Construction project carbon emission ledger compiling method based on artificial intelligence

Abstract

The invention discloses a construction project carbon emission ledger compiling method based on artificial intelligence, and relates to the technical field of building construction, and the specific steps of the compiling method are as follows: S100, multi-source data acquisition and preparation: deploying a sensor at a construction site to monitor the data of the construction site in real time, recording the material data by using a bar code scanning device and an RFID reader-writer, and storing the material data in a database; project documents and construction logs are processed by means of the OCR technology, data are synchronously standardized, multi-source data of energy consumption, environment, position and state of the construction site can be comprehensively collected in real time by deploying various sensors and adopting the advanced OCR technology, standardization processing is carried out on the multi-source data, the efficiency and accuracy of data collection are greatly improved, and the data collection cost is reduced. In addition, a solid foundation is provided for subsequent carbon emission calculation, meanwhile, in combination with a natural language processing technology and a correlation analysis formula, potential relations between data can be deeply mined, and therefore the total carbon emission of the construction activity can be calculated more accurately.

Description

Technical Field

[0001] This invention relates to the field of building construction technology, specifically to a method for compiling carbon emission ledgers for construction projects based on artificial intelligence. Background Technology

[0002] With the global climate change problem becoming increasingly severe, reducing carbon emissions has become a global consensus. In the construction industry, construction projects are one of the main sources of energy consumption and carbon emissions, making carbon emission management particularly important. In recent years, with the rapid development of artificial intelligence technology, its application in data processing, information mining, and intelligent decision-making has become increasingly widespread, providing new technical means for carbon emission management of construction projects. By integrating multiple sensors, OCR technology, natural language processing, and knowledge graph technology, it is possible to achieve comprehensive monitoring, accurate calculation, and intelligent management of carbon emissions from construction projects, thereby promoting the construction industry towards low-carbon, green, and sustainable development.

[0003] Traditional carbon emission management methods for construction projects mainly rely on manual statistics and estimation. This method has many shortcomings. First, the data collection process is cumbersome and prone to errors, resulting in inaccurate and incomplete carbon emission data. Second, traditional calculation methods are often based on empirical formulas or simple models, which cannot fully consider the complexity and diversity of construction projects, thus leading to a large deviation between the calculation results and the actual emissions. In addition, traditional methods lack intelligent management and decision support, making it difficult to achieve dynamic monitoring and timely control of carbon emissions. These problems limit the effectiveness of traditional methods in carbon emission management of construction projects and hinder the green development process of the construction industry.

[0004] Therefore, developing an AI-based method for compiling carbon emission ledgers for construction projects will help promote the construction industry toward low-carbon, green, and sustainable development, and has significant practical value and application prospects. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies and provide an artificial intelligence-based method for compiling carbon emission ledgers for construction projects. This method integrates key technologies such as multi-source data acquisition, data mining and emission calculation, carbon emission knowledge graph construction, carbon emission management ledger generation, and emission reduction strategy simulation and optimization. This achieves comprehensive, accurate, and intelligent management of carbon emissions from construction projects. It not only improves the accuracy and completeness of carbon emission data but also provides strong data support and decision-making basis for energy conservation and emission reduction in construction projects.

[0006] To solve the above-mentioned technical problems, this invention provides the following technical solution: a method for compiling carbon emission ledgers for construction projects based on artificial intelligence, the specific steps of which are as follows: S100, Multi-source Data Acquisition and Preparation: Sensors are deployed at the construction site to monitor the data of the construction site in real time, barcode scanning equipment and RFID readers are used to record material data, project documents and construction logs are processed with the help of OCR technology, and the data is standardized and stored in a distributed database simultaneously. S200, Data Mining and Emissions Calculation: Extract multi-source data from the database, perform deep semantic understanding of unstructured text using natural language processing technology, conduct correlation analysis on structured data, combine the results of both, and calculate the total carbon emissions using the formula for calculating the total carbon emissions of construction activities. S300, Carbon Emission Knowledge Graph Construction: Neo4j is selected as the construction tool, defining equipment, materials, personnel, construction activities and carbon emissions as nodes, and use, association and generation as relationship edges. The information is transformed into nodes and edges through the Cypher query language to construct the graph, and the carbon emission knowledge graph is verified and optimized. S400, carbon emission management ledger generation: Based on the calculated carbon emissions and knowledge graph logic, the initial ledger is generated by extracting and integrating data from the storage center in a standard format, and is updated in real time during construction, and a visual interface is built for managers; S500, emission reduction strategy simulation and optimization: collect construction schedule data and input it into the construction carbon emission simulation model. The model simulates carbon emissions based on different scenario assumptions. Based on the results, emission reduction strategies are generated. After applying the strategies, feedback data is collected to update the knowledge graph and carbon emission management ledger.

[0007] Furthermore, in S100, the sensors used in the multi-source data acquisition and preparation process are: The energy consumption sensors are: current sensors and voltage sensors; The environmental sensors include: temperature and humidity sensors, dust sensors, and noise sensors; The location sensors are: GPS sensors and BeiDou satellite positioning system sensors; The status sensors are: pressure sensors and vibration sensors.

[0008] Furthermore, in S200, the specific steps of using natural language processing technology to perform deep semantic understanding of unstructured text data in data mining and emission calculation are as follows: cleaning the extracted unstructured text data, performing lexical analysis to split the text into individual words, performing part-of-speech tagging and stemming, identifying the semantic role of each word in the sentence, extracting key event information from the text based on the semantic role tagging results, and integrating the extracted event information with a pre-built construction domain knowledge base.

[0009] Furthermore, in step S200, the extracted structured data is subjected to association analysis using a correlation analysis formula in the data mining and emission calculation process. The formula is as follows: ,in Representing the Class data and the first The correlation between two classes of data ranges from -1 to 1. The closer the absolute value is to 1, the stronger the correlation between the two classes of data; the closer it is to 0, the weaker the correlation. The sign indicates the direction of the correlation: positive for positive correlation and negative for negative correlation. It is the total number of time periods for the data. For the first Class data in the first Standardized values ​​for each time period, For the first Class data in the first Standardized values ​​for each time period, It is the first The weighting coefficients for each time period are subjectively set based on the importance of the data in different time periods, and their values ​​range from 0 to 1. It is the first Class data and the first The number of delay periods for this type of data in the time series. This represents the total number of construction project time cycles. The time period number represents the data.

[0010] Furthermore, in step S200, the total carbon emissions of construction activities are calculated using the formula for calculating the total carbon emissions of construction activities in data mining and emissions calculation. The formula is as follows: ,in The total carbon emissions of a certain construction activity. This represents the total carbon emissions of the construction equipment during the construction activity. This represents the total carbon emissions of building materials during the construction activity. This refers to the carbon emissions generated by other factors during the construction activity.

[0011] Furthermore, in S200, the calculation of each parameter in the formula for calculating the total carbon emissions of construction activities in data mining and emissions calculation, and the total carbon emissions of construction equipment in the construction activity. The calculation formula is: ,in The number and types of equipment involved in the construction activity. It is the first The average power of the equipment is obtained from the equipment's technical parameter table. For the first The actual operating time of the equipment during the construction activity is determined by the time information in the equipment usage events. It is the first The load factor of this type of equipment, ranging from 0 to 1, is calculated based on the equipment's energy consumption and power data. It is the first The percentage correction for the impact of the construction environment on energy consumption is determined based on the influence of weather conditions and site topography on equipment energy consumption. For the first The carbon emission intensity of the energy used by the equipment is obtained from relevant standards or databases based on the energy type; the total carbon emissions of building materials in this construction activity. The calculation formula is: ,in This refers to the types and quantities of building materials used in the construction activity. It is the first The amount of material used is determined through material usage data. It is the first The carbon emissions per unit mass during the production stage of this material are obtained from the environmental impact reports provided by the material suppliers. It is the first The carbon emissions per unit mass of the material during the transportation phase are calculated using transportation records and relevant transportation carbon emission standards. It is the first The percentage increase in carbon emissions due to material loss and waste during construction is corrected by statistical analysis of material loss at the construction site; carbon emissions from other factors during construction activities are also considered. The calculation is determined by statistically analyzing the carbon emissions generated from lighting and ventilation energy consumption at the construction site.

[0012] Furthermore, in S300, the specific steps for constructing the carbon emission knowledge graph for construction projects are as follows: (1) Select Neo4j as the build tool, complete the installation and environment configuration, and create a new database; (2) Define equipment, materials, personnel, construction activities, and carbon emissions as nodes, and clarify the attributes of each node; at the same time, determine use, association, and generation as relation edges; (3) Clean and preprocess the extracted information, and use Cypher query language to convert it into nodes and edges; (4) Verify the constructed knowledge graph in terms of structure, data integrity, logical consistency, and duplicate data; (5) Based on the verification results, optimize the performance of the knowledge graph and update the data as the project progresses. At the same time, incorporate relevant external knowledge to improve the graph content.

[0013] Furthermore, the creation of the construction carbon emission simulation model in the S500 emission reduction strategy simulation and optimization is based on the following formula: ,in To simulate carbon emissions in the scenario, This refers to the types and quantities of construction equipment. It is the first The power of the equipment For the first The running time of the device in the simulated scenario It is the first The efficiency adjustment coefficient for this type of equipment ranges from 0.8 to 1.2, and is determined based on factors such as the equipment's maintenance condition and service life. It is the first The operating condition coefficients of this type of equipment under different construction scenarios range from 0.7 to 1.1. The types and quantities of building materials. It is the first The amount of each material used in the simulated scenario is determined based on the resource allocation list and scenario assumptions. It is the first The carbon emission intensity per unit of a material under simulated scenarios was determined using data provided by the material manufacturer and carbon emissions during transportation. It is the first The loss coefficient of this material during construction ranges from 0.05 to 0.15, and is determined based on the construction process and management level. This refers to the types and quantities of other carbon emission sources. It is the first The scale of activities from other carbon emission sources, It is the first The carbon emission intensity per unit scale of other carbon emission sources is determined through actual measurement or by referring to data from similar projects. It is the first The correction factors for other carbon emission sources under different scenarios range from 0.9 to 1.1.

[0014] Furthermore, in the S500, the personalized emission reduction strategy in the emission reduction strategy simulation and optimization is as follows: Regarding equipment: This involves selecting and replacing high-energy-consuming equipment, optimizing scheduling through intelligent systems, and conducting regular maintenance and technology upgrades. Materials sector: Selecting low-carbon materials, optimizing procurement and inventory management, and improving transportation; In terms of construction process: adjust the construction sequence, adopt green technologies, and strengthen information management; From a personnel perspective: organize energy conservation and emission reduction training and establish performance evaluation and incentive mechanisms.

[0015] Compared with existing technologies, this artificial intelligence-based method for compiling carbon emission ledgers for construction projects has the following advantages: I. This invention, by deploying multiple sensors and employing advanced OCR technology, can collect multi-source data on energy consumption, environment, location, and status of construction sites in real time and comprehensively, and perform standardized processing on the data. This not only greatly improves the efficiency and accuracy of data collection but also provides a solid foundation for subsequent carbon emission calculations. Furthermore, by combining natural language processing technology and correlation analysis formulas, this invention can deeply explore the potential connections between data, thereby more accurately calculating the total carbon emissions of construction activities. In addition, by constructing a carbon emission knowledge graph for construction projects, it can also realize the visualization and real-time updating of carbon emission data, providing managers with a more intuitive and convenient means of carbon emission management.

[0016] Second, this invention creates a construction carbon emission simulation model that can simulate carbon emission scenarios based on different assumptions and generate personalized emission reduction strategies. These strategies cover multiple aspects, including equipment selection and replacement, optimized material procurement, construction process adjustments, and personnel training, providing strong support for achieving comprehensive emission reduction. At the same time, this invention can also collect feedback data based on actual application effects to continuously optimize the knowledge graph and AI model, thereby further improving the effectiveness and pertinence of emission reduction strategies. This AI-based emission reduction strategy simulation and optimization method can not only effectively reduce the carbon emissions of construction projects, but also help promote the green and sustainable development of the construction industry.

[0017] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from an examination of the following, or may be learned from the practice of the invention. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0019] Figure 1 A flowchart for a method of compiling carbon emission ledgers for construction projects based on artificial intelligence; Figure 2 This is a framework diagram of a method for compiling carbon emission ledgers for construction projects based on artificial intelligence. Detailed Implementation

[0020] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0021] Example 1: High-rise residential building construction project.

[0022] Multi-source data acquisition and preparation (S100): At high-rise residential construction sites, current and voltage sensors are installed on the power supply lines of various construction equipment to collect real-time energy consumption data. Temperature and humidity sensors, dust sensors, and noise sensors are distributed in different areas of the construction site to monitor environmental conditions. GPS sensors and Beidou satellite positioning system sensors are installed on construction equipment and material transport vehicles to track their location information. Pressure and vibration sensors are deployed in key structural parts of the building, such as the foundation and beams and columns, to monitor the structural condition. In terms of material management, barcode scanning equipment and RFID readers register the entry and exit of each batch of steel bars and cement materials, recording detailed information such as the material type, quantity, and batch. At the same time, paper documents such as drawings, construction logs, and progress reports generated during the construction process are converted into electronic image formats by scanners and imported into OCR software. For parts of the documents with blurred handwriting, special fonts, or complex layouts, staff perform manual proofreading. Then, using lexical analysis and grammatical structure parsing technology, information related to the construction project is extracted, such as the start and end times of construction activities, the amount of materials used, and the operating time of equipment. This data is then standardized and stored in a distributed database.

[0023] Data Mining and Emission Calculation (S200): Data is extracted from the database, and the unstructured text data of the construction logs is cleaned to remove irrelevant information. Lexical analysis is then performed to break the text down into individual words, followed by part-of-speech tagging and stemming to identify the semantic role of each word in the sentence. Key event information, such as concrete pouring time and equipment maintenance records, is extracted and integrated with a pre-built construction domain knowledge base. For structured data such as construction equipment operating time and material usage, association analysis formulas are used to determine the degree of correlation between different data. The formula is: ,in Representing the Class data and the first The correlation between two classes of data ranges from -1 to 1. The closer the absolute value is to 1, the stronger the correlation between the two classes of data; the closer it is to 0, the weaker the correlation. The sign indicates the direction of the correlation: positive for positive correlation and negative for negative correlation. It is the total number of time periods for the data. For the first Class data in the first Standardized values ​​for each time period, For the first Class data in the first Standardized values ​​for each time period, It is the first The weighting coefficients for each time period range from 0 to 1. It is the first Class data and the first The number of delay periods for this type of data in the time series. Given the total number of construction project time cycles, the carbon emissions of each construction activity are calculated using the formula for calculating the total carbon emissions of construction activities. The formula is as follows: ,in The total carbon emissions of a certain construction activity. This represents the total carbon emissions of the construction equipment during the construction activity. This represents the total carbon emissions of building materials during the construction activity. For carbon emissions from other factors in this construction activity, taking pile driving during the foundation construction phase as an example, the total carbon emissions from construction equipment in this construction activity are... The calculation is performed using the following formula: ,in The number of different types of equipment involved in the piling operation. For the first The average power of the equipment For the first The actual running time of this type of equipment For load factor, This represents the percentage correction for the impact of the construction environment on energy consumption. The carbon intensity of the energy used, and the total carbon emissions of building materials in this construction activity. The calculation is based on the formula, which is: , The types and quantities of building materials used. For the first The amount of this material used For the first Carbon emissions per unit mass during the production stage of a certain material. This refers to the carbon emissions per unit mass during the transportation phase. This represents the percentage correction for increased carbon emissions due to losses during construction, and the carbon emissions from other factors. The calculation is based on the carbon emissions generated by the energy consumption of lighting and ventilation at the construction site.

[0024] Carbon Emission Knowledge Graph Construction (S300): Neo4j was selected as the construction tool. After installation and environment configuration, a new database instance was created. Piling equipment, rebar, construction personnel, foundation construction activities, and carbon emissions were defined as nodes, and the attributes of each node were specified, such as the model of the piling equipment, the specifications of the rebar, the job type of the construction personnel, the time of the construction activity, and the value of the carbon emissions. Use, association, and generation were determined as relation edges. For example, piling equipment is "used" in foundation construction activities, rebar is "associated" with foundation construction activities, and foundation construction activities "generate" carbon emissions. After cleaning and preprocessing the extracted information, Cypher query language was used to transform it into nodes and edges to construct a carbon emission knowledge graph for the construction project. The graph was verified in terms of structure, data integrity, logical consistency, and duplicate data. The performance of the knowledge graph was optimized based on the verification results. As the project progressed, the data was continuously updated, and relevant external knowledge, such as new carbon emission calculation standards in the industry and equipment energy-saving technologies, was incorporated to improve the content of the graph.

[0025] Carbon Emission Management Ledger Generation (S400): Based on the calculated carbon emissions and the constructed knowledge graph logic, data is extracted and integrated from the storage center in a standard format to generate an initial carbon emission management ledger for the basic construction phase. The ledger records in detail the carbon emission data of piling equipment, rebar equipment, and materials, as well as the carbon emissions of basic construction activities. During construction, the ledger information is updated in a timely manner as the data on equipment operating time and material usage changes in real time. At the same time, a visual interface is built for project managers to intuitively display the carbon emission status of each construction stage in the form of charts and reports, making it convenient for managers to keep track of the project's carbon emission dynamics at any time.

[0026] Emission reduction strategy simulation and optimization (S500): Collect construction schedule and resource allocation list data, input them into the construction carbon emission simulation model, and the model calculation formula is as follows: ,in To simulate carbon emissions in the scenario, This refers to the types and quantities of construction equipment. It is the first The power of the equipment For the first The running time of the device in the simulated scenario It is the first The efficiency adjustment coefficient for this type of equipment ranges from 0.8 to 1.2, and is determined based on factors such as the equipment's maintenance condition and service life. It is the first The operating condition coefficients of this type of equipment under different construction scenarios range from 0.7 to 1.1. The types and quantities of building materials. It is the first The amount of each material used in the simulated scenario is determined based on the resource allocation list and scenario assumptions. It is the first The carbon emission intensity per unit of a material under simulated scenarios was determined using data provided by the material manufacturer and carbon emissions during transportation. It is the first The loss coefficient of this material during construction ranges from 0.05 to 0.15, and is determined based on the construction process and management level. This refers to the types and quantities of other carbon emission sources. It is the first The scale of activities from other carbon emission sources, It is the first The carbon emission intensity per unit scale of other carbon emission sources is determined through actual measurement or by referring to data from similar projects. It is the first The correction coefficients for other carbon emission sources under different scenarios range from 0.9 to 1.1. Assuming that during the main construction phase, a new, high-efficiency tower crane will be used to replace the existing one, the model simulates carbon emissions based on this hypothetical scenario. Based on the simulation results, personalized emission reduction strategies are developed. In terms of equipment, this includes replacing high-energy-consuming equipment (e.g., new tower cranes) with new ones; optimizing scheduling using intelligent systems to reduce equipment idling time; and improving equipment energy efficiency through regular maintenance and technological upgrades. In the materials field, low-carbon materials are selected, and procurement and inventory management are optimized to reduce material waste; transportation methods are improved to reduce carbon emissions during transportation. In terms of construction processes, the construction sequence is adjusted to avoid unnecessary repetitive work; green technologies are adopted, such as energy-saving lighting systems and water-saving construction techniques; and information management is strengthened to improve construction efficiency. From a personnel perspective, energy conservation and emission reduction training is organized to raise the environmental awareness of construction workers; and a performance evaluation and incentive mechanism is established to encourage employees to actively take energy conservation and emission reduction measures during construction. After applying these strategies, feedback data is collected to update the knowledge graph and carbon emission management ledger, and emission reduction strategies are further optimized based on actual conditions.

[0027] In summary, in high-rise residential construction projects, this invention's AI-based method for compiling carbon emission ledgers for construction projects achieves comprehensive collection and organization of construction data through multi-source data acquisition and preparation. It utilizes data mining and emission calculation to derive accurate carbon emission figures and constructs a carbon emission knowledge graph, providing intuitive data association displays for management. The generated carbon emission management ledger can be updated in real time, facilitating managers' control over carbon emission dynamics. After simulation using a construction carbon emission simulation AI model, personalized emission reduction strategies are formulated and applied, effectively reducing project carbon emissions. This method runs throughout the entire construction process, from data to management to emission reduction optimization, forming a complete system that provides strong support for the low-carbon development of high-rise residential construction.

[0028] Example 2: Commercial complex construction project.

[0029] Multi-source data acquisition and preparation (S100): At the construction site of the commercial complex, various sensors are fully operational. Energy consumption sensors monitor the energy consumption of cranes, concrete pump trucks, large construction machinery, and electrical equipment in temporary office areas, acquiring current and voltage data. Environmental sensors are distributed throughout the construction site, monitoring temperature, humidity, dust concentration, and noise levels in real time to ensure the construction environment meets safety standards. Position sensors are installed on construction vehicles and equipment, using GPS and BeiDou satellite positioning systems to accurately track their locations, facilitating the rational arrangement of the construction site layout. Status sensors are installed in key construction areas such as deep foundation pits and high-formwork structures to monitor pressure and vibration, ensuring construction safety. In the materials management stage, barcode scanning equipment and RFID readers record detailed information on glass curtain wall materials and steel structure materials, including batch, specifications, and quantity information. A large number of paper documents such as drawings, change documents, and construction logs generated during construction are converted into electronic images by scanners and imported into OCR software. The software carefully proofreads complex graphic annotations in drawings, special formats in change documents, and blurred handwriting in construction logs. Then, the text recognized by OCR is preprocessed, and lexical and syntactic analysis techniques are used to extract key information such as construction time, material usage, and equipment operating status. This information is then standardized and stored in a distributed database.

[0030] Data Mining and Emission Calculation (S200): Data is extracted from the database, and unstructured text data from construction logs and change documents is cleaned to remove redundant information. Natural language processing techniques are used for lexical analysis, part-of-speech tagging, and stemming to identify the semantic role of each word in the text. Key event information, such as equipment failure and maintenance and construction process changes, is extracted and integrated with the construction domain knowledge base. For construction equipment operation data and material procurement and transportation data, association analysis formulas are used to determine the degree of correlation between different data. The formula is as follows: The carbon emissions of each construction activity are calculated using the formula for calculating the total carbon emissions of construction activities. The formula is as follows: ,in The total carbon emissions of a certain construction activity. This represents the total carbon emissions of the construction equipment during the construction activity. This represents the total carbon emissions of building materials during the construction activity. For carbon emissions from other factors in this construction activity, taking pile driving during the foundation construction phase as an example, the total carbon emissions from construction equipment in this construction activity are... The calculation is performed using the following formula: ,in The number of different types of equipment involved in the piling operation. For the first The average power of the equipment For the first The actual running time of this type of equipment For load factor, This represents the percentage correction for the impact of the construction environment on energy consumption. The carbon intensity of the energy used, and the total carbon emissions of building materials in this construction activity. The calculation is based on the formula, which is: , The types and quantities of building materials used. For the first The amount of this material used For the first Carbon emissions per unit mass during the production stage of a certain material. This refers to the carbon emissions per unit mass during the transportation phase. This represents the percentage correction for increased carbon emissions due to losses during construction, and the carbon emissions from other factors. The carbon emissions will be calculated based on the energy consumption of lighting and ventilation at the construction site.

[0031] Carbon Emission Knowledge Graph Construction (S300): Neo4j was selected as the construction tool. After installation and environment configuration, a new database instance was created. Nodes were defined, including cranes, steel structure materials, construction teams, steel structure installation activities, and carbon emissions. The attributes of each node were clarified, such as crane model and lifting weight, steel structure material specifications and origin, construction team personnel composition, steel structure installation activity time and process, and carbon emission values. Relationships were defined as "use," "association," and "generation." For example, a crane is "used" in steel structure installation activities, steel structure materials are "associated" with steel structure installation activities, and steel structure installation activities "generate" carbon emissions. After cleaning and preprocessing the extracted information, Cypher query language was used to transform it into nodes and edges, constructing a carbon emission knowledge graph for the construction project. The graph was validated in terms of structure, data integrity, logical consistency, and duplicate data. Based on the validation results, the knowledge graph's performance was optimized. As the project progresses, the data is continuously updated, incorporating new carbon emission research results and material environmental standards within the industry to improve the graph content.

[0032] Carbon Emission Management Ledger Generation (S400): Based on the calculated carbon emissions and the constructed knowledge graph logic, data is extracted and integrated from the storage center according to a standard format to generate an initial carbon emission management ledger for the steel structure installation phase. The ledger records in detail the carbon emission data of cranes, steel structure materials and equipment, as well as the carbon emission of steel structure installation activities. During construction, the ledger information is updated in a timely manner as the equipment operating status and material usage data change in real time. At the same time, a visual interface is built for project managers to display the carbon emission status of each construction stage in an intuitive chart and report format, making it convenient for managers to understand the project's carbon emission dynamics at any time.

[0033] Emission reduction strategy simulation and optimization (S500): Collect data from the construction schedule and resource allocation list, input them into the construction carbon emission simulation model for simulation, and use the following formula: Assuming that during the curtain wall installation phase, the plan is to increase the number of construction workers and optimize the construction process, the model simulates carbon emissions based on this hypothetical scenario. Based on the simulation results, personalized emission reduction strategies are developed. In terms of equipment, this includes upgrading welding equipment to improve energy efficiency; optimizing equipment scheduling using an intelligent control system to reduce equipment idle time; selecting low-carbon emission curtain wall sealant materials; optimizing procurement plans to reduce material inventory backlog; and improving material transportation methods to reduce carbon emissions during transportation. Regarding the construction process, the model adjusts the construction sequence to avoid inefficiencies caused by overlapping operations; adopts new construction techniques to shorten construction time; and strengthens information management to achieve precise allocation of construction resources. From a personnel perspective, the model organizes energy conservation and emission reduction training to improve the environmental awareness of construction workers; and establishes a performance appraisal and incentive mechanism to encourage employees to actively participate in energy conservation and emission reduction work. After applying these strategies, feedback data is collected to update the knowledge graph and carbon emission management ledger, and emission reduction strategies are further optimized based on actual conditions.

[0034] In summary, the method of this invention, applied to commercial complex construction projects, leverages various sensors and technologies to acquire abundant construction data during the data acquisition phase. Data mining and emission calculation accurately analyze carbon emissions, and the construction of a carbon emission knowledge graph clarifies data relationships. A carbon emission management ledger records and presents carbon emission status in real time, facilitating managerial decision-making. In the emission reduction strategy simulation and optimization phase, AI models simulate different scenarios to formulate personalized emission reduction strategies covering equipment, materials, construction processes, and personnel. After implementation, these strategies are continuously optimized based on feedback, effectively reducing the project's carbon emissions. Overall, this method, in commercial complex construction, ensures close coordination among all stages, from basic data processing to the final emission reduction effect, powerfully promoting the green construction process of the project.

[0035] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A method for compiling carbon emission ledgers for construction projects based on artificial intelligence, characterized in that, The specific steps of this compilation method are as follows: S100, Multi-source Data Acquisition and Preparation: Sensors are deployed at the construction site to monitor the data of the construction site in real time, barcode scanning equipment and RFID readers are used to record material data, project documents and construction logs are processed with the help of OCR technology, and the data is standardized and stored in a distributed database simultaneously. S200, Data Mining and Emissions Calculation: Extract multi-source data from the database, perform deep semantic understanding of unstructured text using natural language processing technology, conduct correlation analysis on structured data, combine the results of both, and calculate the total carbon emissions using the formula for calculating the total carbon emissions of construction activities. S300, Carbon Emission Knowledge Graph Construction: Neo4j is selected as the construction tool, defining equipment, materials, personnel, construction activities and carbon emissions as nodes, and use, association and generation as relationship edges. The information is transformed into nodes and edges through the Cypher query language to construct the graph, and the carbon emission knowledge graph is verified and optimized. S400, carbon emission management ledger generation: Based on the calculated carbon emissions and knowledge graph logic, the initial ledger is generated by extracting and integrating data from the storage center in a standard format, and is updated in real time during construction, and a visual interface is built for managers; S500, emission reduction strategy simulation and optimization: collect construction schedule data and input it into the construction carbon emission simulation model. The model simulates carbon emissions based on different scenario assumptions. Based on the results, emission reduction strategies are generated. After applying the strategies, feedback data is collected to update the knowledge graph and carbon emission management ledger.

2. The method for compiling a carbon emission ledger for a construction project based on artificial intelligence according to claim 1, characterized in that, The sensors used in the multi-source data acquisition and preparation process in S100 are: The energy consumption sensors are: current sensors and voltage sensors; The environmental sensors include: temperature and humidity sensors, dust sensors, and noise sensors; The location sensors are: GPS sensors and BeiDou satellite positioning system sensors; The status sensors are: pressure sensors and vibration sensors.

3. The method for compiling a carbon emission ledger for a construction project based on artificial intelligence according to claim 1, characterized in that, The specific steps of using natural language processing technology to perform deep semantic understanding of unstructured text data in S200 data mining and emission calculation are as follows: cleaning the extracted unstructured text data, performing lexical analysis to split the text into individual words, performing part-of-speech tagging and stemming, identifying the semantic role of each word in the sentence, extracting key event information from the text based on the semantic role tagging results, and integrating the extracted event information with a pre-built construction domain knowledge base.

4. The method for compiling a carbon emission ledger for a construction project based on artificial intelligence according to claim 1, characterized in that, In step S200, during data mining and emission calculation, correlation analysis is performed on the extracted structured data using a correlation analysis formula, which is: ,in Representing the Class data and the first The correlation between two classes of data ranges from -1 to 1. The closer the absolute value is to 1, the stronger the correlation between the two classes of data; the closer it is to 0, the weaker the correlation. The sign indicates the direction of the correlation: positive for positive correlation and negative for negative correlation. It is the total number of time periods for the data. For the first Class data in the first Standardized values ​​for each time period, For the first Class data in the first Standardized values ​​for each time period, It is the first The weighting coefficients for each time period are subjectively set based on the importance of the data in different time periods, and their values ​​range from 0 to 1. It is the first Class data and the first The number of delay periods in the time series of this type of data. This represents the total number of construction periods. The time period number represents the data.

5. The method for compiling a carbon emission ledger for a construction project based on artificial intelligence according to claim 1, characterized in that, In step S200, the total carbon emissions of construction activities are calculated using the formula for calculating total carbon emissions of construction activities in data mining and emissions calculation. The formula is as follows: ,in The total carbon emissions of a certain construction activity. This represents the total carbon emissions of the construction equipment during the construction activity. This represents the total carbon emissions of building materials during the construction activity. This refers to the carbon emissions generated by other factors during the construction activity.

6. The method for compiling a carbon emission ledger for a construction project based on artificial intelligence, as described in claim 5, is characterized in that... In S200, the calculation of each parameter in the formula for calculating the total carbon emissions of construction activities in data mining and emissions calculation, and the total carbon emissions of construction equipment in the construction activity. The calculation formula is: ,in The number and types of equipment involved in the construction activity. It is the first The average power of the equipment is obtained from the equipment's technical parameter table. For the first The actual operating time of the equipment during the construction activity is determined by the time information in the equipment usage events. It is the first The load factor of this type of equipment, ranging from 0 to 1, is calculated based on the equipment's energy consumption and power data. It is the first The percentage correction for the impact of the construction environment on energy consumption is determined based on the influence of weather conditions and site topography on equipment energy consumption. For the first The carbon emission intensity of the energy used by the equipment is obtained from relevant standards or databases based on the energy type; the total carbon emissions of building materials in this construction activity. The calculation formula is: ,in This refers to the types and quantities of building materials used in the construction activity. It is the first The amount of material used is determined through material usage data. It is the first The carbon emissions per unit mass during the production stage of this material are obtained from the environmental impact reports provided by the material suppliers. It is the first The carbon emissions per unit mass of the material during the transportation phase are calculated using transportation records and relevant transportation carbon emission standards. It is the first The percentage increase in carbon emissions due to material loss and waste during construction is corrected by statistical analysis of material loss at the construction site; carbon emissions from other factors during construction activities are also considered. The calculation is determined by statistically analyzing the carbon emissions generated from lighting and ventilation energy consumption at the construction site.

7. The method for compiling a carbon emission ledger for a construction project based on artificial intelligence according to claim 1, characterized in that, The specific steps for constructing a carbon emission knowledge graph for construction projects in S300 are as follows: (1) Select Neo4j as the build tool, complete the installation and environment configuration, and create a new database; (2) Define equipment, materials, personnel, construction activities, and carbon emissions as nodes, and clarify the attributes of each node; at the same time, determine use, association, and generation as relation edges; (3) Clean and preprocess the extracted information, and use Cypher query language to convert it into nodes and edges; (4) Verify the constructed knowledge graph in terms of structure, data integrity, logical consistency, and duplicate data; (5) Based on the verification results, optimize the performance of the knowledge graph and update the data as the project progresses. At the same time, incorporate relevant external knowledge to improve the graph content.

8. The method for compiling a carbon emission ledger for a construction project based on artificial intelligence according to claim 1, characterized in that, The S500, in the simulation and optimization of emission reduction strategies, establishes a construction carbon emission simulation model using the following formula: ,in To simulate carbon emissions in the scenario, This refers to the types and quantities of construction equipment. It is the first The power of the equipment For the first The running time of the device in the simulated scenario It is the first The efficiency adjustment coefficient for this type of equipment ranges from 0.8 to 1.2, and is determined based on factors such as the equipment's maintenance condition and service life. It is the first The operating condition coefficients of this type of equipment under different construction scenarios range from 0.7 to 1.

1. The types and quantities of building materials. It is the first The amount of each material used in the simulated scenario is determined based on the resource allocation list and scenario assumptions. It is the first The carbon emission intensity per unit of a material under simulated scenarios was determined using data provided by the material manufacturer and carbon emissions during transportation. It is the first The loss coefficient of this material during construction ranges from 0.05 to 0.15, and is determined based on the construction process and management level. This refers to the types and quantities of other carbon emission sources. It is the first The scale of activities from other carbon emission sources, It is the first The carbon emission intensity per unit scale of other carbon emission sources is determined through actual measurement or by referring to data from similar projects. It is the first The correction factors for other carbon emission sources under different scenarios range from 0.9 to 1.

1.

9. The method for compiling a carbon emission ledger for a construction project based on artificial intelligence according to claim 1, characterized in that, The S500, in the emission reduction strategy simulation and optimization, includes the following personalized emission reduction strategy: Regarding equipment: This involves selecting and replacing high-energy-consuming equipment, optimizing scheduling through intelligent systems, and conducting regular maintenance and technology upgrades. Materials sector: Selecting low-carbon materials, optimizing procurement and inventory management, and improving transportation; In terms of construction process: adjust the construction sequence, adopt green technologies, and strengthen information management; From a personnel perspective: organize energy conservation and emission reduction training and establish performance evaluation and incentive mechanisms.

Images