Multi-period auditing data processing method based on project cost budget and bidding

Abstract

The invention discloses a multi-period audit data processing method based on project cost budget and price, and belongs to the technical field of project cost, and the method comprises the following steps: S1, carrying out the collection and preprocessing of the multi-period audit data of project cost budget and price; s2, performing real-time analysis and prediction on the multi-period auditing data of the project cost budget according to the optimal project cost budget auditing prediction model, determining a project cost budget auditing prediction result, and performing timely early warning and intervention on abnormal behaviors; and S3, displaying the project cost budget pricing multi-period auditing data report in a visual form. According to the method, the problems that the existing multi-period auditing data of the project cost budget cannot be effectively processed and predicted, and the project cost budget auditing effect is poor are solved. The method can effectively process and predict the multi-period auditing data of the project cost budget, can monitor the project cost budget and discover abnormal behaviors in real time, and can improve the project cost budget auditing effect.

Description

Technical Field

[0001] The invention relates to the technical field of engineering cost, and in particular to a method for processing data based on multi-period audit of engineering cost budget appraisal. Background Art

[0002] Project cost budget review refers to the one-time investment estimate of the proposed project based on the project design drawings, construction organization design, equipment list and other related materials, in accordance with the policies, specifications, standards and technical requirements issued by the state and industry authorities, with reference to the actual cost experience data of similar projects, combined with the project's geographical location, geological conditions, climate and environment and other factors, using appropriate pricing basis and methods. Simply put, it is the process of estimating and controlling the pre-construction costs of the project.

[0003] The Chinese patent with publication number CN115100001A discloses a method for engineering cost consulting, which involves cost consulting technology. The key points of its technical solution are: establish a file library with each blank land; conduct on-site survey and mapping based on the content of the file library, collect field data, and load it into the file library; require the consultant to input BIM model and engineering evaluation sheet information; compare the engineering evaluation sheet information with the content of the file library; if there is no match, the file library shall prevail, and if there is a match, proceed to the next step; the consultant's consulting information can be compared with the actual information to ensure that the data in the subsequent consulting process is correct, avoid the occurrence of building structure errors during the construction process after the consultation, and avoid negative impacts on the consultant and the consulting company; however, the patent has the following defects: Existing technologies cannot effectively process and predict multi-period audit data of engineering cost budget appraisal, cannot monitor engineering cost budget appraisal in real time and discover abnormal behavior, resulting in poor results of engineering cost budget appraisal. Summary of the invention

[0004] The purpose of the present invention is to provide a method for processing multi-period audit data based on engineering cost budget appraisal, which can effectively process and predict multi-period audit data of engineering cost budget appraisal, can monitor engineering cost budget appraisal in real time and discover abnormal behavior, can improve the effect of engineering cost budget appraisal, and solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: The data processing method based on multi-period review of engineering cost budget includes the following steps: S1: Collecting multi-period audit data of engineering cost budget review and valuation, pre-processing the multi-period audit data of engineering cost budget review and valuation, determining standardized multi-period audit data of engineering cost budget review and valuation, and integrating and storing the standardized multi-period audit data of engineering cost budget review and valuation; S2: Construct an optimal engineering cost budget review prediction model, and conduct real-time analysis and prediction of standardized engineering cost budget review multi-period audit data based on the optimal engineering cost budget review prediction model to determine whether there are any abnormalities in the engineering cost budget review process, determine the engineering cost budget review prediction results, and conduct timely warning and intervention for abnormal behaviors; S3: A multi-period audit data report on the engineering cost budget review is generated based on the multi-period audit data of the engineering cost budget review and the forecast results of the engineering cost budget review, and the multi-period audit data report on the engineering cost budget review is displayed in a visual form, so that the staff can check and discover budget review problems in the engineering cost project in a timely manner.

[0006] Preferably, in S1, multiple review data of the project cost budget appraisal are collected, and the following operations are performed: Real-time monitoring and collection of construction equipment costs, labor costs, material costs, management fees, taxes and profits in engineering cost items are carried out to determine multi-period audit data for engineering cost budget review.

[0007] Preferably, in S1, the multi-period audit data of the project cost budget appraisal is preprocessed, and the following operations are performed: Obtain multi-period audit data of project cost budget review; Clean the multi-period audit data of engineering cost budget review, including: Conduct consistency checks on multiple audit data of project cost budget review; According to the data consistency requirements, check whether there are inconsistent data that are useless for the engineering cost budget review in the multi-period review data of the engineering cost budget review, and remove the inconsistent data in the multi-period review data of the engineering cost budget review; Check invalid and missing values ​​of multiple audit data of project cost budget appraisal; According to the requirements of data validity and integrity, check whether there are invalid values ​​and missing values ​​that are useless for the engineering cost budget review in the multi-period review data of the engineering cost budget review, and remove the invalid values ​​and missing values ​​in the multi-period review data of the engineering cost budget review; Determine the multi-period audit data for the engineering cost budget review that is useful for the engineering cost budget review.

