A neural network model cost estimation method, device and electronic equipment

Abstract

A neural network model cost budgeting method, device and electronic equipment relate to the field of engineering cost budgeting. The method includes: in response to a user's engineering cost budgeting operation for a target project, obtaining a project list corresponding to the target project, the project list being a list of target materials required for the target project; obtaining price influencing factors corresponding to the target materials and an engineering feature group corresponding to the target project; according to the engineering feature group, obtaining a neural network budget model corresponding to the engineering feature group in an engineering cost preset model database, the engineering cost preset model database storing the correspondence between the engineering feature group and the neural network budget model; according to the project list and the price influencing factors, obtaining the engineering cost budget corresponding to the target project through the neural network budget model. The technical solution of the present application solves the problem that it is time-consuming and inaccurate to predict the cost of the target project through personal experience.

Description

Technical Field

[0001] The present application relates to the field of engineering cost budgeting, and in particular to a neural network model cost budgeting method, device and electronic equipment. Background Art

[0002] The construction cost is a key factor in the management of the entire construction and engineering project. It directly affects the financial planning, resource allocation and final feasibility of the project. Therefore, the budget of the construction cost is particularly important in the project planning and execution stage.

[0003] Nowadays, when making a budget for construction costs, most people rely on the experience of project managers or cost engineers to estimate the cost. This method predicts the cost of the target project based on the cost data of similar projects in the past and personal experience. However, when facing a large-scale and technically complex target project, it takes a lot of time to collect data only through the above method. In addition, predicting the cost of the target project based on personal experience cannot fully take into account the price impact caused by various factors such as market conditions, material prices and labor costs, which greatly reduces the accuracy of the construction cost budget. Therefore, there are problems such as high time consumption and inaccurate construction cost budget.

[0004] Therefore, there is an urgent need for a neural network model cost estimation method, device and electronic equipment. Summary of the invention

[0005] The present application provides a neural network model cost estimation method, device and electronic equipment, which solve the problem that it is time-consuming and inaccurate to estimate the cost of a target project through personal experience.

[0006] In a first aspect of the present application, a neural network model cost budgeting method is provided, the method comprising: in response to a user's engineering cost budgeting operation for a target project, obtaining a project list corresponding to the target project, the project list being a list of target materials required for the target project; obtaining price influencing factors corresponding to the target materials and an engineering feature group corresponding to the target project; according to the engineering feature group, obtaining a neural network budgeting model corresponding to the engineering feature group in an engineering cost preset model database, the engineering cost preset model database storing the correspondence between the engineering feature group and the neural network budgeting model; according to the project list and the price influencing factors, obtaining the engineering cost budget corresponding to the target project through the neural network budgeting model.

[0007] By adopting the above technical scheme, the target materials required for the target project are obtained according to the project list corresponding to the target project, so as to obtain the corresponding price influencing factors according to the target materials, and the engineering feature group corresponding to the target project is obtained, so as to obtain the neural network budget model corresponding to the engineering feature group in the engineering cost preset model database according to the engineering feature group, so as to obtain the engineering cost budget corresponding to the target project through the neural network budget model according to the project list and the price influencing factors, thereby solving the problem of high cost and inaccurate engineering cost budget predicted by personal experience.

[0008] Optionally, before obtaining the neural network budget model corresponding to the engineering feature group in the engineering cost preset model database according to the engineering feature group, constructing the engineering cost preset model database, specifically including: obtaining multiple historical target projects and historical engineering feature groups corresponding to the multiple historical target projects, one historical target project corresponds to one historical engineering feature group; obtaining multiple neural network budget models, constructing a correspondence between multiple neural network budget models and multiple historical engineering feature groups, one neural network budget model corresponds to one historical engineering feature group; and saving the correspondence between multiple neural network budget models and multiple historical engineering feature groups in the engineering cost preset model database.

[0009] By adopting the above technical solution, a database of preset engineering cost models is constructed, and the correspondence between multiple neural network budget models and multiple historical engineering feature groups is constructed. One neural network budget model corresponds to one historical engineering feature group, so that the preset engineering cost model corresponding to the target project can be determined through the historical engineering feature group according to the correspondence.

[0010] Optionally, before obtaining the neural network budget model corresponding to the engineering feature group in the engineering cost preset model database according to the engineering feature group, a neural network budget model is constructed, specifically including: obtaining historical engineering cost data corresponding to the historical target project; the historical engineering cost data includes historical engineering lists, historical price influencing factors and historical engineering feature groups; and constructing a neural network budget model based on the historical engineering cost data.

[0011] By adopting the above technical solution, by obtaining the historical engineering cost data corresponding to the historical target project, and the historical engineering cost data includes the historical engineering list, historical price influencing factors and historical engineering feature groups, it is convenient to build a neural network budget model based on the historical engineering cost data.

[0012] Optionally, based on the engineering feature group, a neural network budget model corresponding to the engineering feature group is obtained in the engineering cost preset model database, specifically including: obtaining a first historical engineering feature group and a first neural network budget model corresponding to the first historical engineering feature group, obtaining a second historical engineering feature group and a second neural network budget model corresponding to the second historical engineering feature group, the first historical engineering feature group and the second historical engineering feature group being any two different feature groups among multiple historical engineering feature groups; respectively calculating a first similarity between the engineering feature group and the first historical engineering feature group and a second similarity between the engineering feature group and the second historical engineering feature group; if it is confirmed that the first similarity is greater than the second similarity; then using the first neural network budget model corresponding to the first historical engineering feature group as the neural network budget model corresponding to the engineering feature group.

[0013] By adopting the above technical scheme, the similarity between the engineering feature group corresponding to the target project and the historical engineering feature group in the engineering cost preset model database is calculated, the historical engineering feature group includes a first historical engineering feature group and a second historical engineering feature group, the first historical engineering feature group and the second historical engineering feature group are any two different feature groups among multiple historical engineering feature groups, and it is confirmed that the first similarity is greater than the second similarity, that is, it is determined that the first similarity calculated between the first historical engineering feature group and the engineering feature group corresponding to the target project is the largest among all similarities, so that the historical engineering feature group with the largest similarity, that is, the neural network budget model corresponding to the first historical engineering feature group, is used as the neural network budget model corresponding to the target project.

[0014] Optionally, according to the project list and price influencing factors, the project cost budget corresponding to the target project is obtained through the neural network budget model, specifically including: calculating the project cost budget through the following formula: ;

[0015] Among them, C is the project cost budget, Q i is the demand for the i-th material in the target material, P i is the basic unit price of the i-th material. The basic unit price is the unit price of the i-th material without considering price influencing factors. j，i A is the adjustment coefficient of the jth price influencing factor affecting the price of the i-th material, FEA It is the characteristic adjustment coefficient, which is used to reflect the impact of the engineering characteristic group on the engineering cost budget.

[0016] By adopting the above technical solution, by obtaining the demand quantity of the i-th material in the target material, the basic unit price of the i-th material, the adjustment coefficient of the j-th price influencing factor affecting the price of the i-th material, and the characteristic adjustment coefficient, the characteristic adjustment coefficient is used to reflect the impact of the engineering characteristic group on the engineering cost budget, thereby calculating the engineering cost budget corresponding to the target project.

[0017] Optionally, after obtaining the project cost budget corresponding to the target project through the neural network budget model based on the project list and price influencing factors, the method also includes: obtaining the actual cost corresponding to the target project; obtaining the cost difference between the actual cost and the preset project cost; judging whether the cost difference is greater than the preset cost difference; if the cost difference is greater than the preset cost difference, obtaining the deviation factor between the actual cost and the preset project cost; and adjusting the neural network budget model according to the deviation factor.

[0018] By adopting the above technical solution, the cost difference between the actual cost and the preset project cost is obtained, and it is determined whether the cost difference is greater than the preset cost difference. When the cost difference is greater than the preset cost difference, the deviation factor between the actual cost and the preset project cost is obtained, so as to adjust the neural network budget model according to the deviation factor.

[0019] Optionally, after obtaining the engineering cost budget corresponding to the target project through the neural network budget model according to the project list and price influencing factors, the method also includes: responding to the user's progress management operation for the target project, the progress management operation includes viewing the project list, viewing the target materials, and viewing the engineering cost budget; obtaining the permission information input by the user; if the permission information is confirmed to be the preset permission information, opening the user to the permission of the progress management operation of the target project.

[0020] By adopting the above technical solution, the permission information input by the user is obtained to perform permission verification, that is, when the user attempts to perform progress management operations, the server prompts the user to enter permission information. Only when the permission information entered by the user is consistent with the preset permission information, the user is allowed to access the progress management operations of the project. The progress management operations include viewing the project list, material information, and project cost budget, etc., thereby ensuring that only authorized users can access sensitive information, thereby ensuring the security of project information.

[0021] In a second aspect of the present application, a neural network model cost estimation device is provided, the device comprising an acquisition module and a processing module, wherein:

[0022] An acquisition module is used to respond to the user's engineering cost budget operation for the target project, obtain the project list corresponding to the target project, which is a list of target materials required for the target project; obtain the price influencing factors corresponding to the target materials and the engineering feature group corresponding to the target project; according to the engineering feature group, obtain the neural network budget model corresponding to the engineering feature group in the engineering cost preset model database, and the engineering cost preset model database stores the correspondence between the engineering feature group and the neural network budget model.

[0023] The processing module is used to obtain the engineering cost budget corresponding to the target project through the neural network budget model according to the engineering list and price influencing factors.

[0024] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.

[0025] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to perform any of the above methods.

[0026] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0027] 1. By adopting the above technical scheme, the target materials required for the target project are obtained according to the project list corresponding to the target project, and the corresponding price influencing factors are obtained according to the target materials. The engineering feature group corresponding to the target project is obtained, and according to the engineering feature group, a neural network budget model corresponding to the engineering feature group is obtained in the engineering cost preset model database. According to the project list and the price influencing factors, the engineering cost budget corresponding to the target project is obtained through the neural network budget model, thereby solving the problem of high cost and inaccurate engineering cost budget predicted by personal experience.

[0028] 2. By constructing a database of preset engineering cost models, and building the correspondence between multiple neural network budget models and multiple historical engineering feature groups, one neural network budget model corresponds to one historical engineering feature group, so that the preset engineering cost model corresponding to the target project can be determined through the historical engineering feature group based on the correspondence.

[0029] 3. By obtaining the historical engineering cost data corresponding to the historical target project, and the historical engineering cost data includes the historical engineering list, historical price influencing factors and historical engineering feature groups, it is convenient to build a neural network budget model based on the historical engineering cost data. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a flowchart of a neural network model cost estimation method provided in an embodiment of the present application;

[0031] Figure 2 It is a module schematic diagram of a neural network model cost estimation device provided in an embodiment of the present application;

[0032] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0033] Explanation of the reference numerals: 21, acquisition module; 22, processing module; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0034] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0035] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more listed items.

[0036] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0037] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0038] The construction cost is a key factor in the management of the entire construction and engineering project. It directly affects the financial planning, resource allocation and final feasibility of the project. Therefore, the budget of the construction cost is particularly important in the project planning and execution stage.

[0039] Nowadays, when making a budget for construction costs, most people rely on the experience of project managers or cost engineers to estimate the cost. This method predicts the cost of the target project based on the cost data of similar projects in the past and personal experience. However, when facing a large-scale and technically complex target project, it takes a lot of time to collect data only through the above method. In addition, predicting the cost of the target project based on personal experience cannot fully take into account the price impact caused by various factors such as market conditions, material prices and labor costs, which greatly reduces the accuracy of the construction cost budget. Therefore, there are problems such as high time consumption and inaccurate construction cost budget.

[0040] Therefore, there is an urgent need for a neural network model cost estimation method, device and electronic equipment.

[0041] Please refer to Figure 1 , which shows a flow chart of a neural network model cost estimation method provided in an embodiment of the present application. The method is applied to a server. The flow chart mainly includes the following steps: S101 to S104.

[0042] Step S101, in response to a user's engineering cost budget operation for a target project, a project list corresponding to the target project is obtained, where the project list is a list of target materials required for the target project.

[0043] Specifically, when the user performs a construction cost budget operation for the target project, the server obtains the project list corresponding to the target project. The project list is used to record all materials required in the target project, including but not limited to cement, bricks, steel bars, wood, glass and other materials and resources. It should be noted that in the present application, the target project is not the entire construction project, but a project node in the entire construction project, that is, the entire construction project can be divided into project nodes. The present application does not limit the division of project nodes, and can be divided according to the specific needs of the construction project. For example, for a simple residential construction project, it can be divided into multiple project nodes according to the sequence of construction steps, that is, the target project is any one of the multiple project nodes. The target project includes one or more construction measures, and multiple target projects include but are not limited to: foundation construction, foundation construction includes excavation, leveling of foundation pits, laying of concrete foundations and other construction measures; structure construction, structure construction includes The following are the construction measures: purchase and installation of steel bars, pouring of concrete walls, etc.; roofing works, including the construction of roof frames, laying of roof tiles, etc.; external works, including external wall masonry work, external wall paint or painting, etc.; interior decoration, including interior wall plastering and painting, floor laying, etc.; plumbing and electrical works, including the installation of water pipes and drainage systems, wiring and installation of switches and sockets, etc.; door and window installation, including the purchase and installation of doors, purchase and installation of windows, etc.; fixture and equipment installation, including kitchen cabinets and equipment installation, bathroom sanitary facilities installation, etc. Among the above multiple target projects, each target project has a unique corresponding project list, which is a list of all target materials required for the corresponding target project.

[0044] Step S102, obtaining the price influencing factors corresponding to the target material and the engineering feature group corresponding to the target engineering.

