Construction engineering cost management system

Abstract

The invention relates to the technical field of project cost management, in particular to a construction engineering cost management system which comprises a stage boundary module, a stage characteristic fitting module, a global parameter optimization module, a double-layer dynamic inference module and a real-time adaptation adjustment module. According to the method, the accuracy of stage division is improved by extracting the single-stage construction period consumption and the stage cost ratio and combining calculation of the slope and the inflection point and accurately recognizing the stage demarcation point, the definition of segmented data is enhanced through cost change rate difference calculation and stage boundary point marking, and the accuracy of stage division is improved. On the basis of calculation of the ratio of resource investment to stage cost increment, the fitness of a cost trend model is optimized, smoothness and accuracy of the overall cost trend are achieved through global error extraction and demarcation point adjustment, dynamic prediction is combined with segmented cost volatility and newly-added data, the accuracy and timeliness of the cost prediction range are optimized, and the cost prediction efficiency is improved. And calculating the construction period consumption and the cost increment deviation value in real time, and dynamically adjusting the trend parameters.

Description

Technical Field

[0001] The present invention relates to the technical field of project cost management, and in particular to a construction engineering cost management system. Background Art

[0002] The technical field of project cost management includes technologies related to comprehensive planning, control and optimization of key elements such as resources, funds, and construction period involved in the project implementation process. Its core content is to achieve reasonable allocation and efficient use of resources through scientific management methods and means to ensure the realization of project goals. This technical field covers budget preparation, cost forecasting, expense accounting, fund scheduling and other aspects. It usually uses information technology and computing tools to digitize and systematize complex project management processes to improve the accuracy and efficiency of project execution.

[0003] Among them, the construction project cost management system refers to a systematic technical solution for cost calculation, budget management and expense accounting involved in construction projects. The patent subject covers technical matters such as classification, aggregation, real-time accounting and dynamic adjustment of various expense items in the construction process of construction projects. Specifically, the budget and cost calculation system of the project is established through a parameterized expense model, and combined with the project database, the allocation and statistical analysis of funds required for different project links are completed based on structured data processing technology.

[0004] The existing technology lacks accurate identification of the demarcation points of the stages, resulting in fuzzy stage divisions and difficulty in extracting stage data features. The relationship between resource input and cost increment cannot be effectively calculated, and the cost trend model has low adaptability and is difficult to reflect the real trend. The global error processing capability is insufficient and there is a lack of a demarcation point adjustment mechanism, resulting in the problem of accumulated deviations in the cost trend model. Dynamic forecasting cannot capture cost volatility and trend rates, making it difficult to cope with cost change requirements for complex projects. Real-time adjustments rely on static models and cannot effectively respond to real-time construction period consumption and cost changes, resulting in delayed resource allocation and affecting management effectiveness and project progress. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a construction project cost management system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: A construction project cost management system comprises: The stage demarcation module is based on the phased cost data of the construction project, extracts the consumption of the single structure construction period and the stage cost ratio, calculates the slope and inflection point of the ratio change, determines whether the stage demarcation point meets the fluctuation threshold, calculates the difference in the cost change rate between the starting point and the end point of the segment, marks the stage boundary points of the foundation construction and the main construction, and generates a set of stage demarcation parameters; The stage characteristic fitting module extracts the segmented construction period consumption and construction equipment input of reinforced concrete pouring based on the stage boundary parameter set, calculates the ratio of resource input to stage cost increment, selects the fitting model that meets the cost trend, adjusts the model parameters and calculates the error interval, and generates a segmented cost trend parameter set; The global parameter optimization module extracts the global fitting error and the single-segment parameter smoothness based on the stage boundary parameter set and the segment cost trend parameter set, compares the error range and adjusts the position of the boundary point, corrects the fitting trend model parameters, and generates an overall cost trend parameter set; The two-layer dynamic inference module extracts the incremental volatility and trend rate of segmented costs based on the overall cost trend parameter set, calculates the cost change interval in combination with the newly added project data, screens the prediction parameter range and calculates the fluctuation value to generate a dynamic cost prediction range; The real-time adaptive adjustment module extracts the real-time construction period consumption and labor cost allocation weights based on the dynamic cost forecast range, calculates the offset value of the real-time cost increment and trend change rate, calculates the difference between trend offset and fluctuation, adjusts the boundary parameters and fits the trend change parameters, calculates the current cost volatility and real-time forecast results, and generates real-time dynamic cost parameters.

[0007] As a further solution of the present invention, the stage boundary parameter set specifically includes the stage boundary point, the slope of the ratio change, the inflection point, the difference in the cost change rate between the starting point and the end point of the segment, and the stage boundary point; the segment cost trend parameter set includes the resource input, the ratio of the stage cost increment, the error interval, and the fitting model; the overall cost trend parameter set specifically refers to the global fitting error, the smoothness of the single-segment parameter, and the fitting trend model parameters; the dynamic cost prediction range specifically includes the cost increment volatility, the trend rate, the cost change interval, and the prediction parameter range; the real-time dynamic cost parameters include the real-time construction period consumption, the cost allocation weight, the real-time cost increment, the offset value of the trend change rate, the difference between the trend offset and the fluctuation, the current cost volatility, and the real-time prediction result.

