CN117808499A - Engineering cost management method and system based on big data - Google Patents
Engineering cost management method and system based on big data Download PDFInfo
- Publication number
- CN117808499A CN117808499A CN202410231989.0A CN202410231989A CN117808499A CN 117808499 A CN117808499 A CN 117808499A CN 202410231989 A CN202410231989 A CN 202410231989A CN 117808499 A CN117808499 A CN 117808499A
- Authority
- CN
- China
- Prior art keywords
- data
- cost
- engineering
- construction
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 42
- 238000010276 construction Methods 0.000 claims abstract description 120
- 238000012544 monitoring process Methods 0.000 claims abstract description 81
- 230000008859 change Effects 0.000 claims abstract description 52
- 239000000463 material Substances 0.000 claims abstract description 40
- 238000012502 risk assessment Methods 0.000 claims abstract description 28
- 238000007405 data analysis Methods 0.000 claims abstract description 19
- 238000007477 logistic regression Methods 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 16
- 238000004140 cleaning Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 238000011161 development Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 230000001755 vocal effect Effects 0.000 claims description 4
- 238000013075 data extraction Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000012954 risk control Methods 0.000 description 3
- 238000003756 stirring Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000002759 z-score normalization Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a project cost management method and system based on big data, wherein the method comprises the following steps: s1, acquiring engineering project data, and cleaning the data to obtain engineering cost data; s2, carrying out data analysis on engineering cost data through a cost prediction model to obtain cost change data; s3, carrying out cost prediction on the engineering cost data and the cost change data through a logistic regression model to obtain engineering cost prediction data, and comparing the engineering cost data with the engineering cost prediction data to obtain risk assessment data; and S4, carrying out real-time key monitoring on the engineering project according to the engineering cost data and the cost change data, and carrying out early warning according to the monitoring result. According to the invention, the construction cost is predicted by carrying out construction cost prediction on the engineering, and the real-time change of the predicted material is used for carrying out construction cost prediction, so that the accuracy of risk assessment of the engineering project in construction is improved, and the economic loss caused by risks is reduced.
Description
Technical Field
The invention relates to the field of engineering cost management, in particular to an engineering cost management method and system based on big data.
Background
Along with the rapid development of the times, the scientific technology is continuously updated, the big data technology is also rapidly developed, more and more enterprises begin to try to apply the big data technology to various fields, wherein in the field of engineering cost management, the big data technology is widely applied, the big data technology becomes an effective means for improving the cost control and efficiency of engineering projects, the traditional engineering cost management method often has the problems of insufficient data collection, processing and analysis capability, and the like, the engineering cost management system based on the big data technology can comprehensively analyze and predict various types of data such as market price, material price, labor cost and the like through collecting various types of data, so that the enterprises can better master engineering cost dynamic and risk control, the big data technology can also help the enterprises predict and optimize engineering cost, and through analyzing historical data and market trend, the engineering cost management system can predict future cost trend, thereby helping the enterprises to formulate more scientific and reasonable investment plans and risk control strategies.
However, the existing big data-based engineering cost management method and system do not perform pre-estimation calculation on price fluctuation generated by time variation of materials during engineering construction, so that the big data-based engineering cost management method and system are very easy to delay the engineering and estimate the engineering cost due to price stirring during risk assessment on the engineering cost, and the risk assessment accuracy of the existing big data-based engineering cost management method and system is not ideal, so that the use effect of the existing big data-based engineering cost management method and system is affected, and the use efficiency of the existing big data-based engineering cost management method and system is not ideal.
For the problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a big data-based engineering cost management method and a big data-based engineering cost management system, which have the advantage of being convenient for risk assessment according to price stirring, and further solve the problem that the accuracy of risk assessment is not ideal.
In order to realize the advantage of being convenient for risk assessment according to price stirring, the invention adopts the following specific technical scheme:
according to an aspect of the present invention, there is provided a construction cost management method based on big data, the method comprising the steps of:
s1, acquiring engineering project data, and cleaning the data to obtain engineering cost data;
s2, analyzing engineering cost data through a preset cost prediction model to obtain cost change data;
s3, carrying out cost prediction on the engineering cost data and the cost change data through a logistic regression model to obtain engineering cost prediction data, and comparing the engineering cost data with the engineering cost prediction data to obtain risk assessment data;
s4, carrying out real-time monitoring on engineering projects according to the risk assessment data and the cost change data, and carrying out early warning according to monitoring results;
s5, generating an adjusting scheme according to the early warning result, adjusting the engineering construction scheme through the adjusting scheme, calculating the engineering adjusting cost according to the adjusted engineering construction scheme, and feeding back in real time.
Preferably, the engineering project data are obtained and data cleaning is performed, and the engineering cost data are obtained, which comprises the following steps:
s11, classifying the acquired data according to engineering projects, constructing a data set according to classification results, and performing data deduplication on the data set;
s12, filling data into the data set subjected to data deduplication;
s13, performing data outlier processing through the data set filled with data;
s14, carrying out data normalization on the data set processed by the abnormal value to obtain engineering cost data.
Preferably, the data analysis is performed on the engineering cost data through a cost prediction model, and the obtaining of the cost change data comprises the following steps:
s21, extracting data characteristics of engineering cost data, and dividing the data characteristic extraction result into a training set and a testing set;
s22, carrying out model training by taking the training set into the cost prediction model, evaluating the cost prediction model through the testing set, calculating an error value of the cost prediction model, and optimizing the cost prediction model by utilizing the error value to obtain a trained cost prediction model;
s23, predicting the engineering cost data after the data feature extraction by using the trained cost prediction model, and calculating the error between the predicted value and the engineering cost data to obtain cost change data.
Preferably, the cost prediction is performed on the engineering cost data and the cost change data through a logistic regression model to obtain engineering cost prediction data, and the risk assessment data is obtained by comparing the engineering cost data with the engineering cost prediction data, comprising the following steps:
s31, extracting data of engineering cost data and cost change data, and dividing the engineering cost data and the cost change data into a development set and a verification set according to key data extraction results;
s32, carrying out model training by taking the development set into a logistic regression model, evaluating the logistic regression model through the verification set, and calculating the engineering cost data and the cost change data by using the logistic regression model to obtain engineering cost prediction data;
s33, comparing the engineering cost data with the engineering cost prediction data, and acquiring risk assessment data.
Preferably, comparing the construction cost data with the construction cost prediction data, and acquiring the risk assessment data includes the steps of:
s331, carrying out data formatting on engineering cost data and engineering cost prediction data;
and S332, calculating a difference value of the engineering cost data and the engineering cost prediction data after the data formatting, and acquiring risk assessment data according to a calculation result.
Preferably, the real-time key monitoring of the engineering project is carried out according to the engineering cost data and the cost change data, and the early warning is carried out according to the monitoring result, comprising the following steps:
s41, acquiring engineering material prices according to engineering cost data and cost change data, arranging priorities through the material prices, and distributing monitoring paths according to arrangement results;
s42, monitoring data analysis is carried out on engineering project workers by adopting a Kalman filter algorithm according to the monitoring path, and analysis results are classified;
s43, performing corresponding processing according to the classified monitoring data.
Preferably, the monitoring data analysis of engineering project workers by adopting a Kalman filter algorithm according to the monitoring path, the monitoring data analysis of engineering project workers by adopting a target tracking algorithm according to the monitoring path, and the classification of the analysis result comprises the following steps:
s421, determining an index and a threshold value of the engineering project worker during detection according to the work types of the engineering project worker;
s422, carrying out engineering construction monitoring on engineering project workers through a Kalman filter algorithm according to the monitoring path to obtain monitoring data;
s423, analyzing the monitoring data, classifying according to the analysis result, and sending out corresponding early warning according to the classification result.
Preferably, the monitoring data is analyzed, classified according to the analysis result, and corresponding early warning is sent out according to the classification result, comprising the following steps:
s4231, analyzing results are divided into construction period delay, material loss and important supervision;
s4232, dividing the early warning into a verbal warning, a interview warning and an open warning, and corresponding to the construction period delay and the important supervision of material loss.
Preferably, an adjusting scheme is set according to the early warning result, the engineering construction scheme is adjusted through the adjusting scheme, the engineering adjustment cost is calculated according to the adjusted engineering construction scheme, and real-time feedback is performed, wherein the method comprises the following steps:
s51, generating a criticizing scheme, an appointment scheme and an opening scheme according to the oral warning, the appointment warning and the opening warning;
s52, adjusting the construction scheme of the engineering project workers according to the criticizing scheme, the interviewing scheme and the opening scheme, and collecting the follow-up monitoring data of the engineering project workers for examination;
and S53, calculating the engineering adjustment cost according to the examination result, and presetting an out-of-range value to feed the engineering adjustment cost back to engineering supervision staff in real time.
According to another aspect of the present invention, there is provided a construction cost management system based on big data, the system comprising:
the engineering data acquisition module is used for acquiring engineering project data and cleaning the data to obtain engineering cost data;
the construction cost change module is used for carrying out data analysis on construction cost data through the cost prediction model to obtain construction cost change data;
the project prediction evaluation module is used for predicting the cost of the project cost data and the cost change data through a logistic regression model to obtain project cost prediction data, and comparing the project cost data with the project cost prediction data to obtain risk evaluation data;
the engineering monitoring management module is used for carrying out real-time key monitoring on engineering projects according to engineering cost data and cost change data and carrying out early warning according to monitoring results;
and the engineering project adjusting module is used for setting an adjusting scheme according to the early warning result, adjusting the engineering construction scheme through the adjusting scheme, calculating the engineering adjusting cost according to the adjusted engineering construction scheme and feeding back engineering supervision personnel in real time.
Compared with the prior art, the invention provides a big data-based engineering cost management method and system, which have the following beneficial effects:
(1) According to the invention, the construction cost is predicted by the engineering, the real-time change of the predicted material is used for predicting the construction cost, the accuracy of risk assessment of the engineering project during construction is improved, the economic loss caused by risks is reduced, and meanwhile, the delay of the engineering progress caused by overlarge construction cost errors during engineering construction is improved, so that the engineering cost management method and system based on big data are more accurate in managing the engineering cost, and the use efficiency of the engineering cost management method and system based on big data is improved.
(2) The invention monitors workers in engineering projects in real time, so that the efficiency of the workers in engineering construction is conveniently monitored, engineering delay caused by human factors is reduced, meanwhile, the material consumption in engineering construction is conveniently confirmed by monitoring materials, the loss of materials in engineering construction is reduced, the efficiency of engineering construction is improved, the increase of engineering cost is conveniently reduced, and the management effect of the engineering cost management method and system based on big data on the engineering cost is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a big data based project cost management method according to an embodiment of the present invention;
fig. 2 is a system schematic block diagram of a big data based project cost management system in accordance with an embodiment of the present invention.
In the figure:
1. an engineering data acquisition module; 2. a construction cost change module; 3. an engineering prediction evaluation module; 4. an engineering monitoring management module; 5. and an engineering project adjusting module.
Detailed Description
For the purpose of further illustrating the various embodiments, the present invention provides the accompanying drawings, which are a part of the disclosure of the present invention, and which are mainly used to illustrate the embodiments and, together with the description, serve to explain the principles of the embodiments, and with reference to these descriptions, one skilled in the art will recognize other possible implementations and advantages of the present invention, wherein elements are not drawn to scale, and like reference numerals are generally used to designate like elements.
According to the embodiment of the invention, a method and a system for managing engineering cost based on big data are provided.
The invention will now be further described with reference to the accompanying drawings and detailed description, as shown in fig. 1, a big data based construction cost management method according to an embodiment of the invention, comprising the steps of:
s1, acquiring engineering project data, and cleaning the data to obtain engineering cost data;
specifically, the engineering project data are obtained, data cleaning is carried out, and the engineering cost data are obtained, which comprises the following steps:
s11, classifying the acquired data according to engineering projects, constructing a data set according to classification results, and performing data deduplication on the data set;
specifically, it is determined which data needs to be collected, such as engineering plans, construction drawings, bill of materials, personnel arrangements, etc., and when collecting engineering project data, duplicate records are subjected to deduplication processing, and unique records are reserved.
S12, filling data into the data set subjected to data deduplication;
specifically, interpolation is adopted for filling missing values of collected engineering project data, the missing values of the engineering project data are checked, data needing to be filled are determined, the minimum value and the maximum value of existing numerical values in the engineering project data are found, the existing data are ordered from small to large according to the numerical values, differences between adjacent data points are calculated, the differences form a sequence, each missing value needing to be filled is found, the existing data points on the left side and the right side of the missing value needing to be filled are found, the distance proportion between the missing values and the data needing to be filled is calculated, and filling is carried out according to the distance proportion.
S13, performing data outlier processing through the data set filled with data;
specifically, the data outlier in engineering project data is corrected by adopting an LSTM time sequence model, model training and parameter optimization are carried out, existing data is input into the model, prediction of future data points is carried out, the future data value predicted by the model is compared with an actual data value, errors between the future data value and the actual data value are calculated, the error value is obtained, the error data value is calculated based on the last data of the error value, and the original data outlier is replaced.
S14, carrying out data normalization on the data set processed by the abnormal value to obtain engineering cost data.
Specifically, the data type of each field in the dataset is checked, ensuring that it is a continuous type variable, not a typed variable or a text type variable, and the mean and standard deviation of each field is calculated by checking the data range and unit of each field using Z-score normalization, and then subtracting the mean from each data point and dividing by the standard deviation.
