weight calculation is based on an improved word frequency-inverse document frequency (TF-I DF) algorithm, and the calculation formula is as follows:
Wherein W represents a weight; TF (word frequency) represents the number of times a keyword appears in a document; DF (document frequency) represents the number of documents containing keywords; n represents the total number of documents; TD (type term frequency) represents the number of times a keyword appears in a certain type of document; TDF (type document frequency) represents the number of documents containing keywords in a certain type document; m represents the total number of documents of a certain type. Alpha and beta are weight coefficients used to adjust the impact of different types of documents on keyword weights.
Step S214, carrying out cluster analysis on the keyword weight list to obtain at least two group clusters, wherein each group cluster comprises a supply chain member type.
Preferably, in this step, keywords with similar attributes are classified into the same cluster group by applying a K-nearest neighbor clustering algorithm. At least two clusters are obtained after cluster analysis, each cluster representing a supply chain member type, such as power generation enterprises, energy trading markets, end users, etc. In the step, the keywords in the keyword weight list are classified through cluster analysis, so that the characteristics and the connection of each member type in the power supply chain can be conveniently mined.
Step S215, randomly screening a representative keyword from each group cluster to obtain the member information of the supply chain.
Preferably, in this step, a representative keyword is selected from the keywords of each cluster group using a random sampling algorithm. These representative keywords can reflect the characteristics of the various links of the power supply chain, facilitating further analysis of the structure and characteristics of the supply chain.
Step S220, establishing topological relation among the members of the supply chain according to the member information of the supply chain to obtain member relation information.
This step can infer correlations, such as upstream and downstream relationships, competing relationships, etc., between the members of the supply chain based on the representative keywords and their contextual information in the text data. Topological relationships refer to logistic, energy, and information flow relationships between power supply chain members. For example, power producers provide power to power distributors, which in turn provide power to end users, which form a logistical relationship for the supply chain; meanwhile, the electric power transaction and settlement are required between the manufacturer and the distributor, which forms an information flow relation of a supply chain. In this embodiment, the establishment of the topological relation can help to determine the relation between the members of the power supply chain, including the flowing direction of energy and logistics, the interaction mode of information, etc., so as to help to comprehensively understand and analyze the operation mode and links of the power supply chain, thereby improving the operation efficiency of the power supply chain and reducing the carbon emission.
Step S230, a supply chain flow model is constructed according to the membership information, and the supply chain flow information is calculated according to the supply chain flow model.
The supply chain flow model models the flow of each link in the whole power supply chain, including links of purchasing, producing, selling, distributing and the like, and is used for representing the relation and the flow among the links. And then the system calculates and obtains the flow information of the supply chain according to the constructed flow model of the supply chain, wherein the flow information comprises the information of the operation mode, the operation environment, the production capacity, the flow efficiency and the like of the supply chain. This information can be used to analyze the overall condition of the power supply chain, provide information and guidance for support decisions, and also provide a data base for subsequent carbon emissions calculations and management. The calculation of the supply chain flow information can be realized through a mathematical model, and the specific calculation formula is as follows:
wherein i, j, k represent the names of the members in the supply chain, respectively; f (F) i,j Representing the amount of flow information from member i to member j; w (w) i,k A weight representing the information that member i passes to member k; t is t k,j Representing the time when member k passes information to member j; s is(s) i,k Representing the loss rate of member i when transferring information to member k; n represents the total number of power supply chain members.
Step S240, matching calculation is performed on the operation data in the supply chain flow model and the supply chain structure, so as to obtain the supply chain operation data.
By calculating the operation data of the supply chain, the operation condition of each link in the supply chain can be known, the problem points and the optimization space can be found, and the efficiency and the benefit of the supply chain are improved.
Step S250, integrating the supply chain member information, the membership information, the supply chain flow information and the supply chain operation data to obtain the supply chain structure information.
In the step, through analysis of the structure information of the supply chain, the relation among all members in the power supply chain can be known in depth, so that an optimization scheme is provided, and the efficiency and transparency of the supply chain are improved. For example, unnecessary links can be found by analyzing the relation between the supply chain operation data and the members, and a scheme for removing the links is proposed, so that the cost and the time consumption are reduced. Meanwhile, through integration and analysis of the structure information of the supply chain, risk assessment and control can be carried out on the power supply chain, and the stability of the whole supply chain is further improved.
