Building supply chain carbon emission reduction target dynamic adjustment method

Abstract

The invention discloses a building supply chain carbon emission reduction target dynamic adjustment method, which comprises the steps of obtaining utility functions of all parties under different carbon emission reduction targets according to historical data and real-time data provided by all participants of a building supply chain; analyzing influence factors of carbon emission in different stages and cross influence of the influence factors, and obtaining key driving factors of the carbon emission in each stage and weight coefficients of the key driving factors; based on the key driving factor of carbon emission in each stage and the weight coefficient of the key driving factor, in combination with a carbon emission reduction measure library, obtaining a strategy combination of carbon emission reduction measures by judging the action effect and constraint condition of each measure in different implementation scenes; according to a progress plan and a resource allocation condition of the construction engineering project, determining a feasible region of a carbon emission reduction sub-target in each stage by combining a strategy combination of carbon emission reduction measures; and dynamically adjusting the carbon emission reduction target according to the feasible region of the carbon emission reduction sub-target in each stage in combination with the adjustment requirement of the carbon emission reduction target.

Description

Technical Field

[0001] The present invention belongs to the technical field of dynamic adjustment of carbon emission reduction, and in particular relates to a method for dynamically adjusting carbon emission reduction targets in a building supply chain. Background Art

[0002] There are many technical contradictions and difficulties in the dynamic adjustment of carbon emission reduction targets in the construction supply chain. First, there are many participants in the construction supply chain, including building materials suppliers, design units, construction companies, operation and management parties, etc. The interests and carbon emission reduction intentions of each party are different. How to achieve dynamic optimization of the overall carbon emission reduction target while taking into account the interests of all parties is a major challenge. Secondly, the carbon emissions of the entire life cycle of a building cover multiple stages such as building materials production, transportation, construction, operation, and demolition. The factors affecting carbon emissions at different stages are complex, and there are cross-influences between the stages. It is difficult to formulate a carbon emission reduction strategy for a certain stage. It is necessary to comprehensively consider the carbon emission characteristics of each stage and quantitatively analyze the interactions and constraints between various carbon emission reduction measures in order to formulate a scientific and reasonable dynamic adjustment plan. In addition, construction projects have the characteristics of long construction period, large investment, and irreversibility. Once the carbon emission reduction target is determined, the space for subsequent adjustment is very limited, and the dynamic adjustment process may cause contract disputes, cost increases, and other problems. Therefore, it is necessary to carefully evaluate the necessity and feasibility of dynamic adjustment of carbon emission reduction targets, and formulate a sound risk prevention and control mechanism to ensure the smooth operation of the dynamic adjustment mechanism. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a dynamic adjustment method for carbon emission reduction targets in the construction supply chain, which realizes the dynamic optimization of carbon emission reduction targets in the construction supply chain and balance of interests of multiple parties, effectively improves the carbon emission reduction effect, reduces implementation risks, and provides technical support for the realization of carbon neutrality goals in the construction industry.

[0004] To achieve the above-mentioned purpose, the present invention provides a method for dynamically adjusting carbon emission reduction targets in a building supply chain, comprising: quantitatively analyzing the interests and carbon emission reduction intentions of each party based on historical data and real-time data provided by each party in the building supply chain, and obtaining the utility functions of each party under different carbon emission reduction targets;

[0005] Based on the utility function and the carbon emission data of each stage of the building's life cycle, the influencing factors of carbon emissions at different stages and their cross-influence are analyzed to obtain the key driving factors of carbon emissions at each stage and the weight coefficients of the key driving factors;

[0006] Based on the key driving factors of carbon emissions at each stage and their weight coefficients, combined with the carbon emission reduction measures library, the strategic combination of carbon emission reduction measures is obtained by judging the effects and constraints of each measure under different implementation scenarios;

[0007] According to the construction project schedule and resource allocation, combined with the strategic combination of carbon emission reduction measures, determine the feasible domain of carbon emission reduction sub-targets at each stage;

[0008] Based on the feasible domain of the carbon emission reduction sub-targets in each stage and the need to adjust the carbon emission reduction target, the carbon emission reduction target is dynamically adjusted.