[0008] As a further solution of the present invention, the step of obtaining the stage boundary parameter set is specifically as follows: Extract the consumption of a single phase of construction and the phase cost ratio from the phased cost data of the construction project, calculate its slope based on the multi-phase ratio change, use the segmented interval calculation method to perform slope calculation and set operation on the continuous phases, and generate a single-phase ratio change slope set; The single-stage ratio change slope set is tested to identify the extreme points and inflection points of the ratio change slope, and marked by comparing the change range of its local derivative. Combined with set operations, it is determined whether the ratio fluctuation amplitude of the continuous interval exceeds the set fluctuation threshold, and the stage fluctuation change judgment result set is generated; Based on the stage fluctuation change determination result set, the difference in the cost change rate between the starting point and the end point of the segment is calculated using the formula: ; Calculate the cost rate difference and mark the stage boundary points to generate a set of stage boundary parameters; in, Represents the difference in the rate of change of costs, is the slope of the phase ratio change, is the weight adjustment coefficient, is the cost change rate parameter, is the adjustment coefficient, Represents the current stage index, is the total number of stages, is the parameter index; Combine the stage fluctuation change determination result set with the stage boundary parameter set, extract the boundary points marked in the difference set, call the stage fluctuation change determination result set to jointly verify the boundary point position and characteristics, and integrate the boundary points that meet the conditions into the stage boundary parameter set.

[0009] As a further solution of the present invention, the step of obtaining the segmented cost trend parameter set is specifically as follows: Extracting the segmented duration consumption and the project resource input from the stage boundary parameter set, accumulating the resource input of each stage and then standardizing it by stage, calculating the ratio of resource input to stage cost increment by calling the segmented duration consumption, and generating a resource input and cost increment ratio set; Based on the resource input and cost increment ratio set, a fitting model that meets the cost trend is screened, and the model performance is compared by calculating the fitting error interval of multiple models, and the error range is compared and the model parameter set that meets the standard is detected based on the aggregation function, so as to generate a fitting model parameter set that meets the conditions; The correlation between the set of fitting model parameters that meet the conditions and the consumption of the segmented construction period is calculated using the formula: ; Calculate the model error interval and adjust the stage parameters of the fitting model to generate a set of segmented cost trend parameters; in, represents the model error range, is the actual cost value, To predict the cost value for the fitted model, is the number of stages, is the phase duration parameter, is the resource adjustment factor, is the number of resource types, is the stage adjustment factor, is the resource adjustment factor, is the stage index, Index for resources; Combine the qualified fitting model parameter set with the segmented cost trend parameter set, extract the boundary point positions in the cost trend, call the boundary point characteristic values ​​to adjust the model parameters of the stage trend, update and integrate the stage parameter trends, and generate a segmented cost trend parameter set.

[0010] As a further solution of the present invention, the steps of obtaining the overall cost trend parameter set are specifically as follows: Based on the stage boundary parameter set and the segment cost trend parameter set, extract the global fitting error of the multi-segment duration and the single-segment parameter smoothness, calculate the error standard deviation and smoothness index of the segment respectively through statistical analysis, and generate a global fitting error and smoothness data set; Extracting segmented data with the best error range and smoothness from the global fitting error and smoothness data set, comparing the errors and smoothness of multiple segments, screening and comparing the demarcation point positions that need to be adjusted through the error range, and generating an adjusted demarcation point position set; Based on the adjusted set of cut-off point locations, use the formula: ; Calculate the error range and smoothness index, modify the segmented fitting trend model parameters, and generate the overall cost trend parameter set; in, represents the indicator value of the modified trend model, Representative The fitting error of the segment, is the mean error, is the standard deviation of error, is the smoothness, is the smoothness average, is the smoothness standard deviation, is the total number of segments; In combination with the adjusted demarcation point position set and the overall cost trend parameter set, the demarcation point position parameters are called to perform parameter correction on the fitting model of the stage cost trend, and the corrected model trend is integrated to generate the overall cost trend parameter set.

[0011] As a further solution of the present invention, the step of obtaining the dynamic cost prediction range is specifically as follows: Extracting the segmented cost increment volatility and trend rate based on the overall cost trend parameter set, and generating a segmented cost increment and trend rate set by calculating the absolute difference value of the segmented cost increment volatility and combining the trend rate calculation fluctuation range; Combine the newly added project data with the segmented cost increment and trend rate set, calculate the cost change interval of each segment, filter the prediction parameters by judging the difference value range between the cost change interval and the characteristics of the newly added project, and generate a prediction parameter range set; For the set of prediction parameter ranges, the formula is used: ; Calculate the cost fluctuation value and adjust the cost parameter range according to the fluctuation value to generate a dynamic cost forecast range; in, Represents the cost fluctuation value, is the cost increment volatility, is the trend rate, is the adjustment factor, is the total number of stages, is the cost trend parameter, is the smoothing adjustment factor, is the current stage index, Index of the cost parameter.

[0012] As a further solution of the present invention, the step of obtaining the real-time dynamic cost parameter is specifically as follows: Based on the dynamic cost forecast range, extract the real-time construction period consumption and cost allocation weight, call the real-time monitored construction period consumption data, analyze the real-time weight change in combination with the historical cost allocation ratio, and generate real-time construction period consumption and cost weight data based on real-time fluctuation analysis; Calculating the real-time cost increment and trend change rate from the real-time construction period consumption and cost weight data, obtaining the real-time increment change trend through differential operation, calculating the real-time cost increment based on the trend rate deviation and generating the real-time cost increment and trend change rate data; By comparing the real-time cost increment and trend change rate data with the historical trend parameters, the formula is used: ; Calculate the trend deviation and fluctuation difference, correct the real-time boundary parameters and fit trend change parameters according to the deviation difference, and generate real-time dynamic cost parameters; in, Represents the trend deviation and volatility difference, is the real-time fee increment, is the trend change rate, is the preset trend mean, is the number of data points, is the square of the deviation, To avoid abnormal calculation of small values, the incremental index is used. is the deviation index.

