An intelligent analysis and estimation method and system for architectural engineering drawings

Abstract

The present application relates to a method and system for intelligently parsing and estimating construction engineering drawings, wherein the method comprises: parsing the acquired construction engineering drawings through a geometric figure recognition algorithm to obtain the project structured data of the initial design; parsing the acquired user demand instructions through a large language model to obtain demand structured instructions; based on the demand structured instructions, modifying the project structured data through the large language model to obtain demand structured data; based on the demand structured data, calculating the cost of the construction project after the demand is modified through an engineering estimate algorithm to obtain a demand estimate report. Through this application, when the construction project demand changes, the user can directly input instructions to instruct the LLM to make modifications and obtain an estimate report, without having to manually modify and then estimate in professional software, which greatly improves the efficiency of automatic engineering estimates and solves the problem of how to improve the efficiency of existing construction project estimates.

Description

Technical Field

[0001] The present application relates to the field of computer graphics technology, and in particular to a method and system for intelligent analysis and estimation of architectural engineering drawings. Background Art

[0002] Design Estimate refers to the preliminary calculation of the total investment and cost of a project in the early stages of the project based on technical information such as design drawings, estimate quotas or estimate indicators, and cost quotas. It directly affects the project's funding, cost control, and scheme selection.

[0003] Traditional engineering budget estimates rely on manual interpretation of drawings and reference to quotas in combination with BIM quantity calculation software for calculation. That is, it requires manual input of parameters and establishment of three-dimensional models for engineering quantity calculation, which is time-consuming and labor-intensive and prone to calculation deviations. In addition, it is difficult to dynamically modify design drawings during the engineering budget estimate process, and the flexibility is low, which reduces the efficiency of engineering budget estimates.

[0004] Currently, no effective solution has been proposed for the problem of how to improve the efficiency of the budget estimate of existing construction projects in related technologies. Summary of the Invention

[0005] The embodiments of the present application provide a method and system for intelligent analysis and estimation of construction engineering drawings, so as to at least solve the problem in the related art of how to improve the efficiency of existing construction engineering estimation.

[0006] In a first aspect, an embodiment of the present application provides a method for intelligently analyzing and estimating construction engineering drawings, the method comprising:

[0007] The acquired architectural engineering drawings are parsed using geometric pattern recognition algorithms to obtain the project structured data of the initial design;

[0008] The acquired user demand instructions are parsed through a large language model to obtain demand structured instructions;

[0009] Based on the demand structuring instruction, modifying the project structured data by using the large language model to obtain demand structured data;

[0010] Based on the demand structured data, the cost of the construction project after the demand is modified is calculated using a project budget algorithm to obtain a demand budget report after the demand is modified.

[0011] In some embodiments, the method further comprises:

[0012] Based on the project structured data, calculating the cost of the initially designed construction project using an engineering budget algorithm to obtain an initially designed project budget report;

[0013] The demand estimate report after the demand modification and the project estimate report of the initial design are used for users to compare and select construction project plans.

[0014] In some embodiments, the acquired user demand instructions are parsed using a large language model to obtain demand structured instructions including:

[0015] Acquiring user demand instructions input by a user, wherein the user demand instructions include design change instructions, cost optimization instructions, and functional area modification instructions;

[0016] The user demand instructions are parsed through a trained large language model to generate demand structured instructions corresponding to the standard specifications of the construction engineering industry.

[0017] In some embodiments, after parsing the acquired user demand instructions using a large language model to obtain demand structured instructions, the method includes:

[0018] Collecting the demand structured instructions generated by the large language model to obtain an instruction dataset, and validating the instruction dataset to obtain a verification dataset, wherein the verification dataset includes the demand structured instructions and a label indicating whether each demand structured instruction is correctly generated;

[0019] Under the preset iterative update conditions, the large language model is iteratively updated using the verification data set to obtain an iteratively updated large language model.

[0020] In some embodiments, collecting the demand structured instructions generated by the large language model to obtain an instruction dataset, and validating the instruction dataset to obtain a validation dataset includes:

[0021] Collecting the demand structured instructions generated by the large language model to obtain an instruction data set, wherein the instruction data set includes a basic instruction set and an extended instruction set, the basic instruction corresponds to a single general user demand instruction, and the extended instruction corresponds to a continuous and complex user demand instruction;

[0022] Verify each basic instruction in the basic instruction set one by one to verify whether the large language model correctly understands the user's required instructions;

[0023] Verifying each extended instruction in the extended instruction set one by one to verify whether the logical relationship between the basic instructions constituting the extended instruction is correct;

[0024] Based on the results of the two verifications, a verification dataset was obtained.

[0025] In some embodiments, upon satisfying a preset iterative update condition, iteratively updating the large language model using the validation dataset includes:

[0026] Setting preset iterative update conditions for triggering iterative updates of the large language model, wherein the preset iterative update conditions include frequent errors in parsing user demand instructions and new provisions in construction engineering industry standards and specifications;

[0027] Under the preset iterative update conditions, the large language model is iteratively updated through incremental learning based on the verification data set.

[0028] In some embodiments, based on the demand structuring instruction, modifying the project structured data using the large language model to obtain the demand structured data includes:

[0029] Based on the multi-dimensional features of the building components in the construction engineering drawings, labeling the project structured data of each building component using the large language model to obtain a multi-dimensional label for the building component;

[0030] Based on the multi-dimensional tags and the demand structured instructions, the project structured data of the corresponding building components are modified through the large language model to obtain demand structured data.

[0031] In some embodiments, based on the multi-dimensional features of the building components in the construction engineering drawings, generating labels for the project structured data of each building component using the large language model includes:

[0032] Based on the positional features and shape features of the building components in the construction engineering drawings, generating geometric feature labels for the project structured data of each building component using the large language model;

[0033] Based on the usage characteristics and design specification characteristics of the building components in the construction engineering drawings, generating functional attribute labels for the project structured data of each building component through the large language model;

[0034] Based on the material type characteristics and construction process characteristics of the building components in the construction engineering drawings, the large language model is used to generate material construction labels for the project structured data of each building component;

[0035] Based on the inter-component topological features of the building components in the construction engineering drawings, relational labels are generated for the project structured data of each building component through the large language model.

[0036] In some embodiments, based on the multi-dimensional tags and the demand structured instructions, modifying the corresponding project structured data of the building component using the large language model includes:

[0037] Based on the multi-dimensional labels of different building components, an inverted index of project structured data is established;

[0038] The target building component corresponding to the demand structured instruction is located by using the large language model, and the project structured data of the target building component is retrieved by using the inverted index, and then the project structured data is modified.

[0039] In a second aspect, an embodiment of the present application provides an intelligent parsing and budgeting system for construction engineering drawings, the system being configured to execute any of the methods described in the first aspect above, the system comprising a drawing parsing module, a demand modification module, and a project budgeting module;

[0040] The drawing parsing module is used to parse the acquired architectural engineering drawings using a geometric figure recognition algorithm to obtain the project structured data of the initial design;

[0041] The demand modification module is used to parse the acquired user demand instructions through a large language model to obtain demand structured instructions;

[0042] The requirement modification module is used to modify the project structured data according to the requirement structured instruction through the large language model to obtain requirement structured data;

[0043] The project estimate module is used to calculate the cost of the construction project after the demand is modified based on the demand structured data through a project estimate algorithm to obtain a demand estimate report after the demand is modified.

[0044] Compared with the related art, the embodiment of the present application provides an intelligent parsing and estimating method for construction engineering drawings, wherein the method parses the acquired construction engineering drawings through a geometric figure recognition algorithm to obtain the project structured data of the initial design; parses the acquired user demand instructions through a large language model to obtain demand structured instructions; based on the demand structured instructions, modifies the project structured data through the large language model to obtain demand structured data; based on the demand structured data, calculates the cost of the construction project after the demand is modified through the engineering estimate algorithm to obtain a demand estimate report, and realizes the use of a large language model to modify the demand of the initially designed construction engineering drawings and automatically calculates the demand estimate report of the modified project, that is, when the demand of the construction project changes, the user can directly input instructions to instruct the LLM to make modifications and obtain the estimate report, without the need to manually modify and then estimate in professional software, which greatly improves the efficiency of automatic engineering estimate and solves the problem of how to improve the efficiency of existing construction project estimate. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0046] Figure 1 This is a flowchart of the steps of the method for intelligent analysis and estimation of construction engineering drawings according to an embodiment of the present application;

[0047] Figure 2 Schematic diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is described and illustrated below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely used to explain this application and are not intended to limit this application. Based on the embodiments provided in this application, all other embodiments obtained by those of ordinary skill in the art without making any creative efforts are within the scope of protection of this application.

[0049] Obviously, the drawings described below are merely examples or embodiments of the present application. Those skilled in the art can, without inventive effort, apply the present application to other similar scenarios based on these drawings. Furthermore, it is also understood that, although the effort involved in such a development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, changes in design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as an insufficiency of the content disclosed in this application.

[0050] References to "embodiments" in this application mean that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described in this application may be combined with other embodiments unless there is a conflict.

[0051] Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by persons of ordinary skill in the art to which this application belongs. The terms "a," "an," "an," "the," and similar expressions used herein do not denote quantitative limitations and may refer to either the singular or the plural. The terms "comprise," "include," "have," and any variations thereof, used herein, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or modules (units) is not limited to the listed steps or units but may also include steps or units not listed, or may include other steps or units inherent to the process, method, product, or apparatus. The terms "connected," "connected," "coupled," and similar expressions used herein are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. As used herein, "plurality" means two or more. "And / or" describes an association between associated objects, indicating that three possible relationships exist. For example, "A and / or B" may mean: A exists alone; A and B exist simultaneously; or B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific order for the objects.

[0052] The present invention provides a method for intelligently analyzing and estimating construction engineering drawings. Figure 1 This is a flowchart of the steps of the intelligent analysis and estimation method of the construction engineering drawings according to the embodiment of the present application. Figure 1As shown, the method includes:

[0053] Step S102: parsing the acquired architectural engineering drawings using a geometric pattern recognition algorithm to obtain initially designed project structured data;

[0054] Step S102 specifically includes the following steps:

[0055] Step S1021: First, obtain a complete set of construction engineering drawings for the construction project. These construction engineering drawings are professional engineering software drawings (such as CAD drawings).

[0056] In step S1022, the complete set of architectural engineering drawings is parsed using a geometric figure recognition algorithm. The specific parsing process is as follows: first, based on the geometric features of the floor table and the table content features, the floor table is found in the drawing and read and analyzed to generate floor information; then, based on the geometric features of the drawing frame table and the axis grid, the entire drawing is split to generate drawing sub-drawings; then, information such as the drawing name and drawing number are extracted from each drawing sub-drawing to obtain the type of the drawing sub-drawing, and the floor attribution information of each sub-drawing is set in combination with the above-mentioned floor information and the type of the drawing sub-drawing; finally, based on the floor attribution of each sub-drawing, the overall project structured data is generated, including the structured attribute data of the building components (such as axis grids, columns, walls, beams, slabs, etc.).

[0057] Step S104: parsing the acquired user demand instructions through a large language model to obtain demand structured instructions;

[0058] Step S104 specifically includes the following steps:

[0059] Step S1041 , obtaining user demand instructions input by the user, wherein the user demand instructions include design change instructions (such as material replacement, floor height adjustment), cost optimization instructions (such as engineering quantity compression, unit price adjustment), and functional area modification instructions (such as functional area use change);

[0060] For example, these user demand instructions cover all disciplines of construction engineering (architecture, structure, mechanical and electrical engineering, etc.), such as "Replace dry-hanging stone on the facade with paint," "Adjust the standard floor height from 3.6 meters to 3.3 meters," and "Convert the office area into a conference room." Design change records, engineering instruction sheets, and corresponding budget adjustment data were extracted from historical projects of partner organizations to form an original instruction library. Through user interviews and questionnaire surveys, we collected the most frequently requested instructions from engineers in actual operations.

[0061] Step S1042: parse the user demand instructions through the trained large language model to generate demand structured instructions corresponding to the construction engineering industry standards and specifications.

[0062] For example, the large language model in this embodiment is specifically used for estimating construction project budgets. It integrates industry standards for construction projects (such as the "Construction Project Bill of Quantities Pricing Specifications" and "Construction Project Budget Quotas"). The large language model parses user input and generates structured demand instructions corresponding to the manual provisions of the specifications (such as quantity calculation rules and material price tables). For example: Manual provision: "Concrete beam quantities are calculated by volume" → Structured demand instruction: "Calculate the volume of all concrete beams."

[0063] It should be noted that when making a budget estimate for an actual construction project, it is often necessary to consider how to save costs or how to be more economical. At this time, it is often handled by modifying the decorative materials or compressing the floor height. The traditional method requires manual modification of the material floor height in the model in the budget software and recalculation of the budget report, which is often labor-intensive. However, through the embodiment of the present application, the modified plan can be input into the large language model in a natural language manner. After understanding the structured data, the large language model searches and judges it and modifies the relevant data.

[0064] After step S104, the method further includes step S105, collecting the requirement structured instructions generated by the large language model to obtain an instruction data set, and verifying the instruction data set to obtain a verification data set, wherein the verification data set includes the requirement structured instructions and whether each requirement structured instruction generates a correct annotation; under the preset iterative update conditions, the large language model is iteratively updated using the verification data set to obtain an iteratively updated large language model.

[0065] Step S105 specifically includes the following steps:

[0066] Step S1051: collecting structured demand instructions generated by the large language model to obtain an instruction dataset, wherein the instruction dataset includes a basic instruction set and an extended instruction set. The basic instruction corresponds to a single general user demand instruction, and the extended instruction corresponds to a continuous and complex user demand instruction.

[0067] To illustrate, the demand structured instructions generated by the large language model are divided into a basic instruction set and an extended instruction set. The basic instructions correspond to single general user demand instructions, such as "change the material of the wall", and the extended instructions correspond to continuous and complex user demand instructions, such as "change the thickness of the facade wall from 200mm to 150mm, and change the facade material to stone."

[0068] In step S1052, each basic instruction in the basic instruction set is verified one by one to verify whether the large language model correctly understands the user's required instructions; each extended instruction in the extended instruction set is verified one by one to verify whether the logical relationship between the basic instructions that constitute the extended instructions is correct; based on the results of the two verifications, a verification data set is obtained.

[0069] To illustrate, for the verification of the basic instruction set, manual review can be adopted (such as forming an evaluation team composed of engineering cost experts, designers, and construction representatives) to review the basic instructions one by one to verify whether the user demand instructions can be parsed by the large language model and converted into structured instructions. For example: a single general user demand instruction "adjust the standard floor height from 3.6 meters to 3.3 meters", check whether the large model can generate structured instructions to correctly modify the floor table and associated component coordinate data; for the verification of the extended instruction set, it is necessary to detect whether there is a logical conflict between the basic instructions in the extended instructions. For example: a continuous and complex user demand instruction is "change the facade wall thickness from 200mm to 150mm, and change the facade material to stone", it is necessary to verify whether the facade wall thickness of 150mm supports the construction specifications of the stone material.

[0070] Step S1053: setting preset iterative update conditions for triggering iterative updates of the large language model, wherein the preset iterative update conditions include frequent errors in parsing user demand instructions and new provisions in construction engineering industry standards and specifications;

[0071] As an example, there are frequent errors in the parsing of user demand instructions, such as the large language model failing to recognize that the number of times the user demand instruction "adjust the fire zone boundary" reaches the preset threshold; new clauses have appeared in the construction engineering industry standards and specifications, such as the green building standard has updated new clauses.

[0072] Step S1054: When the preset iterative update conditions are met, the large language model is iteratively updated through incremental learning based on the verification dataset.

[0073] As an example, the validation dataset is used as an incremental training set, and incremental learning technology is used to fine-tune the large model, retaining the original knowledge while adapting to new instructions. At the same time, contrastive learning is used to enhance the large language model's ability to distinguish similar instructions (such as "replace paint" and "replace paint brand").

[0074] Step S106, based on the demand structured instruction, modify the project structured data through the large language model to obtain demand structured data;

[0075] Step S106 specifically includes the following steps:

[0076] Step S1061: Based on the multi-dimensional features of the building components in the construction engineering drawings, the project structured data of each building component is labeled using a large language model to obtain a multi-dimensional label for the building component, wherein the multi-dimensional label includes a geometric feature label, a functional attribute label, a material construction label, and a relational label;

[0077] Step S1061 specifically:

[0078] ① Based on the location and shape features of building components in architectural engineering drawings, a large language model is used to generate geometric feature labels for the project structured data of each building component;

[0079] For example, for a building component whose coordinates are located at the outermost layer of the building outline and whose type is wall, its geometric feature label is "facade"; for a building component with a cantilever length greater than 1 meter and fewer than 2 support points, its geometric feature label is "cantilever structure".

[0080] ② Based on the usage characteristics and design specification characteristics of building components in architectural engineering drawings, a large language model is used to generate functional attribute labels for the project structured data of each building component;

[0081] For example, for a building component whose wall material is fireproof gypsum board and is located at the partition boundary, its functional attribute label is "fire partition"; for a building component whose load attribute of a structural column or beam is greater than the threshold, its functional attribute label is "load-bearing component";

[0082] ③ Based on the material type characteristics and construction process characteristics of building components in the construction engineering drawings, the large language model is used to generate material construction labels for the project structured data of each building component;

[0083] For example, for a building component whose wall material attribute is stone and whose construction method is dry hanging, its material construction label is "dry hanging stone"; for a building component whose production attribute is factory prefabricated, its material construction label is "prefabricated component";

[0084] ④ Based on the topological characteristics of building components in construction engineering drawings, a large language model is used to generate relational labels for the project structured data of each building component.

[0085] To illustrate, for a building component located at the junction of upper and lower floors, its relational label is "adjacent floors".

[0086] Step S1062 : Based on the multi-dimensional tags and the demand structured instructions, the project structured data of the corresponding building components are modified by the large language model to obtain demand structured data.

[0087] Specifically, step S1062 establishes an inverted index of project structured data based on the multi-dimensional labels of different building components; locates the target building component corresponding to the demand structured instruction through the large language model, and uses the inverted index to retrieve the project structured data of the target building component, and then modifies the project structured data to obtain the demand structured data.

[0088] An example to illustrate this is the retrieval of building components through multi-dimensional tags. That is, multi-dimensional tags are used to establish an inverted index for the project structured data of each building component, supporting logical operators (such as AND, OR) to combine multiple tags (such as simultaneously satisfying #external facade AND#dry-hanging stone walls); after the results are retrieved, they can be further filtered according to attributes (such as the floor is 3F), and the attribute fields of the components can be modified according to user instructions through batch update statements. If the modification affects the associated components, the component dependency is maintained through the graph database, the topology update is realized, and cascading updates are automatically triggered (for example, after the floor height is adjusted, the height of the column and wall must be modified accordingly).

[0089] Step S108 , based on the demand structured data, calculate the cost of the construction project after the demand is modified by using a project budget algorithm to obtain a demand budget report after the demand is modified.

[0090] After step S108, the method includes: based on the project structured data, calculating the cost of the initially designed construction project through the engineering budget algorithm to obtain the initially designed project budget report; the demand budget report after the demand modification and the initially designed project budget report are used for users to compare and select construction project plans.

[0091] For example, FunctionCall calls the project estimate algorithm, matching and mapping the component attributes in the structured data with the bill of quantities items (for example, matching "wall volume" with the "masonry engineering - brick wall" quota sub-item, and "concrete beam volume" with the "concrete engineering - cast-in-place beam" quota sub-item). The project quantities are then calculated item by item, and the sub-item costs are calculated based on the quota rules and material unit prices, resulting in a modified demand estimate report.

[0092] Through the above steps in the embodiment of the present application, a structured analysis of the complete drawings of the entire project is achieved by using a geometric figure recognition algorithm, which can identify all drawing information of the entire project and structure it to avoid the problem of missing key information during manual interpretation; a large language model is used to support users in modifying project parameters through natural language instructions, such as replacing materials, adjusting floor heights, changing functional areas, etc., which can dynamically respond to design changes, solve the defect that fixed template-based software cannot update interpretation results in a timely manner, and improve interpretation efficiency and accuracy; at the same time, it can output multiple versions of budget comparisons in real time, provide users with sufficient cost analysis basis, facilitate users to compare schemes, and assist in scientific engineering decision-making.

[0093] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0094] The embodiment of the present application provides an intelligent analysis and budgeting system for construction engineering drawings, which includes a drawing analysis module, a demand modification module, and a project budgeting module;

[0095] The drawing parsing module is used to parse the acquired architectural engineering drawings through a geometric figure recognition algorithm to obtain the project structured data of the initial design;

[0096] The demand modification module is used to parse the acquired user demand instructions through a large language model to obtain demand structured instructions;

[0097] The requirement modification module is used to modify the project structured data through the large language model according to the requirement structured instructions to obtain the requirement structured data;

[0098] The project estimate module is used to calculate the cost of the construction project after the demand is modified based on the demand structured data through the project estimate algorithm, and obtain the demand estimate report after the demand is modified.

[0099] Through the drawing parsing module, requirement modification module and project estimate module in the embodiments of the present application, it is possible to use a large language model to modify the requirements of the initially designed construction engineering drawings, and automatically calculate the requirement estimate report of the modified project. That is, when the requirements of the construction project change, the user can directly input instructions to instruct the LLM to make modifications and obtain the estimate report, without the need to manually modify and then estimate in professional software, which greatly improves the efficiency of automatic project estimates and solves the problem of how to improve the efficiency of existing construction project estimates.

[0100] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0101] This embodiment provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any one of the above method embodiments.

[0102] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0103] Optionally, the electronic device may further include a processor, a memory, a network interface, a display screen, and an input device connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for intelligent analysis and estimation of architectural engineering drawings is implemented. The display screen of the electronic device may be a liquid crystal display or an electronic ink display screen, and the input device of the electronic device may be a touch layer covering the display screen, or a button, trackball, or touchpad provided on the housing of the electronic device, or an external keyboard, touchpad, or mouse.

[0104] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be repeated here.

[0105] In addition, in conjunction with the intelligent analysis and estimation method for architectural drawings in the above-mentioned embodiments, embodiments of the present application may provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by a processor, it implements any of the intelligent analysis and estimation methods for architectural drawings in the above-mentioned embodiments.

[0106] In one embodiment, Figure 2 is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application, such as Figure 2 As shown, an electronic device is provided, which may be a server, and its internal structure diagram may be as shown in FIG. Figure 2As shown. The electronic device includes a processor, a network interface, an internal memory, and a non-volatile memory connected via an internal bus, wherein the non-volatile memory stores an operating system, a computer program, and a database. The processor is used to provide computing and control capabilities, the network interface is used to communicate with external terminals via a network connection, the internal memory is used to provide an environment for the operation of the operating system and the computer program. When executed by the processor, the computer program implements a method for intelligent analysis and estimation of architectural engineering drawings, and the database is used to store data.

[0107] Those skilled in the art will understand that Figure 2 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0108] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0109] Those skilled in the art should understand that the various technical features of the above-described embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the various technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0110] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. An intelligent analysis and estimation method for architectural engineering drawings, characterized in that: The method comprises: The acquired architectural engineering drawings are parsed using geometric pattern recognition algorithms to obtain the project structured data of the initial design; The acquired user demand instructions are parsed through a large language model to obtain demand structured instructions; Based on the positional features and shape features of the building components in the construction engineering drawings, generating geometric feature labels for the project structured data of each building component using the large language model; Based on the usage characteristics and design specification characteristics of the building components in the construction engineering drawings, generating functional attribute labels for the project structured data of each building component through the large language model; Based on the material type characteristics and construction process characteristics of the building components in the construction engineering drawings, the large language model is used to generate material construction labels for the project structured data of each building component; Based on the topological features between the building components in the construction engineering drawings, the large language model is used to generate relational labels for the project structured data of each building component to obtain multi-dimensional labels for the building components; Based on the multi-dimensional labels of different building components, an inverted index of project structured data is established; Locating the target building component corresponding to the demand structured instruction using the large language model, retrieving project structured data of the target building component using the inverted index, and then modifying the project structured data to obtain demand structured data; Based on the demand structured data, the cost of the construction project after the demand is modified is calculated using a project budget algorithm to obtain a demand budget report after the demand is modified.

2. The method according to claim 1, characterized in that The method further comprises: Based on the project structured data, calculating the cost of the initially designed construction project using an engineering budget algorithm to obtain an initially designed project budget report; The demand estimate report after the demand modification and the project estimate report of the initial design are used for users to compare and select construction project plans.

3. The method according to claim 1, characterized in that The acquired user demand instructions are parsed through a large language model to obtain demand structured instructions including: Acquiring user demand instructions input by a user, wherein the user demand instructions include design change instructions, cost optimization instructions, and functional area modification instructions; The user demand instructions are parsed through a trained large language model to generate demand structured instructions corresponding to the standard specifications of the construction engineering industry.

4. The method according to claim 1, wherein After parsing the acquired user demand instructions using the large language model to obtain demand structured instructions, the method includes: Collecting the demand structured instructions generated by the large language model to obtain an instruction dataset, and validating the instruction dataset to obtain a verification dataset, wherein the verification dataset includes the demand structured instructions and a label indicating whether each demand structured instruction is correctly generated; Under the preset iterative update conditions, the large language model is iteratively updated using the verification data set to obtain an iteratively updated large language model.

5. The method according to claim 4, characterized in that Collecting the demand structured instructions generated by the large language model to obtain an instruction dataset, and validating the instruction dataset to obtain a validation dataset includes: Collecting the demand structured instructions generated by the large language model to obtain an instruction data set, wherein the instruction data set includes a basic instruction set and an extended instruction set, the basic instruction corresponds to a single general user demand instruction, and the extended instruction corresponds to a continuous and complex user demand instruction; Verify each basic instruction in the basic instruction set one by one to verify whether the large language model correctly understands the user's required instructions; Verifying each extended instruction in the extended instruction set one by one to verify whether the logical relationship between the basic instructions constituting the extended instruction is correct; Based on the results of the two verifications, a verification dataset was obtained.

6. The method according to claim 4, characterized in that Under the preset iterative update conditions, iteratively updating the large language model using the verification data set includes: Setting preset iterative update conditions for triggering iterative updates of the large language model, wherein the preset iterative update conditions include frequent errors in parsing user demand instructions and new provisions in construction engineering industry standards and specifications; Under the preset iterative update conditions, the large language model is iteratively updated through incremental learning based on the verification data set.

7. An intelligent analysis and budget estimation system for construction engineering drawings, characterized by: The system is used to execute the method according to any one of claims 1 to 6, and the system includes a drawing parsing module, a demand modification module, and a project budget module; The drawing parsing module is used to parse the acquired architectural engineering drawings using a geometric figure recognition algorithm to obtain the project structured data of the initial design; The demand modification module is used to parse the acquired user demand instructions through a large language model to obtain demand structured instructions; The requirement modification module is used to modify the project structured data according to the requirement structured instruction through the large language model to obtain requirement structured data; The project estimate module is used to calculate the cost of the construction project after the demand is modified based on the demand structured data through a project estimate algorithm to obtain a demand estimate report after the demand is modified.

Images