[0009] Optionally, obtaining the utility functions of each party under different carbon reduction targets includes:

[0010] Obtain historical and real-time data from all parties involved in the construction supply chain;

[0011] Preprocess the historical data and real-time data provided by all parties involved in the construction supply chain to obtain preprocessed data;

[0012] Analyze the preprocessed data to obtain the correlation between the parties involved;

[0013] According to the association relationship, a utility function model is constructed to analyze the strategic choices of each participant and obtain the utility functions of each party under different carbon emission reduction targets.

[0014] Optionally, the key driving factors of carbon emissions at each stage and the weight coefficients of the key driving factors include:

[0015] Obtain carbon emission data at each stage of the building's life cycle, pre-process the carbon emission data at each stage of the building's life cycle, remove outliers and missing values, and obtain a standardized carbon emission data set;

[0016] Mining frequent item sets and association rules based on the standardized carbon emission data set to obtain the influencing factors of carbon emissions at different stages and their cross-influence relationships;

[0017] Evaluate and sort the mined association rules, screen out strong association rules, and determine the key driving factors of carbon emissions at each stage;

[0018] The principal components of the key driving factors of carbon emissions are extracted according to the key driving factors of carbon emissions in each stage, the variance contribution rate of each principal component is calculated, and the weight coefficient of the key driving factor is determined according to the size of the variance contribution rate.

[0019] Optional strategies to achieve carbon reduction measures include:

[0020] Obtain data related to carbon emission reduction measures and build a knowledge base of carbon emission reduction measures;

[0021] Based on the carbon emission reduction measures knowledge base, construct a measures ontology;

[0022] According to the measure ontology, the semantic association relationship between different measure nodes is analyzed to obtain a measure association graph;

[0023] Match applicable carbon reduction measures and evaluate the reduction effects based on the measure association map and implementation scenario characteristics;

[0024] Determine the feasibility of the carbon emission reduction measures, eliminate conflicting combinations, and obtain a candidate set;

[0025] A combination of measures with the best carbon emission reduction effect and satisfying the constraint conditions is searched according to the candidate set to obtain a strategic combination of carbon emission reduction measures.

[0026] Optionally, the feasible domains for determining carbon reduction targets at each stage include:

[0027] Obtain the schedule and resource allocation information of the construction project, and build a multi-objective optimization model based on the carbon emission reduction target;

[0028] Calculating the multi-objective optimization model to obtain a Pareto optimal solution set for the carbon emission reduction target;

[0029] According to the Pareto optimal solution set of the carbon emission reduction target, the feasible domain of the carbon emission reduction sub-targets in each stage is determined.

[0030] Optional dynamic adjustments to carbon reduction targets include:

[0031] According to the need to adjust carbon emission reduction targets, balance the interests of all parties and build a carbon emission reduction incentive compatibility mechanism;

[0032] Obtain the interests and benefits data of all parties under the original carbon reduction target, input into the game theory model, and obtain the equilibrium point of the interests of all parties;

[0033] Determine the adjusted carbon emission reduction target based on the balance point of the interests of all parties;

[0034] According to the carbon emission reduction incentive compatibility mechanism and the adjusted carbon emission reduction target, the benefit distribution plan and emission reduction responsibilities are implemented to all parties, and the actual emission reduction behavior and benefit feedback of all parties are obtained;

[0035] Based on the actual emission reduction behaviors and benefit feedback of all parties, the carbon emission reduction incentive compatibility mechanism is dynamically optimized to achieve dynamic adjustment of carbon emission reduction targets.

[0036] Optionally, the dynamic adjustment of carbon emission reduction targets also includes quantitative assessment of the probability and impact of relevant risk events caused by the dynamic adjustment of carbon emission reduction targets, and formulation of corresponding risk avoidance and transfer strategies, including:

[0037] Based on the relevant data of dynamic adjustment of carbon emission reduction targets, we analyze historical cases to determine the probability distribution and impact distribution of various types of disputes in view of contract dispute risks;

[0038] For cost risks, determine the probability distribution and impact distribution of each cost by analyzing the historical data and market trends of each cost;

[0039] Monte Carlo simulation is performed on the probability distribution and impact degree distribution of various disputes and the probability distribution and impact degree distribution of various costs. Through multiple iterations of simulation, the quantitative results of the probability and impact degree of contract disputes and cost risks are obtained;

[0040] Based on the quantified results of the probability of occurrence and impact of the contract disputes and cost risks, the contract disputes and cost risks are judged to obtain the judgment results;

[0041] Based on the judgment results, the risk avoidance and transfer strategies are dynamically optimized.

[0042] Technical effect of the invention: The invention discloses a method for dynamically adjusting carbon emission reduction targets in a building supply chain. First, the interests and carbon emission reduction intentions of all parties in the supply chain are quantitatively analyzed to obtain a utility function. Then, based on the carbon emission data of the entire life cycle of the building, the key driving factors of carbon emissions at each stage are analyzed. A strategy combination scheme is formed by constructing a carbon emission reduction measure library and inferring the correlation between measures. According to the project progress and resource conditions, the Pareto optimal solution set of the carbon emission reduction target is solved, and the sub-targets of each stage are determined. If the target needs to be adjusted dynamically, the game theory method is used to perform a multi-party interest balance analysis and construct an incentive compatibility mechanism. At the same time, the risks that may be caused by the adjustment are quantitatively evaluated and avoidance strategies are formulated. The present invention realizes the dynamic optimization of the carbon emission reduction targets of the building supply chain and the balance of interests of multiple parties through methods such as data mining, multi-objective optimization, and game theory, which can effectively improve the carbon emission reduction effect, reduce the implementation risk, and provide technical support for the realization of the carbon neutrality goal in the construction industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0044] Figure 1 The present invention is a flowchart of a method for dynamically adjusting carbon emission reduction targets in a building supply chain according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0046] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0047] like Figure 1 As shown, in this embodiment, a method for dynamically adjusting carbon emission reduction targets of a building supply chain is provided, including: quantitatively analyzing the interests and carbon emission reduction intentions of each party based on historical data and real-time data provided by each party in the building supply chain, and obtaining the utility functions of each party under different carbon emission reduction targets;

[0048] Based on the utility function and the carbon emission data of each stage of the building's life cycle, the influencing factors of carbon emissions at different stages and their cross-influence are analyzed to obtain the key driving factors of carbon emissions at each stage and the weight coefficients of the key driving factors;

[0049] Based on the key driving factors of carbon emissions at each stage and their weight coefficients, combined with the carbon emission reduction measures library, the strategic combination of carbon emission reduction measures is obtained by judging the effects and constraints of each measure under different implementation scenarios;

[0050] According to the construction project schedule and resource allocation, combined with the strategic combination of carbon emission reduction measures, determine the feasible domain of carbon emission reduction sub-targets at each stage;

[0051] Based on the feasible domain of the carbon emission reduction sub-targets in each stage and the need to adjust the carbon emission reduction target, the carbon emission reduction target is dynamically adjusted.

[0052] Furthermore, the utility functions of each party under different carbon reduction targets are obtained, including:

[0053] Obtain historical and real-time data from all parties involved in the construction supply chain;

[0054] Preprocess the historical data and real-time data provided by all parties involved in the construction supply chain to obtain preprocessed data;

[0055] Analyze the preprocessed data to obtain the correlation between the parties involved;

[0056] According to the association relationship, a utility function model is constructed to analyze the strategic choices of each participant and obtain the utility functions of each party under different carbon emission reduction targets.

[0057] Specifically, the multi-objective optimization algorithm NSGA-II is used to solve the carbon emission reduction game problem. The objective function is set to maximize the overall utility and minimize the total carbon emissions. Through iterative optimization, the Pareto optimal solution is obtained, which balances the interests of all parties. The optimal solution shows that the design company reduces emissions by 18%, the construction unit reduces emissions by 22%, the material supplier reduces emissions by 15%, and the property management company reduces emissions by 12%. The optimal carbon emission reduction strategy is converted into an executable action plan, and the responsibilities and obligations of each participant are clarified. For example, the design company needs to adopt low-carbon design standards, the construction unit needs to use green construction technology, the material supplier needs to provide low-carbon materials, and the property management company needs to implement energy-saving and emission reduction management. A monitoring and evaluation system for carbon emission reduction effects is established. Using big data analysis technology, the emission reduction behaviors and effects of all parties are tracked and evaluated in real time through the Hadoop platform, and the optimization model and strategy are dynamically adjusted. For example, by analyzing the real-time monitoring data, it is found that the carbon emissions of the material supplier exceed expectations by 5%. The system automatically adjusts its emission reduction target to 17%, and optimizes related strategies to ensure the realization of the overall carbon emission reduction target.

