Highway bridge engineering cost measuring and calculating system and method based on big data

Abstract

The invention relates to the technical field of engineering cost calculation, in particular to a highway bridge engineering cost calculation system and method based on big data, and the method comprises the steps: calculating the cost data of highway bridge engineering construction materials based on the predicted consumption data of the highway bridge engineering construction materials and the minimum supply unit price data of the highway bridge engineering construction materials; inputting the collected highway bridge engineering construction drawing data into a bridge engineering construction drawing analysis model for analysis, generating highway bridge engineering construction workload data, matching the highway bridge engineering construction workload data with construction process unit engineering amount labor cost data, generating highway bridge engineering construction unit engineering amount labor cost data, and outputting the highway bridge engineering construction unit engineering amount labor cost data. Highway bridge engineering construction labor cost data are calculated; and performing summation processing on the highway bridge engineering construction material cost data and the highway bridge engineering construction labor cost data to generate highway bridge engineering expected cost data, and finally constructing highway bridge engineering cost measurement and calculation data to realize accurate measurement and calculation of the highway bridge engineering cost.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering cost estimation, and in particular to a highway bridge engineering cost estimation system and method based on big data. Background Art

[0002] As an important part of transportation infrastructure, the engineering cost estimation of highway bridges can effectively and intuitively show the construction costs in all aspects, and provide reasonable and reliable technical and economic guidance for construction units during the construction process.

[0003] The Chinese invention patent with publication number CN116797263B introduces a construction project cost accounting management method and system. The method accurately classifies the construction record data information of the construction project into the attribute node data information of the construction project, and determines the construction cost accounting rules through the obtained project cost influencing factors. The construction project attribute node data information is calculated according to the determined project cost accounting rules to generate the project cost accounting results. The accounting error factor is determined through the historical cost data processing experience to correct the project cost accounting results, and the closed-loop accounting results of the construction project cost are accurately obtained to realize the intelligent accounting processing of the project cost. However, it is impossible to calculate the construction project cost in advance, and it is difficult for the construction unit to intuitively display the economic expenditure of the entire construction project. Summary of the invention

[0004] 1. Technical issues to be solved

[0005] In order to solve the deficiencies in the background technology, the present invention provides a highway bridge engineering cost estimation system and method based on big data, so as to realize the accurate estimation of the highway bridge engineering cost.

[0006] (II) Technical solution

[0007] A highway bridge engineering cost estimation method based on big data includes the following steps:

[0008] S1. Collect the estimated consumption data of construction materials for highway and bridge projects;

[0009] S2. Establishing the minimum supply unit price data of highway and bridge engineering construction materials, and performing construction material cost measurement processing according to the estimated consumption data of highway and bridge engineering construction materials and the minimum supply unit price data of highway and bridge engineering construction materials, to generate highway and bridge engineering construction material cost data;

[0010] S3, collect sample data of bridge engineering construction and construct a bridge engineering construction drawing analysis model;

[0011] S4, collecting highway bridge engineering construction drawing data, performing highway bridge engineering construction workload analysis processing based on the highway bridge engineering construction drawing data and the bridge engineering construction drawing analysis model, and generating highway bridge engineering construction workload data;

[0012] S5, performing construction process matching processing on the highway bridge project construction workload data and the construction process unit construction labor cost data, generating highway bridge project construction unit construction labor cost data, and calculating the highway bridge project construction labor cost data;

[0013] S6, performing numerical sum processing on the highway bridge project construction material cost data and the highway bridge project construction labor cost data to generate expected highway bridge project cost data;

[0014] S7. Construct highway bridge project cost estimation data based on the estimated highway bridge project construction material consumption data, the highway bridge project construction workload data and the highway bridge project expected cost data, and push the data to the highway bridge project cost estimation platform.

[0015] The present invention measures the construction material cost through the estimated consumption data of the construction materials of the highway bridge project and the minimum supply unit price data of the construction materials of the highway bridge project, generates the construction material cost data of the highway bridge project, constructs the bridge project construction drawing analysis model based on the collected bridge project construction sample data, performs the highway bridge project construction workload analysis processing according to the collected highway bridge project construction drawing data and the bridge project construction drawing analysis model, generates the highway bridge project construction workload data, and performs construction process matching processing with the labor cost data of unit engineering quantity of the construction process to generate the labor cost data of unit engineering quantity of the highway bridge project, then calculates the labor cost data of the highway bridge project construction, performs numerical sum processing on the construction material cost data of the highway bridge project and the labor cost data of the highway bridge project construction to generate the expected cost data of the highway bridge project, and finally constructs the highway bridge project cost estimation data, and pushes it to the highway bridge project cost estimation platform to realize the accurate estimation of the highway bridge project cost.

[0016] Preferably, the specific steps for collecting the estimated consumption data of highway bridge construction materials are as follows:

[0017] S11. The estimated consumption quantity of different construction materials in the list of construction materials for highway and bridge projects is collected online through the highway and bridge project cost estimation platform, and the estimated consumption data set of construction materials for highway and bridge projects is obtained. A={a1, a2, …, a i ,…,a k}, where a iIt represents the estimated consumption quantity of the i-th type of construction materials in the list of construction materials for highway and bridge projects collected online through the highway and bridge project cost estimation platform, and k represents the total number of construction material types, and the construction materials include but are not limited to steel, cement, sand and gravel, admixtures, prestressed materials and waterproof materials.