Step S300, according to the supply chain structure information and a preset power system analysis model, obtaining cooperative mechanism information among the supply chain members, wherein the cooperative mechanism information comprises cooperative strategies and game behaviors among the supply chain members.
In the field of power supply, a cooperative mechanism among members of a supply chain is an important guarantee for guaranteeing stable operation of the whole power supply chain. By analyzing the collaboration mechanism information, the members of the supply chain can be helped to better know the relationship and collaboration mode between each other, so that the maximization of the collaboration benefit is realized, and the overall efficiency and stability of the supply chain are improved. The step S300 includes step S310, step S320, step S330, step S340, and step S350.
Step S310, performing topology ordering processing on the supply chain structure information to obtain the ordered relation of the supply chain members.
Topological ordering is a commonly used graph algorithm that can order Directed Acyclic Graphs (DAGs). This is advantageous in determining the role and responsibility of each member in the supply chain and in facilitating troubleshooting and solving problems in the supply chain. In the power supply chain, there is a clear sequence relationship among members such as a power producer, a power transmission enterprise, a power distribution enterprise and the like, and the topological ordering can help to determine responsibility and function of each member and a cooperative mechanism and a cooperative strategy among the members, so that the efficiency and reliability of the power supply chain are improved.
And step 320, analyzing interaction strategies among the members of the supply chain according to the ordered relation and a preset game theory mathematical model to obtain game strategy information.
By establishing a game theory model, the optimal decision of the supply chain members in different environments can be analyzed, and the cooperation mode and benefit distribution mode among the members can be determined, so that the efficiency and stability of the supply chain are improved. Meanwhile, the game theory model can also help a manager to predict possible crisis and risks, measures are timely taken to avoid loss, and smooth operation of a supply chain is ensured. Through the establishment and analysis of the game theory model, more scientific decision support is provided for a manager, and the operation efficiency and stability of a supply chain are optimized.
And step S330, optimizing a mathematical model according to the game strategy information and preset constraint to obtain the optimal cooperation strategy of each supply chain member.
And analyzing the interaction strategy among all members through the game theory mathematical model, and calculating the optimal cooperation strategy by utilizing the constraint optimization mathematical model. The method has the advantages of helping each member of the supply chain to determine the optimal cooperation strategy, improving the benefit and the overall operation level of the supply chain, and avoiding unnecessary waste and cost. Through the step, the coordination problem and the resource allocation problem in the supply chain can be effectively relieved, and the sustainable development capability of the supply chain is improved.
And step 340, performing multi-objective planning processing on the optimal cooperation strategy to obtain a balanced cooperation scheme among the supply chain members.
Different goals and interests often exist between different members, and thus maximization of the overall benefit is required through a reasonable synergistic scheme. The basic idea of multi-objective planning is to consider multiple objective functions simultaneously and seek a balance point between different objectives to maximize the overall benefit. Specifically, it is necessary to convert a plurality of objective functions into one integrated objective function and solve it. In this embodiment, objective functions such as cost and service level may be taken into consideration, and a balanced collaborative scheme may be obtained through a multi-objective planning method.
And step S350, analyzing the balanced coordination scheme to obtain coordination mechanism information among the members of the supply chain.
In this step, the equilibrium collaboration scheme is analyzed to investigate the collaboration mechanism information between the supply chain members. Such information includes collaboration policies, collaboration activities, etc. among the various members, all to achieve collaboration and win-win of the supply chain. By analyzing the collaboration mechanism information, the supply chain members can better coordinate the collaboration among each other, jointly cope with market changes and risks, and improve the efficiency and competitiveness of the whole power supply chain.
And step 400, obtaining a carbon footprint prediction result of each link of the power supply chain according to the cooperative mechanism information and a preset machine learning mathematical model.
It can be appreciated that in this step, the carbon footprint of each link of the power supply chain can be predicted and estimated by using the collaborative mechanism information and the machine learning model, so as to optimize the energy and the logistics flow in the supply chain, reduce unnecessary carbon emission, and reduce the environmental impact of the supply chain. The step S400 includes a step S410, a step S420, a step S430, a step S440, and a step S450.
And step S410, extracting features of the cooperative mechanism information to obtain a feature matrix.
The method comprises the steps of mining information in data through means of data exploration, statistical analysis, visualization and the like, and performing feature selection and feature construction. In the power supply chain, the impact of a number of factors on the carbon footprint may be involved, including energy consumption, logistic costs, production efficiency, etc. Each row of the feature matrix represents a supply chain member and each column represents a feature including energy consumption, carbon emissions, energy efficiency level, resource utilization, etc.
And S420, inputting the characteristic matrix into a preset deep neural network mathematical model for training to obtain a carbon footprint prediction model.
In the step, each element in the feature matrix is trained by a deep learning method, so that a neural network model capable of accurately predicting the carbon footprint is obtained.
And S430, performing forward propagation calculation according to the carbon footprint prediction model and real-time supply chain operation data in the text data to obtain carbon footprint prediction values of all links.
In the step, real-time supply chain operation data are used as the input of a model, and then forward propagation calculation is carried out on the data through the model to obtain the carbon footprint predicted value of each link. In the process, the deep learning model maps input data into an output data space according to parameters such as weight, bias and the like obtained by previous training to obtain a carbon footprint predicted value of each link, and the deep learning model has high self-adaptability and nonlinear mapping capability, so that the carbon emission condition of each link in a supply chain can be predicted more accurately.
And S440, performing sliding window processing on the carbon footprint predicted value to obtain a short-term trend analysis result.
The sliding window process may facilitate short term trend analysis of supply chain carbon footprint predictions to timely learn about supply chain carbon emissions and predict future carbon emissions trends. Short-term trend analysis is to identify the trend of data and possible future trends and rules by counting and analyzing the data within a certain period of time.
And S450, comparing the short-term trend analysis result with long-term historical data in the text data to obtain a carbon footprint prediction result of each link of the power supply chain.
In the step, by comparing the current carbon emission with the long-term historical data, whether the current carbon emission is normal or not can be judged more accurately, and whether abnormal fluctuation exists or not is judged, so that the operation strategy of the supply chain is adjusted in time, unnecessary carbon emission is reduced, and the efficiency and the sustainability of the supply chain are improved. By analyzing the short-term and long-term carbon footprint data, the carbon emission condition of each link of the power supply chain is predicted more comprehensively and accurately. Such predictions may be provided to supply chain members and related policy makers with reference to provide them with a better understanding of the operation of the supply chain and the problems that exist and to provide corresponding solutions.
And S500, obtaining an optimal carbon footprint reduction scheme according to the carbon footprint prediction result and a preset optimized mathematical model.
In this step, supply chain optimization based on carbon footprint prediction results is converted into a mathematical problem, so that an optimal carbon footprint mitigation scheme can be quickly and effectively found. By adopting the optimal carbon footprint slowing scheme, the operation efficiency and economic benefit of the supply chain can be effectively improved, the influence on the environment is reduced, and sustainable development is realized. The step S500 includes a step S510, a step S520, a step S530, a step S540, and a step S550.
And S510, carrying out integration treatment on the carbon footprint prediction result to obtain the carbon emission and the total carbon emission of each link.
It will be appreciated that in this step, detailed carbon emission data is provided to assist supply chain members in assessing their carbon emission levels, as well as providing data support for policy makers and stakeholders.
And step S520, obtaining a carbon emission optimization objective function through linear programming processing according to the carbon emission amount, the total carbon emission amount and preset constraint conditions of each link.
The step obtains an objective function of carbon emission optimization through linear programming treatment, and the objective function can help optimize the operation mode among the members of the supply chain so as to reduce the carbon emission and reduce the influence on the environment. Linear programming is a common mathematical optimization method that can help find the optimal solution, i.e. the value of the decision variable that makes the objective function reach the minimum or maximum under given constraints. In this step, the optimization objective function is determined by calculating the carbon emission amount, the total carbon emission amount, and the preset constraint conditions of each link, so that the accuracy and feasibility of the optimization result can be ensured.
And step S530, obtaining optimized supply chain parameters according to the carbon emission optimization objective function and a preset particle swarm optimization mathematical model.