S2, analyzing engineering cost data through a preset cost prediction model to obtain cost change data;
specifically, the engineering cost data is subjected to data analysis through a cost prediction model, and the cost change data is obtained by the following steps:
s21, extracting data characteristics of engineering cost data, and dividing the data characteristic extraction result into a training set and a testing set;
specifically, the engineering cost data generally comprises a plurality of monetary value data, statistical characteristics, correlation characteristics, time sequence characteristics and space characteristics in the engineering cost data are extracted, and training sets and testing sets are distributed according to 30% of the training sets and 70% of the testing sets;
statistical characteristics: engineering cost data typically comprise numerous monetary value data, and features such as mean, median, standard deviation, maximum and minimum values are known from statistical features to data distribution, bias, and dispersion.
Correlation characteristics: in engineering cost data, different projects or cost constitution projects may have the conditions of mutual association or dependence, and influence relations among the data are understood by calculating indexes such as correlation coefficients, covariance and the like among various fields.
Time sequence characteristics: engineering cost data is usually recorded according to time sequence, characteristics of trend, periodicity, seasonality and the like of the data are extracted through a time sequence analysis method, future trend and abnormal events are predicted, and cost control and risk management are carried out.
Spatial characteristics: and extracting the characteristics of distribution, clustering, thermodynamic diagram and the like of the related characteristic calculation data by using a spatial data analysis method so as to better know the spatial distribution and change rule of the data.
S22, carrying out model training by taking the training set into the cost prediction model, evaluating the cost prediction model through the testing set, calculating an error value of the cost prediction model, and optimizing the cost prediction model by utilizing the error value to obtain a trained cost prediction model;
specifically, the cost prediction model is a linear regression model, and the formula of the linear regression model is:
wherein,predicting the construction cost for the engineering;
regression coefficients for initial parameters of the model;
regression coefficients for the first parameters of the model;
regression coefficients for model n parameters;
is->Factors influencing engineering cost by regression coefficients;
is->Regression coefficients influence the engineering cost factors.
And inputting the test set into the trained model for prediction, and calculating an error value between the predicted value and the actual value.
S23, predicting the engineering cost data after the data feature extraction by using the trained cost prediction model, and calculating the error between the predicted value and the engineering cost data to obtain cost change data.
Specifically, the error between the calculated predicted value and the actual value is calculated by adopting a mean square error, and the cost change data is obtained by comparing the difference between the actual cost and the predicted cost.
The mean square error calculation formula is:
wherein,is an error value;
the number of the engineering cost data samples is the number of the engineering cost data samples;
is a practical value;
to predict the value.
S3, carrying out cost prediction on the engineering cost data and the cost change data through a logistic regression model to obtain engineering cost prediction data, and comparing the engineering cost data with the engineering cost prediction data to obtain risk assessment data;
specifically, the construction cost data and the construction cost change data are subjected to cost prediction through a logistic regression model to obtain construction cost prediction data, and the risk assessment data are obtained by comparing the construction cost data with the construction cost prediction data, wherein the risk assessment data comprise the following steps:
s31, extracting data of engineering cost data and cost change data, and dividing the engineering cost data and the cost change data into a development set and a verification set according to key data extraction results;
s32, carrying out model training by taking the development set into a logistic regression model, evaluating the logistic regression model through the verification set, and calculating the engineering cost data and the cost change data by using the logistic regression model to obtain engineering cost prediction data;
s33, comparing the engineering cost data with the engineering cost prediction data, and acquiring risk assessment data.
Specifically, comparing the construction cost data with the construction cost prediction data, and obtaining the risk assessment data includes the following steps:
s331, carrying out data formatting on engineering cost data and engineering cost prediction data;
specifically, the construction cost data and the construction cost prediction data are respectively placed in different tables, each row represents a data point, each column represents a variable, and units related to the construction cost data and the construction cost prediction data are unified.
And S332, calculating a difference value of the engineering cost data and the engineering cost prediction data after the data formatting, and acquiring risk assessment data according to a calculation result.
Specifically, the relative error refers to the difference between the actual value and the predicted value divided by the absolute value of the actual value, and if the result is a positive number, the actual value is greater than the predicted value; if the result is negative, the actual value is smaller than the predicted value, and if the difference value is smaller, the predicted result is more accurate, and the risk is lower; if the difference value is larger, the prediction result is not accurate enough, the risk is higher, and corresponding risk control measures can be formulated according to the magnitude of the difference value so as to reduce the risk.
