CN117057743A - Building engineering project consultation cost management method and system thereof - Google Patents
Building engineering project consultation cost management method and system thereof Download PDFInfo
- Publication number
- CN117057743A CN117057743A CN202311059937.1A CN202311059937A CN117057743A CN 117057743 A CN117057743 A CN 117057743A CN 202311059937 A CN202311059937 A CN 202311059937A CN 117057743 A CN117057743 A CN 117057743A
- Authority
- CN
- China
- Prior art keywords
- cost
- feature vector
- expense
- feature
- vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000007726 management method Methods 0.000 title claims description 46
- 239000011159 matrix material Substances 0.000 claims abstract description 120
- 230000008859 change Effects 0.000 claims abstract description 43
- 238000004458 analytical method Methods 0.000 claims abstract description 15
- 238000012552 review Methods 0.000 claims abstract description 8
- 239000013598 vector Substances 0.000 claims description 252
- 238000010276 construction Methods 0.000 claims description 46
- 238000009223 counseling Methods 0.000 claims description 18
- 238000013527 convolutional neural network Methods 0.000 claims description 15
- 238000003062 neural network model Methods 0.000 claims description 12
- 230000004927 fusion Effects 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 230000004048 modification Effects 0.000 claims description 7
- 238000012986 modification Methods 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 11
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 7
- 238000007689 inspection Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000002708 enhancing effect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 238000000547 structure data Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000007728 cost analysis Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
A method and system for managing the consultation cost of building engineering project are disclosed. Firstly, acquiring expense examination data of a building engineering project, wherein the expense examination data comprises consultation expense details, consultation service stage expense, expense payment records, expense change adjustment records, expense invoice certificates and expense accounting reports, then, carrying out semantic analysis on the expense examination data to obtain a topology expense related global feature matrix, and then, determining whether the project consultation expense is reasonable or not based on the topology expense related global feature matrix. In this way, a rationality review of project consultation costs can be performed to reduce the impact of human error and subjective factors on review results.
Description
Technical Field
The present disclosure relates to the field of intelligent management, and more particularly, to a construction project consultation cost management method and system thereof.
Background
The construction project consultation cost management means that the consultation cost is effectively controlled and optimized so as to ensure the rationality, transparency and effectiveness of the consultation cost. The construction project consultation cost management is an important component of construction project management and is also a key factor for improving the benefit of construction projects.
Wherein, the expense examination is an important link in the consulting expense management of the construction project. Which is usually done manually. There are the following problems: (1) The efficiency of manual examination cost is low, the time consumption is long, and errors are easy to occur; (2) The quality of the manual examination cost is low, and objectivity and fairness are difficult to ensure; (3) The method of manually examining the cost is single, and various factors and relevance are difficult to consider.
Thus, an optimized solution is desired.
Disclosure of Invention
In view of this, the disclosure provides a method and a system for managing project consultation costs of construction engineering, which can automatically capture and construct complex association relationships contained in cost inspection data by using a graph neural network, so as to realize reasonable inspection of project consultation costs, and reduce the influence of human errors and subjective factors on inspection results.
According to an aspect of the present disclosure, there is provided a construction project consultation cost management method including:
acquiring expense examination data of a building engineering project, wherein the expense examination data comprises consultation expense details, consultation service stage expense, expense payment records, expense change adjustment records, expense invoice certificates and expense accounting reports;
carrying out semantic analysis on the expense examination data to obtain a topological expense related global feature matrix; and
and determining whether project consultation cost is reasonable or not based on the topology cost related global feature matrix.
According to another aspect of the present disclosure, there is provided a construction project consultation cost management system including:
the system comprises a cost examination data acquisition module, a cost verification module and a cost verification module, wherein the cost examination data acquisition module is used for acquiring cost examination data of a building engineering project, and the cost examination data comprises consultation cost details, consultation service stage cost, cost payment records, cost change adjustment records, cost invoice certificates and cost accounting reports;
the semantic analysis module is used for carrying out semantic analysis on the expense examination data to obtain a topological expense related global feature matrix; and
and the cost rationality judging module is used for determining whether the project consultation cost is reasonable or not based on the topology cost related global feature matrix.
According to an embodiment of the present disclosure, first, fee examination data of a construction project is acquired, the fee examination data including a consultation fee detail, a consultation service stage fee, a fee payment record, a fee change adjustment record, a fee invoice credential and a fee accounting report, then, semantic analysis is performed on the fee examination data to obtain a topology fee-related global feature matrix, and then, whether the project consultation fee is reasonable is determined based on the topology fee-related global feature matrix. In this way, a rationality review of project consultation costs can be performed to reduce the impact of human error and subjective factors on review results.
Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features and aspects of the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 illustrates a flowchart of a construction project consultation cost management method according to an embodiment of the present disclosure.
Fig. 2 illustrates an architecture diagram of a construction project consultation cost management method according to an embodiment of the present disclosure.
Fig. 3 shows a flowchart of sub-step S120 of the construction project consultation cost management method according to an embodiment of the present disclosure.
Fig. 4 shows a flowchart of sub-step S121 of the construction project consultation cost management method according to an embodiment of the present disclosure.
Fig. 5 shows a flowchart of sub-step S130 of the construction project consultation cost management method according to an embodiment of the present disclosure.
Fig. 6 shows a flowchart of sub-step S131 of the construction project consultation cost management method according to an embodiment of the present disclosure.
Fig. 7 illustrates a block diagram of an architectural engineering project consultation charge management system according to an embodiment of the present disclosure.
Fig. 8 illustrates an application scenario diagram of a construction project consultation cost management method according to an embodiment of the present disclosure.
Detailed Description
The following description of the embodiments of the present disclosure will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the disclosure. All other embodiments, which can be made by one of ordinary skill in the art without undue burden based on the embodiments of the present disclosure, are also within the scope of the present disclosure.
As used in this disclosure and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
In addition, numerous specific details are set forth in the following detailed description in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order not to obscure the present disclosure.
Aiming at the technical problems, the technical concept of the present disclosure is to automatically capture and construct complex association relations contained in the expense examination data by using a graph neural network, so as to realize reasonable examination of project consultation expense, and reduce the influence of human errors and subjective factors on examination results.
It should be appreciated that the graph data structure has the capability of expressing complex relationships, and can flexibly represent the connection relationships between nodes. There is a complex association between individual data items of the expense review data (counsel expense details, counsel service stage expense, expense payment records, expense change adjustment records, expense invoice vouchers, and expense accounting reports), which can be better characterized using the graph data structure.
Based on this, fig. 1 shows a flowchart of a construction project consultation cost management method according to an embodiment of the present disclosure. Fig. 2 illustrates an architecture diagram of a construction project consultation cost management method according to an embodiment of the present disclosure. As shown in fig. 1 and 2, the construction project consultation cost management method according to an embodiment of the present disclosure includes the steps of: s110, acquiring expense examination data of the building engineering project, wherein the expense examination data comprises consultation expense details, consultation service stage expense, expense payment records, expense change adjustment records, expense invoice certificates and expense accounting reports; s120, carrying out semantic analysis on the expense examination data to obtain a topological expense related global feature matrix; and S130, determining whether project consultation cost is reasonable or not based on the topology cost related global feature matrix.
Accordingly, in the technical solution of the present disclosure, first, fee examination data including counseling fee details, counseling service stage fee, fee payment record, fee modification adjustment record, fee invoice credential, and fee accounting report is acquired.
Then, extracting node characteristic information and topology characteristic information of the expense examination data to obtain an expense related global characteristic matrix and a similarity topology characteristic matrix; and the cost related global feature matrix and the similarity topological feature matrix are subjected to a semantic association encoder based on a graph neural network model to obtain the topological cost related global feature matrix.
In one specific example of the present disclosure, the encoding process for extracting node feature information and topology feature information of the expense review data to obtain an expense-related global feature matrix and a similarity topology feature matrix includes: firstly, respectively carrying out data structuring on the consultation cost detail, the consultation service stage cost, the cost payment record, the cost change adjustment record, the cost invoice certificate and the cost accounting report to obtain a consultation cost detail coding vector, a consultation service stage cost coding vector, a cost payment record coding vector, a cost change adjustment record coding vector, a cost invoice certificate coding vector and a cost accounting coding vector; then, the consultation expense detail code vector, the consultation service stage expense code vector, the expense payment record code vector, the expense change adjustment record code vector, the expense invoice credential code vector and the expense accounting code vector are respectively processed through a feature extractor of a full-connection layer to obtain a consultation expense detail feature vector, a consultation service stage expense feature vector, an expense payment record feature vector, an expense change adjustment record feature vector, an expense invoice credential feature vector and an expense accounting feature vector; calculating cosine similarity between any two of the consultation cost detail feature vector, the consultation service stage cost feature vector, the cost payment record feature vector, the cost change adjustment record feature vector, the cost invoice credential feature vector and the cost accounting feature vector to obtain a similarity topology matrix; then, the similarity topological matrix passes through a topological feature extractor based on a two-dimensional convolutional neural network model to obtain a similarity topological feature matrix; further, the counseling fee detail feature vector, the counseling service stage fee feature vector, the fee payment record feature vector, the fee change adjustment record feature vector, the fee invoice credential feature vector and the fee accounting feature vector are arranged into a fee-related global feature matrix.
That is, semantic information contained in the counsel fee details, counsel service stage fee, fee payment record, fee change adjustment record, fee invoice voucher and fee accounting report is extracted as a node, and association degree information among the data items is established as an edge in a cosine similarity manner. In this way, the graph data structure is constructed.
And then, the cost related global feature matrix and the similarity topological feature matrix are subjected to a semantic association encoder based on a graph neural network model to obtain a topological cost related global feature matrix.
Accordingly, as shown in fig. 3, performing semantic analysis on the expense censored data to obtain a topology expense related global feature matrix, including: s121, extracting node characteristic information and topology characteristic information of the expense examination data to obtain an expense related global characteristic matrix and a similarity topology characteristic matrix; and S122, the cost-related global feature matrix and the similarity topological feature matrix are subjected to a semantic association encoder based on a graph neural network model to obtain the topological cost-related global feature matrix. It should be appreciated that the graph neural network (Graph Neural Network, GNN for short) is a machine learning model for processing graph structure data. It captures the topology of the graph by defining interactions between nodes on the graph and applies these topological features to the nodes' representation learning and prediction tasks. The main purpose of the graph neural network is to analyze and model graph structure data, wherein nodes can be represented as entities in the graph, and edges can represent relationships or connections between the entities. Unlike conventional neural networks, graph neural networks allow for interactions between nodes, where information can be propagated and aggregated. Features can be extracted from two aspects using a graph neural network model: node characteristic information and topology characteristic information. 1. Node characteristic information: each node may contain features associated with it, such as cost amount, cost type, cost time, etc., and through the neural network model, the node's representation vector may be learned, including the node's own feature information and its neighboring nodes ' information. 2. Topology characteristic information: the graph neural network model can propagate and aggregate information in the graph through message passing and aggregation operations, so that each node can obtain topological characteristics related to adjacent nodes, such as neighbor node characteristics of the node, centrality of the node and the like, and the topological characteristics can reflect positions and relations of the nodes in the graph, and are helpful for understanding roles of the nodes in the whole graph structure. By combining the node characteristic information and the topology characteristic information, a global characteristic matrix and a similarity topology characteristic matrix which are related to the cost can be obtained. The global feature matrix contains the comprehensive features of all nodes and can be used for overall cost correlation analysis. The similarity topological feature matrix reflects the similarity and topological relation among the nodes and can be used for similarity measurement and cluster analysis of the nodes. Finally, through a semantic association encoder based on a graph neural network model, the cost-related global feature matrix and the similarity topological feature matrix can be encoded and integrated to obtain the topological cost-related global feature matrix. This matrix may be used for further cost analysis, prediction or other related tasks to grasp the characteristics and relevance of the cost review data as a whole.
More specifically, in step S121, as shown in fig. 4, node feature information and topology feature information of the expense inspection data are extracted to obtain an expense-related global feature matrix and a similarity topology feature matrix, including: s1211, respectively carrying out data structuring on the consultation cost detail, the consultation service stage cost, the cost payment record, the cost change adjustment record, the cost invoice credential and the cost accounting report to obtain a consultation cost detail coding vector, a consultation service stage cost coding vector, a cost payment record coding vector, a cost change adjustment record coding vector, a cost invoice credential coding vector and a cost accounting coding vector; s1212, the counseling expense detail code vector, the counseling service stage expense code vector, the expense payment record code vector, the expense change adjustment record code vector, the expense invoice credential code vector and the expense accounting code vector are respectively processed by a feature extractor of a full connection layer to obtain a counseling expense detail feature vector, a counseling service stage expense feature vector, an expense payment record feature vector, an expense change adjustment record feature vector, an expense invoice credential feature vector and an expense accounting feature vector; s1213, arranging the consultation expense detail feature vector, the consultation service stage expense feature vector, the expense payment record feature vector, the expense change adjustment record feature vector, the expense invoice credential feature vector and the expense accounting feature vector into the expense-related global feature matrix; s1214, constructing a similarity topology matrix based on similarity association between the counsel fee detail feature vector, the counsel service stage fee feature vector, the fee payment record feature vector, the fee change adjustment record feature vector, the fee invoice credential feature vector and the fee accounting feature vector; and S1215, passing the similarity topological matrix through a topological feature extractor based on a two-dimensional convolutional neural network model to obtain the similarity topological feature matrix. It is worth mentioning that the two-dimensional convolutional neural network (2D Convolutional Neural Network, abbreviated as 2D CNN) is a deep learning model for processing two-dimensional image data, which is a variant of the convolutional neural network (Convolutional Neural Network, abbreviated as CNN) specifically designed for processing input data having a two-dimensional structure. The two-dimensional convolutional neural network extracts features by applying a two-dimensional convolutional operation on the input data. The convolution operation is a local perceptual mechanism that uses a filter (also called a convolution kernel) to slide over the input data and calculate the convolution results for each location. This effectively captures spatially localized features in the input data, such as edges, textures, shapes, and the like. In two-dimensional convolutional neural networks, convolutional operations are typically used in combination with other operations, such as activation functions, pooling operations, and fully-connected layers, which can further extract and combine features to enable the network to learn higher-level representations. A typical structure of a two-dimensional convolutional neural network includes a stack of multiple convolutional layers and pooled layers. The convolutional layer is used to extract features, and by increasing the number and layer number of convolutional kernels, the network can learn more abstract and complex features gradually. The pooling layer is used for reducing the space dimension of the feature map, reducing the parameter number and enhancing the invariance of the network to translation and scaling. Finally, through the full connection layer and the output layer, the two-dimensional convolutional neural network can map the extracted features to specific categories or predict.
More specifically, in step S1214, constructing a similarity topology matrix based on a similarity association between the counsel expense detail feature vector, the counsel service stage expense feature vector, the expense payment record feature vector, the expense change adjustment record feature vector, the expense invoice credential feature vector, and the expense accounting feature vector, includes: and calculating cosine similarity between any two of the consultation cost detail feature vector, the consultation service stage cost feature vector, the cost payment record feature vector, the cost change adjustment record feature vector, the cost invoice credential feature vector and the cost accounting feature vector to obtain the similarity topology matrix.
Further, the topological cost related global feature matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether project consultation cost is reasonable or not.
Accordingly, as shown in fig. 5, determining whether the project consultation cost is reasonable based on the topology cost related global feature matrix includes: s131, performing feature distribution optimization on the topology expense related global feature matrix to obtain an optimized topology expense related global feature matrix; and S132, passing the optimized topological cost related global feature matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating whether project consultation cost is reasonable or not.
More specifically, in step S131, as shown in fig. 6, the feature distribution optimization is performed on the topology expense related global feature matrix to obtain an optimized topology expense related global feature matrix, including: s1311, cascading the consultation cost detail feature vector, the consultation service stage cost feature vector, the cost payment record feature vector, the cost change adjustment record feature vector, the cost invoice credential feature vector and the cost accounting feature vector to obtain a first cascade feature vector; s1312, cascading each row feature vector of the topological cost-related global feature matrix to obtain a second cascading feature vector; s1313, performing homogeneous Gilbert space metric dense point distribution sampling fusion on the first cascade feature vector and the second cascade feature vector to obtain an optimized second cascade feature vector; and S1314, reconstructing the feature vector of the optimized second cascade feature vector to obtain the global feature matrix related to the optimized topology cost.
In the technical scheme of the disclosure, when the cost-related global feature matrix and the similarity topological feature matrix are obtained through a semantic association encoder based on a graph neural network model, each row of feature vectors of the topological cost-related global feature matrix are used for expressing topological association representation of the encoding feature representation of each data item of the cost inspection data under a feature semantic similarity topology, so that the representation of the original encoding semantic feature distribution of the data item is influenced while the topological association feature representation is enhanced.
Accordingly, applicants of the present disclosure consider optimizing the topology cost-related global feature matrix by fusing the individual row feature vectors of the topology cost-related global feature matrix with the individual feature vectors representing the original encoded semantic feature distribution of the data item, and further consider dense mining pattern-associated feature expressions of vector-level homogeneous coding based on feature vector granularity, whether feature extraction of full-connection layers or topology-associated coding of a graph neural network model, thereby ranking the consultation cost detail feature vector, the consultation service stage cost feature vector, the cost payment record feature vector, the cost change adjustment record feature vector, the cost invoice credential feature vector, and the cost accounting feature vector as first-level feature vectors obtained after concatenation of cost-related global feature matrices, e.g., asA second cascade of feature vectors concatenated with the respective row feature vectors of the topology cost-dependent global feature matrix, e.g. denoted +.>And performing homogeneous Gilbert spatial metric dense point distribution sampling fusion.
Accordingly, in a specific example, performing homogeneous gilbert spatial metric dense point distribution sampling fusion on the first cascade feature vector and the second cascade feature vector to obtain an optimized second cascade feature vector, including: carrying out homogeneous Gilbert space metric dense point distribution sampling fusion on the first cascade feature vector and the second cascade feature vector by using the following optimization formula to obtain the optimized second cascade feature vector; wherein, the optimization formula is:wherein (1)>Representing the first cascaded eigenvector, < >>Representing the second cascade feature vector, +.>Representing a transpose operation->Represent Min distance and +.>Is super-parameter (herba Cinchi Oleracei)>And->The first cascade feature vector +.>And the second concatenated feature vectorIs defined as the global feature mean value of (2), and feature vector +.>And->Are all row vectors, +.>For multiplying by position point +.>For the addition of position->Representing covariance matrix>Representing the optimized second cascade feature vector.
Here, by the first cascade feature vectorAnd said second cascade feature vector +.>Homogeneous gilbert spatial metric of the feature distribution center of (2) to +.>And said second cascade feature vector +.>Carrying out real (group-trunk) geometric center constraint of fused feature manifold hyperplane in high-dimensional feature space, and taking point-by-point feature association of cross distance constraint as biasThe item is arranged to realize feature dense point sampling pattern distribution fusion in the association constraint limit of the feature distribution, thereby enhancing homogeneous sampling association fusion among vectors, reducing the optimized second cascade feature vector into a topology expense related global feature matrix, improving the representation of the optimized topology expense related global feature matrix on the original coding semantic feature distribution of the data item, and improving the accuracy of classification results obtained by a classifier.
Further, in S132, the global feature matrix related to the optimized topology expense is passed through a classifier to obtain a classification result, where the classification result is used to indicate whether the project consultation expense is reasonable, and the method includes: expanding the global feature matrix related to the optimized topology cost into an optimized classification feature vector according to a row vector or a column vector; performing full-connection coding on the optimized classification feature vector by using a full-connection layer of the classifier to obtain a coding classification feature vector; and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.
That is, in the technical solution of the present disclosure, the label of the classifier includes a reasonable project consultation cost (a first label) and an unreasonable project consultation cost (a second label), wherein the classifier determines to which classification label the optimized topology cost-related global feature matrix belongs through a soft maximum function. It should be noted that the first tag p1 and the second tag p2 do not include a manually set concept, and in fact, during the training process, the computer model does not have a concept of "whether the project consultation cost is reasonable" which is simply that there are two kinds of classification tags and the probability that the output feature is under the two kinds of classification tags, that is, the sum of p1 and p2 is one. Therefore, whether the project consultation cost is reasonable or not is effectively converted into the class probability distribution of the two classes conforming to the natural law through the classification label, and the physical meaning of the natural probability distribution of the label is essentially used instead of the language text meaning of whether the project consultation cost is reasonable or not.
It should be appreciated that the role of the classifier is to learn the classification rules and classifier using a given class, known training data, and then classify (or predict) the unknown data. Logistic regression (logistics), SVM, etc. are commonly used to solve the classification problem, and for multi-classification problems (multi-class classification), logistic regression or SVM can be used as well, but multiple bi-classifications are required to compose multiple classifications, but this is error-prone and inefficient, and the commonly used multi-classification method is the Softmax classification function.
In summary, according to the construction project consultation cost management method disclosed by the embodiment of the disclosure, the project consultation cost can be reasonably inspected, so that the influence of human errors and subjective factors on inspection results is reduced.
Fig. 7 shows a block diagram of an architectural engineering project consultation charge management system 100 according to an embodiment of the present disclosure. As shown in fig. 7, the construction project consultation charge management system 100 according to the embodiment of the present disclosure includes: a fee examination data acquiring module 110 for acquiring fee examination data of the construction project, the fee examination data including a consultation fee detail, a consultation service stage fee, a fee payment record, a fee change adjustment record, a fee invoice credential and a fee accounting report; the semantic analysis module 120 is configured to perform semantic analysis on the expense examination data to obtain a topology expense related global feature matrix; and a cost rationality judging module 130, configured to determine whether the project consultation cost is reasonable based on the topology cost related global feature matrix.
In one possible implementation, the semantic analysis module 120 includes: the feature matrix extraction unit is used for extracting node feature information and topology feature information of the expense examination data to obtain an expense-related global feature matrix and a similarity topology feature matrix; and the semantic association coding unit is used for enabling the cost-related global feature matrix and the similarity topological feature matrix to pass through a semantic association coder based on a graph neural network model so as to obtain the topological cost-related global feature matrix.
In one possible implementation manner, the feature matrix extracting unit includes: a data structuring subunit, configured to perform data structuring on the counsel fee details, the counsel service stage fee, the fee payment record, the fee modification adjustment record, the fee invoice credential, and the fee accounting report to obtain a counsel fee detail encoding vector, a counsel service stage fee encoding vector, a fee payment record encoding vector, a fee modification adjustment record encoding vector, a fee invoice credential encoding vector, and a fee accounting encoding vector, respectively; the full-connection feature extraction subunit is configured to pass the counsel cost detail coding vector, the counsel service stage cost coding vector, the cost payment record coding vector, the cost change adjustment record coding vector, the cost invoice credential coding vector and the cost accounting coding vector through a feature extractor of a full-connection layer to obtain a counsel cost detail feature vector, a counsel service stage cost feature vector, a cost payment record feature vector, a cost change adjustment record feature vector, a cost invoice credential feature vector and a cost accounting feature vector; a global feature matrix arrangement subunit, configured to arrange the consultation cost detail feature vector, the consultation service stage cost feature vector, the cost payment record feature vector, the cost change adjustment record feature vector, the cost invoice credential feature vector and the cost accounting feature vector into the cost-related global feature matrix; a similarity calculation subunit configured to construct a similarity topology matrix based on a similarity association between the counseling fee detail feature vector, the counseling service stage fee feature vector, the fee payment record feature vector, the fee change adjustment record feature vector, the fee invoice credential feature vector, and the fee accounting feature vector; and a topological feature extraction subunit, configured to pass the similarity topological matrix through a topological feature extractor based on a two-dimensional convolutional neural network model to obtain the similarity topological feature matrix.
Here, it will be understood by those skilled in the art that the specific functions and operations of the respective units and modules in the above-described construction project consultation cost management system 100 have been described in detail in the above description of the construction project consultation cost management method with reference to fig. 1 to 6, and thus, repetitive descriptions thereof will be omitted.
As described above, the construction project consultation cost management system 100 according to the embodiment of the present disclosure may be implemented in various wireless terminals, for example, a server or the like having a construction project consultation cost management algorithm. In one possible implementation, the construction project consultation cost management system 100 according to the embodiments of the present disclosure may be integrated into the wireless terminal as one software module and/or hardware module. For example, the construction project consultation cost management system 100 may be a software module in the operating system of the wireless terminal, or may be an application developed for the wireless terminal; of course, the construction project consultation cost management system 100 may also be one of a plurality of hardware modules of the wireless terminal.
Alternatively, in another example, the construction project consultation cost management system 100 and the wireless terminal may be separate devices, and the construction project consultation cost management system 100 may be connected to the wireless terminal through a wired and/or wireless network and transmit the interactive information according to the agreed data format.
Fig. 8 illustrates an application scenario diagram of a construction project consultation cost management method according to an embodiment of the present disclosure. As shown in fig. 8, in this application scenario, first, fee examination data (e.g., D illustrated in fig. 8) of a construction project is acquired, wherein the fee examination data includes a consultation fee detail, a consultation service stage fee, a fee payment record, a fee modification adjustment record, a fee invoice voucher, and a fee accounting report, and then the fee examination data is input to a server where a construction project consultation fee management algorithm is deployed (e.g., S illustrated in fig. 8), wherein the server can process the fee examination data using the construction project consultation fee management algorithm to obtain a classification result for indicating whether the project consultation fee is reasonable.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. A construction project consultation cost management method, comprising:
acquiring expense examination data of a building engineering project, wherein the expense examination data comprises consultation expense details, consultation service stage expense, expense payment records, expense change adjustment records, expense invoice certificates and expense accounting reports;
carrying out semantic analysis on the expense examination data to obtain a topological expense related global feature matrix; and
and determining whether project consultation cost is reasonable or not based on the topology cost related global feature matrix.
2. The construction project consultation cost management method according to claim 1, characterized in that the semantic analysis of the cost review data to obtain a topology cost related global feature matrix includes:
extracting node characteristic information and topology characteristic information of the expense examination data to obtain an expense related global characteristic matrix and a similarity topology characteristic matrix; and
and the cost-related global feature matrix and the similarity topological feature matrix are subjected to a semantic association encoder based on a graph neural network model to obtain the topological cost-related global feature matrix.
3. The construction project consultation fee management method according to claim 2, characterized in that extracting node characteristic information and topology characteristic information of the fee-censoring data to obtain a fee-related global characteristic matrix and a similarity topology characteristic matrix includes:
respectively carrying out data structuring on the consultation cost detail, the consultation service stage cost, the cost payment record, the cost change adjustment record, the cost invoice certificate and the cost accounting report to obtain a consultation cost detail coding vector, a consultation service stage cost coding vector, a cost payment record coding vector, a cost change adjustment record coding vector, a cost invoice certificate coding vector and a cost accounting coding vector;
the consultation expense detail code vector, the consultation service stage expense code vector, the expense payment record code vector, the expense change adjustment record code vector, the expense invoice credential code vector and the expense accounting code vector are respectively processed through a feature extractor of a full-connection layer to obtain a consultation expense detail feature vector, a consultation service stage expense feature vector, an expense payment record feature vector, an expense change adjustment record feature vector, an expense invoice credential feature vector and an expense accounting feature vector;
arranging the counseling fee detail feature vector, the counseling service stage fee feature vector, the fee payment record feature vector, the fee change adjustment record feature vector, the fee invoice credential feature vector and the fee accounting feature vector into the fee-related global feature matrix;
constructing a similarity topology matrix based on a similarity association between the counseling expense detail feature vector, the counseling service stage expense feature vector, the expense payment record feature vector, the expense change adjustment record feature vector, the expense invoice credential feature vector, and the expense accounting feature vector; and
and the similarity topological matrix is passed through a topological feature extractor based on a two-dimensional convolutional neural network model to obtain the similarity topological feature matrix.
4. The construction project consultation cost management method according to claim 3 characterised in that constructing a similarity topology matrix based on a similarity association between the consultation cost detail feature vector, the consultation service stage cost feature vector, the cost payment record feature vector, the cost change adjustment record feature vector, the cost invoice credential feature vector and the cost accounting feature vector includes:
and calculating cosine similarity between any two of the consultation cost detail feature vector, the consultation service stage cost feature vector, the cost payment record feature vector, the cost change adjustment record feature vector, the cost invoice credential feature vector and the cost accounting feature vector to obtain the similarity topology matrix.
5. The construction project consultation cost management method of claim 4 including determining if the project consultation cost is reasonable based on the topology cost related global feature matrix including:
performing feature distribution optimization on the topology expense related global feature matrix to obtain an optimized topology expense related global feature matrix; and
and the global feature matrix related to the optimized topological cost is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the project consultation cost is reasonable or not.
6. The construction project consultation cost management method according to claim 5, characterized in that performing feature distribution optimization on the topology cost related global feature matrix to obtain an optimized topology cost related global feature matrix includes:
cascading the counseling expense detail feature vector, the counseling service stage expense feature vector, the expense payment record feature vector, the expense change adjustment record feature vector, the expense invoice credential feature vector and the expense accounting feature vector to obtain a first cascade feature vector;
cascading each row feature vector of the topological cost related global feature matrix to obtain a second cascading feature vector;
carrying out homogeneous Gilbert space metric dense point distribution sampling fusion on the first cascade feature vector and the second cascade feature vector to obtain an optimized second cascade feature vector; and
and reconstructing the feature vector of the optimized second cascade feature vector to obtain the global feature matrix related to the optimized topology cost.
7. The construction project consultation cost management method of claim 6 including performing homogeneous gilbert spatial metric dense point distribution sampling fusion on the first cascading feature vector and the second cascading feature vector to obtain an optimized second cascading feature vector, including:
carrying out homogeneous Gilbert space metric dense point distribution sampling fusion on the first cascade feature vector and the second cascade feature vector by using the following optimization formula to obtain the optimized second cascade feature vector;
wherein, the optimization formula is:wherein (1)>Representing the first cascaded eigenvector, < >>Representing the second cascade feature vector, +.>Indicating the operation of the transpose,represent Min distance and +.>Is super-parameter (herba Cinchi Oleracei)>And->The first cascade feature vector +.>And said second cascade feature vector +.>Is defined as the global feature mean value of (2), and feature vector +.>And->Are all row vectors, +.>For multiplying by position point +.>For the addition of position->Representing covariance matrix>Representing the optimized second cascade feature vector.
8. A construction project consultation cost management system, comprising:
the system comprises a cost examination data acquisition module, a cost verification module and a cost verification module, wherein the cost examination data acquisition module is used for acquiring cost examination data of a building engineering project, and the cost examination data comprises consultation cost details, consultation service stage cost, cost payment records, cost change adjustment records, cost invoice certificates and cost accounting reports;
the semantic analysis module is used for carrying out semantic analysis on the expense examination data to obtain a topological expense related global feature matrix; and
and the cost rationality judging module is used for determining whether the project consultation cost is reasonable or not based on the topology cost related global feature matrix.
9. The construction project consultation fee management system of claim 8 wherein the semantic analysis module comprises:
the feature matrix extraction unit is used for extracting node feature information and topology feature information of the expense examination data to obtain an expense-related global feature matrix and a similarity topology feature matrix; and
the semantic association coding unit is used for enabling the cost-related global feature matrix and the similarity topological feature matrix to pass through a semantic association coder based on a graph neural network model to obtain the topological cost-related global feature matrix.
10. The construction project consultation fee management system according to claim 9, characterized in that the feature matrix extracting unit includes:
a data structuring subunit, configured to perform data structuring on the counsel fee details, the counsel service stage fee, the fee payment record, the fee modification adjustment record, the fee invoice credential, and the fee accounting report to obtain a counsel fee detail encoding vector, a counsel service stage fee encoding vector, a fee payment record encoding vector, a fee modification adjustment record encoding vector, a fee invoice credential encoding vector, and a fee accounting encoding vector, respectively;
the full-connection feature extraction subunit is configured to pass the counsel cost detail coding vector, the counsel service stage cost coding vector, the cost payment record coding vector, the cost change adjustment record coding vector, the cost invoice credential coding vector and the cost accounting coding vector through a feature extractor of a full-connection layer to obtain a counsel cost detail feature vector, a counsel service stage cost feature vector, a cost payment record feature vector, a cost change adjustment record feature vector, a cost invoice credential feature vector and a cost accounting feature vector;
a global feature matrix arrangement subunit, configured to arrange the consultation cost detail feature vector, the consultation service stage cost feature vector, the cost payment record feature vector, the cost change adjustment record feature vector, the cost invoice credential feature vector and the cost accounting feature vector into the cost-related global feature matrix;
a similarity calculation subunit configured to construct a similarity topology matrix based on a similarity association between the counseling fee detail feature vector, the counseling service stage fee feature vector, the fee payment record feature vector, the fee change adjustment record feature vector, the fee invoice credential feature vector, and the fee accounting feature vector; and
and the topological feature extraction subunit is used for enabling the similarity topological matrix to pass through a topological feature extractor based on a two-dimensional convolutional neural network model to obtain the similarity topological feature matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311059937.1A CN117057743B (en) | 2023-08-22 | 2023-08-22 | Building engineering project consultation cost management method and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311059937.1A CN117057743B (en) | 2023-08-22 | 2023-08-22 | Building engineering project consultation cost management method and system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117057743A true CN117057743A (en) | 2023-11-14 |
| CN117057743B CN117057743B (en) | 2024-03-01 |
Family
ID=88665991
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311059937.1A Active CN117057743B (en) | 2023-08-22 | 2023-08-22 | Building engineering project consultation cost management method and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117057743B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107895177A (en) * | 2017-11-17 | 2018-04-10 | 南京邮电大学 | A kind of migration classification learning method for keeping image classification sparsity structure |
| CN111985894A (en) * | 2020-08-15 | 2020-11-24 | 武汉华胜工程建设科技有限公司 | Construction engineering project consultation cost management method and system and intelligent terminal |
| CN113657864A (en) * | 2021-08-24 | 2021-11-16 | 深圳市联合创艺建筑设计有限公司 | Management system and management method for consultation cost of construction engineering project |
| CN114387131A (en) * | 2022-01-15 | 2022-04-22 | 中远融通工程咨询有限公司 | Data auditing method and system for engineering cost project |
| CN115034911A (en) * | 2022-07-05 | 2022-09-09 | 广州高新工程顾问有限公司 | BIM-based whole-process cost consultation service method and system |
| CN115187610A (en) * | 2022-09-08 | 2022-10-14 | 中国科学技术大学 | Neuron morphological analysis method and device based on graph neural network and storage medium |
| CN116258504A (en) * | 2023-03-16 | 2023-06-13 | 广州信瑞泰信息科技有限公司 | Bank customer relationship management system and method thereof |
-
2023
- 2023-08-22 CN CN202311059937.1A patent/CN117057743B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107895177A (en) * | 2017-11-17 | 2018-04-10 | 南京邮电大学 | A kind of migration classification learning method for keeping image classification sparsity structure |
| CN111985894A (en) * | 2020-08-15 | 2020-11-24 | 武汉华胜工程建设科技有限公司 | Construction engineering project consultation cost management method and system and intelligent terminal |
| CN113657864A (en) * | 2021-08-24 | 2021-11-16 | 深圳市联合创艺建筑设计有限公司 | Management system and management method for consultation cost of construction engineering project |
| CN114387131A (en) * | 2022-01-15 | 2022-04-22 | 中远融通工程咨询有限公司 | Data auditing method and system for engineering cost project |
| CN115034911A (en) * | 2022-07-05 | 2022-09-09 | 广州高新工程顾问有限公司 | BIM-based whole-process cost consultation service method and system |
| CN115187610A (en) * | 2022-09-08 | 2022-10-14 | 中国科学技术大学 | Neuron morphological analysis method and device based on graph neural network and storage medium |
| CN116258504A (en) * | 2023-03-16 | 2023-06-13 | 广州信瑞泰信息科技有限公司 | Bank customer relationship management system and method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117057743B (en) | 2024-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111652280B (en) | Behavior-based target object data analysis method, device and storage medium | |
| CN110852881B (en) | Risk account identification method and device, electronic equipment and medium | |
| CN112367273B (en) | Flow classification method and device of deep neural network model based on knowledge distillation | |
| WO2023179099A1 (en) | Image detection method and apparatus, and device and readable storage medium | |
| CN107402859A (en) | Software function verification system and verification method thereof | |
| CN117041017B (en) | Intelligent operation and maintenance management method and system for data center | |
| CN114612251A (en) | Risk assessment method, device, equipment and storage medium | |
| CN113761250A (en) | Model training method, merchant classification method and device | |
| CN117237559A (en) | Digital twin city-oriented three-dimensional model data intelligent analysis method and system | |
| CN116206327A (en) | Image classification method based on online knowledge distillation | |
| CN112580616B (en) | Crowd quantity determination method, device, equipment and storage medium | |
| Wang et al. | Deep blind image quality assessment powered by online hard example mining | |
| CN113569048A (en) | Method and system for automatically dividing affiliated industries based on enterprise operation range | |
| CN117078007A (en) | Multi-scale wind control system integrating scale labels and method thereof | |
| CN117574915A (en) | Public data platform based on multiparty data sources and data analysis method thereof | |
| CN117057743B (en) | Building engineering project consultation cost management method and system thereof | |
| CN113781201B (en) | Risk assessment method and device for electronic financial activity | |
| Huang et al. | Spatial‐temporal correlation graph convolutional networks for traffic forecasting | |
| Xu et al. | Recursive multi-relational graph convolutional network for automatic photo selection | |
| Pandkar et al. | 3D Facial Biometric Verification Using a DNA Sample for Law Enforcement Applications | |
| CN117633140B (en) | Urban geological investigation method based on big data cloud computing technology | |
| CN117014382B (en) | Data stream processing system and method based on convergence and distribution equipment | |
| CN115174421B (en) | Network fault prediction method and device based on self-supervision unwrapping hypergraph attention | |
| CN116977021B (en) | Automatic pushing method for system butt joint based on big data | |
| US20230325630A1 (en) | Graph learning-based system with updated vectors |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |