An engineering carbon emission factor dynamic calculation and traceability analysis method and system

Abstract

The application provides an engineering carbon emission factor dynamic calculation and traceability analysis method and system, and belongs to the field of engineering construction. The method comprises the following steps: acquiring multi-source heterogeneous data of the whole process of engineering construction, and pre-processing the multi-source heterogeneous data to form a data set supporting knowledge modeling and calculation analysis; constructing a semantic knowledge structure of the carbon emission factor field of the whole process of engineering construction by using knowledge graph technology; dynamically calculating the carbon emission factor and correcting the weight; and visualizing the dynamic calculation result and the correction result to complete the dynamic calculation and traceability analysis of the engineering carbon emission factor. The application solves the deficiencies existing in the current carbon emission accounting system in the field of engineering construction.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of engineering construction, and particularly relates to a method and system for dynamic calculation and traceability analysis of engineering carbon emission factors. BACKGROUND

[0002] As an important field of energy consumption and greenhouse gas emission, the engineering construction industry has become a key link of low-carbon transformation and energy saving and emission reduction. Engineering construction activities cover multiple stages such as material production, transportation, construction and operation, and the carbon emission sources are complex in structure and scattered in data, so it is urgent to establish a scientific, systematic and dynamically updated carbon emission factor calculation and management system.

[0003] At present, the commonly used carbon emission accounting methods include emission coefficient method, material balance method and measurement method, however, these methods are mainly designed for industrial and operation stages, and the processing of multi-source dynamic data and regional differences in the construction stage is still insufficient, resulting in lack of uniformity and real-time of the accounting results.

[0004] In terms of carbon emission management, the digital functions of "seeing carbon, analyzing carbon and reducing carbon" have been realized, but they are mainly concentrated in the energy industry or enterprise level, and there is still a lack of systematic solutions for carbon emission monitoring, calculation and traceability analysis in the whole process of engineering construction. In addition, although low-carbon technology research in the fields of building and energy has been relatively mature, there are still problems such as complex types of low-carbon technology, non-uniform evaluation system in the engineering construction link, lack of knowledge-based and structured management and correlation mechanism, and it is difficult to realize the dynamic linkage of low-carbon technology and carbon emission factor calculation results. Therefore, it is necessary to build a knowledge graph-based engineering carbon emission factor dynamic calculation and traceability analysis system, combine multi-source data fusion with knowledge management, establish a dynamic update, knowledge correlation and whole-process traceability mechanism of carbon emission factors, and support accurate accounting and intelligent decision-making of carbon emission in the engineering construction stage. SUMMARY

[0005] In view of the above deficiencies in the prior art, the engineering carbon emission factor dynamic calculation and traceability analysis method and system provided by the application solve the deficiencies in the existing carbon emission accounting system in the field of engineering construction.

[0006] In order to achieve the above purpose, the technical scheme adopted by the application is as follows: a method for dynamic calculation and traceability analysis of engineering carbon emission factors, comprising the following steps:

[0007] S1, obtaining multi-source heterogeneous data of the whole process of engineering construction, and preprocessing the multi-source heterogeneous data to form a data set supporting knowledge modeling and calculation analysis;

[0008] S2, based on the data set, a semantic knowledge structure of a carbon emission factor field in the whole process of engineering construction is constructed by using a knowledge graph technology, wherein the semantic knowledge structure of the carbon emission factor field is used for intelligent completion, semantic reasoning and causal tracing of the carbon emission factor;

[0009] S3, based on the semantic knowledge structure of the carbon emission factor field, the carbon emission factor is dynamically calculated and the weight is corrected;

[0010] S4, the dynamic calculation result and the correction result are visualized and analyzed, and the dynamic calculation and tracing analysis of the engineering carbon emission factor are completed.

[0011] The beneficial effects of the present application are: the present application realizes dynamic updating, causal tracing and whole-process visual management of carbon emission factors by multi-source heterogeneous data fusion, semantic modeling and knowledge reasoning technology, significantly improves the scientificity, accuracy and intelligent level of carbon accounting in the engineering construction stage, and solves the problems existing in the existing carbon emission accounting system in the engineering construction field.

[0012] Further, the S1 comprises the following steps:

[0013] S101, multi-source heterogeneous data in the whole process of engineering construction is acquired, and the multi-source heterogeneous data is preprocessed, wherein the multi-source heterogeneous data comprises basic engineering data, material and energy data, monitoring and environmental data and standard and specification data;

[0014] S102, the preprocessed multi-source heterogeneous data is written into a graph database and a time series database to form a data set supporting knowledge modeling and calculation analysis.

[0015] The beneficial effects of the above further scheme are: the present application realizes unified management of data in semantic dimension and time dimension by standardizing preprocessing of multi-source heterogeneous data in the whole process of engineering construction and using a graph database and a time series database for structured storage, significantly improves the consistency, integrity and traceability of data, and provides a high-quality, fusible data basis for subsequent knowledge modeling and dynamic calculation, thereby enhancing the real-time response capability and calculation precision of the system, and ensuring dynamic update and high-trust tracing of carbon emission factors in space and time dimensions.

[0016] Further, the S2 comprises the following steps:

[0017] S201, field ontology construction and semantic definition: based on the data set, the entity category and its attribute are defined, and the hierarchical relationship and semantic constraint between entities are defined by using an ontology description language, so as to model the carbon emission field ontology model covering the whole life cycle of engineering construction;

[0018] S202, knowledge extraction and fusion: extract carbon emission related knowledge elements, based on the semantic definition result, through named entity recognition, attribute extraction and triple generation, convert the knowledge into structured form, and align and express the semantics between the knowledge consistently;

[0019] S203, semantic alignment and integration: based on the fusion result, use the semantic similarity calculation method based on word embedding and graph embedding for entity level and probability level alignment processing, to form a unified knowledge structure through semantic merging and concept aggregation, and store it in a graph database as a carrier;

[0020] S204, knowledge graph storage and indexing: in the integrated knowledge system, construct multiple semantic relationships, wherein the multiple semantic relationships constitute the semantic skeleton of the semantic knowledge structure of the carbon emission factor field, forming a dynamic knowledge grid;

[0021] S205, knowledge reasoning and completion mechanism: integrate rule-based reasoning and probabilistic reasoning mechanisms based on the knowledge graph to mine implicit relationships and automatically complete knowledge, and complete the construction of the semantic knowledge structure of the carbon emission factor field, wherein based on rule-based reasoning, causal chain deduction is performed according to predefined logical rules; unknown relationships are inferred through the probabilistic reasoning mechanism to identify potential associations and dynamic updates.

[0022] The beneficial effects of the above further scheme are: by constructing a carbon emission field ontology model covering the whole process of engineering construction, and combining knowledge extraction, semantic alignment and reasoning and completion technology, semantic fusion and intelligent modeling of multi-source knowledge are realized. This step not only converts scattered engineering data and standard literature into structured and inferable knowledge system, but also automatically identifies and completes the potential association between carbon emission factors, forms a dynamically evolving semantic knowledge structure, improves the semantic precision and intelligent level of carbon emission factor calculation, and provides logical support and data foundation for subsequent dynamic calculation, causal tracing and low-carbon technology recommendation.

[0023] Further, the multiple semantic relationships include:

[0024] Activity-factor relationship: representing the direct impact of engineering activities on carbon emission factors;

[0025] Factor-energy relationship: describing the energy conversion and emission correspondence between energy consumption and carbon emission factors;

[0026] Energy-equipment relationship: reveals the dependency relationship between energy types and equipment operation characteristics;

[0027] Factor-technology relationship: represents the reduction, control or replacement effect of low-carbon technology on carbon emission factors;

[0028] Causal-temporal relationship: reflects the evolution logic and causal chain of carbon emission factors in the time dimension and process stage.

[0029] The beneficial effect of the further scheme is that by constructing multi-dimensional semantic relationships such as activity-factor, factor-energy, energy-equipment, factor-technology and causal-temporal, a core semantic skeleton of the semantic knowledge structure in the field of carbon emission factors is formed. The logical association between engineering activities, energy consumption, equipment operation and low-carbon technology is realized, and the causal chain of carbon emission factors in the time and process dimensions is established. The system can realize dynamic correlation, causal tracing and technology matching of carbon emission data at the semantic level, significantly improving the accuracy, interpretability and intelligent level of carbon emission factor calculation.

[0030] Further, the S3 comprises the following steps:

[0031] S301, based on the semantic knowledge structure in the field of carbon emission factors, constructing a carbon emission calculation formula;

[0032] S302, under the framework of the carbon emission calculation formula, dynamically correcting the carbon emission factors according to the multi-dimensional semantic relationships, to generate dynamic emission factors;

[0033] S303, introducing a multi-source data fusion mechanism, taking the dynamic emission factors as prior information, updating the prior information using Bayes, to weight correct the carbon emission factors, and generating dynamic emission coefficients, wherein the dynamic emission coefficients are fed back to the carbon emission formula calculation in S301, for real-time calculation of engineering carbon emission;

[0034] S304, trend identification and anomaly detection are performed on the carbon emission data, based on the detection results, the potential causes are located based on the semantic relationships in the knowledge graph, and based on the positioning results, the dynamic emission coefficients are used for self-correction processing.

[0035] The beneficial effect of the further scheme is that by constructing a carbon emission calculation formula based on a semantic knowledge structure, and combining dynamic correction with multi-dimensional semantic relationships and multi-source data weighted fusion, adaptive updating of carbon emission factors is realized. The system can automatically adjust the emission factors and emission reduction parameters when new monitoring data arrives, so that the calculation results continuously fit the actual engineering state. At the same time, by using the trend identification and anomaly detection mechanism, the system can locate the potential abnormal reasons based on the knowledge graph, and perform self-correction operation, forming a dynamic closed loop of "semantic reasoning-data correction-model feedback", improving the real-time, accuracy and intelligent level of carbon emission accounting, and ensuring that the system still has high robustness and credibility in complex and variable engineering scenarios.

[0036] Further, the carbon emission calculation formula is as follows:

[0037] ;

[0038] ;

[0039] ;

[0040] ;

[0041] ;

[0042] in, Indicates carbon emissions. Indicates activity level data, Indicates carbon emission factor, Indicates the emission reduction rate. This indicates the effective emission percentage that was not reduced. , and All of these represent weight coefficients determined through Bayesian learning. This represents the theoretical emission reduction percentage. This indicates the emission reduction efficiency obtained based on real-time monitoring data from the engineering site. This represents the emission reduction percentage predicted through knowledge graph reasoning and machine learning. This represents the baseline emissions without the adoption of low-carbon technologies. This represents the measured emissions after adopting low-carbon technologies. This represents the theoretical activity level under conditions without energy-saving measures. This indicates the current measured activity level.

[0043] The beneficial effect of the above-mentioned further measures is that they will reduce emissions by [percentage missing]. The model is a multi-source weighted fusion model composed of technological emission reduction rate, observed emission reduction rate and predicted emission reduction rate. Bayesian learning is used to determine the weight coefficients, enabling the system to comprehensively utilize low-carbon technology parameters, measured monitoring data and knowledge reasoning results to achieve dynamic correction and adaptive updating of carbon emission factors. This improves the real-time performance, accuracy and stability of carbon emission calculation, maintains calculation consistency under different engineering stages and data conditions, and has automatic learning and self-correction capabilities, thus providing a highly reliable calculation basis for engineering carbon emission accounting and emission reduction decisions.

[0044] Furthermore, S303 specifically refers to:

[0045] A multi-source data fusion mechanism is introduced, using dynamic emission factors as prior information, and Bayesian methods are used to update the prior information.

[0046] Based on the updating result, the carbon emission factor is weightedly corrected by comprehensively utilizing the project account book, the energy bill, the sensor monitoring data and the external database information, wherein when the new measured data appears, the new measured data is regarded as the posterior information to update the prior carbon emission factor distribution, and the dynamic carbon emission coefficient most conforming to the engineering condition is obtained.

[0047] The beneficial effects of the above further scheme are that: by introducing the multi-source data fusion and the Bayesian updating mechanism, the system can comprehensively utilize the project account book, the energy bill, the sensor monitoring and the multi-source data such as the external database to dynamically weightedly correct the carbon emission factor. When the new measured data appears, the system automatically updates the prior distribution by taking the new measured data as the posterior information, so that the dynamic carbon emission coefficient most conforming to the engineering condition is obtained, the calculation accuracy and the real-time performance of the carbon emission factor are improved, the system has the continuous learning and self-adaptive adjustment capability, the system remains stable and reliable in long-term operation, and technical support is provided for accurate carbon accounting and intelligent decision-making in complex engineering scenarios.

[0048] The application also provides an engineering carbon emission factor dynamic calculation and traceability analysis system, comprising:

[0049] A data acquisition and fusion layer is used to acquire multi-source heterogeneous data in the whole process of engineering construction, and pre-process the multi-source heterogeneous data to form a data set supporting knowledge modeling and calculation analysis;

[0050] A knowledge modeling and reasoning layer is used to construct a semantic knowledge structure in the field of carbon emission factor based on the data set;

[0051] A dynamic calculation and analysis layer is used to dynamically calculate the carbon emission factor and correct the weight based on the semantic knowledge structure in the field of carbon emission factor;

[0052] A visualization and service layer is used to visually analyze the dynamic calculation result and the correction result, and complete the dynamic calculation and traceability analysis of the engineering carbon emission factor.

[0053] Compared with the existing engineering carbon emission accounting and management system, the application has the following significant advantages:

[0054] 1. Dynamic updating and high-precision accounting: the knowledge graph is used to associate the engineering activities, the energy types and the emission factors, the dynamic calculation and automatic correction of the emission factors are realized, the changes of the region, the process and the material are reflected in real time, and the accuracy and the timeliness of the accounting are improved;

[0055] 2. Traceable and high-reliable data management: the knowledge graph path reasoning mechanism is used to establish a carbon emission factor whole-chain traceability system, the data source, the calculation model and the reference standard are traceable, and the verifiability and the transparency of the result are enhanced;

[0056] 3. Data fusion and resource saving: Adopting hierarchical storage and graph database structure, realizing semantic fusion and efficient query of multi-source data, reducing repeated storage and network transmission, saving computing and bandwidth resources;

[0057] 4. Intelligent analysis and decision support: Combined with semantic reasoning and knowledge matching mechanism, automatically identifying high-emission links and recommending low-carbon technology solutions, providing intelligent carbon emission reduction decision support for engineering projects;

[0058] 5. Safe and reliable and strong compatibility: Through multi-level permission control, data encryption and access audit mechanism, data security and operation traceability are guaranteed, and system docking with existing carbon management platforms is supported, with good compatibility and deployment flexibility. BRIEF DESCRIPTION OF DRAWINGS

[0059] Figure 1 The method flowchart of the present application.

[0060] Figure 2 The system structure schematic diagram of the present application. DETAILED DESCRIPTION

[0061] The specific embodiments of the present application are described below to facilitate those skilled in the art to understand the present application, but it should be clear that the present application is not limited to the scope of the specific embodiments, and for those skilled in the art, it is obvious that various changes are within the spirit and scope of the present application defined and determined by the appended claims, and all inventions utilizing the concept of the present application are within the scope of protection.

[0062] Example 1

[0063] In view of the deficiencies in the existing carbon emission accounting system in the field of engineering construction, the present application mainly solves the following problems:

[0064] 1. Carbon emission factor lacks dynamic updating mechanism, and it is difficult to reflect the carbon emission difference brought by different time, region and construction process change;

[0065] 2. Carbon emission data sources are scattered and complex in structure, and the semantic association and traceability mechanism between engineering activities and carbon emission factors has not been established, resulting in insufficient consistency of accounting results;

[0066] 3. The existing carbon accounting and management platform model is static, lacking dynamic perception, automatic reasoning and knowledge learning ability, and cannot support real-time analysis and decision-making in complex scenarios;

[0067] 4. The low-carbon technology system is fragmented and cannot realize knowledge linkage with carbon emission factors, making it difficult to support intelligent identification and recommendation of carbon emission reduction path.

[0068] To solve the above problems, the application provides a knowledge graph-based engineering carbon emission factor dynamic calculation and traceability analysis method. Through multi-source heterogeneous data fusion, semantic modeling and knowledge reasoning technology, the application realizes dynamic updating of carbon emission factors, causal tracing and whole-process visual management, significantly improving the scientificity, accuracy and intelligent level of carbon accounting in the engineering construction stage.

[0069] As shown in Figure 1 The application provides an engineering carbon emission factor dynamic calculation and traceability analysis method, and the implementation method is as follows:

[0070] S1, obtaining multi-source heterogeneous data of the whole process of engineering construction, and preprocessing the multi-source heterogeneous data to form a data set supporting knowledge modeling and calculation analysis, and the implementation method is as follows:

[0071] S101, obtaining multi-source heterogeneous data of the whole process of engineering construction, and preprocessing the multi-source heterogeneous data, wherein the multi-source heterogeneous data includes basic engineering data, material and energy data, monitoring and environmental data, and standard and specification data;

[0072] S102, writing the preprocessed multi-source heterogeneous data into a graph database and a time series database to form a data set supporting knowledge modeling and calculation analysis.

[0073] In this embodiment, S1 is implemented by using a data acquisition and fusion layer, which is used to access multi-source heterogeneous data of the whole process of engineering construction, and the multi-source heterogeneous data includes:

[0074] Basic engineering data, including project geographic location, engineering category, construction stage, process flow, equipment type, construction period, etc.;

[0075] Material and energy data, including building material production energy consumption, transportation distance and mode, fuel type and usage, power consumption, etc.;

[0076] Monitoring and environmental data, including field temperature and humidity, climate conditions, environmental monitoring parameters and real-time energy consumption monitoring data;

[0077] Standard and specification data, including national and local carbon emission standards, industry technical specifications and policy indicators, etc.

[0078] The data acquisition and fusion layer realizes real-time access and format unification of multi-source heterogeneous data through an interface module, adopts data cleaning, standardization, unit conversion and time series resampling methods, etc., to ensure that the multi-source heterogeneous data structure is consistent and the semantics is unified. The processed multi-source heterogeneous data is written into a graph database and a time series database to form a basic data set supporting knowledge modeling and calculation analysis.

[0079] S2, based on the data set, a semantic knowledge structure of the carbon emission factor field in the whole process of engineering construction is constructed by using knowledge graph technology, wherein the semantic knowledge structure of the carbon emission factor field is used for intelligent completion, semantic reasoning and causal tracing of the carbon emission factor, and the implementation method is as follows:

[0080] S201, field ontology construction and semantic definition: based on the data set, the entity category and its attribute are defined, and the hierarchical relationship and semantic constraint between entities are defined by using ontology description language, so as to model the carbon emission field ontology model covering the whole life cycle of engineering construction;

[0081] S202, knowledge extraction and fusion: extract carbon emission related knowledge elements, based on the semantic definition result, through named entity recognition, attribute extraction and triple generation, the knowledge is converted into a structured form, and the semantic alignment and consistency expression of the knowledge are processed;

[0082] S203, semantic alignment and integration: based on the fusion result, the semantic similarity calculation method based on word embedding and graph embedding is used for entity level and probability level alignment processing, so as to form a unified knowledge structure through semantic merging and concept aggregation, and the graph database is used as a carrier for storage;

[0083] S204, knowledge graph storage and index: in the integrated knowledge system, multi-class semantic relationships are constructed, wherein the multi-class semantic relationships constitute the semantic skeleton of the semantic knowledge structure of the carbon emission factor field, and a dynamic knowledge grid is formed;

[0084] S205, knowledge reasoning and completion mechanism: based on the knowledge graph, the rule reasoning and probability reasoning mechanism are integrated to mine and automatically complete the implicit relationship, and the construction of the semantic knowledge structure of the carbon emission factor field is completed, wherein based on rule reasoning, the causal chain is deduced according to the pre-defined logical rules; unknown relationships are inferred by the probability reasoning mechanism to identify potential associations and dynamic updates.

[0085] In this embodiment, S2 is implemented by using the knowledge modeling and reasoning layer.

[0086] The knowledge modeling and reasoning layer is the core part of the application, which is responsible for constructing the semantic knowledge structure of the carbon emission factor field in the whole process of engineering construction, realizing the semantic modeling, logical association and knowledge reasoning between engineering activities, energy types, equipment, materials, carbon emission factors and low-carbon technologies and other multi-source elements. This layer establishes the semantic knowledge structure of the carbon emission factor field in the whole process of engineering construction by using the knowledge graph technology, realizes the intelligent completion, semantic reasoning and causal tracing of the carbon emission factor, and provides semantic support and logical foundation for subsequent dynamic calculation and intelligent analysis. Specifically, the following steps are included:

[0087] Domain ontology construction and semantic definition, establish a semantic knowledge structure covering the carbon emission factor domain of the whole process of engineering construction, define the core entity categories and their attributes, mainly including engineering activities (design, construction, transportation, operation, etc.), energy types (electricity, diesel, natural gas, etc.), materials (steel, cement, concrete, etc.), equipment types, carbon emission factors, carbon emission sources and low-carbon technologies, etc. On this basis, the invention uses ontology description language (OWL) to define the hierarchical relationship and semantic constraints between entities, clearly defines the logic paths such as "consumption-generation-control-optimization", and forms a semantic knowledge structure with reasoning ability;

[0088] Knowledge extraction and fusion, based on natural language processing (NLP) and relation extraction technology, extract carbon emission related knowledge elements from specification standards, industry guidelines, databases and historical engineering projects. Through named entity recognition, attribute extraction and triple generation, the knowledge is converted into a structured form, such as: (engineering activity → consumption → energy type), (energy type → generation → emission factor), (emission factor → controlled by → low-carbon technology) etc. To solve the problem of heterogeneity caused by multiple data sources, the invention uses a semantic fusion method based on rule template model to realize semantic alignment and consistent expression of knowledge;

[0089] Semantic alignment and integration, in view of the naming differences, different granularities and unit heterogeneity in different source knowledge, the invention uses a semantic similarity calculation method based on word embedding and graph embedding to realize entity-level and concept-level alignment and eliminate semantic conflicts. Through semantic merging and concept aggregation, a unified knowledge structure is formed, and a graph database (Neo4j) is used for persistent storage, thereby building a knowledge network with multiple semantic associations;

[0090] Knowledge graph storage and indexing, in the integrated knowledge system, the invention focuses on building the following five types of semantic relationships:

[0091] Activity-factor relationship (Activity-Factor): representing the direct influence of engineering activities on carbon emission factors;

[0092] Factor-energy relationship (Factor-Energy): describing the energy conversion and emission correspondence between energy consumption and carbon emission factors;

[0093] Energy-equipment relationship (Energy-Equipment): revealing the dependence relationship between energy types and equipment operation characteristics;

[0094] Factor-technology relationship (Factor-Technology): representing the reduction, control or replacement effect of low-carbon technology on emission factors;

[0095] Causal–Temporal: Reflects the evolution logic and causal chain of carbon emission factors in the time dimension and between process stages.

[0096] The above relationships constitute the core semantic skeleton of the system, forming a dynamic knowledge grid of "engineering activities-energy consumption-emission factors-low carbon technologies", which can support multi-dimensional query, semantic association and path reasoning;

[0097] Knowledge reasoning and completion mechanism, the invention integrates rule-based reasoning and probabilistic reasoning mechanism on the basis of knowledge graph, realizes implicit relationship mining and knowledge automatic completion. On the one hand, based on rule-based reasoning, the causal chain is deduced according to the predefined logical rules, for example: "if the construction stage uses diesel machinery → high emission factor → suggest using electric drive equipment"; on the other hand, the probabilistic graph model (Bayesian network) is used to infer the unknown or uncertain relationship, realize the potential association identification and dynamic update. At the same time, through the path reasoning algorithm (Path Reasoning), the formation process and influence path of any carbon emission factor node can be tracked, and multi-level tracing of emission sources can be realized.

[0098] Through the above modeling and reasoning mechanism, the knowledge modeling and reasoning layer builds a multi-dimensional, evolvable and interpretable carbon emission knowledge network (i.e., the semantic knowledge structure of the carbon emission factor field). The carbon emission knowledge network not only realizes the semantic association between carbon emission factors and engineering behavior, energy consumption, equipment operation and low carbon technology, but also dynamically infers the causal chain and technology optimization path, so as to realize dynamic calculation, carbon tracing and low carbon decision recommendation to provide knowledge basis and logical support.

[0099] S3, based on the semantic knowledge structure of the carbon emission factor field, the carbon emission factor is dynamically calculated and the weight is corrected, and the implementation method is as follows:

[0100] S301, based on the semantic knowledge structure of the carbon emission factor field, a carbon emission calculation formula is constructed;

[0101] S302, under the framework of the carbon emission calculation formula, according to the multi-dimensional semantic relationship, the carbon emission factor is dynamically corrected to generate a dynamic emission factor;

[0102] S303, a multi-source data fusion mechanism is introduced, the dynamic emission factor is used as prior information, the prior information is updated by using Bayesian to weight the correction of the carbon emission factor, and a dynamic emission coefficient is generated, wherein the dynamic emission coefficient is returned to the carbon emission formula calculation of S301 for real-time calculation of engineering carbon emission, and the implementation method is as follows:

[0103] A multi-source data fusion mechanism is introduced, a dynamic emission factor is taken as prior information, and the prior information is updated by using Bayes; based on the updating result, a project account, an energy bill, sensor monitoring data and external database information are comprehensively utilized to perform weighted correction on the carbon emission factor, wherein when the weighted correction is performed, when new measured data appears, the new measured data is regarded as posterior information, the prior carbon emission factor distribution is updated, and a dynamic carbon emission coefficient that is most suitable for engineering conditions is acquired;

[0104] In S304, trend identification and anomaly detection are performed on the carbon emission data, based on the detection result, a potential cause is located in combination with a semantic relationship in a knowledge graph, and based on the locating result, self-correction processing is performed by using a dynamic emission coefficient.

[0105] In this embodiment, the correction result (a dynamic emission factor EF') generated in S302 is continuously updated by Bayes as prior information in S303, and a final dynamic emission coefficient EF* (a fusion layer correction result) is generated, and the dynamic emission coefficient EF* is directly returned to the carbon emission calculation formula E = A x EF x (1 - η) in S301, and is used for real-time calculation of engineering carbon emission; subsequently, the abnormality detection and self-correction stage in S304 is continuously verified and optimized, and a dynamic cycle adaptive calculation system is formed. That is, S301: constructing the formula E = A x EF x (1 - η); S302: correcting the emission factor based on the semantic relationship -> obtaining EF'; S303: fusing multi-source data, Bayes weighted updating -> obtaining EF*; S304: calculating E(A, EF*, η), wherein EF' represents a dynamic emission factor, and EF* represents a dynamic emission coefficient.

[0106] In this embodiment, the measured data refers to real operation data directly collected by a monitoring device or an energy consumption sensor system on an engineering site, including an electric meter, a fuel flow meter, a water meter, a carbon emission sensor, a flue gas detector, an environmental monitoring device, a construction machine, a generator, a transportation device and the like.

[0107] In this embodiment, S3 is implemented by using a dynamic calculation and analysis layer. The dynamic calculation and analysis layer implements dynamic calculation and weight correction of the carbon emission factor, and mainly includes:

[0108] Constructing a carbon emission calculation formula:

[0109] ;

[0110] ​Wherein: E represents carbon emissions (unit: tCO2-e), A represents activity data, that is, the actual use of energy, fuel or materials in a certain engineering activity, EF represents the emission factor, which is derived from the semantic relationship of energy type, process condition, equipment characteristics and other semantic relationship in the knowledge graph, η (Eta) represents the reduction efficiency or carbon capture rate, that is, the reduction rate achieved by low-carbon technology, energy-saving equipment or carbon capture measures, (1-η) represents the effective emission rate that is not reduced, which is used to correct the actual emission of activity data after the implementation of emission reduction measures.

[0111] The physical meaning of the carbon emission calculation formula is that the carbon emission is equal to the theoretical emission value generated by the activity multiplied by the actual emission rate. Considering the factors such as carbon capture and energy saving reconstruction, the real emission level under different stages and different technical conditions can be dynamically reflected. The present application realizes the quantitative description of the effect of carbon emission reduction measures by dynamically estimating the reduction rate η.

[0112] In this embodiment, the reduction rate η is not a static parameter, but is dynamically inferred and calculated according to the multi-dimensional relationship in the knowledge graph, and its value mainly comes from the following three types:

[0113] 1. Calculation based on low-carbon technology parameters: a semantic chain of "low-carbon technology-energy consumption reduction rate-carbon capture efficiency" is established in the knowledge modeling layer. When a specific energy-saving or carbon capture technology (waste heat recovery system, renewable energy replacement, carbon capture device, etc.) is used in the project, the reduction coefficient corresponding to the technology is searched through the knowledge graph, and the calculation formula is as follows:

[0114] ;

[0115] Wherein, represents the baseline emission without using low-carbon technology, represents the measured emission or model prediction value after using low-carbon technology, which is used to correct the reduction rate η in the dynamic calculation model.

[0116] 2. Estimation based on measured energy efficiency and monitoring data: the present application accesses the field energy consumption monitoring equipment (electricity meter, fuel flow meter, carbon emission sensor, etc.), and real-time collects energy efficiency change data. By comparing the energy consumption level before and after the technical transformation, the value of the reduction rate η is dynamically estimated:

[0117] ;

[0118] Wherein, This indicates the theoretical emission reduction rate achieved by the adopted low-carbon technologies or carbon capture technologies. This indicates the emission reduction efficiency obtained based on real-time monitoring data from the engineering site. This represents the emission reduction rate obtained through knowledge graph reasoning and machine learning prediction models. This represents the theoretical activity level under conditions without energy-saving measures. This represents the current measured activity level. If the energy consumption is lower than the theoretical energy consumption, it indicates that there is an energy-saving effect, and the value of the emission reduction rate η will increase accordingly.

[0119] 3. Comprehensive Prediction Based on Knowledge Reasoning and Historical Samples: When complete measured data is lacking, the system utilizes the semantic reasoning function of the knowledge graph and historical project samples to estimate the value of parameter η. Finally, the comprehensive emission reduction rate is obtained by weighted fusion of three sources (technology coefficients, monitoring data, and inference predictions).

[0120] ;

[0121] in, , and This indicates that the weight coefficients determined through Bayesian learning satisfy... .

[0122] In this embodiment, the carbon emission calculation formula is applied dynamically. In actual operation, when new engineering data or monitoring information is received, the following calculation logic is automatically executed:

[0123] By retrieving relevant nodes from the knowledge graph, the energy type, equipment type, and low-carbon technology involved in this phase of the project are determined; based on the "technology-energy consumption-emission reduction rate" relationship between nodes, the corresponding emission reduction rate is deduced. The value; the dynamically calculated emission reduction rate Input into carbon emission calculation formula In the middle; output the corrected carbon emissions E in real time, and include the calculation path (including emission reduction rate). Source and parameters The correlation relationships are recorded in the graph database to support subsequent source tracing analysis. Therefore, the emission reduction rate η plays a "dual adjustment" role in the model: vertically, it reflects the dynamic effect of carbon capture and energy-saving technologies; horizontally, it adjusts the emission differences at different stages and in different regions.

[0124] In this embodiment, the carbon emission factor dynamic correction mechanism, under the framework of the carbon emission calculation formula, the application realizes the dynamic correction of the carbon emission factor according to the multi-dimensional semantic relationship of “engineering activity-energy type-equipment-emission factor” in the knowledge graph. Specifically, when the input data (such as energy structure, construction process or equipment operation parameter) changes, the system automatically identifies the affected node relationship through the reasoning mechanism and updates the corresponding emission factor EF value in real time.

[0125] In this embodiment, the multi-source fusion and Bayesian correction algorithm is introduced to improve the robustness and timeliness of the calculation results. The application comprehensively utilizes project account, energy bill, sensor monitoring data and external database information to perform weighted correction on the carbon emission factor. The correction algorithm adopts Bayesian update model to realize dynamic probability correction: when new measured data appears, the system regards it as posterior information and updates the prior emission factor distribution, so as to obtain the dynamic emission coefficient that best meets the engineering conditions. This method can effectively reduce the deviation caused by a single data source, and make the carbon emission factor have self-adaptive adjustment ability in space and time dimensions.

[0126] In this embodiment, abnormality identification and model self-correction, the application uses time series analysis to identify trends and detect anomalies in emission data. When the carbon emission factor or calculation result deviates from the historical rule or expected interval, the early warning mechanism will be automatically triggered, and the semantic relationship in the knowledge graph is used to locate the potential causes (such as equipment failure, energy structure change or data missing), and then the model self-correction strategy is executed to restore the stability and calculation accuracy of the model.

[0127] S4, visual analysis of dynamic calculation results and correction results, complete dynamic calculation and traceability analysis of engineering carbon emission factors.

[0128] In this embodiment, S4 utilizes the visualization and service layer, the visualization and service layer realize the dynamic visualization analysis of carbon emission factor and project carbon emission through the Web end display interface, mainly including:

[0129] Carbon emission monitoring view: display the real-time carbon emission of each engineering stage and subsystem;

[0130] Low-carbon technology recommendation interface: based on the knowledge reasoning results and project characteristics, recommend matching energy-saving and carbon-reducing technology solutions.

[0131] To sum up, the data acquisition and fusion layer, the knowledge modeling and reasoning layer, the dynamic calculation and analysis layer, and the visualization and service layer in the application are in cooperative operation to form a closed-loop architecture of "data driving-knowledge correlation-intelligent reasoning-visualized decision", and the application realizes intelligent calculation and traceability analysis of carbon emission factors through knowledge graph modeling, graph database storage, multi-source data fusion, and dynamic calculation algorithm.

[0132] Embodiment 2

[0133] As shown in Figure 2 The application provides an engineering carbon emission factor dynamic calculation and traceability analysis system for executing the engineering carbon emission factor dynamic calculation and traceability analysis method described in Embodiment 1, which comprises:

[0134] The data acquisition and fusion layer is configured to acquire multi-source heterogeneous data in the whole process of engineering construction, and to pre-process the multi-source heterogeneous data to form a data set supporting knowledge modeling and calculation analysis;

[0135] The knowledge modeling and reasoning layer is configured to construct a semantic knowledge structure in the field of carbon emission factors based on the data set;

[0136] The dynamic calculation and analysis layer is configured to perform dynamic calculation on the carbon emission factors and correct the weights based on the semantic knowledge structure in the field of carbon emission factors;

[0137] The visualization and service layer is configured to perform visualized analysis on the dynamic calculation results and the correction results, and to complete dynamic calculation and traceability analysis on the engineering carbon emission factors.

[0138] In this embodiment, the engineering carbon emission factor dynamic calculation and traceability analysis system contains hardware structures and / or software modules corresponding to each function in order to realize the principles and beneficial effects of the engineering carbon emission factor dynamic calculation and traceability analysis method. Those skilled in the art should easily realize that, in combination with the description of each schematic unit and algorithm steps in the embodiments disclosed in the application, the application can be realized in the form of hardware and / or a combination of hardware and computer software, and whether a certain function is executed in the form of hardware or computer software depends on the specific application and design constraints of the technical solution, and different methods can be used to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

Claims

1. A method for dynamic calculation and source tracing analysis of engineering carbon emission factors, characterized in that, Includes the following steps: S1. Acquire multi-source heterogeneous data throughout the entire engineering construction process, and preprocess the multi-source heterogeneous data to form a dataset that supports knowledge modeling and computational analysis; S2. Based on the dataset, a semantic knowledge structure for carbon emission factors in the entire process of engineering construction is constructed using knowledge graph technology. The semantic knowledge structure for carbon emission factors is used for intelligent completion, semantic reasoning and causal tracing of carbon emission factors. S3. Based on the semantic knowledge structure of the carbon emission factor domain, the carbon emission factor is dynamically calculated and the weights are corrected. S3 includes the following steps: S301. Construct a carbon emission calculation formula based on the semantic knowledge structure of the carbon emission factor domain; S302. Within the framework of the carbon emission calculation formula, the carbon emission factor is dynamically corrected based on multidimensional semantic relationships to generate a dynamic emission factor. S303. Introduce a multi-source data fusion mechanism, use dynamic emission factors as prior information, use Bayesian methods to update the prior information, and use weighted correction of carbon emission factors to generate dynamic emission coefficients. The dynamic emission coefficients are fed back into the carbon emission formula in S301 for real-time calculation of engineering carbon emissions. S304. Perform trend identification and anomaly detection on carbon emission data. Based on the detection results, locate potential causes by combining semantic relationships in the knowledge graph. Based on the location results, perform self-correction processing using dynamic emission coefficients. The carbon emission calculation formula is as follows: ； ； ； ； ； in, Indicates carbon emissions. Indicates activity level data, Indicates carbon emission factor, Indicates the emission reduction rate. This indicates the effective emission percentage that was not reduced. , and All of these represent weight coefficients determined through Bayesian learning. This represents the theoretical emission reduction percentage. This indicates the emission reduction efficiency obtained based on real-time monitoring data from the engineering site. This represents the emission reduction percentage predicted through knowledge graph reasoning and machine learning. This represents the baseline emissions without the adoption of low-carbon technologies. This indicates the measured emissions after adopting low-carbon technologies. This represents the theoretical activity level under conditions without energy-saving measures. This indicates the current measured activity level; S4. Visualize and analyze the dynamic calculation results and correction results to complete the dynamic calculation and source analysis of the carbon emission factors of the project.

2. The method for dynamic calculation and source tracing analysis of engineering carbon emission factors according to claim 1, characterized in that, S1 includes the following steps: S101. Acquire multi-source heterogeneous data throughout the entire engineering construction process and preprocess the multi-source heterogeneous data. The multi-source heterogeneous data includes basic engineering data, material and energy data, monitoring and environmental data, and standards and specifications data. S102. Write the preprocessed multi-source heterogeneous data into a graph database and a time-series database to form a dataset that supports knowledge modeling and computational analysis.

3. The method for dynamic calculation and source tracing analysis of engineering carbon emission factors according to claim 1, characterized in that, S2 includes the following steps: S201. Domain ontology construction and semantic definition: Based on the dataset, define entity categories and their attributes, and use an ontology description language to define the hierarchical relationships and semantic constraints between entities, so as to model the domain ontology model covering the entire life cycle of engineering construction. S202 Knowledge Extraction and Fusion: Extract knowledge elements related to carbon emissions, and based on the semantic definition results, transform the knowledge into a structured form through named entity recognition, attribute extraction and triple generation, and process the semantics between knowledge to align and express them in a consistent manner; S203. Semantic Alignment and Integration: Based on the fusion results, semantic similarity calculation methods based on word embedding and graph embedding are used to perform entity-level and probability-level alignment processing, so as to form a unified knowledge structure through semantic merging and concept aggregation, and store it in a graph database. S204. Knowledge Graph Storage and Indexing: In the integrated knowledge system, multiple semantic relationships are constructed. Among them, multiple semantic relationships constitute the semantic skeleton of the semantic knowledge structure in the field of carbon emission factors, forming a dynamic knowledge grid. S205. Knowledge Reasoning and Completion Mechanism: Based on the knowledge graph, rule-based reasoning and probabilistic reasoning mechanisms are integrated to mine implicit relationships and automatically complete knowledge, thereby constructing a semantic knowledge structure for the carbon emission factor domain. Among them, rule-based reasoning is used to deduce causal chains according to predefined logical rules; and probabilistic reasoning mechanisms are used to infer unknown relationships, identify potential associations, and dynamically update them.

4. The method for dynamic calculation and source tracing analysis of engineering carbon emission factors according to claim 3, characterized in that, The multiple semantic relationships include: Activity-factor relationship: characterizing the direct impact of engineering activities on carbon emission factors; Factor-Energy Relationship: Describes the correspondence between energy consumption and carbon emission factors in terms of energy conversion and emissions; Energy-equipment relationship: revealing the dependency between energy type and equipment operating characteristics; Factor-technology relationship: indicates the effect of low-carbon technologies on the reduction, control, or substitution of carbon emission factors; Causal-temporal relationship: reflects the evolutionary logic and causal chain of carbon emission factors across time and process stages.

5. The method for dynamic calculation and source tracing analysis of engineering carbon emission factors according to claim 1, characterized in that, Specifically, S303 is: A multi-source data fusion mechanism is introduced, using dynamic emission factors as prior information, and Bayesian methods are used to update the prior information. Based on the updated results, the carbon emission factors are weighted and corrected by comprehensively utilizing project ledgers, energy bills, sensor monitoring data, and external database information. When weighting and correcting, new measured data are treated as posterior information when they appear, and the prior carbon emission factor distribution is updated to obtain the dynamic carbon emission coefficient that best meets the engineering conditions.

6. A system for dynamic calculation and source tracing analysis of engineering carbon emission factors, used to execute the method for dynamic calculation and source tracing analysis of engineering carbon emission factors as described in any one of claims 1-5, characterized in that, include: The data acquisition and fusion layer is used to acquire multi-source heterogeneous data throughout the entire engineering construction process, and to preprocess the multi-source heterogeneous data to form a dataset that supports knowledge modeling and computational analysis. The knowledge modeling and reasoning layer is used to construct semantic knowledge structures in the field of carbon emission factors based on datasets. The dynamic calculation and analysis layer is used to dynamically calculate carbon emission factors and correct their weights based on the semantic knowledge structure of the carbon emission factor domain. The visualization and service layer is used to visualize and analyze the dynamic calculation results and correction results, and to complete the dynamic calculation and source analysis of the carbon emission factors of the project.

Images