[0018] Preferably, the minimum supply unit price data of highway bridge engineering construction materials is established, and the construction material cost measurement processing is performed according to the estimated consumption data of highway bridge engineering construction materials and the minimum supply unit price data of highway bridge engineering construction materials. The specific steps of generating the highway bridge engineering construction material cost data are as follows:

[0019] S21. Collect the supply unit prices given by various material suppliers for the types of construction materials corresponding to the estimated consumption data of construction materials for each highway bridge project in the estimated consumption data of construction materials for highway bridge projects online through the highway bridge project cost estimation platform, and count the minimum supply unit prices of various types of construction materials to generate the minimum supply unit price data set A' = {a'1, a'2, ..., a' i ,…,a' k}, where a' i It indicates the lowest supply unit price of the i-th type of construction materials in the list of construction materials for highway and bridge projects collected online through the highway and bridge project cost estimation platform;

[0020] S22: Perform construction material cost measurement processing based on the estimated highway bridge construction material consumption data in the highway bridge construction material estimated consumption data set and the highway bridge construction material minimum supply unit price data in the highway bridge construction material minimum supply unit price data set to generate highway bridge construction material cost data.

[0021] By collecting online the supply unit prices given by various material suppliers for the types of construction materials corresponding to the estimated consumption data of construction materials for each highway and bridge project, the minimum supply unit prices of various types of construction materials are counted, the lowest supply unit price data is accurately obtained, and the construction material cost measurement processing is performed together with the collected estimated consumption data of construction materials, so as to achieve accurate calculation of the cost data of construction materials for highway and bridge projects, while ensuring that the calculated material cost is within a reasonable range.

[0022] Preferably, the specific steps of collecting bridge engineering construction sample data and constructing a bridge engineering construction drawing analysis model are as follows:

[0023] S31. Establish a sample data set of bridge engineering construction B = {b1, b2, ..., b i ,…,b l}, where b irepresents the i-th bridge engineering construction sample data, l represents the total number of bridge engineering construction sample data, and the bridge engineering construction sample data includes bridge engineering construction drawing sample data and workload sample data of each construction process in the bridge engineering construction process;

[0024] S32, setting a training data ratio and a test data ratio, dividing the bridge engineering construction sample data set according to the training data ratio and the test data ratio, and generating a bridge engineering construction training sample data set and a bridge engineering construction test sample data set;

[0025] S33, constructing an initial long short-term memory network model, setting the number of input layer nodes of the initial long short-term memory network model to a, the number of hidden layer nodes to b, the number of output layer nodes to c, the initial weight to ω, the initial threshold to ξ, the initial cell state to ψ, and the initial hidden layer state to ζ;

[0026] S34, setting a training loss threshold, inputting the bridge engineering construction training sample data in the bridge engineering construction training sample data set into the initial long short-term memory network model in sequence, calculating the training loss value of the initial long short-term memory network model through the operation of the input layer, the hidden layer and the output layer and the update of the cell state, if the training loss value is less than or equal to the training loss threshold, stop training and obtain a trained long short-term memory network model; otherwise, continue training until the training loss value is less than or equal to the training loss threshold;

[0027] S35. Set a test accuracy threshold, input the bridge engineering construction test sample data in the bridge engineering construction test sample data set into the trained long short-term memory network model in turn for testing, calculate the test accuracy, and when the test accuracy is greater than or equal to the test accuracy threshold, use the trained long short-term memory network model as the bridge engineering construction drawing analysis model; otherwise, use the gradient descent algorithm to tune the parameters of the trained long short-term memory network model to obtain the bridge engineering construction drawing analysis model.

[0028] A bridge engineering construction drawing analysis model is constructed through the collected bridge engineering construction sample data, providing a reliable analysis tool for subsequent operations.

[0029] Preferably, the specific steps of collecting highway bridge engineering construction drawing data, performing highway bridge engineering construction workload analysis processing based on the highway bridge engineering construction drawing data and the bridge engineering construction drawing analysis model, and generating highway bridge engineering construction workload data are as follows:

[0030] S41, collecting construction drawing data corresponding to the target highway bridge project online through the highway bridge project cost estimation platform to obtain highway bridge project construction drawing data C;

[0031] S42, inputting the highway bridge engineering construction drawing data C into the bridge engineering construction drawing analysis model to perform highway bridge engineering construction workload analysis processing, and generating a highway bridge engineering construction workload data set D = {d1, d2, ..., d i ,…,d p}, where d i represents the construction workload data corresponding to the i-th construction process in the target highway bridge project, and p represents the total number of construction workload data of the highway bridge project.

[0032] The bridge engineering construction drawing analysis model is used to accurately split the collected highway bridge engineering construction drawing data, and precisely identify the construction workload data of each construction process in the target highway bridge project.

[0033] Preferably, the construction process matching processing is performed on the highway bridge engineering construction workload data and the construction process unit engineering labor cost data to generate the highway bridge engineering construction unit engineering labor cost data, and the specific steps of calculating the highway bridge engineering construction labor cost data are as follows:

[0034] S51. Establish a data set of labor cost per unit of construction process E = {e1, e2, ..., e i ,…,e o}, where e i represents the labor cost per unit of construction quantity corresponding to the ith construction process stored in the highway bridge engineering cost estimation platform, and o represents the total number of construction processes stored in the highway bridge engineering cost estimation platform;

[0035] S52, using the White Shark optimization algorithm, sequentially matching each highway bridge engineering construction workload data set with the construction process unit engineering workload labor cost data set to generate a highway bridge engineering construction unit engineering workload labor cost data set;

[0036] S521. Construct a construction process to search for white shark populations. Set the construction process to search for white shark populations as N, wave motion frequency as θ, speed contraction factor as μ, current number of iterations as t, and maximum number of iterations as t. max And the search space dimension of labor cost per unit engineering quantity of construction process is P;

[0037] The construction process unit engineering quantity labor cost data set is used as the construction process unit engineering quantity labor cost data search space, N construction process unit engineering quantity labor cost data are randomly generated in the construction process unit engineering quantity labor cost data search space, each construction process unit engineering quantity labor cost data search corresponds to a construction process search white shark individual in the construction process search white shark population, and the position of each construction process search white shark individual in the construction process search white shark population is initialized;

[0038] S522, calculating the fitness values ​​of the labor cost data per unit engineering volume of the construction process corresponding to each individual in the construction process white shark population and the matching highway bridge engineering construction workload data, arranging each individual in the construction process white shark population from large to small according to the fitness value, and selecting the individual with the highest fitness value as the current optimal individual;

[0039] S523, each individual white shark in the construction process search population will sense the position of the prey through the fluctuations generated when the prey moves in the construction process unit engineering labor cost data search space, and update its own speed; the speed update formula is as follows:

[0040]

[0041] Among them, V i new and V i They represent the speed of the white shark individual after and before the position update in the i-th construction process, α1 and α2 represent X best and X i,best The motion control parameters, rand1 and rand2 both represent random numbers uniformly distributed between [0,1], X best represents the position of the current optimal individual, X i,best and X i They represent the optimal position and current position of searching for white shark individuals in the i-th construction process respectively;

[0042] S524, each construction process search white shark individual in the construction process search white shark population moves to the prey position according to the updated speed in the construction process unit engineering labor cost data search space to update the position; the position update formula is as follows:

[0043]

[0044] in, It represents the position of the white shark individual after the i-th construction process searches for the updated position. represents the negation operator, β0 represents the logical vector, λ max and λ min They represent the upper and lower limits of the search space of the labor cost per unit engineering quantity of the construction process, respectively. a and b both represent one-dimensional binary vectors. η represents the kinetic force of the white shark individual moving toward the prey position during the construction process search. The calculation formula is as follows:

[0045]

[0046] Among them, ε0 and ε1 represent constants that control exploration behavior and exploitation behavior, respectively;

[0047] S525, each construction process searching white shark individual in the construction process searching white shark population updates its position by approaching the current optimal individual in the construction process unit engineering labor cost data search space, so as to achieve the purpose of approaching the optimal prey position; the position update formula is as follows:

[0048]

[0049] Among them, rand4, rand5 and rand6 all represent random numbers that are uniformly distributed between [0,1]. i represents the distance between the white shark individual and the best prey in the i-th construction process, sgn() represents the sign function, It indicates the sensory intensity of the white shark individuals when they are close to the best prey location during the construction process search;

[0050] S526, calculating the fitness value of each construction process searching white shark individual in the construction process searching white shark population after the position is updated, if the fitness value of the construction process searching white shark individual after the position is updated is greater than the original fitness value, then the new position is used to replace the original position, and the new position is marked as the optimal position searched by the construction process searching white shark individual; otherwise, the original position is retained;

[0051] Rearranging the construction process searching white shark individuals in the construction process searching white shark population from large to small according to fitness values, and selecting the construction process searching white shark individual with the highest fitness value as the new current optimal individual;

[0052] S527: Determine whether the current number of iterations t is less than the maximum number of iterations t max , if the current number of iterations t is less than the maximum number of iterations t max , then the current iteration number t is increased by 1, and the process returns to S523; otherwise, the current optimal individual is taken as the global optimal solution, and the labor cost data per unit engineering quantity of the construction process corresponding to the global optimal solution is output;

[0053] S528, repeating steps S521 to S527 until all the highway bridge engineering construction workload data in the highway bridge engineering construction workload data set are traversed to generate a highway bridge engineering construction unit engineering labor cost data set E'={e'1, e'2, ..., e' i ,…,e' p}, where e' i Represents the labor cost data per unit of construction volume corresponding to the i-th construction process in the target highway bridge project;

[0054] S53, performing construction material cost measurement processing according to the highway bridge engineering construction workload data in the highway bridge engineering construction workload data set and the highway bridge engineering construction unit engineering labor cost data in the highway bridge engineering construction unit engineering labor cost data set, and obtaining the highway bridge engineering construction labor cost data set.

[0055] Through the White Shark optimization algorithm, the construction workload data of each highway bridge project is matched with the unit construction labor cost data of the construction process in turn, and the unit construction labor cost data corresponding to the construction workload data of each highway bridge project is scientifically searched out, providing an accurate quantitative standard for calculating the labor cost data of highway bridge project construction. At the same time, the White Shark optimization algorithm has good robustness, which can ensure the stability of construction process matching for different data and ensure the reliability of matching results.

[0056] Preferably, the specific steps of numerically summing the highway bridge project construction material cost data and the highway bridge project construction labor cost data to generate the highway bridge project expected cost data are as follows:

[0057] S61, using the summation formula to calculate the cost data of the construction materials of the highway bridge project and the labor cost data for the construction of the highway bridge project Perform numerical summation to generate expected cost data for highway bridge projects

[0058] Preferably, the specific steps of constructing highway bridge engineering cost estimation data based on the estimated consumption data of highway bridge engineering construction materials, the highway bridge engineering construction workload data and the expected cost data of the highway bridge engineering, and pushing the data to the highway bridge engineering cost estimation platform are as follows:

[0059] S71, combining the estimated highway bridge project construction material consumption data set A, the highway bridge project construction workload data set D and the expected highway bridge project cost data F to construct highway bridge project cost estimation data Q = (A, D, F);

[0060] S72. Push the highway bridge engineering cost estimation data Q=(A, D, F) to the highway bridge engineering cost estimation platform through the communication network and display it on a display screen.

[0061] The present invention also discloses a highway bridge engineering cost estimation system based on big data, including a construction material estimated consumption data acquisition module, a highway bridge engineering construction material cost calculation module, a bridge engineering construction drawing analysis model construction module, a highway bridge engineering construction workload analysis module, a highway bridge engineering construction labor cost calculation module, and a highway bridge engineering cost estimation data construction module;

[0062] The estimated consumption data collection module for construction materials collects the estimated consumption quantities of different construction materials in the list of construction materials for highway and bridge projects online through the highway and bridge project cost estimation platform to obtain the estimated consumption data of construction materials for highway and bridge projects;

[0063] The highway bridge engineering construction material cost calculation module collects the supply unit prices given by various material suppliers for the construction material types corresponding to the estimated consumption data of various highway bridge engineering construction materials through the highway bridge engineering cost calculation platform online, and counts the minimum supply unit prices of various types of construction materials to generate the minimum supply unit price data of highway bridge engineering construction materials, and calculates the highway bridge engineering construction material cost data based on the estimated consumption data of highway bridge engineering construction materials and the minimum supply unit price data of highway bridge engineering construction materials;

[0064] The bridge engineering construction drawing analysis model building module trains and tests the initial long short-term memory network model through the established highway bridge engineering construction material cost data to obtain the bridge engineering construction drawing analysis model;

[0065] The highway bridge engineering construction workload analysis module inputs the collected highway bridge engineering construction drawing data into the bridge engineering construction drawing analysis model to perform highway bridge engineering construction workload analysis processing, thereby generating highway bridge engineering construction workload data;

[0066] The highway bridge engineering construction labor cost calculation module uses the White Shark optimization algorithm to match the construction workload data of each highway bridge engineering with the established construction process unit engineering labor cost data in turn, generates the highway bridge engineering construction unit engineering labor cost data, and performs construction material cost measurement processing with the highway bridge engineering construction workload data to obtain the highway bridge engineering construction labor cost data;

[0067] The highway bridge project cost estimation data construction module generates expected highway bridge project cost data by numerically summing up the highway bridge project construction material cost data and the highway bridge project construction labor cost data, and combines the data with the highway bridge project construction material estimated consumption data and the highway bridge project construction workload data to construct the highway bridge project cost estimation data, and pushes it to the highway bridge project cost estimation platform through the communication network.

[0068] (III) Beneficial effects

[0069] 1. The present invention measures the construction material cost through the estimated consumption data of the construction materials of the highway bridge project and the minimum supply unit price data of the construction materials of the highway bridge project, generates the construction material cost data of the highway bridge project, builds the bridge project construction drawing analysis model based on the collected bridge project construction sample data, performs the highway bridge project construction workload analysis processing according to the collected highway bridge project construction drawing data and the bridge project construction drawing analysis model, generates the construction workload data of the highway bridge project, and performs the construction process matching processing with the labor cost data of the unit engineering quantity of the construction process to generate the labor cost data of the unit engineering quantity of the highway bridge project, and then calculates the labor cost data of the highway bridge project, performs the numerical sum processing on the construction material cost data of the highway bridge project and the labor cost data of the highway bridge project, generates the expected cost data of the highway bridge project, and finally constructs the cost estimation data of the highway bridge project, and pushes it to the highway bridge project cost estimation platform to realize the accurate estimation of the cost of the highway bridge project;

[0070] 2. Collect the supply unit prices given by various material suppliers for the types of construction materials corresponding to the estimated consumption data of construction materials for various highway and bridge projects online, calculate the minimum supply unit prices of various types of construction materials, accurately obtain the lowest supply unit price data, and perform construction material cost measurement processing with the collected estimated consumption data of construction materials, so as to achieve accurate calculation of the cost data of construction materials for highway and bridge projects, and ensure that the calculated material cost is within a reasonable range;

[0071] 3. Construct a bridge engineering construction drawing analysis model through the collected bridge engineering construction sample data to provide a reliable analysis tool for subsequent operations. The bridge engineering construction drawing analysis model is used to accurately split the collected highway bridge engineering construction drawing data and accurately identify the construction workload data of each construction process in the target highway bridge project;

[0072] 4. The White Shark optimization algorithm is used to match the construction workload data of each highway bridge project with the unit construction labor cost data of the construction process in turn, and the unit construction labor cost data corresponding to the construction workload data of each highway bridge project is scientifically searched out, which provides an accurate quantitative standard for calculating the labor cost data of highway bridge project construction. At the same time, the White Shark optimization algorithm has good robustness, which can ensure the stability of construction process matching for different data and ensure the reliability of matching results. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying creative work.

[0074] Figure 1 A flowchart of a highway bridge engineering cost estimation method based on big data provided by the present invention;

[0075] Figure 2 A schematic diagram of a module of a highway bridge engineering cost estimation system based on big data provided by the present invention. DETAILED DESCRIPTION

[0076] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0077] In the description of the present invention, it is necessary to understand that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.

[0078] Embodiment 1 is as follows:

[0079] See also Figure 1 , a highway bridge engineering cost estimation method based on big data, comprising the following steps:

[0080] S1. Collect the estimated consumption data of construction materials for highway and bridge projects;

[0081] S11. The estimated consumption quantity of different construction materials in the list of construction materials for highway and bridge projects is collected online through the highway and bridge project cost estimation platform, and the estimated consumption data set of construction materials for highway and bridge projects is obtained. A={a1, a2, …, a i ,…,a k}, where a i It represents the estimated consumption quantity of the i-th type of construction materials in the list of construction materials for highway and bridge projects collected online through the highway and bridge project cost estimation platform, and k represents the total number of construction material types, and the construction materials include but are not limited to steel, cement, sand and gravel, admixtures, prestressed materials and waterproof materials.

[0082] S2. Establishing the minimum supply unit price data of highway and bridge engineering construction materials, and performing construction material cost measurement processing according to the estimated consumption data of highway and bridge engineering construction materials and the minimum supply unit price data of highway and bridge engineering construction materials, to generate highway and bridge engineering construction material cost data;

[0083] S21. Collect the supply unit prices given by various material suppliers for the types of construction materials corresponding to the estimated consumption data of construction materials for each highway bridge project in the estimated consumption data of construction materials for highway bridge projects online through the highway bridge project cost estimation platform, and count the minimum supply unit prices of various types of construction materials to generate the minimum supply unit price data set A' = {a'1, a'2, ..., a' i ,…,a' k}, where a' i It indicates the lowest supply unit price of the i-th type of construction materials in the list of construction materials for highway and bridge projects collected online through the highway and bridge project cost estimation platform;

[0084] S22: Perform construction material cost measurement processing based on the estimated highway bridge construction material consumption data in the highway bridge construction material estimated consumption data set and the highway bridge construction material minimum supply unit price data in the highway bridge construction material minimum supply unit price data set to generate highway bridge construction material cost data.

[0085] S3, collect sample data of bridge engineering construction and construct a bridge engineering construction drawing analysis model;

[0086] S31. Establish a sample data set of bridge engineering construction B = {b1, b2, ..., b i ,…,b l}, where b irepresents the i-th bridge engineering construction sample data, l represents the total number of bridge engineering construction sample data, and the bridge engineering construction sample data includes bridge engineering construction drawing sample data and workload sample data of each construction process in the bridge engineering construction process;

[0087] S32, setting a training data ratio and a test data ratio, dividing the bridge engineering construction sample data set according to the training data ratio and the test data ratio, and generating a bridge engineering construction training sample data set and a bridge engineering construction test sample data set;

[0088] S33, constructing an initial long short-term memory network model, setting the number of input layer nodes of the initial long short-term memory network model to a, the number of hidden layer nodes to b, the number of output layer nodes to c, the initial weight to ω, the initial threshold to ξ, the initial cell state to ψ, and the initial hidden layer state to ζ;

[0089] S34, setting a training loss threshold, inputting the bridge engineering construction training sample data in the bridge engineering construction training sample data set into the initial long short-term memory network model in sequence, calculating the training loss value of the initial long short-term memory network model through the operation of the input layer, the hidden layer and the output layer and the update of the cell state, if the training loss value is less than or equal to the training loss threshold, stop training and obtain a trained long short-term memory network model; otherwise, continue training until the training loss value is less than or equal to the training loss threshold;

[0090] S35. Set a test accuracy threshold, input the bridge engineering construction test sample data in the bridge engineering construction test sample data set into the trained long short-term memory network model in turn for testing, calculate the test accuracy, and when the test accuracy is greater than or equal to the test accuracy threshold, use the trained long short-term memory network model as the bridge engineering construction drawing analysis model; otherwise, use the gradient descent algorithm to tune the parameters of the trained long short-term memory network model to obtain the bridge engineering construction drawing analysis model.

[0091] S4, collecting highway bridge engineering construction drawing data, performing highway bridge engineering construction workload analysis processing based on the highway bridge engineering construction drawing data and the bridge engineering construction drawing analysis model, and generating highway bridge engineering construction workload data;

[0092] S41, collecting construction drawing data corresponding to the target highway bridge project online through the highway bridge project cost estimation platform to obtain highway bridge project construction drawing data C;

[0093] S42, inputting the highway bridge engineering construction drawing data C into the bridge engineering construction drawing analysis model to perform highway bridge engineering construction workload analysis processing, and generating a highway bridge engineering construction workload data set D = {d1, d2, ..., d i ,…,d p}, where d i represents the construction workload data corresponding to the i-th construction process in the target highway bridge project, and p represents the total number of construction workload data of the highway bridge project.

[0094] S5, performing construction process matching processing on the highway bridge project construction workload data and the construction process unit construction labor cost data, generating highway bridge project construction unit construction labor cost data, and calculating the highway bridge project construction labor cost data;

[0095] S51. Establish a data set of labor cost per unit of construction process E = {e1, e2, ..., e i ,…,e o}, where e i represents the labor cost per unit of construction quantity corresponding to the ith construction process stored in the highway bridge engineering cost estimation platform, and o represents the total number of construction processes stored in the highway bridge engineering cost estimation platform;

[0096] S52, using the White Shark optimization algorithm, sequentially matching each highway bridge engineering construction workload data set with the construction process unit engineering workload labor cost data set to generate a highway bridge engineering construction unit engineering workload labor cost data set;

[0097] S521. Construct a construction process to search for white shark populations. Set the construction process to search for white shark populations as N, wave motion frequency as θ, speed contraction factor as μ, current number of iterations as t, and maximum number of iterations as t. max And the search space dimension of labor cost per unit engineering quantity of construction process is P;

[0098] The construction process unit engineering quantity labor cost data set is used as the construction process unit engineering quantity labor cost data search space, N construction process unit engineering quantity labor cost data are randomly generated in the construction process unit engineering quantity labor cost data search space, each construction process unit engineering quantity labor cost data search corresponds to a construction process search white shark individual in the construction process search white shark population, and the position of each construction process search white shark individual in the construction process search white shark population is initialized;

[0099] S522, calculating the fitness values ​​of the labor cost data per unit engineering volume of the construction process corresponding to each individual in the construction process white shark population and the matching highway bridge engineering construction workload data, arranging each individual in the construction process white shark population from large to small according to the fitness value, and selecting the individual with the highest fitness value as the current optimal individual;

[0100] S523, each individual white shark in the construction process search population will sense the position of the prey through the fluctuations generated when the prey moves in the construction process unit engineering labor cost data search space, and update its own speed; the speed update formula is as follows:

[0101] V i new =μ·[V i +α1·(X best -X i )·rand1+α2·(X i,best -X i )·rand2],

[0102] Among them, V i new and V i They represent the speed of the white shark individual after and before the position update in the i-th construction process, α1 and α2 represent X best and X i,best The motion control parameters, rand1 and rand2 both represent random numbers uniformly distributed between [0,1], X best represents the position of the current optimal individual, X i,best and X i They represent the optimal position and current position of searching for white shark individuals in the i-th construction process respectively;

[0103] S524, each construction process search white shark individual in the construction process search white shark population moves to the prey position according to the updated speed in the construction process unit engineering labor cost data search space to update the position; the position update formula is as follows:

[0104]

[0105] in, It represents the position of the white shark individual after the i-th construction process searches for the updated position. represents the negation operator, β0 represents the logical vector, λ max and λ minThey represent the upper and lower limits of the search space of the labor cost per unit engineering quantity of the construction process, respectively. a and b both represent one-dimensional binary vectors. η represents the kinetic force of the white shark individual moving toward the prey position during the construction process search. The calculation formula is as follows:

[0106]

[0107] Among them, ε0 and ε1 represent constants that control exploration behavior and exploitation behavior, respectively;

[0108] S525, each construction process searching white shark individual in the construction process searching white shark population updates its position by approaching the current optimal individual in the construction process unit engineering labor cost data search space, so as to achieve the purpose of approaching the optimal prey position; the position update formula is as follows:

[0109]

[0110] Among them, rand4, rand5 and rand6 all represent random numbers that are uniformly distributed between [0,1]. i represents the distance between the white shark individual and the best prey in the i-th construction process, sgn() represents the sign function, It indicates the sensory intensity of the white shark individuals when they are close to the best prey location during the construction process search;

[0111] S526, calculating the fitness value of each construction process searching white shark individual in the construction process searching white shark population after the position is updated, if the fitness value of the construction process searching white shark individual after the position is updated is greater than the original fitness value, then the new position is used to replace the original position, and the new position is marked as the optimal position searched by the construction process searching white shark individual; otherwise, the original position is retained;

[0112] Rearranging the construction process searching white shark individuals in the construction process searching white shark population from large to small according to fitness values, and selecting the construction process searching white shark individual with the highest fitness value as the new current optimal individual;

[0113] S527: Determine whether the current number of iterations t is less than the maximum number of iterations t max , if the current number of iterations t is less than the maximum number of iterations t max , then the current iteration number t is increased by 1, and the process returns to S523; otherwise, the current optimal individual is taken as the global optimal solution, and the labor cost data per unit engineering quantity of the construction process corresponding to the global optimal solution is output;

[0114] S528, repeating steps S521 to S527 until all the highway bridge engineering construction workload data in the highway bridge engineering construction workload data set are traversed to generate a highway bridge engineering construction unit engineering labor cost data set E'={e'1, e'2, ..., e' i ,…,e' p}, where e' i Represents the labor cost data per unit of construction volume corresponding to the i-th construction process in the target highway bridge project;

[0115] S53, performing construction material cost measurement processing according to the highway bridge engineering construction workload data in the highway bridge engineering construction workload data set and the highway bridge engineering construction unit engineering labor cost data in the highway bridge engineering construction unit engineering labor cost data set, and obtaining the highway bridge engineering construction labor cost data set.

[0116] S6, performing numerical sum processing on the highway bridge project construction material cost data and the highway bridge project construction labor cost data to generate expected highway bridge project cost data;

[0117] S61, using the summation formula to calculate the cost data of the construction materials of the highway bridge project and the labor cost data for the construction of the highway bridge project Perform numerical summation to generate expected cost data for highway bridge projects

[0118] S7, constructing highway bridge project cost estimation data based on the estimated consumption data of highway bridge project construction materials, the highway bridge project construction workload data and the expected cost data of the highway bridge project, and pushing the data to the highway bridge project cost estimation platform;

[0119] S71, combining the estimated highway bridge project construction material consumption data set A, the highway bridge project construction workload data set D and the expected highway bridge project cost data F to construct highway bridge project cost estimation data Q = (A, D, F);

[0120] S72. Push the highway bridge engineering cost estimation data Q=(A, D, F) to the highway bridge engineering cost estimation platform through the communication network and display it on a display screen.