[0058] Furthermore, the key driving factors of carbon emissions at each stage and the weight coefficients of the key driving factors are obtained, including:

[0059] Obtain carbon emission data at each stage of the building's life cycle, pre-process the carbon emission data at each stage of the building's life cycle, remove outliers and missing values, and obtain a standardized carbon emission data set;

[0060] Mining frequent item sets and association rules based on the standardized carbon emission data set to obtain the influencing factors of carbon emissions at different stages and their cross-influence relationships;

[0061] Evaluate and sort the mined association rules, screen out strong association rules, and determine the key driving factors of carbon emissions at each stage;

[0062] The principal components of the key driving factors of carbon emissions are extracted according to the key driving factors of carbon emissions in each stage, the variance contribution rate of each principal component is calculated, and the weight coefficient of the key driving factor is determined according to the size of the variance contribution rate.

[0063] Specifically, in the analysis of carbon emission data throughout the life cycle of a building, firstly, outliers and missing values ​​are removed by data preprocessing technology, and the box plot method is used to identify and remove abnormal data points beyond the interquartile range to ensure the accuracy and reliability of the data. Then, the Apriori algorithm is applied to mine association rules, and the support threshold is set to 5% and the confidence threshold is set to 70%, so as to find rules such as "energy consumption in the construction stage is highly correlated with material usage". By calculating the lift of these rules, strong association rules with a lift greater than 2 are screened out, which reveal the key influencing factors of carbon emissions between different stages. The principal component analysis method is further used to extract the principal components from multiple key driving factors. Assuming that the variance contribution rates of the first three principal components are 30%, 25% and 20% respectively, the weight coefficients of each factor are determined accordingly. After normalizing these weight coefficients, a weight vector is constructed and multiplied with the carbon emission data of each stage. The weighted influence calculated indicates that the construction stage is the key stage of carbon emissions. For this stage, a decision tree algorithm is used to build a carbon emission prediction model, with key driving factors such as energy consumption, material usage and construction methods as characteristic attributes. The model predicts the impact of different construction methods on carbon emissions, thereby evaluating and selecting the best carbon emission reduction strategy.

[0064] Further, the strategy combination for obtaining carbon reduction measures includes:

[0065] Obtain data related to carbon emission reduction measures and build a knowledge base of carbon emission reduction measures;

[0066] Based on the carbon emission reduction measures knowledge base, construct a measures ontology;

[0067] According to the measure ontology, the semantic association relationship between different measure nodes is analyzed to obtain a measure association graph;

[0068] Match applicable carbon reduction measures and evaluate the reduction effects based on the measure association map and implementation scenario characteristics;

[0069] Determine the feasibility of the carbon emission reduction measures, eliminate conflicting combinations, and obtain a candidate set;

[0070] A combination of measures with the best carbon emission reduction effect and satisfying the constraint conditions is searched according to the candidate set to obtain a strategic combination of carbon emission reduction measures.

[0071] Specifically, a multi-objective optimization algorithm such as a genetic algorithm is used, and the objective function is set to maximize the emission reduction effect and minimize the implementation cost, and the constraints are technical compatibility and budget constraints. Through iterative calculations, the combination of measures with the best carbon emission reduction effect and satisfying the constraints is searched from the candidate set. For example, after 100 iterations, "high-efficiency energy-saving air conditioning + intelligent lighting system" is determined to be the optimal combination, with an estimated emission reduction effect of 25 tons / year and cost control within the budget. Finally, a carbon emission reduction strategy plan is formed that includes specific measures, implementation steps and expected effects. For example, the plan lists in detail the installation location, operating parameters of "high-efficiency energy-saving air conditioning" and the control strategy of "intelligent lighting system" to ensure the operability and effectiveness of the plan. Through information technology processing, each step is ensured to be executed automatically, data is seamlessly transferred, and the optimal carbon emission reduction strategy plan is finally output, providing a scientific basis and implementation guidance for carbon emission reduction throughout the life cycle of the building.