[0013] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by extracting the single-stage construction period consumption and the stage cost ratio, combined with the calculation of the slope and the inflection point, the stage demarcation point is accurately identified, thereby improving the accuracy of the stage division. The clarity of the segmented data is enhanced by calculating the difference in the cost change rate and marking the stage boundary points. The adaptability of the cost trend model is optimized based on the calculation of the ratio of resource input to stage cost increment. The smoothness and accuracy of the overall cost trend are achieved through global error extraction and demarcation point adjustment. Dynamic prediction combines the segmented cost volatility and the newly added data to optimize the accuracy and timeliness of the cost prediction range. The construction period consumption and the cost increment offset value are calculated in real time, and the trend parameters are dynamically adjusted to significantly enhance the flexibility and adaptability of real-time cost control. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a system flow chart of the present invention; Figure 2 A flow chart of the steps for obtaining a set of stage boundary parameters of the present invention; Figure 3 A flow chart of the steps for obtaining the segmented cost trend parameter set of the present invention; Figure 4 A flowchart of the steps for obtaining the overall cost trend parameter set of the present invention; Figure 5 A flow chart of the steps for obtaining a dynamic cost prediction range of the present invention; Figure 6 This is a flow chart of the steps for obtaining real-time dynamic cost parameters of the present invention. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0016] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0017] Example 1: Please refer to Figure 1, a construction project cost management system includes: The stage demarcation module is based on the phased cost data of the construction project, extracts the consumption of the single structure construction period and the stage cost ratio, calculates the slope and inflection point of the ratio change, determines whether the stage demarcation point meets the fluctuation threshold, calculates the difference in the cost change rate between the starting point and the end point of the segment, marks the stage boundary points of the foundation construction and the main construction, and generates a set of stage demarcation parameters; The stage characteristic fitting module extracts the segmented construction period consumption and construction equipment input of reinforced concrete pouring based on the stage boundary parameter set, calculates the ratio of resource input to stage cost increment, selects the fitting model that conforms to the cost trend, adjusts the model parameters and calculates the error interval, and generates a segmented cost trend parameter set; The global parameter optimization module extracts the global fitting error and the smoothness of the single-segment parameters based on the stage boundary parameter set and the segment cost trend parameter set, compares the error range and adjusts the position of the boundary point, corrects the fitting trend model parameters, and generates the overall cost trend parameter set; The two-layer dynamic inference module extracts the incremental volatility and trend rate of segmented costs based on the overall cost trend parameter set, calculates the cost change range in combination with the newly added project data, screens the prediction parameter range and calculates the fluctuation value to generate a dynamic cost prediction range; The real-time adaptive adjustment module extracts the real-time construction period consumption and labor cost allocation weights based on the dynamic cost forecast range, calculates the offset value of the real-time cost increment and trend change rate, calculates the difference between trend offset and fluctuation, adjusts the boundary parameters and fits the trend change parameters, calculates the current cost volatility and real-time forecast results, and generates real-time dynamic cost parameters.

[0018] The stage boundary parameter set specifically includes the stage boundary point, the slope of the ratio change, the inflection point, the difference in the cost change rate between the starting point and the end point of the segment, and the stage boundary point. The segment cost trend parameter set includes the resource input, the ratio of the stage cost increment, the error range, and the fitting model. The overall cost trend parameter set specifically refers to the global fitting error, the single-segment parameter smoothness, and the fitting trend model parameters. The dynamic cost prediction range specifically includes the cost increment volatility, the trend rate, the cost change range, and the prediction parameter range. The real-time dynamic cost parameters include the real-time construction period consumption, the cost allocation weight, the real-time cost increment, the offset value of the trend change rate, the difference between the trend offset and the fluctuation, the current cost volatility, and the real-time prediction result.

[0019] See also Figure 2 , the steps for obtaining the stage boundary parameter set are specifically as follows: Extract the consumption of a single phase of construction and the phase cost ratio from the phased cost data of the construction project, calculate its slope based on the multi-phase ratio change, use the segmented interval calculation method to perform slope calculation and set operation on the continuous phases, and generate a single-phase ratio change slope set; The consumption of a single-stage construction period and the stage cost ratio are extracted from the staged cost data of the construction project. Based on the data extracted from the single-stage construction period, the start and end points of each stage are first calibrated in chronological order, the construction period is divided into multiple continuous intervals and the cost data in the interval is recorded. At the same time, the cost ratio of each interval is extracted. The cost ratio is calculated by the ratio of the total cost in the interval to the total cost of the installment; next, based on the time series data of the cost ratio, the ratio changes of each stage are calculated by constructing a segmented interval model, and the slope value is calculated using the slope formula for the ratio changes of the continuous stages. The slope formula is: in, is the difference in cost ratios between adjacent stages, For the time intervals between adjacent stages, all calculation results are recorded as a single-stage ratio change slope set, and a table arranged by interval is formed; then, by extracting the data in the slope table, check one by one whether the slope of each interval meets the characteristics of continuous increase or decrease. If the slope of an interval does not conform to the trend, it is recorded as an abnormal point, and finally a single-stage ratio change slope set is formed.

[0020] The single-stage ratio change slope set is tested to identify the extreme points and inflection points of the ratio change slope, and marked by comparing the change range of its local derivative. Combined with set operations, it is determined whether the ratio fluctuation amplitude of the continuous interval exceeds the set fluctuation threshold, and the stage fluctuation change judgment result set is generated; The single-stage ratio change slope set is tested. First, the extreme points of each stage are extracted by calculating the local derivative change range of each interval. The calculation formula of the local derivative is: in, is the ratio change value of adjacent stages, The extreme points are matched with the ratio fluctuation values ​​as time intervals to mark the ratio inflection point positions in each stage. Subsequently, for the marked extreme points, the ratio fluctuation amplitude is combined to determine whether it exceeds the set fluctuation threshold. The fluctuation amplitude calculation is achieved by the difference between the absolute value of the ratio extreme point and the adjacent value. The threshold setting is determined by the standard deviation calculation of the historical data, and the interval exceeding the threshold is marked as the fluctuation abnormal interval. Finally, all the marked abnormal points and the fluctuation interval are integrated through set operations to generate a set of stage fluctuation change judgment results.