[0008] Preferably, in S1, the multi-period audit data of the project cost budget appraisal is preprocessed, and the following operations are further performed: After checking invalid values ​​and missing values ​​of multiple audit data of engineering cost budget appraisal, the number of data corresponding to invalid values ​​and the number of missing values ​​corresponding to missing values ​​are extracted; Extracting the data type corresponding to the invalid value and the weight value corresponding to the data type; Obtaining an invalid value weight coefficient using a weight value of the data type corresponding to the invalid value; The invalid value weight coefficient is obtained by the following formula:

[0009] Among them, S w represents the weight coefficient of invalid values; n represents the number of data corresponding to invalid values; w i Indicates the weight value corresponding to the data type of the i-th invalid value; w max Indicates the maximum weight value corresponding to the data type of all invalid values; C wi represents the amount of data corresponding to the i-th invalid value; C wyi represents the amount of data corresponding to the valid value of the same data type closest to the time when the i-th invalid value was generated; w p Indicates the average weight value corresponding to all valid values; Comparing the invalid value weight coefficient with a preset first weight coefficient threshold; When the invalid value weight coefficient is not lower than the preset first weight coefficient threshold, an abnormal data quality alarm is issued for the multi-period audit data of the project cost budget appraisal; When the invalid value weight coefficient is lower than a preset first weight coefficient threshold, the data type corresponding to the missing value and the weight value corresponding to the data type are retrieved; Obtaining a missing value weight coefficient using a weight value of the data type corresponding to the missing value; The missing value weight coefficient is obtained by the following formula:

[0010] Among them, S q represents the missing value weight coefficient; m represents the number of missing values ​​corresponding to the missing value; k i Indicates the weight value corresponding to the data type of the i-th missing value; w p Represents the average weight value corresponding to all valid values; k x represents a weight reference value, and the weight reference value is obtained by the following formula;

[0011] Among them, k x represents the weight reference value; w max Indicates the maximum weight value corresponding to the data type of all invalid values; k maxrepresents the maximum value of the weight corresponding to the data type to which all missing values ​​belong; λ represents the preset correlation value between the data type corresponding to the maximum value of the weight corresponding to the data type to which all missing values ​​belong and the data type corresponding to the maximum value of the weight corresponding to the data type to which all invalid values ​​belong; Comparing the missing value weight coefficient with a preset second weight coefficient threshold; When the missing value weight coefficient exceeds the preset second weight coefficient threshold, an abnormal data quality alarm is issued for the multi-period audit data of the project cost budget appraisal; When the missing value weight coefficient does not exceed the preset second weight coefficient threshold, it is determined that the multi-period audit data of the engineering cost budget appraisal has no quality anomaly.

[0012] Preferably, in S1, the multi-period audit data of the project cost budget appraisal is preprocessed, and the following operations are further performed: Obtain multi-period audit data of engineering cost budget review that is useful for engineering cost budget review; Convert the multi-period audit data of engineering cost budget review that is useful for engineering cost budget review, unify the format of the multi-period audit data of engineering cost budget review, eliminate the dimensional differences between the multi-period audit data of engineering cost budget review, and determine the standardized multi-period audit data of engineering cost budget review; Obtain standardized multi-period audit data of engineering cost budget review; The standardized multi-period audit data of the engineering cost budget appraisal are integrated so that the standardized multi-period audit data of the engineering cost budget appraisal are integrated into a database, and the standardized multi-period audit data of the engineering cost budget appraisal are stored.

[0013] Preferably, in S2, an optimal project cost budget appraisal forecasting model is constructed, and the following operations are performed: Collect historical engineering cost budget review and appraisal data for multiple periods; Classify the historical engineering cost budget review and multi-period review data, and divide the historical engineering cost budget review and multi-period review data into a training set and a test set; Based on the training set, the deep learning model is trained and iterated to train a project cost budget appraisal prediction model; Based on the test set, the performance of the engineering cost budget review and valuation prediction model is tested to determine whether the engineering cost budget review and valuation prediction model can achieve the expected results and to determine the optimal engineering cost budget review and valuation prediction model.

[0014] Preferably, the historical engineering cost budget review multi-period audit data is divided into a training set and a test set, including: Extract invalid value weight coefficient and missing value weight coefficient; The invalid value weight coefficient and the missing value weight coefficient are integrated to obtain a comprehensive weight coefficient; The comprehensive weight coefficient is obtained by the following formula:

[0015] Among them, S represents the comprehensive weight coefficient; S w Indicates the weight coefficient of invalid value; S q represents the missing value weight coefficient; The comprehensive weight coefficient is used as the observation weight value, and the comprehensive weight coefficient is combined with the invalid value weight coefficient and the missing value weight coefficient to obtain the division ratio corresponding to the training set and the division ratio corresponding to the test set; The division ratio corresponding to the training set and the division ratio corresponding to the test set are obtained by the following formula:

[0016] Among them, B x Indicates the division ratio corresponding to the training set; B x0 Indicates the initial division ratio corresponding to the preset training set; B c Indicates the division ratio corresponding to the test set.

[0017] Preferably, in S2, it is determined whether an abnormality occurs during the project cost budget review process, and the following operations are performed: Obtain the optimal engineering cost budget review and forecast model; Deploy the optimal engineering cost budget review prediction model in the actual engineering cost budget review environment; According to the optimal engineering cost budget appraisal prediction model, the standardized engineering cost budget appraisal multi-period audit data is analyzed and predicted in real time to determine whether there are any abnormalities in the engineering cost budget appraisal process and determine the engineering cost budget appraisal prediction results; Among them, the forecast result of the engineering cost budget review includes the existence of abnormal behavior in the engineering cost budget review process or the absence of abnormal behavior in the engineering cost budget review process.

[0018] Preferably, in S2, timely warning and intervention are performed on abnormal behavior by performing the following operations: Obtain the project cost budget review and forecast results; When abnormal behavior occurs during the project cost budget review process, timely warnings will be issued, and staff will be automatically reminded via email or text messages to intervene in the project cost budget review, and multiple audit data of the project cost budget review will be reviewed again.

[0019] Preferably, in S3, the multi-period audit data report of the project cost budget appraisal is displayed in a visual form, and the following operations are performed: Obtain multi-period audit data of engineering cost budget review and engineering cost budget review forecast results; Analyze the multi-period audit data of the project cost budget and the forecast results of the project cost budget to form a multi-period audit data report of the project cost budget; The multi-period audit data report of the engineering cost budget appraisal is uploaded to the display screen, and the multi-period audit data report of the engineering cost budget appraisal is displayed in a visual form, so that the staff can check and discover the budget appraisal problems in the engineering cost project in time.

[0020] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention collects multi-period audit data of engineering cost budget appraisal, pre-processes the multi-period audit data of engineering cost budget appraisal, determines standardized multi-period audit data of engineering cost budget appraisal, integrates and stores the standardized multi-period audit data of engineering cost budget appraisal, constructs an optimal engineering cost budget appraisal prediction model, and performs real-time analysis and prediction on the standardized multi-period audit data of engineering cost budget appraisal according to the optimal engineering cost budget appraisal prediction model, determines whether an abnormality occurs in the engineering cost budget appraisal process, determines the engineering cost budget appraisal prediction result, and promptly warns and intervenes in abnormal behavior, can effectively process and predict the multi-period audit data of engineering cost budget appraisal, can monitor the engineering cost budget appraisal in real time and discover abnormal behavior, and can improve the engineering cost budget appraisal effect.

[0021] 2. The present invention generates a multi-period audit data report of the engineering cost budget appraisal by analyzing the multi-period audit data of the engineering cost budget appraisal and the engineering cost budget appraisal forecast results, and displays the multi-period audit data report of the engineering cost budget appraisal in a visual form, so that the staff can check and discover the budget appraisal problems in the engineering cost project in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 The present invention is a flow chart of a method for processing data based on multi-period review of engineering cost budget appraisal. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] In order to solve the existing problems of being unable to effectively process and predict the multi-period audit data of the project cost budget review, being unable to monitor the project cost budget review in real time and discover abnormal behavior, resulting in poor project cost budget review results, please refer to Figure 1 , this embodiment provides the following technical solutions: The data processing method based on multi-period review of engineering cost budget includes the following steps: S1: Collecting multi-period audit data of engineering cost budget review and valuation, pre-processing the multi-period audit data of engineering cost budget review and valuation, determining standardized multi-period audit data of engineering cost budget review and valuation, and integrating and storing the standardized multi-period audit data of engineering cost budget review and valuation; In this embodiment, as the preferred technical solution of the present invention, the multi-period audit data of the project cost budget appraisal is collected, and the following operations are performed: Real-time monitoring and collection of construction equipment costs, labor costs, material costs, management fees, taxes and profits in engineering cost items are carried out to determine multi-period audit data for engineering cost budget review.

[0025] It should be noted that construction equipment costs refer to the costs of various types of machinery, equipment, tools and other means of production required in the process of building or infrastructure construction; construction equipment costs are an important part of the total construction cost and directly affect the investment benefits of the project.

[0026] It should be noted that labor costs refer to the remuneration paid to workers for completing various construction tasks during the construction or infrastructure construction process; labor costs are one of the important components of the total construction cost and directly affect the investment benefits of the project.