S4, carrying out real-time monitoring on engineering projects according to the risk assessment data and the cost change data, and carrying out early warning according to monitoring results;
specifically, the method for carrying out real-time key monitoring on the engineering project according to the engineering cost data and the cost change data and carrying out early warning according to the monitoring result comprises the following steps:
s41, acquiring engineering material prices according to engineering cost data and cost change data, arranging priorities through the material prices, and distributing monitoring paths according to arrangement results;
specifically, it is first required to determine what material price indexes need to be monitored, such as raw material price, transportation cost, tax, etc., different monitoring indexes can be selected according to different material and service requirements, relevant material price data can be collected and arranged into a form of a table or a database for further processing and analysis, the distance from each purchasing point to each supplier and transportation cost are calculated by analyzing the data by using a data analysis tool and are evaluated by combining the monitoring indexes, an optimal monitoring path is formulated according to the data analysis result, including selecting the optimal suppliers and purchasing points, optimizing the logistics path, reducing the logistics cost, etc., and corresponding measures are implemented according to the formulated monitoring path scheme, such as establishing a purchasing plan, coordinating logistics transportation, arranging stock, etc., so as to set the monitoring path.
S42, monitoring data analysis is carried out on engineering project workers by adopting a Kalman filter algorithm according to the monitoring path, and analysis results are classified;
s43, performing corresponding processing according to the classified monitoring data.
Specifically, the monitoring data analysis is performed on engineering project workers by adopting a target tracking algorithm according to the monitoring path, the monitoring data analysis is performed on the engineering project workers by adopting the target tracking algorithm according to the monitoring path, and the analysis result is classified, and the method comprises the following steps:
s421, determining an index and a threshold value of the engineering project worker during detection according to the work types of the engineering project worker;
s422, carrying out engineering construction monitoring on engineering project workers through a Kalman filter algorithm according to the monitoring path to obtain monitoring data;
specifically, the occurrence frequency of workers is monitored at the intersection through setting cameras, engineering project indexes such as construction progress, personnel workload, equipment conditions and the like which need to be monitored are determined, relevant monitoring data are collected and are arranged into a form of a table or a database so as to be further processed and analyzed, a Kalman filter algorithm is used for establishing a state model, namely, a construction state model comprising state variables, observation variables, state transition equations, observation equations and the like is deduced according to the monitoring data, state estimation values are updated according to the current observation values and the previous state information, state errors, state covariance matrixes and the like are calculated, and workers of the engineering projects are monitored and evaluated according to the state estimation results, such as whether the workers arrive on time, whether the working strength is reasonable or not and the like.
Specifically, it is first necessary to determine the state variables that need to be monitored, such as position, velocity, acceleration, etc. According to different engineering projects and monitoring requirements, different state variables can be selected, then the variables used for observing the state variables, such as measured values output by a sensor or other monitoring equipment, are required to be determined, the relation among the state variables, namely a state transition equation, is established according to a physical principle or an empirical rule, and then how to map the actual measured values onto the state variables is determined, so that an observation equation is established. The observation equation is usually nonlinear, and needs to be linearized, before the state estimation using the kalman filter algorithm is started, the state variable and the covariance matrix need to be initialized, and in the monitoring process, the state update using the kalman filter algorithm is performed according to the observation value and the previous state information, including a prediction step and an update step, the prediction step is used for predicting the state value and the covariance matrix of the next time step, and the update step is used for performing the state estimation and the covariance matrix update according to the observation value and the prediction value.
S423, analyzing the monitoring data, classifying according to the analysis result, and sending out corresponding early warning according to the classification result.
Specifically, the monitoring data are analyzed, the analysis results are classified, and corresponding early warning is sent out according to the classification results, and the method comprises the following steps:
s4231, analyzing results are divided into construction period delay, material loss and important supervision;
specifically, the construction period delay is that the material is not lost, but the construction progress is not attached to the preset construction progress, the material is lost and is lost, but the construction progress is attached to the preset construction progress, the important supervision is that the material is lost, and the construction progress is not attached to the preset construction progress.
S4232, dividing the early warning into a verbal warning, a interview warning and an open warning, and corresponding to the construction period delay and the important supervision of material loss.
Specifically, when the construction period is delayed, a verbal warning scheme is generated for the engineering construction workers, the workers are required to improve the construction efficiency, when the materials are lost, an appointment scheme is generated for the engineering construction workers, warning punishment is performed for the workers according to the appointment result, when the important supervision is performed, a division scheme is generated for the engineering construction workers, and the lost material price is required to be compensated for by the workers.
S5, generating an adjusting scheme according to the early warning result, adjusting the engineering construction scheme through the adjusting scheme, calculating the engineering adjusting cost according to the adjusted engineering construction scheme, and feeding back in real time.
Specifically, an adjusting scheme is set according to the early warning result, the engineering construction scheme is adjusted through the adjusting scheme, the engineering adjustment cost is calculated according to the adjusted engineering construction scheme, and real-time feedback is carried out, and the method comprises the following steps:
s51, according to the spoken warning, the appointment warning and the prescribing warning, the production criticizing scheme, the appointment scheme and the prescribing scheme;
specifically, the criticizing scheme is to carry out lazy criticizing warning on engineering project workers with construction period delay, the talking about scheme is to carry out talking about warning on engineering project workers with material theft, and the removing scheme is to remove and fine engineering project workers with material theft.