[0021] Based on the stage fluctuation change determination result set, the difference in the cost change rate between the starting point and the end point of the segment is calculated using the formula: ; Calculate the cost rate difference and mark the stage boundary points to generate a set of stage boundary parameters; in, Represents the difference in the rate of change of costs, is the slope of the phase ratio change, is the weight adjustment coefficient, is the cost change rate parameter, is the adjustment coefficient, Represents the current stage index, is the total number of stages, is the parameter index; formula: ; The benefit of the formula is that the weights are adjusted by and adjustment coefficient The introduction of improves the ability to handle outliers in the cost change rate, while more accurately controlling the cumulative fluctuations within a stage, effectively reducing the impact of extreme values ​​on the overall analysis results.

[0022] Detailed explanation of the formula and the process of formula calculation and derivation: in, Represents the difference in the rate of change of costs, is the slope of the phase ratio change, according to the formula It is calculated that, is the difference between the costs of adjacent stages, is the time interval between adjacent stages, The weight adjustment coefficient is set based on the weight distribution of the impact of the change range in each stage. The calculation is based on the fluctuation range and historical weight data. To adjust the coefficient, adjust the threshold range and set it by the standard deviation interval of the actual data fluctuation range. is the cost change rate parameter, according to the formula It is calculated that, is the stage cost value, is the length of the stage; bring in the sample data, assuming there are three stages of data, namely: the first stage , , second stage , , , The weight adjustment coefficients are , , , adjustment coefficient ; Calculated: 1. , , ; 2. , , ; 3. ; 4. , , , ; 5. .

[0023] The result shows that the difference in the cost change rate is 1.56, which belongs to the range with relatively small fluctuations and is directly related to the set of stage boundary parameters that need to be judged in the subsequent steps.

[0024] Combine the stage fluctuation change determination result set with the stage boundary parameter set, extract the boundary points marked in the difference set, call the stage fluctuation change determination result set to jointly verify the boundary point position and characteristics, and integrate the boundary points that meet the conditions into the stage boundary parameter set.

[0025] Combine the stage fluctuation change judgment result set with the stage boundary parameter set, extract the boundary points marked in the difference set, compare the boundary points with the fluctuation data within the stage, and screen out the boundary points with large fluctuation differences as the final boundary points by calculating the local slope of the fluctuation points and the fluctuation difference value between adjacent points. Finally, call the abnormal points and fluctuation amplitude data of the ratio change to form a unified boundary feature set, and integrate the qualified boundary points into the stage boundary parameter set.

[0026] See also Figure 3 The specific steps of obtaining the segment cost trend parameter set are as follows: Extracting the segmented duration consumption and the project resource input from the stage boundary parameter set, accumulating the resource input of each stage and then standardizing it by stage, calculating the ratio of resource input to stage cost increment by calling the segmented duration consumption, and generating a resource input and cost increment ratio set; The segmented duration consumption and project resource input are extracted from the stage boundary parameter set. The resource consumption corresponding to each stage is extracted according to the time period based on the segmented duration consumption. The resource usage details of each stage are extracted separately, and classified into three categories: human resources, equipment resources and material resources according to the actual project resource classification. The consumption of each type of resource is accumulated and divided by the total resource volume to standardize its relative proportion. The resource usage ratio is generated by calculating the ratio of the proportion of resource classification in each stage and the stage duration. The cost details of each stage are extracted by calling the segmented duration consumption, and the stage cost increment is calculated by a stage-by-stage accumulation method. The resource usage ratio is combined with the stage cost increment ratio to generate a set of resource input to stage cost increment ratios, and finally a set of resource input and cost increment ratios is obtained.

[0027] Based on the resource input and cost increment ratio set, a fitting model that meets the cost trend is screened, and the model performance is compared by calculating the fitting error interval of multiple models, and the error range is compared and the model parameter set that meets the standard is detected based on the aggregation function, so as to generate a fitting model parameter set that meets the conditions; Based on the resource input and cost increment ratio set, the fitting model that meets the cost trend is screened. By establishing the relationship matrix between resource input and cost change trends, the stage in the ratio set that is significantly higher than the mean is extracted. The polynomial fitting model is selected using the minimum error optimization principle. The fitting parameters of the model are gradually adjusted by setting the initial parameters and the highest order of the polynomial fitting, and the sum of squared errors after fitting is calculated. The optimal model and its parameter combination are screened out according to the order of error values ​​from small to large, and the optimal fitting model parameter combination is called to generate a model that meets the fitting accuracy requirements. By comparing the error value with the reference error threshold, a qualified fitting model parameter set is generated based on the degree of fit between the final model and the actual data.

[0028] The correlation between the set of fitting model parameters that meet the conditions and the consumption of the segmented construction period is calculated using the formula: ; Calculate the model error interval and adjust the stage parameters of the fitting model to generate a set of segmented cost trend parameters; in, represents the model error range, is the actual cost value, To predict the cost value for the fitted model, is the number of stages, is the phase duration parameter, is the resource adjustment factor, is the number of resource types, is the stage adjustment factor, is the resource adjustment factor, is the stage index, Index for resources; formula: ; The benefit of the formula is that it introduces resource adjustment coefficients and adjustment factors to calculate model errors, compares actual costs with predicted costs, and comprehensively considers multi-stage resource weights and adjustment coefficients in error optimization, thereby improving the dynamic adaptability of model fitting and the accuracy of error assessment.

[0029] Detailed explanation of the formula and the process of formula calculation and derivation: The actual cost value of the stage is obtained by adding up the cost details of each stage. For example, if the cost value of the first stage is 100 and the cost value of the second stage is 200, then the actual cost value of the first stage is 100 and the actual cost value of the second stage is 300. To predict the cost value, it is calculated by fitting the model. For example, the predicted value of the first stage calculated by the polynomial fitting model is 95, and the predicted value of the second stage is 210; is the total number of stages, assuming there are 3 stages, namely ; The resource classification weight, for example, the material resource weight is 0.4, the human resource weight is 0.35, and the equipment resource weight is 0.25. The specific weight value is calculated by the classification proportion after the normalization of each resource; is the adjustment coefficient of resource classification. For example, considering the actual supply imbalance of material resources, the adjustment coefficient is set to 0.8, the human resource adjustment coefficient is 1.2, and the equipment resource adjustment coefficient is 1.1; is the resource adjustment benchmark, which is set to the square root of the average value of total resource utilization efficiency. If the total efficiency is 0.85, then ; is the cost adjustment factor, which is set to 0.15 considering the fluctuation of cost growth rate in each stage; Calculation formula: 1. Calculate the error sum of squares: ; 2. Calculate the RMS error: ; 3. Computing resource adjustment part: ; ; ; 4. Comprehensive calculation: ;

[0030] The result shows that the model error is 53.693, which reflects the degree of deviation of the fitting model from the actual cost data. This value will be used to adjust the fitting model parameters to reduce the error and optimize the segmented cost trend analysis, and finally generate a segmented cost trend parameter set.

[0031] Combine the qualified fitting model parameter set with the segmented cost trend parameter set, extract the boundary point positions in the cost trend, call the boundary point characteristic values ​​to adjust the model parameters of the stage trend, update and integrate the stage parameter trends, and generate a segmented cost trend parameter set.

[0032] Combine the qualified fitting model parameter set with the segmented cost trend parameter set, extract the boundary point positions in the cost trend, calculate the boundary characteristics of the cost trend by adjusting the errors of the stage dividing points in the fitting model parameters, accumulate the cost increments at each dividing point, and mark the boundary points based on the fluctuation points in the actual data. By updating the boundary point parameters, gradually adjust the stage trend of the model to make the boundary point characteristics closer to the actual data, and finally integrate them to form a segmented cost trend parameter set.

[0033] See also Figure 4 The steps for obtaining the overall cost trend parameter set are specifically as follows: Based on the stage boundary parameter set and the segment cost trend parameter set, extract the global fitting error of the multi-segment duration and the single-segment parameter smoothness, calculate the error standard deviation and smoothness index of the segment respectively through statistical analysis, and generate a global fitting error and smoothness data set; Based on the stage boundary parameter set and the segment cost trend parameter set, we first need to quantify the global fitting error of the segment duration, compare the actual cost of each segment with the predicted cost value by segment fitting, and calculate the square sum of the errors to reflect the fitting degree of each segment. The specific calculation formula is: ,in It is The fitting error of the segment, is the actual cost value, is the predicted cost value, is the total number of data points. The results of each segment fitting error are stored for subsequent analysis. Then, the smoothness of the single segment parameter is quantified by calculating the variation of the parameter in the continuous time series, using the smoothness formula ,in is the smoothness, It is The parameter value at each time point, is the number of time points. This method can reflect the stability of the parameters through the mean of the absolute difference. After calculating all the segmented error values ​​and smoothness values ​​separately, they are summarized into complete global fitting error and smoothness data to form a global fitting error and smoothness data set.

[0034] Combine the qualified fitting model parameter set with the segmented cost trend parameter set, extract the boundary point positions in the cost trend, calculate the boundary characteristics of the cost trend by adjusting the errors of the stage dividing points in the fitting model parameters, accumulate the cost increments at each dividing point, and mark the boundary points based on the fluctuation points in the actual data. By updating the boundary point parameters, gradually adjust the stage trend of the model to make the boundary point characteristics closer to the actual data, and finally integrate them to form a segmented cost trend parameter set.

[0035] See also Figure 4 The steps for obtaining the overall cost trend parameter set are specifically as follows: Based on the stage boundary parameter set and the segment cost trend parameter set, extract the global fitting error of the multi-segment duration and the single-segment parameter smoothness, calculate the error standard deviation and smoothness index of the segment respectively through statistical analysis, and generate a global fitting error and smoothness data set; Based on the stage boundary parameter set and the segment cost trend parameter set, we first need to quantify the global fitting error of the segment duration, compare the actual cost of each segment with the predicted cost value by segment fitting, and calculate the square sum of the errors to reflect the fitting degree of each segment. The specific calculation formula is: ,in It is The fitting error of the segment, is the actual cost value, is the predicted cost value, is the total number of data points. The results of each segment fitting error are stored for subsequent analysis. Then, the smoothness of the single segment parameter is quantified by calculating the variation of the parameter in the continuous time series, using the smoothness formula ,in is the smoothness, It is The parameter value at each time point, is the number of time points. This method can reflect the stability of the parameters through the mean of the absolute difference. After calculating all the segmented error values ​​and smoothness values ​​separately, they are summarized into complete global fitting error and smoothness data to form a global fitting error and smoothness data set.

[0036] Based on the adjusted set of cut-off point locations, use the formula: ; Calculate the error range and smoothness index, modify the segmented fitting trend model parameters, and generate the overall cost trend parameter set; in, represents the indicator value of the modified trend model, Representative The fitting error of the segment, is the mean error, is the standard deviation of error, is the smoothness, is the smoothness average, is the smoothness standard deviation, is the total number of segments; formula: ; The benefit of the formula is that, by comprehensively considering the deviations of both fitting error and parameter smoothness, it can quantify the need for correction of the overall fitting trend of the segment, which helps to improve the trend stability and consistency between segments.

[0037] Detailed explanation of the formula and the process of formula calculation and derivation: Set the total number of segments , get the piecewise fitting error from the global fitting error and smoothness data , mean error , standard deviation of error , smoothness , smoothness mean , smoothness standard deviation .

[0038] First calculate the standardized error and the smoothness sum of squares for each segment: ; ; Add the error term to the smoothness term and take the average: ; This result shows that by calculating the correction index , it can be judged that the fitting error and parameter smoothness deviation of the overall segment are within a reasonable range, providing a basic basis for the subsequent correction of the model.

[0039] In combination with the adjusted demarcation point position set and the overall cost trend parameter set, the demarcation point position parameters are called to perform parameter correction on the fitting model of the stage cost trend, and data integration is performed on the corrected model trend to generate the overall cost trend parameter set.

[0040] Combined with the adjusted demarcation point location set and the overall cost trend parameter set, the demarcation point location set is first called to re-divide the stage boundary, and the fitting error and smoothness of each segment are recalculated according to the adjusted segment range. Specifically, the segment summary method is used to obtain the updated parameter value of each segment. For example, the error calculation formula is , the smoothness calculation formula is The final updated error value and smoothness result are used to correct the overall trend model; then the updated segmentation parameters are called to further smooth the trend of the fitting model, and finally generate a set of overall cost trend parameters.

[0041] See also Figure 5 The steps for obtaining the dynamic cost prediction range are specifically as follows: Extracting the segmented cost increment volatility and trend rate based on the overall cost trend parameter set, and generating a segmented cost increment and trend rate set by calculating the absolute difference value of the segmented cost increment volatility and combining the trend rate calculation fluctuation range; Based on the overall cost trend parameter set, the cost increment volatility and trend rate are extracted from each segment. By calculating the absolute difference of the cost increment volatility of the segmented cost, the cost data of each stage in the overall cost trend parameter set is called, and the incremental change rate of each stage is calculated by multi-segment linear regression with time as the variable. The change rate is divided into three categories according to the trend change direction: growth, decline and stability. The difference calculation is performed based on the trend rate with time as the dimension to quantify the change amplitude and direction of the rate. The change direction is indicated by the positive and negative values ​​of the trend rate, and finally a set of segmented cost increments and trend rates is generated; Combine the newly added project data with the segmented cost increment and trend rate set, calculate the cost change interval of each segment, filter the prediction parameters by judging the difference value range between the cost change interval and the characteristics of the newly added project, and generate a prediction parameter range set; Combine the newly added project data with the segmented cost increment and trend rate set, extract the cost change range of each segment, cross-compare each cost type in the newly added project data with the trend rate and increment volatility in the segmented data, quantify the similarity as the percentage of the difference, calculate the error range of the cost change range in each stage, map the newly added project cost items with the volatility of the segmented change range by cost type, calculate the matching degree of each cost, and screen the adapted prediction parameter range based on the cost matching degree, and finally generate a prediction parameter range set; For the set of prediction parameter ranges, the formula is used: ; Calculate the cost fluctuation value and adjust the cost parameter range according to the fluctuation value to generate a dynamic cost forecast range; in, Represents the cost fluctuation value, is the cost increment volatility, is the trend rate, is the adjustment factor, is the total number of stages, is the cost trend parameter, is the smoothing adjustment factor, is the current stage index, Index of the cost parameter.

[0042] formula: ; The benefit of the formula is that it quantifies the fluctuation range of costs by comprehensively calculating multiple parameters such as cost increment volatility, trend rate, adjustment factor, etc., and improves the stability of parameter change calculation through smoothing adjustment factors, making the dynamic cost forecast range more accurate.

[0043] Detailed explanation of the formula and the process of formula calculation and derivation: is the cost increment volatility, which is calculated by the change range of each cost type in the segmented data over time. For example, if the increments of a segment are 5, 10, and 15 units respectively, then for , is the trend rate, which is calculated by the absolute value of the difference in trend changes per unit time. For example, if the rate changes are 2, 4, and 6, then for , is the adjustment factor, which represents the correction parameter between stages. It is calculated proportionally by the residual of volatility and trend rate. For example, if the residual of a certain segment is 0.2, then for , is the cost trend parameter, which is calculated by the standard deviation of the overall cost trend parameter set. If the cost trend data is 1, 2, 3, or 4, then , is the smoothing adjustment factor, which is set according to the ratio with the trend fluctuation residual. .

[0044] Substituting the above parameters into the formula: , the calculation process is: .

[0045] The results show that the cost fluctuation value in the dynamic cost forecast range is 0.476, which is combined with the change rate and trend rate of each segment to form the cost forecast range. The calculation results can be used to further adjust the prediction model parameters to generate the final cost forecast range.

[0046] See also Figure 6The steps for obtaining the real-time dynamic cost parameters are as follows: Based on the dynamic cost forecast range, extract the real-time construction period consumption and cost allocation weight, call the real-time monitored construction period consumption data, analyze the real-time weight change in combination with the historical cost allocation ratio, and generate real-time construction period consumption and cost weight data based on real-time fluctuation analysis; Based on the dynamic cost forecast range, the real-time data in the dynamic cost forecast range is called. The real-time duration consumption is collected through the dynamic monitoring of the segmented duration data. The daily consumption duration is extracted through the decomposition of the daily project execution records. Combined with the real-time resource allocation records, the dynamic weight parameters are calculated according to the resource input and total consumption ratio. The formula is used ,in Assign weights to costs, is the amount of resources invested in a certain stage, The total number of stages is taken as the total number of stages. The resource allocation ratio of each stage is dynamically calculated in this way. Then, through stage-by-stage fluctuation analysis, the current real-time resource weight is compared with the historical resource mean deviation value, and the historical fluctuation standard deviation of the allocation weight is used as the judgment basis. If the weight deviation exceeds twice the historical fluctuation value, it is marked as an abnormal stage. The data of the abnormal stage is eliminated and the effective stage weight is recalculated. Finally, the effective weight value and construction period consumption are integrated to generate real-time construction period consumption and cost weight data.

