Project cost consultation management system based on big data
By using big data and parameter transfer training technology, a cross-regional engineering cost prediction model was established, which solved the problems of low efficiency and unstable accuracy in existing technologies, and achieved efficient and accurate engineering cost consulting.
Patent Information
- Application Number
- CN202511478905.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-16
- Publication Date
- 2026-02-10
AI Technical Summary
In existing technologies, the efficiency and accuracy of engineering cost consulting results are low, leading to uncontrolled project budgets and cost overruns, which affect the economic and social benefits of engineering projects.
The engineering cost consulting management system based on big data is adopted. By acquiring big data training samples of engineering cost, an initial network model is trained. Then, by using parameter transfer training technology, multiple engineering cost prediction models are established to achieve cross-regional cost prediction.
It improves the efficiency and accuracy of engineering cost consulting, ensures the precision and consistency of cost forecasts, and reduces project cost risks.
Smart Images
Figure CN121504500A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of engineering cost prediction, and in particular to an engineering cost consulting management system based on big data. Background Technology
[0002] Construction engineering refers to the entire process of building various buildings or structures with clearly defined functions in a specific geographical location through a series of systematic workflows, including professional design and planning, standardized construction, and standardized supervision and management. This complex process involves not only the design and construction of building structures but also the coordinated efforts of multiple professional fields such as civil engineering, installation engineering, and decoration. Construction engineering often incurs significant economic costs, including material procurement costs, equipment rental costs, labor costs, and various management and operational expenses. Cost forecasting for construction projects requires professional appraisers to apply their expertise in construction cost estimation and conduct a comprehensive assessment based on the actual project conditions. The more extensive the construction project and the more complex the bill of quantities, the longer the assessment time will be, and the accuracy of the assessment will heavily depend on the professional competence and practical experience of the appraisers. Furthermore, differences in economic development levels across regions will also affect the assessment, particularly regarding material and labor costs in the construction area; for example, there are significant differences in building material prices and labor wages between first-tier cities and third- and fourth-tier cities. Therefore, existing technologies suffer from low efficiency and unstable accuracy in obtaining cost consulting results. These problems often lead to risks such as project budget loss and cost overruns, seriously affecting the economic and social benefits of engineering projects. Summary of the Invention
[0003] Therefore, the purpose of this application is to provide an engineering cost consulting management system based on big data, which can overcome the shortcomings of the existing technology.
[0004] To achieve the above objectives, the technical solution adopted in this application is as follows:
[0005] The first aspect of this application provides a big data-based engineering cost consulting management system, comprising:
[0006] The big data training sample acquisition module is used to acquire engineering cost big data training samples; the engineering cost big data training samples include engineering cost data training samples from multiple initial regions; the engineering cost data training samples include engineering parameters and corresponding engineering costs;
[0007] The first prediction model training module is used to determine the initial region corresponding to the engineering cost data training sample with the largest amount of sample data as the first region, and train the corresponding initial network model based on the engineering cost data training sample of the first region to obtain the first engineering cost prediction model corresponding to the first region.
[0008] The sample similarity acquisition module is used to train samples based on the engineering cost data of the first region and the remaining engineering cost data of the initial region to obtain multiple data sample similarities.
[0009] The second prediction model training module is used to perform parameter transfer training on the initial network model of the multiple initial regions based on the similarity of the multiple data samples, the first engineering cost prediction model and the engineering cost data training samples of other initial regions, to obtain multiple second engineering cost prediction models.
[0010] The cost prediction module is used to obtain the predicted cost of the received engineering cost consulting data based on the first engineering cost prediction model and the plurality of second engineering cost prediction models.
[0011] As one implementation, the step of obtaining the similarity of multiple data samples based on the engineering cost data training samples of the first region and the remaining engineering cost data training samples of the initial region includes:
[0012] The engineering cost data training samples of the first region are used as the target domain, and the remaining engineering cost data training samples of the initial region are used as multiple source domains. The domain similarity between the multiple source domains and the target domain is obtained, and the highest domain similarity is stored as the data sample similarity.
[0013] If the number of source domains is greater than a preset threshold, the engineering cost data training samples of the initial region corresponding to the data sample similarity are determined as target domains, the domain similarity between the remaining source domains and target domains is updated, and the highest domain similarity is stored as data sample similarity.
[0014] As one implementation method, the domain similarity between the source domain and the target domain is obtained through the following steps:
[0015] Obtain the maximum mean difference between the source domain and the target domain;
[0016] The domain similarity is obtained based on the maximum mean difference; wherein, the smaller the maximum mean difference, the greater the domain similarity.
[0017] As one implementation, the step of obtaining the maximum mean difference between the source domain and the target domain includes:
[0018] The maximum mean difference can be obtained using the following formula:
[0019]
[0020] Among them, MMD(X) S ,X T X represents the maximum mean difference; S For the source domain; X T Let be the target domain; φ(·) be the mapping function; m be the number of training samples in the source domain; and n be the number of training samples in the target domain. Let i be the i-th sample data of the training samples in the source domain; Let j be the j-th sample data of the training samples for the target domain.
[0021] As one implementation, the step of performing parameter transfer training on the initial network models of the multiple initial regions based on the similarity of the multiple data samples, the first engineering cost prediction model, and the engineering cost data training samples of other initial regions to obtain multiple second engineering cost prediction models includes:
[0022] If the target domain of the data sample similarity corresponds to the engineering cost prediction model, and the source domain of the data sample similarity corresponds to the initial network model, the model parameters of the engineering cost prediction model are transferred to the initial network model to obtain a transfer learning model; the engineering cost prediction model includes a first engineering cost prediction model and a second engineering cost prediction model.
[0023] The transfer learning model is trained based on the sample data of the source domain; the second engineering cost prediction model for the initial region corresponding to the source domain is obtained.
[0024] As one implementation method, the step of obtaining the predicted cost of the received engineering cost consulting data based on the first engineering cost prediction model and the plurality of second engineering cost prediction models includes:
[0025] The first engineering cost prediction model and the plurality of second engineering cost prediction models are deployed to the corresponding regional servers in the initial region as engineering cost prediction edge models;
[0026] The engineering cost consulting data received by the regional server is input into the corresponding engineering cost prediction edge model to obtain the predicted cost.
[0027] As one implementation method, the step of obtaining the predicted cost of the received engineering cost consulting data based on the first engineering cost prediction model and the plurality of second engineering cost prediction models includes:
[0028] Identify the target project parameters and construction area in the received engineering cost consulting data;
[0029] Based on the correspondence between the construction area and the multiple initial areas, the target project cost prediction model is obtained from the first project cost prediction model and the multiple second project cost prediction models;
[0030] The target project parameters are input into the target project cost prediction model to obtain the predicted cost.
[0031] As one implementation method, after obtaining the predicted cost, the steps include:
[0032] The predicted cost is sent to the terminal device that uploaded the engineering cost consulting data.
[0033] As one implementation method, after obtaining the predicted cost, the steps include:
[0034] Send the engineering cost consulting data and the predicted cost to the designated email address.
[0035] As one implementation method, the step of sending the engineering cost consulting data and the predicted cost to a designated email address includes:
[0036] The engineering cost consulting data and the predicted cost are encrypted and compressed according to the compression password to obtain encrypted and compressed cost consulting data.
[0037] The compressed password is sent to the terminal device that uploads the engineering cost consulting data, and the encrypted and compressed cost consulting data is sent to the designated email address.
[0038] Compared with traditional technologies, the beneficial effects of this application are:
[0039] This application designates the initial region corresponding to the engineering cost data training samples with the largest sample size as the first region. An initial network model is trained based on the engineering cost data training samples of the first region to obtain a first engineering cost prediction model for the first region. Then, based on the engineering cost data training samples of the first region and the remaining engineering cost data training samples of the initial regions, multiple data sample similarities are obtained. Next, based on the multiple data sample similarities, the first engineering cost prediction model and the engineering cost data training samples of the other initial regions are used to perform parameter transfer training on the initial network models of the multiple initial regions to obtain multiple second engineering cost prediction models. Finally, based on the first engineering cost prediction model and the multiple second engineering cost prediction models, the predicted cost of the received engineering cost consulting data is obtained. By using the first engineering cost prediction model and the multiple second engineering cost prediction models, the predicted cost of engineering cost consulting data can be obtained efficiently and accurately, improving the efficiency and accuracy of engineering cost consulting.
[0040] To better understand and implement this application, the following detailed description is provided in conjunction with the accompanying drawings. Attached Figure Description
[0041] Figure 1 This is a schematic diagram of the module connections of a big data-based engineering cost consulting management system according to one embodiment of this application;
[0042] Figure 2 A flowchart of steps S131-S132 of a big data-based engineering cost consulting management system according to an embodiment of this application;
[0043] Figure 3 The flowchart shows steps S141-S142 of a big data-based engineering cost consulting management system according to an embodiment of this application.
[0044] 100. Engineering cost consulting management system based on big data; 110. Big data training sample acquisition module; 120. First prediction model training module; 130. Sample similarity acquisition module; 140. Second prediction model training module; 150. Prediction cost module. Detailed Implementation
[0045] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.
[0046] It should be understood that the described embodiments are merely some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of the embodiments of this application.
[0047] In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. In the description of this application, it should be understood that the terms "first," "second," "third," etc., are used only to distinguish similar objects and are not necessarily used to describe a specific order or sequence, nor should they be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances. The singular forms "a," "the," and "the" used in this application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. The word "if" as used herein can be interpreted as "when," "when," or "in response to determination."
[0048] Furthermore, in the description of this application, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.
[0049] Please see Figure 1 This is a schematic diagram of the module connections of the big data-based engineering cost consulting management system 100 according to the first embodiment of this application, including:
[0050] The big data training sample acquisition module 110 is used to acquire engineering cost big data training samples; the engineering cost big data training samples include engineering cost data training samples from multiple initial regions; the engineering cost data training samples include engineering parameters and corresponding engineering costs.
[0051] The first prediction model training module 120 is used to determine the initial region corresponding to the engineering cost data training sample with the largest amount of sample data as the first region, train the corresponding initial network model based on the engineering cost data training sample of the first region, and obtain the first engineering cost prediction model corresponding to the first region.
[0052] The sample similarity acquisition module 130 is used to obtain multiple data sample similarities based on the engineering cost data of the first region and the remaining engineering cost data of the initial region.
[0053] Please see Figure 2 The step of obtaining the similarity of multiple data samples based on the engineering cost data training samples of the first region and the remaining engineering cost data training samples of the initial region includes:
[0054] S131: Take the engineering cost data training samples of the first region as the target domain, take the remaining engineering cost data training samples of the initial region as multiple source domains, obtain the domain similarity between the multiple source domains and the target domain, and store the highest domain similarity as the data sample similarity.
[0055] S132: If the number of source domains is greater than a preset number threshold, the engineering cost data training sample of the initial region corresponding to the data sample similarity is determined as the target domain, the domain similarity between the remaining source domains and the target domains is updated, and the highest domain similarity is stored as the data sample similarity.
[0056] The preset quantity threshold is 0.
[0057] In this embodiment, the highest domain similarity is obtained by comparing the domain similarity between multiple source domains and the target domain, and is used as the data sample similarity. The corresponding engineering cost data training sample of the initial region is determined as the target domain to update the data of the source domain and the target domain. This updates the domain similarity between each source domain and each target domain. The highest domain similarity is again used as the data sample similarity, and the corresponding engineering cost data training sample of the initial region is determined as the target domain. This process is repeated until the number of source domains is reduced to 0. The domain similarity between the source domain and the target domain can be dynamically updated to obtain the most similar object among the remaining engineering cost data training samples of the initial region, so as to determine the order of transfer learning training.
[0058] The second prediction model training module 140 is used to perform parameter transfer training on the initial network model of the multiple initial regions based on the similarity of the multiple data samples, the first engineering cost prediction model and the engineering cost data training samples of other initial regions, to obtain multiple second engineering cost prediction models.
[0059] The cost prediction module 150 is used to obtain the predicted cost of the received engineering cost consulting data based on the first engineering cost prediction model and the plurality of second engineering cost prediction models.
[0060] Compared with traditional technologies, the beneficial effects of this application are:
[0061] This application designates the initial region corresponding to the engineering cost data training samples with the largest sample size as the first region. An initial network model is trained based on the engineering cost data training samples of the first region to obtain a first engineering cost prediction model for the first region. Then, based on the engineering cost data training samples of the first region and the remaining engineering cost data training samples of the initial regions, multiple data sample similarities are obtained. Next, based on the multiple data sample similarities, the first engineering cost prediction model and the engineering cost data training samples of the other initial regions are used to perform parameter transfer training on the initial network models of the multiple initial regions to obtain multiple second engineering cost prediction models. Finally, based on the first engineering cost prediction model and the multiple second engineering cost prediction models, the predicted cost of the received engineering cost consulting data is obtained. By using the first engineering cost prediction model and the multiple second engineering cost prediction models, the predicted cost of engineering cost consulting data can be obtained efficiently and accurately, improving the efficiency and accuracy of engineering cost consulting.
[0062] Please see Figure 3 In a feasible embodiment, the domain similarity between the source domain and the target domain is obtained through the following steps:
[0063] Obtain the maximum mean difference between the source domain and the target domain;
[0064] The domain similarity is obtained based on the maximum mean difference; wherein, the smaller the maximum mean difference, the greater the domain similarity.
[0065] In this embodiment, the domain similarity between the source domain and the target domain can be accurately obtained based on the maximum mean difference between the source domain and the target domain.
[0066] In a feasible embodiment, the step of obtaining the maximum mean difference between the source domain and the target domain includes:
[0067] The maximum mean difference can be obtained using the following formula:
[0068]
[0069] Among them, MMD(X) S ,X T X represents the maximum mean difference; S For the source domain; X T Let be the target domain; φ(·) be the mapping function; m be the number of training samples in the source domain; and n be the number of training samples in the target domain. Let i be the i-th sample data of the training samples in the source domain; Let j be the j-th sample data of the training samples for the target domain.
[0070] In this embodiment, the maximum mean difference can be accurately obtained using the above formula.
[0071] Please see Figure 3 In one feasible embodiment, the step of performing parameter transfer training on the initial network models of the multiple initial regions based on the similarity of the multiple data samples, the first engineering cost prediction model, and the engineering cost data training samples of other initial regions to obtain multiple second engineering cost prediction models includes:
[0072] S141: If the target domain of the data sample similarity corresponds to the engineering cost prediction model, and the source domain of the data sample similarity corresponds to the initial network model, the model parameters of the engineering cost prediction model are transferred to the initial network model to obtain a transfer learning model; the engineering cost prediction model includes a first engineering cost prediction model and a second engineering cost prediction model.
[0073] S142: Train the transfer learning model based on the sample data of the source domain; obtain the second engineering cost prediction model for the initial region corresponding to the source domain.
[0074] Among them, the sample data of the source domain are the sample data of the engineering cost data training samples of the corresponding initial region.
[0075] In this embodiment, model parameters are transferred based on data sample similarity to obtain a transfer learning model. The transfer learning model is then trained based on the sample data of the corresponding source domain. Even if the amount of sample data in the source domain is less than the amount of sample data in the first region, a second engineering cost prediction model with high accuracy can still be obtained.
[0076] In a feasible embodiment, the step of obtaining the predicted cost of the received engineering cost consulting data based on the first engineering cost prediction model and the plurality of second engineering cost prediction models includes:
[0077] S151: Deploy the first engineering cost prediction model and the plurality of second engineering cost prediction models to the corresponding regional server of the initial region as engineering cost prediction edge models.
[0078] S152: Input the engineering cost consulting data received by the regional server into the corresponding engineering cost prediction edge model to obtain the predicted cost.
[0079] In this embodiment, by deploying the first engineering cost prediction model and the plurality of second engineering cost prediction models to the corresponding regional server in the initial region as an edge model for engineering cost prediction, the regional server can directly input the engineering cost consultation data uploaded by the terminal device in the corresponding region into the corresponding edge model for engineering cost prediction, so as to obtain the predicted cost efficiently and accurately.
[0080] In a feasible embodiment, the step of obtaining the predicted cost of the received engineering cost consulting data based on the first engineering cost prediction model and the plurality of second engineering cost prediction models includes:
[0081] S153: Identify the target project parameters and construction area in the received engineering cost consulting data;
[0082] S154: Based on the correspondence between the construction area and the plurality of initial areas, obtain the target project cost prediction model from the first project cost prediction model and the plurality of second project cost prediction models;
[0083] S155: Input the target project parameters into the target project cost prediction model to obtain the predicted cost.
[0084] Steps S153-S155 are independent of steps S151-S152.
[0085] In this embodiment, after identifying the target project parameters and construction area in the received engineering cost consulting data, the target project parameters are input into the target project cost prediction model corresponding to the construction area, so as to accurately obtain the predicted cost.
[0086] In one feasible embodiment, after obtaining the predicted cost, the step includes:
[0087] The predicted cost is sent to the terminal device that uploaded the engineering cost consulting data.
[0088] In one feasible embodiment, after obtaining the predicted cost, the step includes:
[0089] Send the engineering cost consulting data and the predicted cost to the designated email address.
[0090] In one feasible embodiment, the step of sending the engineering cost consulting data and the predicted cost to a designated email address includes:
[0091] The engineering cost consulting data and the predicted cost are encrypted and compressed according to the compression password to obtain encrypted and compressed cost consulting data.
[0092] The compressed password is sent to the terminal device that uploads the engineering cost consulting data, and the encrypted and compressed cost consulting data is sent to the designated email address.
[0093] The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without any inventive effort.
[0094] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0095] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function selected in one or more boxes.
[0096] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function selected in one or more boxes.
[0097] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0098] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.
[0099] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.
[0100] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0101] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.
Claims
1. A big data-based engineering cost consulting management system, characterized in that, include: The big data training sample acquisition module is used to acquire engineering cost big data training samples; the engineering cost big data training samples include engineering cost data training samples from multiple initial regions; the engineering cost data training samples include engineering parameters and corresponding engineering costs; The first prediction model training module is used to determine the initial region corresponding to the engineering cost data training sample with the largest amount of sample data as the first region, and train the corresponding initial network model based on the engineering cost data training sample of the first region to obtain the first engineering cost prediction model corresponding to the first region. The sample similarity acquisition module is used to train samples based on the engineering cost data of the first region and the remaining engineering cost data of the initial region to obtain multiple data sample similarities. The second prediction model training module is used to perform parameter transfer training on the initial network model of the multiple initial regions based on the similarity of the multiple data samples, the first engineering cost prediction model and the engineering cost data training samples of other initial regions, to obtain multiple second engineering cost prediction models. The cost prediction module is used to obtain the predicted cost of the received engineering cost consulting data based on the first engineering cost prediction model and the plurality of second engineering cost prediction models.
2. The engineering cost consulting management system based on big data according to claim 1, characterized in that, The step of obtaining the similarity of multiple data samples based on the engineering cost data training samples of the first region and the remaining engineering cost data training samples of the initial region includes: The engineering cost data training samples of the first region are used as the target domain, and the remaining engineering cost data training samples of the initial region are used as multiple source domains. The domain similarity between the multiple source domains and the target domain is obtained, and the highest domain similarity is stored as the data sample similarity. If the number of source domains is greater than a preset threshold, the engineering cost data training samples of the initial region corresponding to the data sample similarity are determined as target domains, the domain similarity between the remaining source domains and target domains is updated, and the highest domain similarity is stored as data sample similarity.
3. The engineering cost consulting management system based on big data according to claim 2, characterized in that, The domain similarity between the source domain and the target domain is obtained through the following steps: Obtain the maximum mean difference between the source domain and the target domain; The domain similarity is obtained based on the maximum mean difference; wherein, the smaller the maximum mean difference, the greater the domain similarity.
4. The engineering cost consulting management system based on big data according to claim 3, characterized in that, The step of obtaining the maximum mean difference between the source domain and the target domain includes: The maximum mean difference can be obtained using the following formula: Among them, MMD(X) S ,X T X is the maximum mean difference; S For the source domain; X T Let be the target domain; φ(·) be the mapping function; m be the number of training samples in the source domain; and n be the number of training samples in the target domain. Let i be the i-th sample data of the training samples in the source domain; Let j be the j-th sample data of the training samples for the target domain.
5. The engineering cost consulting management system based on big data according to claim 2, characterized in that, The step of performing parameter transfer training on the initial network models of the multiple initial regions based on the similarity of the multiple data samples, the first engineering cost prediction model, and the engineering cost data training samples of other initial regions to obtain multiple second engineering cost prediction models includes: If the target domain of the data sample similarity corresponds to the engineering cost prediction model, and the source domain of the data sample similarity corresponds to the initial network model, the model parameters of the engineering cost prediction model are transferred to the initial network model to obtain a transfer learning model; the engineering cost prediction model includes a first engineering cost prediction model and a second engineering cost prediction model. The transfer learning model is trained based on the sample data of the source domain; the second engineering cost prediction model for the initial region corresponding to the source domain is obtained.
6. The engineering cost consulting management system based on big data according to claim 1, characterized in that, The step of obtaining the predicted cost of the received engineering cost consulting data based on the first engineering cost prediction model and the plurality of second engineering cost prediction models includes: The first engineering cost prediction model and the plurality of second engineering cost prediction models are deployed to the corresponding regional servers in the initial region as engineering cost prediction edge models; The engineering cost consulting data received by the regional server is input into the corresponding engineering cost prediction edge model to obtain the predicted cost.
7. The engineering cost consulting management system based on big data according to claim 1, characterized in that, The step of obtaining the predicted cost of the received engineering cost consulting data based on the first engineering cost prediction model and the plurality of second engineering cost prediction models includes: Identify the target project parameters and construction area in the received engineering cost consulting data; Based on the correspondence between the construction area and the multiple initial areas, the target project cost prediction model is obtained from the first project cost prediction model and the multiple second project cost prediction models; The target project parameters are input into the target project cost prediction model to obtain the predicted cost.
8. The engineering cost consulting management system based on big data according to claim 6 or 7, characterized in that, After obtaining the predicted cost, the steps include: The predicted cost is sent to the terminal device that uploaded the engineering cost consulting data.
9. The engineering cost consulting management system based on big data according to claim 6 or 7, characterized in that, After obtaining the predicted cost, the steps include: Send the engineering cost consulting data and the predicted cost to the designated email address.
10. The engineering cost consulting management system based on big data according to claim 9, characterized in that, The steps of sending the engineering cost consulting data and the predicted cost to the designated email address include: The engineering cost consulting data and the predicted cost are encrypted and compressed according to the compression password to obtain encrypted and compressed cost consulting data. The compressed password is sent to the terminal device that uploads the engineering cost consulting data, and the encrypted and compressed cost consulting data is sent to the designated email address.