Engineering consultation intelligent management and cost scheme recommendation method based on data driving

Abstract

The invention discloses an engineering consultation intelligent management and cost scheme recommendation method based on data driving. The method comprises the steps of collecting demand data of a to-be-consulted project to perform feasibility evaluation on the project; building a cloud sharing platform based on the BIM data of a plurality of past projects, and matching the demand data with the cloud sharing platform to screen out a reference case so as to formulate a preliminary cost scheme; acquiring plan progress, task category, resource configuration condition and personnel arrangement information of each task stage of the to-be-consulted project, and determining prediction progress of each task stage; comparing the prediction progress with the planning progress to determine delay duration; key tasks and importance degree coefficients are identified, and resources are reallocated to the key tasks according to the resource allocation model; and constructing a target function by taking the lowest cost as a target based on the allocation result, and searching an optimal solution through a genetic algorithm to update the initial cost scheme. According to the invention, scientific and reasonable allocation of engineering resources is realized, the accuracy and rationality of the cost scheme are improved, and the energy efficiency of engineering consultation management is remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of engineering consulting technology, and in particular to a data-driven intelligent management and cost estimation scheme recommendation method for engineering consulting. Background Technology

[0002] In the field of engineering consulting, traditional management and cost estimation methods have many drawbacks. Previously, when collecting project requirements data, methods were often limited to superficial information, lacking in-depth and comprehensive consideration of key elements such as the overall project construction schedule, budget, resource allocation ratios, and safety standards, significantly compromising the accuracy of project feasibility assessments. Regarding cost estimation, reliance on experienced professionals based on past experience is crucial. This is not only inefficient but also highly susceptible to subjective factors, making it difficult to accurately match the unique needs of each project, resulting in significant discrepancies between estimated and actual costs. Furthermore, during project execution, the lack of scientifically based resource allocation leads to resource shortages in some critical areas while potentially wasting resources in other non-critical areas. Traditional methods also fail to fully utilize project data for accurate forecasting of progress at each task stage, making it difficult to detect potential delays in advance. Moreover, when facing task delays, there is a lack of scientific and effective methods to identify critical tasks and rationally reallocate resources, often resulting in resource waste or improper allocation, further impacting project costs and schedules. Summary of the Invention

[0003] To address at least one of the aforementioned technical problems, this invention provides a data-driven intelligent management and cost estimation scheme recommendation method for engineering consulting.

[0004] In a first aspect, the present invention provides a data-driven intelligent management and cost estimation scheme recommendation method for engineering consulting, the method comprising:

[0005] Collect the requirements information for the project to be consulted, including the overall planning schedule of the project construction, budget, resource allocation ratio and safety standards, and conduct a feasibility assessment of the project based on the requirements information;

[0006] A cloud-based sharing platform is built based on BIM data from multiple past projects. Once a project passes the feasibility assessment, the requirements of the project to be consulted are matched with historical project examples in the cloud-based sharing platform. Reference cases are selected based on the matching results, and a preliminary cost plan is developed for the project to be consulted based on the cost plan of the reference cases.

[0007] Collect information on the planned progress, task categories, resource allocation, and personnel arrangements for each task stage of the project to be consulted, and form time series data; use an LSTM model to model and analyze the time series data to determine the predicted progress of each task stage; determine the delay duration by comparing the predicted progress and the planned progress of each task stage.

[0008] Clarify the relationships between each task stage, identify key tasks based on the delay duration and relationships of each task stage, determine the importance coefficient of key tasks, and reallocate resources for key tasks according to a pre-set resource allocation model.

[0009] Based on the results of resource reallocation, an objective function is constructed with the goal of minimizing construction costs. The optimal solution is then found through a genetic algorithm, and the preliminary cost plan is updated.

[0010] Preferably, the feasibility assessment of the project based on the requirements data includes:

[0011] The evaluation indicators for planning progress, budget, resource allocation ratio, and safety standards are obtained respectively; the first interactive evaluation indicator is determined based on the evaluation indicators for planning progress and budget, and the second interactive evaluation indicator is determined based on the evaluation indicators for resource allocation ratio and safety standards.

[0012] The feasibility index is calculated based on the planning progress, budget, resource allocation ratio, and evaluation indicators of the safety index, as well as the first and second interactive evaluation indicators:

[0013] Determine whether the feasibility index exceeds a preset threshold; if it does, the project is deemed to have passed the feasibility assessment.

[0014] Preferably, the step of identifying key tasks based on the delay duration and correlation of each task stage includes:

[0015] Identify task segments with delays exceeding the preset time and mark them as high-risk task segments;

[0016] Construct a Critical Path Method (CPM) graph to determine the relationships between tasks in the project. Use a graph attention network to process the CPM graph, obtain the embedding vector of each task stage, and filter out the embedding vectors of high-risk task stages.

[0017] Based on the delay duration and embedding vector of high-risk task stages, a decision tree algorithm is used to identify critical tasks.

[0018] Preferably, the association between any two tasks is as follows:

[0019] ;

[0020] In the formula, Indicates construction task For construction tasks The degree of correlation, For construction tasks completion rate The completion coefficient. ; Indicates construction task Resource availability, Indicates construction task and Spatial correlation between them Indicates construction task Construction personnel skills team and construction tasks Skill matching degree of required skills For resource impact coefficient, .

[0021] Preferably, determining the importance coefficient of key tasks includes:

[0022] ;

[0023] In the formula, It is a critical mission The delay value, It is the number of all critical tasks. For critical missions Importance coefficient.

[0024] Preferably, the step of reallocating resources for critical tasks according to a pre-set resource allocation model includes:

[0025] Determine the resource adjustment ratio model:

[0026] ;

[0027] In the formula, Indicates the resource adjustment ratio. Indicates task Relationships with other tasks The preset threshold corresponding to the strength of the association. It is a natural constant; , All are adjustment factors, with a value range of [value range missing]. ;

[0028] Establish a resource reallocation model to redistribute resources for key tasks:

[0029] ;

[0030] In the formula, This is the adjusted resource allocation. This represents the initial resource allocation.

[0031] Secondly, the present invention also provides a data-driven intelligent management and cost estimation scheme recommendation device for engineering consulting, the device comprising:

[0032] The feasibility assessment module is used to collect the requirements data of the project to be consulted, including the overall planning schedule of the project construction, the budget, the resource allocation ratio and the safety standards, and to conduct a feasibility assessment of the project based on the requirements data.

[0033] The cost estimate generation module is used to build a cloud-based shared platform based on BIM data from multiple past projects. After a project passes the feasibility assessment, the module matches the requirements of the project to be consulted with historical project instances in the cloud-based shared platform. Reference cases are selected based on the matching results, and a preliminary cost estimate is developed for the project to be consulted based on the cost estimates of the reference cases.

[0034] The delay duration determination module is used to collect information on the planned progress, task categories, resource allocation status, and personnel arrangements for each task stage of the project to be consulted, forming time series data; it uses an LSTM model to model and analyze the time series data to determine the predicted progress of each task stage; and it determines the delay duration by comparing the predicted progress and planned progress of each task stage.

[0035] The resource reallocation module is used to clarify the relationship between each task stage, identify key tasks based on the delay time and relationship between each task stage, determine the importance coefficient of key tasks, and reallocate resources to key tasks according to the pre-set resource allocation model.

[0036] The cost plan update module is used to construct an objective function based on the results of resource reallocation, with the goal of minimizing the construction cost, and to find the optimal solution through a genetic algorithm to update the preliminary cost plan.

[0037] Thirdly, the present invention also provides an electronic device including a processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein when the processor executes the computer instructions, the electronic device performs a method as described in the first aspect above and any possible implementation thereof.

[0038] Fourthly, the present invention also provides a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor of an electronic device, cause the processor to perform a method as described in the first aspect above and any possible implementation thereof.

[0039] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0040] This invention provides a data-driven intelligent management and cost estimation scheme recommendation method for engineering consulting. By comprehensively collecting the requirements data of the projects to be consulted, it can more accurately assess the feasibility of the projects. A cloud-based sharing platform is built using BIM data from multiple past projects. After the project passes the feasibility assessment, the requirements data of the projects to be consulted are matched with historical project examples to select reference cases, and a preliminary cost estimation scheme is formulated accordingly. Compared with traditional experience-based estimation, this significantly improves the accuracy and rationality of the cost estimation scheme. During the project execution phase, time series data is collected, including planned progress, task categories, resource allocation status, and personnel arrangements for each task stage. LSTM modeling and analysis are used to determine the predicted progress, and the delay duration is determined by comparing it with the planned progress, enabling timely and accurate detection of progress delays. By clarifying the relationships between task stages, key tasks are identified and their importance coefficients are determined based on delay duration and relationships. Then, resources are reallocated according to a pre-set resource allocation model, achieving scientific and rational resource allocation. Finally, based on the resource reallocation results, an objective function is constructed with the goal of minimizing construction costs, and the optimal solution is found through a genetic algorithm to update the preliminary cost plan. This ensures that while guaranteeing the smooth progress of the project, construction costs are minimized to the greatest extent possible, significantly improving the scientific nature and efficiency of engineering consulting management.

[0041] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the background art, the accompanying drawings used in the embodiments of the present invention or the background art will be described below.

[0043] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the specification, serve to illustrate the technical solutions of this disclosure.

[0044] Figure 1 This is a flowchart illustrating a data-driven intelligent management and cost estimation scheme recommendation method for engineering consulting, provided in an embodiment of the present invention.

[0045] Figure 2 for Figure 1 A flowchart illustrating the sub-steps of step S10;

[0046] Figure 3 for Figure 1 A flowchart illustrating the sub-steps of step S40;

[0047] Figure 4This is a schematic diagram of a data-driven intelligent management and cost estimation scheme recommendation device for engineering consulting, provided in an embodiment of the present invention. Detailed Implementation

[0048] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0050] Please see Figure 1 , Figure 1 This is a flowchart illustrating a data-driven intelligent management and cost estimation scheme recommendation method for engineering consulting, provided as an embodiment of the present invention. Figure 1 As shown, the method includes:

[0051] S10. Collect the requirements information for the project to be consulted, including the overall planning schedule of the project construction, the budget, the resource allocation ratio and the safety standards, and conduct a feasibility assessment of the project based on the requirements information.

[0052] S20. Build a cloud-based sharing platform based on BIM data from multiple past projects. After a project passes the feasibility assessment, match the requirements of the project to be consulted with historical project examples in the cloud-based sharing platform. Select reference cases based on the matching results and formulate a preliminary cost plan for the project to be consulted based on the cost plan of the reference cases.

[0053] S30. Collect information on the planned progress, task categories, resource allocation, and personnel arrangements for each task stage of the project to be consulted, and form time series data; use the LSTM model to model and analyze the time series data to determine the predicted progress of each task stage; determine the delay duration by comparing the predicted progress and the planned progress of each task stage.

[0054] S40. Clarify the relationships between each task stage, identify key tasks based on the delay duration and relationships of each task stage, determine the importance coefficient of key tasks, and reallocate resources for key tasks according to the pre-set resource allocation model.

[0055] S50. Based on the results of resource reallocation, construct an objective function with the goal of minimizing construction costs, find the optimal solution through a genetic algorithm, and update the preliminary cost plan.

[0056] In step S10, detailed requirements information for the project to be consulted is first collected, including the overall project construction schedule, budget, resource allocation ratio, and safety standards. A preliminary feasibility assessment is then conducted based on the collected information. The project feasibility assessment primarily evaluates whether the project's technical requirements can be met, determines whether available technical resources and expertise are available to support the project, analyzes the complexity and reliability of the technical solutions, and also considers economic factors to assess the overall feasibility of the project. If the assessment fails, it indicates that the entire project requires rectification; only if it passes will the cost process be further considered.

[0057] Current engineering consulting processes often suffer from the problem of "information silos," meaning that information from different projects is relatively isolated, making it impossible to provide advice for new projects by drawing on experience from past projects and sharing data. To address this, step S20 involves building a cloud-based sharing platform based on BIM data from multiple past projects. Once the feasibility assessment is passed, the project requirements information of the project to be consulted is clustered and matched with historical project cases on the cloud-based sharing platform. This is typically achieved using clustering algorithms. Based on the matching results, reference cases can be quickly selected, and a preliminary cost estimate is generated for the project to be consulted based on the cost estimates of these reference cases.

[0058] Specifically, when establishing a cloud-based sharing platform, BIM data from multiple past projects is collected. This data is cleaned and standardized to ensure consistent formatting for easy subsequent analysis and use. A reliable and secure cloud service provider is then selected to ensure secure data storage and efficient access. When matching cases through clustering, the K-means algorithm is prioritized. Based on the specific needs of the project to be consulted, the most similar historical projects are selected from the clustering results as reference cases. The similarity between the project to be consulted and each reference case is calculated using methods such as Euclidean distance and cosine similarity. The historical project case with the highest similarity is used as the reference case, and an initial cost plan is generated for the project to be consulted based on the cost plan of the reference case. By referencing the experience of historical projects, the planning of new projects becomes more efficient, avoiding design work starting from scratch. Clustering analysis based on a large amount of historical data can more accurately identify reference cases similar to the project to be consulted, thereby providing more reliable cost plans and significantly improving the planning efficiency of the initial plan.

[0059] Once the initial cost estimate is determined, some unreasonable aspects or areas requiring improvement may arise, such as time planning and resource allocation issues. Therefore, in step S30, to further adjust the initial cost estimate and enhance its rationality, information on the planned schedule, task categories, resource allocation, and personnel arrangements for each task phase of the project is collected. Time series data is then constructed, and an LSTM model is used to model and analyze this data to determine the predicted schedule for each task phase. By comparing the predicted schedule with the planned schedule, delays are identified and their duration is calculated. This allows for an accurate assessment of time delays in the project, which can then be used in subsequent resource allocation adjustments and cost estimate optimization processes.

[0060] Furthermore, in step S40, the relationships between each task stage are first clarified, and critical tasks are identified based on the delay duration and relationships of each task stage. The importance coefficient of each critical task is determined, and resources are reallocated to the critical tasks according to a preset resource adjustment model. By identifying and prioritizing critical tasks, the project can be ensured to be completed on time, avoiding delays in the entire project due to delays in individual tasks. This allows for the reasonable allocation of limited resources, ensuring sufficient support for critical tasks and maximizing resource utilization. Finally, after resource reallocation, the overall project plan inevitably changes. To optimize the initial cost plan, in step S50, based on the results of resource reallocation, an objective function is constructed with the goal of minimizing cost. This objective function is then solved using a genetic algorithm to update the initial cost plan, ensuring that the project meets schedule requirements while minimizing costs.

[0061] Therefore, the method provided in this embodiment utilizes BIM technology and a cloud-based sharing platform to integrate detailed data from multiple historical projects, providing a rich reference case library for new projects, improving the accuracy of preliminary feasibility assessments, and solving the data silo problem. By matching the project requirements information of the project to be consulted with historical project cases on the cloud-based sharing platform, reference cases are selected to generate an initial cost plan for the project to be consulted. Compared with manual experience, this method is more scientifically grounded and improves the efficiency and rationality of cost plan consultation. By using an LSTM model to model time series data, the actual progress of each task stage can be predicted more accurately, thereby identifying potential delay risks in advance. The relationships between each task stage are determined, and key tasks are identified based on the delay duration and relationships of each task stage. The importance coefficient of key tasks is determined, and resources are reallocated to key tasks according to a preset resource adjustment model. By dynamically adjusting the resource allocation strategy according to the actual situation, the rationality of resource allocation is ensured, and resource utilization is improved. The objective function constructed based on the resource reallocation results, combined with the optimization solution of a genetic algorithm, can find the lowest cost solution while ensuring project quality and safety, effectively controlling the total project cost.

[0062] See Figure 2 In one embodiment, the feasibility assessment of the project based on the requirements data includes:

[0063] S101. Obtain evaluation indicators for planning progress, budget, resource allocation ratio, and safety standards respectively; determine the first interactive evaluation indicator based on the evaluation indicators for planning progress and budget, and determine the second interactive evaluation indicator based on the evaluation indicators for resource allocation ratio and safety standards.

[0064] S102. Calculate the feasibility index based on the planning progress, budget, resource allocation ratio, and evaluation indicators of the safety index, the first interactive evaluation indicator, and the second interactive evaluation indicator:

[0065] ;

[0066] In the formula, , , , , All are weights; , , , These are evaluation indicators for planning progress, budget, resource allocation ratio, and safety index. and They are the first interaction evaluation index and the second interaction evaluation index, respectively, and satisfy the following:

[0067] ;

[0068] ;

[0069] in, , , , All meet function:

[0070] ;

[0071] In the formula, As the independent variable, These are the preset thresholds for each evaluation indicator. This is an adjustment factor, with a value range of [value range missing]. ;

[0072] S103. Determine whether the feasibility index exceeds the preset threshold. If it does, the project is deemed to have passed the feasibility assessment.

[0073] To aid understanding, let's first explain each indicator:

[0074] Evaluation metrics for project progress typically include plan completion rate, schedule delay rate, and critical path schedule deviation. These metrics help assess whether the project is progressing according to the predetermined timeline.

[0075] Evaluation indicators for the budget mainly include budget execution, such as calculating the difference between actual and budgeted costs, cost overrun rate, and cost-benefit analysis. These are used to measure the effectiveness of project cost control and ensure the economy and efficiency of fund utilization.

[0076] First interactive evaluation indicator: Based on the evaluation indicators of planning progress and budget, a "budget-schedule performance indicator" can be constructed, which is the first interactive evaluation indicator. This indicator is used to reflect whether the project progress meets expectations while adhering to the cost budget, and can identify whether the project is in a state of cost-effectiveness and reasonable schedule.

[0077] Evaluation indicators for resource allocation ratios: These involve the efficiency and balance of resource utilization, such as labor, materials, and equipment, and can be measured through indicators such as resource utilization rate, resource waiting time, and resource idle rate. Efficient and rational resource allocation helps improve project efficiency and reduce costs.

[0078] The evaluation indicators for the safety index include the abnormal construction rate and the rate of investigation and rectification of safety hazards. These indicators reflect the level of safety management at the construction site and are crucial for preventing accidents and protecting worker safety.

[0079] The second interactive evaluation index: Based on the evaluation indexes of resource allocation ratio and construction safety index, a "resource allocation-safety index" can be constructed, which aims to evaluate the efficiency and effectiveness of resource utilization under the premise of ensuring construction safety.

[0080] After obtaining the above indicators, the feasibility index is calculated according to the above formula, where the evaluation indicators for planning progress, budget, resource allocation ratio, and safety index are as follows: , , , That is, the forms of each index function, all of which satisfy The function, specifically the sigmoid function. This function follows an exponential function curve. As the independent variable, we can substitute the corresponding parameters to obtain the results. , , , . This is an adjustment factor used to adjust the steepness of the curve. When, the function curve becomes steeper; when When the time is right, the function curve will be flatter. This value can be set as needed. The first interactive evaluation index aims to measure the negative impact of additional costs when the planning progress is slower than expected. The second interactive evaluation index focuses on the problem of decreased safety assurance levels under insufficient resource allocation. Finally, the overall feasibility index of the project is calculated based on all the above evaluation indicators and their corresponding weights. This process not only considers the influence of individual factors, but also incorporates the influence of interactions between factors, thus obtaining a more comprehensive and accurate evaluation result.

[0081] Once the feasibility index is calculated, the feasibility assessment result of the project is determined based on the magnitude of the feasibility index. For example, a preset threshold can be set; if the feasibility index is greater than the preset threshold, the assessment result is considered passed, and otherwise, it is considered failed, requiring modifications to the project plan.

[0082] Therefore, the feasibility assessment method provided in the above embodiments allows for a more scientific evaluation of whether a project is worth investing in and developing through quantitative analysis, helping decision-makers make more rational choices. In particular, considering risk factors such as cost overruns and time delays, it helps to identify potential problems in advance and take corresponding measures to avoid them. By adjusting different weight settings, the assessment focus can be flexibly adjusted according to the actual situation, making it suitable for feasibility studies of various types of projects.

[0083] See Figure 3 In one embodiment, identifying key tasks based on the delay duration and correlation of each task stage includes:

[0084] S401. Identify task segments with delays exceeding the preset duration and mark them as high-risk task segments;

[0085] S402. Construct a Critical Path Method (CPM) graph to determine the relationships between tasks in the project. Use a graph attention network to process the CPM graph, obtain the embedding vector of each task stage, and filter out the embedding vectors of high-risk task stages.

[0086] S403. Based on the delay duration and embedding vector of high-risk task segments, a decision tree algorithm is used to identify critical tasks.

[0087] In this embodiment, task segments with delays exceeding a preset time are first identified and marked as high-risk task segments. Then, based on the specific arrangements and relationships between tasks in the project, a critical path method (CPM) diagram is constructed. The CPM diagram is used to determine the relationships and critical paths between tasks in the project, as follows:

[0088] Task: A specific work unit in a project. For example, in a construction project, "foundation construction", "main structure construction", and "decoration work" can all be regarded as independent tasks.

[0089] Relationship: The sequential relationship between tasks, such as "main structure construction" can only be carried out after "basic construction" is completed.

[0090] Critical Path: The longest path from start to finish in a project, determining the shortest possible completion time. Tasks on the critical path are called critical tasks, and delays in these tasks will directly extend the project duration.

[0091] The constructed CPM (Critical Path Method) graph is then input into a pre-trained graph attention network. This network learns the complex relationships between task nodes and generates embedding vectors for each task stage, containing key feature information about the task nodes. Finally, from all the embedding vectors, those marked as high-risk task stages are selected. Using the delay time and embedding vectors of these high-risk task stages as input features, a decision tree algorithm is employed to identify critical tasks—those that significantly impact the overall project schedule.

[0092] Therefore, this embodiment, through automated delay monitoring and high-risk task identification, can promptly identify potential risks in a project, helping to take preventative measures to reduce the likelihood of project delays. Identified critical tasks help project managers prioritize the allocation of limited resources, ensuring these tasks are completed on time, thereby guaranteeing the smooth progress of the entire project. Utilizing visualization tools to display the Critical Path Method (CPM) diagram and critical path increases the transparency of project management. Combining graph neural network identification and decision tree classification extraction enables the automatic extraction of critical tasks from large amounts of data, providing scientific data support for project management and improving the quality and efficiency of decision-making.

[0093] Preferably, in the above embodiments, the association between any two tasks is as follows:

[0094] ;

[0095] In the formula, Indicates construction task For construction tasks The degree of correlation, For construction tasks completion rate The completion coefficient. ; Indicates construction task Resource availability, Indicates construction task and Spatial correlation between them Indicates construction task Construction personnel skills team and construction tasks Skill matching degree of required skills For resource impact coefficient, .

[0096] In this embodiment, since the interrelationship between the two construction stages is closely related to issues such as construction completion rate, resource conflicts and sharing, and the skill allocation of construction personnel, the above formula considers the influence of these parameters to calculate the degree of correlation between the two construction stages. For the construction phase The higher the completion rate of the previous stage, the more conducive it is to the implementation of the next stage. Indicates the construction phase Resource availability is considered when the overlap of resources used in two stages is low, indicating a weak correlation. For example, foundation treatment and material handling can be carried out simultaneously without a specific order. Spatial correlation considers the activity range of two construction stages. For instance, if the activity area occupied by the previous stage affects the implementation of the subsequent stage, then the correlation is relatively high, and the subsequent stage can only proceed after the previous stage is completed and space is made available. Skill matching considers personnel overlap, i.e., whether the skills of the construction personnel in the previous stage match those in the subsequent stage. A higher match indicates a stronger correlation. Therefore, by considering multiple factors and combining the above model, the correlation between various construction stages can be quickly and accurately analyzed, providing a basis for formulating a scientific and reasonable construction sequence.

[0097] In one embodiment, determining the importance coefficient of the key task includes:

[0098] ;

[0099] In the formula, It is a critical mission The delay value, It is the number of all critical tasks. For critical missions Importance coefficient.

[0100] Furthermore, the reallocation of resources for critical tasks according to a pre-defined resource allocation model includes:

[0101] Determine the resource adjustment ratio model:

[0102] ;

[0103] In the formula, Indicates the resource adjustment ratio. Indicates task Relationships with other tasks The preset threshold corresponding to the strength of the association. It is a natural constant; , All are adjustment factors, with a value range of [value range missing]. ;

[0104] Establish a resource reallocation model to redistribute resources for key tasks:

[0105] ;

[0106] In the formula, This is the adjusted resource allocation. This represents the initial resource allocation.

[0107] In this embodiment, the delay value of each critical task is used. The importance coefficient of each task is calculated by dividing by the sum of the delay values ​​of all critical tasks. Thus, the longer the delay of a task, the higher its importance coefficient, indicating a greater impact on the project schedule.

[0108] When determining the resource adjustment ratio model, the importance coefficient of the task was taken into account. Strength of correlation between tasks To determine the resource adjustment ratio. This partly reflects the importance of the task, meaning that tasks with longer delays will receive more resources. This part reflects the strength of the correlation between tasks. When Greater than the preset threshold When, the value of this part is close to 1; when Less than the preset threshold At that time, the value of this part is close to 0. This indicates that tasks with stronger correlations will receive a larger proportion of resource adjustments, while , These are all adjustment factors used to balance the impact of importance and correlation on the resource adjustment ratio. Finally, the resource adjustment ratio was determined. After that, it is only necessary to adjust the initial resource allocation. Multiply This will give you the adjusted resource allocation. .if If the value is greater than 0, resource allocation will increase; otherwise, resource allocation will decrease.

[0109] Therefore, by prioritizing critical tasks that are severely delayed and have a significant impact on the project, the resource reallocation method in this embodiment can effectively control project progress and ensure timely project completion. Allocating resources rationally based on task importance and interrelationships ensures that critical tasks receive sufficient support while avoiding resource waste. By reducing delays and optimizing resource allocation, the additional costs caused by delays can be reduced.

[0110] In one embodiment, step S50 involves constructing an objective function based on the results of resource reallocation, aiming at minimizing construction cost, finding the optimal solution using a genetic algorithm, and updating the initial cost plan. This specifically includes the following steps:

[0111] Establish the objective function:

[0112] ;

[0113] ;

[0114] In the formula, Let be the objective function. Indicates task The adjusted construction cost It is the initial construction cost. It is a task After resources were allocated The subsequent performance index function, This refers to the overall performance expected to be achieved. As a weighting factor; It is the cost growth rate;

[0115] Construct constraints:

[0116] ;

[0117] ;

[0118] In the formula, Indicates the total construction cost budget. This represents the minimum performance index.

[0119] In the above formula, the objective function aims to minimize the total cost and consists of two parts: the first part... This directly reflects the sum of costs after adjustments to all tasks, Part Two. This is a penalty term used to ensure that overall performance is close to the expected value. The weighting factor is used to balance the relationship between cost and performance; if the actual performance deviates from the expected performance, it will increase additional cost. The adjusted construction cost... Describes the process of completing the task. Allocate more resources, assuming This represents a quantity of a certain form of resource, the cost of which will increase proportionally from the initial cost. This growth rate is defined, and its value range is typically [value range missing]. However, when determining the constraints, This means that the total cost cannot exceed the total budget. This means that each task must meet at least the minimum performance standard to ensure service quality.

[0120] To facilitate understanding, a specific example is provided below:

[0121] 1) Assume a project contains 3 tasks, with the following parameter settings:

[0122] Table 1. Meaning and values ​​of each parameter

[0123]

[0124] 2) Assume the performance function is a linear relationship with resource allocation:

[0125] Task 1: ;

[0126] Task 2: ;

[0127] Task 3: ;

[0128] 3) The objective function is:

[0129]

[0130] The constraints are:

[0131] ;

[0132] ;

[0133] ;

[0134] ;

[0135] ;

[0136] 4) Solving using genetic algorithm:

[0137] Variable: Resource allocation , , ;

[0138] Encoding method: Real number encoding, initial population (e.g., 50 individuals) is generated randomly.

[0139] The fitness value is the reciprocal of the objective function (the smaller the better).

[0140] Calculate adjustment costs: ;

[0141] =600 (If the budget constraint is violated, the individual will be eliminated).

[0142] By selecting feasible solutions and generating new individuals through crossover and mutation, it is possible to eventually converge to the optimal solution.

[0143] Under this optimal solution,

[0144] Total cost: Ten thousand yuan (meets the budget);

[0145] Overall performance: (Above the target).

[0146] Thus, the optimal solution was obtained through genetic algorithm optimization, which determined the final cost plan. The costs for tasks 1, 2, and 3 are as follows: Ten thousand yuan.

[0147] Therefore, by establishing the objective function and constraints through the above model, and then optimizing the initial cost plan through the genetic algorithm, the project can be optimized based on resource optimization. This ensures the required performance while effectively controlling the total cost, thus improving the project's economic benefits and making the cost plan more rational. This achieves the optimal resource allocation strategy under the given objectives.

[0148] See Figure 4 In one embodiment, the present invention also provides a data-driven intelligent management and cost estimation scheme recommendation device for engineering consulting, the device comprising:

[0149] The feasibility assessment module 100 is used to collect the requirements data of the project to be consulted, including the overall planning schedule of the project construction, the budget, the resource allocation ratio and the safety standards, and to conduct a feasibility assessment of the project based on the requirements data.

[0150] The cost estimate generation module 200 is used to build a cloud-based shared platform based on BIM data from multiple past projects. After a project passes the feasibility assessment, the project's requirements are matched with historical project instances in the cloud-based shared platform. Reference cases are selected based on the matching results, and a preliminary cost estimate is developed for the project based on the cost estimates of the reference cases.

[0151] The delay duration determination module 300 is used to collect information on the planned progress, task categories, resource allocation status, and personnel arrangements for each task stage of the project to be consulted, forming time series data; it uses an LSTM model to model and analyze the time series data to determine the predicted progress of each task stage; and it determines the delay duration by comparing the predicted progress and planned progress of each task stage.

[0152] The resource reallocation module 400 is used to clarify the relationship between each task stage, identify key tasks based on the delay time and relationship between each task stage, determine the importance coefficient of key tasks, and reallocate resources to key tasks according to a pre-set resource allocation model.

[0153] The cost scheme update module 500 is used to construct an objective function based on the results of resource reallocation, with the goal of minimizing the cost, and to find the optimal solution through a genetic algorithm to update the preliminary cost scheme.

[0154] It is understood that the functions or modules of the device provided in this embodiment can be used to execute the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0155] The present invention also provides an electronic device including a processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein when the processor executes the computer instructions, the electronic device performs a method as described in any of the above possible implementations.

[0156] The present invention also provides a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor of an electronic device, cause the processor to perform a method as described in any of the above possible implementations.

[0157] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

Claims

1. A data-driven intelligent management and cost estimation scheme recommendation method for engineering consulting, characterized in that, The method includes: Collect the requirements information for the project to be consulted, including the overall planning schedule of the project construction, the budget, the resource allocation ratio and the safety standards, and conduct a feasibility assessment of the project based on the requirements information; A cloud-based sharing platform is built based on BIM data from multiple past projects. Once a project passes the feasibility assessment, the requirements of the project to be consulted are matched with historical project examples in the cloud-based sharing platform. Reference cases are selected based on the matching results, and a preliminary cost plan is developed for the project to be consulted based on the cost plan of the reference cases. Collect information on the planned progress, task categories, resource allocation, and personnel arrangements for each task stage of the project to be consulted, and form time series data; use an LSTM model to model and analyze the time series data to determine the predicted progress of each task stage; determine the delay duration by comparing the predicted progress and the planned progress of each task stage. Clarify the relationships between each task stage, identify key tasks based on the delay duration and relationships of each task stage, determine the importance coefficient of key tasks, and reallocate resources for key tasks according to a pre-set resource allocation model. Based on the results of resource reallocation, an objective function is constructed with the goal of minimizing construction costs. The optimal solution is then found through a genetic algorithm, and the preliminary cost plan is updated.

2. The data-driven intelligent management and cost estimation scheme recommendation method for engineering consulting as described in claim 1, characterized in that, The feasibility assessment of the project based on the requirements data includes: The evaluation indicators for planning progress, budget, resource allocation ratio, and safety standards are obtained respectively; the first interactive evaluation indicator is determined based on the evaluation indicators for planning progress and budget, and the second interactive evaluation indicator is determined based on the evaluation indicators for resource allocation ratio and safety standards. The feasibility index is calculated based on the planning progress, budget, resource allocation ratio, and evaluation indicators of the safety index, as well as the first and second interactive evaluation indicators: Determine whether the feasibility index exceeds a preset threshold; if it does, the project is deemed to have passed the feasibility assessment.

3. The efficient engineering consulting management method based on BIM and data sharing according to claim 1, characterized in that, The identification of key tasks based on the delay duration and correlation of each task stage includes: Identify task segments with delays exceeding the preset time and mark them as high-risk task segments; Construct a Critical Path Method (CPM) graph to determine the relationships between tasks in the project. Use a graph attention network to process the CPM graph, obtain the embedding vector of each task stage, and filter out the embedding vectors of high-risk task stages. Based on the delay duration and embedding vector of high-risk task stages, a decision tree algorithm is used to identify critical tasks.

4. The efficient engineering consulting management method based on BIM and data sharing according to claim 3, characterized in that, The relationship between any two tasks is as follows: ； In the formula, Indicates construction task For construction tasks The degree of correlation, For construction tasks completion rate The completion coefficient. ; Indicates construction task Resource availability, Indicates construction task and Spatial correlation between them Indicates construction task Construction personnel skills team and construction tasks Skill matching degree of required skills For resource impact coefficient, .

5. The data-driven intelligent management and cost estimation scheme recommendation method for engineering consulting as described in claim 1, characterized in that, The determination of the importance coefficient of key tasks includes: ； In the formula, It is a critical mission The delay value, It is the number of all critical tasks. For critical missions Importance coefficient.

6. The data-driven intelligent management and cost estimation scheme recommendation method for engineering consulting as described in claim 5, characterized in that, The process of reallocating resources for critical tasks according to a pre-defined resource allocation model includes: Determine the resource adjustment ratio model: ； In the formula, Indicates the resource adjustment ratio. Indicates task Relationships with other tasks The preset threshold corresponding to the strength of the association. It is a natural constant; , All are adjustment factors, with a value range of [value range missing]. ; Establish a resource reallocation model to redistribute resources for key tasks: ； In the formula, This is the adjusted resource allocation. This represents the initial resource allocation.

7. A data-driven intelligent management and cost estimation solution recommendation device for engineering consulting, characterized in that, The device includes: The feasibility assessment module is used to collect the requirements data of the project to be consulted, including the overall planning schedule of the project construction, the budget, the resource allocation ratio and the safety standards, and to conduct a feasibility assessment of the project based on the requirements data. The cost estimate generation module is used to build a cloud-based shared platform based on BIM data from multiple past projects. After a project passes the feasibility assessment, the module matches the requirements of the project to be consulted with historical project instances in the cloud-based shared platform. Reference cases are selected based on the matching results, and a preliminary cost estimate is developed for the project to be consulted based on the cost estimates of the reference cases. The delay duration determination module is used to collect information on the planned progress, task categories, resource allocation status, and personnel arrangements for each task stage of the project to be consulted, forming time series data; it uses an LSTM model to model and analyze the time series data to determine the predicted progress of each task stage; and it determines the delay duration by comparing the predicted progress and planned progress of each task stage. The resource reallocation module is used to clarify the relationship between each task stage, identify key tasks based on the delay time and relationship between each task stage, determine the importance coefficient of key tasks, and reallocate resources to key tasks according to the pre-set resource allocation model. The cost plan update module is used to construct an objective function based on the results of resource reallocation, with the goal of minimizing the construction cost, and to find the optimal solution through a genetic algorithm to update the preliminary cost plan.

8. An electronic device, characterized in that, include: A processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein when the processor executes the computer instructions, the electronic device performs the data-driven intelligent management and cost estimation scheme recommendation method for engineering consulting as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which includes program instructions that, when executed by a processor of an electronic device, cause the processor to perform the data-driven intelligent management and cost estimation scheme recommendation method for engineering consulting as described in any one of claims 1 to 7.

Images