In this step, the collaborative mechanism and collaborative strategy between supply chain members is optimized by inputting the carbon emission optimization objective function into the particle swarm optimization mathematical model to achieve the goal of minimizing carbon emission. Through the optimized supply chain parameters, the structure and the operation mode of the supply chain can be more reasonably adjusted by the power supply chain members, so that the carbon emission is minimized, and the influence on the environment is reduced. The particle swarm optimization method has the advantages of high efficiency, stability, strong global optimization capability and the like, so that the power supply chain members can be helped to find the optimal solution more quickly, and the operation efficiency and the sustainable development level of the supply chain are further improved.
And step S540, calculating according to the optimized supply chain parameters to obtain an optimized carbon footprint prediction result.
It will be appreciated that in this step, the optimized supply chain parameters are used to compare with the actual operating data in the historical data to verify the validity of the optimization. In addition, the step also calculates the carbon emission and the total carbon emission of each link and the change trend of each index, thereby providing more detailed and specific operation guidance for the supply chain members.
And step S550, obtaining an optimal carbon footprint slowing scheme according to the optimized carbon footprint prediction result and a preset evaluation index.
The setting and analysis of the evaluation index are helpful to evaluate the feasibility and effect of the scheme, and comprehensively evaluate the advantages and disadvantages of the scheme from the economic, environmental and social aspects. In this embodiment, the cost, the carbon emission reduction amount, the energy efficiency, the social benefit and other indexes of different schemes can be compared, and the optimal scheme can be selected to achieve the optimal carbon footprint reduction effect. This may promote collaboration among supply chain members, strengthen awareness of carbon emissions reduction, and improve social image and reputation of the enterprise.
Example 2:
as shown in fig. 2, the present embodiment provides a natural language-based power plant supply chain carbon footprint optimization device, which includes:
and the acquisition module 1 is used for acquiring text data related to the power supply chain.
The analysis module 2 is configured to perform natural language analysis on the text data to obtain supply chain structure information, where the supply chain structure information is used to represent a composition, an operation manner and an operation environment of the power supply chain.
And the processing module 3 is used for obtaining the collaboration mechanism information among the supply chain members according to the supply chain structure information and a preset power system analysis model, wherein the collaboration mechanism information comprises collaboration strategies and game behaviors among the supply chain members.
And the prediction module 4 is used for obtaining a carbon footprint prediction result of each link of the power supply chain according to the cooperative mechanism information and a preset machine learning mathematical model.
And the optimizing module 5 is used for obtaining an optimal carbon footprint slowing scheme according to the carbon footprint predicting result and a preset optimizing mathematical model.
In one embodiment of the present disclosure, the analysis module 2 includes:
the first extraction unit 21 is configured to perform entity recognition and keyword extraction on the text data, so as to obtain supply chain member information.
The first construction unit 22 is configured to establish a topological relation between supply chain members according to the supply chain member information, so as to obtain member relation information.
The first calculating unit 23 is configured to construct a supply chain process model according to the membership information, and calculate supply chain process information according to the supply chain process model.
The second calculating unit 24 is configured to perform matching calculation on the operation data in the supply chain flow model and the supply chain structure, so as to obtain supply chain operation data.
The first integration unit 25 is configured to integrate the supply chain member information, the membership information, the supply chain flow information and the supply chain operation data to obtain the supply chain structure information.
In one embodiment of the present disclosure, the first extraction unit 21 includes:
the first processing unit 211 is configured to pre-process the text data to obtain clean text data with noise and irrelevant information removed.
The first identifying unit 212 is configured to obtain an entity list of the power supply chain according to the pure text data and a preset entity identification mathematical model, where the entity identification mathematical model includes a dictionary in the power supply chain and the carbon emission management field.
The first ranking unit 213 is configured to perform weight calculation and ranking on the keywords in the entity list, so as to obtain a keyword weight list.
A first clustering unit 214, configured to perform cluster analysis on the keyword weight list to obtain at least two clusters, where each cluster includes a supply chain member type.
The first screening unit 215 is configured to randomly screen out a representative keyword from each cluster group to obtain supply chain member information.
In one embodiment of the present disclosure, the first recognition unit 212 includes:
the first conversion unit 2121 is configured to perform word vector conversion processing on the plain text data, so as to obtain a vector representation of the plain text data.
The second extracting unit 2122 is configured to perform feature extraction on the text according to the vector representation and a preset convolutional neural network mathematical model, so as to obtain a feature vector.
The second construction unit 2123 is configured to perform sequence modeling on the feature vector according to the feature vector and a preset long-short-term memory network mathematical model, so as to obtain sequence information.
The first determining unit 2124 is configured to perform entity boundary detection and category determination according to the sequence information and a preset entity recognition mathematical model, so as to obtain an entity candidate list.
The second filtering unit 2125 is configured to filter the entity candidate list with the context information to obtain an entity list of the power supply chain.
In one embodiment of the present disclosure, the processing module 3 includes:
the second ordering unit 31 is configured to perform topology ordering processing on the supply chain structure information to obtain an ordered relationship of the supply chain members.
The first analysis unit 32 is configured to analyze the interaction strategy between the supply chain members according to the ordered relationship and a preset game theory mathematical model, so as to obtain game strategy information.
The second analysis unit 33 is configured to optimize the mathematical model according to the game policy information and a preset constraint, and obtain an optimal cooperation policy of each supply chain member.
And a third analysis unit 34, configured to perform multi-objective planning processing on the optimal cooperation strategy, so as to obtain a balanced cooperation scheme among the supply chain members.
And a fourth analysis unit 35, configured to analyze the balanced coordination scheme to obtain coordination mechanism information between the supply chain members.
In one embodiment of the present disclosure, the prediction module 4 includes:
and a third extraction unit 41, configured to perform feature extraction on the collaboration mechanism information to obtain a feature matrix.
The first training unit 42 is configured to input the feature matrix to a preset deep neural network mathematical model for training, so as to obtain a carbon footprint prediction model.
And a third calculation unit 43, configured to perform forward propagation calculation according to the carbon footprint prediction model and the real-time supply chain operation data in the text data to obtain a carbon footprint prediction value of each link.
The second processing unit 44 is configured to perform sliding window processing on the carbon footprint predicted value to obtain a short-term trend analysis result.
The first comparing unit 45 is configured to compare the short-term trend analysis result with the long-term history data in the text data, so as to obtain a carbon footprint prediction result of each link of the power supply chain.
In one embodiment of the present disclosure, the optimization module 5 includes:
the second integrating unit 51 is configured to integrate the carbon footprint prediction result to obtain the carbon emission and the total carbon emission of each link.
And a third processing unit 52, configured to obtain a carbon emission optimization objective function through linear programming processing according to the carbon emission amount, the total carbon emission amount and the preset constraint condition of each link.
The fourth processing unit 53 is configured to obtain optimized supply chain parameters according to the carbon emission optimization objective function and a preset particle swarm optimization mathematical model.
And a fourth calculation unit 54, configured to calculate an optimized carbon footprint prediction result according to the optimized supply chain parameter.
And a fifth processing unit 55, configured to obtain an optimal carbon footprint reduction scheme according to the optimized carbon footprint prediction result and a preset evaluation index.
It should be noted that, regarding the apparatus in the above embodiments, the specific manner in which the respective modules perform the operations has been described in detail in the embodiments regarding the method, and will not be described in detail herein.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. A natural language based power plant supply chain carbon footprint optimization method, comprising:
acquiring text data related to a power supply chain;
performing natural language analysis on the text data to obtain supply chain structure information, wherein the supply chain structure information is used for representing the composition, the operation mode and the operation environment of an electric power supply chain;
obtaining cooperative mechanism information among the supply chain members according to the supply chain structure information and a preset power system analysis model, wherein the cooperative mechanism information comprises cooperative strategies and game behaviors among the supply chain members;
obtaining a carbon footprint prediction result of each link of the power supply chain according to the cooperative mechanism information and a preset machine learning mathematical model;
and obtaining an optimal carbon footprint slowing scheme according to the carbon footprint predicting result and a preset optimizing mathematical model.
2. The power plant supply chain carbon footprint optimization method of claim 1, wherein performing natural language analysis on the text data to obtain supply chain structural information comprises:
performing entity identification and keyword extraction on the text data to obtain supply chain member information;
establishing topological relation among the supply chain members according to the supply chain member information to obtain member relation information;
constructing a supply chain flow model according to the membership information, and calculating to obtain supply chain flow information according to the supply chain flow model;
matching and calculating the operation data in the supply chain flow model and the supply chain structure to obtain supply chain operation data;
and integrating the supply chain member information, the membership information, the supply chain flow information and the supply chain operation data to obtain the supply chain structure information.
3. The power plant supply chain carbon footprint optimization method of claim 2, wherein performing entity recognition and keyword extraction on the text data to obtain supply chain member information comprises:
preprocessing the text data to obtain pure text data with noise and irrelevant information removed;
Obtaining an entity list of the power supply chain according to the pure text data and a preset entity identification mathematical model, wherein the entity identification mathematical model comprises a dictionary in the power supply chain and carbon emission management field;
carrying out weight calculation and sequencing on keywords in the entity list to obtain a keyword weight list;
performing cluster analysis on the keyword weight list to obtain at least two group clusters, wherein each group cluster comprises a supply chain member type;
and randomly screening a representative keyword from each group of clusters to obtain the member information of the supply chain.
4. The power plant supply chain carbon footprint optimization method of claim 3, wherein obtaining an entity list of the power supply chain according to the clean text data and a preset entity recognition mathematical model comprises:
performing word vector conversion processing on the clean text data to obtain vector representation of the clean text data;
extracting the characteristics of the text according to the vector representation and a preset convolutional neural network mathematical model to obtain a characteristic vector;
performing sequence modeling on the feature vector according to the feature vector and a preset long-short-term memory network mathematical model to obtain sequence information;
Performing entity boundary detection and category judgment according to the sequence information and a preset entity identification mathematical model to obtain an entity candidate list;
and screening the entity candidate list for correlation and context information to obtain an entity list of the power supply chain.
5. The power plant supply chain carbon footprint optimization method of claim 1, wherein obtaining an optimal carbon footprint mitigation scheme according to the carbon footprint prediction result and a preset optimization mathematical model comprises:
integrating the carbon footprint prediction result to obtain carbon emission and total carbon emission of each link;
obtaining a carbon emission optimization objective function through linear programming processing according to the carbon emission of each link, the total carbon emission and preset constraint conditions;
obtaining optimized supply chain parameters according to the carbon emission optimization objective function and a preset particle swarm optimization mathematical model;
calculating according to the optimized supply chain parameters to obtain an optimized carbon footprint prediction result;
and obtaining an optimal carbon footprint slowing scheme according to the optimized carbon footprint prediction result and a preset evaluation index.
6. A natural language based power plant supply chain carbon footprint optimization device, comprising:
The acquisition module is used for acquiring text data related to the power supply chain;
the analysis module is used for carrying out natural language analysis on the text data to obtain supply chain structure information, wherein the supply chain structure information is used for representing the composition, the operation mode and the operation environment of the power supply chain;
the processing module is used for obtaining cooperative mechanism information among the supply chain members according to the supply chain structure information and a preset power system analysis model, wherein the cooperative mechanism information comprises cooperative strategies and game behaviors among the supply chain members;
the prediction module is used for obtaining a carbon footprint prediction result of each link of the power supply chain according to the cooperative mechanism information and a preset machine learning mathematical model;
and the optimization module is used for obtaining an optimal carbon footprint slowing scheme according to the carbon footprint prediction result and a preset optimization mathematical model.
7. The power plant supply chain carbon footprint optimization device of claim 6, wherein the analysis module comprises:
the first extraction unit is used for carrying out entity identification and keyword extraction on the text data to obtain supply chain member information;
the first construction unit is used for establishing topological relation among the supply chain members according to the supply chain member information to obtain member relation information;
The first calculation unit is used for constructing a supply chain flow model according to the membership information and calculating to obtain supply chain flow information according to the supply chain flow model;
the second calculation unit is used for carrying out matching calculation on the operation data in the supply chain flow model and the supply chain structure to obtain supply chain operation data;
and the first integration unit is used for integrating the supply chain member information, the membership information, the supply chain flow information and the supply chain operation data to obtain the supply chain structure information.
8. The plant supply chain carbon footprint optimization device of claim 7, wherein the first extraction unit comprises:
the first processing unit is used for preprocessing the text data to obtain pure text data with noise and irrelevant information removed;
the first identification unit is used for obtaining an entity list of the power supply chain according to the pure text data and a preset entity identification mathematical model, wherein the entity identification mathematical model comprises a dictionary in the power supply chain and carbon emission management field;
the first ordering unit is used for carrying out weight calculation and ordering on the keywords in the entity list to obtain a keyword weight list;
The first clustering unit is used for carrying out cluster analysis on the keyword weight list to obtain at least two group clusters, and each group cluster comprises a supply chain member type;
and the first screening unit is used for randomly screening one representative keyword from each group of clusters to obtain the member information of the supply chain.
9. The power plant supply chain carbon footprint optimization device of claim 8, wherein the first identification unit comprises:
the first conversion unit is used for carrying out word vector conversion processing on the pure text data to obtain vector representation of the pure text data;
the second extraction unit is used for extracting the characteristics of the text according to the vector representation and a preset convolutional neural network mathematical model to obtain a characteristic vector;
the second construction unit is used for carrying out sequence modeling on the feature vector according to the feature vector and a preset long-short-time memory network mathematical model to obtain sequence information;
the first judging unit is used for carrying out entity boundary detection and category judgment according to the sequence information and a preset entity identification mathematical model to obtain an entity candidate list;
and the second screening unit is used for screening the correlation and the context information of the entity candidate list to obtain an entity list of the power supply chain.
10. The plant supply chain carbon footprint optimization device of claim 6, wherein the optimization module comprises:
the second integration unit is used for integrating the carbon footprint prediction result to obtain the carbon emission and the total carbon emission of each link;
the third processing unit is used for obtaining a carbon emission optimization objective function through linear programming processing according to the carbon emission of each link, the total carbon emission and preset constraint conditions;
the fourth processing unit is used for obtaining optimized supply chain parameters according to the carbon emission optimization objective function and a preset particle swarm optimization mathematical model;
a fourth calculation unit, configured to calculate an optimized carbon footprint prediction result according to the optimized supply chain parameter;
and the fifth processing unit is used for obtaining an optimal carbon footprint reduction scheme according to the optimized carbon footprint prediction result and a preset evaluation index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310517951.5A CN116542380B (en) | 2023-05-09 | 2023-05-09 | Power plant supply chain carbon footprint optimization method and device based on natural language |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310517951.5A CN116542380B (en) | 2023-05-09 | 2023-05-09 | Power plant supply chain carbon footprint optimization method and device based on natural language |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116542380A true CN116542380A (en) | 2023-08-04 |
| CN116542380B CN116542380B (en) | 2023-11-14 |
Family
ID=87446651
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310517951.5A Active CN116542380B (en) | 2023-05-09 | 2023-05-09 | Power plant supply chain carbon footprint optimization method and device based on natural language |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116542380B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218690A (en) * | 2013-04-23 | 2013-07-24 | 清华大学 | Method for measuring carbon emission quantities during power consumption by active power distribution network users and based on carbon emission flow |
| CN108197109A (en) * | 2017-12-29 | 2018-06-22 | 北京百分点信息科技有限公司 | A kind of multilingual analysis method and device based on natural language processing |
| US20210224819A1 (en) * | 2020-01-16 | 2021-07-22 | International Business Machines Corporation | Carbon footprint tracker |
| CN114399294A (en) * | 2022-03-25 | 2022-04-26 | 南京擎天科技有限公司 | Automatic carbon emission accounting method and system applied to carbon emission meter |
| CN114564543A (en) * | 2022-02-24 | 2022-05-31 | 国网上海市电力公司 | Carbon footprint acquisition method based on knowledge graph |
| CN115292436A (en) * | 2022-06-28 | 2022-11-04 | 北京沃东天骏信息技术有限公司 | Carbon emission information generation method, apparatus, electronic device, medium, and program product |
| CN115438912A (en) * | 2022-08-04 | 2022-12-06 | 欧冶工业品股份有限公司 | Comprehensive management method and system for carbon emission information data of industrial product purchase supply chain |
| CN115688989A (en) * | 2022-10-20 | 2023-02-03 | 国网福建省电力有限公司经济技术研究院 | Carbon footprint prediction method and terminal based on Stacking ensemble learning |
| CN115860529A (en) * | 2022-11-23 | 2023-03-28 | 卡奥斯工业智能研究院(青岛)有限公司 | Supply chain carbon accounting system based on industrial internet |
-
2023
- 2023-05-09 CN CN202310517951.5A patent/CN116542380B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218690A (en) * | 2013-04-23 | 2013-07-24 | 清华大学 | Method for measuring carbon emission quantities during power consumption by active power distribution network users and based on carbon emission flow |
| CN108197109A (en) * | 2017-12-29 | 2018-06-22 | 北京百分点信息科技有限公司 | A kind of multilingual analysis method and device based on natural language processing |
| US20210224819A1 (en) * | 2020-01-16 | 2021-07-22 | International Business Machines Corporation | Carbon footprint tracker |
| CN114564543A (en) * | 2022-02-24 | 2022-05-31 | 国网上海市电力公司 | Carbon footprint acquisition method based on knowledge graph |
| CN114399294A (en) * | 2022-03-25 | 2022-04-26 | 南京擎天科技有限公司 | Automatic carbon emission accounting method and system applied to carbon emission meter |
| CN115292436A (en) * | 2022-06-28 | 2022-11-04 | 北京沃东天骏信息技术有限公司 | Carbon emission information generation method, apparatus, electronic device, medium, and program product |
| CN115438912A (en) * | 2022-08-04 | 2022-12-06 | 欧冶工业品股份有限公司 | Comprehensive management method and system for carbon emission information data of industrial product purchase supply chain |
| CN115688989A (en) * | 2022-10-20 | 2023-02-03 | 国网福建省电力有限公司经济技术研究院 | Carbon footprint prediction method and terminal based on Stacking ensemble learning |
| CN115860529A (en) * | 2022-11-23 | 2023-03-28 | 卡奥斯工业智能研究院(青岛)有限公司 | Supply chain carbon accounting system based on industrial internet |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116542380B (en) | 2023-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111324642A (en) | Model algorithm type selection and evaluation method for power grid big data analysis | |
| Zhou et al. | Corporate communication network and stock price movements: insights from data mining | |
| Drori et al. | Automl using metadata language embeddings | |
| CN114048436A (en) | Construction method and construction device for forecasting enterprise financial data model | |
| Elwakil et al. | Construction productivity fuzzy knowledge base management system | |
| CN117349782B (en) | Intelligent data early warning decision tree analysis method and system | |
| CN111476274A (en) | Big data prediction analysis method, system, device and storage medium | |
| Vilaysouk et al. | Semisupervised machine learning classification framework for material intensity parameters of residential buildings | |
| CN117495094A (en) | Comprehensive evaluation and early warning method and system for safety risk of industrial chain | |
| CN117522607A (en) | Enterprise financial management system | |
| CN110597796B (en) | Big data real-time modeling method and system based on full life cycle | |
| CN116542380B (en) | Power plant supply chain carbon footprint optimization method and device based on natural language | |
| Zhang et al. | Industrial text analytics for reliability with derivative-free optimization | |
| CN116307765A (en) | Artificial intelligence government affair data review method and system | |
| Macedo et al. | A machine learning approach for spare parts lifetime estimation | |
| KR102543211B1 (en) | Company's growth potential prediction system using unstructured data | |
| Wei et al. | Using machine learning to detect PII from attributes and supporting activities of information assets | |
| Thangarasu et al. | Detection of Cyberbullying Tweets in Twitter Media Using Random Forest Classification | |
| Liu et al. | An intelligent system for estimating full product Life Cycle Cost at the early design stage | |
| Sedano et al. | The application of a two-step AI model to an automated pneumatic drilling process | |
| CN117787569B (en) | Intelligent auxiliary bid evaluation method and system | |
| Zhang et al. | Forecast the price of chemical products with multivariate data | |
| Qin et al. | Investment Risk Analysis and Evaluation of Petroleum Exploration and Development Based on Artificial Intelligence | |
| CN113657599B (en) | Accident cause and effect reasoning method, device, electronic equipment and readable storage medium | |
| Pérez-Pons et al. | Towards financial valuation in data-driven companies |
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 |