Building cost estimation method and device based on artificial intelligence, storage medium and electronic device

By automatically extracting architectural drawing information through artificial intelligence technology and combining it with knowledge graphs, a rapid and accurate estimation of construction costs is achieved, solving the problems of long time consumption and large errors in traditional methods, and improving the efficiency of construction cost estimation and the company's customer acquisition capabilities.

CN120807001APending Publication Date: 2025-10-17CHINA DESIGN DIGITAL TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202510747137.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-05
Publication Date
2025-10-17

Smart Images

  • Figure CN120807001A_ABST
    Figure CN120807001A_ABST
Patent Text Reader

Abstract

The invention discloses a building cost estimation method and device based on artificial intelligence, a storage medium and an electronic device. The method comprises the steps that a target drawing is acquired, and information in the target drawing is recognized and mapped to a standard layer; space planning is conducted on the target drawing, a target contour is determined based on the standard layer and the space planning scheme, and the target contour is used for cost measurement and calculation; calling an intelligent semantic recognition engine, analyzing product usage information in the target contour, classifying the primitives based on the spatial relationship and the product features, and determining a target primitive classification result; product processes are intelligently matched based on the target primitive classification result, the price library is called to calculate the target price for estimation list information, the target estimation building cost is determined, the estimation list information comprises the product processes and product usage information, and the technical problem that in the prior art, the building cost estimation efficiency is low is solved.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the field of computers, in particular to an artificial intelligence-based building cost estimation method and device, a storage medium and an electronic device. BACKGROUND

[0002] In the customer acquisition stage of the construction industry, pricing based on scheme drawings is a core link in the early stage of project communication with customers, directly affecting the market competitiveness and customer trust of enterprises. However, the current technology mainly relies on the experience of senior designers and cost accounting personnel. Taking a single teaching building as an example, traditional cost estimation usually takes about a week, and due to the diversity of process selection, scattered material procurement, and complex data processing, it leads to low estimation efficiency, high error risk, and high procurement cost, which is difficult to meet the urgent needs of customers for speed, accuracy, transparency, and controllability. There is a problem of low efficiency of building cost estimation.

[0003] In summary, the prior art has the technical problem of low efficiency of building cost estimation. How to realize the intelligent upgrading of building industrialization and improve the efficiency of building cost estimation has not yet been proposed an effective solution. SUMMARY

[0004] The embodiments of the present application provide an artificial intelligence-based building cost estimation method, device, storage medium and electronic device to at least solve the technical problem of low efficiency of large building cost estimation.

[0005] According to an aspect of an embodiment of the present application, an artificial intelligence-based building cost estimation method is provided, including: obtaining a target drawing, identifying information in the target drawing and mapping it to a standard layer; performing spatial planning on the target drawing, determining a target contour based on the standard layer and the spatial planning scheme, wherein the target contour is used for cost estimation; calling an intelligent semantic recognition engine, analyzing product quantity information in the target contour, and classifying graph elements based on the spatial relationship and product characteristics to determine a target graph element classification result; intelligently matching product processes based on the target graph element classification result, calling a price library to calculate a target price for the estimation list information, and determining a target estimated building cost, wherein the estimation list information includes the product process and the product quantity information.

[0006] According to another aspect of an embodiment of the present application, an artificial intelligence-based building cost estimation device is also provided, including: An acquisition unit is configured to obtain a target drawing, identify information in the target drawing, and map it to a standard layer; A first determination unit is configured to perform spatial planning on the target drawing, and determine a target contour based on the standard layer and the spatial planning scheme, wherein the target contour is used for cost estimation; The second determining unit is configured to call an intelligent semantic recognition engine, analyze product quantity information in the target contour, classify graph elements based on the spatial relationship and product features, and determine a target graph element classification result. The computing unit is configured to intelligently match a product process based on the target graph element classification result, call a price library to calculate a target price based on estimated list information, and determine a target estimated construction cost, wherein the estimated list information comprises the product process and the product quantity information.

[0007] According to another aspect of the embodiments of the present application, a computer readable storage medium is provided, which stores a computer program configured to execute the above-mentioned artificial intelligence-based construction cost estimation method when running.