[0072] Furthermore, the feasible scope of carbon emission reduction sub-targets at each stage is determined to include:

[0073] Obtain the schedule and resource allocation information of the construction project, and build a multi-objective optimization model based on the carbon emission reduction target;

[0074] Calculating the multi-objective optimization model to obtain a Pareto optimal solution set for the carbon emission reduction target;

[0075] According to the Pareto optimal solution set of the carbon emission reduction target, the feasible domain of the carbon emission reduction sub-targets in each stage is determined.

[0076] Specifically, when constructing a multi-objective optimization model, environmental protection is first set as the core consideration to ensure that all goals in the model are aimed at reducing carbon emissions. For example, the specific carbon emission limit in construction projects is set to no more than 1,000 tons per month. A genetic algorithm is used for solving the problem, which is suitable for dealing with complex nonlinear problems in the model. Before the algorithm is implemented, the environmental data is preprocessed, such as through data cleaning and normalization, to ensure the accuracy and applicability of the input data. In the genetic algorithm, the population size is set to 200, the crossover rate is 8, and the mutation rate is 05 to ensure the diversity of the algorithm and the global search ability of the solution. The solution set is updated iteratively. After each iteration, the individuals in the current population are sorted according to fitness, and the top 20% with the highest fitness are selected to enter the next generation, and the iteration is continued for 1,000 times. After obtaining the Pareto optimal solution set, each solution in the solution set is analyzed in detail to evaluate its environmental benefits, such as whether the carbon emission reduction reaches the expected 800 tons, and its practical feasibility, such as whether the cost is within the allowable range. Through these detailed analyses, the final carbon reduction strategy is determined, such as selecting the plan with the lowest cost and the best carbon reduction effect, providing scientific data support and implementation recommendations for decision makers.

[0077] Furthermore, dynamic adjustments to carbon reduction targets include:

[0078] According to the need to adjust carbon emission reduction targets, balance the interests of all parties and build a carbon emission reduction incentive compatibility mechanism;

[0079] Obtain the interests and benefits data of all parties under the original carbon reduction target, input into the game theory model, and obtain the equilibrium point of the interests of all parties;

[0080] Determine the adjusted carbon emission reduction target based on the balance point of the interests of all parties;

[0081] According to the carbon emission reduction incentive compatibility mechanism and the adjusted carbon emission reduction target, the benefit distribution plan and emission reduction responsibilities are implemented to all parties, and the actual emission reduction behavior and benefit feedback of all parties are obtained;

[0082] Based on the actual emission reduction behaviors and benefit feedback of all parties, the carbon emission reduction incentive compatibility mechanism is dynamically optimized to achieve dynamic adjustment of carbon emission reduction targets.

[0083] Specifically, according to the results of the equilibrium point, it is judged whether the expected benefits of each party under the adjusted carbon emission reduction target are not lower than the level before the adjustment. If the conditions are met, the benefit distribution plan is embedded in the carbon emission reduction policies and measures to form an incentive compatibility mechanism. If not, a penalty function is introduced into the game model to impose economic penalties on the party that fails to meet the target, and the game analysis is re-performed and iteratively solved until a new carbon emission reduction target is obtained in which the benefits of all parties are not reduced. Finally, the agreed benefit distribution plan and emission reduction responsibility are put on the chain by using smart contract technology, and automatic execution is achieved through blockchain. At the same time, the reinforcement learning algorithm is used to dynamically adjust and optimize the parameters of the incentive compatibility mechanism according to the actual emission reduction and benefits obtained by each party, forming a positive cycle of carbon emission reduction driven by benefits. For example, during the implementation of the project, the actual emission reduction of each party was 900,000 yuan, 700,000 yuan, and 400,000 yuan, which was lower than the expected level. The penalty coefficient was adjusted by the reinforcement learning algorithm, and the economic penalty for the party that failed to complete the emission reduction target was increased, which prompted all parties to increase their enthusiasm for emission reduction and finally achieve the dynamic optimization of the project's carbon emission reduction target.

