Building cost calculation method and device, equipment, storage medium and product

Abstract

The invention discloses a building cost calculation method and device, equipment, a storage medium and a product, and relates to the technical field of engineering cost, and the building cost calculation method comprises the steps: obtaining a building project file, carrying out the component analysis of the building project file, and obtaining a component object, the component object comprises geometric data, attribute data and relational data; inputting the component object into a preset multi-modal recognition model to perform multi-modal feature extraction to obtain target features, fusing the target features to obtain fused comprehensive features, and performing classification based on the comprehensive features to obtain a component recognition result, the component identification result comprises a component type, a construction process, a structural feature and a material type, and the target feature comprises a geometric feature, a semantic feature and a context feature; and based on the component identification result, performing quota matching, and based on the corresponding quota category, performing building cost calculation. And the working efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of engineering cost technology, and in particular to a method, apparatus, equipment, storage medium and product for calculating construction costs. Background Technology

[0002] In modern construction engineering, especially in the cost management of large and complex projects (such as super high-rise buildings and large complexes), accurately identifying the type, material, construction process, and structural characteristics of components is a prerequisite for achieving refined pricing. In related technologies, cost estimation work typically relies on manual review of drawings, BIM models, or bills of quantities, combined with experience-based application of quota items, which reduces work efficiency. Summary of the Invention

[0003] The main purpose of this application is to provide a method, device, equipment, storage medium and product for calculating construction costs, which aims to solve the technical problem that manual review of drawings, BIM models or bills of quantities, and application of quota items based on experience reduces work efficiency.

[0004] To achieve the above objectives, this application proposes a method for calculating construction costs, the method comprising: Obtain the building project file, parse the building project file into components to obtain component objects, wherein the component objects include geometric data, attribute data and relation data; The component object is input into a preset multimodal recognition model for multimodal feature extraction to obtain target features. The target features are then fused to obtain fused comprehensive features. Based on the comprehensive features, the component is classified to obtain the component recognition result. The component recognition result includes component type, construction process and structural features, and material type. The target features include geometric features, semantic features, and contextual features. Based on the component identification results, quota matching is performed, and based on the corresponding quota category, the construction cost is calculated.

[0005] In one embodiment, the steps of matching quotas based on the component identification results and calculating construction costs based on the corresponding quota categories include: Based on the structural features, determine whether the building height is greater than the height threshold; If the height is greater than the building height, then the construction zones will be divided based on the building height. Based on the component identification results, semantic query intents corresponding to different construction sections are generated respectively; In the preset structured quota knowledge graph, retrieve the initial quota categories corresponding to the semantic query intents respectively; Based on preset project constraints, the initial quota categories are filtered to obtain a preset number of quota categories; Based on the geometric data, the quantities of work are calculated, and based on the quantities of work and the quota categories, the construction cost is calculated.

[0006] In one embodiment, the step of retrieving the initial quota category corresponding to the semantic query intent from a preset structured quota knowledge graph includes: Obtain the quota specification document, perform text recognition on the quota specification document, and obtain a digital copy; Based on the digital copy, the structured information corresponding to each quota category is parsed, wherein the structured information includes the quota category, material, construction type, region and technical specifications; Each quota category is treated as a category node, and based on the structured information, the associated concept node of the quota category is determined. Establish semantic relationship edges between the category nodes and the concept nodes, wherein the semantic relationship edges include data attributes; An initial knowledge graph is constructed based on the category nodes, concept nodes, and semantic relationship edges; The initial knowledge graph is augmented to obtain an augmented structured quota knowledge graph.

[0007] In one embodiment, the step of performing knowledge enhancement on the initial knowledge graph to obtain an enhanced structured quota knowledge graph includes: Obtain quota data from different versions of the same region; Perform semantic similarity comparison on text descriptions with the same quota number in the quota data; If the semantic similarity is greater than the threshold, then establish candidate relationships between different versions of quota categories; Based on the candidate relationships, the initial knowledge graph is augmented to obtain an augmented structured quota knowledge graph.

[0008] In one embodiment, the step of generating the semantic query intent corresponding to different construction sections based on the component identification result includes: Traverse the center point coordinates of each component in the component identification results and assign the component to the corresponding construction section; Based on the comprehensive features corresponding to each component in the construction section, the section features are aggregated to obtain the target comprehensive feature vector; Based on the target comprehensive feature vector, the semantic query intent corresponding to different construction sections is generated.

[0009] In one embodiment, the steps of calculating the quantity of work based on the geometric data, and calculating the construction cost based on the quantity of work and the quota category, include: Based on the material type of each component in the construction section, calculate the pumping surcharge corresponding to different construction sections; Based on the geometric data, the quantities of work are calculated, and based on the quantities of work, the quota categories, and the pumping surcharge, the construction cost is calculated.

[0010] Furthermore, to achieve the above objectives, this application also proposes a construction cost calculation device, which includes: The acquisition module is used to acquire building project files, parse the building project files into components, and obtain component objects, wherein the component objects include geometric data, attribute data, and relational data; The classification module is used to input the component object into a preset multimodal recognition model for multimodal feature extraction to obtain target features, fuse the target features to obtain fused comprehensive features, classify based on the comprehensive features, and obtain component recognition results. The component recognition results include component type, construction process and structural features, and material type. The target features include geometric features, semantic features, and contextual features. The matching module is used to perform quota matching based on the component identification results and to calculate the construction cost based on the corresponding quota category.

[0011] In addition, to achieve the above objectives, this application also proposes a construction cost calculation device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the construction cost calculation method described above.

[0012] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the construction cost calculation method described above.

[0013] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the construction cost calculation method described above.

[0014] One or more technical solutions proposed in this application have at least the following technical effects: In related technologies, cost estimation work typically relies on manual review of drawings, BIM models, or bills of quantities, combined with experience to apply quota items, which reduces work efficiency. This application obtains building project documents, parses the building project documents into components to obtain component objects, wherein the component objects include geometric data, attribute data, and relational data; inputs the component objects into a preset multimodal recognition model for multimodal feature extraction to obtain target features, fuses the target features to obtain fused comprehensive features, classifies based on the comprehensive features to obtain component identification results, wherein the component identification results include component type, construction technology and structural features, and material type, and the target features include geometric features, semantic features, and contextual features; based on the component identification results, quota matching is performed, and based on the corresponding quota category, building cost is calculated. After obtaining the building project documents, this application will automatically parse the building project documents to obtain the component objects, and automatically input the component objects into the preset multimodal recognition model to obtain the component recognition results. Based on the component recognition results, the corresponding quota category will be automatically matched to realize the building cost calculation. There is no need to manually look up the drawings, BIM model or bill of quantities, and combine experience to apply the quota sub-items, which improves work efficiency. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating the first embodiment of the construction cost calculation method of this application. Figure 2 This is a flowchart illustrating the second embodiment of the construction cost calculation method of this application. Figure 3 This is a schematic diagram of the module structure of the building cost calculation device according to an embodiment of this application; Figure 4 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the construction cost calculation method in this application embodiment.

[0018] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0019] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0020] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0021] The main solution of this application embodiment is as follows: Obtain a building project file; parse the building project file into components to obtain component objects, wherein the component objects include geometric data, attribute data, and relational data; input the component objects into a preset multimodal recognition model for multimodal feature extraction to obtain target features; fuse the target features to obtain fused comprehensive features; classify based on the comprehensive features to obtain component recognition results, wherein the component recognition results include component type, construction technology and structural features, and material type; the target features include geometric features, semantic features, and contextual features; based on the component recognition results, perform quota matching; and calculate the building cost based on the corresponding quota category.

[0022] In related technologies, cost estimation work usually relies on manual review of drawings, BIM models, or bills of quantities, combined with experience to apply quota items, which reduces work efficiency.

[0023] After obtaining the building project documents, this application will automatically parse the building project documents to obtain the component objects, and automatically input the component objects into the preset multimodal recognition model to obtain the component recognition results. Based on the component recognition results, the corresponding quota category will be automatically matched to realize the building cost calculation. There is no need to manually look up the drawings, BIM model or bill of quantities, and combine experience to apply the quota sub-items, which improves work efficiency.

[0024] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or construction cost calculation device capable of performing the above functions. The following description uses a construction cost calculation device as an example to illustrate this embodiment and the subsequent embodiments.

[0025] Based on this, the embodiments of this application provide a method for calculating building costs, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the construction cost calculation method of this application.

[0026] In this embodiment, the construction cost calculation method includes steps S10 to S30: Step S10: Obtain the building project file, parse the building project file into components to obtain component objects, wherein the component objects include geometric data, attribute data and relation data; It should be noted that the execution entity in this embodiment is a building cost calculation device. Building project files refer to multimodal engineering data containing at least one of the following: building information model files, 3D point cloud data, construction drawings, or design specification documents. Component objects refer to objects that digitally describe each physical component (such as beams, slabs, columns, and walls) in a building. Their geometric data includes the component's dimensions, shape, and spatial location; attribute data includes material type, strength grade, and construction process information; and relational data includes the hierarchical relationships, connection relationships, and the construction section to which they belong. The building cost calculation device, through multimodal fusion component analysis technology, uniformly transforms engineering information from different sources and with different structures into structured component objects. This provides an accurate and complete data foundation for subsequent quantity extraction, quota matching, and cost calculation, overcoming the information loss and error problems caused by scattered data and inconsistent formats in traditional cost calculations.

[0027] Step S20: Input the component object into a preset multimodal recognition model to extract multimodal features and obtain target features. Fuse the target features to obtain fused comprehensive features. Classify based on the comprehensive features to obtain component recognition results. The component recognition results include component type, construction process and structural features, and material type. The target features include geometric features, semantic features, and contextual features. Understandably, the multimodal recognition model is a deep learning framework integrating point cloud processing networks, natural language processing models, and cross-modal attention mechanisms to process component information from different data sources in parallel. Geometric features in the target features refer to quantitative descriptive vectors such as shape, size, and curvature extracted from component point clouds or BIM geometry; semantic features refer to encoded text vectors of keywords, process descriptions, and material specifications extracted from design specifications or component attributes; contextual features refer to vectors reflecting the component's spatial location (e.g., floor, area), its connection to other components, and its associated construction section within the overall building. The building cost calculation device uses the cross-modal attention mechanism to weighted align and complement the above heterogeneous features, obtaining a comprehensive feature representation. Based on this comprehensive feature, it classifies components into predefined categories and predicts their construction process, structural characteristics, and material type.

[0028] For example, in the BIM model of a super high-rise building, the system inputs a component object labeled "structural wall" into the multimodal recognition model. The model extracts geometric features such as "arc shape and gradual thickness change" from its point cloud data, semantic features such as "double-layer steel plate concrete composite shear wall" from the associated design specifications, and contextual features such as "located in the core tube, height range of 150-160 meters, and belonging to the strengthening layer" from its spatial attributes. After cross-modal attention fusion, the model accurately classifies and identifies it as: component type "shear wall", construction process "composite structure cast-in-place", and structural feature "height range distribution". This refined recognition result enables the system to accurately match specific quota items such as "arc-shaped steel plate concrete wall", rather than general wall quotas.

[0029] Step S30: Based on the component identification results, perform quota matching, and calculate the construction cost based on the corresponding quota category.

[0030] It should be noted that quota categories refer to standardized pricing items in the quota knowledge graph, which include consumption standards and calculation rules. The construction cost calculation device takes the component identification results as input, queries the preset quota knowledge graph, automatically finds the corresponding quota category, and automatically calculates various costs such as sub-item project costs, measure project costs, regulatory fees, and taxes based on the matched quota category and the latest labor, material, and machinery unit prices obtained from the dynamic price interface, and then summarizes and generates the total project cost.

[0031] In one feasible implementation, step S30 includes: Based on the structural features, determine whether the building height is greater than the height threshold; Understandably, the structural features of the building cost calculation device here refer to the overall attributes related to the vertical dimension of the building extracted from the BIM model or component identification results. These include the building's total height, the type of main structural system (such as frame-core tube, mega-bracing, etc.), and the division information of different height sections. Height thresholds refer to the critical height values ​​pre-set according to national or local engineering cost standards to trigger the calculation of specific height-related costs or adjustments to construction measures. Examples include 60 meters (often used as the starting point for concrete pumping surcharges), 100 meters, or 300 meters (used to distinguish the level of super high-rise buildings). By automatically determining whether the building height exceeds the key thresholds, the building cost calculation device achieves intelligent triggering and accurate calculation of height-sensitive costs such as additional costs for super high-rise construction and vertical transportation measures. This avoids omissions or delays in manual judgment and ensures the consistency between cost calculations and actual construction.

[0032] If the height is greater than the building height, then the construction zones will be divided based on the building height. It should be noted that a construction section refers to a logical segment into which the entire building is divided vertically based on its total height, structural system change points (such as the location of reinforcement layers and refuge floors), and preset vertical division rules (such as every 60 meters or a specific number of floors). Components within each section have similar construction conditions, resource consumption characteristics, and cost calculation rules. The construction cost calculation device, based on the building height, structural characteristics, and a built-in rule library, automatically executes an analysis process including threshold judgment, fuzzy matching, and logical combination through a rule engine to determine the construction section category of each floor or component. This refined vertical segmentation based on building height allows for differentiated cost calculations considering the varying construction difficulty, measure inputs, and resource efficiency of sections at different heights. This provides a structured framework for calculating complex costs such as precise additional costs for ultra-high-rise construction and phased pricing of large machinery, significantly improving the rationality and accuracy of cost estimation for ultra-high-rise or complex structure projects.

[0033] Based on the component identification results, semantic query intents corresponding to different construction sections are generated respectively; Understandably, the construction cost calculation device dynamically combines the component identification results with the construction section attributes to generate highly targeted and context-aware query intents. This allows the quota matching process to fully consider the impact of construction environment differences on costs and processes, thereby achieving a leap from "component-level" to "section-based" intelligent cost calculation. This solves the problem of crude pricing caused by traditional methods that ignore construction stages and spatial differences.

[0034] In the preset structured quota knowledge graph, retrieve the initial quota categories corresponding to the semantic query intents respectively; It should be noted that the pre-defined structured quota knowledge graph refers to a knowledge base that stores, organizes, and manages engineering pricing rules in the form of a graph database, where nodes represent entities such as quota sub-items, materials, and processes. The construction cost calculation device receives semantic query intent as input and uses graph traversal algorithms, graph embedding vector similarity calculations, or rule-based reasoning engines to search for the initial quota category most relevant to the query intent in the graph database. This significantly improves the coverage breadth and initial efficiency of quota matching, laying the foundation for subsequent accurate matching.

[0035] Based on preset project constraints, the initial quota categories are filtered to obtain a preset number of quota categories; Understandably, the preset project constraints refer to the set of restrictive rules or conditions strongly related to the specific engineering project, loaded by the system during the project initialization phase. These include, but are not limited to, the quota version and regional adjustment coefficient of the project location, the specific time of project commencement or budget preparation (used to determine the price base period), special pricing requirements stipulated in the bidding documents or contract, the permitted range of construction techniques in the current construction phase, and the reasonable fluctuation range of material market prices. The construction cost calculation device compares and verifies the initial quota categories one by one with the above project constraints, eliminates categories that do not meet all constraints, and sorts the remaining categories according to the matching degree score, ultimately retaining the preset number (e.g., 3) of the most matching quota categories.

[0036] Based on the geometric data, the quantities of work are calculated, and based on the quantities of work and the quota categories, the construction cost is calculated.

[0037] It should be noted that the construction cost calculation device, based on the geometric data of the component objects (such as length, area, volume, and number of points), strictly follows the current national or local engineering quantity calculation standards. It automatically performs calculations including geometric parameter analysis, merging of similar components, and deductions between entities (such as the intersection of beams, slabs, and columns). Finally, it generates the quantities of various components in standard units of measurement (such as cubic meters, square meters, and tons). The calculated quantity of each component is multiplied by the "comprehensive unit price" of labor, materials, and machinery under the matched quota category after adjustment by the dynamic price interface to calculate the "total price" of the component. Then, it is summarized level by level according to the categories of sub-items, measures, and other items, and the regulatory fees and taxes are calculated according to the rules to finally generate the total cost of the project.

[0038] In one feasible implementation, prior to the step of retrieving the initial quota category corresponding to the semantic query intent from a preset structured quota knowledge graph, the following steps are included: Obtain the quota specification document, perform text recognition on the quota specification document, and obtain a digital copy; Understandably, quota regulations refer to pricing standard documents issued by government cost management departments or authoritative industry organizations, existing in paper or electronic image form. These documents contain quota items, quantity calculation rules, cost structure, adjustment coefficients, and explanations. Construction cost calculation devices utilize optical character recognition technology to automatically recognize and convert printed text in images or scanned copies of quota regulations, transforming them into computer-readable and editable digital copies.

[0039] Based on the digital copy, the structured information corresponding to each quota category is parsed, wherein the structured information includes the quota category, material, construction type, region and technical specifications; It should be noted that, here, "quota category" specifically refers to a pricing item unit with a unique code formed after parsing; "material quota item" refers to the specific name, specification, and unit of measurement of resource consumption items such as labor, materials, and machinery included in the material quota item; "construction type" refers to the type of building component or engineering part to which the quota item applies; "region" refers to the administrative region or economic zone to which the quota item applies; and "technical specification quota item" refers to the construction process standards, operating requirements, and calculation rules upon which its implementation depends. The construction cost calculation device, through in-depth parsing and structured information extraction of the digital copy of the quota, transforms the originally unstructured or semi-structured quota text into structured information.

[0040] Each quota category is treated as a category node, and based on the structured information, the associated concept node of the quota category is determined. Understandably, a category node refers to a core entity in the constructed quota knowledge graph, used to uniquely identify and store all attributes of a complete quota sub-item. A concept node refers to other knowledge entities that have a direct logical relationship with the quota sub-item, identified based on the structured information of the category node through semantic mapping rules and entity linking technology. The construction cost calculation device graphs quota items into an interconnected network of nodes.

[0041] Establish semantic relationship edges between the category nodes and the concept nodes, wherein the semantic relationship edges include data attributes; It should be noted that in the quota knowledge graph, the construction cost calculation device is used to connect category nodes with various concept nodes and to express the specific semantic relationship between them through directed or undirected semantic relationship edges, which may contain data attributes such as "unit consumption: 10.5" and "loss rate: 0.02".

[0042] An initial knowledge graph is constructed based on the category nodes, concept nodes, and semantic relationship edges; Understandably, the construction cost calculation device integrates scattered and isolated quota items and their related knowledge into an organically connected semantic network, realizing the systematization, structuring, and computation of knowledge in the field of engineering cost.

[0043] The initial knowledge graph is augmented to obtain an augmented structured quota knowledge graph.

[0044] It should be noted that the construction cost calculation device obtains an enhanced structured quota knowledge graph by performing deep knowledge enhancement on the initial knowledge graph.

[0045] In one feasible implementation, the step of performing knowledge enhancement on the initial knowledge graph to obtain an enhanced structured quota knowledge graph includes: Obtain quota data from different versions of the same region; It is understandable that "same region" refers to a designated administrative area or economic zone, such as Shanghai; different versions of quota data refer to multiple sets of engineering pricing standard datasets that are officially released and implemented by the cost management department of the region at different historical periods (such as different years), and have time sequence and rule continuity or differences. The construction cost calculation device acquires and manages multiple versions of quota data of the same region, enabling the system to be compatible with and process engineering projects that started or settled at different times. It supports complex business scenarios such as historical project auditing, cross-period comparison of cost indicators, and selection of specific version quotas for pricing according to contractual agreements, thereby enhancing the system's adaptability and practicality in the time dimension.

[0046] Perform semantic similarity comparison on text descriptions with the same quota number in the quota data; It should be noted that the same quota number refers to a unique identifier code representing the same sub-item of work in different versions of the quota database, and its text description may be modified with version updates. The construction cost calculation device converts the text descriptions (including work content, construction technology, material specifications, etc.) corresponding to the same quota number in different versions into high-dimensional semantic vectors, and quantifies the degree of semantic change of the quota item between different versions by calculating the cosine similarity and other measures between these vectors.

[0047] If the semantic similarity is greater than the threshold, then establish candidate relationships between different versions of quota categories; Understandably, the threshold refers to a pre-set critical similarity score used to determine whether two text descriptions are semantically similar enough to potentially represent the same substantive content of the quota. For example, 0.85. A relation candidate refers to a preliminary association created in the knowledge graph between quota category nodes that are semantically highly similar (i.e., greater than the threshold) in different versions, representing the "evolution of the same quota item in different versions," and awaiting further confirmation or enrichment of attributes. By automatically establishing relation candidates between quota categories across versions, the construction cost calculation device provides structured clues for the system's intelligent identification and management of the version evolution of the quota system. This not only supports the connection and conversion between historical projects and new quotas, and the cross-period statistical analysis of cost indicators, but also lays a traceable and analyzable relational foundation for the continuous learning and knowledge updating of the quota library.

[0048] Based on the candidate relationships, the initial knowledge graph is augmented to obtain an augmented structured quota knowledge graph.

[0049] It should be noted that the construction cost calculation device utilizes the established "version evolution candidate" relationship between cross-version quota categories, and through technical means such as relationship confirmation, node attribute inheritance and completion, and historical rule chain construction, it deeply expands and optimizes the initial knowledge graph to obtain an enhanced structured quota knowledge graph.

[0050] In this embodiment, the enhanced structured quota knowledge graph refers to a more complete knowledge network that incorporates a clear evolution path of quota versions, a traceable history of rule changes, and cross-period related attributes on the basis of the initial graph, thereby significantly improving the system's adaptability and authority in dealing with complex contracts and long-term projects.

[0051] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 The step of generating semantic query intents corresponding to different construction sections based on the component identification results includes steps S01 to S03: Step S01: Traverse the center point coordinates of each component in the component identification results and assign the component to the corresponding construction section; Understandably, the center point coordinates refer to the coordinates (X, Y, Z) of a point representing its average position in three-dimensional space, calculated from the geometric data of the component. Among these, the Z coordinate (elevation) is the key basis for allocating construction sections in the vertical direction. The construction cost calculation device compares the Z coordinates of the component's center point with the preset elevation ranges of each construction section (e.g., 0-50 meters for section one, 50-100 meters for section two), and determines the construction section identifier to which the component belongs through spatial position judgment logic.

[0052] Step S02: Based on the comprehensive features corresponding to each component in the construction section, perform section feature aggregation to obtain the target comprehensive feature vector; It should be noted that the construction cost calculation device takes the comprehensive features of all components within each construction section (each component's comprehensive feature is a multi-dimensional vector) as input, and calculates them using a preset aggregation function (such as mean pooling, weighted summation, max pooling, or dynamic aggregation based on attention mechanism). The result is a target comprehensive feature vector that can represent the overall attributes of all components in the construction section. By elevating the fine-grained features at the component level to a macro-level feature representation at the section level, the system can grasp the construction characteristics and resource consumption patterns of different vertical sections from a holistic perspective.

[0053] Step S03: Based on the target comprehensive feature vector, generate the semantic query intent corresponding to different construction sections.

[0054] Understandably, the construction cost calculation device takes the target comprehensive feature vector of each construction section as input. Through a pre-trained intent decoding model (such as a Transformer-based decoder or a specific multi-layer neural network), it decodes and reconstructs the overall attributes of the section contained in the vector into structured conditional statements that conform to the quota knowledge graph query specifications. By reverse-engineering precise semantic query intents from the aggregated section-level features, it achieves an intelligent transformation from "data features" to "executable queries." This avoids the computational redundancy caused by generating query intents separately for each component within a section, and can grasp the overall construction characteristics of the section, generating queries that better reflect the common needs and special conditions of the section. This enables more efficient, macroscopic, and construction organization-compliant quota matching in subsequent knowledge graph retrieval.

[0055] In one feasible implementation, the steps of calculating the quantity of work based on the geometric data, and calculating the construction cost based on the quantity of work and the quota category, include: Based on the material type of each component in the construction section, calculate the pumping surcharge corresponding to different construction sections; It should be noted that the construction cost calculation device first identifies all concrete components based on the material type of each component in each construction section. Then, based on the height range represented by the construction section and the preset calculation rules for pumping surcharges (such as different rate standards corresponding to different height ranges), it automatically calculates the total quantity of concrete components in the section and calculates the additional costs for vertical transportation machinery and energy consumption. By combining material type identification with section height information, it achieves automated and precise calculation of pumping surcharges for concrete projects.

[0056] Based on the geometric data, the quantities of work are calculated, and based on the quantities of work, the quota categories, and the pumping surcharge, the construction cost is calculated.

[0057] Understandably, the construction cost calculation device takes the quantity of components, the matching quota categories, and the related pumping surcharges as direct inputs. Through its built-in pricing engine, it automatically calculates and summarizes the costs of each sub-item of the project, the costs of the measures, the costs of other items, the regulatory fees, and the taxes, and finally generates the total project cost.

[0058] In this implementation, the semantic query intent generated based on the overall characteristics of the section can more comprehensively and accurately reflect the comprehensive conditions and special requirements of the construction of that section (such as common superelevation and specific process combinations). This ensures that the subsequent quota matching results are not merely a simple correspondence of component attributes, but also a precise capture of resource consumption patterns under specific construction environments, thereby making the cost calculation results more reasonable and instructive.

[0059] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the construction cost calculation method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0060] This application also provides a construction cost calculation device, please refer to... Figure 3 The building cost calculation device includes: The acquisition module 10 is used to acquire building project files, parse the building project files into components, and obtain component objects, wherein the component objects include geometric data, attribute data, and relational data. The classification module 20 is used to input the component object into a preset multimodal recognition model for multimodal feature extraction to obtain target features, fuse the target features to obtain fused comprehensive features, classify based on the comprehensive features, and obtain component recognition results. The component recognition results include component type, construction process and structural features, and material type. The target features include geometric features, semantic features, and contextual features. The matching module 30 is used to perform quota matching based on the component identification results and to calculate the construction cost based on the corresponding quota category.

[0061] Optionally, the matching module includes: The retrieval submodule is used to determine whether the building height is greater than a height threshold based on the structural features; if it is greater, the construction section is divided based on the building height; based on the component identification results, the semantic query intent corresponding to each of the different construction sections is generated; the initial quota category corresponding to each semantic query intent is retrieved from the preset structured quota knowledge graph; the initial quota category is filtered based on preset project constraints to obtain a preset number of quota categories; the quantity of work is calculated based on the geometric data, and the construction cost is calculated based on the quantity of work and the quota category.

[0062] Optionally, the retrieval submodule includes: A unit is established to acquire quota regulations documents, perform text recognition on the quota regulations documents to obtain a digital copy; based on the digital copy, parse the structured information corresponding to each quota category, wherein the structured information includes the quota category, materials, construction type, region, and technical specifications; designate each quota category as a category node, and determine the associated concept nodes based on the structured information; establish semantic relationship edges between the category nodes and the concept nodes, wherein the semantic relationship edges include data attributes; construct an initial knowledge graph based on the category nodes, concept nodes, and semantic relationship edges; and perform knowledge enhancement on the initial knowledge graph to obtain an enhanced structured quota knowledge graph.

[0063] The traversal unit is used to traverse the center point coordinates of each component in the component identification result and assign the component to the corresponding construction section; based on the comprehensive features corresponding to each component in the construction section, the section features are aggregated to obtain the target comprehensive feature vector; based on the target comprehensive feature vector, the semantic query intent corresponding to different construction sections is generated.

[0064] Optionally, the establishment unit includes: An enhancement subunit is used to acquire quota data from different versions of the same region; perform semantic similarity comparison on text descriptions with the same quota number in the quota data; if the semantic similarity is greater than a threshold, establish a relationship candidate between quota categories of different versions; based on the relationship candidate, perform knowledge enhancement on the initial knowledge graph to obtain an enhanced structured quota knowledge graph.

[0065] Optionally, the traversal unit includes: The calculation subunit is used to calculate the pumping surcharge corresponding to different construction sections based on the material type of each component in the construction section; calculate the quantity of work based on the geometric data; and calculate the construction cost based on the quantity of work, the quota category, and the pumping surcharge.

[0066] The construction cost calculation device provided in this application, employing the construction cost calculation method described in the above embodiments, can solve the technical problem of construction cost calculation. Compared with the prior art, the beneficial effects of the construction cost calculation device provided in this application are the same as those of the construction cost calculation method described in the above embodiments, and other technical features in the construction cost calculation device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0067] This application provides a construction cost calculation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the construction cost calculation method in the above embodiment 1.

[0068] The following is for reference. Figure 4 The diagram illustrates a structural schematic of a construction cost calculation device suitable for implementing embodiments of this application. The construction cost calculation device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, tablets, digital broadcast receivers, PDAs (Personal Digital Assistants), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The construction cost calculation device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0069] like Figure 4 As shown, the construction cost calculation device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the construction cost calculation device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 allows the construction cost calculation device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows construction cost calculation devices with various systems, it should be understood that it is not required to implement or possess all of the systems shown. More or fewer systems may be implemented alternatively.

[0070] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0071] The construction cost calculation device provided in this application, employing the construction cost calculation method described in the above embodiments, can solve the technical problem of construction cost calculation. Compared with the prior art, the beneficial effects of the construction cost calculation device provided in this application are the same as those of the construction cost calculation method described in the above embodiments, and other technical features of the construction cost calculation device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0072] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0073] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0074] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the construction cost calculation method described in the above embodiments.

[0075] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0076] The aforementioned computer-readable storage medium may be included in the construction cost calculation device; or it may exist independently and not be assembled into the construction cost calculation device.

[0077] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the construction cost calculation device, the construction cost calculation device performs the following actions: acquires a construction project file; parses the construction project file into components to obtain component objects, wherein the component objects include geometric data, attribute data, and relational data; inputs the component objects into a preset multimodal recognition model for multimodal feature extraction to obtain target features; fuses the target features to obtain fused comprehensive features; classifies the components based on the comprehensive features to obtain component recognition results, wherein the component recognition results include component type, construction technology and structural features, and material type; the target features include geometric features, semantic features, and contextual features; and performs quota matching based on the component recognition results, and calculates the construction cost based on the corresponding quota category.

[0078] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0079] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0080] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0081] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described construction cost calculation method, and is capable of solving the technical problem of construction cost calculation. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the construction cost calculation method provided in the above embodiments, and will not be repeated here.

[0082] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the construction cost calculation method described above.

[0083] The computer program product provided in this application can solve the technical problem of building cost calculation. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the building cost calculation method provided in the above embodiments, and will not be repeated here.

[0084] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.

Claims

1. A method for calculating building costs, characterized in that, The method for calculating construction costs includes: Obtain the building project file, parse the building project file into components to obtain component objects, wherein the component objects include geometric data, attribute data and relation data; The component object is input into a preset multimodal recognition model for multimodal feature extraction to obtain target features. The target features are then fused to obtain fused comprehensive features. Based on the comprehensive features, the component is classified to obtain the component recognition result. The component recognition result includes component type, construction process and structural features, and material type. The target features include geometric features, semantic features, and contextual features. Based on the component identification results, quota matching is performed, and based on the corresponding quota category, the construction cost is calculated.

2. The construction cost calculation method as described in claim 1, characterized in that, The steps of matching quotas based on the component identification results and calculating construction costs based on the corresponding quota categories include: Based on the structural features, determine whether the building height is greater than the height threshold; If the height is greater than the building height, then the construction zones will be divided based on the building height. Based on the component identification results, semantic query intents corresponding to different construction sections are generated respectively; In the preset structured quota knowledge graph, retrieve the initial quota categories corresponding to the semantic query intents respectively; Based on preset project constraints, the initial quota categories are filtered to obtain a preset number of quota categories; Based on the geometric data, the quantities of work are calculated, and based on the quantities of work and the quota categories, the construction cost is calculated.

3. The construction cost calculation method as described in claim 2, characterized in that, Before the step of retrieving the initial quota category corresponding to the semantic query intent from the preset structured quota knowledge graph, the following steps are included: Obtain the quota specification document, perform text recognition on the quota specification document, and obtain a digital copy; Based on the digital copy, the structured information corresponding to each quota category is parsed, wherein the structured information includes the quota category, material, construction type, region and technical specifications; Each quota category is treated as a category node, and based on the structured information, the associated concept node of the quota category is determined. Establish semantic relationship edges between the category nodes and the concept nodes, wherein the semantic relationship edges include data attributes; An initial knowledge graph is constructed based on the category nodes, concept nodes, and semantic relationship edges; The initial knowledge graph is augmented to obtain an augmented structured quota knowledge graph.

4. The construction cost calculation method as described in claim 3, characterized in that, The step of performing knowledge augmentation on the initial knowledge graph to obtain the augmented structured quota knowledge graph includes: Obtain quota data from different versions of the same region; Perform semantic similarity comparison on text descriptions with the same quota number in the quota data; If the semantic similarity is greater than the threshold, then establish candidate relationships between different versions of quota categories; Based on the candidate relationships, the initial knowledge graph is augmented to obtain an augmented structured quota knowledge graph.

5. The construction cost calculation method as described in claim 2, characterized in that, The step of generating the semantic query intent corresponding to different construction sections based on the component identification result includes: Traverse the center point coordinates of each component in the component identification results and assign the component to the corresponding construction section; Based on the comprehensive features corresponding to each component in the construction section, the section features are aggregated to obtain the target comprehensive feature vector; Based on the target comprehensive feature vector, the semantic query intent corresponding to different construction sections is generated.

6. The construction cost calculation method as described in claim 2, characterized in that, The steps of calculating the quantity of work based on the geometric data, and calculating the construction cost based on the quantity of work and the quota category, include: Based on the material type of each component in the construction section, calculate the pumping surcharge corresponding to different construction sections; Based on the geometric data, the quantities of work are calculated, and based on the quantities of work, the quota categories, and the pumping surcharge, the construction cost is calculated.

7. A construction cost calculation device, characterized in that, The device includes: The acquisition module is used to acquire building project files, parse the building project files into components, and obtain component objects, wherein the component objects include geometric data, attribute data, and relational data; The classification module is used to input the component object into a preset multimodal recognition model for multimodal feature extraction to obtain target features, fuse the target features to obtain fused comprehensive features, classify based on the comprehensive features, and obtain component recognition results. The component recognition results include component type, construction process and structural features, and material type. The target features include geometric features, semantic features, and contextual features. The matching module is used to perform quota matching based on the component identification results and to calculate the construction cost based on the corresponding quota category.

8. A construction cost calculation device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the construction cost calculation method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the construction cost calculation method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the construction cost calculation method as described in any one of claims 1 to 6.

Images