Project cost consultation method based on artificial intelligence

Abstract

The invention discloses a project cost consultation method based on artificial intelligence, and the method mainly comprises the following steps: S1, providing an intelligent system, and obtaining a project quantity list, a construction plan and a material price; s2, receiving and analyzing project requirements through a natural language processing algorithm, and generating a cost consultation task; s3, analyzing the project data by using a machine learning algorithm, and generating a budget scheme and a pre-settlement report; s4, executing risk identification, and providing risk control suggestions; s5, dynamically adjusting a budget scheme based on project progress conditions, and providing cost optimization suggestions; and S6, generating a report including cost prediction, risk control and optimization schemes. The method optimizes the analysis and processing of the cost data through an intelligent algorithm, improves the budgeting accuracy and risk recognition capability, reduces the manual intervention, and improves the working efficiency and decision scientificity.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering cost management, and in particular to an engineering cost consulting method based on artificial intelligence. Background Art

[0002] In the field of modern engineering project management and cost consulting, accurate prediction and control of engineering costs is one of the key links to project success. Traditional engineering cost consulting methods rely on manual operations and expert experience to collect, analyze, generate budgets, and identify risks in the process of project progress. Although these traditional methods have been practiced for many years, they still have some shortcomings when facing challenges such as increasing data complexity, expanding project scale, and increasing demand for real-time data feedback:

[0003] The first is that the existing labor cost consulting methods are inefficient and have limited data processing capabilities. In large-scale engineering projects, it is usually necessary to process massive amounts of engineering data, such as bills of quantities, material prices, construction plans, etc. These data often come from different sources and formats, and rely on manual collection and sorting, which can easily lead to data loss or errors. In addition, manual processing methods are difficult to respond to project changes in real time, especially in terms of dynamic project adjustments and real-time budget optimization. There is a significant lag. As the scale of projects increases, the efficiency of manual data processing further decreases, making it difficult to meet the needs of modern projects for efficient data processing.

[0004] Second, traditional methods lack intelligent analysis tools, and budget generation and adjustment are lagging. Existing budget generation methods mainly rely on historical data and expert experience, and budget plans are difficult to dynamically adjust according to the real-time progress of the project. In actual projects, construction progress, material prices, and changes in construction period will have an impact on the budget, but existing technologies usually make it difficult to update budget plans in a timely manner based on these changes, resulting in inaccurate cost control and resource allocation. This lagging budget adjustment method may lead to project overruns or construction delays, increasing the difficulty of engineering cost management.

[0005] Third, the risk identification and control methods of existing technologies are relatively simple, usually relying on the experience and judgment of project managers, and lacking intelligent risk assessment tools. Although project managers can predict and control some common risks based on historical experience, for multi-dimensional risks in complex projects, especially in terms of construction delays, cost overruns, material shortages, etc., existing technologies make it difficult to conduct comprehensive and accurate risk prediction and control, which can easily lead to unpredictable risks in the later stages of the project.

[0006] Fourth, the lack of personalization in traditional cost consulting methods also limits their application effect. Different projects vary greatly in scale, region, construction technology, etc. The existing budget generation and risk control methods are difficult to make personalized adjustments to the specific conditions of each project, resulting in many projects performing poorly in budget control and risk management. At the same time, manual processing methods cannot achieve efficient processing and feedback of real-time data, and it is difficult to make dynamic adjustments and optimizations based on the real-time situation of the project.

[0007] Therefore, how to provide an engineering cost consulting method based on artificial intelligence is an urgent problem that technicians in this field need to solve. Summary of the invention

[0008] One purpose of the present invention is to propose an artificial intelligence-based engineering cost consulting method, which makes full use of natural language processing and machine learning algorithms, and describes in detail how to intelligently analyze project requirements, generate budget plans, dynamically adjust budgets, and perform risk identification and control algorithms. The method has the advantages of high automation, accurate budget generation, real-time adjustment, and precise risk control, which significantly improves the efficiency of engineering cost management and the scientific nature of decision-making, while reducing the need for manual intervention.

[0009] An artificial intelligence-based engineering cost consulting method according to an embodiment of the present invention comprises the following steps:

[0010] S1. Provide an intelligent system based on engineering cost data analysis, which collects preliminary data by obtaining the project's bill of quantities, construction plan and material prices;

[0011] S2. Receive project requirements input by users through natural language processing algorithms, and parse and generate corresponding cost consulting tasks;

[0012] S3. Use machine learning algorithms to analyze the collected project data and generate project budget plans and preliminary settlement reports;

[0013] S4. Based on the analysis results, perform intelligent risk identification and provide corresponding risk control suggestions;

[0014] S5. Dynamically adjust the budget plan according to the project progress and provide real-time cost optimization suggestions;

[0015] S6. Generate an engineering cost consulting report including cost forecasts, risk control suggestions and optimization solutions, and output it to the user.

[0016] Optionally, the S2 specifically includes:

[0017] S21. Perform word segmentation on the text input by the user through natural language processing algorithms to identify and extract keywords and semantic information in project requirements;

[0018] S22. Use the pre-trained semantic understanding model to analyze the contextual association of project requirements and generate structured cost consulting tasks;

[0019] S23. Combined with project characteristics, a dynamic task mapping algorithm is used to map user requirements into task modules that can be processed by the system. m =f(D,K,C), where T m represents the generated task module, D represents the structured data of project requirements, K represents the keyword set, and C represents the contextual information;

[0020] S24. Through the task parsing module, the generated task module is matched with the standard cost task template in the database to generate a corresponding task list.

[0021] Optionally, the S23 specifically includes:

[0022] S231, extracting context information from the user input requirement text through the semantic parsing model and converting it into structured data D, wherein the structured data is represented by the weight matrix W c Multi-layer weighted generation of information combined with context:

[0023]

[0024] in, represents the i-th part of the user input text, Represents contextual information related to the project. is the context weight matrix, which reflects the weight differences of different parts of the project cost;

[0025] S232. Generate a keyword set K through keyword extraction and context dependency analysis, and adopt a nonlinear weight adjustment strategy in combination with project features:

[0026]

[0027] in, is the dynamic weight matrix of keywords, which is used to adjust the importance of keywords related to project cost in different situations. project represents the project feature data, σ is a nonlinear activation function used to optimize the selection of keywords;

[0028] S233, generating a task module T based on the structured data D, the keyword set K and the context information C adjusted based on the context weight m, and generate the final task through the weighted matching function g:

[0029]

[0030] in, It is the weighted matrix of the task modules, which is used to accurately assign priorities to the generated task modules. f3 combines the key parameters in the engineering cost consulting process;

[0031] S234. A multi-dimensional weight matching mechanism based on task characteristics is adopted to connect the task module with the actual needs in engineering cost consulting, thereby realizing intelligent cost task allocation.

[0032] Optionally, the S3 specifically includes:

[0033] S31. Through the data preprocessing module, the collected engineering cost-related data is cleaned, deduplicated and formatted to generate a preprocessed data set D p , where the data cleaning process is based on the multi-dimensional data dependency matrix W d Make adjustments:

[0034]

[0035] in, is the weighted value of the data dependency matrix, is the original data;

[0036] S32, based on machine learning algorithm, the preprocessed data set D p Perform feature extraction to generate project feature set F p , the feature extraction process is through the weighted feature mapping matrix W f Adjust the priority of different features:

[0037]

[0038] in, is the feature mapping matrix, which adjusts the weights of different features in the budget plan generation, P project is the project characteristic parameter;

[0039] S33. Use historical data to build a budget forecast model M b , the model is based on the feature set F p Input, adjust the weight matrix W of the budget model through the dynamic optimization function f5 b :

[0040]

[0041] Among them, H d is a historical engineering cost dataset. is the weight matrix element in the budget model;

[0042] S34, based on project progress data P real And dynamic feedback mechanism, adjust the budget plan, the optimized budget plan B ′ Through the nonlinear error adjustment function Δf(B,P real ) for calibration:

[0043] B ′ =B+β·Δf(B,Preal);

[0044] Among them, β is the nonlinear adjustment coefficient, Δf(B,P real ) is the error adjustment function between the budget and the actual progress, which is used to dynamically optimize the budget plan B;

[0045] S35. According to the optimized budget plan B ′ , generate a preliminary settlement report containing cost forecasts, expense allocations and dynamic adjustment suggestions, and output it to the user.

[0046] Optionally, the S34 specifically includes:

[0047] S341, real-time collection of project progress data real , including engineering quantity, material usage, labor cost and construction progress, generating real-time data set P real , real-time data is fed back through the multidimensional feedback matrix W p The weight matrix is ​​dynamically adjusted according to the importance of various data sources:

[0048]

[0049] in, To collect the original data of project progress in real time, Indicates the dynamic feedback weights associated with various types of progress data;

[0050] S342, based on the real-time data set P real The error between the budget solution B and the initial error matrix ΔB is generated, and the error matrix is ​​multi-corrected by the nonlinear adjustment formula:

[0051]

[0052] in, is the error weight matrix, which is used to dynamically balance the impact of various error data on the budget deviation. and B (j) Represent the corresponding dimensions of real-time data and budget data respectively;

[0053] S343. According to the preliminary error matrix ΔB, the budget plan is iteratively corrected through the timing adjustment mechanism:

[0054] B ′ =B+β·ΔB+γ·h(T,ΔB);

[0055] Among them, β is the dynamic adjustment coefficient, which is used to control the error adjustment amplitude, γ is the timing correction coefficient, and h(T, ΔB) represents the error time correction function based on time T and error history, which is used to optimize the dynamic budget correction in long-term projects;

[0056] S344, through the multi-dimensional dynamic feedback mechanism, real-time adjustment of the optimized budget plan B ′ , and compare future budget forecasts with real-time progress data to generate the final optimized budget plan.

[0057] Optionally, the S4 specifically includes:

[0058] S41. Based on the historical data and current project data of the engineering project, the risk identification module is used to identify the key links of the project and generate a preliminary list of risk factors, including construction delays, cost overruns, material shortages and contract risks;

[0059] S42. Analyze the project requirements and risk descriptions input by the user through the natural language processing algorithm, classify and annotate the input risk descriptions in combination with the historical risk case library, and generate risk classification information;

[0060] S43. Based on the risk identification results, multi-dimensional risk analysis is conducted in combination with project characteristics. The analysis dimensions include project scale, construction stage, project type and regional characteristics, and the impact weights and priority rankings of various risks are generated;

[0061] S44. Based on the generated risk impact weights, evaluate various risks, estimate the possibility of risk occurrence and the potential impact on the overall cost of the project, and generate corresponding risk control recommendations;

[0062] S45. Compare the generated risk control suggestions with the project requirements input by the user, and automatically match the corresponding risk warning information to generate an intelligent risk identification report.

[0063] Optionally, the S5 specifically includes:

[0064] S51. Obtain the progress of the project in real time through the monitoring module, including construction progress, material usage and personnel allocation, and generate a real-time project data set;

[0065] S52. Compare the real-time project data set with the initial budget plan, identify the deviation between the actual progress and the budget, and mark the budget items that need to be adjusted;

[0066] S53. Re-evaluate the marked budget items through the dynamic budget adjustment module, analyze them in combination with real-time project data and historical data, and determine whether the cost control plan needs to be adjusted;

[0067] S54. Automatically generate an adjusted budget plan based on the evaluation results, and optimize the key project costs involved in the adjustment;

[0068] S55. Combine the real-time progress feedback of the project to match the adjusted budget plan with future project needs, and dynamically update the budget plan based on real-time data;

[0069] S56. Generate a cost optimization report based on the final adjusted budget plan and optimization suggestions. The report content includes the specific details of the adjustment, impact analysis and optimized project cost forecast.

[0070] The beneficial effects of the present invention are:

[0071] (1) The present invention automatically parses the project requirements input by the user through a natural language processing algorithm, and combines a machine learning algorithm to efficiently analyze data such as the bill of quantities, construction plan, and material prices, and automatically generates a budget plan and preliminary settlement report, which significantly improves data processing efficiency and the accuracy of budget generation and reduces the need for manual intervention.

[0072] (2) The present invention can dynamically adjust the budget plan and provide cost optimization suggestions according to the real-time progress of the project. By collecting real-time data of the project, such as engineering quantity, material usage and labor costs, the present invention uses a multi-dimensional feedback mechanism to make real-time corrections to the budget plan to ensure that the budget plan is consistent with the project progress, thereby improving the real-time and flexibility of project cost management.

[0073] (3) Based on historical project data and real-time data, the present invention uses an intelligent risk identification module to automatically identify potential risks in the project, such as construction delays, cost overruns, etc., and generates corresponding risk control recommendations. By analyzing and prioritizing risk impact weights, the present invention can accurately assess the likelihood of risk occurrence and its impact on the overall cost of the project, helping project managers to control risks more effectively.

[0074] (4) The present invention uses a dynamic task mapping algorithm to map project requirements into processable task modules based on project characteristics and user needs, generates a personalized cost consulting task list, and generates structured data in combination with project characteristics. This customized task generation method improves the accuracy and pertinence of cost consulting tasks and adapts to the diverse needs of different projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0076] Figure 1 A flowchart of an artificial intelligence-based engineering cost consulting method proposed by the present invention;

[0077] Figure 2 The present invention provides a flowchart of dynamic budget adjustment in an artificial intelligence-based engineering cost consulting method. DETAILED DESCRIPTION

[0078] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0079] refer to Figure 1-2 , an engineering cost consulting method based on artificial intelligence, comprising the following steps:

[0080] S1. Provide an intelligent system based on engineering cost data analysis, which collects preliminary data by obtaining the project's bill of quantities, construction plan and material prices;

[0081] S2. Receive project requirements input by users through natural language processing algorithms, and parse and generate corresponding cost consulting tasks;

[0082] S3. Use machine learning algorithms to analyze the collected project data and generate project budget plans and preliminary settlement reports;

[0083] S4. Based on the analysis results, perform intelligent risk identification and provide corresponding risk control suggestions;

[0084] S5. Dynamically adjust the budget plan according to the project progress and provide real-time cost optimization suggestions;

[0085] S6. Generate an engineering cost consulting report including cost forecasts, risk control suggestions and optimization solutions, and output it to the user.

[0086] In this implementation, S2 specifically includes:

[0087] S21. Perform word segmentation on the text input by the user through natural language processing algorithms to identify and extract keywords and semantic information in project requirements;

[0088] S22. Use the pre-trained semantic understanding model to analyze the contextual association of project requirements and generate structured cost consulting tasks;

[0089] S23. Combined with project characteristics, a dynamic task mapping algorithm is used to map user requirements into task modules that can be processed by the system. m =f(D,K,C), where T m represents the generated task module, D represents the structured data of project requirements, K represents the keyword set, and C represents the contextual information;

[0090] S24. Through the task parsing module, the generated task module is matched with the standard cost task template in the database to generate a corresponding task list.

[0091] In this implementation manner, the S23 specifically includes:

[0092] S231, extracting context information from the user input requirement text through the semantic parsing model and converting it into structured data D, wherein the structured data is represented by the weight matrix W c Multi-layer weighted generation of information combined with context:

[0093]

[0094] in, represents the i-th part of the user input text, Represents contextual information related to the project. is the context weight matrix, which reflects the weight differences of different parts of the project cost;

[0095] S232. Generate a keyword set K through keyword extraction and context dependency analysis, and adopt a nonlinear weight adjustment strategy in combination with project features:

[0096]

[0097] in, is the dynamic weight matrix of keywords, which is used to adjust the importance of keywords related to project cost in different situations. project represents the project feature data, σ is a nonlinear activation function used to optimize the selection of keywords;

[0098] S233, generating a task module T based on the structured data D, the keyword set K and the context information C adjusted based on the context weightm , and generate the final task through the weighted matching function g:

[0099]

[0100] in, It is the weighted matrix of the task modules, which is used to accurately assign priorities to the generated task modules. f3 combines the key parameters in the engineering cost consulting process;

[0101] S234. A multi-dimensional weight matching mechanism based on task characteristics is adopted to connect the task module with the actual needs in engineering cost consulting, thereby realizing intelligent cost task allocation.

[0102] In this implementation, S3 specifically includes:

[0103] S31. Through the data preprocessing module, the collected engineering cost-related data is cleaned, deduplicated and formatted to generate a preprocessed data set D p , where the data cleaning process is based on the multi-dimensional data dependency matrix W d Make adjustments:

[0104]

[0105] in, is the weighted value of the data dependency matrix, is the original data;

[0106] S32, based on machine learning algorithm, the preprocessed data set D p Perform feature extraction to generate project feature set F p , the feature extraction process is through the weighted feature mapping matrix W f Adjust the priority of different features:

[0107]

[0108] in, is the feature mapping matrix, which adjusts the weights of different features in the budget plan generation, P project is the project characteristic parameter;

[0109] S33. Use historical data to build a budget forecast model M b , the model is based on the feature set F p Input, adjust the weight matrix W of the budget model through the dynamic optimization function f5 b :

[0110]

[0111] Among them, H d is a historical engineering cost dataset. is the weight matrix element in the budget model;

[0112] S34, based on project progress data P real And dynamic feedback mechanism, adjust the budget plan, the optimized budget plan B ′ Through the nonlinear error adjustment function Δf(B,P real ) for calibration:

[0113] B ′ =B+β·Δf(B,Preal);

[0114] Among them, β is the nonlinear adjustment coefficient, Δf(B,P real ) is the error adjustment function between the budget and the actual progress, which is used to dynamically optimize the budget plan B;

[0115] S35. According to the optimized budget plan B ′ , generate a preliminary settlement report containing cost forecasts, expense allocations and dynamic adjustment suggestions, and output it to the user.

[0116] In this implementation manner, the S34 specifically includes:

[0117] S341, real-time collection of project progress data real , including engineering quantity, material usage, labor cost and construction progress, generating real-time data set P real , real-time data is fed back through the multidimensional feedback matrix W p The weight matrix is ​​dynamically adjusted according to the importance of various data sources:

[0118]

[0119] in, To collect the original data of project progress in real time, Indicates the dynamic feedback weights associated with various types of progress data;

[0120] S342, based on the real-time data set P real The error between the budget solution B and the initial error matrix ΔB is generated, and the error matrix is ​​multi-corrected by the nonlinear adjustment formula:

[0121]

[0122] in, is the error weight matrix, which is used to dynamically balance the impact of various error data on the budget deviation. and B (j) Represent the corresponding dimensions of real-time data and budget data respectively;

[0123] S343. According to the preliminary error matrix ΔB, the budget plan is iteratively corrected through the timing adjustment mechanism:

[0124] B ′ =B+β·ΔB+γ·h(T,ΔB);

[0125] Among them, β is the dynamic adjustment coefficient, which is used to control the error adjustment amplitude, γ is the timing correction coefficient, and h(T, ΔB) represents the error time correction function based on time T and error history, which is used to optimize the dynamic budget correction in long-term projects;

[0126] S344, through the multi-dimensional dynamic feedback mechanism, real-time adjustment of the optimized budget plan B ′ , and compare future budget forecasts with real-time progress data to generate the final optimized budget plan.

[0127] In this implementation manner, the S4 specifically includes:

[0128] S41. Based on the historical data and current project data of the engineering project, the risk identification module is used to identify the key links of the project and generate a preliminary list of risk factors, including construction delays, cost overruns, material shortages and contract risks;

[0129] S42. Analyze the project requirements and risk descriptions input by the user through the natural language processing algorithm, classify and annotate the input risk descriptions in combination with the historical risk case library, and generate risk classification information;

[0130] S43. Based on the risk identification results, multi-dimensional risk analysis is conducted in combination with project characteristics. The analysis dimensions include project scale, construction stage, project type and regional characteristics, and the impact weights and priority rankings of various risks are generated;

[0131] S44. Based on the generated risk impact weights, evaluate various risks, estimate the possibility of risk occurrence and the potential impact on the overall cost of the project, and generate corresponding risk control recommendations;

[0132] S45. Compare the generated risk control suggestions with the project requirements input by the user, and automatically match the corresponding risk warning information to generate an intelligent risk identification report.

[0133] In this implementation manner, S5 specifically includes:

[0134] S51. Obtain the progress of the project in real time through the monitoring module, including construction progress, material usage and personnel allocation, and generate a real-time project data set;

[0135] S52. Compare the real-time project data set with the initial budget plan, identify the deviation between the actual progress and the budget, and mark the budget items that need to be adjusted;

[0136] S53. Re-evaluate the marked budget items through the dynamic budget adjustment module, analyze them in combination with real-time project data and historical data, and determine whether the cost control plan needs to be adjusted;

[0137] S54. Automatically generate an adjusted budget plan based on the evaluation results, and optimize the key project costs involved in the adjustment;

[0138] S55. Combine the real-time progress feedback of the project to match the adjusted budget plan with future project needs, and dynamically update the budget plan based on real-time data;

[0139] S56. Generate a cost optimization report based on the final adjusted budget plan and optimization suggestions. The report content includes the specific details of the adjustment, impact analysis and optimized project cost forecast.

[0140] Embodiment 1:

[0141] The artificial intelligence-based engineering cost consulting method of the present invention was applied in a large-scale engineering construction project in China. The project is a cross-city highway construction project with an estimated total cost of RMB 2.5 billion. The project involves a long construction period, complex materials, and variable construction conditions. Therefore, traditional cost management methods face huge challenges. The project management team introduced the intelligent system of the present invention to solve the problems of untimely budget adjustment, inaccurate risk identification, and lack of real-time cost control in the prior art.

[0142] In this project, the intelligent system first received the demand input from the project manager through the natural language processing algorithm. These demands include multi-dimensional information such as the project's construction schedule, material supply plan, and personnel arrangement. Through step S2, the system interprets these demands into standardized cost consulting tasks, and generates a preliminary task list in combination with the specific characteristics of the project. Then, the machine learning algorithm is used to comprehensively analyze the data of the project and generate a preliminary budget plan. The budget plan covers material procurement costs, labor costs, equipment rental costs, and other expenses. In this process, the system also refers to historical data of similar highway projects and performs intelligent calibration of each budget. Through the use of these algorithms, the budget generated by the system is closer to the actual situation of the project. After entering the construction stage, the intelligent system of the present invention begins to implement the risk identification and control function of step S4. The system automatically generates a risk control recommendation list based on common risks in historical projects, such as construction delays and material supply shortages. In the third month of the project, the construction progress was delayed due to sudden weather changes. The system automatically identified this potential risk and promptly proposed corresponding countermeasures, such as increasing construction personnel and equipment, to ensure that the project is completed within the specified time. During the project, the system dynamically adjusted the budget plan through a dynamic adjustment mechanism combined with real-time collected project progress data. In the sixth month of construction, the project's material supplier raised the price of some materials due to market price fluctuations, causing the budget to exceed expectations. The intelligent system automatically adjusted the material costs in the budget through real-time monitoring of material costs, and proposed suggestions for optimizing procurement channels. Ultimately, it successfully controlled the overspending within an acceptable range and avoided further budget overruns.

[0143] Through the intelligent system of the present invention, the project management team not only greatly improves the efficiency of data processing and analysis, but also effectively controls the cost of the project:

[0144] Table 1 Budget adjustment and risk control data table for project construction phase

[0145]

[0146] As shown in Table 1 above, the intelligent system monitors and adjusts the budget in real time at different stages of the project. In particular, when responding to unexpected risk events, the system can provide effective response measures in a timely manner. For example, in the third month, due to the risk of delays in the construction period, the system proposed to increase the number of construction personnel, successfully controlling the possible delays in the construction period to the minimum. In the sixth month, when material price fluctuations led to budget overruns, the system optimized procurement channels to control material costs within an acceptable range, avoiding the negative impact of overruns on the overall project.

[0147] Through the implementation of the system of the present invention, automated data processing and intelligent budget generation greatly reduce the need for manual intervention, improve the accuracy of budget generation, and dynamically adjust the budget plan according to the real-time progress of the project to ensure that the budget always matches the actual situation of the project. Finally, through intelligent risk identification and control, the present invention helps the project management team effectively avoid potential risks and reduce project costs.

[0148] In summary, the present invention successfully solves the problems of low efficiency, insufficient risk identification, delayed budget adjustment, etc. in existing engineering cost consulting methods by applying artificial intelligence technologies such as natural language processing and machine learning, and significantly improves the cost management level of engineering projects.

[0149] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An artificial intelligence-based engineering cost consulting method, characterized in that: The steps include: S1. Provide an intelligent system based on engineering cost data analysis, which collects preliminary data by obtaining the project's bill of quantities, construction plan and material prices; S2. Receive project requirements input by users through natural language processing algorithms, and parse and generate corresponding cost consulting tasks; S3. Use machine learning algorithms to analyze the collected project data and generate project budget plans and preliminary settlement reports; S4. Based on the analysis results, perform intelligent risk identification and provide corresponding risk control suggestions; S5. Dynamically adjust the budget plan according to the project progress and provide real-time cost optimization suggestions; S6. Generate an engineering cost consulting report including cost forecasts, risk control suggestions and optimization solutions, and output it to the user.

2. According to claim 1, the method for engineering cost consulting based on artificial intelligence is characterized in that: The S2 specifically includes: S21. Perform word segmentation on the text input by the user through natural language processing algorithms to identify and extract keywords and semantic information in project requirements; S22. Use the pre-trained semantic understanding model to analyze the contextual association of project requirements and generate structured cost consulting tasks; S23. Combined with project characteristics, a dynamic task mapping algorithm is used to map user requirements into task modules that can be processed by the system. m =f(D,K,C), where T m represents the generated task module, D represents the structured data of project requirements, K represents the keyword set, and C represents the context information; S24. Through the task parsing module, the generated task module is matched with the standard cost task template in the database to generate a corresponding task list.

3. The method for engineering cost consulting based on artificial intelligence according to claim 2 is characterized in that: The S23 specifically includes: S231, extracting context information from the user input requirement text through the semantic parsing model and converting it into structured data D, wherein the structured data is represented by the weight matrix W c Multi-layer weighted generation of information combined with context: in, represents the i-th part of the user input text, Represents contextual information related to the project. It is the context weight matrix, which reflects the weight differences of different parts of the project cost. S232. Generate a keyword set K through keyword extraction and context dependency analysis, and adopt a nonlinear weight adjustment strategy in combination with project features: in, is the dynamic weight matrix of keywords, which is used to adjust the importance of keywords related to project cost in different situations. project represents the project feature data, σ is a nonlinear activation function used to optimize the selection of keywords; S233, generating a task module T based on the structured data D, the keyword set K and the context information C after adjusting the context weight m , and generate the final task through the weighted matching function g: in, It is the weighted matrix of the task modules, which is used to accurately assign priorities to the generated task modules. f3 combines the key parameters in the engineering cost consulting process; S234. A multi-dimensional weight matching mechanism based on task characteristics is adopted to connect the task module with the actual needs in engineering cost consulting, thereby realizing intelligent cost task allocation.

4. The method for engineering cost consulting based on artificial intelligence according to claim 1 is characterized in that: The S3 specifically includes: S31. Through the data preprocessing module, the collected engineering cost-related data is cleaned, deduplicated and formatted to generate a preprocessed data set D p , where the data cleaning process is based on the multi-dimensional data dependency matrix W d Make adjustments: in, is the weighted value of the data dependency matrix, is the original data; S32, based on machine learning algorithm, the preprocessed data set D p Perform feature extraction to generate project feature set F p , the feature extraction process is through the weighted feature mapping matrix W f Adjust the priority of different features: in, is the feature mapping matrix, which adjusts the weights of different features in the budget plan generation, P project is the project characteristic parameter; S33. Use historical data to build a budget forecast model M b , the model is based on the feature set F p Input, adjust the weight matrix W of the budget model through the dynamic optimization function f5 b : Among them, H d is a historical engineering cost dataset. is the weight matrix element in the budget model; S34, based on project progress data P real And dynamic feedback mechanism, adjust the budget plan, the optimized budget plan B ′ Through the nonlinear error adjustment function Δf(B,P real ) for calibration: B ′ =B+β·Δf(B,Preal); Among them, β is the nonlinear adjustment coefficient, Δf(B,P real ) is the error adjustment function between the budget and the actual progress, which is used to dynamically optimize the budget plan B; S35. According to the optimized budget plan B ′ , generate a preliminary settlement report containing cost forecasts, expense allocations and dynamic adjustment suggestions, and output it to the user.

5. The method for engineering cost consulting based on artificial intelligence according to claim 4 is characterized in that: The S34 specifically includes: S341, real-time collection of project progress data real , including engineering quantity, material usage, labor cost and construction progress, generating real-time data set P real , real-time data is fed back through the multi-dimensional feedback matrix W p The weight matrix is ​​dynamically adjusted according to the importance of various data sources: in, To collect the original data of project progress in real time, Indicates the dynamic feedback weights associated with various types of progress data; S342, based on the real-time data set P real The error between the budget solution B and the initial error matrix ΔB is generated, and the error matrix is ​​multi-corrected by the nonlinear adjustment formula: in, is the error weight matrix, which is used to dynamically balance the impact of various error data on the budget deviation. and B (j) Represent the corresponding dimensions of real-time data and budget data respectively; S343. According to the preliminary error matrix ΔB, the budget plan is iteratively corrected through the timing adjustment mechanism: B ′ =B+β·ΔB+γ·h(T,ΔB); Among them, β is the dynamic adjustment coefficient, which is used to control the error adjustment amplitude, γ is the time series correction coefficient, and h(T, ΔB) represents the error time correction function based on time T and error history, which is used to optimize the dynamic budget correction in long-term projects; S344, through the multi-dimensional dynamic feedback mechanism, real-time adjustment of the optimized budget plan B ′ , and compare future budget forecasts with real-time progress data to generate the final optimized budget plan.

6. The method for engineering cost consulting based on artificial intelligence according to claim 1 is characterized in that: The S4 specifically includes: S41. Based on the historical data and current project data of the engineering project, the risk identification module is used to identify the key links of the project and generate a preliminary list of risk factors, including construction delays, cost overruns, material shortages and contract risks; S42. Analyze the project requirements and risk descriptions input by the user through the natural language processing algorithm, classify and annotate the input risk descriptions in combination with the historical risk case library, and generate risk classification information; S43. Based on the risk identification results, multi-dimensional risk analysis is conducted in combination with project characteristics. The analysis dimensions include project scale, construction stage, project type and regional characteristics, and the impact weights and priority rankings of various risks are generated; S44. Based on the generated risk impact weights, evaluate various risks, estimate the possibility of risk occurrence and the potential impact on the overall cost of the project, and generate corresponding risk control recommendations; S45. Compare the generated risk control suggestions with the project requirements input by the user, and automatically match the corresponding risk warning information to generate an intelligent risk identification report.

7. The method for engineering cost consulting based on artificial intelligence according to claim 1 is characterized in that: The S5 specifically includes: S51. Obtain the progress of the project in real time through the monitoring module, including construction progress, material usage and personnel allocation, and generate a real-time project data set; S52. Compare the real-time project data set with the initial budget plan, identify the deviation between the actual progress and the budget, and mark the budget items that need to be adjusted; S53. Re-evaluate the marked budget items through the dynamic budget adjustment module, analyze them in combination with real-time project data and historical data, and determine whether the cost control plan needs to be adjusted; S54. Automatically generate an adjusted budget plan based on the evaluation results, and optimize the key project costs involved in the adjustment; S55. Combine the real-time progress feedback of the project to match the adjusted budget plan with future project needs, and dynamically update the budget plan based on real-time data; S56. Generate a cost optimization report based on the final adjusted budget plan and optimization suggestions. The report content includes the specific details of the adjustment, impact analysis and optimized project cost forecast.

Images