Cost control methods, devices, equipment, storage media and products for engineering construction costs
By dividing the project into multiple construction phases and training the risk assessment model at each phase, the problem of poor project cost control was solved and timely adjustment and optimization of cost control measures were achieved.
Patent Information
- Application Number
- CN202411821437.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-11
- Publication Date
- 2025-09-30
- Estimated Expiration
- 2044-12-11
AI Technical Summary
In the existing technology, the cost control method of engineering cost lacks systematic strategies and precise execution means, resulting in poor cost control effects, especially in large projects, which are difficult to adjust and optimize in time.
The project is divided into multiple construction phases, and the corresponding risk assessment model is trained for each phase. The impact of dynamic changing factors is transmitted through the risk assessment model to generate a target cost control plan.
It improves model training efficiency, enables timely adjustment and optimization of cost control measures, and enhances cost control effects.
Smart Images
Figure CN119761715B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to methods, devices, equipment, storage media, and products for cost control of engineering costs. Background Art
[0002] Currently, cost control is a crucial aspect of project management. Reasonable cost control strategies and methods can not only improve the project's economic benefits but also enhance a company's market competitiveness. However, in practice, cost control is often affected by various factors, such as design changes, material price fluctuations, and construction efficiency, leading to frequent cost overruns. Traditional cost control methods often lack systematic strategies and precise implementation methods, resulting in poor cost control results.
[0003] Related technologies typically use deep neural network learning models to analyze real-time project funding information and project cost budgets, and implement cost control based on the obtained abnormal funding results. However, training deep neural network models in this method often requires a large number of training samples, and often fails to account for dynamic changes in large projects with long construction times. This makes it difficult to adjust and optimize cost control measures in a timely manner, resulting in poor cost control effectiveness.
[0004] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the Invention
[0005] The main purpose of this application is to provide a cost control method for engineering construction costs, aiming to solve the technical problem of poor cost control effect.
[0006] To achieve the above objectives, the present application proposes a method for controlling construction cost, which includes:
[0007] Acquire first construction phase information of a current construction phase, first project construction status information of the first construction phase information, and a first risk assessment model;
[0008] Based on the first project construction status information, a risk assessment is performed using a first risk assessment model for the current construction stage to obtain a first risk impact value for the current construction stage, wherein a corresponding risk assessment model exists for each construction stage;
[0009] Based on the first construction stage information, determine whether the current construction stage has reached the preset final construction stage; if the current construction stage has not reached the final construction stage, send the first risk impact value to the second risk assessment model for the next construction stage, and perform risk assessment using the second risk assessment model based on the second project construction status information for the next construction stage to obtain a second risk impact value for the next construction stage, until the current construction stage reaches the final construction stage, and obtain a third risk impact value for the final construction stage;
[0010] Based on the third risk impact value, a target cost control plan is generated.
[0011] Optionally, before the step of obtaining first construction stage information of the current construction stage, first project construction status information of the first construction stage information, and a first risk assessment model, the method includes:
[0012] Obtaining a construction status sample, a risk impact value sample of a previous construction stage of the construction status sample, and a risk impact value label of the construction status sample;
[0013] Based on the construction status samples, the risk impact value samples of the previous construction stage and the risk impact value labels, the preset model to be trained is iteratively trained to obtain a target risk assessment model, wherein the target risk assessment model includes a first risk assessment model, a second risk assessment model, a third risk assessment model and risk assessment models for other construction stages.
[0014] Optionally, the step of iteratively training a preset model to be trained based on the construction status samples, the risk impact value samples of the previous construction stage, and the risk impact value labels to obtain a target risk assessment model includes:
[0015] Obtaining construction duration information of the construction status sample;
[0016] Determining a time weight of the construction status sample based on the construction duration information;
[0017] Based on the construction status samples, the risk impact value samples of the previous construction stage, the time weights and the risk impact value labels, the preset model to be trained is iteratively trained to obtain a target risk assessment model.
[0018] Optionally, the step of iteratively training a preset to-be-trained model based on the construction status sample, the risk impact value sample of the previous construction stage, the time weight, and the risk impact value label to obtain a target risk assessment model includes:
[0019] Based on the construction status sample, the risk impact value sample of the previous construction stage, and the time weight, a risk assessment is performed using a preset to-be-trained model to obtain a predicted risk impact value;
[0020] Calculate the difference between the predicted risk impact value and the risk impact value label to obtain an error result;
[0021] Based on the error result, determining whether the error result meets an error standard indicated by a preset error threshold range;
[0022] If the error result does not meet the error standard indicated by the preset error threshold range, the model parameters of the model to be trained are updated based on the error result, and the risk impact value sample based on the construction status sample, the risk impact value sample of the previous construction stage and the time weight are returned. The risk assessment is performed through the preset model to be trained to obtain the predicted risk impact value. The training is stopped until the error result meets the error standard indicated by the preset error threshold range to obtain the target risk assessment model.
[0023] Optionally, before the step of obtaining first construction stage information of the current construction stage, first project construction status information of the first construction stage information, and a first risk assessment model, the method includes:
[0024] Obtain multimodal information related to engineering construction at each construction stage;
[0025] Based on the multimodal information, information fusion is performed through a preset multimodal fusion model to obtain the target project construction status information of each construction stage, wherein the target project construction status information includes the first project construction status information, the second project construction status information, and the project construction status information of other construction stages.
[0026] Optionally, the multimodal information related to the engineering construction includes engineering progress information, resource allocation information, cost control information and risk management information.
[0027] In addition, to achieve the above-mentioned purpose, the present application also proposes a cost control device for construction costs, the cost control device for construction costs comprising:
[0028] An acquisition module, configured to acquire first construction stage information of a current construction stage, first project construction status information of the first construction stage information, and a first risk assessment model;
[0029] An assessment module, configured to perform a risk assessment based on the first project construction status information using a first risk assessment model for the current construction phase to obtain a first risk impact value for the current construction phase;
[0030] an iterative module, configured to determine, based on the first construction stage information, whether the current construction stage has reached a preset final construction stage; if the current construction stage has not reached the final construction stage, send the first risk impact value to a second risk assessment model for a next construction stage; and perform a risk assessment using the second risk assessment model based on the second project construction status information for the next construction stage to obtain a second risk impact value for the next construction stage, until the current construction stage reaches the final construction stage, thereby obtaining a third risk impact value for the final construction stage;
[0031] A generating module is used to generate a target cost control plan based on the third risk impact value.
[0032] In addition, to achieve the above-mentioned purpose, the present application also proposes a cost control device for engineering cost, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the cost control method for engineering cost as described above.
[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the cost control method for engineering cost as described above are implemented.
[0034] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the cost control method for engineering cost as described above.
[0035] One or more technical solutions proposed in this application have at least the following technical effects:
[0036] In related technologies, deep neural network learning models are usually used to analyze the real-time capital usage information and project cost budget information of the project, and realize cost control of the project cost based on the abnormal capital expenditure results obtained. However, the training of the deep neural network learning model in this method often requires a large number of training samples for learning, and when faced with large projects with long construction times, it is often unable to take into account dynamic change factors, making it difficult to adjust and optimize cost control measures in a timely manner, which in turn leads to poor cost control effects. In comparison, the present application proposes obtaining first construction stage information of the current construction stage, first project construction status information of the first construction stage information, and a first risk assessment model; based on the first project construction status information, performing risk assessment through the first risk assessment model of the current construction stage to obtain a first risk impact value of the current construction stage, wherein each construction stage has a corresponding risk assessment model; based on the first construction stage information, judging whether the current construction stage has reached a preset final construction stage; if the current construction stage has not reached the final construction stage, sending the first risk impact value to the second risk assessment model of the next construction stage, and based on the second project construction status information of the next construction stage, performing risk assessment through the second risk assessment model to obtain a second risk impact value of the next construction stage, until the current construction stage reaches the final construction stage, obtaining a third risk impact value of the final construction stage; based on the third risk impact value, generating a target cost control plan. It is understandable that this application divides a construction project into multiple construction phases and trains a corresponding risk assessment model at each construction phase. The risk assessment model for each construction phase only requires a small number of training samples to complete the precision model training, without the need for a large number of training samples for learning, which improves the training efficiency of the model. In addition, by dividing a construction project into multiple construction phases, the risk impacts generated by the dynamic changes in factors at each construction phase can be transferred to the next construction phase, thereby enabling timely adjustment and optimization of cost control measures, thereby improving cost control effectiveness. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0039] Figure 1 A flowchart of the first embodiment of the cost control method for construction cost of this application is provided;
[0040] Figure 2 A flow chart illustrating a second embodiment of the cost control method for construction cost of this application;
[0041] Figure 3 This is a schematic diagram of the module structure of the cost control device for the construction cost of an embodiment of the present application;
[0042] Figure 4 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the cost control method for engineering cost in the embodiment of the present application.
[0043] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0044] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.
[0045] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0046] The main solution of the embodiment of the present application is: obtaining the first construction stage information of the current construction stage, the first project construction status information of the first construction stage information, and the first risk assessment model; based on the first project construction status information, performing risk assessment through the first risk assessment model of the current construction stage to obtain the first risk impact value of the current construction stage, wherein each construction stage has a corresponding risk assessment model; based on the first construction stage information, judging whether the current construction stage has reached the preset final construction stage; if the current construction stage has not reached the final construction stage, sending the first risk impact value to the second risk assessment model of the next construction stage, and based on the second project construction status information of the next construction stage, performing risk assessment through the second risk assessment model to obtain the second risk impact value of the next construction stage, until the current construction stage reaches the final construction stage, obtaining the third risk impact value of the final construction stage; based on the third risk impact value, generating a target cost control plan.
[0047] In this embodiment, the cost control device of the engineering cost is used as the execution body. For the convenience of description, it will be explained as "device" hereinafter.
[0048] Related technologies typically use deep neural network learning models to analyze real-time project funding information and project cost budgets, and implement cost control based on the obtained abnormal funding results. However, training deep neural network models in this method often requires a large number of training samples and often fails to account for dynamic changes in large projects with long construction times. This makes it difficult to adjust and optimize cost control measures in a timely manner, resulting in poor cost control effectiveness.
[0049] This application provides a solution to achieve timely adjustment and optimization of cost control measures based on the risk impacts generated by dynamic changing factors in each construction stage, thereby improving cost control effects.
[0050] As can be seen from the above embodiments, this application divides a construction project into multiple construction phases and trains a corresponding risk assessment model at each construction phase. The risk assessment model for each construction phase only requires a small number of training samples to complete the precision model training, without the need for a large number of training samples for learning, thereby improving the training efficiency of the model. In addition, by dividing a construction project into multiple construction phases, the risk impacts generated by the dynamic changes in factors at each construction phase can be transferred to the next construction phase, thereby enabling timely adjustment and optimization of cost control measures, thereby improving cost control effectiveness.
[0051] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device or terminal system capable of implementing the above functions. The following uses a cost control device for construction cost as an example to illustrate this embodiment and the following embodiments.
[0052] Based on this, the embodiment of the present application provides a cost control method for engineering cost, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the cost control method for engineering cost of this application.
[0053] In this embodiment, the method for controlling the construction cost includes steps S100 to S400:
[0054] Step S100, obtaining first construction stage information of the current construction stage, first project construction status information of the first construction stage information, and a first risk assessment model;
[0055] It should be noted that this application proposes to divide each project into multiple construction stages, and each construction stage has a corresponding risk assessment model, that is, each construction stage corresponds to a pre-trained risk assessment model. During the training process, the risk assessment model does not need to use the training samples of the entire project, but only uses the training samples involved in the corresponding construction stage for model training. The risk assessment model of each construction stage only needs a small number of training samples to complete the precision model training, and does not require a large number of training samples for learning, thereby improving the training efficiency of the risk assessment model of each construction stage.
[0056] It is understandable that the construction stage information refers to the current construction stage belonging to a specific stage of the entire project. For example, the project includes 5 construction stages X1-X5, and the current construction stage is X1, then the first construction stage information is X1.
[0057] In practice, construction status information refers to the specific status of construction progress, quality, and safety management during the first construction phase. This information includes whether the current construction progress is proceeding as planned, whether the project quality meets standards, whether on-site safety measures are in place, whether materials meet construction requirements, and whether construction techniques are being correctly applied.
[0058] In practice, risk assessment models are used to identify, evaluate, and respond to potential project risks. Common project risk management models include qualitative risk analysis models, quantitative risk analysis models, Monte Carlo simulation models, sensitivity analysis models, and risk matrix models. The first risk assessment model can be one or a combination of these models, used to assess the risks faced during the first construction phase. This includes steps such as risk identification, risk assessment, risk response planning, and risk monitoring.
[0059] In a specific implementation, before the step of the device acquiring first construction stage information of the current construction stage, first project construction status information of the first construction stage information, and a first risk assessment model, the method includes:
[0060] Acquire multimodal information related to the engineering construction at each construction stage; based on the multimodal information, perform information fusion through a preset multimodal fusion model to obtain target engineering construction status information at each construction stage, wherein the target engineering construction status information includes first engineering construction status information, second engineering construction status information, and engineering construction status information at other construction stages.
[0061] It should be noted that the engineering construction status information is information generated by multi-dimensional information fusion of multimodal information, wherein the multimodal information includes but is not limited to engineering progress information, resource allocation information, cost control information and risk management information.
[0062] In practice, the pre-set multimodal fusion model refers to an algorithm or system capable of integrating and analyzing data from different modalities. The purpose of this model is to effectively integrate data from different modalities, overcome the differences and heterogeneity between modalities, and fully utilize the advantages of each to achieve better performance and results than a single modality. Specifically, the device uses the multimodal fusion model to fuse data extracted from different modalities into a multimodal representation, which is used to characterize different aspects of an entity or to mutually demonstrate the same aspect of the entity, thereby obtaining more comprehensive feature data for the entity.
[0063] In specific implementation, this application improves the ability to understand complex scenes and content by integrating data from different modalities. That is, by fusing multimodal data, the artificial intelligence model can obtain richer and more complete information and improve its ability to understand complex scenes and content.
[0064] Step S200: Based on the first project construction status information, a risk assessment is performed using a first risk assessment model for the current construction stage to obtain a first risk impact value for the current construction stage, wherein a corresponding risk assessment model exists for each construction stage;
[0065] In a specific implementation, the device inputs the first project construction status information into a first risk assessment model, and the model analyzes the data, identifies risk factors, and evaluates the impact of these risks on the project.
[0066] Furthermore, the first risk impact value is the result of the risk assessment, i.e., the risk value calculated by the model based on the input construction status information. This value represents the degree of risk that may be faced during the current construction phase and can be quantitative (e.g., probability, loss amount, etc.) or qualitative (e.g., high, medium, or low risk levels). The probability of the risk situation occurring during each construction phase is selected.
[0067] In specific implementation, this application proposes that there are corresponding risk assessment models for each construction stage, that is, each construction stage has a dedicated risk assessment model. These models will be designed according to the characteristics and risk factors of each stage to ensure the accuracy and effectiveness of the risk assessment. The above process emphasizes that in construction management, the risks of each construction stage are quantified and evaluated by using a dedicated risk assessment model in order to better control and manage project risks and reduce potential losses and impacts. This approach helps construction teams identify and prepare response strategies in advance to reduce the impact of risks on project schedules, costs, and quality.
[0068] Step S300: Based on the first construction stage information, determine whether the current construction stage has reached the preset final construction stage. If the current construction stage has not reached the final construction stage, send the first risk impact value to the second risk assessment model for the next construction stage, and perform risk assessment using the second risk assessment model based on the second project construction status information for the next construction stage to obtain a second risk impact value for the next construction stage. This process continues until the current construction stage reaches the final construction stage, thereby obtaining a third risk impact value for the final construction stage.
[0069] In a specific implementation, the device first determines whether the current construction phase has reached the preset final construction stage based on the information from the first construction phase (i.e., the pre-divided construction progress). If the current construction phase has not yet reached the final construction stage, the risk impact value of the current phase (i.e., the first risk impact value) is transferred to the risk assessment model for the next construction phase (i.e., the second risk assessment model).
[0070] Furthermore, the device uses the construction status information for the next construction phase to conduct a risk assessment using a second risk assessment model, resulting in a risk impact value for the next construction phase (i.e., the second risk impact value). This process is repeated until the current construction phase reaches its final stage, at which point the final risk impact value for the construction phase (i.e., the third risk impact value) is obtained. In other words, by dividing a construction project into multiple phases, the device can transfer the risk impacts generated by dynamically changing factors in each phase to the next, enabling timely adjustment and optimization of cost control measures and improving cost control effectiveness.
[0071] Step S400: generating a target cost control plan based on the third risk impact value.
[0072] In practice, at the final stage of the construction process, a final risk impact value is generated, integrating the risk assessment results from all construction stages. Based on this final risk impact value, the device generates a target cost control plan. This plan considers potential risk factors to ensure that project costs remain within budget.
[0073] In specific implementation, the target cost control plan will include measures to prevent and respond to risks, such as adjusting resource allocation, optimizing construction plans, taking risk mitigation measures, etc., to reduce the impact of risks on costs.
[0074] In related technologies, deep neural network learning models are usually used to analyze the real-time capital usage information and project cost budget information of the project, and realize cost control of the project cost based on the abnormal capital expenditure results obtained. However, the training of the deep neural network learning model in this method often requires a large number of training samples for learning, and when faced with large projects with long construction times, it is often unable to take into account dynamic change factors, making it difficult to adjust and optimize cost control measures in a timely manner, which in turn leads to poor cost control effects. In comparison, the present application proposes obtaining first construction stage information of the current construction stage, first project construction status information of the first construction stage information, and a first risk assessment model; based on the first project construction status information, performing risk assessment through the first risk assessment model of the current construction stage to obtain a first risk impact value of the current construction stage, wherein each construction stage has a corresponding risk assessment model; based on the first construction stage information, judging whether the current construction stage has reached a preset final construction stage; if the current construction stage has not reached the final construction stage, sending the first risk impact value to the second risk assessment model of the next construction stage, and based on the second project construction status information of the next construction stage, performing risk assessment through the second risk assessment model to obtain a second risk impact value of the next construction stage, until the current construction stage reaches the final construction stage, obtaining a third risk impact value of the final construction stage; based on the third risk impact value, generating a target cost control plan. It is understandable that this application divides a construction project into multiple construction phases and trains a corresponding risk assessment model at each construction phase. The risk assessment model for each construction phase only requires a small number of training samples to complete the precision model training, without the need for a large number of training samples for learning, which improves the training efficiency of the model. In addition, by dividing a construction project into multiple construction phases, the risk impacts generated by the dynamic changes in factors at each construction phase can be transferred to the next construction phase, thereby enabling timely adjustment and optimization of cost control measures, thereby improving cost control effectiveness.
[0075] This application also proposes another embodiment based on the above first embodiment, referring to Figure 2 , the cost control method of the project cost includes:
[0076] In a specific implementation, before the step of obtaining the first construction stage information of the current construction stage, the first engineering construction status information of the first construction stage information, and the first risk assessment model, the method includes:
[0077] Step A100, obtaining a construction status sample, a risk impact value sample of a previous construction stage of the construction status sample, and a risk impact value label of the construction status sample;
[0078] In a specific implementation, the device acquires construction status samples, that is, it collects status data for the current construction phase. This data includes, but is not limited to, information such as construction progress, quality, safety status, and resource allocation. Secondly, the device acquires risk impact value samples from the previous construction phase, that is, it collects risk impact value data from the previous construction phase that is directly related to the current construction phase. These data reflect the risk assessment results of the previous phase and can serve as a reference for risk assessment in the current phase. Finally, the device also needs to collect risk impact value labels corresponding to the construction status samples. These labels are the actual risk assessment results and are used to train the model to predict future risk impact values.
[0079] Step A200, based on the construction status sample, the risk impact value sample of the previous construction stage and the risk impact value label, iteratively train the preset model to be trained to obtain a target risk assessment model, wherein the target risk assessment model includes a first risk assessment model, a second risk assessment model, a third risk assessment model and risk assessment models for other construction stages.
[0080] In practice, the device iteratively trains a pre-set model using collected construction status samples, risk impact value samples from the previous construction phase, and risk impact value labels. This process involves using a machine learning algorithm to adjust model parameters to minimize the difference between the model's predicted values and the actual risk impact value labels.
[0081] Furthermore, through iterative training, a target risk assessment model that can accurately predict the risk impact value of the construction stage is finally obtained. This model includes multiple sub-models, each corresponding to a different construction stage.
[0082] In its implementation, the target risk assessment model includes a primary risk assessment model, a secondary risk assessment model, a tertiary risk assessment model, and other risk assessment models for each construction phase. Each model is tailored to its corresponding construction phase and can predict the risk impact value based on samples of the specific construction status of that phase and samples of the risk impact values of the previous phase. In other words, the above process describes a process of training risk assessment models using historical data, aiming to provide a tool that can accurately predict the risk impact value for each construction phase. These models can help construction managers identify and address potential risks in advance, thereby more effectively controlling project risks.
[0083] In a specific implementation, the device iteratively trains a preset to-be-trained model based on the construction status sample, the risk impact value sample of the previous construction stage, and the risk impact value label to obtain a target risk assessment model, including:
[0084] Obtain the construction duration information of the construction status sample; determine the time weight of the construction status sample based on the construction duration information; iteratively train the preset model to be trained based on the construction status sample, the risk impact value sample of the previous construction stage, the time weight and the risk impact value label to obtain a target risk assessment model.
[0085] In a specific implementation, the device obtains the construction duration information of the construction status sample, that is, the device collects the construction duration data corresponding to each construction status sample, where the construction duration information includes but is not limited to the duration of a single task in the project, the total duration of each construction stage, and the duration impact caused by risks.
[0086] Furthermore, the device assigns a time weight to each construction status sample based on construction duration information. The time weight reflects the impact of construction duration on risk assessment. It can be a direct numerical value of construction duration or a weighted value calculated based on construction duration, which is used to adjust the importance of different samples during model training.
[0087] It should be noted that since different time points (including seasons) in the construction process will have corresponding impacts on the construction progress, construction quality, etc., the construction duration of each construction stage will also affect the next construction stage. For example, the X2 construction stage is in the spring from March to May. The weather and environment are more suitable for construction than the summer construction time from June to August, with higher construction efficiency and lower cost. If the construction stage is in the summer construction time from June to August, it is necessary to increase the corresponding risk impact value of weather and environmental factors caused by time, and the X2 construction stage also needs to consider the impact of construction delay caused by the risk impact value of the previous construction stage. That is, the same construction stage will have different risk impacts in different time periods. Therefore, the risk impact weight of the same feature information will be different in different time periods. Therefore, time weight should be introduced to improve the accuracy of model prediction.
[0088] In a specific implementation, the device iteratively trains a preset to-be-trained model based on the construction status sample, the risk impact value sample of the previous construction stage, the time weight, and the risk impact value label to obtain a target risk assessment model, including:
[0089] Based on the construction status samples, the risk impact value samples of the previous construction stage and the time weight, risk assessment is performed through the preset model to be trained to obtain a predicted risk impact value; the predicted risk impact value and the risk impact value label are difference calculated to obtain an error result; based on the error result, it is judged whether the error result meets the error standard indicated by the preset error threshold range; if the error result does not meet the error standard indicated by the preset error threshold range, the model parameters of the model to be trained are updated based on the error result, and the step of performing risk assessment based on the construction status samples, the risk impact value samples of the previous construction stage and the time weight through the preset model to be trained to obtain the predicted risk impact value is returned, and training is stopped until the error result meets the error standard indicated by the preset error threshold range to obtain a target risk assessment model.
[0090] In its implementation, the device first uses a pre-set model to be trained, combining current construction status samples, risk impact samples from the previous construction phase, and time weights to perform a risk assessment and obtain a predicted risk impact value. The device then performs a difference calculation between the predicted risk impact value and the risk impact value label. Specifically, the device compares the model-predicted risk impact value with the actual risk impact value label (i.e., the true value), calculates the difference between the two, and obtains the error result.
[0091] The device then determines whether the error result meets a preset error threshold range. Specifically, the device compares the calculated error result with the preset error threshold range to determine whether the model's prediction accuracy meets acceptable standards. If the error result exceeds the preset error threshold range, it indicates that the model's prediction accuracy is insufficient and the model parameters need to be adjusted. After adjusting the model parameters, the new model parameters are used again to conduct a risk assessment based on the same construction status sample, the risk impact value sample of the previous construction stage, and the time weight to obtain a new predicted risk impact value. The above steps are then repeated until the model's prediction error meets the preset error threshold range.
[0092] It should be noted that the risk assessment model for each construction stage is trained using the iterative training method described above. The construction status samples used in each construction stage's risk assessment model are constructed based on the collected information from that stage. Specifically, only the first construction stage does not require the inclusion of the risk impact value samples from the previous construction stage (which can also be set to 0). All other construction stages require the inclusion of risk impact value samples from the previous construction stage. These risk impact value samples can be independently set based on experiments, or the risk impact values output by the risk assessment model for the previous construction stage can be used in a time-series manner as the risk impact value samples for that construction stage.
[0093] It is understandable that the risk assessment model for each of the above construction stages can be obtained through independent training or through joint training. Independent training means that the risk assessment model for each construction stage only uses the construction status samples constructed by the collected information of its own corresponding construction stage and the risk impact value of the previous construction stage set by itself for model training, that is, the risk assessment model of each construction stage is independent of each other; and joint training means that the risk assessment model for each construction stage uses the construction status samples constructed by the collected information of its own corresponding construction stage and the risk impact value output by the risk assessment model of the previous construction stage according to the time sequence as the risk impact value sample of the construction stage for training, that is, the joint training process is trained according to the time sequence, and finally the target risk assessment model is obtained.
[0094] It should be noted that the above examples are only used to understand this application and do not constitute a limitation on the cost control method of the engineering cost of this application. More simple transformations based on this technical concept are all within the scope of protection of this application.
[0095] This application also provides a cost control device for engineering cost, referring to Figure 3 , the cost control device for the construction cost includes:
[0096] An acquisition module 10 is configured to acquire first construction stage information of a current construction stage, first project construction status information of the first construction stage information, and a first risk assessment model;
[0097] An assessment module 20 is configured to perform a risk assessment based on the first project construction status information using a first risk assessment model for the current construction phase to obtain a first risk impact value for the current construction phase;
[0098] The iteration module 30 is configured to determine, based on the first construction stage information, whether the current construction stage has reached a preset final construction stage; if the current construction stage has not reached the final construction stage, send the first risk impact value to a second risk assessment model for a next construction stage, and perform a risk assessment using the second risk assessment model based on the second project construction status information for the next construction stage to obtain a second risk impact value for the next construction stage, until the current construction stage reaches the final construction stage, thereby obtaining a third risk impact value for the final construction stage;
[0099] The generating module 40 is configured to generate a target cost control solution based on the third risk impact value.
[0100] Optionally, the cost control device for the construction cost further includes:
[0101] A sample acquisition module is used to acquire a construction status sample, a risk impact value sample of a previous construction stage of the construction status sample, and a risk impact value label of the construction status sample;
[0102] A training module is used to iteratively train a preset model to be trained based on the construction status sample, the risk impact value sample of the previous construction stage and the risk impact value label to obtain a target risk assessment model, wherein the target risk assessment model includes a first risk assessment model, a second risk assessment model, a third risk assessment model and risk assessment models for other construction stages.
[0103] Optionally, the training module includes:
[0104] A duration information acquisition module, used to obtain the construction duration information of the construction status sample;
[0105] a determination module, configured to determine a time weight of the construction status sample based on the construction duration information;
[0106] The model training module is used to iteratively train the preset model to be trained based on the construction status sample, the risk impact value sample of the previous construction stage, the time weight and the risk impact value label to obtain a target risk assessment model.
[0107] Optionally, the model training module includes:
[0108] A prediction module, configured to perform risk assessment based on the construction status sample, the risk impact value sample of the previous construction stage, and the time weight, using a preset to-be-trained model to obtain a predicted risk impact value;
[0109] a calculation module, configured to calculate the difference between the predicted risk impact value and the risk impact value label to obtain an error result;
[0110] a judgment module, configured to judge, based on the error result, whether the error result satisfies an error standard indicated by a preset error threshold range;
[0111] An iterative training module is used to update the model parameters of the model to be trained based on the error result if the error result does not meet the error standard indicated by the preset error threshold range, and return the risk impact value sample based on the construction status sample, the previous construction stage and the time weight, and perform risk assessment through the preset model to be trained to obtain the predicted risk impact value. The training is stopped until the error result meets the error standard indicated by the preset error threshold range to obtain the target risk assessment model.
[0112] Optionally, the cost control device for the construction cost further includes:
[0113] Multimodal information acquisition module, used to obtain multimodal information related to engineering construction at each construction stage;
[0114] The information fusion module is used to perform information fusion based on the multimodal information through a preset multimodal fusion model to obtain the target project construction status information of each construction stage, wherein the target project construction status information includes the first project construction status information, the second project construction status information and the project construction status information of other construction stages.
[0115] The cost control device for construction costs provided in this application utilizes the cost control method for construction costs in the above-described embodiments, and can solve the technical problem of cost control for construction costs. Compared with the prior art, the beneficial effects of the cost control device for construction costs provided in this application are the same as those of the cost control method for construction costs provided in the above-described embodiments. The other technical features of the cost control device for construction costs are the same as those disclosed in the above-described embodiments, and are not further described here.
[0116] The present application provides a cost control device for engineering cost, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the cost control method for engineering cost in the above-mentioned embodiment one.
[0117] Reference below Figure 4 , which shows a schematic diagram of the structure of a cost control device for project costs suitable for implementing the embodiments of the present application. The cost control device for project costs in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The cost control device for engineering cost shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0118] like Figure 4As shown, the construction cost control device may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the construction cost control device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008, such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003, such as a magnetic tape or hard disk; and communication device 1009. The communication device 1009 can allow the cost control device for construction cost to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a cost control device for construction cost with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or provided instead.
[0119] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0120] The cost control device for construction costs provided in this application utilizes the cost control method for construction costs in the above-described embodiments to solve the technical problem of cost control for construction costs. Compared to the prior art, the beneficial effects of the cost control device for construction costs provided in this application are the same as those of the cost control method for construction costs provided in the above-described embodiments. The other technical features of the cost control device for construction costs are the same as those disclosed in the above-described embodiments and are not further described here.
[0121] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0122] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.
[0123] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, and the computer-readable program instructions are used to execute the cost control method for engineering costs in the above-mentioned embodiment.
[0124] The computer-readable storage medium provided herein may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including, but not limited to, wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.
[0125] The computer-readable storage medium may be included in the cost control device for construction cost, or may exist independently without being assembled into the cost control device for construction cost.
[0126] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the cost control device for construction cost, the cost control device for construction cost performs cost control of construction cost.
[0127] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0128] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.
[0129] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.
[0130] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned method for controlling project costs, thereby resolving the technical problem of controlling project costs. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the method for controlling project costs provided in the aforementioned embodiments, and are not further elaborated here.
[0131] The present application also provides a computer program product, comprising a computer program, which implements the steps of the above-mentioned method for controlling the cost of engineering costs when executed by a processor.
[0132] The computer program product provided in this application can solve the technical problem of cost control of construction costs. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the cost control method of construction costs provided in the above embodiment, and will not be repeated here.
[0133] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A method for controlling construction cost, characterized in that: The method for cost control of the project cost includes: Obtaining a construction status sample, a risk impact value sample of a previous construction stage of the construction status sample, and a risk impact value label of the construction status sample; Obtaining construction duration information of the construction status sample; Determine the time weight of the construction status sample based on the construction duration information, wherein the time weight reflects the impact of weather conditions on construction in different time periods, and the construction duration of each construction stage will affect the next construction stage; Based on the construction status samples, the risk impact value samples of the previous construction stage, the time weight, and the risk impact value label, iteratively train the preset to-be-trained model to obtain a target risk assessment model, wherein the target risk assessment model includes a first risk assessment model, a second risk assessment model, a third risk assessment model, and risk assessment models for other construction stages; Acquire first construction phase information of a current construction phase, first project construction status information of the first construction phase information, and a first risk assessment model; Based on the first project construction status information, a risk assessment is performed using a first risk assessment model for the current construction stage to obtain a first risk impact value for the current construction stage, wherein a corresponding risk assessment model exists for each construction stage; The construction status information refers to the specific construction progress, quality, and safety management status during the current construction phase, and is generated by multi-dimensional information fusion of multimodal information, including project progress information, resource allocation information, cost control information, and risk management information. Based on the first construction stage information, determine whether the current construction stage has reached the preset final construction stage; if the current construction stage has not reached the final construction stage, send the first risk impact value to the second risk assessment model for the next construction stage, and perform risk assessment using the second risk assessment model based on the second project construction status information for the next construction stage to obtain a second risk impact value for the next construction stage, until the current construction stage reaches the final construction stage, and obtain a third risk impact value for the final construction stage; Based on the third risk impact value, a target cost control plan is generated.
2. The method for controlling construction cost according to claim 1, wherein: The step of iteratively training a preset model to be trained based on the construction status sample, the risk impact value sample of the previous construction stage, the time weight, and the risk impact value label to obtain a target risk assessment model includes: Based on the construction status sample, the risk impact value sample of the previous construction stage, and the time weight, a risk assessment is performed using a preset to-be-trained model to obtain a predicted risk impact value; Calculate the difference between the predicted risk impact value and the risk impact value label to obtain an error result; Based on the error result, determining whether the error result meets an error standard indicated by a preset error threshold range; If the error result does not meet the error standard indicated by the preset error threshold range, the model parameters of the model to be trained are updated based on the error result, and the risk impact value sample based on the construction status sample, the risk impact value sample of the previous construction stage and the time weight are returned. The risk assessment is performed through the preset model to be trained to obtain the predicted risk impact value. The training is stopped until the error result meets the error standard indicated by the preset error threshold range to obtain the target risk assessment model.
3. The method for controlling construction cost according to claim 1, wherein: Before the step of obtaining first construction stage information of the current construction stage, first project construction status information of the first construction stage information, and a first risk assessment model, the method includes: Obtain multimodal information related to engineering construction at each construction stage; Based on the multimodal information, information fusion is performed through a preset multimodal fusion model to obtain the target project construction status information of each construction stage, wherein the target project construction status information includes the first project construction status information, the second project construction status information, and the project construction status information of other construction stages.
4. The method for controlling construction cost according to claim 3, wherein: The multimodal information related to engineering construction includes engineering progress information, resource allocation information, cost control information and risk management information.
5. A cost control device for construction cost, characterized in that: The device comprises: A sample acquisition module is used to acquire a construction status sample, a risk impact value sample of the previous construction stage of the construction status sample, and a risk impact value label of the construction status sample; A duration information acquisition module, used to obtain the construction duration information of the construction status sample; A determination module is configured to determine a time weight of the construction status sample based on the construction duration information, wherein the time weight reflects the impact of the weather environment on construction in different time periods; a model training module is configured to iteratively train a preset to-be-trained model based on the construction status sample, the risk impact value sample of the previous construction stage, the time weight, and the risk impact value label to obtain a target risk assessment model, wherein the target risk assessment model includes a first risk assessment model, a second risk assessment model, a third risk assessment model, and risk assessment models for other construction stages; an acquisition module, configured to acquire first construction stage information of a current construction stage, first project construction status information of the first construction stage information, and a first risk assessment model, wherein the project construction status information refers to the specific construction progress, quality, and safety management status in the current construction stage, and the project construction status information is information generated by multi-dimensional information fusion of multimodal information, wherein the multimodal information includes project progress information, resource allocation information, cost control information, and risk management information; An assessment module, configured to perform a risk assessment based on the first project construction status information using a first risk assessment model for the current construction phase to obtain a first risk impact value for the current construction phase; an iterative module, configured to determine, based on the first construction stage information, whether the current construction stage has reached a preset final construction stage; if the current construction stage has not reached the final construction stage, send the first risk impact value to a second risk assessment model for a next construction stage; and perform risk assessment using the second risk assessment model based on the second project construction status information for the next construction stage to obtain a second risk impact value for the next construction stage, until the current construction stage reaches the final construction stage, thereby obtaining a third risk impact value for the final construction stage, wherein the construction duration of each construction stage will affect the next construction stage; A generating module is used to generate a target cost control plan based on the third risk impact value.
6. A cost control device for construction cost, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for controlling the cost of engineering costs according to any one of claims 1 to 4.
7. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for controlling the cost of engineering costs according to any one of claims 1 to 4 are implemented.
8. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method for controlling the cost of engineering costs according to any one of claims 1 to 4 are implemented.