A Method and System for Querying Project Cost Data for Construction Projects

Abstract

The present invention relates to the technical field of data processing, and particularly relates to a method and system for querying project cost data for construction projects. It obtains the unit costs of each item, constructs a fully connected graph according to the correlation degree between any two unit costs, and divides the fully connected graph into regions to obtain multiple communities. Then, it performs principal component analysis on the unit costs within each community to obtain the core unit costs within each community. Based on the association between the unit costs of the communities, it obtains the degree of association, and thus obtains the confidence level for index construction according to the degree of association. Finally, according to the confidence level for index construction, it constructs a relationship index, which can reduce the workload and difficulty of project cost query and improve the efficiency of project cost query.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method and system for querying project cost data for construction projects. Background Art

[0002] Querying project cost data is an important link in construction project management, which plays a key role in ensuring the budget, cost control, and resource allocation of engineering projects. The existing project cost data mainly comes from various databases, industry standards, and data accumulation of historical projects, but these data often have problems such as untimely updates and insufficient accuracy. Through technical means such as big data and artificial intelligence, automatic data update, precise matching, and intelligent recommendation can be achieved.

[0003] The project cost data of construction projects is stored by constructing a relational database in the form of cost reports, and different relational databases are connected through relational indexes. However, the construction of a project is a long-term process, and the market is dynamically changing. Therefore, as the progress of the project construction changes, the project cost will also change in real time. Therefore, it is necessary to realize real-time estimation and calculation of the project cost during this process. However, the relational database is pre-constructed based on the projects of construction projects. If it is necessary to reconstruct the relational database, the workload is extremely large, and it is impossible to make the relational structure in the pre-constructed database (if there is a relationship between different engineering projects, connection is required) add connections as the market changes, resulting in great difficulty in querying relevant data or projects during the estimation and calculation of the project cost. Summary of the Invention

[0004] In order to solve the technical problem of the relatively large difficulty in querying the existing project cost data, the purpose of the present invention is to provide a method and system for querying project cost data for construction projects, and the specific technical solutions adopted are as follows:

[0005] In the first aspect of the present invention, a method for querying project cost data for construction projects is provided, including:

[0006] Obtain each unit cost, where the unit cost is each cost item in each construction project;

[0007] Construct a fully connected graph according to the correlation degree between any two unit costs, and divide the fully connected graph into regions to obtain multiple communities;

[0008] Perform principal component analysis on the unit costs within each community to obtain the core unit costs within each community;

[0009] Based on the association between each unit cost of each community and the core unit costs of other communities, obtain the association degree between each unit cost of each community and the core unit costs of other communities;

[0010] Integrate the correlation degree between the unit costs of each community and the core unit costs of other communities to obtain the confidence level of index construction for the unit costs of each community with respect to other communities.

[0011] Construct the relationship index of each community according to the confidence level of index construction.

[0012] In an exemplary embodiment, the process of obtaining the correlation degree between any two unit costs includes:

[0013] Obtain the construction period consistency between any two unit costs according to the time interval between the construction periods of the any two unit costs.

[0014] Based on the construction period consistency, in combination with whether the any two unit costs are in the same construction project and the similarity between the any two unit costs, obtain the correlation degree between the any two unit costs.

[0015] In an exemplary embodiment, based on the correlation between the unit costs of each community and the core unit costs of other communities, obtaining the correlation degree between the unit costs of each community and the core unit costs of other communities includes:

[0016] Obtain the regression parameters when the unit costs in the first target community are in the linear combination of the core unit costs in the first target community during the principal component analysis of the unit costs in the first target community; the first target community is any community.

[0017] According to the regression parameters and the preset starting weights, obtain the weighted regression parameters of the unit costs in the first target community for each core unit cost.

[0018] Obtain the similarity between the unit costs in the first target community and the unit costs in the second target community; the second target community is any community and is different from the first target community.

[0019] According to the weighted regression parameters and the similarity, obtain the correlation degree between the unit costs in the second target community and the core unit costs in the first target community.

[0020] In an exemplary embodiment, according to the weighted regression parameters and the similarity, obtaining the correlation degree between the unit costs in the second target community and the core unit costs in the first target community includes:

[0021] Obtain the associated sub - degree corresponding to each unit cost in the first target community based on the weighted regression parameters and similarities of each unit cost in the first target community with respect to each core unit cost;

[0022] Fuse the associated sub - degrees corresponding to each unit cost in the first target community to obtain the association degree between each unit cost in the second target community and each core unit cost in the first target community.

[0023] In an exemplary embodiment, the calculation formula of the association degree is as follows:

[0024] ;

[0025] where, represents the association degree between the i - th unit cost in the second target community and the j - th core unit cost in the K - th community, is the number of unit costs in the K - th community, and the K - th community corresponds to the first target community; is the regression parameter when the m - th unit cost in the K - th community forms a linear combination of the j - th core unit cost in the K - th community, is the preset start weight of the m - th unit cost in the K - th community. If the construction period of the m - th unit cost has started at the current moment, then the preset start weight of the m - th unit cost is recorded as 1, otherwise it is recorded as 0; is the cost sequence of the i - th unit cost in the second target community, is the cost sequence of the m - th unit cost in the K - th community, represents and the similarity of, represents the normalization function.

[0026] In an exemplary embodiment, fusing the association degrees between each unit cost of each community and each core unit cost of other communities to obtain the index construction confidence of each unit cost of each community includes:

[0027] Obtain the maximum value among the association degrees between each unit cost in the second target community and each core unit cost in the first target community;

[0028] Obtain the remaining association degrees except the maximum value among the association degrees between each unit cost in the second target community and each core unit cost in the first target community;

[0029] Determine the index construction confidence of each unit cost in the second target community with respect to the first target community according to the difference between the maximum value and the remaining association degrees.

[0030] In an exemplary embodiment, the calculation formula of the index construction confidence is as follows:

[0031] ;

[0032] Wherein, represents the index construction confidence of the i-th unit cost in the second target community and the K-th community, represents the maximum value of the degree of association between the i-th unit cost in the second target community and all core unit costs in the K-th community, represents the number of the remaining core unit costs in the K-th community except the core unit cost corresponding to the maximum value, represents the -th core unit cost in the K-th community except the core unit cost corresponding to the maximum value, represents the degree of association between the i-th unit cost in the second target community and the -th core unit cost in the K-th community.

[0033] In an exemplary embodiment, according to the index construction confidence, relationship indexes of each community are constructed, including:

[0034] Comparing each unit cost of each community with the index construction confidence of other communities and a preset threshold;

[0035] Constructing relationship indexes of databases corresponding to the communities where the unit costs corresponding to the index construction confidence greater than the preset threshold are located.

[0036] In an exemplary embodiment, the fully connected graph is divided into regions to obtain multiple communities, including:

[0037] Using the louvain algorithm to divide the fully connected graph into regions to obtain multiple communities.

[0038] In a second aspect of the present invention, there is provided a project cost data query system for construction projects, including: a memory and a processor; the memory is connected to the processor; the memory is used for storing program instructions; the processor is used for implementing the above-mentioned project cost data query method for construction projects when the program instructions are executed.

[0039] The present invention has the following beneficial effects: First, according to the correlation degree between any two unit costs, a fully connected graph is constructed, and the fully connected graph is divided into regions to obtain multiple communities, which is convenient for accurately constructing the relationship index of each community for the relational database. Then, in order to reduce the workload of data processing and analyze the relevant unit costs targeted, principal component analysis is performed on the unit costs within each community to obtain the core unit costs within each community. Then, according to the association between each unit cost in each community and the core unit costs in other communities, the association degree between each unit cost in each community and the core unit costs in other communities is obtained. Thus, based on the association degree, the index construction confidence of each unit cost in each community and other communities is obtained. Finally, according to the index construction confidence, the relationship index of each community is constructed. In this way, the workload and query difficulty of engineering cost query can be reduced, and the engineering cost query efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 FIG. is a schematic diagram of factors affecting project cost in the project settlement process provided by an embodiment of the present invention;

[0041] Figure 2 FIG. is a flowchart of a method for querying project cost data for a construction project provided by an embodiment of the present invention;

[0042] Figure 3 FIG. is a flowchart for obtaining the correlation degree provided by an embodiment of the present invention;

[0043] Figure 4 FIG. is a flowchart for obtaining the association degree provided by an embodiment of the present invention;

[0044] Figure 5 FIG. is a specific implementation flowchart of step 4-4 provided by an embodiment of the present invention;

[0045] Figure 6 FIG. is a flowchart for obtaining the index construction confidence provided by an embodiment of the present invention;

[0046] Figure 7 FIG. is a flowchart for constructing the relationship index provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following combines the drawings and preferred embodiments to elaborate in detail on the specific implementation manner, structure, features, and effects of the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs.

[0049] Generally, the project cost involves the following stages: investment estimate (at the stage of project proposal and feasibility study); design budget estimate (at the preliminary design stage), at this stage, it is necessary to construct an initial relational database for the quotations and relationships between each engineering project according to experience and market prices; revised budget estimate (at the technical design stage, technical design can be carried out as needed for major projects or technically complex projects); construction drawing budget (at the construction drawing design stage); maximum tender price / tender control price (at the tender stage); contract price (at the contract signing stage); project settlement (at the contract implementation stage), project settlement mainly involves after the end of each construction stage or construction project, this step mainly measures the expenses required for the subsequent project based on the current expenses, market prices, etc., and its main manifestation is the engineering change of the design plan, specifically manifested as budget reduction, adjustment of unnecessary expenses, etc. Although there are many types of engineering changes and various reasons for their occurrence, essentially, they are manifested as changes in price and quantity; final accounts of completed projects (at the stage of completion acceptance).

[0050] Factors affecting project cost during project settlement (the impact of engineering changes), such as Figure 1 shown, in most cases, it is caused by design changes.

[0051] This embodiment provides a method for querying project cost data for construction projects. The main purpose of this method for querying project cost data is to add indexes between databases with existing relationships in the relational database on the basis of the original relational database, so as to improve the convenience of querying project cost data and reduce the query difficulty.

[0052] As Figure 2 shown, this method for querying project cost data includes the following steps:

[0053] Step 1: Obtain each unit cost, where the unit cost is each cost item in each construction project;

[0054] Step 2: Construct a fully connected graph according to the correlation degree between any two unit costs, and divide the fully connected graph into regions to obtain multiple communities;

[0055] Step 3: Perform principal component analysis on the unit costs within each community to obtain the core unit costs within each community;

[0056] Step 4: Based on the association between each unit cost of each community and the core unit costs of other communities, obtain the association degree between each unit cost of each community and the core unit costs of other communities;

[0057] Step 5: Integrate the correlation degree between each unit cost of each community and the core unit costs of other communities to obtain the confidence level of index construction for each unit cost of each community with respect to other communities.

[0058] Step 6: Construct the relationship index for each community based on the confidence level of index construction.

[0059] The implementation process of each step is specifically described as follows.

[0060] Step 1: Obtain each unit cost, where the unit cost is each cost item in each construction project.

[0061] In the construction project plan, there are multiple construction projects and the estimated costs of each construction project. And a complete construction project contains several cost items, and each cost item is a unit cost. Therefore, the construction project plan includes multiple construction projects, and each construction project includes multiple unit costs. Thus, each unit cost is obtained according to the construction project plan.

[0062] The construction project plan is the daily consumption volume of each unit cost. If there are cases where the unit costs in different stages and projects are the same, the unit costs are named in the order they appear in the construction project plan to avoid the situation where multiple unit costs are exactly the same.

[0063] It should be understood that the unit cost involves multiple cost data (i.e., cost values) corresponding to the corresponding items in the construction project. For example, the corresponding construction period is divided into multiple time periods (such as every day), and one cost data is obtained for each time period, so as to obtain multiple cost data involved in the unit cost. Therefore, the unit cost is essentially a cost sequence composed of multiple cost data.

[0064] This construction project cost data query method is used to solve the following existing problems: Since different unit costs in a complete construction project may have different start times and inconsistent time sequences, it has led to a sharp increase in the difficulty of constructing a relational database, and the difficulty of constructing an index has increased due to time mismatch during query.

[0065] Step 2: Construct a fully connected graph according to the correlation degree between any two unit costs, and divide the fully connected graph into regions to obtain multiple communities.

[0066] Only the expected project cost consumption can be reflected in the construction project plan. Therefore, an initial relational database needs to be constructed based on their mutual relationships, that is, the existing covariation relationship. In this embodiment, a full connection graph is constructed according to the correlation degree between any two unit costs to analyze different unit costs and construct an initial relational database.

[0067] In an exemplary embodiment, as Figure 3 shown, the process of obtaining the correlation degree includes:

[0068] Step 2-1: Obtain the construction period consistency of any two unit costs according to the time interval between the construction periods of any two unit costs.

[0069] Set the first unit cost and the second unit cost as any two unit costs. It should be understood that the longer the time interval between the construction periods of the first unit cost and the second unit cost, that is, the farther the construction periods of these two unit costs are apart in time, then the lower the construction period consistency between these two unit costs. Therefore, according to the time interval between the construction periods of the first unit cost and the second unit cost, the construction period consistency of the first unit cost and the second unit cost is obtained, and the construction period consistency is inversely proportional to the time interval. In an exemplary embodiment, the calculation formula for the construction period consistency of the first unit cost and the second unit cost is as follows:

[0070] ;

[0071] Wherein, represents the construction period consistency of the first unit cost and the second unit cost, represents the time interval between the construction periods of the first unit cost and the second unit cost, represents the exponential function with the natural constant e as the base, which is used for negative correlation normalization.

[0072] The time interval refers to: assuming that the construction period of the first unit cost is earlier than that of the second unit cost, then the time interval between the construction periods of the first unit cost and the second unit cost is the time interval between the end moment of the construction period of the first unit cost and the start moment of the construction period of the second unit cost. If the end moment of the construction period of the first unit cost is later than the start moment of the construction period of the second unit cost, the time interval between the construction periods of the first unit cost and the second unit cost is set to 0.

[0073] Step 2-2: Based on the construction period consistency, combined with whether any two unit costs are in the same construction project and the similarity of any two unit costs, obtain the correlation degree of any two unit costs.

[0074] Set a judgment coefficient using the first unit cost and the second unit cost to characterize whether the first unit cost and the second unit cost are in the same construction project. If the first unit cost and the second unit cost are in the same construction project, the judgment coefficient of the first unit cost and the second unit cost is 1. If the first unit cost and the second unit cost are not in the same construction project, the judgment coefficient of the first unit cost and the second unit cost is 0.

[0075] Obtain the similarity between the first unit cost and the second unit cost. In an exemplary embodiment, the similarity between the first unit cost and the second unit cost is specifically the Pearson correlation coefficient between the first unit cost and the second unit cost. As other implementation manners, it can also be other similarity calculation methods such as the cosine similarity between the first unit cost and the second unit cost. It should be understood that due to objective factors, such as different construction periods, the number of cost data included in the first unit cost and the second unit cost is different. Therefore, interpolation can also be performed on other shorter unit costs (that is, unit costs with fewer cost data), so that the lengths of the first unit cost and the second unit cost are the same. Additionally, if the interpolation operation is not performed, the DTW distance between the first unit cost and the second unit cost can also be obtained, and then the obtained DTW distance is negatively correlated to obtain the similarity.

[0076] It should be understood that regardless of the similarity calculation method used, after obtaining the similarity, it needs to be normalized for subsequent processing. The normalization in this embodiment, as well as the norm normalization function, can be specifically set according to the actual situation. For example: The maximum-minimum normalization method can be used, or the following common methods can also be used: , represents the processing object, and exp represents the exponential function with the natural constant e as the base.

[0077] Therefore, according to the construction period consistency between the first unit cost and the second unit cost, combined with whether the first unit cost and the second unit cost are in the same construction project, and the similarity between the first unit cost and the second unit cost, the correlation degree between the first unit cost and the second unit cost is obtained. The calculation formula is as follows:

[0078]

[0079] Among them, is the correlation degree between the first unit cost and the second unit cost, is the judgment coefficient of the first unit cost and the second unit cost, is the similarity between the first unit cost and the second unit cost after normalization.

[0080] The degree of correlation can indicate the mutual influence relationship between the first unit cost and the second unit cost. The larger the value, the greater the influence relationship. The closer the value is to 0, it indicates that there is less association between the first unit cost and the second unit cost.

[0081] Therefore, according to the degree of correlation between any two unit costs, a fully connected graph is constructed, where each node in the fully connected graph is each unit cost, and the degree between any two nodes is the degree of correlation.

[0082] Then, the fully connected graph is partitioned into regions to obtain multiple communities. In an exemplary embodiment, the louvain algorithm is used to partition the fully connected graph into regions to obtain multiple communities. There are several unit costs in each community, and there is a relationship between them.

[0083] Step 3: Perform principal component analysis on the unit costs within each community to obtain the core unit costs within each community.

[0084] The same community contains several unit costs, which have similarities or are in the same construction project. And some unit costs change due to the influence of other unit costs. Therefore, if all the unit costs in the community are analyzed, it is not very realistic for large-scale construction projects. So in this embodiment, by analyzing the unit costs in the same community, only the source unit costs are obtained and used as the core unit costs for analysis.

[0085] Set the first target community as any community. Interpolate the construction periods of all unit costs in the first target community. Perform interpolation operations on all unit costs in the first target community according to the construction period of the longest unit cost in the first target community, where the object of interpolation is the cost data for each day during the construction period of the unit cost. Make the construction periods of each unit cost in the first target community the same.

[0086] Then, use the PCA principal component analysis algorithm to perform principal component analysis on all unit costs in the first target community for dimensionality reduction, obtaining several principal component directions. These principal component directions are linear combinations of the cost data for each day during the construction period of multiple unit costs. Each principal component direction represents a source unit cost influencing factor. When the unit cost in the principal component direction changes, other related unit costs will also change accordingly.

[0087] Use the PCA principal component analysis algorithm to perform principal component analysis on all unit costs in the first target community, and obtain the unit costs corresponding to each principal component direction in the first target community. Define these unit costs as the core unit costs.

[0088] Step 4: Based on the associations between the individual unit costs of each community and the core unit costs of other communities, obtain the degree of association between the individual unit costs of each community and the core unit costs of other communities.

[0089] Since it is different from the construction project plan in the specific construction process, and during the construction period of a unit cost, due to the need to cooperate with other unit costs in the project, there may be situations where the construction period is completed ahead of schedule or behind schedule, resulting in different daily cost consumption from the plan during the actual construction process. Although this change will affect the recording of project cost data, its change can more prominently show the relationship with other unit costs not in the same community. Therefore, in this embodiment, by analyzing the covariation relationship between the corresponding unit costs and other related unit costs during the construction period up to the current date, the hidden relationship of project cost data changes is analyzed to obtain the confidence level of index construction. Before obtaining the confidence level of index construction, it is necessary to obtain the degree of association between the individual unit costs of each community and the core unit costs of other communities based on the associations between the individual unit costs of each community and the core unit costs of other communities.

[0090] In an exemplary embodiment, as Figure 4 shown, the process of obtaining the degree of association includes:

[0091] Step 4-1: Obtain the regression parameters when the individual unit costs in the first target community form a linear combination of the core unit costs in the first target community during the principal component analysis of the individual unit costs in the first target community.

[0092] Based on the core principle of the PCA algorithm, the core unit costs in the first target community are a linear combination of all unit costs in the first target community. Therefore, during the principal component analysis of the individual unit costs in the first target community, obtain the regression parameters when the individual unit costs in the first target community form a linear combination of the core unit costs in the first target community. Thus, the contribution of the individual unit costs in the first target community to the core unit costs in the first target community depends on the magnitude of their regression parameters.

[0093] Step 4-2: According to the regression parameters and the preset starting weights, obtain the weighted regression parameters of the individual unit costs in the first target community for each core unit cost.

[0094] Preset a starting weight. Each unit cost in the first target community corresponds to a preset starting weight. Set any one unit cost in the first target community as the m-th unit cost. If at the current moment, that is, during the construction period of the current date, the construction period of the m-th unit cost has started, then the preset starting weight of the m-th unit cost is recorded as 1, otherwise it is recorded as 0. Thus, the preset starting weights of each unit cost in the first target community are obtained.

[0095] According to the regression parameters and the preset starting weights, obtain the weighted regression parameters of each unit cost in the first target community with respect to each core unit cost. In this embodiment, multiply the regression parameters by the preset starting weights, and use the obtained product as the weighted regression parameters.

[0096] Step 4-3: Obtain the similarity between each unit cost in the first target community and each unit cost in the second target community.

[0097] Set the second target community as any community, and it is a different community from the first target community. Obtain the similarity between each unit cost in the first target community and each unit cost in the second target community. The similarity can be the Pearson correlation coefficient, cosine similarity, etc.

[0098] Step 4-4: According to the weighted regression parameters and the similarity, obtain the correlation degree between each unit cost in the second target community and each core unit cost in the first target community.

[0099] In an exemplary embodiment, as Figure 5 shown, the specific implementation process of step 4-4 is as follows:

[0100] Step 4-4-1: According to the weighted regression parameters of each unit cost in the first target community with respect to each core unit cost and the similarity, obtain the associated sub-degree corresponding to each unit cost in the first target community.

[0101] Step 4-4-2: Integrate the associated sub-degrees corresponding to each unit cost in the first target community to obtain the correlation degree between each unit cost in the second target community and each core unit cost in the first target community.

[0102] In an exemplary embodiment, the calculation formula of the correlation degree is as follows:

[0103] ;

[0104] Among them, represents the correlation degree between the i-th unit cost in the second target community and the j-th core unit cost in the K-th community, represents the j-th core unit cost in the K-th community, is the quantity of unit costs in the Kth community, where the Kth community corresponds to the first target community; is the regression parameter when the mth unit cost in the Kth community is in the linear combination of the jth core unit cost in the Kth community; is the preset start weight of the mth unit cost in the Kth community. If the construction period of the mth unit cost has started at the current moment, the preset start weight of the mth unit cost is recorded as 1, otherwise it is recorded as 0; is the cost sequence of the ith unit cost within the second target community; is the cost sequence of the mth unit cost in the Kth community; denotes and similarity of denotes the normalization function.

[0105] denotes the reference weight when the mth unit cost in the Kth community is the regression parameter in the linear combination of the jth core unit cost in the Kth community. The larger this value, the greater the reference significance of the mth unit cost in constructing the jth core unit cost. Then if at this time has a larger value, it indicates that the mth unit cost is more important and has a greater change correlation.

[0106] denotes the degree of associated sub - corresponding to the mth unit cost in the Kth community.

[0107] By adopting the above method, the association degree between each unit cost within the second target community and the jth core unit cost within the Kth community is obtained, thereby obtaining the association degree between each unit cost within other each community and the jth core unit cost within the Kth community, and thus obtaining the association degree between each unit cost within other each community and each core unit cost within each community.

[0108] Step 5: Integrate the association degrees between each unit cost of each community and each core unit cost of other each community to obtain the index - construction confidence of each unit cost of each community with respect to other each community.

[0109] If there are multiple core unit costs in the K-th community and they are necessarily linearly independent of each other, then when the difference in the degree of association between the i-th unit cost in the second target community and the multiple core unit costs in the K-th community is not significant, it indicates that the association between the i-th unit cost and the K-th community is not strong enough, so there is no need to construct an index. Then when the degree of association between the i-th unit cost and only one core unit cost in the K-th community is greater, it is only related to one type of core unit cost, that is, the i-th unit cost is highly similar to only one core unit cost in the K-th community and extremely dissimilar to other core unit costs, and an index needs to be constructed. Therefore, in this embodiment, the degree of association between the i-th unit cost and each core unit cost in the K-th community is integrated to obtain the index construction confidence level of the i-th unit cost and the K-th community.

[0110] In an exemplary embodiment, as Figure 6 shown, a specific obtaining process of the index construction confidence level is given as follows:

[0111] Step 5-1: Obtain the maximum value among the degrees of association between each unit cost in the second target community and each core unit cost in the first target community.

[0112] Step 5-2: Obtain the remaining degrees of association except the maximum value among the degrees of association between each unit cost in the second target community and each core unit cost in the first target community.

[0113] Step 5-3: Determine the index construction confidence level of each unit cost in the second target community and the first target community according to the difference between the maximum value and the remaining degrees of association.

[0114] The greater the degree of difference between the maximum value and the remaining degrees of association, the more it indicates that the unit cost in the second target community is only related to one type of core unit cost in the first target community, and the difference between this degree of association and the degrees of association with other core unit costs in the first target community is large, indicating that the association between the unit cost in the second target community and the first target community is strong enough, so an index needs to be constructed.

[0115] In an exemplary embodiment, the calculation formula of the index construction confidence level is as follows:

[0116] ;

[0117] Wherein, represents the index construction confidence level of the i-th unit cost in the second target community and the K-th community, represents the maximum value among the degrees of association between the i-th unit cost in the second target community and all core unit costs in the K-th community, Denotes the number of core unit costs other than the core unit cost corresponding to the maximum value in the Kth community. Denotes the th core unit cost other than the core unit cost corresponding to the maximum value in the Kth community. Denotes the degree of association between the ith unit cost in the second target community and the th core unit cost in the Kth community.

[0118] Denotes the mean of the degrees of association between the ith unit cost in the second target community and the th core unit cost in the Kth community, excluding the maximum degree of association.

[0119] Denotes the degree of difference between the maximum value of the degrees of association between the ith unit cost in the second target community and all core unit costs in the Kth community, and the degrees of association between the ith unit cost in the second target community and all core unit costs in the Kth community excluding the maximum value. The larger this value, the greater the difference between the maximum core unit cost and other core unit costs, indicating that there is an index for which a relationship needs to be constructed.

[0120] Step 6: Construct a confidence level based on the index and construct a relationship index for each community.

[0121] The greater the confidence level for index construction, the more a relationship index needs to be constructed. In an exemplary embodiment, as Figure 7 shown, a specific construction process for the relationship index is as follows:

[0122] Step 6-1: Compare the confidence levels for index construction of each unit cost in each community with other communities with a preset threshold.

[0123] Step 6-2: Construct a relationship index for the database corresponding to the community where the unit cost corresponding to the confidence level for index construction greater than the preset threshold is located.

[0124] Preset a threshold, the range of this preset threshold is 0 - 1, and the specific value of this preset threshold is set according to actual judgment needs, such as 0.68.

[0125] Compare the confidence levels for index construction of each unit cost in each community with other communities with the preset threshold. If it is greater than the preset threshold, it means the confidence level for index construction is relatively large and a relationship index needs to be constructed; if it is less than or equal to the preset threshold, it means the confidence level for index construction is relatively small and a relationship index does not need to be constructed.

[0126] Obtain the index construction confidence greater than the preset threshold of each unit cost of each community and the index construction confidence of other communities, and the corresponding unit costs of each community of these index construction confidences.

[0127] Take the index construction confidence of the i-th unit cost in the second target community and the K-th community as an example. If the index construction confidence is greater than the preset threshold, then, in the database corresponding to the k-th community, construct a relationship index for the database corresponding to the second target community where the i-th unit cost is located.

[0128] Thus, the construction of the relationship index is completed.

[0129] This embodiment also provides a project cost data query system for construction projects, including: a memory and a processor; the memory is connected to the processor, and the memory is used to store program instructions; the processor is used to implement the steps in the above-described embodiment of the project cost data query method for construction projects when the program instructions are executed.

[0130] In an exemplary embodiment, the present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, it implements the steps in the above-described embodiment of the project cost data query method for construction projects.

[0131] It should be noted that: the above sequence of embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or consecutive order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0132] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

Claims

1. A method for querying project cost data for construction projects, characterized in that Including: Obtain each unit cost, where the unit cost is each cost item in each construction project; Construct a fully connected graph according to the correlation degree between any two unit costs, and partition the fully connected graph into regions to obtain multiple communities; Perform principal component analysis on the unit costs within each community to obtain the core unit costs within each community; Obtain the regression parameters when each unit cost in the first target community forms a linear combination of the core unit costs in the first target community during the principal component analysis of the unit costs in the first target community; the first target community is any community; according to the regression parameters and a preset starting weight, obtain the weighted regression parameters of each unit cost in the first target community with respect to each core unit cost; obtain the similarity between each unit cost in the first target community and each unit cost in the second target community; The second target community is any community and is different from the first target community; according to the weighted regression parameters and the similarity, obtain the correlation degree between each unit cost in the second target community and each core unit cost in the first target community; Fuse the correlation degrees between each unit cost in each community and each core unit cost in other communities to obtain the index construction confidence degrees of each unit cost in each community with respect to other communities; Construct a relationship index for each community according to the index construction confidence degrees; 2. The method for querying project cost data for construction projects according to claim 1, characterized in that, The process of obtaining the correlation degree between any two unit costs includes: Obtain the construction period consistency of any two unit costs according to the time interval between the construction periods of the any two unit costs; Based on the construction period consistency, combine whether the any two unit costs are in the same construction project and the similarity of the any two unit costs to obtain the correlation degree between the any two unit costs; 3. The method for querying project cost data for construction projects according to claim 1, characterized in that, According to the weighted regression parameters and the similarity, obtaining the correlation degree between each unit cost in the second target community and each core unit cost in the first target community includes: Obtain the associated sub - degrees corresponding to each unit cost in the first target community according to the weighted regression parameters of each unit cost in the first target community with respect to each core unit cost and the similarity; Fuse the associated sub - degrees corresponding to each unit cost in the first target community to obtain the correlation degree between each unit cost in the second target community and each core unit cost in the first target community; 4. The method for querying project cost data for construction projects according to claim 3, characterized in that, The calculation formula of the correlation degree is as follows: ； Among them, represents the degree of association between the i-th unit cost in the second target community and the j-th core unit cost in the K-th community, is the number of unit costs in the K-th community, and the K-th community corresponds to the first target community; is the regression parameter when the m-th unit cost in the K-th community forms a linear combination of the j-th core unit costs in the K-th community, is the preset start weight of the m-th unit cost in the K-th community. If the construction period of the m-th unit cost has started at the current moment, then the preset start weight of the m-th unit cost is recorded as 1, otherwise it is recorded as 0; is the cost sequence of the i-th unit cost in the second target community, is the cost sequence of the m-th unit cost in the K-th community, represents and similarity, represents a normalization function.

5. The method for querying project cost data for construction projects according to claim 1 is characterized in that it integrates Fusing the correlation degrees between each unit cost in each community and each core unit cost in other communities to obtain the index construction confidence degrees of each unit cost in each community with respect to other communities includes: Obtain the maximum value among the correlation degrees between each unit cost in the second target community and each core unit cost in the first target community; Obtain the remaining correlation degrees except the maximum value among the correlation degrees between each unit cost in the second target community and each core unit cost in the first target community; Determine the confidence level of index construction for each unit cost in the second target community and the first target community according to the difference between the maximum value and the remaining correlation degrees.

6. The method for querying project cost data for construction projects according to claim 5, characterized in that, The calculation formula for the confidence level of index construction is as follows: ； Among them, represents the confidence level of the construction of the index of the i-th unit cost in the second target community and the K-th community, represents the maximum value among the degrees of association between the i-th unit cost in the second target community and all core unit costs in the K-th community, represents the number of the remaining core unit costs in the K-th community except for the core unit cost corresponding to the maximum value, represents the -th core unit cost in the K-th community except for the core unit cost corresponding to the maximum value, represents the degree of association between the i-th unit cost in the second target community and the -th core unit cost in the K-th community.

7. The method for querying project cost data for construction projects according to claim 1, characterized in that, Construct the relationship index of each community according to the confidence level of index construction, including: Compare each unit cost of each community with the confidence level of index construction of other communities and a preset threshold; Construct the relationship index of the database corresponding to the community where the unit cost corresponding to the confidence level of index construction greater than the preset threshold is located.

8. A method for querying project cost data for construction projects as described in claim 1, characterized in that, Perform regional division on the fully connected graph to obtain multiple communities, including: Use the louvain algorithm to perform regional division on the fully connected graph to obtain multiple communities.

9. A project cost data query system for construction projects, characterized by comprising: A memory and a processor; The memory is connected to the processor; The memory is used to store program instructions; The processor is used to implement the method for querying project cost data for construction projects described in any one of claims 1-8 when the program instructions are executed.

Images