[0027] It should be noted that material costs refer to the costs of purchasing, storing, transporting, inspecting, and repairing raw materials, semi-finished products, components, etc. consumed in completing various construction tasks during the construction or infrastructure construction process; material costs are an important component of the total construction cost and directly affect the investment benefits of the project.

[0028] It should be noted that management fees are an indirect cost in construction projects. They include various expenses incurred for organizing, coordinating and managing construction activities. Management fees usually account for a certain proportion of the total construction cost. They are mainly used to pay project management personnel's salaries, office expenses, travel expenses, fixed asset depreciation and rental fees, labor insurance and employee welfare expenses, etc.

[0029] It should be noted that taxes and fees refer to various taxes that need to be paid in construction projects. Taxes and fees are an important part of construction projects, involving value-added tax, business tax, urban maintenance and construction tax, education surcharge, corporate income tax and other aspects.

[0030] It should be noted that profit refers to the portion of income that an enterprise obtains in excess of costs in its operating activities. In construction projects, profit usually refers to the portion remaining after deducting all direct and indirect costs after the project is completed.

[0031] In this embodiment, as a preferred technical solution of the present invention, the multi-period audit data of the project cost budget appraisal is preprocessed, and the following operations are performed: Obtain multi-period audit data of project cost budget review; Clean the multi-period audit data of engineering cost budget review, including: Conduct consistency checks on multiple audit data of project cost budget review; According to the data consistency requirements, check whether there are inconsistent data that are useless for the engineering cost budget review in the multi-period review data of the engineering cost budget review, and remove the inconsistent data in the multi-period review data of the engineering cost budget review; Check invalid and missing values ​​of multiple audit data of project cost budget appraisal; According to the requirements of data validity and integrity, check whether there are invalid values ​​and missing values ​​that are useless for the engineering cost budget review in the multi-period review data of the engineering cost budget review, and remove the invalid values ​​and missing values ​​in the multi-period review data of the engineering cost budget review; Determine the multi-period audit data for the engineering cost budget review that is useful for the engineering cost budget review.

[0032] It should be noted that data cleaning is one of the important links in data analysis, data mining and application, aiming to improve data quality and the accuracy of analysis results, including checking data consistency, processing invalid values ​​and missing values, etc.

[0033] Among them, the consistency check is to check whether the data meets the requirements based on the reasonable value range and mutual relationship of each parameter, and find out the data that is beyond the normal range, logically unreasonable or contradictory. For example, the variables measured by the 1-7 scale have a value of 0, and the weight has a negative number, which should be regarded as beyond the normal value range; computer software such as SPSS, SAS and Excel can automatically identify each variable value that exceeds the range according to the defined value range; logically inconsistent answers may appear in many forms: for example, many respondents said that they drove to work, but reported that they did not have a car; or the respondents reported that they were heavy buyers and users of a certain brand, but at the same time gave a very low score on the familiarity scale. When inconsistencies are found, the questionnaire number, record number, variable name, error category, etc. should be listed to facilitate further verification and correction.

[0034] Therefore, by cleaning the multi-period audit data of engineering cost budget appraisal, inconsistent data, invalid values ​​and missing values ​​that are useless for engineering cost budget appraisal can be removed, and then the multi-period audit data of engineering cost budget appraisal that is useful for engineering cost budget appraisal can be determined, which can improve the subsequent processing accuracy and efficiency of the multi-period audit data of engineering cost budget appraisal.

[0035] Specifically, in S1, the multi-period audit data of the project cost budget review is preprocessed, and the following operations are performed: After checking invalid values ​​and missing values ​​of multiple audit data of engineering cost budget appraisal, the number of data corresponding to invalid values ​​and the number of missing values ​​corresponding to missing values ​​are extracted; Extracting the data type corresponding to the invalid value and the weight value corresponding to the data type; Obtaining an invalid value weight coefficient using a weight value of the data type corresponding to the invalid value; The invalid value weight coefficient is obtained by the following formula:

[0036] Among them, S w represents the weight coefficient of invalid values; n represents the number of data corresponding to invalid values; w i Indicates the weight value corresponding to the data type of the i-th invalid value; w max Indicates the maximum weight value corresponding to the data type of all invalid values; C wi represents the amount of data corresponding to the i-th invalid value; C wyi represents the amount of data corresponding to the valid value of the same data type closest to the time when the i-th invalid value was generated; w p Indicates the average weight value corresponding to all valid values; Comparing the invalid value weight coefficient with a preset first weight coefficient threshold; When the invalid value weight coefficient is not lower than the preset first weight coefficient threshold, an abnormal data quality alarm is issued for the multi-period audit data of the project cost budget appraisal; When the invalid value weight coefficient is lower than a preset first weight coefficient threshold, the data type corresponding to the missing value and the weight value corresponding to the data type are retrieved; Obtaining a missing value weight coefficient using a weight value of the data type corresponding to the missing value; The missing value weight coefficient is obtained by the following formula:

[0037] Among them, S q represents the missing value weight coefficient; m represents the number of missing values ​​corresponding to the missing value; k iIndicates the weight value corresponding to the data type of the i-th missing value; w p Represents the average weight value corresponding to all valid values; k x represents a weight reference value, and the weight reference value is obtained by the following formula;

[0038] Among them, k x represents the weight reference value; w max Indicates the maximum weight value corresponding to the data type of all invalid values; k max represents the maximum value of the weight corresponding to the data type to which all missing values ​​belong; λ represents the preset correlation value between the data type corresponding to the maximum value of the weight corresponding to the data type to which all missing values ​​belong and the data type corresponding to the maximum value of the weight corresponding to the data type to which all invalid values ​​belong; Comparing the missing value weight coefficient with a preset second weight coefficient threshold; When the missing value weight coefficient exceeds the preset second weight coefficient threshold, an abnormal data quality alarm is issued for the multi-period audit data of the project cost budget appraisal; When the missing value weight coefficient does not exceed the set second weight coefficient threshold, it is determined that the multi-period audit data of the engineering cost budget appraisal has no quality anomaly.

[0039] The technical effect of the above technical solution is: through the inspection of invalid values ​​and missing values, incomplete or erroneous parts in the data can be quickly identified, providing a clear starting point for subsequent data processing. Extracting specific information of invalid values ​​and missing values ​​(such as the number of data, data type and corresponding weight value) helps to understand the quality status of the data more accurately. Using the calculation formula of the invalid value weight coefficient (Sw) and the missing value weight coefficient (Sq), the number, data type, weight value and correlation with other valid values ​​of invalid values ​​and missing values ​​are comprehensively considered, thereby realizing a refined evaluation of data quality. This evaluation method not only considers the influence of a single dimension (such as quantity), but also incorporates multiple factors such as data type and weight value, making the evaluation result more comprehensive and accurate. According to the comparison result of the invalid value weight coefficient and the missing value weight coefficient with the preset threshold, the data quality abnormality alarm can be automatically triggered. This mechanism can not only detect and deal with potential problems in the data in a timely manner, but also avoid unnecessary false alarms and omissions. By setting different weight coefficient thresholds, the sensitivity of data quality monitoring can be adjusted according to actual needs, thereby achieving more flexible and personalized data quality management. Through strict monitoring and early warning of data quality, errors and incomplete parts in the data can be discovered and corrected in a timely manner, thereby ensuring the smooth progress of the engineering cost budget review process. This helps to improve the accuracy and reliability of the engineering cost budget and reduce decision-making errors and risks caused by data quality issues.

[0040] In summary, this technical solution realizes the effective monitoring and management of multi-period audit data of engineering cost budget appraisal through refined data preprocessing and quality assessment mechanism, improves the quality and availability of data, and provides strong guarantee for the accuracy and reliability of engineering cost budget.

[0041] In this embodiment, as a preferred technical solution of the present invention, the multi-period audit data of the project cost budget appraisal is preprocessed, and the following operations are performed: Obtain multi-period audit data of engineering cost budget review that is useful for engineering cost budget review; Convert the multi-period audit data of engineering cost budget review that is useful for engineering cost budget review, unify the format of the multi-period audit data of engineering cost budget review, eliminate the dimensional differences between the multi-period audit data of engineering cost budget review, and determine the standardized multi-period audit data of engineering cost budget review; Obtain standardized multi-period audit data of engineering cost budget review; The standardized multi-period audit data of the engineering cost budget appraisal are integrated so that the standardized multi-period audit data of the engineering cost budget appraisal are integrated into a database, and the standardized multi-period audit data of the engineering cost budget appraisal are stored.

[0042] S2: Construct an optimal engineering cost budget review prediction model, and conduct real-time analysis and prediction of standardized engineering cost budget review multi-period audit data based on the optimal engineering cost budget review prediction model to determine whether there are any abnormalities in the engineering cost budget review process, determine the engineering cost budget review prediction results, and conduct timely warning and intervention for abnormal behaviors; In this embodiment, as a preferred technical solution of the present invention, an optimal project cost budget appraisal forecasting model is constructed, and the following operations are performed: Collect historical engineering cost budget review and appraisal data for multiple periods; Classify the historical engineering cost budget review and multi-period review data, and divide the historical engineering cost budget review and multi-period review data into a training set and a test set; Based on the training set, the deep learning model is trained and iterated to train a project cost budget appraisal prediction model; Based on the test set, the performance of the engineering cost budget review and valuation prediction model is tested to determine whether the engineering cost budget review and valuation prediction model can achieve the expected results and to determine the optimal engineering cost budget review and valuation prediction model.

[0043] Specifically, the historical engineering cost budget review and appraisal multi-period audit data is divided into a training set and a test set, including: Extract invalid value weight coefficient and missing value weight coefficient; The invalid value weight coefficient and the missing value weight coefficient are integrated to obtain a comprehensive weight coefficient; The comprehensive weight coefficient is obtained by the following formula:

[0044] Among them, S represents the comprehensive weight coefficient; S w Indicates the weight coefficient of invalid value; S q represents the missing value weight coefficient; The comprehensive weight coefficient is used as the observation weight value, and the comprehensive weight coefficient is combined with the invalid value weight coefficient and the missing value weight coefficient to obtain the division ratio corresponding to the training set and the division ratio corresponding to the test set; The division ratio corresponding to the training set and the division ratio corresponding to the test set are obtained by the following formula:

[0045] Among them, B x Indicates the division ratio corresponding to the training set; B x0 Indicates the initial division ratio corresponding to the preset training set; B c Indicates the division ratio corresponding to the test set.

[0046] The technical effect of the above technical solution is: by extracting the invalid value weight coefficient (Sw) and the missing value weight coefficient (Sq), the technical solution can quantitatively evaluate the data quality problems in the multi-period audit data of the historical engineering cost budget appraisal. This evaluation not only considers the number of invalid values ​​and missing values, but also considers their impact on the overall quality of the data (reflected by the weight value). The comprehensive weight coefficient (S) obtained by integrating the invalid value weight coefficient and the missing value weight coefficient provides a comprehensive data quality indicator. This indicator can reflect the overall status of the data quality in the data set and provide an important basis for subsequent data division. By taking the comprehensive weight coefficient as the observation weight value and combining the invalid value weight coefficient and the missing value weight coefficient, the technical solution can intelligently determine the division ratio of the training set and the test set. This division method not only considers the quantity of data, but also the quality of data, thereby ensuring the balance of data quality between the training set and the test set. Since the division of the training set and the test set is based on data quality, this method can ensure that the training set contains enough high-quality data, thereby improving the accuracy and reliability of model training. At the same time, the test set can also better reflect the performance of the model in practical applications. The formulas and parameters in this technical solution (such as the initial partition ratio corresponding to the preset training set) can be adjusted and optimized according to actual conditions to adapt to different data sets and application scenarios. This flexibility and adaptability make this technical solution more widely applicable in practical applications. By quantitatively evaluating data quality and intelligently partitioning data sets, this technical solution provides strong support for data-driven decision-making. It enables decision makers to make decisions based on more accurate and reliable data, thereby improving the scientificity and effectiveness of decisions.

[0047] In summary, this technical solution achieves effective utilization and high-quality management of multi-period audit data of historical engineering cost budget appraisal by introducing comprehensive weight coefficients and intelligent data division methods, improves the accuracy and reliability of model training, and promotes the development of data-driven decision-making.

[0048] In this embodiment, as a preferred technical solution of the present invention, it is determined whether an abnormality occurs during the project cost budget review process, and the following operations are performed: Obtain the optimal engineering cost budget review and forecast model; Deploy the optimal engineering cost budget review prediction model in the actual engineering cost budget review environment; According to the optimal engineering cost budget appraisal prediction model, the standardized engineering cost budget appraisal multi-period audit data is analyzed and predicted in real time to determine whether there are any abnormalities in the engineering cost budget appraisal process and determine the engineering cost budget appraisal prediction results; Among them, the forecast result of the engineering cost budget review includes the existence of abnormal behavior in the engineering cost budget review process or the absence of abnormal behavior in the engineering cost budget review process.

[0049] In this embodiment, as the preferred technical solution of the present invention, timely warning and intervention of abnormal behavior are performed by performing the following operations: Obtain the project cost budget review and forecast results; When abnormal behavior occurs during the project cost budget review process, timely warnings will be issued, and staff will be automatically reminded via email or text messages to intervene in the project cost budget review, and multiple audit data of the project cost budget review will be reviewed again.

[0050] S3: A multi-period audit data report on the engineering cost budget review is generated based on the multi-period audit data of the engineering cost budget review and the forecast results of the engineering cost budget review, and the multi-period audit data report on the engineering cost budget review is displayed in a visual form, so that the staff can check and discover budget review problems in the engineering cost project in a timely manner.

[0051] In this embodiment, as a preferred technical solution of the present invention, the multi-period audit data report of the project cost budget appraisal is displayed in a visual form, and the following operations are performed: Obtain multi-period audit data of engineering cost budget review and engineering cost budget review forecast results; Analyze the multi-period audit data of the project cost budget and the forecast results of the project cost budget to form a multi-period audit data report of the project cost budget; The multi-period audit data report of the engineering cost budget appraisal is uploaded to the display screen, and the multi-period audit data report of the engineering cost budget appraisal is displayed in a visual form, so that the staff can check and discover the budget appraisal problems in the engineering cost project in time.

[0052] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0053] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A multi-period audit data processing method based on engineering cost budget appraisal, characterized in that: The steps include: S1: Collecting multi-period audit data of engineering cost budget review and valuation, pre-processing the multi-period audit data of engineering cost budget review and valuation, determining standardized multi-period audit data of engineering cost budget review and valuation, and integrating and storing the standardized multi-period audit data of engineering cost budget review and valuation; S2: Construct an optimal engineering cost budget review prediction model, and conduct real-time analysis and prediction of standardized engineering cost budget review multi-period audit data based on the optimal engineering cost budget review prediction model to determine whether there are any abnormalities in the engineering cost budget review process, determine the engineering cost budget review prediction results, and conduct timely warning and intervention for abnormal behaviors; S3: Based on the multi-period audit data of the engineering cost budget and the forecast results of the engineering cost budget, a multi-period audit data report of the engineering cost budget is generated, and the multi-period audit data report of the engineering cost budget is displayed in a visual form, so that the staff can check and find budget appraisal problems in the engineering cost project in a timely manner; In S1, multiple review data of the project cost budget are collected, and the following operations are performed: Real-time monitoring and collection of construction equipment costs, labor costs, material costs, management fees, taxes and profits in engineering cost items, and determination of multi-period audit data for engineering cost budget review; In S1, the multi-period audit data of the project cost budget review is preprocessed, and the following operations are performed: Obtain multi-period audit data of project cost budget review; Clean the multi-period audit data of engineering cost budget review, including: Conduct consistency checks on multiple audit data of project cost budget review; According to the data consistency requirements, check whether there are inconsistent data that are useless for the engineering cost budget review in the multi-period review data of the engineering cost budget review, and remove the inconsistent data in the multi-period review data of the engineering cost budget review; Check invalid and missing values ​​of multiple audit data of project cost budget review; According to the requirements of data validity and integrity, check whether there are invalid values ​​and missing values ​​that are useless for the engineering cost budget review in the multi-period review data of the engineering cost budget review, and remove the invalid values ​​and missing values ​​in the multi-period review data of the engineering cost budget review; Determine the multi-period audit data for the engineering cost budget review that is useful for the engineering cost budget review.

2. The method for processing data based on multi-period review of construction cost budget appraisal according to claim 1 is characterized in that: In S1, the multi-period audit data of the project cost budget review is preprocessed, and the following operations are performed: After checking invalid values ​​and missing values ​​of multiple audit data of engineering cost budget appraisal, the number of data corresponding to invalid values ​​and the number of missing values ​​corresponding to missing values ​​are extracted; Extracting the data type corresponding to the invalid value and the weight value corresponding to the data type; Obtaining an invalid value weight coefficient using a weight value of the data type corresponding to the invalid value; The invalid value weight coefficient is obtained by the following formula: Among them, S w represents the weight coefficient of invalid values; n represents the number of data corresponding to invalid values; w i Indicates the weight value corresponding to the data type of the i-th invalid value; w max Indicates the maximum weight value corresponding to the data type of all invalid values; C wi Indicates the amount of data corresponding to the i-th invalid value; C wyi represents the amount of data corresponding to the valid value of the same data type closest to the time when the i-th invalid value was generated; w p Indicates the average weight value corresponding to all valid values; Comparing the invalid value weight coefficient with a preset first weight coefficient threshold; When the invalid value weight coefficient is not lower than the preset first weight coefficient threshold, an abnormal data quality alarm is issued for the multi-period audit data of the project cost budget appraisal; When the invalid value weight coefficient is lower than a preset first weight coefficient threshold, the data type corresponding to the missing value and the weight value corresponding to the data type are retrieved; Obtaining a missing value weight coefficient using a weight value of the data type corresponding to the missing value; The missing value weight coefficient is obtained by the following formula: Among them, S q represents the missing value weight coefficient; m represents the number of missing values ​​corresponding to the missing value; k i Indicates the weight value corresponding to the data type of the i-th missing value; w p Represents the average weight value corresponding to all valid values; k x represents a weight reference value, and the weight reference value is obtained by the following formula; Among them, k x represents the weight reference value; w max Indicates the maximum weight value corresponding to the data type of all invalid values; k max represents the maximum value of the weight corresponding to the data type to which all missing values ​​belong; λ represents the preset correlation value between the data type corresponding to the maximum value of the weight corresponding to the data type to which all missing values ​​belong and the data type corresponding to the maximum value of the weight corresponding to the data type to which all invalid values ​​belong; Comparing the missing value weight coefficient with a preset second weight coefficient threshold; When the missing value weight coefficient exceeds the preset second weight coefficient threshold, an abnormal data quality alarm is issued for the multi-period audit data of the project cost budget appraisal; When the missing value weight coefficient does not exceed the preset second weight coefficient threshold, it is determined that the multi-period audit data of the engineering cost budget appraisal has no quality anomaly.

3. The method for processing data based on multi-period review of construction cost budget appraisal according to claim 2 is characterized in that: In S1, the multi-period audit data of the project cost budget review is preprocessed, and the following operations are performed: Obtain multi-period audit data of engineering cost budget review that is useful for engineering cost budget review; Convert the multi-period audit data of engineering cost budget review that is useful for engineering cost budget review, unify the format of the multi-period audit data of engineering cost budget review, eliminate the dimensional differences between the multi-period audit data of engineering cost budget review, and determine the standardized multi-period audit data of engineering cost budget review; Obtain standardized multi-period audit data of engineering cost budget review; The standardized multi-period audit data of the engineering cost budget appraisal are integrated so that the standardized multi-period audit data of the engineering cost budget appraisal are integrated into a database, and the standardized multi-period audit data of the engineering cost budget appraisal are stored.

4. The method for processing data based on multi-period review of construction cost budget appraisal according to claim 3 is characterized in that: In S2, an optimal project cost budget review and forecasting model is constructed, and the following operations are performed: Collect historical engineering cost budget review and appraisal data for multiple periods; Classify the historical engineering cost budget review and multi-period review data, and divide the historical engineering cost budget review and multi-period review data into a training set and a test set; Based on the training set, the deep learning model is trained and iterated to train a project cost budget appraisal prediction model; Based on the test set, the performance of the engineering cost budget review and valuation prediction model is tested to determine whether the engineering cost budget review and valuation prediction model can achieve the expected results and to determine the optimal engineering cost budget review and valuation prediction model.

5. The method for processing data based on multi-period review of construction cost budget appraisal according to claim 4 is characterized in that: The historical engineering cost budget review and appraisal multi-period audit data is divided into training set and test set, including: Extract invalid value weight coefficient and missing value weight coefficient; The invalid value weight coefficient and the missing value weight coefficient are integrated to obtain a comprehensive weight coefficient; The comprehensive weight coefficient is obtained by the following formula: Among them, S represents the comprehensive weight coefficient; S w Indicates the weight coefficient of invalid value; S q represents the missing value weight coefficient; The comprehensive weight coefficient is used as the observation weight value, and the comprehensive weight coefficient is combined with the invalid value weight coefficient and the missing value weight coefficient to obtain the division ratio corresponding to the training set and the division ratio corresponding to the test set; The division ratio corresponding to the training set and the division ratio corresponding to the test set are obtained by the following formula: Among them, B x Indicates the division ratio corresponding to the training set; B x0 Indicates the initial division ratio corresponding to the preset training set; B c Indicates the division ratio corresponding to the test set.

6. The method for processing data based on multi-period review of construction cost budget appraisal according to claim 5 is characterized in that: In S2, it is determined whether an abnormality occurs during the project cost budget review process, and the following operations are performed: Obtain the optimal engineering cost budget review and forecast model; Deploy the optimal engineering cost budget review prediction model in the actual engineering cost budget review environment; According to the optimal engineering cost budget appraisal prediction model, the standardized engineering cost budget appraisal multi-period audit data is analyzed and predicted in real time to determine whether there are any abnormalities in the engineering cost budget appraisal process and determine the engineering cost budget appraisal prediction results; Among them, the forecast result of the engineering cost budget review includes the existence of abnormal behavior in the engineering cost budget review process or the absence of abnormal behavior in the engineering cost budget review process.

7. The method for processing data based on multi-period review of construction cost budget appraisal according to claim 6 is characterized in that: In S2, timely warning and intervention are carried out for abnormal behavior, and the following operations are performed: Obtain the project cost budget review and forecast results; When abnormal behavior occurs during the project cost budget review process, timely warnings will be issued, and staff will be automatically reminded via email or text messages to intervene in the project cost budget review, and multiple audit data of the project cost budget review will be reviewed again.

8. The method for processing data based on multi-period review of construction cost budget appraisal according to claim 7 is characterized in that: In S3, the multi-period audit data report of the project cost budget appraisal is displayed in a visual form, and the following operations are performed: Obtain multi-period audit data of engineering cost budget review and engineering cost budget review forecast results; Analyze the multi-period audit data of the project cost budget and the forecast results of the project cost budget to form a multi-period audit data report of the project cost budget; The multi-period audit data report of the engineering cost budget appraisal is uploaded to the display screen, and the multi-period audit data report of the engineering cost budget appraisal is displayed in a visual form, so that the staff can check and discover the budget appraisal problems in the engineering cost project in time.

Images