Semantic understanding-based sub-item project cost matching mapping method and system
Through semantic recognition and the construction of tree structure diagrams, the problem of inefficient cost matching of engineering contracts is solved, automated cost matching and visual analysis are realized, and the refinement and real-time nature of project cost management is improved.
Patent Information
- Application Number
- CN202510889310.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-30
- Publication Date
- 2025-07-29
- Estimated Expiration
- 2045-06-30
AI Technical Summary
In the prior art, the cost matching and comparison of engineering contracts relies on manual review, which is inefficient and prone to errors, making it difficult to quickly locate sub-project nodes, and cannot meet the real-time requirements of dynamic engineering management.
Through semantic recognition technology, a tree structure diagram is constructed, and a cost matching model is established to determine the cost and actual cost in real time to realize automated cost matching mapping.
It significantly improves the processing efficiency and accuracy of project contract cost matching, provides accurate cost traceability analysis and visual decision-making basis, and supports project cost control and deviation warning.
Smart Images

Figure CN120386871A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to data processing technologies, and in particular to a method and system for matching and mapping the project cost of sub - items based on semantic understanding. Background Art
[0002] An engineering contract is a legal agreement between the employer (Party A) and the contractor (Party B) in an engineering construction project to complete a specific engineering construction task, clarifying the rights and obligations of both parties. It is the core document in the engineering construction process, running through various stages such as project planning, design, construction, and acceptance.
[0003] During the engineering construction process, the matching and comparison of the actual cost and the calibrated cost in the engineering contract is the core link of cost management. Currently, traditional cost matching and comparison methods mainly rely on manual review of contract texts and cost data, listing numerical differences through tables. This method has obvious deficiencies. On the one hand, engineering contracts often contain a large amount of sub - item engineering information, resulting in low manual processing efficiency and being prone to data omission or comparison deviation due to subjective negligence. On the other hand, two - dimensional tables are difficult to intuitively display the cost correlations between different - level contract nodes. When there are cost differences, it is difficult to quickly locate specific sub - item engineering nodes, unable to meet the real - time requirements of project dynamic management.
[0004] Therefore, there is an urgent need for a method and system for matching and mapping the project cost of sub - items based on semantic understanding that can improve processing efficiency. Summary of the Invention
[0005] Based on the above problems, the present invention is proposed to provide a method and system for matching and mapping the project cost of sub - items based on semantic understanding that can overcome the above problems or at least partially solve the above problems.
[0006] According to one aspect of the present invention, a method for matching and mapping the project cost of sub - items based on semantic understanding is provided, including: Performing semantic recognition on each obtained engineering contract, and dividing the engineering contracts corresponding to the same general project into the same general - item group based on the obtained contract content; Performing hierarchical division on all engineering contracts in the same general - item group to obtain a tree - shaped structure diagram composed of hierarchical nodes corresponding to each engineering contract; Establishing a cost matching model based on each hierarchical node, determining the calibrated cost of the corresponding engineering contract based on the contract content, and updating the cost matching model based on the actual cost of the retrieved corresponding engineering contract and the calibrated cost.
[0007] Optionally, in the method according to the present invention, semantic recognition is performed on each obtained project contract, and based on the obtained contract content, project contracts corresponding to the same general project item are divided into the same general item group, including: Performing character recognition on each project contract based on the OCR recognition technology, and determining the project item composed of the contract characters in response to the contract characters obtained being the same as the project key characters of the corresponding project attributes; Performing duplicate removal processing on all project items included in each project contract, and determining the number of project items corresponding to all project items after the duplicate removal processing; In response to the number of project items corresponding to any project contract being one, establishing a general item group including the project contract; Summarizing all other project contracts except the project contracts located in the general item group into the division determination group, and in response to any project contract located in the division determination group having a contract association relationship with a project contract located in any general item group, dividing the project contract located in the division determination group into the corresponding general item group.
[0008] Optionally, in the method according to the present invention, performing character recognition on each project contract based on the OCR recognition technology, and determining the project paragraph composed of the contract characters in response to the contract characters obtained being the same as the project key characters of the corresponding project attributes, including: Performing character recognition on each project contract based on the OCR recognition technology to determine all contract characters included in each project contract; Retrieving the project key characters corresponding to the project attributes, and in response to any contract character included in any project contract being the same as the project key characters, determining the contract character as the target character; Taking the target character as the starting point, and determining the characters on the left and right sides of the target character respectively; In response to any contract character on the left corresponding to the left angle bracket, determining the contract character as the first marker, and in response to any contract character on the right corresponding to the right angle bracket, determining the contract character as the second marker; Composing all contract characters between the first marker and the second marker into the project items included in the project contract.
[0009] Optionally, in the method according to the present invention, in response to any project contract located in the division determination group having a contract association relationship with a project contract located in any general item group, dividing the project contract located in the division determination group into the corresponding general item group, including: In response to any project contract located in the division determination group having the same project items as a project contract located in any general item group, determining that there is a contract association relationship between the two, and performing shielding processing on the corresponding same project items included in the project contract located in the division determination group; The project contracts that have undergone the shielding process are divided by the division determination group into the general item groups that have the contract association relationship with them, obtaining an updated division determination group and general item groups; Repeat the above steps until there is no project contract in the division determination group.
[0010] Optionally, in the method according to the present invention, all project contracts in the same general item group are hierarchically divided to obtain a tree structure diagram composed of hierarchical nodes corresponding to each project contract, including: Obtain the division order of all project contracts divided into the same general item group, and perform a division sorting from the front to the back on each project contract based on the division order to obtain a division sequence; Based on the division sequence, hierarchically establish hierarchical nodes of each project contract extending downward corresponding to different division orders in sequence, and connect the hierarchical nodes corresponding to the contract association relationship to obtain a tree structure diagram composed of hierarchical nodes corresponding to each project contract.
[0011] Optionally, in the method according to the present invention, a cost matching model is established based on each hierarchical node, the calibrated cost of the corresponding project contract is determined based on the contract content, and the cost matching model is updated based on the actual cost of the corresponding project contract retrieved and the calibrated cost, including: Determine the calibrated cost of the corresponding project contract based on the contract content, and obtain the actual cost of the corresponding project contract; Establish an image coordinate system corresponding to the tree structure diagram, where the image coordinate system includes an X-axis and a Y-axis, and the tree structure diagram is located on the horizontal coordinate plane formed by the X-axis and the Y-axis; Generate a Z-axis connected to the X-axis and the Y-axis respectively in a direction perpendicular to the horizontal coordinate, and determine the vertical coordinate plane formed by the X-axis and the Z-axis; Generate a three-dimensional display space based on the horizontal coordinate plane and the vertical coordinate plane, and generate a cost matching model corresponding to each hierarchical node based on the three-dimensional display space, where the cost matching model includes a first sub-model corresponding to the actual cost and a second sub-model corresponding to the calibrated cost connected to the hierarchical node on both sides of each hierarchical node along the extension direction of the Z-axis; In response to the actual cost corresponding to the same project contract being different from the calibrated cost, update the first sub-model and the second sub-model.
[0012] Optionally, in the method according to the present invention, in response to the actual cost corresponding to the same project contract being different from the calibrated cost, update the first sub-model and the second sub-model, including: Perform character filling for the actual cost and calibrated cost corresponding to the first sub-model and the second sub-model; Determine the cost ratio corresponding to the actual cost and the calibrated cost, determine the smaller of the actual cost and the calibrated cost as the differential cost, and reduce the size of the sub-model corresponding to the differential cost based on the cost ratio; In response to the actual cost being lower than the calibrated cost, perform pixel rendering on the first sub-model corresponding to a preset first pixel value; In response to the actual cost being higher than the calibrated cost, perform pixel rendering on the first sub-model corresponding to a second pixel value different from the first pixel value.
[0013] Optionally, in the method according to the present invention, the method further includes: Send the three-dimensional display space to the user terminal for display, and in response to the user terminal interacting with any hierarchical node, determine the hierarchical node as the display node, and determine each other hierarchical node connected to and below the display node as the collaborative node; Compare all the engineering projects included in the engineering contract corresponding to any display node with all the engineering projects included in the engineering contract corresponding to any collaborative node, and determine the same engineering projects as the display projects based on the comparison result; Based on the horizontal coordinate plane, determine the collaborative coordinate points corresponding to each collaborative node, and obtain the X-axis coordinate values corresponding to each of the collaborative coordinate points; Connect the collaborative coordinate point with the largest X-axis coordinate value and the collaborative coordinate point with the smallest X-axis coordinate value, and establish a display interface corresponding to the display project and parallel to the vertical coordinate plane based on the obtained display baseline.
[0014] Optionally, in the method according to the present invention, establishing a display interface corresponding to the display project and parallel to the vertical coordinate plane based on the obtained display baseline includes: Calculate the difference in X-axis coordinate values for adjacent collaborative coordinate points based on the display baseline, and perform a half-value process on the obtained X-axis difference to obtain a difference half-value; Based on the display baseline, determine the collaborative distribution lines centered on each collaborative coordinate point and corresponding to the difference half-value, and determine the project distribution ratio corresponding to the display project based on the contract content of the engineering contract corresponding to each collaborative node; Using each collaborative distribution line as the starting point, generate project ratio axes corresponding to the project distribution ratio and parallel to the vertical coordinate plane to obtain the display interface.
[0015] According to another aspect of the present invention, there is provided a sub-item project cost matching and mapping system based on semantic understanding, including: A grouping module configured to perform semantic recognition on each obtained project contract and divide the project contracts corresponding to the same general project item into the same general item group based on the obtained contract content; A division module configured to perform hierarchical division on all project contracts in the same general item group to obtain a tree structure diagram composed of hierarchical nodes corresponding to each project contract; A matching module configured to establish a cost matching model based on each hierarchical node, determine the calibrated cost of the corresponding project contract based on the contract content, and update the cost matching model based on the actual cost of the retrieved corresponding project contract and the calibrated cost.
[0016] According to the solution of the present invention, first, the present invention intelligently groups project contracts through semantic recognition technology, and can automatically classify project contracts of the same general project item into the same general item group, avoiding omissions and time-consuming of manual classification, and significantly improving the processing efficiency, especially suitable for complex project scenarios with multiple levels and multiple sub-items; secondly, a tree structure diagram can be constructed based on the obtained general item group to visually present the logical relationship between different project contracts in the form of hierarchical nodes, making the cost association of sub-item projects present a structured tree layout, which is convenient for quickly locating cost nodes at a specific level; finally, the cost matching model established based on hierarchical nodes can real-time associate the calibrated cost and the actual cost in the contract, realize cost traceability analysis from the general item to the sub-item, provide accurate and visual decision-making basis for project cost control and deviation warning, and improve the refinement and real-time of project cost management. Description of the Drawings
[0017] Figure 1 Shows a flowchart of a sub-item project cost matching and mapping method based on semantic understanding according to an embodiment of the present invention; Figure 2 Shows a schematic diagram of the tree structure diagram in this embodiment; Figure 3 Shows a schematic diagram of the first sub-model and the second sub-model in this embodiment; Figure 4 Shows a structural block diagram of a sub-item project cost matching and mapping system based on semantic understanding according to another embodiment of the present invention. Detailed Embodiments
[0018] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.
[0019] To solve the problems existing in the above-mentioned prior art, the inventors proposed the solution of the present invention. An embodiment of the present invention provides a method for matching and mapping the project cost of sub-items based on semantic understanding, which can be executed in a computing device. Herein, the computing device can be understood as a terminal with data processing functions, such as a mobile phone or a computer.
[0020] Figure 1 The flowchart of the method for matching and mapping the project cost of sub-items based on semantic understanding in this embodiment is shown, as Figure 1 shown, the method starts from step S1, and in step S1, the following contents are included: Perform semantic recognition on each obtained project contract, and divide the project contracts corresponding to the same general project item into the same general item group based on the obtained contract content.
[0021] For example, in this embodiment, a project contract can be understood as a corresponding contract signed between Party A and Party B based on a certain project. Herein, the contract content of each project contract should include the project content of the corresponding project and the calibrated cost (i.e., the planned amount required to complete the project content). Since different projects may correspond to the same general project item, for example, a construction project of an amusement park may include different sub-projects such as a camping park and amusement facilities. In this case, the construction project can be regarded as the general project item, and the corresponding sub-projects can be regarded as different project contracts belonging to the general project item. Based on this, in order to define the contract scope included in each general project item, semantic recognition can be performed on each obtained project contract, and based on the recognized contract content, the project contracts corresponding to the same general project item can be divided into the same general item group, which can also facilitate the subsequent unified management and processing of the relevant contracts of the same general project item, and improve the accuracy and efficiency of the subsequent cost matching and comparison involved.
[0022] Furthermore, in this embodiment, the above-mentioned "perform semantic recognition on each obtained project contract, and divide the project contracts corresponding to the same general project item into the same general item group" may further include the following steps: Perform character recognition on each project contract based on the OCR recognition technology, and determine the project composed of the contract characters in response to the contract characters obtained being the same as the key characters of the corresponding project attributes. Deduplicate all project items included in each project contract, and determine the number of project items corresponding to all project items after the deduplication process; In response to the number of items corresponding to any one project contract being one, establish a total item grouping including the said project contract; Summarize all other project contracts except those in the total item grouping into the division determination group, and in response to any project contract in the division determination group having a contract association relationship with a project contract in any total item grouping, divide the project contract in the division determination group into the corresponding total item grouping.
[0023] For example, in this embodiment, dividing project contracts corresponding to the same project total item into the same total item grouping can be specifically achieved through the following method steps: First, character recognition can be performed on each project contract based on OCR recognition technology, and each recognized contract character is compared with the project key characters corresponding to the retrieved project attributes. Here, the project key characters corresponding to the project attributes can be understood as relevant characters used to indicate project items. When it is determined that the two are the same based on the comparison result, it indicates that the corresponding contract character can be used to indicate the project item. Therefore, the project item composed can be determined based on this contract character. It should be noted that since the OCR technology is a mature existing technology, the specific recognition process is not elaborated in this embodiment. It can efficiently extract project-related information from the contract text, reducing the error and workload of manual recognition; Next, since in actual project contracts, the same project item may be cited in different contract clauses, therefore, to ensure the accuracy of counting the number of project items for a project, it is necessary to deduplicate all project items included in each project contract and determine the number of items after deduplication; If the number of project items after deduplication of a certain project contract is one, that is, the project contract only corresponds to one project item, that is, the project contract should correspond to the aforementioned project total item. At this time, a total item grouping including the project contract can be established accordingly; Finally, after completing the determination of different total item groupings, the project contracts that have not entered any total item grouping can be further summarized into the division determination group. When any project contract in the division determination group has a contract association relationship with a project contract corresponding to a certain total item grouping (that is, the two have the same project item, indicating that the two are parent-child contracts), then the project contract can be divided into the corresponding total item grouping, so that the scattered contracts of the same project total item can be gradually collected, ensuring that all relevant contracts are included in the corresponding grouping and avoiding omission.
[0024] Further, in this embodiment, the above "performing character recognition on each engineering contract based on OCR recognition technology, and determining the project paragraph composed of the contract characters in response to the contract characters obtained being the same as the project key characters corresponding to the corresponding project attributes" may further include the following steps: Performing character recognition on each engineering contract based on OCR recognition technology to determine all contract characters included in each engineering contract; Retrieving the project key characters corresponding to the corresponding project attributes, and in response to any contract character included in any engineering contract being the same as the project key characters, determining the contract character as the target character; Taking the target character as the starting point, determining the characters corresponding to the left and right sides of the target character respectively; In response to any contract character on the left corresponding to the left book title mark, determining the contract character as the first marker, and in response to any contract character on the right corresponding to the right book title mark, determining the contract character as the second marker; Combining all the contract characters between the first marker and the second marker to form the engineering project included in the engineering contract.
[0025] For example, in this embodiment, the determination of the project paragraph in each engineering contract can be implemented based on the following specific method steps: First, perform a character recognition operation on each engineering contract using OCR recognition technology to determine all contract characters included in each engineering contract; Secondly, retrieve the project key characters corresponding to the corresponding project attributes, and compare all the contract characters with the project key characters. When it is determined based on the comparison result that there is a contract character in any engineering contract that is the same as the project key characters, the character needs to be determined as the target character. Here, based on the above content, the project key characters corresponding to the corresponding project attributes can be understood as the relevant characters used to indicate the engineering project, such as "project", "engineering", "construction", "planning", etc.; Then, in the corresponding engineering contract, taking the target character as the starting point, characters can be determined to its left and right respectively. It can be explained that since in a regular engineering contract, the project name corresponding to the engineering project is generally included in book title marks (such as "Amusement Park Construction Project"), therefore, among the left characters, if there is a contract character corresponding to the left book title mark, it is determined as the first marker; similarly, among the right characters, if there is a contract character corresponding to the right book title mark, it is determined as the second marker; Finally, all the contract characters between the first identifier and the second identifier can be combined into the engineering projects included in the engineering contract, so as to realize the complete extraction of the project names of specific engineering projects from the contract text. That is, the scope can be defined by matching the project key characters and the book title mark identifier, ensuring the accuracy and integrity of the extraction of engineering projects.
[0026] In addition, in this embodiment, the above "responding to that any engineering contract in the determined division group has a contract association relationship with the engineering contract in any general item group, and dividing the engineering contract in the determined division group into the corresponding general item group" may further include the following steps: Responding to that any engineering contract in the determined division group has the same engineering project as the engineering contract in any general item group, determining that there is a contract association relationship between the two, and performing shielding processing on the corresponding same engineering project included in the engineering contract in the determined division group; Dividing the engineering contract after the shielding processing from the determined division group into the general item group having the contract association relationship with it, to obtain an updated determined division group and general item group; Repeat the above steps until there is no engineering contract in the determined division group.
[0027] For example, in this embodiment, the corresponding grouping of each engineering contract based on the obtained general item group can be realized based on the following method steps: First of all, it can be explained that since different engineering contracts corresponding to the same general engineering item are generally corresponding parent-child contracts, and the engineering contract corresponding to the sub-contract generally quotes the engineering project of the engineering contract corresponding to the parent contract. For example: the engineering contract A corresponding to the parent contract includes the engineering project a, and the corresponding engineering contract B of the sub-contract includes the engineering project a and an additional engineering project b. Based on this, each engineering contract in the determined division group can be compared with the engineering contracts in different general item groups. When any engineering contract in the determined division group has the same engineering project as the engineering contract in a certain general item group, it is determined that there is a contract association relationship between the two (that is, it indicates that the two are parent-child contracts); Meanwhile, in order to determine the division order of each project contract assigned to the general item group based on the corresponding contract association relationship, the same project items included in the project contract in the division determination group can also be masked; here, the masking process can be understood as that the project items included in the project contract in the division determination group cannot be used for comparison with other project contracts, that is, the project item a included in project contract B cannot be used for comparison with other project contracts, and other project contracts can only be compared based on the project item a included in project contract A, or can be compared based on the project item b included in project contract B. Moreover, if project contract C also includes the corresponding project item a, it can be indicated that project contract B and project contract C belong to the sub-contracts of project contract A; Next, the project contracts that have completed the masking process are divided from the division determination group into the corresponding general item groups, thereby obtaining an updated division determination group and general item groups; Subsequently, repeat the above steps until there are no project contracts in the division determination group, ensuring that all contracts are grouped based on the relevance of project items.
[0028] It can be explained that based on the above division method, all project contracts of the same general project can be included in the same general item group, and by masking duplicate items and cyclic division, it is ensured that each project contract can be sequentially assigned to the same general item group according to different contract association relationships.
[0029] In step S2, the following contents are included: Perform hierarchical division on all project contracts in the same general item group to obtain a tree structure diagram composed of hierarchical nodes corresponding to each project contract.
[0030] For example, in this embodiment, after all project contracts are divided into the corresponding general item groups, since all project contracts in the same general item group are established based on the same general project, therefore, in order to determine the different contract association relationships of all project contracts, it is necessary to perform hierarchical division on all project contracts in the same general item group to obtain a tree structure diagram composed of hierarchical nodes corresponding to each project contract. It can be explained that the tree structure diagram can include multiple hierarchical nodes. For the above-mentioned project contract A and project contract B, the hierarchical node corresponding to project contract A should be above the hierarchical node corresponding to project contract B.
[0031] Furthermore, in this embodiment, the above-mentioned "perform hierarchical division on all project contracts in the same general item group to obtain a tree structure diagram composed of hierarchical nodes corresponding to each project contract" can also include the following steps: Obtain the division order of all project contracts divided into the same general item group, and perform a division sorting on each project contract from the front to the back based on the division order to obtain a division sequence; Based on the division sequence, hierarchal nodes corresponding to each project contract with different division orders are sequentially established and extended downward, and the hierarchal nodes with contract association relationships are connected to obtain a tree structure diagram composed of hierarchal nodes corresponding to each project contract.
[0032] For example, in this embodiment, the establishment of the tree structure diagram can be specifically implemented based on the following method steps: First, based on the above content, it can be known that all project contracts divided into the same general item group are divided in sequence based on the corresponding contract association relationships. Therefore, the division order of all project contracts divided into the same general item group can be obtained, and each project contract is sorted from the front to the back according to this division order to form a division sequence, so as to clarify the sequential logical relationship of each project contract within the general item group; Finally, after determining the division sequence, hierarchal nodes corresponding to each project contract with different division orders can be sequentially established and extended downward based on the obtained division sequence, and the hierarchal nodes with contract association relationships are connected. Eventually, a tree structure diagram composed of hierarchal nodes corresponding to each project contract can be formed to visually present the hierarchical subordination relationship and association context between different project contracts based on the tree structure diagram, and the logical relationship and association path of each project contract within the same project general item can be clearly displayed in a hierarchical and graphical manner.
[0033] In the visual cost matching and comparison scenario, this tree structure provides a structured framework for the subsequent establishment of a three-dimensional cost matching model: on the one hand, the ordered arrangement of hierarchal nodes facilitates quickly locating the cost data of a specific contract and its associated contracts; on the other hand, the connection relationship between nodes can intuitively reflect the cost impact path between contracts, enabling the comparative analysis of the calibrated cost and the actual cost to be carried out based on the contract hierarchical relationship, improving the logic and visualization effect of cost matching, and helping users efficiently understand the cost association system in complex project contracts.
[0034] In step S3, the following content is included: Establish a cost matching model based on each hierarchal node, determine the calibrated cost of the corresponding project contract based on the contract content, and update the cost matching model based on the actual cost of the corresponding project contract retrieved and the calibrated cost.
[0035] For example, in this embodiment, after obtaining the corresponding tree structure diagram, since the connections between nodes at different levels can intuitively reflect the cost impact paths between different project contracts, in order to further conduct cost comparison based on the tree structure diagram (including the calibrated cost and the actual cost mentioned above), a cost matching model can be further established based on each level of nodes. It should be noted that this cost matching model is mainly a carrier of the cost matching relationship corresponding to each level of nodes, based on the tree structure nodes formed by hierarchical division of different project contracts within the same general item group; and further, the calibrated cost of the corresponding project contract can be determined based on the contract content of each project contract obtained above. Generally, the calibrated cost is recorded in the corresponding project contract, so it can be determined by traversing the contract content. Similarly, the actual cost can be obtained based on the actual situation of the corresponding project; after obtaining the actual cost and determining the calibrated cost, the cost matching model can be updated based on the two, so as to represent the comparison result of the corresponding cost comparison in a visual form.
[0036] Further, in this embodiment, the above-mentioned "establishing a cost matching model based on each level of nodes, determining the calibrated cost of the corresponding project contract based on the contract content, and updating the cost matching model based on the actual cost and the calibrated cost of the retrieved corresponding project contract" may further include the following steps: Determine the calibrated cost of the corresponding project contract based on the contract content, and obtain the actual cost of the corresponding project contract; Establish an image coordinate system corresponding to the tree structure diagram, where the image coordinate system includes an X-axis and a Y-axis, and the tree structure diagram is located on the horizontal coordinate plane formed by the X-axis and the Y-axis; Generate a Z-axis that is connected to the X-axis and the Y-axis respectively along a direction perpendicular to the horizontal coordinate, and determine the vertical coordinate plane formed by the X-axis and the Z-axis; Generate a three-dimensional display space based on the horizontal coordinate plane and the vertical coordinate plane, and generate a cost matching model corresponding to each level of nodes based on the three-dimensional display space, where the cost matching model includes a first sub-model corresponding to the actual cost and a second sub-model corresponding to the calibrated cost that are connected to the level of nodes on both sides along the extension direction of the Z-axis; In response to the actual cost corresponding to the same project contract being different from the calibrated cost, update the first sub-model and the second sub-model.
[0037] For example, in this embodiment, updating the established cost matching model based on the actual cost and the calibrated cost can be specifically implemented based on the following method steps: First, based on the above, it can be known that the calibrated cost of the corresponding project contract can be determined by traversing the contract content included in the project contract, and at the same time, the actual cost can be obtained based on the actual situation of the corresponding project; Then, a corresponding image coordinate system can be established based on the tree structure diagram. Moreover, the X-axis and Y-axis included in the image coordinate system can form a horizontal coordinate plane correspondingly, and the tree structure diagram is also correspondingly located in this plane to achieve a visual layout based on a two-dimensional perspective; Next, a Z-axis can be generated in a direction perpendicular to the horizontal coordinate plane, and the Z-axis is connected to the X-axis and Y-axis respectively to form a vertical coordinate plane composed of the X-axis and the Z-axis. Thus, a three-dimensional display space can be generated based on the horizontal coordinate plane and the formed vertical coordinate plane, that is, the three-dimensional space dimension is expanded, and further, a cost matching model is generated for each hierarchical node in this three-dimensional display space. It should be noted that each cost matching model includes a first sub-model connecting the corresponding actual cost and a second sub-model connecting the corresponding calibrated cost on both sides of the hierarchical node along the extension direction of the Z-axis. Furthermore, the model association between the cost and each project contract can be constructed based on the cost matching model in the three-dimensional display space; Finally, when there is a difference between the actual cost and the calibrated cost corresponding to the same project contract, the first sub-model and the second sub-model can be updated to ensure that the cost deviation is reflected in real time through the cost matching model. Compared with the traditional visual layout based on a two-dimensional perspective, the cost differences of different hierarchical nodes can be presented more intuitively, facilitating users to quickly locate the problem nodes and supporting users to analyze the cost deviation layer by layer based on the three-dimensional display space, improving the clarity of the analysis logic.
[0038] Furthermore, in this embodiment, the above "responding to the actual cost corresponding to the same project contract being different from the calibrated cost and updating the first sub-model and the second sub-model" may further include the following steps: Perform character filling of the corresponding actual cost and calibrated cost for the first sub-model and the second sub-model; Determine the cost ratio corresponding to the actual cost and the calibrated cost, determine the smaller of the actual cost and the calibrated cost as the differential cost, and reduce the size of the sub-model corresponding to the differential cost based on the cost ratio; Responding to the actual cost being lower than the calibrated cost, perform pixel rendering of the first sub-model corresponding to a preset first pixel value; Responding to the actual cost being higher than the calibrated cost, perform pixel rendering of the first sub-model corresponding to a second pixel value different from the first pixel value.
[0039] For example, in this embodiment, based on the difference between the actual cost and the calibrated cost, the cost matching model is updated. Specifically, it can be implemented based on the following method steps: First, it should be noted that the model sizes, model shapes, and model colors of the first sub-model and the second sub-model should be the same in the initial state. When there is a corresponding cost difference between the actual cost and the calibrated cost, in order to reflect the cost difference based on the first sub-model and the second sub-model, the first sub-model and the second sub-model can be filled with characters corresponding to the actual cost and the calibrated cost to provide a clear numerical basis for cost comparison; Then, the cost ratio of the actual cost to the calibrated cost can be calculated. For example, when the actual cost is 1 million and the calibrated cost is 500,000, the corresponding cost ratio is 2. At this time, the smaller one of the two values can be determined as the differential cost, and the sub-model corresponding to the differential cost can be reduced in size according to the cost ratio. That is, the calibrated cost can be determined as the differential cost, and the second sub-model corresponding to the calibrated cost can be reduced in size based on the cost ratio, that is, the second sub-model can be reduced to half of the size of the corresponding first sub-model, so as to complete the corresponding update of the size of the cost matching model based on cost comparison; Finally, after completing the update of the cost matching model based on the model size, in order to further improve the reflection of the cost difference, the cost matching model can also be updated based on pixel values. Specifically, it includes: if the actual cost is higher than the calibrated cost, the first sub-model is pixel-rendered with a second pixel value different from the first pixel value, and the high and low cost states are visually distinguished through different pixel rendering effects (such as color depth, brightness difference, etc.).
[0040] For example, Figure 2 The schematic diagram of the tree structure diagram in this embodiment is shown. It can be seen that Figure 2 The shown tree structure diagram includes hierarchical nodes corresponding to engineering contract A, engineering contract B, and engineering contract C. And the hierarchical nodes corresponding to engineering contract B and engineering contract C are located at the hierarchical nodes corresponding to engineering contract A; Similarly, Figure 3 The schematic diagrams of the first sub-model and the second sub-model in this embodiment are shown. Among them, both the first sub-model and the second sub-model are established based on engineering contract B, and the size of the corresponding first sub-model is half of the size of the corresponding second sub-model, that is, the actual cost corresponding to engineering contract B is half of the calibrated cost.
[0041] In addition, based on the above content, it can be known that all project contracts in the same general item grouping should have a corresponding parent-child relationship. For example, for the aforementioned Project Contract A, Project Contract B, and Project Contract C, among them, Project Contract B and Project Contract C are both sub-contracts of Project Contract A. That is, Project Contract B and Project Contract C are formed based on a certain project in Project Contract A. It can also be understood that the Party A or Party B corresponding to Project Contract A has carried out further project allocation for a certain project in Project Contract A, thus forming Project Contract B and Project Contract C. For example, in the case of the "Amusement Park Construction Project" in Project Contract A, in order to improve the construction efficiency, the Party A corresponding to Project Contract A allocates this project to the Party B corresponding to Project Contract B and the Party B corresponding to Project Contract C according to a corresponding ratio. In this case, in order to form a display based on the project allocation, in this embodiment, the following steps may also be included: Send the three-dimensional display space to the user terminal for display, and in response to the interaction of the user terminal with any hierarchical node, determine this hierarchical node as the display node, and determine each other hierarchical node connected to and below the display node as the collaborative node; Compare all the projects included in the project contract corresponding to any display node with all the projects included in the project contract corresponding to any collaborative node, and based on the comparison result, determine the same projects as the display projects; Based on the horizontal coordinate plane, determine the collaborative coordinate points corresponding to each collaborative node, and obtain the X-axis coordinate values corresponding to each of the collaborative coordinate points; Connect the collaborative coordinate point with the largest X-axis coordinate value and the collaborative coordinate point with the smallest X-axis coordinate value in terms of coordinates, and based on the obtained display baseline, establish a display interface corresponding to the display project and parallel to the vertical coordinate plane.
[0042] For example, in this embodiment, the collaborative display of the project can be specifically implemented based on the following method steps: First, after forming the corresponding three-dimensional display space, the three-dimensional display space (constituted by the horizontal coordinate plane and the vertical coordinate plane, including the tree structure diagram and the cost matching model of each hierarchical node) can be further sent to the user terminal for visual display. Here, the user terminal can be understood as the terminal used by the Party A corresponding to the general project item, such as a mobile phone or a computer; Then, in response to the interaction operation of the user terminal on any hierarchical node (for example, it can be specifically a click or selection), this node can be determined as the display node, and all hierarchical nodes connected to and below the display node can be determined as the collaborative nodes, realizing the user's need to focus on a specific contract level; Next, in order to perform corresponding allocation display based on the display nodes, all the engineering projects of the engineering contracts corresponding to the display nodes can be compared item by item with all the engineering projects of the engineering contracts corresponding to each collaboration node, and the same engineering projects can be screened out according to the comparison results and determined as display projects, so as to determine the co-existing engineering projects for subsequent processing; Subsequently, based on the horizontal coordinate plane, determine the collaboration coordinate points corresponding to each collaboration node, and obtain the X-axis coordinate values corresponding to each collaboration coordinate point, so as to position each collaboration node accordingly; Finally, after obtaining all the X-axis coordinate values, the display baseline can be formed by connecting the two collaboration coordinate points with the largest and smallest X-axis coordinate values, and a display interface parallel to the vertical coordinate plane can be established based on this display baseline, so that the display projects can be allocated and displayed from a corresponding two-dimensional perspective based on the display interface; here, it can be explained that the display baseline can be understood as the edge contour line forming the display interface.
[0043] Furthermore, in this embodiment, the above-mentioned "establishing a display interface corresponding to the display project and parallel to the vertical coordinate plane based on the obtained display baseline" may further include the following steps: Calculate the difference in X-axis coordinate values for the collaboration coordinate points adjacent to each other based on the display baseline, and perform a half-value processing on the obtained X-axis difference to obtain the difference half-value; Based on the display baseline, determine the collaboration allocation lines centered on each collaboration coordinate point and corresponding to the difference half-value, and determine the project allocation ratio corresponding to the display project based on the contract content of the engineering contract corresponding to each collaboration node; Taking each collaboration allocation line as the starting point, generate a project ratio axis corresponding to the project allocation ratio and parallel to the vertical coordinate plane to obtain the display interface.
[0044] For example, in this embodiment, the formation of the display interface can be specifically implemented based on the following method steps: First, after obtaining each collaboration coordinate point, calculate the difference in X-axis coordinate values for two adjacent collaboration coordinate points based on the display baseline, and then perform a half-value processing on the obtained X-axis difference to obtain the difference half-value. For example, when there are collaboration coordinate point M(1, 2), collaboration coordinate point N(2, 2), and collaboration coordinate point O(3, 2), then it is necessary to calculate the difference between collaboration coordinate point M and collaboration coordinate point N, and the difference between collaboration coordinate point N and collaboration coordinate point O, and perform a half-value processing on the obtained X-axis difference to obtain the difference half-value, which is 0.5; Then, with the display baseline as a reference, determine the collaborative allocation lines centered on each collaborative coordinate point with a length equal to half of the difference value. At the same time, it is also possible to traverse the contract content of the project contracts corresponding to each determined collaborative node to determine the project allocation ratio of the display project corresponding to each collaborative node. For example, in the engineering project of "Amusement Park Construction Project" in Engineering Contract A, by traversing the contract content of Engineering Contract B and Engineering Contract C respectively, it can be determined that the project allocation ratio of Engineering Contract B is 60%, while the project allocation ratio of Engineering Contract C is 40%. Finally, taking each collaborative allocation line as the starting point, generate the project ratio axis corresponding to the project allocation ratio in the direction parallel to the vertical coordinate plane. Furthermore, the numerical size of the allocation ratio can be visually mapped through the length of the project ratio axis. Finally, all the project ratio axes together form a display interface to visually display the project allocation ratio of any engineering project based on the three-dimensional display space according to the needs of the user terminal, and realize the fusion display of multi-data information, improving the data acquisition efficiency.
[0045] In summary, first, in this embodiment, the engineering contracts are intelligently grouped through semantic recognition technology, and the engineering contracts of the same general engineering item can be automatically classified into the same general item group, avoiding the omissions and time-consuming of manual classification and significantly improving the contract processing efficiency, especially suitable for complex engineering scenarios with multiple levels and sub-items; second, a tree structure diagram can be constructed based on the obtained general item group to visually present the logical relationship between different engineering contracts in the form of hierarchical nodes, making the cost correlation of the sub-projects present a structured tree layout, which is convenient for quickly locating the cost nodes at a specific level; finally, based on the cost matching model established by the hierarchical nodes, the calibrated cost and the actual cost in the contract can be associated in real time to realize the cost traceability analysis from the general item to the sub-item, providing accurate and visual decision-making basis for project cost control and deviation warning, and improving the refinement and real-time of project cost management.
[0046] Another embodiment of the present invention provides a sub-project cost matching and mapping system based on semantic understanding, Figure 4 and its corresponding structural block diagram. The system includes: A grouping module, configured to perform semantic recognition on each obtained engineering contract and divide the engineering contracts corresponding to the same general engineering item into the same general item group based on the obtained contract content; A division module, configured to perform hierarchical division on all the engineering contracts in the same general item group to obtain a tree structure diagram composed of hierarchical nodes corresponding to each engineering contract; A matching module, configured to establish a cost matching model based on nodes at each level, determine the calibrated cost of a corresponding project contract based on the contract content, and update the cost matching model based on the actual cost of the corresponding project contract retrieved and the calibrated cost.
[0047] In the specification provided herein, the algorithms and displays are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems may also be used in conjunction with the examples of the present invention. The structure required to construct such a system will be apparent from the above description. Additionally, the present invention is not directed to any particular programming language. It should be understood that the content of the present invention described herein can be implemented using various programming languages, and the description of a particular language above is for the purpose of disclosing the preferred embodiments of the present invention.
[0048] In the specification provided herein, a large number of specific details are set forth. However, it is understood that embodiments of the present invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.
[0049] Similarly, it should be understood that, in order to streamline the present disclosure and assist in understanding one or more of the various inventive aspects, in the foregoing description of the exemplary embodiments of the present invention, the various features of the present invention are sometimes grouped together in a single embodiment, figure, or description thereof.
[0050] Those skilled in the art should understand that the modules or units or components of the devices in the examples disclosed herein may be arranged in the devices as described in this embodiment, or alternatively may be located in one or more devices different from the devices in this example. The modules in the foregoing examples may be combined into one module or may be further divided into multiple sub-modules.
[0051] Those skilled in the art can understand that the modules in the devices in the embodiments can be adaptively changed and arranged in one or more devices different from this embodiment. The modules or units or components in the embodiments can be combined into one module or unit or component, and furthermore can be divided into multiple sub-modules or sub-units or sub-components.
[0052] In addition, those skilled in the art will be able to understand that, although some of the embodiments described herein include certain features included in other embodiments but not other features, the combination of the features of different embodiments is meant to be within the scope of the present invention and forms different embodiments.
[0053] In addition, some of the embodiments described herein are described as a method or a combination of method elements that can be implemented by a processor of a computer system or by other devices performing the functions. Therefore, a processor having the necessary instructions for implementing the method or method elements forms a device for implementing the method or method elements. In addition, the elements described herein in the device embodiments are examples of the following devices: the device is used to implement the functions performed by the elements for the purpose of implementing the invention.
[0054] As used herein, unless otherwise specified, the use of ordinal numbers "first", "second", "third", etc. to describe ordinary objects only represents different instances of similar objects, and is not intended to imply that the objects so described must have a given order in terms of time, space, sorting, or in any other way.
[0055] Although the present invention has been described in terms of a limited number of embodiments, those skilled in the art in this technical field will appreciate that other embodiments can be envisioned within the scope of the present invention as thus described. In addition, it should be noted that the language used in this specification is mainly selected for readability and teaching purposes, rather than for the purpose of explaining or limiting the subject matter of the present invention.
Claims
1. A method for matching and mapping the project cost of sub - items based on semantic understanding, characterized in that including: Performing semantic recognition on each obtained project contract, and dividing the project contracts corresponding to the same general project item into the same general item group based on the obtained contract content; Performing hierarchical division on all project contracts in the same general item group to obtain a tree structure diagram composed of hierarchical nodes corresponding to each project contract; Establishing a cost matching model based on each hierarchical node, determining the calibrated cost of the corresponding project contract based on the contract content, and updating the cost matching model based on the actual cost of the corresponding project contract retrieved and the calibrated cost.
2. The sub-item project cost matching and mapping method based on semantic understanding according to claim 1, wherein Performing semantic recognition on each obtained project contract, and dividing the project contracts corresponding to the same general project item into the same general item group based on the obtained contract content, including: Performing character recognition on each project contract based on OCR recognition technology, and determining the project composed of the contract characters in response to the contract characters obtained being the same as the project key characters of the corresponding project attributes; Performing duplicate removal processing on all project items included in each project contract, and determining the number of project items corresponding to all project items after the duplicate removal processing; In response to the number of project items corresponding to any one project contract being one, establishing a general item group including the project contract; Summarizing all other project contracts except those in the general item group into a division determination group, and in response to any project contract in the division determination group having a contract association relationship with a project contract in any general item group, dividing the project contract in the division determination group into the corresponding general item group.
3. The sub-item project cost matching and mapping method based on semantic understanding according to claim 2, wherein Performing character recognition on each project contract based on OCR recognition technology, and determining the project paragraph composed of the contract characters in response to the contract characters obtained being the same as the project key characters of the corresponding project attributes, including: Performing character recognition on each project contract based on OCR recognition technology to determine all contract characters included in each project contract; Retrieving the project key characters corresponding to the project attributes, and in response to any contract character included in any project contract being the same as the project key character, determining the contract character as the target character; Taking the target character as the starting point, and determining the characters on the left and right sides of the target character respectively; In response to any contract character on the left corresponding to the left angle bracket, determining the contract character as the first marker, and in response to any contract character on the right corresponding to the right angle bracket, determining the contract character as the second marker; Composing all contract characters between the first marker and the second marker into the project items included in the project contract.
4. The sub-item project cost matching and mapping method based on semantic understanding according to claim 2, wherein In response to any project contract in the division determination group having a contract association relationship with a project contract in any general item group, dividing the project contract in the division determination group into the corresponding general item group, including: If an engineering contract in the division-determined group has the same engineering project as an engineering contract in any general item group, it is determined that there is a contractual association between the two, and the corresponding identical engineering projects included in the engineering contract in the division-determined group are masked; The engineering contract after the masking process is divided from the division-determined group to the general item group having the contractual association with it to obtain an updated division-determined group and general item group; Repeat the above steps until there is no engineering contract in the division-determined group.
5. The method for matching and mapping the cost of sub-items of a project based on semantic understanding according to claim 4, characterized in that All engineering contracts in the same general item group are hierarchically divided to obtain a tree structure diagram composed of hierarchical nodes corresponding to each engineering contract, including: Obtain the division order of all engineering contracts divided into the same general item group, and perform a division sorting on each engineering contract from first to last based on the division order to obtain a division sequence; Based on the division sequence, hierarchically nodes corresponding to each engineering contract extending downward in sequence are established, and the hierarchically nodes having a contractual association are connected to obtain a tree structure diagram composed of hierarchically nodes corresponding to each engineering contract.
6. The method for matching and mapping the cost of sub-items of a project based on semantic understanding according to claim 5, characterized in that A cost matching model is established based on each hierarchical node, the calibrated cost of the corresponding engineering contract is determined based on the contract content, and the cost matching model is updated based on the actual cost of the corresponding engineering contract retrieved and the calibrated cost, including: Determine the calibrated cost of the corresponding engineering contract based on the contract content, and obtain the actual cost of the corresponding engineering contract; An image coordinate system corresponding to the tree structure diagram is established, wherein the image coordinate system includes an X-axis and a Y-axis, and the tree structure diagram is located on the horizontal coordinate plane formed by the X-axis and the Y-axis; A Z-axis connected to the X-axis and the Y-axis respectively is generated in a direction perpendicular to the horizontal coordinate, and a vertical coordinate plane formed by the X-axis and the Z-axis is determined; A three-dimensional display space is generated based on the horizontal coordinate plane and the vertical coordinate plane, and a cost matching model corresponding to each hierarchical node is generated based on the three-dimensional display space, wherein the cost matching model includes a first sub-model corresponding to the actual cost and a second sub-model corresponding to the calibrated cost connected to the hierarchical node on both sides of each hierarchical node along the extension direction of the Z-axis; In response to the actual cost corresponding to the same engineering contract being different from the calibrated cost, the first sub-model and the second sub-model are updated.
7. The method for matching and mapping the cost of sub-items of a project based on semantic understanding according to claim 6, characterized in that In response to the actual cost corresponding to the same engineering contract being different from the calibrated cost, the first sub-model and the second sub-model are updated, including: Perform character filling of the actual cost and the calibrated cost on the first sub-model and the second sub-model; Determine the cost ratio corresponding to the actual cost and the calibrated cost, determine the smaller of the actual cost and the calibrated cost as the differential cost, and reduce the size of the sub-model corresponding to the differential cost based on the cost ratio; In response to the actual cost being lower than the calibrated cost, perform pixel rendering on the first sub-model corresponding to a preset first pixel value; In response to the actual cost being higher than the calibrated cost, perform pixel rendering on the first sub-model corresponding to a second pixel value different from the first pixel value.
8. The method for matching and mapping the cost of sub-items of a project based on semantic understanding according to claim 7, wherein: The method further includes: Send the three-dimensional display space to the user terminal for display, and in response to the user terminal interacting with any hierarchical node, determine the hierarchical node as the display node, and determine each other hierarchical node connected to and below the display node as the collaborative node; Compare all the engineering projects included in the engineering contract corresponding to any display node with all the engineering projects included in the engineering contract corresponding to any collaborative node, and determine the same engineering projects as the display projects based on the comparison result; Based on the horizontal coordinate plane, determine the collaborative coordinate points corresponding to each collaborative node, and obtain the X-axis coordinate values corresponding to each of the collaborative coordinate points; Connect the collaborative coordinate point with the largest X-axis coordinate value and the collaborative coordinate point with the smallest X-axis coordinate value, and establish a display interface corresponding to the display project and parallel to the vertical coordinate plane based on the obtained display baseline.
9. The method for matching and mapping the cost of sub-items of a project based on semantic understanding according to claim 8, wherein: Establishing a display interface corresponding to the display project and parallel to the vertical coordinate plane based on the obtained display baseline includes: Calculate the difference in X-axis coordinate values for adjacent collaborative coordinate points based on the display baseline, and perform a half-value process on the obtained X-axis difference to obtain the difference half-value; Based on the display baseline, determine the collaborative distribution lines centered on each collaborative coordinate point and corresponding to the difference half-value, and determine the project distribution ratio corresponding to the display project based on the contract content of the engineering contract corresponding to each collaborative node; Using each collaborative distribution line as a starting point, generate a project ratio axis corresponding to the project distribution ratio and parallel to the vertical coordinate plane to obtain the display interface.
10. A sub - item project cost matching and mapping system based on semantic understanding, characterized in that, Includes: A grouping module configured to perform semantic recognition on each obtained engineering contract, and divide the engineering contracts corresponding to the same general engineering item into the same general item group based on the obtained contract content; A division module configured to perform hierarchical division on all the engineering contracts in the same general item group to obtain a tree structure diagram composed of hierarchical nodes corresponding to each engineering contract; A matching module configured to establish a cost matching model based on each hierarchical node, determine the calibrated cost corresponding to the engineering contract based on the contract content, and update the cost matching model based on the actual cost of the retrieved engineering contract and the calibrated cost.
Citation Information
Patent Citations
Project cost index generation and use method, device and equipment
CN119026809A
Building engineering cost data analysis and management system and method
CN119721949A
Real-time continuous realignment of a large-scale distributed project
US20160132828A1