[0047] Calculating the real-time cost increment and trend change rate from the real-time construction period consumption and cost weight data, obtaining the real-time increment change trend through differential operation, calculating the real-time cost increment based on the trend rate deviation and generating real-time cost increment and trend change rate data; From the real-time construction period consumption and cost weight data, call the real-time construction period consumption data and cost weight parameters, calculate the real-time cost increment by segmenting the daily consumption according to the resource weight, and calculate the cost increment through the cost increment calculation formula ,in is the real-time fee increment, is the real-time construction period consumption, is the resource weight parameter, combined with the cost increment to compare the historical trend change curve, and the trend change rate formula is used ,in is the trend change rate, is the cost increment change value, The trend rate and historical rate are offset analyzed for time intervals. If the offset exceeds the set threshold, it is marked as an abnormal stage. By checking the trend offset stage by stage, correcting the abnormal data interval and recalculating the trend rate, real-time cost increment and trend change rate data are finally generated.

[0048] By comparing the real-time cost increment and trend change rate data with the historical trend parameters, the formula is used: ; Calculate the trend deviation and fluctuation difference, correct the real-time boundary parameters and fit trend change parameters according to the deviation difference, and generate real-time dynamic cost parameters; in, Represents the trend deviation and volatility difference, is the real-time fee increment, is the trend change rate, is the preset trend mean, is the number of data points, is the square of the deviation, To avoid calculating abnormal small values, is the incremental index, is the deviation index; formula: ; The benefit of the formula is that it uses real-time fee increments and trend rate of change Dynamic adjustment combined with historical trend average and the square of the data deviation , which can dynamically quantify trend deviations and fluctuation differences, and improve forecasting accuracy and real-time control capabilities.

[0049] Detailed explanation of the formula and the process of formula calculation and derivation: Calculation using actual project data: Assuming real-time cost increments Unit (yuan), trend change rate , historical trend mean Unit (yuan), square of deviation Unit (Yuan 2 ), decimal value Unit (Yuan 2 ), the total number of data points .

[0050] Formula calculation steps: Calculate the square of each offset: ; ; ; .

[0051] Sum of Squared Deviations .

[0052] Calculate the sum of squared deviations: .

[0053] Enter the formula to calculate: .

[0054] The result shows that the trend shift and volatility difference is 0.157, indicating that the current real-time cost parameters have small fluctuations and are highly consistent with historical trends, and can be directly applied to subsequent real-time dynamic cost parameter adjustments.

[0055] The real-time dynamic cost parameters are called, the model structure is adjusted in combination with the current budget allocation plan, the budget forecast is updated in real time according to the adjusted parameters of the model, and the adjusted parameters are integrated to generate a real-time cost management report.

[0056] Call real-time dynamic cost parameters and integrate them into the budget allocation plan. Dynamically adjust the budget module through real-time cost parameters, optimize the resource allocation strategy in real time according to the cost volatility, and gradually add the dynamic adjustment results to the budget allocation of each stage. Combined with the real-time monitoring module, the cost forecasting model is verified to ensure the accuracy of the data after the model adjustment, and generate the final real-time cost management report.

[0057] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A construction project cost management system, characterized in that: The system comprises: The stage demarcation module is based on the phased cost data of the construction project, extracts the consumption of the single structure construction period and the stage cost ratio, calculates the slope and inflection point of the ratio change, determines whether the stage demarcation point meets the fluctuation threshold, calculates the difference in the cost change rate between the starting point and the end point of the segment, marks the stage boundary points of the foundation construction and the main construction, and generates a set of stage demarcation parameters; The stage characteristic fitting module extracts the segmented construction period consumption and construction equipment input of reinforced concrete pouring based on the stage boundary parameter set, calculates the ratio of resource input to stage cost increment, selects the fitting model that meets the cost trend, adjusts the model parameters and calculates the error interval, and generates a segmented cost trend parameter set; The global parameter optimization module extracts the global fitting error and the single-segment parameter smoothness based on the stage boundary parameter set and the segment cost trend parameter set, compares the error range and adjusts the position of the boundary point, corrects the fitting trend model parameters, and generates an overall cost trend parameter set; The two-layer dynamic inference module extracts the incremental volatility and trend rate of segmented costs based on the overall cost trend parameter set, calculates the cost change interval in combination with the newly added project data, screens the prediction parameter range and calculates the fluctuation value to generate a dynamic cost prediction range; The real-time adaptive adjustment module extracts the real-time construction period consumption and labor cost allocation weights based on the dynamic cost forecast range, calculates the offset value of the real-time cost increment and trend change rate, calculates the difference between trend offset and fluctuation, adjusts the boundary parameters and fits the trend change parameters, calculates the current cost volatility and real-time forecast results, and generates real-time dynamic cost parameters.

2. The construction project cost management system according to claim 1, characterized in that: The stage boundary parameter set specifically includes the stage boundary point, the slope of the ratio change, the inflection point, the difference in the cost change rate between the starting point and the end point of the segment, and the stage boundary point. The segment cost trend parameter set includes the resource input, the ratio of the stage cost increment, the error range, and the fitting model. The overall cost trend parameter set specifically refers to the global fitting error, the single-segment parameter smoothness, and the fitting trend model parameters. The dynamic cost prediction range specifically includes the cost increment volatility, the trend rate, the cost change range, and the prediction parameter range. The real-time dynamic cost parameters include the real-time construction period consumption, the cost allocation weight, the real-time cost increment, the offset value of the trend change rate, the difference between the trend offset and the fluctuation, the current cost volatility, and the real-time prediction result.

3. The construction project cost management system according to claim 2, characterized in that: The steps for obtaining the stage boundary parameter set are specifically as follows: Extract the consumption of a single phase of construction and the phase cost ratio from the phased cost data of the construction project, calculate its slope based on the multi-phase ratio change, use the segmented interval calculation method to perform slope calculation and set operation on the continuous phases, and generate a single-phase ratio change slope set; The single-stage ratio change slope set is tested to identify the extreme points and inflection points of the ratio change slope, and marked by comparing the change range of its local derivative. Combined with set operations, it is determined whether the ratio fluctuation amplitude of the continuous interval exceeds the set fluctuation threshold, and the stage fluctuation change judgment result set is generated; Based on the stage fluctuation change determination result set, the difference in the cost change rate between the starting point and the end point of the segment is calculated using the formula: ； Calculate the cost rate difference and mark the stage boundary points to generate a set of stage boundary parameters; in, Represents the difference in the rate of change of costs, is the slope of the phase ratio change, is the weight adjustment coefficient, is the cost change rate parameter, is the adjustment coefficient, Represents the current stage index, is the total number of stages, is the parameter index; Combine the stage fluctuation change determination result set with the stage boundary parameter set, extract the boundary points marked in the difference set, call the stage fluctuation change determination result set to jointly verify the boundary point position and characteristics, and integrate the boundary points that meet the conditions into the stage boundary parameter set.

4. The construction project cost management system according to claim 3 is characterized in that: The steps for obtaining the segment cost trend parameter set are specifically as follows: Extracting the segmented duration consumption and the project resource input from the stage boundary parameter set, accumulating the resource input of each stage and then standardizing it by stage, calculating the ratio of resource input to stage cost increment by calling the segmented duration consumption, and generating a resource input and cost increment ratio set; Based on the resource input and cost increment ratio set, a fitting model that meets the cost trend is screened, and the model performance is compared by calculating the fitting error interval of multiple models, and the error range is compared and the model parameter set that meets the standard is detected based on the aggregation function, so as to generate a fitting model parameter set that meets the conditions; The correlation between the set of fitting model parameters that meet the conditions and the consumption of the segmented construction period is calculated using the formula: ； Calculate the model error interval and adjust the stage parameters of the fitting model to generate a set of segmented cost trend parameters; in, represents the model error range, is the actual cost value, To predict the cost value for the fitted model, is the number of stages, is the phase duration parameter, is the resource adjustment factor, is the number of resource types, is the stage adjustment factor, is the resource adjustment factor, is the stage index, Index for resources; Combine the qualified fitting model parameter set with the segmented cost trend parameter set, extract the boundary point positions in the cost trend, call the boundary point characteristic values ​​to adjust the model parameters of the stage trend, update and integrate the stage parameter trends, and generate a segmented cost trend parameter set.

5. The construction project cost management system according to claim 4, characterized in that: The steps for obtaining the overall cost trend parameter set are specifically as follows: Based on the stage boundary parameter set and the segment cost trend parameter set, extract the global fitting error of the multi-segment duration and the single-segment parameter smoothness, calculate the error standard deviation and smoothness index of the segment respectively through statistical analysis, and generate a global fitting error and smoothness data set; Extracting segmented data with the best error range and smoothness from the global fitting error and smoothness data set, comparing the errors and smoothness of multiple segments, screening and comparing the demarcation point positions that need to be adjusted through the error range, and generating an adjusted demarcation point position set; Based on the adjusted set of cut-off point locations, use the formula: ； Calculate the error range and smoothness index, modify the segmented fitting trend model parameters, and generate the overall cost trend parameter set; in, represents the indicator value of the modified trend model, Representative The fitting error of the segment, is the mean error, is the standard deviation of error, is the smoothness, is the smoothness average, is the smoothness standard deviation, is the total number of segments; In combination with the adjusted demarcation point position set and the overall cost trend parameter set, the demarcation point position parameters are called to perform parameter correction on the fitting model of the stage cost trend, and the corrected model trend is integrated to generate the overall cost trend parameter set.

6. The construction project cost management system according to claim 5, characterized in that: The steps for obtaining the dynamic cost prediction range are specifically as follows: Extracting the segmented cost increment volatility and trend rate based on the overall cost trend parameter set, and generating a segmented cost increment and trend rate set by calculating the absolute difference value of the segmented cost increment volatility and combining the trend rate calculation fluctuation range; Combine the newly added project data with the segmented cost increment and trend rate set, calculate the cost change interval of each segment, filter the prediction parameters by judging the difference value range between the cost change interval and the characteristics of the newly added project, and generate a prediction parameter range set; For the set of prediction parameter ranges, the formula is used: ； Calculate the cost fluctuation value and adjust the cost parameter range according to the fluctuation value to generate a dynamic cost forecast range; in, Represents the cost fluctuation value, is the cost increment volatility, is the trend rate, is the adjustment factor, is the total number of stages, is the cost trend parameter, is the smoothing adjustment factor, is the current stage index, Index of the cost parameter.

7. The construction project cost management system according to claim 6, characterized in that: The steps for obtaining the real-time dynamic cost parameters are specifically as follows: Based on the dynamic cost forecast range, extract the real-time construction period consumption and cost allocation weight, call the real-time monitored construction period consumption data, analyze the real-time weight change in combination with the historical cost allocation ratio, and generate real-time construction period consumption and cost weight data based on real-time fluctuation analysis; Calculating the real-time cost increment and trend change rate from the real-time construction period consumption and cost weight data, obtaining the real-time increment change trend through differential operation, calculating the real-time cost increment based on the trend rate deviation and generating real-time cost increment and trend change rate data; By comparing the real-time cost increment and trend change rate data with the historical trend parameters, the formula is used: ； Calculate the trend deviation and fluctuation difference, modify the real-time boundary parameters and fit trend change parameters according to the deviation difference, and generate real-time dynamic cost parameters; in, Represents the trend deviation and volatility difference, is the real-time fee increment, is the trend change rate, is the preset trend mean, is the number of data points, is the square of the deviation, To avoid calculating abnormal small values, is the incremental index, is the deviation index.

Images