[0121] Embodiment 2 is as follows:

[0122] See also Figure 2, a highway bridge engineering cost estimation system based on big data, including a construction material estimated consumption data acquisition module, a highway bridge engineering construction material cost calculation module, a bridge engineering construction drawing analysis model construction module, a highway bridge engineering construction workload analysis module, a highway bridge engineering construction labor cost calculation module, and a highway bridge engineering cost estimation data construction module;

[0123] The estimated consumption data collection module for construction materials collects the estimated consumption quantities of different construction materials in the list of construction materials for highway and bridge projects online through the highway and bridge project cost estimation platform to obtain the estimated consumption data of construction materials for highway and bridge projects;

[0124] The highway bridge engineering construction material cost calculation module collects the supply unit prices given by various material suppliers for the construction material types corresponding to the estimated consumption data of various highway bridge engineering construction materials through the highway bridge engineering cost calculation platform online, and counts the minimum supply unit prices of various types of construction materials to generate the minimum supply unit price data of highway bridge engineering construction materials, and calculates the highway bridge engineering construction material cost data based on the estimated consumption data of highway bridge engineering construction materials and the minimum supply unit price data of highway bridge engineering construction materials;

[0125] The bridge engineering construction drawing analysis model building module trains and tests the initial long short-term memory network model through the established highway bridge engineering construction material cost data to obtain the bridge engineering construction drawing analysis model;

[0126] The highway bridge engineering construction workload analysis module inputs the collected highway bridge engineering construction drawing data into the bridge engineering construction drawing analysis model to perform highway bridge engineering construction workload analysis processing, thereby generating highway bridge engineering construction workload data;

[0127] The highway bridge engineering construction labor cost calculation module uses the White Shark optimization algorithm to match the construction workload data of each highway bridge engineering with the established construction process unit engineering labor cost data in turn, generates the highway bridge engineering construction unit engineering labor cost data, and performs construction material cost measurement processing with the highway bridge engineering construction workload data to obtain the highway bridge engineering construction labor cost data;

[0128] The highway bridge project cost estimation data construction module generates expected highway bridge project cost data by numerically summing up the highway bridge project construction material cost data and the highway bridge project construction labor cost data, and combines the data with the highway bridge project construction material estimated consumption data and the highway bridge project construction workload data to construct the highway bridge project cost estimation data, and pushes it to the highway bridge project cost estimation platform through the communication network.

[0129] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0130] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A highway bridge engineering cost estimation method based on big data, characterized in that: The steps include: S1. Collect the estimated consumption data of construction materials for highway and bridge projects; S2. Establishing the minimum supply unit price data of highway and bridge engineering construction materials, and performing construction material cost measurement processing according to the estimated consumption data of highway and bridge engineering construction materials and the minimum supply unit price data of highway and bridge engineering construction materials, to generate highway and bridge engineering construction material cost data; S3, collect sample data of bridge engineering construction and construct a bridge engineering construction drawing analysis model; S4, collecting highway bridge engineering construction drawing data, performing highway bridge engineering construction workload analysis processing based on the highway bridge engineering construction drawing data and the bridge engineering construction drawing analysis model, and generating highway bridge engineering construction workload data; S5, performing construction process matching processing on the highway bridge project construction workload data and the construction process unit construction labor cost data, generating highway bridge project construction unit construction labor cost data, and calculating the highway bridge project construction labor cost data; S6, performing numerical sum processing on the highway bridge project construction material cost data and the highway bridge project construction labor cost data to generate expected highway bridge project cost data; S7. Construct highway bridge project cost estimation data based on the estimated highway bridge project construction material consumption data, the highway bridge project construction workload data and the highway bridge project expected cost data, and push the data to the highway bridge project cost estimation platform.

2. A highway bridge engineering cost estimation method based on big data according to claim 1, characterized in that: The S1 comprises the following steps: S11. The estimated consumption quantity of different construction materials in the list of construction materials for highway and bridge projects is collected online through the highway and bridge project cost estimation platform, and the estimated consumption data set of construction materials for highway and bridge projects is obtained. A={a1, a2, …, a i ,…,a k }, where a i represents the estimated consumption quantity of the i-th type of construction material, and k represents the total number of construction material types.

3. A highway bridge engineering cost estimation method based on big data according to claim 2, characterized in that: The S2 comprises the following steps: S21. Collect the supply unit prices given by various material suppliers for the types of construction materials corresponding to the estimated consumption data of construction materials for each highway bridge project in the estimated consumption data of construction materials for highway bridge projects online through the highway bridge project cost estimation platform, and count the minimum supply unit prices of various types of construction materials to generate the minimum supply unit price data set A' = {a'1, a'2, ..., a' i ,…,a' k }, where a' i It indicates the lowest supply unit price of the i-th type of construction materials in the list of construction materials for highway and bridge projects collected online through the highway and bridge project cost estimation platform; S22: Perform construction material cost measurement processing based on the estimated consumption data of highway and bridge construction materials in A and the minimum supply unit price data of highway and bridge construction materials in A' to generate highway and bridge construction material cost data.

4. A highway bridge engineering cost estimation method based on big data according to claim 3, characterized in that: The S3 comprises the following steps: S31. Establish a sample data set of bridge engineering construction B = {b1, b2, ..., b i ,…,b l }, where b i represents the i-th bridge engineering construction sample data, l represents the total number of bridge engineering construction sample data, and the bridge engineering construction sample data includes bridge engineering construction drawing sample data and workload sample data of each construction process in the bridge engineering construction process; S32, setting a training data ratio and a test data ratio, dividing the data of B according to the training data ratio and the test data ratio, and generating a bridge engineering construction training sample data set and a bridge engineering construction test sample data set; S33, constructing an initial long short-term memory network model; S34, setting a training loss threshold, inputting the bridge engineering construction training sample data set into the initial long short-term memory network model for training, calculating the training loss value of the initial long short-term memory network model, and if the training loss value is less than or equal to the training loss threshold, stopping the training to obtain a trained long short-term memory network model; otherwise, continuing the training until the training loss value is less than or equal to the training loss threshold; S35. Set a test accuracy threshold, input the bridge engineering construction test sample data set into the trained long short-term memory network model for testing, calculate the test accuracy, and when the test accuracy is greater than or equal to the test accuracy threshold, use the trained long short-term memory network model as the bridge engineering construction drawing analysis model; otherwise, use the gradient descent algorithm to tune the parameters of the trained long short-term memory network model to obtain the bridge engineering construction drawing analysis model.

5. A highway bridge engineering cost estimation method based on big data according to claim 4, characterized in that: The S4 comprises the following steps: S41, collecting construction drawing data corresponding to the target highway bridge project online through the highway bridge project cost estimation platform to obtain highway bridge project construction drawing data C; S42, inputting the C into the bridge engineering construction drawing analysis model to perform highway bridge engineering construction workload analysis processing, and generating a highway bridge engineering construction workload dataset D = {d1, d2, ..., d i ,…,d p }, where d i represents the construction workload data corresponding to the i-th construction process in the target highway bridge project, and p represents the total number of construction workload data of the highway bridge project.

6. A highway bridge engineering cost estimation method based on big data according to claim 5, characterized in that: The S5 comprises the following steps: S51. Establishing a data set of labor cost per unit of construction process; S52, using the White Shark optimization algorithm, sequentially match each highway bridge construction workload data set with the construction process unit engineering labor cost data set to generate a highway bridge construction unit engineering labor cost data set E' = {e'1, e'2, ..., e' i ,…,e' p }, where e' i Represents the labor cost data per unit of construction volume corresponding to the i-th construction process in the target highway bridge project; S53, perform construction material cost measurement processing based on the highway bridge project construction workload data in D and the highway bridge project construction unit engineering labor cost data in E' to obtain the highway bridge project construction labor cost data 7. A highway bridge engineering cost estimation method based on big data according to claim 6, characterized in that: The S52 comprises the following steps: S521. Construct a construction process to search for white shark populations, set the construction process to search for white shark populations to N, the current number of iterations to t, and the maximum number of iterations to t. max And the search space dimension of labor cost per unit engineering quantity of construction process is P; The construction process unit engineering quantity labor cost data set is used as the construction process unit engineering quantity labor cost data search space, N construction process unit engineering quantity labor cost data are randomly generated in the construction process unit engineering quantity labor cost data search space, and each construction process unit engineering quantity labor cost data search corresponds to a construction process search white shark individual; S522, calculating the fitness value of the labor cost data per unit engineering quantity of the construction process corresponding to the white shark individual in each construction process and the matching highway bridge engineering construction workload data; S523, each white shark individual in each construction process searches for the labor cost per unit engineering quantity in the construction process data search space, and senses the position of the prey through the fluctuations generated when the prey moves, and updates its own speed; S524, searching for white shark individuals in each construction process in the construction process unit engineering labor cost data search space to move toward the prey position according to the updated speed to update the position; S525, searching for white shark individuals in each construction process in the labor cost per unit engineering quantity data search space of the construction process by approaching the current optimal individual to update the position, so as to achieve the purpose of approaching the optimal prey position; S526, calculating the fitness value of each construction process after searching for white shark individuals and updating their positions. If the fitness value of each construction process after searching for white shark individuals and updating their positions is greater than the original fitness value, the new position is used to replace the original position; otherwise, the original position is retained; At the same time, the construction process with the highest fitness value is selected to search for the white shark individual as the current optimal individual; S527, determine whether t is less than t max , if t is less than t max , then t is increased by 1, and the process returns to S523; otherwise, the current optimal individual is taken as the global optimal solution, and the labor cost data per unit engineering quantity of the construction process corresponding to the global optimal solution is output; S528. Repeat steps S521 to S527 until all the highway bridge engineering construction workload data in the highway bridge engineering construction workload data set are traversed to generate a highway bridge engineering construction unit engineering workload labor cost data set.

8. A highway bridge engineering cost estimation method based on big data according to claim 7, characterized in that: The S6 comprises the following steps: S61, using the summation formula and stated Perform numerical summation to generate expected cost data for highway bridge projects 9. A highway bridge engineering cost estimation method based on big data according to claim 8, characterized in that: The S7 comprises the following steps: S71, combining the data of A, D and F to construct highway bridge engineering cost estimation data Q=(A, D, F); S72, pushing Q=(A, D, F) to the highway bridge engineering cost estimation platform through the communication network, And display it on the display screen.

10. A system for implementing the highway bridge engineering cost estimation method based on big data as described in any one of claims 1 to 9.

Images