S52, adjusting the construction scheme of the engineering project workers according to the criticizing scheme, the interviewing scheme and the opening scheme, and collecting the follow-up monitoring data of the engineering project workers for examination;
specifically, the method comprises the steps of carrying out key monitoring on lazy criticizing warning, avoiding lazy engineering project workers, carrying out post replacement on the engineering project workers about talking warning, carrying out key monitoring, reducing material stealing by workers, recording the removed engineering project workers and adding a blacklist.
And S53, calculating the engineering adjustment cost according to the examination result, and presetting an out-of-range value to feed the engineering adjustment cost back to engineering supervision staff in real time.
Specifically, the missing engineering project materials are added, the prices of the added engineering project materials are recorded, the amount of the supplementary materials is preset, real-time feedback is carried out on engineering responsible persons according to the ratio of the prices of the added engineering project materials to the amount of the supplementary materials, and the overflow of engineering cost is reduced.
According to another embodiment of the present invention, as shown in fig. 2, there is provided a construction cost management system based on big data, the system including:
the engineering data acquisition module is used for acquiring engineering project data and cleaning the data to obtain engineering cost data;
the construction cost change module is used for carrying out data analysis on construction cost data through the cost prediction model to obtain construction cost change data;
the project prediction evaluation module is used for predicting the cost of the project cost data and the cost change data through a logistic regression model to obtain project cost prediction data, and comparing the project cost data with the project cost prediction data to obtain risk evaluation data;
the engineering monitoring management module is used for carrying out real-time key monitoring on engineering projects according to engineering cost data and cost change data and carrying out early warning according to monitoring results;
and the engineering project adjusting module is used for setting an adjusting scheme according to the early warning result, adjusting the engineering construction scheme through the adjusting scheme, calculating the engineering adjusting cost according to the adjusted engineering construction scheme and feeding back in real time.
In summary, by means of the technical scheme, the engineering cost is predicted by predicting the engineering cost and predicting the real-time change of materials, so that the accuracy of risk assessment of engineering projects in construction is improved, economic loss caused by risks is reduced, and meanwhile, the engineering progress delay caused by overlarge cost errors in engineering construction is improved, so that the engineering cost management method and system based on big data are more accurate in managing the engineering cost, and the use efficiency of the engineering cost management method and system based on big data is improved.
In addition, the invention can monitor the efficiency of workers in engineering construction conveniently by monitoring workers in real time, reduce engineering delay caused by human factors, and can confirm the material consumption in engineering construction conveniently by monitoring materials, reduce the loss of materials in engineering construction, improve the efficiency of engineering construction, reduce the increase of engineering cost and improve the management effect of engineering cost management method and system based on big data on engineering cost.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (10)
1. The engineering cost management method based on big data is characterized by comprising the following steps:
s1, acquiring engineering project data, and cleaning the data to obtain engineering cost data;
s2, analyzing engineering cost data through a preset cost prediction model to obtain cost change data;
s3, carrying out cost prediction on the engineering cost data and the cost change data through a logistic regression model to obtain engineering cost prediction data, and comparing the engineering cost data with the engineering cost prediction data to obtain risk assessment data;
s4, carrying out real-time monitoring on engineering projects according to the risk assessment data and the cost change data, and carrying out early warning according to monitoring results;
s5, generating an adjusting scheme according to the early warning result, adjusting the engineering construction scheme through the adjusting scheme, calculating the engineering adjusting cost according to the adjusted engineering construction scheme, and feeding back in real time.
2. The method for managing construction cost based on big data according to claim 1, wherein the steps of obtaining construction project data and performing data cleaning to obtain construction cost data comprise the steps of:
s11, classifying the acquired data according to engineering projects, constructing a data set according to classification results, and performing data deduplication on the data set;
s12, filling data into the data set subjected to data deduplication;
s13, performing data outlier processing through the data set filled with data;
s14, carrying out data normalization on the data set processed by the abnormal value to obtain engineering cost data.
3. The construction cost management method based on big data according to claim 1, wherein the data analysis of the construction cost data through the cost prediction model, the obtaining of the construction cost variation data comprises the steps of:
s21, extracting data characteristics of engineering cost data, and dividing the data characteristic extraction result into a training set and a testing set;
s22, carrying out model training by taking the training set into the cost prediction model, evaluating the cost prediction model through the testing set, calculating an error value of the cost prediction model, and optimizing the cost prediction model by utilizing the error value to obtain a trained cost prediction model;
s23, predicting the engineering cost data after the data feature extraction by using the trained cost prediction model, and calculating the error between the predicted value and the engineering cost data to obtain cost change data.
4. The method for managing construction costs based on big data according to claim 1, wherein the cost prediction is performed on the construction costs data and the construction costs variation data by a logistic regression model to obtain construction costs prediction data, and the risk assessment data is obtained by comparing the construction costs data with the construction costs prediction data, comprising the steps of:
s31, extracting data of engineering cost data and cost change data, and dividing the engineering cost data and the cost change data into a development set and a verification set according to key data extraction results;
s32, carrying out model training by taking the development set into a logistic regression model, evaluating the logistic regression model through the verification set, and calculating the engineering cost data and the cost change data by using the logistic regression model to obtain engineering cost prediction data;
s33, comparing the engineering cost data with the engineering cost prediction data, and acquiring risk assessment data.
5. The method of claim 4, wherein the comparing the construction cost data with the construction cost prediction data and obtaining the risk assessment data comprises the steps of:
s331, carrying out data formatting on engineering cost data and engineering cost prediction data;
and S332, calculating a difference value of the engineering cost data and the engineering cost prediction data after the data formatting, and acquiring risk assessment data according to a calculation result.
6. The construction cost management method based on big data according to claim 1, wherein the real-time key monitoring of the construction project is performed according to the construction cost data and the construction cost change data, and the early warning is performed according to the monitoring result, comprising the steps of:
s41, acquiring engineering material prices according to engineering cost data and cost change data, arranging priorities through the material prices, and distributing monitoring paths according to arrangement results;
s42, monitoring data analysis is carried out on engineering project workers by adopting a Kalman filter algorithm according to the monitoring path, and analysis results are classified;
s43, performing corresponding processing according to the classified monitoring data.
7. The method for managing construction costs based on big data according to claim 6, wherein the monitoring data analysis of construction project workers using a kalman filter algorithm according to the monitoring path, the monitoring data analysis of construction project workers using a target tracking algorithm according to the monitoring path, and the classification of the analysis result comprises the steps of:
s421, determining an index and a threshold value of the engineering project worker during detection according to the work types of the engineering project worker;
s422, carrying out engineering construction monitoring on engineering project workers through a Kalman filter algorithm according to the monitoring path to obtain monitoring data;
s423, analyzing the monitoring data, classifying according to the analysis result, and sending out corresponding early warning according to the classification result.
8. The construction cost management method based on big data according to claim 7, wherein the analyzing the monitoring data, classifying according to the analysis result, and sending out the corresponding pre-warning according to the classification result comprises the steps of:
s4231, analyzing results are divided into construction period delay, material loss and important supervision;
s4232, dividing the early warning into a verbal warning, a interview warning and an open warning, and corresponding to the construction period delay and the important supervision of material loss.
9. The method for managing construction cost based on big data according to claim 8, wherein the step of setting an adjustment scheme according to the pre-warning result, adjusting the construction scheme by the adjustment scheme, calculating the construction adjustment cost according to the adjusted construction scheme, and feeding back in real time comprises the steps of:
s51, according to the spoken warning, the appointment warning and the prescribing warning, the production criticizing scheme, the appointment scheme and the prescribing scheme;
s52, adjusting the construction scheme of the engineering project workers according to the criticizing scheme, the interviewing scheme and the opening scheme, and collecting the follow-up monitoring data of the engineering project workers for examination;
and S53, calculating the engineering adjustment cost according to the examination result, and presetting an out-of-range value to feed the engineering adjustment cost back to engineering supervision staff in real time.
10. A big data based construction cost management system for implementing the big data based construction cost management method of any of claims 1-9, characterized in that the system comprises:
the engineering data acquisition module is used for acquiring engineering project data and cleaning the data to obtain engineering cost data;
the construction cost change module is used for carrying out data analysis on construction cost data through the cost prediction model to obtain construction cost change data;
the project prediction evaluation module is used for predicting the cost of the project cost data and the cost change data through a logistic regression model to obtain project cost prediction data, and comparing the project cost data with the project cost prediction data to obtain risk evaluation data;
the engineering monitoring management module is used for carrying out real-time key monitoring on engineering projects according to engineering cost data and cost change data and carrying out early warning according to monitoring results;
and the engineering project adjusting module is used for setting an adjusting scheme according to the early warning result, adjusting the engineering construction scheme through the adjusting scheme, calculating the engineering adjusting cost according to the adjusted engineering construction scheme and feeding back engineering supervision personnel in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410231989.0A CN117808499A (en) | 2024-03-01 | 2024-03-01 | Engineering cost management method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410231989.0A CN117808499A (en) | 2024-03-01 | 2024-03-01 | Engineering cost management method and system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117808499A true CN117808499A (en) | 2024-04-02 |
Family
ID=90421978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410231989.0A Pending CN117808499A (en) | 2024-03-01 | 2024-03-01 | Engineering cost management method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117808499A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170308934A1 (en) * | 2016-04-22 | 2017-10-26 | Economy Research Institute of State Grid Zhejiang Electric Power | Management method of power engineering cost |
| CN112348332A (en) * | 2020-10-26 | 2021-02-09 | 郑州铁路职业技术学院 | Engineering cost monitored control system based on cloud calculates |
| CN113793079A (en) * | 2021-11-18 | 2021-12-14 | 捷宏润安工程顾问有限公司 | Engineering cost project management system and method based on big data |
| CN114997462A (en) * | 2022-04-21 | 2022-09-02 | 华北电力大学 | Power grid line project cost prediction method based on machine learning |
| CN116955936A (en) * | 2023-07-28 | 2023-10-27 | 深圳全企通信息技术有限公司 | Enterprise big data algorithm attribute data prediction method |
| CN117273541A (en) * | 2023-10-12 | 2023-12-22 | 翔风工程管理咨询(河南)有限公司 | Building engineering cost quality evaluation system based on big data |
-
2024
- 2024-03-01 CN CN202410231989.0A patent/CN117808499A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170308934A1 (en) * | 2016-04-22 | 2017-10-26 | Economy Research Institute of State Grid Zhejiang Electric Power | Management method of power engineering cost |
| CN112348332A (en) * | 2020-10-26 | 2021-02-09 | 郑州铁路职业技术学院 | Engineering cost monitored control system based on cloud calculates |
| CN113793079A (en) * | 2021-11-18 | 2021-12-14 | 捷宏润安工程顾问有限公司 | Engineering cost project management system and method based on big data |
| CN114997462A (en) * | 2022-04-21 | 2022-09-02 | 华北电力大学 | Power grid line project cost prediction method based on machine learning |
| CN116955936A (en) * | 2023-07-28 | 2023-10-27 | 深圳全企通信息技术有限公司 | Enterprise big data algorithm attribute data prediction method |
| CN117273541A (en) * | 2023-10-12 | 2023-12-22 | 翔风工程管理咨询(河南)有限公司 | Building engineering cost quality evaluation system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109272140A (en) | A kind of transformer equipment runtime forecasting of cost method based on big data analysis | |
| CN115630839B (en) | Intelligent feedback production regulation and control system based on data mining | |
| US20210350337A1 (en) | Systems and methods for managing populations of utility poles | |
| CN116308211B (en) | Enterprise intelligent management system and method based on big data | |
| CN111950577A (en) | Point inspection method and device | |
| Ungermann et al. | Data analytics for manufacturing systems–a data-driven approach for process optimization | |
| CN116862289A (en) | Engineering cost index management method, system, terminal equipment and storage medium | |
| CN117151448B (en) | Intelligent workshop management system based on digital production platform | |
| CN113628024A (en) | Financial data intelligent auditing system and method based on big data platform system | |
| CN116629726B (en) | Environment monitoring management method and system for precise copper pipe packaging workshop | |
| CN112598227A (en) | Power economic index construction method and system based on power data | |
| CN117808499A (en) | Engineering cost management method and system based on big data | |
| Ståhl et al. | Dynamic manufacturing costs—Describing the dynamic behavior of downtimes from a cost perspective | |
| CN114282697A (en) | Method and system for determining differential performance of equipment suppliers | |
| CN109255470A (en) | A kind of non-item class forecasting of cost method of transformer equipment based on big data analysis | |
| CN117010549A (en) | Information tracing method and terminal based on big data management system | |
| RU2295590C1 (en) | Method of the statistical control over the quality of the electrode products | |
| CN114048592A (en) | Finish rolling whole-flow distributed operation performance evaluation and non-optimal reason tracing method | |
| CN113762791A (en) | Railway engineering cost management system | |
| RU2503015C2 (en) | System to control power consumption of industrial enterprises and production facilities | |
| CN111950760A (en) | Labor demand prediction system and prediction method based on machine learning algorithm | |
| Shahin et al. | Estimating overall equipment effectiveness for continuous production lines: with a case study in Esfahan Steel Company | |
| CN116976861B (en) | Maintenance data management method and system for copper pipe production workshop equipment | |
| CN117273467B (en) | Multi-factor coupling-based industrial safety risk management and control method and system | |
| Bouché et al. | AMELIOS Suite or the Fives Digital Package for Carbon 4.0 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |