A carbon emission calculation method and system for railway infrastructure construction

Abstract

The present application relates to the field of carbon emission accounting technology, and specifically discloses a carbon emission calculation method and system for railway infrastructure construction, which first retrieves the basic data of railway infrastructure and the corresponding verified carbon emissions from the background database to construct a reference sample set, and uses deep learning-based data processing technology to embed the basic data of the railway infrastructure to be verified uploaded by the user and each reference sample for dynamic semantic search, thereby intelligently estimating the reasonable carbon emissions of the railway infrastructure to be verified based on the semantic query response information between the basic data to be verified and each reference sample, and then uses this as a basis to judge whether the total carbon emissions of the railway infrastructure to be verified uploaded by the user are true. The present application can realize the rapid and accurate calculation and verification of carbon emissions during the construction of railway infrastructure, avoid false declarations, and improve the authenticity and reliability of carbon emission data.

Description

Technical Field

[0001] The present application relates to the technical field of carbon emission accounting, and more specifically, to a carbon emission calculation method and system for railway infrastructure construction. Background Art

[0002] Against the backdrop of global climate change and growing awareness of environmental protection, reducing greenhouse gas emissions, especially carbon dioxide emissions, has become a major issue of concern to the international community. As an important mode of public transportation, the construction and maintenance of railway infrastructure plays an irreplaceable role in promoting economic development, improving transportation efficiency and reducing carbon emissions in the transportation sector. However, with the continuous expansion and modernization of the railway network, the problem of carbon emissions in the construction of railway infrastructure has gradually become prominent, becoming an important factor restricting the green development of the railway industry. In the construction of railway infrastructure, greenhouse gas emissions such as carbon dioxide will be generated in varying amounts from material production and transportation to the use of machinery during construction. Therefore, accurately calculating and evaluating the carbon emissions of railway construction projects is crucial to achieving green building goals and reducing environmental footprints.

[0003] Traditionally, the calculation of carbon emissions from railway infrastructure construction relies on empirical formulas or manual estimation methods based on static data, which often require a lot of preliminary research work and may result in inaccurate or delayed results due to technical limitations or inaccurate information. In addition, in some cases, for the purpose of cost savings, improving competitiveness or simplifying the approval process, some railway construction projects may falsely report carbon emissions data, which in turn leads to the inability to correctly assess the environmental impact of the project, causing unnecessary waste of resources or environmental pollution, and is not conducive to the realization of global climate governance goals.

[0004] Therefore, there is a need for a carbon emission calculation method and system for railway infrastructure construction. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a carbon emission calculation method and system for railway infrastructure construction, which first retrieves the basic data of the railway infrastructure and the corresponding verified carbon emissions from the background database to construct a reference sample set, and uses deep learning-based data processing technology to embed the basic data of the railway infrastructure to be verified uploaded by the user and each reference sample for dynamic semantic search, thereby intelligently estimating the reasonable carbon emissions of the railway infrastructure to be verified based on the semantic query response information between the basic data to be verified and each reference sample, and then uses this as a basis to judge whether the total carbon emissions of the railway infrastructure to be verified uploaded by the user are true. In this way, it is possible to achieve rapid and accurate calculation and verification of carbon emissions during the construction of railway infrastructure, avoid false declarations, and improve the authenticity and reliability of carbon emission data.

[0006] According to one aspect of the present application, a method for calculating carbon emissions for railway infrastructure construction is provided, which includes:

[0007] Obtain the basic data and total carbon emissions of the railway infrastructure to be verified uploaded by the user;

[0008] Acquire historical data of carbon emissions from railway infrastructure, wherein each data sample in the historical data of carbon emissions from railway infrastructure is {basic data of railway infrastructure, verified as real carbon emissions};

[0009] Performing structured coding on each data sample in the basic data of the railway infrastructure to be verified and the historical data of carbon emissions of the railway infrastructure to obtain a set of embedded coding vectors of the basic data of the railway infrastructure to be verified and embedded concatenated coding vectors of the basic data-carbon emissions;

[0010] Performing a dynamic semantic search based on a selection interval on the set of the railway infrastructure basic data embedded coding vector to be verified and the basic data-carbon emission embedded spliced ​​coding vector to obtain a railway infrastructure query response coding vector to be verified;

[0011] Determining a reasonable estimate of carbon emissions based on the query response code vector of the railway infrastructure to be verified;

[0012] Based on the reasonable estimate of carbon emissions, determine whether the total carbon emissions of the railway infrastructure to be verified are true.

[0013] Preferably, the basic data includes classification of specific construction stages, quantity and type of construction machinery and equipment, electricity consumption, and data related to material manufacturing and transportation.

[0014] Preferably, a dynamic semantic search based on a selection interval is performed on the set of the railway infrastructure basic data embedded coding vector to be verified and the basic data-carbon emission embedded spliced ​​coding vector to obtain the railway infrastructure query response coding vector to be verified, including:

[0015] Determine the historical basic data selection range ratio based on the internal association between the basic data embedded coding vector of the railway infrastructure to be verified and each basic data-carbon emission embedded spliced ​​coding vector in the set of basic data-carbon emission embedded spliced ​​coding vectors;

[0016] Based on the historical basic data selection range ratio, semantic query response encoding is performed on the set of the basic data embedded coding vector of the railway infrastructure to be verified and the basic data-carbon emissions embedded spliced ​​coding vector to obtain the query response coding vector of the railway infrastructure to be verified.

[0017] Preferably, based on the internal association between the railway infrastructure basic data embedding coding vector to be verified and each basic data-carbon emission embedding concatenated coding vector in the set of basic data-carbon emission embedding concatenated coding vectors, determining the historical basic data selection range ratio comprises:

[0018] Calculate the internal relationship score of the railway infrastructure basic data embedding code vector to be verified relative to each basic data-carbon emission embedding splicing code vector in the set of basic data-carbon emission embedding splicing code vectors to obtain a set of internal relationship score values ​​of basic data to be verified-historical basic data;

[0019] The basic data-carbon emissions embedding concatenation coding vector corresponding to the maximum value in the set of internal relationship scores of the basic data to be verified-historical basic data is used as the basic data-carbon emissions dynamic search anchor vector;

[0020] Based on the characteristic distribution characteristics of the basic data-carbon emission dynamic search anchor vector, the historical basic data selection range ratio is determined.

[0021] Preferably, the vector of the starting position of the historical basic data selection range ratio is the basic data-carbon emissions dynamic search anchor vector, and each basic data-carbon emissions embedded splicing coding vector in the historical basic data selection range ratio is defined as a dynamic search optimized basic data-carbon emissions embedded splicing coding vector.

[0022] Preferably, based on the historical basic data selection range ratio, semantic query response encoding is performed on the set of the railway infrastructure basic data embedded coding vector to be verified and the basic data-carbon emissions embedded spliced ​​coding vector to obtain the railway infrastructure query response coding vector to be verified, including:

[0023] The basic data embedding coding vector of the railway infrastructure to be verified and each dynamic search optimization basic data-carbon emission embedding splicing coding vector in the historical basic data selection range ratio are input into the dynamic semantic search encoder to obtain the query response coding vector of the railway infrastructure to be verified.

[0024] Preferably, determining a reasonable estimate of carbon emissions based on the query response encoding vector of the railway infrastructure to be verified includes:

[0025] The railway infrastructure query response encoding vector to be verified is input into a decoder-based carbon emission estimation module to obtain a reasonable estimate of the carbon emission.

[0026] Preferably, determining whether the total carbon emissions of the railway infrastructure to be verified are true based on the reasonable estimate of carbon emissions includes:

[0027] Calculate the difference between the reasonable estimate of carbon emissions and the total carbon emissions of the railway infrastructure to be verified as a carbon emissions deviation value;

[0028] Based on the comparison between the carbon emission deviation value and a preset threshold, it is determined whether the total carbon emission of the railway infrastructure to be verified is true.

[0029] Another aspect of the application provides a carbon emission calculation system for railway infrastructure construction, comprising:

[0030] The infrastructure data collection module is used to obtain the basic data and total carbon emissions of the railway infrastructure to be verified uploaded by the user;

[0031] A carbon emission historical data collection module is used to obtain the railway infrastructure carbon emission historical data, wherein each data sample in the railway infrastructure carbon emission historical data is {basic data of the railway infrastructure, verified as the real carbon emission amount};

[0032] A structured coding module, used for performing structured coding on each data sample in the basic data of the railway infrastructure to be verified and the historical data of carbon emissions of the railway infrastructure to obtain a set of embedded coding vectors of the basic data of the railway infrastructure to be verified and embedded concatenated coding vectors of the basic data-carbon emissions;

[0033] A dynamic semantic search module, used for performing a dynamic semantic search based on a selected interval on the set of the railway infrastructure basic data embedded coding vector and the basic data-carbon emission embedded spliced ​​coding vector to obtain the railway infrastructure query response coding vector to be verified;

[0034] A carbon emission estimation module, configured to determine a reasonable estimate of carbon emissions based on the query response encoding vector of the railway infrastructure to be verified;

[0035] The total carbon emissions verification module is used to determine whether the total carbon emissions of the railway infrastructure to be verified are true based on the reasonable estimate of the carbon emissions.

[0036] This application has at least the following technical effects:

[0037] Compared with the prior art, the carbon emission calculation method and system for railway infrastructure construction provided by the present application first retrieve the basic data of the railway infrastructure and the corresponding verified carbon emissions from the background database to construct a reference sample set, and use deep learning-based data processing technology to embed the basic data of the railway infrastructure to be verified uploaded by the user and each reference sample for encoding and dynamic semantic search, so as to intelligently estimate the reasonable carbon emissions of the railway infrastructure to be verified based on the semantic query response information between the basic data to be verified and each reference sample, and then use this as a basis to judge whether the total carbon emissions of the railway infrastructure to be verified uploaded by the user are true, which can realize the rapid and accurate calculation and verification of carbon emissions during the construction of railway infrastructure, avoid false declarations, and improve the authenticity and reliability of carbon emission data. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0039] Figure 1 Flow chart of a method for calculating carbon emissions for railway infrastructure construction according to an embodiment of the present application.

[0040] Figure 2 Schematic diagram of data flow of a carbon emission calculation method for railway infrastructure construction according to an embodiment of the present application.

[0041] Figure 3 This is a flowchart of sub-step S4 of the carbon emission calculation method for railway infrastructure construction according to an embodiment of the present application.

[0042] Figure 4 This is a flowchart of sub-step S41 of the carbon emission calculation method for railway infrastructure construction according to an embodiment of the present application.

[0043] Figure 5 4 is a block diagram of a carbon emission calculation system for railway infrastructure construction according to an embodiment of the present application. DETAILED DESCRIPTION

[0044] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0045] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0046] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0047] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0048] It is worth noting that in this application, all actions to obtain data are carried out in compliance with the relevant data protection laws and policies of the country where the data is located, and with the authorization given by the owner of the corresponding device.

[0049] Figure 1 Flow chart of a method for calculating carbon emissions for railway infrastructure construction according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of the carbon emission calculation method for railway infrastructure construction according to an embodiment of the present application. Figure 1 and Figure 2As shown, the carbon emission calculation method for railway infrastructure construction includes the following steps: S1, obtaining the basic data and total carbon emissions of the railway infrastructure to be verified uploaded by the user; S2, obtaining the historical data of carbon emissions of the railway infrastructure, wherein each data sample in the historical data of carbon emissions of the railway infrastructure is {basic data of the railway infrastructure, verified as real carbon emissions}; S3, respectively performing structured coding on the basic data of the railway infrastructure to be verified and each data sample in the historical data of carbon emissions of the railway infrastructure to be verified to obtain a set of embedded coding vectors of the basic data of the railway infrastructure to be verified and a set of embedded concatenated coding vectors of the basic data-carbon emissions; S4, performing dynamic semantic search based on a selected interval on the set of embedded coding vectors of the basic data of the railway infrastructure to be verified and the basic data-carbon emissions embedded concatenated coding vector to obtain a query response coding vector of the railway infrastructure to be verified; S5, determining a reasonable estimate of carbon emissions based on the query response coding vector of the railway infrastructure to be verified; S6, determining whether the total carbon emissions of the railway infrastructure to be verified are real based on the reasonable estimate of carbon emissions.

[0050] In the above-mentioned carbon emission calculation method for railway infrastructure construction, the step S1 obtains the basic data and total carbon emissions of the railway infrastructure to be verified uploaded by the user, and the basic data includes the classification of the specific construction stage, the number and type of construction machinery and equipment, the power consumption, and the material manufacturing and transportation related data. It should be understood that the basic data of the railway infrastructure to be verified uploaded by the user is the basis for carbon emission calculation. Among them, different construction stages (such as earthwork, infrastructure, track laying, etc.) will have different carbon emission sources and emissions. Understanding the classification of specific construction stages helps to estimate carbon emissions more accurately. At the same time, the energy consumed and emissions generated by different types of machinery and equipment during use will also be different. By obtaining the number and type of construction machinery and equipment, the total energy consumption and carbon emissions of construction machinery can be calculated. In addition, power consumption is an important indicator for evaluating energy consumption during construction, and material manufacturing and transportation related data covers the entire carbon emission chain from raw material production to construction site, which is crucial for comprehensive calculation of carbon emissions. Based on this, this application provides users with a more comprehensive and accurate carbon emission calculation service by comprehensively considering various carbon emission factors in the construction process of railway infrastructure.

[0051] Specifically, first, for the collection of classified information on specific construction stages, users are required to list each construction stage in detail, including but not limited to survey and design, civil engineering, track laying, electrification installation, etc., and clearly define the time range for each stage. In order to facilitate subsequent processing, it is recommended to adopt a standardized construction stage classification system, such as the internationally accepted Building Information Model (BIM) standard or industry-specific project management guidelines. This helps ensure that all participants use consistent language to describe the construction process and improve the consistency and comparability of data.

[0052] Next, in terms of the number and type of construction machinery and equipment, users are required to provide a detailed list covering all machinery and equipment involved in the construction, such as excavators, loaders, bulldozers, rollers, etc. For each type of equipment, in addition to counting the number, parameters such as model, power, working hours, and frequency of use should also be recorded. This information is crucial for calculating the carbon emissions generated during the operation of machinery and equipment, because different types of machinery and equipment have different energy consumption characteristics and emission factors. In addition, users are encouraged to provide energy efficiency labels or environmental certification information provided by equipment manufacturers in order to more accurately assess carbon dioxide emissions during the use of machinery.

[0053] The collection of electricity consumption is equally important. Users need to submit detailed records of electricity consumption, including electricity used directly on the construction site and electricity indirectly used to produce building materials. For direct electricity use, it is recommended to record daily or weekly electricity consumption in a time series, while distinguishing different electricity consumption patterns during the day and at night. For indirect electricity consumption, it mainly involves electricity used in the manufacturing process of building materials. This part of information may need to be obtained from suppliers, so it is very important to establish an effective supply chain communication mechanism.

[0054] The collection of data related to material manufacturing and transportation involves a wider supply chain network. For the material manufacturing part, users should provide information on the output, production process and energy source of major building materials such as concrete, steel and asphalt. The data collection of the transportation link should not only consider the logistics process from the origin of raw materials to the processing location, but also include the entire path of the finished materials from the processing plant to the construction site. To this end, users are required to provide information such as the type of transport vehicle, load capacity, driving distance, fuel type, and any efforts to optimize transportation routes to reduce emissions.

[0055] In addition, in order to ensure the accuracy and completeness of all the above information, users are encouraged to use spreadsheets, database management systems or other digital tools to manage and submit data. This will not only improve data entry efficiency, but also automatically check data format and logical errors through built-in validation rules, thereby further improving data quality.

[0056] In the above-mentioned carbon emission calculation method for railway infrastructure construction, the step S2 obtains the historical data of carbon emissions of railway infrastructure, and each data sample in the historical data of carbon emissions of railway infrastructure is {basic data of railway infrastructure, verified as real carbon emissions}. Specifically, the carbon emission data of railway infrastructure in the historical period is further used to construct a reference sample set. Specifically, the present application retrieves a large amount of basic data of railway infrastructure and corresponding carbon emission data that have been verified to be real from the background database, and pairs the basic data of each railway infrastructure with the corresponding carbon emission data to form multiple data samples, so as to explore the potential laws and characteristics of carbon emissions under different construction conditions, thereby providing strong data support for the estimation of carbon emissions of the current railway infrastructure to be verified.

[0057] Specifically, in order to create a data sample set that contains basic data on railway infrastructure and verified real carbon emissions, it is necessary to first determine the specific types of information required, such as specific construction stage classifications, the number and type of construction machinery and equipment, electricity consumption, material manufacturing and transportation related data, etc., while clarifying the time range and geographical area restrictions.

[0058] Ideally, data sources should include public data released by official statistical agencies, audited reports provided by government or industry regulators, research results of scientific research institutions, and information voluntarily submitted by enterprises involved in railway construction. Data collected from these channels tend to be more authoritative and reliable. In addition, it is encouraged to obtain carbon emission data from similar projects in other countries and regions through international cooperation and exchanges to enrich the content of the database. For each data source, the access path, access rights requirements and terms of use should be recorded in detail to ensure that subsequent operations are legal and compliant.

[0059] It is crucial to develop a standardized data collection process for the selected data sources. This includes designing a unified data form template, specifying the fields that must be filled in and their format requirements; developing automated tools to assist in data capture and preprocessing to reduce human errors; and setting up a dedicated team to communicate and coordinate with each data provider to ensure that the data is submitted on time and in good quality. In particular, in order to ensure the consistency of data from different sources, it is recommended to adopt internationally recognized standards and protocols, such as the ISO14064 greenhouse gas accounting standard, as the basic framework for data collection.

[0060] Data quality control is a key link in ensuring the reliability of historical data. To this end, a multi-level quality inspection system can be established, covering three stages: preliminary screening, in-depth verification, and expert review. The preliminary screening stage mainly excludes data entries that obviously do not meet the requirements or have major defects, such as missing necessary fields, abnormally large or small values, etc. In-depth verification relies on computer algorithms and statistical models to perform logical consistency checks, trend analysis, and outlier detection on the data. For any problems found, timely feedback is given to the original data provider for clarification or correction. Finally, in the expert review stage, professionals from various fields such as environmental science and engineering are invited to form a review team to conduct a comprehensive review of the data after the first two rounds of screening, especially for the interpretation and confirmation of some complex technical parameters and professional terms.