[0084] Furthermore, the dynamic adjustment of carbon emission reduction targets also includes the quantitative assessment of the probability and impact of relevant risk events caused by the dynamic adjustment of carbon emission reduction targets, and the formulation of corresponding risk avoidance and transfer strategies, including:

[0085] Based on the relevant data of dynamic adjustment of carbon emission reduction targets, we analyze historical cases to determine the probability distribution and impact distribution of various types of disputes in view of contract dispute risks;

[0086] For cost risks, determine the probability distribution and impact distribution of each cost by analyzing the historical data and market trends of each cost;

[0087] Monte Carlo simulation is performed on the probability distribution and impact degree distribution of various disputes and the probability distribution and impact degree distribution of various costs. Through multiple iterations of simulation, the quantitative results of the probability and impact degree of contract disputes and cost risks are obtained;

[0088] Based on the quantified results of the probability of occurrence and impact of the contract disputes and cost risks, the contract disputes and cost risks are judged to obtain the judgment results;

[0089] Based on the judgment results, the risk avoidance and transfer strategies are dynamically optimized.

[0090] Specifically, according to the quantitative results, if the contract disputes and cost risks exceed the preset thresholds of 30% and 5%, corresponding risk avoidance strategies need to be adopted. In view of the risk of contract disputes, the contract terms are optimized, the performance responsibilities and breach of contract compensation are refined, and a diversified dispute resolution mechanism is set up, such as negotiation, mediation, arbitration, etc.; in view of cost risks, the material costs are controlled by means of price-limited ordering and centralized procurement, the labor costs are controlled by means of optimizing construction technology and improving labor efficiency, and the machinery costs are controlled by means of reasonable arrangement of machinery use and strengthening equipment maintenance. During the implementation of the project, the carbon emission reduction target adjustment data, contract performance data, various cost data, etc. are continuously collected, the input parameters of the Monte Carlo simulation are dynamically updated, and the risk avoidance strategy is optimized using the reinforcement learning algorithm based on the updated quantitative evaluation results, such as increasing the degree of refinement of the contract terms and improving the control of material costs, so as to continuously improve the effectiveness of risk management and ensure that the overall benefits of the project are not affected when the carbon emission reduction target is dynamically adjusted.

[0091] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for dynamically adjusting carbon emission reduction targets in a building supply chain, characterized in that: include: Based on the historical and real-time data provided by all parties in the construction supply chain, we conduct a quantitative analysis of the interests and carbon reduction intentions of all parties, and obtain the utility functions of all parties under different carbon reduction targets; Based on the utility function and the carbon emission data of each stage of the building's life cycle, the influencing factors of carbon emissions at different stages and their cross-influence are analyzed to obtain the key driving factors of carbon emissions at each stage and the weight coefficients of the key driving factors; Based on the key driving factors of carbon emissions at each stage and their weight coefficients, combined with the carbon emission reduction measures library, the strategic combination of carbon emission reduction measures is obtained by judging the effects and constraints of each measure under different implementation scenarios; According to the construction project schedule and resource allocation, combined with the strategic combination of carbon emission reduction measures, determine the feasible domain of carbon emission reduction sub-targets at each stage; Based on the feasible domain of the carbon emission reduction sub-targets in each stage and the need to adjust the carbon emission reduction target, the carbon emission reduction target is dynamically adjusted.

2. The method for dynamically adjusting carbon emission reduction targets in a building supply chain according to claim 1, characterized in that: The utility functions of all parties under different carbon reduction targets include: Obtain historical and real-time data from all parties involved in the construction supply chain; Preprocess the historical data and real-time data provided by all parties involved in the construction supply chain to obtain preprocessed data; Analyze the preprocessed data to obtain the correlation between the parties involved; According to the association relationship, a utility function model is constructed to analyze the strategic choices of each participant and obtain the utility functions of each party under different carbon emission reduction targets.

3. The method for dynamically adjusting carbon emission reduction targets in a building supply chain according to claim 1, characterized in that: The key driving factors and weight coefficients of carbon emissions at each stage include: Obtain carbon emission data at each stage of the building's life cycle, pre-process the carbon emission data at each stage of the building's life cycle, remove outliers and missing values, and obtain a standardized carbon emission data set; Mining frequent item sets and association rules based on the standardized carbon emission data set to obtain the influencing factors of carbon emissions at different stages and their cross-influence relationships; Evaluate and sort the mined association rules, screen out strong association rules, and determine the key driving factors of carbon emissions at each stage; The principal components of the key driving factors of carbon emissions are extracted according to the key driving factors of carbon emissions in each stage, the variance contribution rate of each principal component is calculated, and the weight coefficient of the key driving factor is determined according to the size of the variance contribution rate.

4. The method for dynamically adjusting carbon emission reduction targets in a building supply chain according to claim 1, characterized in that: The combination of strategies to achieve carbon reduction measures includes: Obtain data related to carbon emission reduction measures and build a knowledge base of carbon emission reduction measures; Based on the carbon emission reduction measures knowledge base, construct a measures ontology; According to the measure ontology, the semantic association relationship between different measure nodes is analyzed to obtain a measure association graph; Match applicable carbon reduction measures and evaluate the reduction effects based on the measure association map and implementation scenario characteristics; Determine the feasibility of the carbon emission reduction measures, eliminate conflicting combinations, and obtain a candidate set; A combination of measures with the best carbon emission reduction effect and satisfying the constraint conditions is searched according to the candidate set to obtain a strategic combination of carbon emission reduction measures.

5. The method for dynamically adjusting carbon emission reduction targets in a building supply chain according to claim 1, characterized in that: The feasible scope for determining the carbon reduction targets at each stage includes: Obtain the schedule and resource allocation information of the construction project, and build a multi-objective optimization model based on the carbon emission reduction target; Calculating the multi-objective optimization model to obtain a Pareto optimal solution set for the carbon emission reduction target; According to the Pareto optimal solution set of the carbon emission reduction target, the feasible domain of the carbon emission reduction sub-targets in each stage is determined.

6. The method for dynamically adjusting carbon emission reduction targets in a building supply chain according to claim 1, characterized in that: Dynamic adjustments to carbon reduction targets include: According to the need to adjust carbon emission reduction targets, balance the interests of all parties and build a carbon emission reduction incentive compatibility mechanism; Obtain the interests and benefits data of all parties under the original carbon reduction target, input into the game theory model, and obtain the equilibrium point of the interests of all parties; Determine the adjusted carbon emission reduction target based on the balance point of the interests of all parties; According to the carbon emission reduction incentive compatibility mechanism and the adjusted carbon emission reduction target, the benefit distribution plan and emission reduction responsibilities are implemented to all parties, and the actual emission reduction behavior and benefit feedback of all parties are obtained; Based on the actual emission reduction behaviors and benefit feedback of all parties, the carbon emission reduction incentive compatibility mechanism is dynamically optimized to achieve dynamic adjustment of carbon emission reduction targets.

7. The method for dynamically adjusting carbon emission reduction targets in a building supply chain according to claim 1, characterized in that: Dynamic adjustment of carbon emission reduction targets also includes quantitative assessment of the probability and impact of relevant risk events caused by dynamic adjustment of carbon emission reduction targets, and formulation of corresponding risk avoidance and transfer strategies, including: Based on the relevant data of dynamic adjustment of carbon emission reduction targets, we analyze historical cases to determine the probability distribution and impact distribution of various types of disputes in view of contract dispute risks; For cost risks, determine the probability distribution and impact distribution of each cost by analyzing the historical data and market trends of each cost; Monte Carlo simulation is performed on the probability distribution and impact degree distribution of various disputes and the probability distribution and impact degree distribution of various costs. Through multiple iterations of simulation, the quantitative results of the probability and impact degree of contract disputes and cost risks are obtained; Based on the quantified results of the probability of occurrence and impact of the contract disputes and cost risks, the contract disputes and cost risks are judged to obtain the judgment results; Based on the judgment results, the risk avoidance and transfer strategies are dynamically optimized.

Images