[0008] According to another aspect of the embodiments of the present application, an electronic device is provided, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above-mentioned artificial intelligence-based construction cost estimation method through the computer program.

[0009] In the embodiments of the present application, a target drawing is obtained, information in the target drawing is recognized and mapped to a standard layer, spatial planning is performed on the target drawing, a target contour is determined based on the standard layer and the spatial planning scheme, the target contour is used for cost estimation, an intelligent semantic recognition engine is called to analyze product quantity information in the target contour, graph elements are classified based on the spatial relationship and product features, a target graph element classification result is determined, a product process is intelligently matched based on the target graph element classification result, a price library is called to calculate a target price based on estimated list information, and a target estimated construction cost is determined, wherein the estimated list information comprises the product process and the product quantity information, a self-developed semantic recognition engine is called to intelligently supplement the drawing scheme, and product processes are automatically determined through graph element classification, thereby realizing artificial intelligence-based rapid quotation of construction cost and solving the technical problem of low construction cost estimation efficiency in the prior art. BRIEF DESCRIPTION OF DRAWINGS

[0010] The accompanying drawings, which are included to provide a further understanding of the present application and constitute a part of this application, illustrate embodiments of the present application and together with the description serve to explain the present application. In the drawings: Figure 1 is a schematic diagram of an optional artificial intelligence-based construction cost estimation method according to an embodiment of the present application; Figure 2 is a schematic diagram of an optional artificial intelligence-based construction cost estimation method according to an embodiment of the present application; Figure 3 is a schematic diagram of an optional artificial intelligence-based construction cost estimation method according to an embodiment of the present invention; Figure 4 is a schematic diagram of an optional artificial intelligence-based construction cost estimation device according to an embodiment of the present invention; Figure 5 is a schematic structural diagram of an optional electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0011] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0012] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0013] During the customer acquisition phase of the construction industry, quoting based on schematics is a core component of early-stage project communication with clients, directly impacting a company's market competitiveness and customer trust. However, current technology primarily relies on the experience of experienced designers and cost accountants. For a single teaching building, for example, traditional cost estimation typically takes approximately one week. Furthermore, due to diverse process selection, decentralized material procurement, and complex data processing, estimates are inefficient, with a high risk of error and high procurement costs, making it difficult to meet clients' urgent needs for speed, accuracy, transparency, and controllability. With intensified competition and accelerated digital transformation in the construction industry, developing efficient, accurate, automated, and material-controlled cost estimation technology has become a key requirement for improving customer acquisition, optimizing cost management, and enhancing market competitiveness.

[0014] Building cost estimation refers to predicting and calculating the total cost required to complete a project by comprehensively analyzing the core data elements of the project's design parameters, process methods, material consumption, labor input, equipment configuration, etc.

[0015] In the construction engineering industry, by drawing on manufacturing industry thinking and using digital means, the concept of "assemblable and industrialized building products" is taken as the core, a building model is established for the early customer acquisition stage, the cost and process data of different stages are standardized and integrated, and the data transfer from design to procurement is realized by replacing the BOM list (Bill of Materials). Most of the existing technologies are data-driven decisions, reducing the dependence on historical experience, thereby achieving accurate calculation and lean control of construction engineering cost, and improving the accuracy and efficiency of project cost control.

[0016] However, the above existing technologies have the following technical problems: (1) Information loss problem in the message transmission of multiple departments: when market personnel find a project, they pass it on to design personnel for scheme design, and then hand it over to cost personnel for estimation and pricing. There is an information gap that needs to be gradually aligned during the gradual handover process, and there is a large communication cost when the scheme needs to be adjusted and coordinated by multiple parties.

[0017] (2) Limited resources in small and medium-sized enterprises: at the current stage, a project such as a school single building needs to consume a senior design personnel and a senior cost personnel for one week to complete, and the enterprise has limited senior personnel. The annual estimation capacity tends to be constant, and after estimation, if the contract cannot be signed, it will also cause great waste of resources.

[0018] (3) Weak cost control ability: during the scheme design stage, the design results from the creative idea become complex in the cost estimation stage, the list and material selection control is less, the procurement content is scattered, the cost is higher, and the project delivery accounting is easy to exceed the budget.

[0019] (4) Weak customer acquisition ability: based on the above situation, the enterprise's customer acquisition ability is weak due to the inability to quickly quote, resource limitations, and weak cost control ability.

[0020] To solve the above technical problems, the embodiment automatically extracts geometric parameters, component attributes and spatial topological relations in architectural drawings through a self-developed semantic recognition engine, and realizes dynamic mapping of two-dimensional drawings on spatial data. Combined with a real-time material database, the system can identify structural components (such as beams, columns and walls) and non-standard components, and accurately disassemble them into standardized bill of quantities. A multi-dimensional cost knowledge graph is built in, and API (Application Programming Interface) access capability is provided. In the future, real-time market linkage pricing can be supported, and the API of the building material supply chain can be connected to dynamically pull the price fluctuation data of bulk commodities such as steel and concrete, ensuring the timeliness and risk resistance of cost budget. The cost quotation is output in the format of industrial BOM list. With the help of intelligent algorithms and optimization techniques of AI (Artificial Intelligence), the system can intelligently match products and supply chain data through parameterized adjustment (such as changing configuration, product, list and price) based on the knowledge graph capability, and realize cost change and real-time preview. For example, changing the external wall insulation material, the AI quickly matches and calculates the cost change. This makes the "design-cost-value" agile iteration, and realizes the linkage of digital model, which reduces the traditional cost calculation time from weeks to hours. Through data transparency, project uncertainty is reduced, and cost controllability is enhanced. The digital islands of business customer acquisition, building design and cost estimation are connected, and the loss of information transmission and manual calculation error is avoided. If the API interface is provided, different project management software and mainstream platforms can be connected to build a "design-calculation-control" integrated platform ecosystem, and to enable the intelligent upgrading of building industrialization. This system is the core carrier for the transformation of the building industry from "experience-driven" to "algorithm-driven".

[0021] Optionally, as an optional implementation manner, as shown in Figure 1 The building cost estimation method based on artificial intelligence comprises the following steps: S102, acquiring a target drawing, identifying information in the target drawing and mapping the information to a standard layer; S104, performing spatial planning on the target drawing, and determining a target contour based on the standard layer and the spatial planning scheme, wherein the target contour is used for cost calculation; S106, calling an intelligent semantic recognition engine, analyzing product quantity information in the target contour, classifying graph elements based on spatial relationships and product characteristics, and determining a target graph element classification result; S108, intelligently matching product processes based on the target graph element classification result, calling a price library to calculate target prices based on estimation list information, and determining a target estimated building cost, wherein the estimation list information comprises product process and product quantity information.

[0022] Optionally, in this embodiment, before obtaining the target drawing, in step S102, a project may be created in the architectural software and design requirements may be added to improve the drawing information. Inputting the drawing into the target drawing information and mapping it to the standard layer may include, but is not limited to, obtaining a standard layer template from the system, isolating the target drawing layer by layer for viewing, and automatically identifying the information on the drawing layer by layer and mapping it to the standard layer.

[0023] Optionally, in this embodiment, in step S104, space planning is performed on the target drawing, and the target outline is determined based on the standard layer and the space planning scheme, including: obtaining a first space object from the target drawing, the first space object being a geometric body composed of multiple graphic elements that forms a closed space, such as a closed space; after obtaining, identifying the graphic element information in the first space object, and performing semantic processing based on the graphic element information to assign semantic meaning, such as assigning the definition of "bedroom" to a closed space and the meaning of "bathroom" to another closed space.

[0024] Optionally, in this embodiment, after defining the first spatial object, the spatial relationships among multiple first spatial objects are identified and a knowledge graph is created. The knowledge graph is primarily used to complete architectural space, transforming fragmented spatial relationships into a structured network that can be reasoned by machines. Based on the knowledge graph, the second spatial object is intelligently and automatically completed. The second spatial object is a geometric object composed of multiple primitives that does not form a closed space.

[0025] Optionally, in this embodiment, the first spatial object and the completed second spatial object are used to determine a spatial planning scheme. The spatial planning scheme can be understood as a spatial layout strategy generated through systematic analysis based on architectural drawings and functional requirements, and is used to solve the optimal spatial organization form under multiple constraints. The standard layer and the spatial planning scheme are obtained to determine the target outline. The target outline is used to measure the cost within the target range. It can be understood, but is not limited to, as the outline corresponding to the cost within a space for which calculation is required. For example, the outline within a room is one of the target outlines, which is used to efficiently measure the room area and wall length, avoiding the problem of incorrect cost calculation caused by redundant space.

[0026] Optionally, in this embodiment, the original drawing plan is completed through the knowledge graph to facilitate the subsequent calculation of product usage data in the target outline, such as facilitating the calculation of the house area and the length of the house wall.

[0027] Optionally, in this embodiment, in step S106, the intelligent semantic recognition engine is called to analyze the product quantity information in the target contour, such as analyzing the door and window width, room area, etc. It can also include, but is not limited to: calling the semantic recognition engine to determine the target space attribute characteristics of the graph elements of the target contour; obtaining the pre-made formula of the platform, and calculating the target price of the target contour based on the target space attribute characteristics of the graph elements. Specifically, it can include: calling the semantic recognition engine to perform semantic recognition on the layer naming in the target drawing, such as "door" and "fire door", which both mean door, and then matching with the algorithm pre-made in the system for the object, and after matching, it is convenient to extract the numerical value in the graph element in the target contour according to the required geometric parameters. After matching, the space attribute of the graph element is generated according to the topology algorithm pre-made in the standard layer, such as determining the space attribute of the space connected by multiple columns as a wall, and the space attribute of the space connected by four closed columns as a space. The target space attribute characteristics are determined based on the geometric attribute and the space attribute of the graph element, such as a bedroom belonging to a non-water room and a bathroom belonging to a water room. Different attributes correspond to different process methods and costs. After defining the target space attribute characteristics, the target price of the target contour can be calculated based on the pre-made formula in the platform.

[0028] Optionally, in this embodiment, in steps S106-S108, the graph elements are classified based on the space relationship and product characteristics to determine the target graph element classification result, and the product process is intelligently matched based on the target graph element classification result. It includes: first, the graph elements are preliminarily classified according to the space and product type, and the product process is intelligently matched, such as the wall and floor of the water room needing to use waterproof materials. Intelligent matching of process includes obtaining the pre-made process list in the platform, such as wall top, floor, door and window, etc., but the graph element has been defined as a door before, so when selecting the process of the door, only the list of "wooden door, metal door... door" will appear, which facilitates efficient selection of graph element material process.

[0029] Optionally, in this embodiment, in step S108, the price library is called to calculate the target price of the product process and the product quantity information to determine the target estimated construction cost, including: obtaining the enterprise price library and the externally connected industry price library; calling the enterprise price library and the externally connected industry price library to intelligently calculate the target price of the list estimated information including the product process and the product quantity information based on the regional characteristics and the time characteristics; and calculating the target price, and determining the target estimated construction cost of the target price after the calculation. For example, the material price or labor price in a certain region and time period is intelligently matched. The scheme is intelligently evaluated and analyzed, and manual correction of the real-time price of the product is supported.

[0030] Optionally, in this embodiment, after step S108, the data and drawing files can be returned to the cloud for archiving together with the determination of the target estimated construction cost. The cloud supports the viewing of the model and provides leadership review. In this embodiment, after step S108, the target cost estimation scheme can be but not limited to be calculated, and when the cost result exceeds the preset market value, the knowledge graph is used for recalculation again to improve the accuracy and security.

[0031] Optionally, in this embodiment, after step S102 and before step S104, the following can be but not limited to be included: obtaining an enterprise product template, wherein the enterprise product template includes a standard block identifying quantity calculation rules and list prices; supplementing the scheme drawing of the target standard layer with the standard block. Checking each item of the graphic parameter information in the standard layer; product definition is performed on the first appearing graphic. Wherein, the supplement based on the standard block includes design, modification, completion and other functions.

[0032] As a specific embodiment, as shown in Figure 2 the following specific steps are introduced: let a normal market person make a scheme quotation in DWG.

[0033] First, when the market person gets the project, access the scheme quotation system through the access tool, and use "project setting" for simple registration. The registration process includes creating a project, adding construction requirements, and supplementing collaborative personnel; Secondly, understand the drawings obtained, obtain the layer template through the "layer mapping" function, isolate and view the current drawings layer by layer, specify the analysis of layer content, understand the drawing content and map to the standard layer.

[0034] Then, use the "product design" function to obtain the enterprise product template, and design or supplement the scheme drawing. At the same time, check each item of the graphic parameter setting of the layer. The newly added graphic can be defined as a product. The graphic can be placed on the product unit by dragging on the system.

[0035] Subsequently, use the "space positioning" function to perform space planning according to the drawing scheme. At this time, the standardized layers and space relationships will be identified, intelligent details will be supplemented, and cost estimation common contours will be drawn to generate space data, such as room contour for estimating room area, wall length, etc. Intelligent supplement details, such as automatically supplementing lines for spaces that are not closed in the original drawing.

[0036] Then, the "product disassembly" function is used to call the semantic recognition engine, comparison algorithm and other capabilities to analyze and confirm the configuration of the graph element, and to analyze the product usage such as door and window width, room area, etc. The product is preliminarily classified according to the space and product type, and the product process is intelligently matched, such as the wall and floor of the water room needing to use waterproof material. The product list information is confirmed, the product usage information is supplemented, and the final estimated list is generated.

[0037] Then, the "scheme estimation" function is used to aggregate the data in the estimated list, that is, the product usage obtained is displayed in the form of industrialized products. And according to the enterprise price library or the industry price library connected outside, the price is intelligently matched, such as intelligently matching the material price or labor price in a certain region within a certain time period. And the scheme is visualized and displayed in the system, and intelligent evaluation and analysis are carried out, and manual correction of real-time product price is supported, the expected difference is checked after confirming the unit price, and if there is no difference, the cost accounting is completed, and the result is exported.

[0038] Finally, the "disassembly back" is used to return the data and drawing files to the cloud for archiving. In the cloud, the function of viewing and providing leadership for review is supported.

[0039] Optionally, as the overall architecture of the system in the above embodiment, as shown in the figure, the system includes a data reserve layer, a user interaction layer, a model recognition layer, an intelligent decision-making layer, and an archiving management layer: Figure 3 The data reserve layer: reserves the product list quotation, or integrates the target enterprise price library, establishes the association between the graph element and the product through the graph element definition capability in the DWG (Drawing, drawing file format) template, and manages the products within the enterprise through the enterprise-level template.

[0040] The user interaction layer: realizes user identity authentication. In the scheme drawing, the drawing is clear based on the layer, and then the scheme design or product design is carried out. In the operation, the relationship between the graph element and the space is identified and established. The drawing engine is run to supplement the drawing, such as increasing the tolerance between line segments to improve the recognition effect, intelligently recognizing the room and drawing the inner contour, intelligently recognizing the floor and drawing the outer contour line, and intelligently drawing the wall center line, etc.

[0041] The graph element recognition layer: calls the semantic recognition engine to match the layers in the drawing with the standard layers in the system, and generates the spatial attributes of the graph element according to the pre-prepared topology algorithm in the layer after matching; based on the calculation rule of the layer, the set attributes in the graph element are extracted, such as line length and enclosed area, so as to realize fast calculation.

[0042] The intelligent decision-making layer: automatically decides the appropriate process according to the product configuration and space type. The user can optimize and adjust within the scope limited by the enterprise. According to the historical price data of the enterprise or the market price connected outside, the accurate price is intelligently matched, so as to realize fast quotation.​

[0043] Archive management layer: the current operation of the graph module returns to the cloud archive, realizes the consistency of the graph module, and realizes the centralized management and comparison analysis of multiple schemes of a project.

[0044] Optionally, in the embodiment, by acquiring the target drawing, the information in the target drawing is recognized and mapped to the standard layer; the target drawing is spatially planned, and the target contour is determined based on the standard layer and the spatial planning scheme, wherein the target contour is used for cost estimation; an intelligent semantic recognition engine is called to analyze the product usage information in the target contour, and the graph elements are classified based on the spatial relationship and product characteristics to determine the target graph element classification result; the product process is intelligently matched based on the target graph element classification result, the price library is called to calculate the estimated list information to calculate the target price, the target estimated construction cost is determined, the self-developed semantic recognition engine is called to intelligently supplement the drawing scheme, and the product process is automatically decided through the graph element classification, which realizes the building cost fast quotation based on artificial intelligence, and improves the building cost estimation efficiency in the prior art.

[0045] Optionally, in the embodiment, the system optimizes the complex operation that originally needs to be completed by 2-3 tools into an estimation process that can be completed in one tool. Users do not need to switch between different platforms. Secondly, the interactive design is optimized in the tool design. Before using the patent, professional designers need to operate, and after using the patent, ordinary market personnel can operate, the process is more simple and efficient, the use threshold is greatly reduced, and the ease of use is significantly improved.

[0046] Optionally, in the embodiment, in the traditional mode, 2-3 experienced professionals are needed to cooperate to complete the cost estimation of each project, and after optimization by the system, only one ordinary market personnel can complete all the work. This not only reduces the labor cost, but also reduces the dependence on scarce professional resources, and significantly reduces the labor cost.

[0047] Optionally, in the embodiment, the system integrates enterprise-level data templates, product libraries and price libraries to realize standardized and unified management of the quotation process. Compared with the manual control mode of independent quotation of each project and lack of association in the traditional mode, the system ensures that the user works within a controllable range, effectively reduces the risk of cost deviation, and comprehensively improves the product control capability.

[0048] Optionally, in the embodiment, the traditional cost estimation usually takes 3-7 days to complete, while the system compresses this time to within 3 hours. Through the application of automatic tools and intelligent algorithms, the quotation efficiency is significantly improved, more market response time is won for the enterprise, and the work efficiency is greatly improved.

[0049] Optionally, in the embodiment, the system significantly improves the enterprise's acquisition ability of the intended project and the customer acquisition opportunity by accelerating the efficiency of the quotation and reducing the labor cost in the customer acquisition stage. The enterprise can respond to customer demand more quickly, improve the order rate, thereby occupying a greater advantage in market competition, and realizes the enhancement of the project acquisition ability.

[0050] Optionally, in the embodiment, the system not only optimizes the internal process, but also enhances customer trust through accurate and transparent quotation schemes. The enterprise can more efficiently complete the whole process from quotation to signing, improve the rapid order ability, and thus realize business growth, and realizes the improvement of the rapid order ability It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the action sequence described, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application.

[0051] According to another aspect of the embodiment of the present application, an information pushing device for implementing the above-mentioned information pushing method is also provided. As shown in the Figure 4 The device comprises: An acquisition unit 402 is configured to acquire a target drawing, identify information in the target drawing and map the information to a standard layer; A first determination unit 404 is configured to perform spatial planning on the target drawing, and determine a target contour based on the standard layer and the spatial planning scheme, wherein the target contour is used for cost estimation; A second determination unit 406 is configured to call an intelligent semantic recognition engine, analyze product quantity information in the target contour, classify graph elements based on spatial relationship and product characteristics, and determine a target graph element classification result; A calculation unit 408 is configured to intelligently match product processes based on the target graph element classification result, call a price library to calculate a target price based on estimated list information, and determine a target estimated construction cost, wherein the estimated list information comprises product processes and product quantity information.

[0052] According to still another aspect of the embodiment of the present application, an electronic device for implementing the above-mentioned information pushing method is also provided. As shown in the Figure 5 The electronic device comprises a memory 502 and a processor 504, the memory 502 stores a computer program, and the processor 504 is configured to execute the steps in any one of the method embodiments by the computer program.

[0053] Optionally, in the embodiment, the electronic device can be located in at least one of the plurality of network devices of the computer network.

[0054] Optionally, in the embodiment, the processor can be configured to perform the following steps by means of a computer program: S1, obtaining a target drawing, identifying information in the target drawing and mapping to a standard layer; S2, performing spatial planning on the target drawing, determining a target contour based on the standard layer and the spatial planning scheme, wherein the target contour is used for cost estimation; S3, calling an intelligent semantic recognition engine, parsing product quantity information in the target contour, classifying graph elements based on spatial relationship and product characteristics, and determining a target graph element classification result; S4, intelligently matching product processes based on the target graph element classification result, calling a price library to calculate a target price based on estimated list information, and determining a target estimated construction cost, wherein the estimated list information includes product processes and product quantity information.

[0055] Optionally, those skilled in the art can understand that, Figure 5 The structure shown is only schematic, and the electronic device can also be a terminal device such as a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a mobile Internet device (MID), a PAD, etc. Figure 5 It does not limit the structure of the electronic device. For example, the electronic device can further include more or fewer components (such as a network interface, etc.) than those shown in Figure 5 , or have a different configuration than that shown in Figure 5 .

[0056] The memory 502 can be used to store software programs and modules, such as program instructions / modules corresponding to the information pushing method and device in the embodiment of the present application. The processor 504 performs various functional applications and data processing by running the software programs and modules stored in the memory 502, that is, implements the above-mentioned building cost estimation method based on artificial intelligence. The memory 502 can include a high-speed random access memory, and can also include a non-volatile memory such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 502 can further include a memory remotely arranged with respect to the processor 504, which can be connected to the terminal through a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The memory 502 can be used to store information such as a spatial planning scheme, but is not limited to this. As an example, the memory 502 can be used to store a spatial planning scheme, and the processor 504 can be configured to perform the following steps by means of a computer program: Figure 5As shown, the memory 502 can include, but is not limited to, the obtaining unit 402, the first determining unit 404, the second determining unit 406, and the calculating unit 408 in the above-mentioned building cost estimation device based on artificial intelligence. In addition, other module units in the above-mentioned building cost estimation device based on artificial intelligence can also be included, which will not be described herein again in the example.

[0057] Optionally, the transmission device 506 is configured to receive or send data via a network. Specific examples of the network can include wired networks and wireless networks. In an example, the transmission device 506 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers through a network cable to communicate with the Internet or a local area network. In an example, the transmission device 506 is a radio frequency (Radio Frequency, RF) module, which is configured to communicate with the Internet in a wireless manner.

[0058] In addition, the electronic device further includes a display 508 configured to display information such as a space optimization scheme result, and a connection bus 510 configured to connect various module components in the electronic device.

[0059] According to another aspect of the embodiments of the present application, a computer readable storage medium is also provided, which stores a computer program. When the computer program is executed, the steps in any of the above method embodiments can be performed.

[0060] Optionally, in the present embodiment, the computer readable storage medium can be configured to store a computer program for performing the following steps: S1, obtaining a target drawing, identifying information in the target drawing and mapping to a standard layer; S2, performing space planning on the target drawing, determining a target contour based on the standard layer and a space planning scheme, wherein the target contour is used for cost estimation; S3, calling an intelligent semantic recognition engine, analyzing product quantity information in the target contour, classifying graph elements based on spatial relationships and product characteristics, and determining a target graph element classification result; S4, intelligently matching product processes based on the target graph element classification result, calling a price library to calculate a target price based on estimated list information, and determining a target estimated building cost, wherein the estimated list information includes product process and product quantity information.

[0061] Optionally, in the embodiment, a person skilled in the art can understand that all or part of the steps of the various methods in the above embodiment can be completed by instructing the terminal device related hardware through a program, and the program can be stored in a computer readable storage medium, and the storage medium can include a flash disk, a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, etc.

[0062] The serial numbers of the above embodiments of the application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0063] The integrated units in the above embodiments, if realized in the form of software function units and sold or used as independent products, can be stored in the above computer readable storage medium. Based on such understanding, the technical solutions of the application or all or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions for causing one or more computer devices (which can be personal computers, servers or network devices, etc.) to execute all or part of the steps of the embodiments of the application.

[0064] In the above embodiments of the application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0065] In several embodiments provided in the present application, it should be understood that the disclosed client can be implemented by other ways. Among them, the above described device embodiments are only schematic, for example, the division of units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some interface, indirect coupling or communication connection between units or modules, and can be electrical or other forms.

[0066] The units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. According to actual needs, part or all of the units can be selected to realize the purpose of the embodiment.

[0067] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit.

[0068] The above is only the preferred embodiment of the present application, and it should be pointed out that, for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A construction cost estimation method based on artificial intelligence, characterized in that: The method comprises: Obtaining a target drawing, identifying information in the target drawing, and mapping the information onto a standard layer; Performing spatial planning on the target drawing, and determining a target outline based on the standard layer and the spatial planning scheme, wherein the target outline is used for cost estimation; Invoking an intelligent semantic recognition engine to parse product usage information within the target outline, and classifying the graphic elements based on the spatial relationship and product characteristics to determine a target graphic element classification result; Based on the target primitive classification result, the product process is intelligently matched, the price library is called to calculate the target price for the estimated list information, and the target estimated construction cost is determined, wherein the estimated list information includes the product process and the product usage information.

2. The construction cost estimation method based on artificial intelligence according to claim 1, characterized in that: The performing spatial planning on the target drawing and determining the target outline based on the standard layer and the spatial planning scheme includes: Acquire a first spatial object from the target drawing, wherein the first spatial object is a geometric body composed of multiple graphic elements forming a closed space; Identifying graphic element information in the first spatial object and assigning semantic meaning to the first spatial object; The spatial relationship between the standard layer and the first spatial object is obtained to construct a knowledge graph.

3. The construction cost estimation method based on artificial intelligence according to claim 2, characterized in that: The performing spatial planning on the target drawing and determining the target outline based on the standard layer and the spatial planning scheme includes: Intelligently and automatically completing the second spatial object based on the knowledge graph, wherein the second spatial object is a geometric body composed of multiple primitives that does not form a closed space; Determining the space planning scheme based on the first space object and the completed second space object; The target outline is determined based on the standard layer and the spatial planning solution.

4. The construction cost estimation method based on artificial intelligence according to claim 1, characterized in that: The performing of space planning on the target drawing further includes: Obtaining an enterprise product template, wherein the enterprise product template includes a standard block indicating a quantity calculation rule and a list price; The standard blocks are used to supplement the scheme drawing of the target standard layer.

5. The construction cost estimation method based on artificial intelligence according to claim 4 is characterized in that: The performing of space planning on the target drawing further includes: Checking parameter information of various graphic elements in the standard layer; Define the product for the first occurrence of the primitive.

6. The construction cost estimation method based on artificial intelligence according to claim 1, characterized in that: The calling of the intelligent semantic recognition engine to analyze the product usage information within the target outline includes: Invoking an intelligent semantic recognition engine to determine target spatial attribute features of the graphic element of the target outline; Obtain the platform's pre-made formula and calculate the target price of the target contour based on the target spatial attribute characteristics of the primitive.

7. The construction cost estimation method based on artificial intelligence according to claim 1, characterized in that: The calling of the price library to calculate the target price for the estimated list information and determine the target estimated construction cost includes: Obtain enterprise price database and external industry price database; Calling the enterprise price database and the external industry price database to intelligently calculate the target price of the estimated list information based on regional characteristics and time characteristics; The target price is calculated, and the target estimated construction cost is determined based on the calculated target price.

8. A construction cost estimation device based on artificial intelligence, characterized in that: The device comprises: An acquisition unit, configured to acquire a target drawing, identify information in the target drawing, and map the information onto a standard layer; a first determining unit, configured to perform spatial planning on the target drawing and determine a target outline based on the standard layer and the spatial planning scheme, wherein the target outline is used for cost estimation; A second determining unit is configured to call an intelligent semantic recognition engine to analyze the product usage information within the target outline, classify the graphic elements based on the spatial relationship and product characteristics, and determine a classification result of the target graphic element; A calculation unit is used to intelligently match product processes based on the target graphic element classification results, call a price library to calculate a target price for the estimated list information, and determine a target estimated construction cost, wherein the estimated list information includes the product process and the product usage information.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 7 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 7 through the computer program.

Citation Information

Cited By

  • Material cost calculation method for 2D engineering machinery drawing

    CN122175633A