[0045] Specifically, all target materials required in the project list of the target project are obtained, and the price influencing factors corresponding to each target material are obtained. One target material may correspond to one or more price influencing factors, wherein the price influencing factors include but are not limited to supply and demand relationships, changes in raw material costs, transportation costs, etc. An engineering feature group corresponding to the target project is obtained. The engineering feature group is a collection of multiple features of the target project, that is, different engineering nodes correspond to different engineering feature groups, and one engineering node corresponds to one engineering feature group. Multiple features of the target project can be extracted according to the division of engineering nodes. For example, for the foundation construction in step S101, the multiple features that can be extracted are concrete type (such as ordinary, sulfate-resistant or high-performance concrete); steel bar specifications (such as diameter and grade); foundation cushion materials (such as gravel, sand or special fillers); waterproof material types (such as waterproof membranes or coatings), etc., and the above multiple features are used as the engineering feature group corresponding to the foundation construction; for the structural construction in step S101, the multiple features that can be extracted are concrete type for the main structure (such as high-strength or lightweight concrete); steel type for the main load-bearing structure (such as steel for beams and columns); exterior wall materials (such as glass, metal plates or bricks); roofing materials (such as tiles, metal roofs or waterproof coatings), etc., and the above multiple features are used as the engineering feature group corresponding to the structural construction.

[0046] Step S103, according to the engineering feature group, obtain the neural network budget model corresponding to the engineering feature group in the engineering cost preset model database, and the engineering cost preset model database stores the corresponding relationship between the engineering feature group and the neural network budget model.

[0047] Specifically, a neural network budget model corresponding to the engineering feature group is obtained in the engineering cost preset model database, and the engineering cost preset model database is used to store the correspondence between multiple engineering feature groups and multiple neural network budget models, and one engineering feature group corresponds to one neural network budget model. Since different engineering nodes correspond to different engineering feature groups, and one engineering node corresponds to one engineering feature group, the neural network budget model corresponding to the engineering feature group is obtained in the engineering cost preset model database, that is, the neural network budget model used for engineering cost budgeting of the target project is obtained.

[0048] In a possible implementation, step S103 also includes: constructing a preset model database for engineering cost, specifically including: obtaining multiple historical target projects and historical engineering feature groups corresponding to the multiple historical target projects, one historical target project corresponds to one historical engineering feature group; obtaining multiple neural network budget models, constructing a correspondence between multiple neural network budget models and multiple historical engineering feature groups, one neural network budget model corresponds to one historical engineering feature group; and saving the correspondence between multiple neural network budget models and multiple historical engineering feature groups in the preset model database for engineering cost.

[0049] Specifically, in this embodiment, a historical target project corresponds to a historical project feature group, and a historical project feature group corresponds to a neural network budget model, that is, the server simultaneously constructs the correspondence between the historical target project, the historical project feature group, and the neural network budget model. The historical target project is a completed target project. In step S101, the target project is not the entire construction project, but a project node in the entire construction project, that is, the historical target project is a completed project node among multiple completed projects. At this time, the server extracts features from the historical target project and extracts the historical project feature group corresponding to the historical target project. The historical project feature group includes but is not limited to the project scale, geographical location, and project complexity in the historical target project. A corresponding neural network budget model is constructed for each historical project feature group, that is, each neural network budget model is specially tailored for project nodes with similar conditions and features, that is, the number of neural network budget models is the same as the number of project nodes in step S101.

[0050] In a possible implementation, step S103 also includes: obtaining historical project cost data corresponding to the historical target project; the historical project cost data includes a historical project list, historical price influencing factors, and a historical project feature group; and constructing a neural network budget model based on the historical project cost data.

[0051] Specifically, the steps for constructing the neural network budget model are as follows: Use the actual cost data related to each historical engineering feature group as training data. The training data should include the material demand in each historical target project and the price influencing factors of each material; Train the neural network budget model through supervised learning methods. The neural network budget model predicts the engineering cost under similar conditions in the future by learning the relationship between features and costs in historical data; Optimize the neural network budget model to improve its accuracy, and verify it with an independent data set to ensure its generalization ability. Construct the correspondence between the historical engineering feature group and the neural network budget model and save it in the engineering cost preset model database.

[0052] For example, it is assumed that the division of the engineering nodes in a project is divided according to the example in step S101, and is divided into foundation construction, structure construction, roof construction, external engineering, interior decoration, pipeline and electrical engineering, door and window installation, fixture and equipment installation. Then the server obtains multiple completed projects, and extracts the historical engineering feature group for the foundation construction, structure construction, roof construction, external engineering, interior decoration, pipeline and electrical engineering, door and window installation, fixture and equipment installation in the multiple completed projects, that is, extracts the historical engineering feature group corresponding to each different historical target project. Taking the foundation construction historical target project as an example, the historical engineering feature group corresponding to the foundation construction in multiple completed projects is extracted, and the training data includes but is not limited to the project scale, geographical location, and project complexity of the foundation construction. The historical engineering feature group corresponding to the foundation construction includes but is not limited to the type of steel bar, the type of concrete, the price of steel bar, the price of concrete, the factors affecting the price of steel bar, and the factors affecting the price of concrete. The neural network budget model corresponding to the foundation construction is constructed through the above historical engineering feature group, and the corresponding relationship between the historical engineering feature group and the neural network budget model is constructed, and saved in the engineering cost preset model database.

[0053] In a possible implementation, step S103 also includes: obtaining a first historical engineering feature group and a first neural network budget model corresponding to the first historical engineering feature group, obtaining a second historical engineering feature group and a second neural network budget model corresponding to the second historical engineering feature group, the first historical engineering feature group and the second historical engineering feature group being any two different feature groups among a plurality of historical engineering feature groups; respectively calculating a first similarity between the engineering feature group and the first historical engineering feature group and a second similarity between the engineering feature group and the second historical engineering feature group; if it is confirmed that the first similarity is greater than the second similarity; then using the first neural network budget model corresponding to the first historical engineering feature group as the neural network budget model corresponding to the engineering feature group.

[0054] Specifically, the server needs to determine the neural network budget model corresponding to the target project in the engineering cost preset model database. The server first extracts the engineering feature group corresponding to the target project, and then calculates the similarity between the engineering feature group and each historical engineering feature group, and determines the neural network budget model corresponding to the historical engineering feature group with the greatest similarity as the neural network budget model corresponding to the target project. When performing similarity calculation, it is necessary to extract multiple engineering features in the target project as the engineering feature group corresponding to the target project, and perform similarity calculations on each engineering feature with the historical engineering feature group to obtain multiple similarity scores, and then synthesize the similarity scores of each engineering feature to obtain the similarity between the target engineering feature group and each historical engineering feature group.

[0055] For example, assuming that in the target project, three engineering features are obtained through feature extraction, namely features A, B, and C, then features A, B, and C are used as the engineering feature group corresponding to the target project. At this time, the similarities between features A, B, and C and the first historical engineering feature group and the first historical engineering feature group are calculated respectively. It is assumed that the similarities calculated with the first historical engineering feature group are 40%, 92%, and 94%, respectively; it is assumed that the similarities calculated with the second historical engineering feature group are 73%, 43%, and 75%, respectively. During the calculation process, if the obtained similarity is less than the preset similarity, it will be directly filtered. If the preset similarity is set to 70%, the preset similarity is set according to the actual needs of different target projects, and this application does not limit the setting of the preset similarity. Through the filtering operation, the similarities calculated with the first historical engineering feature group are 92% and 94% respectively, and the similarities calculated with the second historical engineering feature group are 73% and 75% respectively. Then, the similarity scores after filtering are calculated, and the first similarity is 93%> the second similarity is 74%. Therefore, the first neural network budget model is used as the neural network budget model corresponding to the engineering feature group.

[0056] In a possible implementation, step S103 further includes: calculating the project cost budget by the following formula: ;

[0057] Among them, C is the project cost budget, Q i is the demand for the i-th material in the target material, P i is the basic unit price of the i-th material. The basic unit price is the unit price of the i-th material without considering price influencing factors. j，i A is the adjustment coefficient of the jth price influencing factor affecting the price of the i-th material, FEA It is the characteristic adjustment coefficient, which is used to reflect the impact of the engineering characteristic group on the engineering cost budget.

[0058] Specifically, when calculating the project cost budget C, it is necessary to comprehensively consider the demand for all target materials in the target project and the basic single pieces, as well as the price influencing factors corresponding to each target material, including but not limited to supply chain changes, seasonal fluctuations, policy changes, etc. The impact of each factor on the price is reflected in the form of a coefficient. In addition, it is also necessary to consider the corresponding engineering feature group in the target project, and calculate the feature adjustment coefficient based on the impact of the project scale, geographical location, project complexity, etc. on the basic cost.

[0059] Step S104, according to the project list and price influencing factors, obtain the project cost budget corresponding to the target project through the neural network budget model.

[0060] Specifically, the project list and price influencing factors are input into the neural network budget model, that is, the project list is used to record all materials required for the target project and the price influencing factors corresponding to each target material are input into the neural network budget model to obtain the engineering cost budget corresponding to the target project.

[0061] In a possible implementation, step S104 also includes: obtaining the actual cost corresponding to the target project; obtaining the cost difference between the actual cost and the preset project cost; determining whether the cost difference is greater than the preset cost difference; if the cost difference is greater than the preset cost difference, obtaining the deviation factor between the actual cost and the preset project cost; and adjusting the neural network budget model according to the deviation factor.

[0062] Specifically, after the target project is completed, its actual cost is collected. The project cost predicted by the neural network model is compared with the actual cost, and the difference between the two is calculated. Cost difference = actual cost - predicted cost. Determine whether the calculated cost difference exceeds the preset cost difference. The preset cost difference is the allowable error range of the target project cost budget, which can be set according to actual needs. This application does not limit the setting of the preset cost difference. If the cost difference exceeds the preset cost difference, this indicates that there is a significant deviation between the prediction model and the actual situation. At this time, it is necessary to obtain the deviation factor and adjust the neural network budget model. The adjustment steps are as follows: Deviation factor analysis: Analyze the reasons for the difference between the actual cost and the predicted cost. Possible reasons include market price changes, design changes, construction challenges, changes in resource utilization, etc.; Model adjustment: According to the results of the deviation analysis, adjust the parameters or structure of the neural network budget model. For example, if it is found that the price fluctuation of a certain material is the main reason, the model may need to be modified to pay more attention to the impact of the price of this material. Retrain the neural network budget model with new data to ensure that it better reflects current market and construction conditions; revalidate and test: The adjusted neural network budget model needs to be validated on an independent test set to ensure its improved accuracy and generalization ability. Continuously monitor the performance of the neural network budget model to ensure its long-term applicability.

[0063] In a possible implementation, step S104 also includes: responding to the user's progress management operation for the target project, the progress management operation includes viewing the project list, viewing the target materials, and viewing the project cost budget; obtaining the permission information input by the user; if the permission information is confirmed to be the preset permission information, opening the user to the permission of the progress management operation of the target project.

[0064] Specifically, the progress management operation includes viewing the project list, target materials, and project cost budget. Obtain the permission information entered by the user for permission verification, that is, when the user attempts to perform a progress management operation, the server prompts the user to enter the permission information. The permission information includes but is not limited to passwords, digital certificates, biometric data, etc. This application does not limit the specific form of the permission information. The server compares and verifies the permission information entered by the user with the preset permission information. If the permission information entered by the user is consistent with the preset permission information, it indicates that the user has the authority to perform related operations. After confirming the user's authority, the server allows the user to access the project's progress management operations, including viewing the project list, material information, and project cost budget. Through the above steps, the server can strictly manage the user's permissions to ensure that only authorized users can access sensitive information, thereby ensuring the security of project information.

[0065] The present application adopts the above method, obtains the target materials required for the target project according to the project list, obtains the corresponding price influencing factors according to the target materials, and obtains the project feature group corresponding to the target project, and obtains the neural network budget model corresponding to the project feature group in the project cost preset model database according to the project feature group, so as to obtain the project cost budget corresponding to the target project through the neural network budget model according to the project list and the price influencing factors, thereby solving the problem of high cost and inaccurate project cost budget predicted by personal experience.

[0066] Please refer to Figure 2 , which shows a module schematic diagram of a neural network model cost estimation device provided in an embodiment of the present application, the device is a server, and the server includes an acquisition module 21 and a processing module 22, wherein,

[0067] The acquisition module 21 is used to respond to the user's engineering cost budget operation for the target project, obtain the project list corresponding to the target project, and the project list is a list of target materials required for the target project; obtain the price influencing factors corresponding to the target materials and the engineering feature group corresponding to the target project; according to the engineering feature group, obtain the neural network budget model corresponding to the engineering feature group in the engineering cost preset model database, and the engineering cost preset model database stores the correspondence between the engineering feature group and the neural network budget model.

[0068] The processing module 22 is used to obtain the engineering cost budget corresponding to the target project through the neural network budget model according to the engineering list and price influencing factors.

[0069] In a possible implementation, the acquisition module 21 is used to construct an engineering cost preset model database before obtaining the neural network budget model corresponding to the engineering feature group in the engineering cost preset model database according to the engineering feature group, specifically including: obtaining multiple historical target projects and historical engineering feature groups corresponding to the multiple historical target projects, one historical target project corresponds to one historical engineering feature group; obtaining multiple neural network budget models, constructing a correspondence between multiple neural network budget models and multiple historical engineering feature groups, one neural network budget model corresponds to one historical engineering feature group; and saving the correspondence between multiple neural network budget models and multiple historical engineering feature groups in the engineering cost preset model database.

[0070] In a possible implementation, the acquisition module 21 is used to construct a neural network budget model before obtaining the neural network budget model corresponding to the engineering feature group in the engineering cost preset model database based on the engineering feature group, specifically including: obtaining historical engineering cost data corresponding to the historical target project; the historical engineering cost data includes historical engineering lists, historical price influencing factors and historical engineering feature groups; and constructing a neural network budget model based on the historical engineering cost data.

[0071] In a possible implementation, the acquisition module 21 is used to obtain a neural network budget model corresponding to an engineering feature group in a preset model database of engineering cost according to the engineering feature group, specifically including: obtaining a first historical engineering feature group and a first neural network budget model corresponding to the first historical engineering feature group, obtaining a second historical engineering feature group and a second neural network budget model corresponding to the second historical engineering feature group, the first historical engineering feature group and the second historical engineering feature group being any two different feature groups among a plurality of historical engineering feature groups; respectively calculating a first similarity between the engineering feature group and the first historical engineering feature group and a second similarity between the engineering feature group and the second historical engineering feature group; if it is confirmed that the first similarity is greater than the second similarity; then using the first neural network budget model corresponding to the first historical engineering feature group as the neural network budget model corresponding to the engineering feature group.

[0072] In a possible implementation, the acquisition module 21 is used to obtain the engineering cost budget corresponding to the target project through a neural network budget model according to the engineering list and price influencing factors, specifically including: calculating the engineering cost budget through the following formula: ;

[0073] Among them, C is the project cost budget, Q i is the demand for the i-th material in the target material, P i is the basic unit price of the i-th material. The basic unit price is the unit price of the i-th material without considering price influencing factors. j，iA is the adjustment coefficient of the jth price influencing factor affecting the price of the i-th material, FEA It is the characteristic adjustment coefficient, which is used to reflect the impact of the engineering characteristic group on the engineering cost budget.

[0074] In one possible implementation, the processing module 22 is used to obtain the project cost budget corresponding to the target project through the neural network budget model according to the project list and price influencing factors. The method also includes: obtaining the actual cost corresponding to the target project; obtaining the cost difference between the actual cost and the preset project cost; determining whether the cost difference is greater than the preset cost difference; if the cost difference is greater than the preset cost difference, obtaining the deviation factor between the actual cost and the preset project cost; and adjusting the neural network budget model according to the deviation factor.

[0075] In one possible implementation, the processing module 22 is used to obtain the project cost budget corresponding to the target project through a neural network budget model based on the project list and price influencing factors. The method also includes: responding to the user's progress management operation for the target project, the progress management operation includes viewing the project list, viewing the target materials, and viewing the project cost budget; obtaining the permission information input by the user; if the permission information is confirmed to be the preset permission information, opening the user to the permission of the progress management operation of the target project.

[0076] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0077] The present application also provides an electronic device. Figure 3 , Figure 3 30 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include: at least one processor 301, at least one communication bus 302, a user interface 303, at least one network interface 304, and a memory 305.

[0078] The communication bus 302 is used to realize the connection and communication between these components.

[0079] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0080] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0081] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0082] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , as a computer storage medium, the memory 305 may include an operating system, a network communication module, a user interface module, and a neural network model cost estimation application.

[0083] exist Figure 3 In the electronic device shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the neural network model cost budget application stored in the memory 305. When executed by one or more processors 301, the electronic device executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0084] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0085] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0086] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0087] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0088] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0089] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0090] The above are only exemplary embodiments disclosed in this application, and the scope of the disclosure of this application cannot be limited by this. That is, any equivalent changes and modifications made according to the teachings disclosed in this application are still within the scope of the disclosure of this application. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other implementation schemes disclosed in this application.

[0091] This application is intended to cover any modifications, uses or adaptive changes disclosed in this application, which follow the general principles disclosed in this application and include common knowledge or customary technical means in the technical field not recorded in this application.

Claims

1. A neural network model cost estimation method, characterized in that: The method comprises: In response to a user's engineering cost budget operation for a target project, a project list corresponding to the target project is obtained, where the project list is a list of target materials required for the target project; Obtaining price influencing factors corresponding to the target material and an engineering feature group corresponding to the target engineering; According to the engineering feature group, a neural network budget model corresponding to the engineering feature group is obtained from an engineering cost preset model database, wherein the engineering cost preset model database stores a correspondence between the engineering feature group and the neural network budget model; According to the project list and the price influencing factors, the project cost budget corresponding to the target project is obtained through the neural network budget model. Before acquiring the neural network budget model corresponding to the engineering feature group in the engineering cost preset model database according to the engineering feature group, constructing the engineering cost preset model database specifically includes: Acquire a plurality of historical target projects and a plurality of historical project feature groups corresponding to the historical target projects, wherein one historical target project corresponds to one historical project feature group; Acquire a plurality of the neural network budget models, and construct a correspondence between the plurality of neural network budget models and a plurality of the historical engineering feature groups, wherein one neural network budget model corresponds to one historical engineering feature group; The corresponding relationship between the plurality of neural network budget models and the plurality of historical engineering feature groups is stored in the engineering cost preset model database, Before acquiring the neural network budget model corresponding to the engineering feature group in the engineering cost preset model database according to the engineering feature group, constructing the neural network budget model specifically includes: Acquire historical engineering cost data corresponding to the historical target engineering; the historical engineering cost data includes a historical engineering list, historical price influencing factors, and the historical engineering feature group; Constructing the neural network budget model based on the historical engineering cost data, The obtaining, according to the project list and the price influencing factors, the project cost budget corresponding to the target project through the neural network budget model specifically includes: The project cost budget is calculated by the following formula: ； Among them, C is the project cost budget, Q i is the demand for the i-th material in the target material, P i is the basic unit price of the i-th material, which is the unit price of the i-th material without considering the price influencing factors. j，i A is the adjustment coefficient of the jth price influencing factor affecting the price of the i-th material, FEA is a feature adjustment coefficient, and the feature adjustment coefficient is used to reflect the impact of the engineering feature group on the engineering cost budget.

2. The method according to claim 1, characterized in that The step of obtaining the neural network budget model corresponding to the engineering feature group in the engineering cost preset model database according to the engineering feature group specifically includes: Obtaining a first historical engineering feature group and a first neural network budget model corresponding to the first historical engineering feature group, obtaining a second historical engineering feature group and a second neural network budget model corresponding to the second historical engineering feature group, wherein the first historical engineering feature group and the second historical engineering feature group are any two different feature groups among the plurality of historical engineering feature groups; respectively calculating a first similarity between the engineering feature group and the first historical engineering feature group and a second similarity between the engineering feature group and the second historical engineering feature group; If it is confirmed that the first similarity is greater than the second similarity, the first neural network budget model corresponding to the first historical engineering feature group is used as the neural network budget model corresponding to the engineering feature group.

3. The method according to claim 1, characterized in that After obtaining the engineering cost budget corresponding to the target project through the neural network budget model according to the engineering list and the price influencing factors, the method further includes: Obtaining the actual cost corresponding to the target project; Obtaining the difference between the actual cost and the preset cost of the project; Determining whether the cost difference is greater than a preset cost difference; If the cost difference is greater than the preset cost difference, obtaining a deviation factor between the actual cost and the preset engineering cost; The neural network budget model is adjusted according to the deviation factor.

4. The method according to claim 1, characterized in that: After obtaining the engineering cost budget corresponding to the target project through the neural network budget model according to the engineering list and the price influencing factors, the method further includes: In response to the user's progress management operation for the target project, the progress management operation includes viewing the project list, viewing the target materials, and viewing the project cost budget; Obtaining permission information input by the user; If it is confirmed that the permission information is the preset permission information, the permission of the progress management operation of the target project is opened to the user.

5. A neural network model cost estimation device, characterized in that: The device comprises an acquisition module (21) and a processing module (22), wherein: The acquisition module (21) is used to respond to the user's engineering cost budget operation for the target project, acquire the engineering list corresponding to the target project, the engineering list is a list of target materials required for the target project; acquire the price influencing factors corresponding to the target materials and the engineering feature group corresponding to the target project; and acquire the neural network budget model corresponding to the engineering feature group in the engineering cost preset model database according to the engineering feature group, the engineering cost preset model database storing the corresponding relationship between the engineering feature group and the neural network budget model; The processing module (22) is used to obtain the engineering cost budget corresponding to the target project through the neural network budget model according to the engineering list and the price influencing factors. The acquisition module (21) is used to construct the engineering cost preset model database before acquiring the neural network budget model corresponding to the engineering feature group in the engineering cost preset model database according to the engineering feature group, and specifically includes: Acquire a plurality of historical target projects and a plurality of historical project feature groups corresponding to the historical target projects, wherein one historical target project corresponds to one historical project feature group; Acquire a plurality of the neural network budget models, and construct a correspondence between the plurality of neural network budget models and a plurality of the historical engineering feature groups, wherein one neural network budget model corresponds to one historical engineering feature group; The corresponding relationship between the plurality of neural network budget models and the plurality of historical engineering feature groups is stored in the engineering cost preset model database, The acquisition module (21) is used to construct the neural network budget model before acquiring the neural network budget model corresponding to the engineering feature group in the engineering cost preset model database according to the engineering feature group, and specifically includes: Acquire historical engineering cost data corresponding to the historical target engineering; the historical engineering cost data includes a historical engineering list, historical price influencing factors, and the historical engineering feature group; Constructing the neural network budget model based on the historical engineering cost data, The acquisition module (21) is used to acquire the engineering cost budget corresponding to the target project through the neural network budget model according to the engineering list and the price influencing factors, and specifically includes: The project cost budget is calculated by the following formula: ； Among them, C is the project cost budget, Q i is the demand for the i-th material in the target material, P i is the basic unit price of the i-th material, which is the unit price of the i-th material without considering the price influencing factors. j，i A is the adjustment coefficient of the jth price influencing factor affecting the price of the i-th material, FEA is a feature adjustment coefficient, and the feature adjustment coefficient is used to reflect the impact of the engineering feature group on the engineering cost budget.

6. An electronic device, characterized in that: The electronic device comprises a processor (301), a communication bus (302), a user interface (303), a network interface (304) and a memory (305), wherein the memory (305) is used to store instructions, the user interface (303) and the network interface (304) are used to communicate with other devices, and the processor (301) is used to execute the instructions stored in the memory (305) so that the electronic device executes the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 4 is performed.

Images