[0061] Next, all the data that have passed quality control will be integrated into a structured database, in which each data sample consists of basic data on railway infrastructure and corresponding carbon emissions. In order to facilitate subsequent use, the database should have powerful search functions and flexible data extraction interfaces, allowing users to query required information based on specific conditions. At the same time, considering the importance of data security and privacy protection, the database must also be equipped with strict access control measures, and only authorized personnel can view and operate sensitive content.

[0062] In the above-mentioned carbon emission calculation method for railway infrastructure construction, the step S3 is to perform structured coding on each data sample in the basic data of the railway infrastructure to be verified and the historical data of carbon emissions of the railway infrastructure to obtain a set of embedded coding vectors of the basic data of the railway infrastructure to be verified and a set of embedded spliced ​​coding vectors of the basic data-carbon emissions. It should be understood that considering that the basic data and carbon emissions data of the railway infrastructure usually exist in various forms such as text and numerical values, it is difficult to directly perform efficient calculations and comparisons. Therefore, this application adopts an embedded coding technology based on deep learning to perform structured processing on each data sample in the basic data of the railway infrastructure to be verified and the historical data of carbon emissions of the railway infrastructure, so as to map different types of discrete or continuous data into a low-dimensional dense vector space, while retaining the semantic information of the data, thereby obtaining a set of embedded coding vectors of the basic data of the railway infrastructure to be verified and a set of embedded spliced ​​coding vectors of the basic data-carbon emissions of the railway infrastructure to be verified with a unified structure. In addition, through embedded coding, basic data with similar semantic features can be close to each other in the vector space, while basic data with different semantic features are far away from each other, thereby revealing the inherent correlation between the data and providing a more effective semantic basis for subsequent carbon emissions estimation. Specifically, for the basic data of the railway infrastructure to be verified, different embedding coding strategies need to be adopted for different types of data. For example, for discrete category data such as the classification of specific construction stages, types of construction machinery and equipment, and material names, one-hot encoding technology can be used for encoding; while for continuous numerical data such as the number of construction machinery and equipment, power consumption, and material transportation distance, numerical embedding or normalization processing can be used for encoding to ensure that different types of basic data can be effectively converted into vector form, and through vector splicing, a complete embedding coding vector of the basic data of the railway infrastructure to be verified is obtained. Similarly, for each data sample in the historical data of carbon emissions of railway infrastructure, the basic data and the corresponding carbon emissions data are respectively subjected to the above-mentioned structured encoding to obtain the embedded vector representation of the basic data and the embedded vector representation of the carbon emissions, and through vector splicing, a basic data-carbon emissions embedded splicing coding vector is formed, thereby constructing the association representation between the basic data of railway infrastructure and carbon emissions.

[0063] In the above-mentioned carbon emission calculation method for railway infrastructure construction, the step S4 performs a dynamic semantic search based on the selection interval on the set of the embedded coding vector of the basic data of the railway infrastructure to be verified and the embedded spliced ​​coding vector of the basic data-carbon emissions to obtain the query response coding vector of the railway infrastructure to be verified. It should be understood that the present application takes into account that some data samples in the historical data of carbon emissions of the railway infrastructure may be significantly different from the basic data of the railway infrastructure to be verified. If a matching analysis is performed directly, not only will the amount of calculation be large, but it may also interfere with the final carbon emissions estimation result. Therefore, in order to accurately filter out samples that are most matched or similar to the current basic data to be verified from historical data, the present application proposes a dynamic semantic search coding method, which performs a preliminary semantic association analysis on the set of embedded coding vectors of the basic data of the railway infrastructure to be verified and the embedded spliced ​​coding vectors of the basic data-carbon emissions to determine a reasonable feature selection range, and uses this as an anchor point to perform refined semantic query matching analysis, thereby improving search efficiency and matching accuracy. Among them, Figure 3 FIG. 4 is a flowchart of sub-step S4 of the carbon emission calculation method for railway infrastructure construction according to an embodiment of the present application. Figure 3 As shown, the step S4 includes the steps of: S41, determining the historical basic data selection range ratio based on the internal correlation between the basic data embedded coding vector of the railway infrastructure to be verified and each basic data-carbon emissions embedded splicing coding vector in the set of basic data-carbon emissions embedded splicing coding vectors; S42, based on the historical basic data selection range ratio, performing semantic query response coding on the basic data embedded coding vector of the railway infrastructure to be verified and the set of basic data-carbon emissions embedded splicing coding vectors to obtain the query response coding vector of the railway infrastructure to be verified.

[0064] Figure 4 FIG. 4 is a flowchart of sub-step S41 of the carbon emission calculation method for railway infrastructure construction according to an embodiment of the present application. Figure 4 As shown, the step S41 includes the steps of: S411, calculating the internal relationship score values ​​of the embedded coding vector of the basic data of the railway infrastructure to be verified relative to each basic data-carbon emissions embedded splicing coding vector in the set of the basic data-carbon emissions embedded splicing coding vector to obtain a set of internal relationship score values ​​of the basic data to be verified-historical basic data; S412, using the basic data-carbon emissions embedded splicing coding vector corresponding to the maximum value in the set of internal relationship score values ​​of the basic data to be verified-historical basic data as the basic data-carbon emissions dynamic search anchor vector; S413, determining the historical basic data selection range ratio based on the characteristic distribution characteristics of the basic data-carbon emissions dynamic search anchor vector.

[0065] More specifically, the step S411 is expressed as follows:

[0066] ;

[0067] ;

[0068] in, is the basic data - a collection of concatenated encoding vectors embedded in carbon emissions, , , , They are the first, second, and third in the set of basic data-carbon emissions embedded concatenated coding vectors. and Basic data - carbon emissions embedded in the concatenated encoding vector, is the embedded coding vector of the basic data of the railway infrastructure to be verified, and They are the weight parameter matrix of historical basic data and the weight parameter matrix of basic data to be verified. is the hyperbolic tangent activation function, is the transposed vector of the internal relationship score reference vector between the basic data to be verified and the historical basic data, For the The corresponding internal relationship score between the basic data to be verified and the historical basic data.

[0069] More specifically, the step S412 is expressed as follows:

[0070] ;

[0071] in, It means extracting the basic data-carbon emission embedding concatenation coding vector corresponding to the maximum value in the set of internal relationship score values ​​of the basic data to be verified-historical basic data, Dynamically search for anchor vectors for basic data - carbon emissions.

[0072] Specifically, the neural network model is first used to perform feature association analysis and internal relationship scoring on the embedded coding vector of the basic data of the railway infrastructure to be verified and each basic data-carbon emissions embedded splicing coding vector to evaluate the information relevance and degree of association between the basic data to be verified and the historical basic data. It should be understood that the higher the internal relationship score value, the more similar the data characteristics between the two are. Therefore, the present application further selects the basic data-carbon emissions embedded splicing coding vector with the highest score value from the set of basic data-carbon emissions embedded splicing coding vectors as the benchmark for comparative analysis based on the obtained internal relationship scores, and defines it as the basic data-carbon emissions dynamic search anchor vector. In this way, by screening out the historical basic data samples that are most similar to the basic data to be verified as the anchor point for subsequent feature comparative analysis, it helps to improve the accuracy and reliability of feature comparative analysis.

[0073] More specifically, the step S413 determines the historical basic data selection range ratio based on the characteristic distribution characteristics of the basic data-carbon emissions dynamic search anchor vector. In a specific example of the present application, the vector of the starting position of the historical basic data selection range ratio is the basic data-carbon emissions dynamic search anchor vector, and each basic data-carbon emissions embedded splicing coding vector in the historical basic data selection range ratio is defined as a dynamic search optimization basic data-carbon emissions embedded splicing coding vector, which is expressed by the formula:

[0074] ;

[0075] ;

[0076] in, , and They respectively represent the maximum eigenvalue, eigenmean and eigenvariance of the basic data-carbon emissions dynamic search anchor vector, is a very small positive number, used to prevent the denominator from being 0. Indicates rounding up operation. Select the window size of the range ratio for the historical base data, The vector for selecting the starting position of the range ratio for the historical basic data is , A vector for selecting the end position of the range ratio for the historical basic data, A set of dynamically searched optimized basic data-carbon emissions embedded concatenated coding vectors is selected for each range ratio of the historical basic data.

[0077] Specifically, considering that relying solely on a single similar data sample for feature comparison analysis may result in inaccurate carbon emissions estimation results due to limitations of data features. Therefore, the present application further uses the basic data-carbon emissions dynamic search anchor vector as the starting position, and based on the characteristic distribution characteristics of the basic data-carbon emissions dynamic search anchor vector, calculates the selection range ratio of the historical basic data, thereby selecting multiple basic data-carbon emissions embedded splicing coding vectors from the set of basic data-carbon emissions embedded splicing coding vectors as candidate samples for comparison and analysis, and constructing a dynamic search optimization basic data-carbon emissions embedded splicing coding vector set. In this way, by limiting the data range for comparative analysis, it is possible to not only reduce the amount of calculation and improve the efficiency of carbon emissions estimation, but also focus on the historical basic data samples that are most similar to the basic data to be verified, thereby avoiding analysis errors caused by a single data sample.

[0078] Specifically, in a specific example of the present application, the step S42 includes: inputting the embedding coding vector of the railway infrastructure basic data to be verified and each dynamic search optimization basic data-carbon emission embedding concatenation coding vector in the historical basic data selection range ratio into the dynamic semantic search encoder to obtain the query response coding vector of the railway infrastructure to be verified, which is expressed by the formula:

[0079] ;

[0080] ;

[0081] in, is the magnitude of the vector, for and The cosine similarity between A query response encoding vector for the railway infrastructure to be verified.

[0082] Specifically, the feature difference between the basic data to be verified and the historical basic data is extracted by performing feature difference calculations on the embedding coding vector of the basic data of the railway infrastructure to be verified and each dynamically searched optimized basic data-carbon emissions embedded splicing coding vector in the selection range, and the feature difference information is weighted and aggregated using the feature similarity between the two as the weight coefficient to comprehensively consider the difference information of the basic data to be verified relative to the reference sample, and further fuse the difference information between the basic data to be verified and the reference sample data with the basic data-carbon emissions dynamic search anchor vector to generate the final query response coding vector of the railway infrastructure to be verified. In this way, the characteristics of the basic data of the railway infrastructure to be verified are taken into account, and the most similar reference data sample is used as the basis, so that the actual situation of the railway infrastructure to be verified can be more comprehensively reflected, and a more comprehensive and reliable basis can be provided for the subsequent accurate estimation of carbon emissions.

[0083] In the above-mentioned carbon emission calculation method for railway infrastructure construction, the step S5 determines a reasonable estimate of carbon emissions based on the query response coding vector of the railway infrastructure to be verified. In a specific example of the present application, the step S5 includes: inputting the query response coding vector of the railway infrastructure to be verified into a decoder-based carbon emission estimation module to obtain the reasonable estimate of carbon emissions. Specifically, the decoder is based on a neural network architecture. After receiving the query response coding vector of the railway infrastructure to be verified as input, it fully learns and utilizes the inherent characteristics of the basic data to be verified implied in the vector and the correlation information between it and the historical reference data through layer-by-layer decoding operations, and gradually parses out the reasonable estimate of carbon emissions corresponding to the basic data of the railway infrastructure to be verified, thereby providing a quantitative basis for the carbon emission management of railway infrastructure.

[0084] Among them, since the set of embedded coding vectors of the basic data of the railway infrastructure to be verified and the set of embedded spliced ​​coding vectors of the basic data-carbon emissions respectively represent the low-dimensional embedded coding features of the basic data of the railway infrastructure to be verified and the embedded coding features of the historical data of carbon emissions of the railway infrastructure, when performing feature dynamic semantic search encoding based on the selection range ratio anchoring, the feature population attributes of different semantics will have dynamic semantic search fairness differences based on the selection range ratio anchoring level, thereby affecting the coding feature distribution response inclusiveness of the query response coding vector of the railway infrastructure to be verified, and reducing the accuracy of the reasonable estimate of carbon emissions obtained by inputting the decoder-based carbon emissions estimation module.

[0085] In a preferred example, inputting the to-be-verified railway infrastructure query response encoding vector into a decoder-based carbon emission estimation module to obtain a reasonable estimate of carbon emissions includes:

[0086] Arranging the query response code vectors of the to-be-verified railway infrastructure in ascending order according to the magnitude of the eigenvalues ​​to obtain the query response code vectors of the to-be-verified railway infrastructure in ascending order;

[0087] Determine the mean of the eigenvalues ​​corresponding to the ascending code vector of the query response to be verified and the standard deviation of the eigenvalues , and multiply the ascending code vector of the railway infrastructure query response to be verified by the point-wise subtraction vector of the eigenvalue mean and the eigenvalue standard deviation to obtain the first railway infrastructure query response code statistical modulation vector to be verified, that is:

[0088] ;

[0089] in, and represent the eigenvalue mean and eigenvalue standard deviation corresponding to the ascending coded vector of the query response to the railway infrastructure to be verified, respectively, represents the ascending code vector of the query response to the railway infrastructure to be verified, Indicates point reduction, represents dot product, A first railway infrastructure query response coding statistical modulation vector is represented;

[0090] The second railway infrastructure query response coding statistical modulation vector to be checked is obtained by multiplying the point-by-point subtraction vector of the railway infrastructure query response to be checked with the eigenvalue standard deviation and the eigenvalue mean, that is:

[0091] ;

[0092] in, A second railway infrastructure query response coding statistical modulation vector is represented;

[0093] After multiplying the bit-by-bit inverse of the second railway infrastructure query response coding statistical modulation vector by the first railway infrastructure query response coding statistical modulation vector, taking the bit-by-bit logarithm with base 2 to obtain the query response coding neuron granularity optimization vector, that is:

[0094] ;

[0095] in, represents the bit-by-bit inverse of the second railway infrastructure query response coding statistical modulation vector to be verified, that is, the inverse of each position characteristic value of the second railway infrastructure query response coding statistical modulation vector to be verified is calculated, Represents the query response encoding neuron granularity optimization vector;

[0096] The eigenvalue mean Divide by the standard deviation of the eigenvalue The square root of the quotient is multiplied by the weight hyperparameter, and then the optimized query response encoding neuron granularity optimization vector point is obtained to obtain the optimized railway infrastructure query response encoding vector to be verified, that is:

[0097] ;

[0098] in, represents the weighted hyperparameter, A code vector representing an optimized railway infrastructure query response to be verified;

[0099] The optimized query response encoding vector of the railway infrastructure to be verified is input into a decoder-based carbon emission estimation module to obtain a reasonable estimation of carbon emissions.

[0100] Therefore, considering the attribute level fairness differences of the data population corresponding to the sequence response fusion features of the railway infrastructure query response coding vector to be verified, in order to improve the response inclusiveness under the feature distribution diversity of the railway infrastructure query response coding vector to be verified, in the technical solution of the present application, by mapping the serialized signal of the railway infrastructure query response coding vector to be verified into the synaptic connection network defined by the statistical features, a meaningful measurement of the activation association of the neural pattern set in the synchronization field can be achieved, and on this basis, a neural activity space with independent activation channels is constructed by adjusting the synaptic plasticity of the neuron response, and the multi-layer neural network of the neuron response is optimized for synaptic pruning in the neural activity space based on the signal query. In this way, a robust distribution fairness unified representation of the railway infrastructure query response coding vector to be verified is achieved to improve the accuracy of the reasonable estimate of carbon emissions obtained by the decoder-based carbon emissions estimation module.

[0101] In the above-mentioned carbon emission calculation method for railway infrastructure construction, the step S6 determines whether the total carbon emissions of the railway infrastructure to be verified are true based on the reasonable estimate of carbon emissions. In a specific example of the present application, the step S6 includes: calculating the difference between the reasonable estimate of carbon emissions and the total carbon emissions of the railway infrastructure to be verified as a carbon emissions deviation value; based on the comparison between the carbon emissions deviation value and a preset threshold, determining whether the total carbon emissions of the railway infrastructure to be verified are true. Specifically, in order to measure the degree of difference between the total carbon emissions declared by the user and the reasonable carbon emissions estimated based on the reference sample, the present application further calculates the difference between the reasonable estimate of carbon emissions and the total carbon emissions of the railway infrastructure to be verified as a carbon emissions deviation value, and by comparing the carbon emissions deviation value with the preset threshold, determines whether the total carbon emissions declared by the user are true, thereby achieving effective verification of carbon emission data during the construction of railway infrastructure and ensuring the authenticity and reliability of carbon emission data. Specifically, if the carbon emission deviation value is less than the preset threshold, it is considered that the total carbon emission amount reported by the user is relatively true and close to the reasonable estimate based on historical data, indicating that the carbon emission management of railway infrastructure is relatively standardized; conversely, if the carbon emission deviation value is greater than or equal to the preset threshold, it may indicate that the total carbon emission amount reported by the user is abnormal and needs further verification and verification. In this way, not only can the errors in carbon emission data be discovered and corrected in a timely manner, but also the supervision of carbon emission management of railway infrastructure can be strengthened, and the railway industry can be promoted to achieve low-carbon, green and sustainable development.

[0102] In summary, the carbon emission calculation method for railway infrastructure construction based on the embodiment of the present application is explained, which first retrieves the basic data of the railway infrastructure and the corresponding verified carbon emissions from the background database to construct a reference sample set, and uses deep learning-based data processing technology to embed the basic data of the railway infrastructure to be verified uploaded by the user and each reference sample for dynamic semantic search, thereby intelligently estimating the reasonable carbon emissions of the railway infrastructure to be verified based on the semantic query response information between the basic data to be verified and each reference sample, and then uses this as a basis to judge whether the total carbon emissions of the railway infrastructure to be verified uploaded by the user are true. In this way, the rapid and accurate calculation and verification of carbon emissions during the construction of railway infrastructure can be achieved, false declarations can be avoided, and the authenticity and reliability of carbon emission data can be improved.

[0103] Furthermore, a carbon emission calculation system for railway infrastructure construction is also provided.

[0104] Figure 5 FIG. 1 is a block diagram of a carbon emission calculation system for railway infrastructure construction according to an embodiment of the present application. Figure 5As shown, according to the embodiment of the present application, the carbon emission calculation system 100 for railway infrastructure construction includes: an infrastructure data acquisition module 110, which is used to obtain the basic data and total carbon emissions of the railway infrastructure to be verified uploaded by the user; a carbon emission history data acquisition module 120, which is used to obtain the railway infrastructure carbon emission history data, wherein each data sample in the railway infrastructure carbon emission history data is {basic data of the railway infrastructure, verified as the real carbon emissions}; a structured coding module 130, which is used to perform structured coding on the basic data of the railway infrastructure to be verified and each data sample in the railway infrastructure carbon emission history data to obtain the railway infrastructure to be verified. A set of railway infrastructure basic data embedded coding vectors and basic data-carbon emissions embedded concatenated coding vectors; a dynamic semantic search module 140, used to perform dynamic semantic search based on a selected interval on the set of railway infrastructure basic data embedded coding vectors and basic data-carbon emissions embedded concatenated coding vectors to obtain the railway infrastructure query response coding vector to be verified; a carbon emissions estimation module 150, used to determine a reasonable estimate of carbon emissions based on the railway infrastructure query response coding vector to be verified; a total carbon emissions verification module 160, used to determine whether the total carbon emissions of the railway infrastructure to be verified are true based on the reasonable estimate of carbon emissions.

[0105] The specific operations of each module in the carbon emission calculation system for railway infrastructure construction have been referenced above. Figures 1 to 4 The carbon emission calculation method for railway infrastructure construction has been introduced in detail in the description of the carbon emission calculation method for railway infrastructure construction, and therefore, its repeated description will be omitted.

[0106] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0107] In the above embodiments, the description of each embodiment has its own emphasis. For the parts that are not described or recorded in detail in a certain embodiment, please refer to the relevant description of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiment described above is only schematic. For example, the unit division is only a logical function division, and there may be other division methods in actual implementation. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0108] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference to a figure in a claim should not be considered as limiting the claim to which it relates.

[0109] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units stated in the system claims can also be implemented by one unit through software or hardware.

[0110] Finally, it should be noted that the above description has been given for the purpose of illustration and description. In addition, the above embodiments are only used to illustrate the technical solution of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for calculating carbon emissions for railway infrastructure construction, characterized in that: include: Obtain the basic data and total carbon emissions of the railway infrastructure to be verified uploaded by the user; Acquire historical data of carbon emissions from railway infrastructure, where each data sample in the historical data of carbon emissions from railway infrastructure is {basic data of railway infrastructure, verified to be real carbon emissions}; Performing structured coding on each data sample in the basic data of the railway infrastructure to be verified and the historical data of carbon emissions of the railway infrastructure to obtain a set of embedded coding vectors of the basic data of the railway infrastructure to be verified and embedded concatenated coding vectors of the basic data-carbon emissions; A dynamic semantic search based on a selection interval is performed on the set of the basic data embedded coding vector of the railway infrastructure to be verified and the basic data-carbon emission embedded spliced ​​coding vector to obtain a query response coding vector of the railway infrastructure to be verified, which includes: Determine the historical basic data selection range ratio based on the internal association between the basic data embedded coding vector of the railway infrastructure to be verified and each basic data-carbon emission embedded spliced ​​coding vector in the set of basic data-carbon emission embedded spliced ​​coding vectors; Based on the historical basic data selection range ratio, semantic query response encoding is performed on the set of the railway infrastructure basic data embedded coding vector to be verified and the basic data-carbon emission embedded spliced ​​coding vector to obtain the railway infrastructure query response coding vector to be verified; Determining a reasonable estimate of carbon emissions based on the query response code vector of the railway infrastructure to be verified; Based on the reasonable estimate of carbon emissions, determine whether the total carbon emissions of the railway infrastructure to be verified are true.

2. The carbon emission calculation method for railway infrastructure construction according to claim 1, characterized in that: The basic data include classification of specific construction stages, quantity and type of construction machinery and equipment, electricity consumption, and data related to material manufacturing and transportation.

3. The carbon emission calculation method for railway infrastructure construction according to claim 2, characterized in that: Based on the internal association between the railway infrastructure basic data embedding coding vector to be verified and each basic data-carbon emission embedding concatenated coding vector in the set of basic data-carbon emission embedding concatenated coding vectors, determining the historical basic data selection range ratio includes: Calculate the internal relationship score value of the railway infrastructure basic data embedding code vector to be verified relative to each basic data-carbon emission embedding splicing code vector in the set of basic data-carbon emission embedding splicing code vectors to obtain a set of internal relationship score values ​​of basic data to be verified-historical basic data; The basic data-carbon emissions embedding concatenation coding vector corresponding to the maximum value in the set of internal relationship scores of the basic data to be verified-historical basic data is used as the basic data-carbon emissions dynamic search anchor vector; Determining the historical basic data selection range ratio based on the characteristic distribution characteristics of the basic data-carbon emissions dynamic search anchor vector; The internal relationship score values ​​of the embedded coding vector of the railway infrastructure basic data to be verified relative to each basic data-carbon emission embedded splicing coding vector in the set of the basic data-carbon emission embedded splicing coding vector are calculated to obtain a set of internal relationship score values ​​of the basic data to be verified-historical basic data, which is expressed by the formula: ； ； in, is the basic data - a collection of concatenated encoding vectors embedded in carbon emissions, , , , They are the first, second, and third in the set of basic data-carbon emissions embedded concatenated coding vectors. and Basic data - carbon emissions embedded in the concatenated encoding vector, is the embedded coding vector of the basic data of the railway infrastructure to be verified, and They are the weight parameter matrix of historical basic data and the weight parameter matrix of basic data to be verified. is the hyperbolic tangent activation function, is the transposed vector of the internal relationship score reference vector between the basic data to be verified and the historical basic data, For the The corresponding internal relationship score between the basic data to be verified and the historical basic data; Among them, the basic data-carbon emissions embedded concatenation coding vector corresponding to the maximum value in the set of internal relationship scores of the basic data to be verified-historical basic data is used as the basic data-carbon emissions dynamic search anchor vector, which is expressed by the formula: ； in, It means extracting the basic data-carbon emission embedding concatenation coding vector corresponding to the maximum value in the set of internal relationship score values ​​of the basic data to be verified-historical basic data, Dynamically search for anchor vectors for basic data - carbon emissions.

4. The carbon emission calculation method for railway infrastructure construction according to claim 3 is characterized in that: The vector of the starting position of the historical basic data selection range ratio is the basic data-carbon emissions dynamic search anchor vector, and each basic data-carbon emissions embedded splicing coding vector in the historical basic data selection range ratio is defined as a dynamic search optimization basic data-carbon emissions embedded splicing coding vector, which is expressed by the formula: ； ； in, , and They respectively represent the maximum eigenvalue, eigenmean and eigenvariance of the basic data-carbon emissions dynamic search anchor vector, is a very small positive number, used to prevent the denominator from being 0. Indicates rounding up operation. Select the window size of the range ratio for the historical base data, A vector for selecting the starting position of the range ratio for the historical base data, A vector for selecting the end position of the range ratio for the historical basic data, A set of dynamically searched optimized basic data-carbon emissions embedded concatenated coding vectors is selected for each range ratio of the historical basic data.

5. The carbon emission calculation method for railway infrastructure construction according to claim 4 is characterized in that: Based on the historical basic data selection range ratio, semantic query response encoding is performed on the set of the railway infrastructure basic data embedded coding vector to be verified and the basic data-carbon emission embedded splicing coding vector to obtain the railway infrastructure query response coding vector to be verified, including: The railway infrastructure basic data embedding coding vector to be verified and each dynamic search optimization basic data-carbon emission embedding concatenation coding vector in the historical basic data selection range ratio are input into the dynamic semantic search encoder to obtain the railway infrastructure query response coding vector to be verified, which is expressed as follows: ； ； in, is the magnitude of the vector, for and The cosine similarity between A query response encoding vector for the railway infrastructure to be verified.

6. The carbon emission calculation method for railway infrastructure construction according to claim 5, characterized in that: Determining a reasonable estimate of carbon emissions based on the query response code vector of the railway infrastructure to be verified includes: Inputting the query response code vector of the railway infrastructure to be verified into a decoder-based carbon emission estimation module to obtain a reasonable estimate of the carbon emission; Inputting the query response code vector of the railway infrastructure to be verified into a decoder-based carbon emissions estimation module to obtain a reasonable estimate of carbon emissions, including: Arrange the query response code vectors of the to-be-verified railway infrastructure in ascending order according to the eigenvalues ​​to obtain the query response ascending code vectors of the to-be-verified railway infrastructure; determine the eigenvalue mean corresponding to the query response ascending code vectors of the to-be-verified railway infrastructure and the standard deviation of the eigenvalues , and multiply the ascending code vector of the railway infrastructure query response to be verified by the point-wise subtraction vector of the eigenvalue mean and the eigenvalue standard deviation to obtain the first railway infrastructure query response code statistical modulation vector to be verified, that is: ； in, and represent the eigenvalue mean and eigenvalue standard deviation corresponding to the ascending coded vector of the query response to the railway infrastructure to be verified, respectively, represents the ascending code vector of the query response to the railway infrastructure to be verified, Indicates point reduction, represents dot product, A first railway infrastructure query response coding statistical modulation vector is represented; The second railway infrastructure query response coding statistical modulation vector to be checked is obtained by multiplying the point-by-point subtraction vector of the railway infrastructure query response to be checked with the eigenvalue standard deviation and the eigenvalue mean, that is: ； in, A second railway infrastructure query response coding statistical modulation vector is represented; After multiplying the bit-by-bit inverse of the second railway infrastructure query response coding statistical modulation vector by the first railway infrastructure query response coding statistical modulation vector, taking the bit-by-bit logarithm with base 2 to obtain the query response coding neuron granularity optimization vector, that is: ； in, represents the bit-by-bit inverse of the second railway infrastructure query response coding statistical modulation vector to be verified, that is, the inverse of the characteristic value of each position of the second railway infrastructure query response coding statistical modulation vector to be verified is calculated, Represents the query response encoding neuron granularity optimization vector; The eigenvalue mean Divide by the standard deviation of the eigenvalue The square root of the quotient is multiplied by the weight hyperparameter, and then the optimized query response encoding neuron granularity optimization vector point is obtained to obtain the optimized railway infrastructure query response encoding vector to be verified, that is: ； in, represents the weighted hyperparameter, A code vector representing an optimized railway infrastructure query response to be verified; The optimized query response encoding vector of the railway infrastructure to be verified is input into a decoder-based carbon emission estimation module to obtain a reasonable estimation of carbon emissions.

7. The carbon emission calculation method for railway infrastructure construction according to claim 6, characterized in that: Based on the reasonable estimate of carbon emissions, determining whether the total carbon emissions of the railway infrastructure to be verified are true includes: Calculate the difference between the reasonable estimate of carbon emissions and the total carbon emissions of the railway infrastructure to be verified as a carbon emissions deviation value; Based on the comparison between the carbon emission deviation value and a preset threshold, it is determined whether the total carbon emission of the railway infrastructure to be verified is true.

8. A carbon emission calculation system for railway infrastructure construction, used to execute the carbon emission calculation method for railway infrastructure construction as claimed in any one of claims 1 to 7, characterized in that: include: The infrastructure data collection module is used to obtain the basic data and total carbon emissions of the railway infrastructure to be verified uploaded by the user; A carbon emission historical data collection module is used to obtain the railway infrastructure carbon emission historical data, wherein each data sample in the railway infrastructure carbon emission historical data is {basic data of the railway infrastructure, verified as the real carbon emission amount}; A structured coding module, used for performing structured coding on each data sample in the basic data of the railway infrastructure to be verified and the historical data of carbon emissions of the railway infrastructure to obtain a set of embedded coding vectors of the basic data of the railway infrastructure to be verified and embedded concatenated coding vectors of the basic data-carbon emissions; A dynamic semantic search module is used to perform a dynamic semantic search based on a selected interval on the set of the railway infrastructure basic data embedded coding vector and the basic data-carbon emission embedded splicing coding vector to obtain the railway infrastructure query response coding vector to be verified, which includes: Determine the historical basic data selection range ratio based on the internal association between the basic data embedded coding vector of the railway infrastructure to be verified and each basic data-carbon emission embedded spliced ​​coding vector in the set of basic data-carbon emission embedded spliced ​​coding vectors; Based on the historical basic data selection range ratio, semantic query response encoding is performed on the set of the railway infrastructure basic data embedded coding vector to be verified and the basic data-carbon emission embedded spliced ​​coding vector to obtain the railway infrastructure query response coding vector to be verified; A carbon emission estimation module, configured to determine a reasonable estimate of carbon emissions based on the query response encoding vector of the railway infrastructure to be verified; The total carbon emissions verification module is used to determine whether the total carbon emissions of the railway infrastructure to be verified are true based on the reasonable estimate of the carbon emissions.

Images