Automatic building energy consumption modeling method based on large language model

Abstract

The invention discloses an automatic building energy consumption modeling method based on a large language model, and the method comprises the steps: obtaining a natural language demand description inputted by a user side, and carrying out the domain semantic analysis of the demand description based on a natural language model, and extracting a modeling parameter; the demand description comprises architectural space attributes; the modeling parameters are input into a building large language model, and a standardized modeling instruction set meeting the grammar specification of the target building energy consumption simulation engine is generated; wherein the building large language model is obtained by finely adjusting a pre-trained large language model through a professional question and answer corpus in the building field; an interface of the target building energy consumption simulation engine is called, a simulation instruction is generated, and the simulation instruction is used for indicating the target building energy consumption simulation engine to output a simulation result based on the standardized modeling instruction set; the simulation result comprises the building model file and a key index of the building model file. By adopting the method, the automation degree of building modeling can be improved, manual intervention is reduced, and the modeling threshold is lowered.

Description

Technical Field

[0001] The present invention belongs to the field of resource environment based on artificial intelligence, and particularly relates to an automated building energy consumption modeling method based on a large language model. Background Art

[0002] Building Energy Modelling (BEM), as the core technology for carbon footprint analysis in the building energy-saving design and operation stages, is mainly realized relying on professional simulation platforms such as EnergyPlus and DesignBuilder. Although such tools can achieve high-precision energy consumption simulation based on thermodynamic principles, their technical frameworks still have the following limitations: First, the modeling process relies on manual completion of building geometric parameterization reconstruction and multi-dimensional physical property definition, with a cumbersome operation process and low efficiency; Second, the user interface is deeply coupled with the modeling logic, building thermodynamics, HVAC system principles, and specific simulation engine syntax rules, resulting in a steep learning curve for non-professional users; Third, existing tools lack the ability to support automated modeling and are difficult to meet the real-time requirements of energy consumption simulation for rapid iteration of building design schemes.

[0003] In recent years, although large language models (LLMs) based on deep learning have demonstrated semantic understanding and logical reasoning advantages in the field of code generation, their application in the BEM field still faces key technical bottlenecks: First, semantic logic deviations often occur in the simulation model files generated by LLMs, mainly due to the insufficient embedding of building domain knowledge bases and energy consumption calculation rules; Second, the model has insufficient parsing ability for the implicit spatial topological relationships and building component constraint conditions in natural language instructions, easily leading to errors in geometric model generation; Third, existing methods do not construct a cross-modal data processing mechanism and are difficult to collaboratively process building drawing data and text description information, restricting the fusion application of multi-source heterogeneous data.

[0004] In the prior art, the interaction paradigm of traditional BEM tools relies on manual modeling driven by expert experience, with bottlenecks in efficiency and scalability, becoming a key obstacle restricting the implementation of intelligent building design and low-carbon technologies. Summary of the Invention

[0005] Based on this, it is necessary to provide an automated building energy consumption modeling method based on a large language model for the above technical problems. By directly converting natural language descriptions into building energy consumption models, it significantly reduces the modeling workload and reduces the dependence on professional knowledge and simulation software during the modeling process.

[0006] In a first aspect, the present application provides an automated building energy consumption modeling method based on a large language model, including: Obtain the natural language requirement description input by the client, and perform domain semantic analysis on the requirement description based on the natural language model to extract modeling parameters; the requirement description includes building space attributes; Input the modeling parameters into the building large language model to generate a standardized modeling instruction set that conforms to the syntax specification of the target building energy consumption simulation engine; among them, the building large language model is obtained by fine-tuning the pre-trained large language model with building domain professional Q&A corpora; Call the interface of the target building energy consumption simulation engine to generate simulation instructions, and the simulation instructions are used to instruct the target building energy consumption simulation engine to output simulation results based on the standardized modeling instruction set; the simulation results include the building model file and the key indicators of the building model file.

[0007] In one embodiment, the training method of the large language model fine-tuned with building domain professional Q&A corpora includes the following steps: S1: Obtain the fine-tuning dataset, and the fine-tuning dataset includes natural language description statements and a standardized modeling instruction set; S2: Map the byte pair encoding vectors of the fine-tuning dataset into matrices, perform matrix operations on the fine-tuning dataset using the following formula, and obtain the attention feature matrix using the softmax function: ; Among them, is the query matrix, is the key-value matrix, is the value matrix, is the dimension of the query matrix and the key-value matrix; S3: Split the query matrix, key-value matrix, and value matrix along the feature dimension into multiple independent subspaces, perform multi-head attention parallel computing on the multiple independent subspaces to obtain a feature tensor including multi-dimensional building modeling features; concatenate the feature tensors output by each independent subspace and project to obtain the fused modeling feature representation of the attention layer; among them, each independent subspace is used to learn different modeling dimension features; S4: Input the fused modeling feature representation into the feed-forward neural network, and obtain the non-linear transformation output through the fully connected layer and activation function of the feed-forward neural network; perform residual connection on the fused modeling feature representation and the non-linear transformation output to obtain the residual result; perform layer normalization on the residual result to obtain the normalized feature vector; S5: Decode the normalized feature vector to obtain the generated instruction set, construct a loss function by comparing the syntax tree structure difference between the generated instruction set and the standard instruction, and obtain the loss value, and drive the backpropagation optimization of the model parameters; S6: Repeat steps S2 to S5 until the loss value is less than the preset value to obtain the building large language model fine-tuned with building domain professional Q&A corpora.

[0008] In one of the embodiments, the method further includes the following steps: S1.1: Sample combinations of different building parameters according to the Latin hypercube orthogonal sampling strategy, and generate a parameter combination sample set in the multi-dimensional parameter space of building modeling. The parameter combination sample set includes the combination of the standardized modeling instruction set and the corresponding building parameters, which is used to indicate the corresponding building model descriptions with different parameter settings; S1.2: Establish a connection between the standardized modeling instruction set and the natural language description based on the parameter combination sample set to obtain a fine-tuning data set.

[0009] Preferably, before performing domain semantic analysis on the requirement description based on the natural language model to extract modeling parameters, it further includes: Obtain a set of modeling requirement parameters at different levels, where the levels are at least divided into two levels; among them, the set of modeling requirement parameters at the first level includes the geometric shape parameters of the building base; the set of modeling requirement parameters at the second level includes the attributes and detail parameters of the first level; the detail parameters include at least one of window position, internal load, enclosure structure, equipment system parameters, and dynamic control parameters; Perform integrity check based on the modeling requirement parameters corresponding to the levels and the requirement description. If the requirement description cannot cover the modeling requirement parameters corresponding to the levels, generate a first prompt message, which is used to prompt the user to input the missing modeling requirement parameters.

[0010] Further, before performing domain semantic analysis on the requirement description based on the natural language model to extract modeling parameters, it further includes: Perform lexical-semantic joint analysis on the natural language description input by the user to identify noises and classify the noise types; the noise types include spelling mistakes, omissions, and redundancies; Perform differential noise processing according to the noise types to obtain corrected data; Generate a requirement description based on the corrected data.

[0011] Further, the building large language model processes the undefined requirement description through an adaptive learning mechanism, including: Extract implicit building semantic elements from the undefined format requirement description input by the user side to generate a structured semantic element set; Generate a candidate modeling instruction set based on the semantic element set, and call the syntax verification interface of the simulation engine to detect the feedback signal of the instruction set; the feedback signal includes logical conflicts and format errors; According to the feedback signal returned by the syntax verification interface, dynamically adjust the weight parameters of the model decoder to obtain a corrected instruction; store the corrected instruction and the corresponding prompt format features in the fine-tuning data set to form an extensible format-rule mapping relationship, which is used to process the undefined format requirement description.

[0012] Further, after generating a simulation instruction by invoking the interface of the target building energy consumption simulation engine, it further includes: Obtaining visualization requirements and obtaining visualization results based on a multimodal visualization mapping strategy; the multimodal visualization mapping strategy includes at least one of temporal evolution, spatial distribution, and correlation analysis.

[0013] In a second aspect, the present application also provides an automated building energy consumption modeling system based on a large language model, including: A natural language processing module, configured to obtain a natural language requirement description input by a user terminal; perform domain semantic analysis on the requirement description based on a natural language model to extract modeling parameters; the requirement description includes building space attributes; A large language model fine-tuning module, configured to input the modeling parameters into a building large language model to generate a standardized modeling instruction set that conforms to the syntax specification of the target building energy consumption simulation engine; wherein, the building large language model is fine-tuned with professional Q&A corpus in the building field; A simulation engine interface module, configured to invoke the interface of the target building energy consumption simulation engine to generate a simulation instruction, and the simulation instruction is used to instruct the target building energy consumption simulation engine to output a simulation result based on the standardized modeling instruction set; the simulation result includes a building model file and key indicators of the building model file.

[0014] In a third aspect, the present application also provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, it implements the above-mentioned automated building energy consumption modeling method based on a large language model.

[0015] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the method as described above.

[0016] The above-mentioned automated building energy consumption modeling method based on a large language model extracts modeling parameters from the unstructured natural language description input by the user through a natural language model, and converts them into a standardized instruction set that conforms to the syntax specification of the building energy consumption simulation engine through a large language model fine-tuned with professional Q&A corpus in the building field. The interface of the target building energy consumption simulation engine is invoked, and the standardized instruction set is used to generate a simulation instruction to obtain a simulated building model file and its key indicators. The above method breaks through the strong dependence of traditional BEM tools on professional modeling knowledge and simulation syntax, reduces the manual modeling error rate through automated parameter extraction and instruction generation, lowers the modeling threshold, supports real-time response of energy consumption simulation in the rapid iteration of building design schemes, and effectively solves the technical implementation obstacles in the fields of intelligent building design and low-carbon transformation. Description of the Drawings

[0017] To more clearly illustrate the technical solutions in the embodiments of the present application or in the related art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the related art. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0018] Figure 1 Schematic flow diagram of an automated building energy consumption modeling method based on a large language model provided by an embodiment of the present invention; Figure 2 Mapping example of natural language description and IDF file; Figure 3 Schematic structural diagram of an automated building energy consumption modeling system based on a large language model provided by an embodiment of the present invention. Detailed implementation manners

[0019] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the following further details the present application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0020] First, a brief introduction is made to the terms involved in the embodiments of the present application.

[0021] Building energy consumption modeling refers to the process of simulating and analyzing the energy consumption situation of a building during its use through mathematical models and computer technologies, so as to predict the building energy consumption situation.

[0022] A large language model is a deep learning model trained using a large amount of text data, aiming to understand and generate natural language text. Large language models play an important role in the field of natural language processing (NLP) and are widely used in various tasks such as text generation, machine translation, sentiment analysis, and question answering systems. These models are usually based on deep learning technologies and can capture the complexity and diversity of language. Large language models usually adopt neural network structures, are trained using large-scale text data, and learn the grammar, semantics, and context information in the text data to generate a model with certain language capabilities. The training process of large language models usually includes two stages: pre-training and fine-tuning. The pre-training stage is to train on a large amount of text data to learn various patterns and structures of the language; the fine-tuning stage is to optimize the model according to specific tasks to improve its performance on specific tasks.

[0023] According to the above-mentioned noun explanations, the implementation environment of the automated building energy consumption modeling method based on a large language model provided by the embodiments of this application is described. Schematically, this implementation environment includes: an interaction terminal, a processor, and a domain knowledge storage array. Among them, the interaction terminal can be a voice acquisition sensor or a text input device; the processor includes, but is not limited to, a central processing unit, a multi-core processor, or an artificial intelligence chip, etc.; the domain knowledge storage array can be a distributed storage system or a centralized storage system, which is not limited here.

[0024] Combined with the above-mentioned noun explanations and implementation environment, the application scenarios of the embodiments of this application are described. The automated building energy consumption modeling method based on a large language model provided in the embodiments of this application can be applied to, but is not limited to, the following scenarios: In the scenario of rapid energy efficiency iteration design of building schemes, building engineers describe the building form through natural language, such as "L-shaped five-story office building, with 40% of the south-facing glass curtain wall". The system automatically analyzes the spatial topological relationship and generates a parametric model, and synchronously outputs the cloud maps of the cooling and heating load distributions of different window-wall ratio schemes, supporting the design team to conduct energy consumption sensitivity analysis in the initial stage of the scheme.

[0025] In the scenario of auxiliary decision-making for energy conservation renovation of existing buildings, property managers input descriptions of the building's current situation. The model automatically completes the missing envelope structure parameters and generates an energy consumption comparison report for multiple renovation schemes to optimize the priority of renovation investment.

[0026] In the scenario of regional energy planning simulation and deduction, the urban planning department submits the text of the area planning, batch generates the energy consumption baseline models of typical building clusters, couples the configuration parameters of regional energy stations, and dynamically simulates the carbon emission trajectories under different renewable energy penetration rates.

[0027] Schematically, the automated building energy consumption modeling method based on a large language model provided by the embodiments of this application can also be applied to other application scenarios. Only examples are given here, and the specific application scenarios are not limited.

[0028] In an exemplary embodiment, as Figure 1 shown, an automated building energy consumption modeling method based on a large language model is provided, including the following steps 101 to 103, where: Step 101, obtain the natural language requirement description input by the user side, and perform domain semantic analysis on the requirement description based on the natural language model to extract modeling parameters; the requirement description includes building space attributes.

[0029] Specifically, it receives the requirement description in natural language input by the user and performs domain semantic analysis to extract modeling parameters. For example, for the following natural language description input by the user: "Simulate a building that is 50 meters long, 30 meters wide, and 10 meters high, with a window-wall ratio of 0.4.", the key modeling parameters are extracted: length 50 meters, width 30 meters, height 10 meters, window-wall ratio (WWR) 0.4, and they are converted into structured modeling instructions. The user can describe parameters such as the geometric shape of the building, window positions, and internal loads in natural language.

[0030] Step 102: Input the modeling parameters into the building large language model to generate a standardized modeling instruction set that conforms to the syntax specification of the target building energy consumption simulation engine. Among them, the building large language model is obtained by fine-tuning the pre-trained large language model with professional Q&A corpora in the building field.

[0031] Specifically, the modeling parameters are converted into structured modeling instructions, and through the building large language model fine-tuned with professional Q&A corpora in the building field, an industrial document format file required by the target building energy consumption simulation engine (such as EnergyPlus, DeST, etc.) is generated. For example, the building large language model obtained by fine-tuning the pre-trained large language model with professional Q&A corpora in the building field converts the modeling parameters into the IDF file required by EnergyPlus. The fine-tuning process uses a specific dataset in the building modeling field to ensure that the model can accurately understand the requirements of the building modeling task.

[0032] Step 103: Invoke the interface of the target building energy consumption simulation engine to generate simulation instructions, which are used to instruct the target building energy consumption simulation engine to output simulation results based on the standardized modeling instruction set; the simulation results include the building model file and the key indicators of the building model file.

[0033] Specifically, by invoking the API interface provided by the target building energy consumption simulation engine, the standardized modeling instruction set is passed to the target simulation engine, and the target simulation engine performs calculations and simulations according to these instructions to generate simulation instructions. For example, by using a Python script to call the API of the EnergyPlus simulation engine, during the simulation process, the simulation engine will read the parameters in the instruction set, perform energy consumption calculations according to the preset algorithms and models, and finally output simulation results, including a detailed building model file (such as an IDF file containing information such as the building geometry, internal space division, and equipment configuration) and the key indicators of the building model file, such as the total annual energy consumption, energy consumption distribution in different seasons, and consumption ratios of various types of energy (electricity, gas, etc.).

[0034] The above-mentioned automated building energy consumption modeling method based on large language models extracts modeling parameters from the description in the unstructured natural language input by the user through a natural language model, and converts them into a standardized instruction set that conforms to the syntax specification of the building energy consumption simulation engine through a large language model fine-tuned with professional Q&A corpora in the building field. The interface of the target building energy consumption simulation engine is called, and the standardized instruction set is used to generate simulation instructions to obtain the simulated building model file and its key indicators. The above method breaks through the strong dependence of traditional BEM tools on professional modeling knowledge and simulation syntax, reduces the manual modeling error rate through automated parameter extraction and instruction generation, lowers the modeling threshold, supports real-time response of energy consumption simulation in the rapid iteration of building design schemes, and effectively solves the technical implementation obstacles in the fields of intelligent building design and low-carbon transformation.

[0035] In one embodiment, the training method of the large language model fine-tuned with professional Q&A corpora in the building field may include the following steps: S1: Obtain a fine-tuning data set, which includes natural language description statements and a standardized modeling instruction set.

[0036] Exemplarily, please refer to Figure 2 the provided mapping example of natural language description and IDF file. The fine-tuning data set covers parameter combinations such as different building geometries, window-wall ratios, internal loads, etc. The sample pairs are composed of corresponding natural language descriptions and IDF files.

[0037] S2: Map the byte pair encoding vectors of the fine-tuning data set into matrices, perform matrix operations on the fine-tuning data set using the following formula, and obtain the attention feature matrix using the softmax function: ; where is the query matrix, is the key-value matrix, is the value matrix, is the dimension of the query matrix and the key-value matrix.

[0038] Exemplarily, a large language model with an attention module as the core is adopted to construct a query matrix, a key-value matrix, and a value matrix. Among them, the query matrix represents specific information that the model focuses on; the key-value matrix is the input feature that determines the content related to the query matrix; the value matrix is used to provide actual information content and can effectively focus on the most important information. Specifically, the self-attention mechanism allows each word to adjust its importance according to the context during the encoding process, which involves encoding the input with a query matrix and a key-value matrix of dimension and a value matrix of dimension Perform a dot product on the value matrices, and then apply a softmax function to obtain the weights of the values; in the building simulation scenario, the query matrix, key-value matrix, and value matrix can be understood as representing the impacts of different parameters on the simulation results in the downstream task (i.e., building modeling). For example, the impacts of heating, cooling, and electricity on a building.

[0039] S3: Split the query matrix, key-value matrix, and value matrix along the feature dimension into multiple independent subspaces, perform parallel multi-head attention calculations on the multiple independent subspaces to obtain a feature tensor including multi-dimensional building modeling features; concatenate the feature tensors output by each independent subspace and project to obtain the fused modeling feature representation of the attention layer; where each independent subspace is used to learn different modeling dimension features.

[0040] Specifically, use the multi-head attention mechanism to enhance the information capture ability of the model. The attention is divided into multiple heads to capture various information channels in the input data, especially when dealing with multiple types of input and prompt formats. Each head has a different representation type. Exemplarily, according to the architecture design and computing resources of the model, determine the number of heads in the multi-head attention mechanism, and evenly split the query matrix, key-value matrix, and value matrix into the corresponding number of independent subspaces according to the feature dimension. Taking 8 heads as an example, each subspace is responsible for processing 1 / 8 of the feature dimensions of the original matrix. In a parallel computing environment, let each independent subspace perform attention calculations simultaneously. Within each subspace, when calculating the attention weights, calculate the attention scores according to their respective query matrices and key-value matrices, and then normalize to obtain the attention distribution. The attention calculations in different subspaces will focus on different aspects of the input information. For example, some subspaces pay more attention to information related to the building space structure, and other subspaces focus on the energy consumption characteristics of building equipment. After the calculation is completed, concatenate the feature tensors output by each subspace along the dimension to form a large tensor containing multi-dimensional information, and project the concatenated tensor to a specified dimension through a linear projection layer to obtain the fused modeling feature representation of the attention layer, providing richer and more comprehensive feature information for subsequent model processing.

[0041] S4: Input the fused modeling feature representation into a feed-forward neural network, and obtain a non-linear transformation output through the fully connected layer and activation function of the feed-forward neural network; perform a residual connection on the fused modeling feature representation and the non-linear transformation output to obtain a residual result; perform layer normalization on the residual result to obtain a normalized feature vector.

[0042] Exemplarily, the attention layer fusion modeling feature representation is input into a feed-forward neural network. The fully connected layer of the feed-forward neural network initializes the weight matrix according to the prior knowledge and data characteristics in the construction field. For example, for the weights corresponding to features such as building orientation and thermal performance of the building envelope, which are closely related to building energy consumption, relatively large initial values can be assigned to enhance the model's learning ability for key information. Exemplarily, the ReLU function is selected as the activation function to perform a non-linear transformation on the output of the fully connected layer, enabling the model to learn complex non-linear relationships in the input data. A residual connection operation is performed, directly adding the input fusion modeling feature representation to the output after non-linear transformation, and layer normalization is performed on the result of the residual connection. The mean and variance of each sample in the feature dimension are calculated and normalized to obtain a normalized feature vector, so as to ensure that information can be effectively transmitted between different layers when the model depth increases, avoiding the problems of gradient disappearance and overfitting, and providing guarantee for the subsequent stable training of the model.

[0043] S5: Decode the normalized feature vector to obtain a generated instruction set, construct a loss function by comparing the syntactic tree structure difference degree between the generated instruction set and the standard instruction, and obtain a loss value to drive the backpropagation optimization of the model parameters.

[0044] Exemplarily, in the fine-tuning process, byte pair encoding is used to encode the dataset, and the model weights are adjusted through backpropagation to minimize the difference between the generated IDF file and the actual IDF file.

[0045] S6: Repeat steps S2 to S5 until the loss value is less than a preset value to obtain a large language model for construction fine-tuned with construction domain professional Q&A corpus.

[0046] Specifically, a preset loss value threshold is set. In each training iteration, steps S2 to S5 are repeated. During the training process, the model is regularly evaluated using a validation dataset, and the change trend of the loss value is observed. When the loss value is less than the preset value, it is considered that the model training has achieved a good effect, and the training is stopped to obtain a large language model for construction fine-tuned with construction domain professional Q&A corpus.

[0047] In one of the embodiments, the method may further include the following steps: S1.1: Sample combinations of different building parameters according to the Latin hypercube orthogonal sampling strategy to generate a parameter combination sample set in the multi-dimensional parameter space of building modeling. The parameter combination sample set includes the combination of a standardized modeling instruction set and corresponding building parameters, which is used to indicate the corresponding building model descriptions for different parameter settings.

[0048] Specifically, different building shapes can be defined according to the building geometry, such as rectangle, L-shape, U-shape, etc., and the parameter ranges such as side length and angle of each shape can be set; in terms of internal load changes, the parameter ranges such as personnel density, equipment power, and lighting power can be determined according to different building functions (such as residential, office, and commercial). Latin hypercube design sampling is used: the value range of each parameter is divided into multiple intervals, and a value is randomly selected from each parameter interval to form a parameter combination. For example, the building geometry is a rectangle with side lengths of 50 meters and 30 meters respectively, the window-to-wall ratio is 0.5, and the internal load is calculated according to the following formula: According to a set of parameters set by the office building standard, based on the extracted parameter combinations, professional building energy consumption simulation software, such as the parametric modeling tool that comes with EnergyPlus, is used to generate an IDF file that conforms to the EnergyPlus syntax specification. During the generation process, the software will automatically fill in the building geometry, envelope structure characteristics, internal heat gain and other information according to the parameter settings to complete the description of the corresponding building model. Through the above steps, a large number of parameter combinations and corresponding IDF files are generated, forming a data set containing descriptions of different building models with various parameter settings, that is, a parameter combination sample set.

[0049] S1.2: Based on the parameter combination sample set, a connection is established between the standardized modeling instruction set and the natural language description to obtain a fine-tuning dataset.

[0050] Exemplarily, for each parameter combination corresponding to the IDF file, the natural language description of the architectural model information contained therein can be used as a prompt to correspond the natural language description to the corresponding IDF file one by one to form a description-IDF sentence pair. The obtained sentence pairs are used as fine-tuning datasets for further training of the architectural language model that has been fine-tuned with professional question and answer corpus in the architectural field, so that the model can better understand the mapping relationship between natural language requirements and the standardized modeling instruction set (IDF file), thereby more accurately generating corresponding modeling instructions based on the natural language input by the user.

[0051] Preferably, before performing domain semantic analysis on the requirement description based on the natural language model to extract modeling parameters, the following steps may also be included: Step 104, obtaining a hierarchical set of modeling requirement parameters, which are divided into at least two levels; wherein the first level of the modeling requirement parameter set includes the geometric parameters of the building base; the second level of the modeling requirement parameter set includes the attributes and detail parameters of the first level; the detail parameters include at least one of the window position, internal load, enclosure structure, equipment system parameters, and dynamic control parameters.

[0052] Exemplarily, a database can be used to construct a hierarchical modeling requirement parameter set. The first level defines the geometric form parameters of the building base, including but not limited to the shape, length, width, height, and floor area of the building, and corresponding table structures are created in the database to store these parameters. For the modeling requirement parameter set of the second level, an associated table is created in the database and associated with the parameter table of the first level. Among them, the attribute parameters can include the use of the building, and different uses correspond to different energy consumption standards and modeling focuses. In terms of detail parameters, for the window position, record the coordinate positions, quantities, and sizes of the windows on each facade of the building; record the internal load parameters such as the personnel density, equipment power, and lighting power; record the enclosure structure parameters such as the wall material, insulation layer thickness, and roof structure; record the equipment system parameters such as the type of air conditioning system and heating method; record the dynamic control parameters such as the start and stop times of the equipment and the conditions for switching the operating mode.

[0053] Step 105, perform an integrity check based on the hierarchical corresponding modeling requirement parameters and requirement descriptions. If the requirement description cannot cover the hierarchical corresponding modeling requirement parameters, generate a first prompt message, which is used to instruct the user to input the missing modeling requirement parameters.

[0054] Exemplarily, an integrity check algorithm based on rule matching and semantic understanding can be used. When the user inputs a requirement description, key information is extracted, and the extracted information is compared with the hierarchical corresponding modeling requirement parameter set. If it is found that the requirement description cannot cover the hierarchical corresponding modeling requirement parameters, a first prompt message is generated according to the type and importance of the missing parameters. For example, if the window position parameter is missing, the prompt message is "The information related to the window position is not included in your requirement description. Please supplement the parameters such as the positions, quantities, and sizes of the windows on each facade of the building" to ensure the robustness of the model in case of missing input information. Furthermore, before performing domain semantic analysis on the requirement description based on the natural language model to extract modeling parameters, it can also include: Step 106, perform a combined lexical-semantic analysis on the natural language description input by the user to identify noise and classify the noise types; the noise types include spelling mistakes, omissions, and redundancies.

[0055] Specifically, the natural language processing toolkit can be used to perform word segmentation on the natural language description input by the user, perform part-of-speech tagging on each word to determine its part of speech, construct a semantic dependency graph with the help of a semantic analysis tool to analyze the semantic connections between words, compare each word with the standard vocabulary library, and if it is found that a certain word does not exist in the vocabulary library or has a very low similarity, mark it as a possible spelling mistake; check whether there is missing key parameter information in the natural language description, and if so, mark it as missing information; judge whether there are repetitive expressions or unnecessary modification information.

[0056] Step 107: Perform differential noise processing according to the noise type to obtain corrected data.

[0057] Exemplarily, for identified spelling mistakes, correction suggestions can be provided or automatically corrected according to the lexicon and context semantics; for missing parameter information, default parameter suggestions can be provided or the user can be prompted to supplement according to the existing requirement descriptions and modeling experience; for redundant information, it is deleted from the natural language description, and key information is retained to obtain the corrected data after noise processing.

[0058] Step 108: Generate a requirement description based on the corrected data.

[0059] Specifically, the words and information after noise processing are recombined according to reasonable grammar and semantic rules to generate a corrected requirement description.

[0060] Furthermore, the building large language model processes undefined requirement descriptions through an adaptive learning mechanism, including: Step 109: Extract implicit building semantic elements from the undefined format requirement description input by the user side to generate a structured set of semantic elements.

[0061] Specifically, basic text cleaning can be performed on the undefined format requirement description input by the user side to remove extra spaces, punctuation marks, word segmentation, etc. Through a dictionary containing common semantic elements in the building field, using named entity recognition technology and combining with a deep learning model, the segmented text is scanned to identify the building semantic elements therein. For example, for the description "That large shopping mall located in the city center has many windows", "shopping mall" can be identified as the building type, and "city center" as the building location-related element. The identified semantic elements are classified and sorted to obtain a structured set of semantic elements.

[0062] Step 110: Generate a candidate modeling instruction set based on the set of semantic elements, and call the syntax verification interface of the simulation engine to detect the feedback signal of the instruction set; the feedback signal includes logical conflicts and format errors.

[0063] Specifically, multiple candidate modeling instruction sets can be generated according to the structured set of semantic elements, combined with the learned building field knowledge and modeling rules. For example, according to the building type of "shopping mall" and the description of "many windows", instructions regarding window area, layout, etc. are generated, and the syntax verification interface of the target building energy consumption simulation engine is called to send the candidate modeling instruction set to this interface for detection. The simulation engine will conduct a detailed inspection of the instruction set and return a feedback signal, including logical conflicts (such as the specified window area in the instruction exceeding the building exterior wall area) and format errors (such as the syntax of the instruction not meeting the requirements of the simulation engine).

[0064] Step 111: Dynamically adjust the weight parameters of the model decoder according to the feedback signal returned by the syntax verification interface to obtain a correction instruction; store the correction instruction and the corresponding hint format feature in the fine-tuning data set to form an extensible format-rule mapping relationship, which is used to process requirement descriptions with undefined formats.

[0065] Specifically, according to the feedback signal returned by the syntax verification interface, use the backpropagation algorithm to dynamically adjust the weight parameters of the model decoder. After the weight parameters are adjusted, the model regenerates the instruction to obtain a correction instruction. The correction instruction can avoid the previously detected logical conflicts and format errors. Store the correction instruction and the corresponding hint format feature (i.e., the feature extracted after processing the user input of the requirement description with an undefined format) in the fine-tuning data set to form an extensible format-rule mapping relationship and enhance the robustness of the model under different input conditions.

[0066] Furthermore, after calling the interface of the target building energy consumption simulation engine to generate a simulation instruction, it may further include: Step 112: Obtain the visualization requirements and obtain the visualization results based on the multimodal visualization mapping strategy; the multimodal visualization mapping strategy includes at least one of temporal evolution, spatial distribution, and correlation analysis.

[0067] Exemplarily, after calling the simulation engine interface to generate a simulation instruction, the user's visualization requirements can be collected through an interactive interface to clarify whether they are concerned with the temporal change, spatial distribution, or variable correlation of energy consumption. If it is temporal evolution, extract the energy consumption data corresponding to the time span from the simulation data, which can be presented as a line chart; for spatial distribution requirements, match the energy consumption data with the building spatial location and display it through a borrowed map or floor plan; if it is a correlation analysis requirement, screen the relevant variable data, calculate the correlation, and present the relationship as a scatter plot to improve the visualization level of the simulation output and facilitate the user's understanding.

[0068] In one specific embodiment of the present application, the method can achieve the automatic modeling of a simple building model, and the specific steps are as follows: (1) Obtain the natural language description input by the user. For example, the user inputs the following natural language description: "Simulate a building with a length of 50 meters, a width of 30 meters, a height of 10 meters, and a window-wall ratio of 0.4." (2) Perform natural language processing and LLM fine-tuning on the natural language description. Parse the user input through the natural language processing module to extract the key modeling parameters: length 50 meters, width 30 meters, height 10 meters, window-wall ratio (WWR) 0.4. The system converts these parameters into structured modeling instructions and generates the IDF file required by EnergyPlus through the fine-tuned LLM.

[0069] (3) Invoke the simulation engine and output the results. By invoking the API of the EnergyPlus simulation engine, a building model is automatically generated and simulated. The simulation results include key indicators such as building energy consumption and indoor temperature, and the system presents the results to the user in a visual form.

[0070] (4) Conduct a robustness test on the natural language description input by the user. By introducing a noise processing mechanism, handle interferences such as spelling mistakes, omissions, and redundancies in the user input. For example, even if the user inputs "Simulate a building that is 50 meters long, 30 meters wide, and 10 meters high, with a window-wall ratio of 0.4 and a window height of 2 meters" (where "window height" is redundant information), the IDF file can still be correctly generated.

[0071] (5) Conduct result verification. The generated IDF file is completely matched with the simulation results, and the accuracy rate reaches 100%. The user can complete the modeling within 1 minute, significantly reducing the modeling workload.

[0072] In one specific embodiment of this application, this method can achieve automated modeling of complex building models, and the specific steps are as follows: (1) Obtain the natural language description input by the user. For example, the user inputs the following natural language description: "Simulate a building that is 100 meters long, 50 meters wide, and 20 meters high, with a window-wall ratio of 0.6, a window sill height of 4 meters, a window height of 16 meters, and a window frame width of 0.01 meters. The occupancy rate is 5 square meters per person, the lighting level is 10 watts per square meter, and the equipment power consumption is 20 watts per square meter." (2) Conduct natural language processing and LLM fine-tuning. Parse the user input through the natural language processing module to extract key modeling parameters: length (100 meters), width (50 meters), height (20 meters), window-wall ratio (0.6), window sill height (4 meters), window height (16 meters), window frame width (0.01 meters), occupancy rate (5 square meters per person), lighting level (10 watts per square meter), and equipment power consumption (20 watts per square meter). Convert these parameters into structured modeling instructions and generate the IDF file required by EnergyPlus through the fine-tuned LLM.

[0073] (3) Invoke the simulation engine and output the results. By invoking the API of the EnergyPlus simulation engine, a building model is automatically generated and simulated. The simulation results include key indicators such as building energy consumption and indoor temperature, and the system presents the results to the user in a visual form.

[0074] (4)Conduct robustness testing. By introducing a noise processing mechanism, it can handle interferences such as spelling mistakes, omissions, and redundancies in user input. For example, even if the user inputs "Simulate a building that is 100 meters long, 50 meters wide, and 20 meters high, with a window-wall ratio of 0.6, a window sill height of 4 meters, a window height of 16 meters, and a window frame width of 0.01 meters. The occupancy rate is 5 square meters per person, the lighting level is 10 watts per square meter, and the equipment power consumption is 20 watts per square meter." (where "window frame width" is redundant information), the system can still correctly generate the IDF file.

[0075] 5) Conduct result verification. The generated IDF file is exactly matched with the simulation results, and the accuracy rate reaches 100%. Users can complete the modeling within 1 minute, significantly reducing the modeling workload.

[0076] In summary, the automated building energy consumption modeling method based on a large language model provided by the embodiments of this application extracts modeling parameters from the description in the unstructured natural language input by the user through the natural language model, and improves the robustness of the model under different input conditions by introducing various prompt formats and a noise processing mechanism to handle interferences such as spelling mistakes, omissions, and redundancies; by constructing a fine-tuning data set including natural language description statements and a standardized modeling instruction set, fine-tuning the large language model based on the attention mechanism to obtain a building large language model fine-tuned with professional Q&A corpus in the building field, where the residual connection and layer normalization design ensure the stability of the model with complex parameter coupling relationships; through the building large language model, the modeling parameters are converted into a standardized instruction set that conforms to the syntax specification of the building energy consumption simulation engine, the interface of the target building energy consumption simulation engine is called, and the standardized instruction set is used to generate simulation instructions to obtain the simulation building model file and its key indicators; execute the multimodal visualization mapping strategy to obtain the visualization results.

[0077] This application realizes the following technical effects through an automated building energy consumption modeling method based on a large language model: (1) Improve modeling efficiency: Compared with manual modeling, the modeling workload is reduced by more than 95%. (2) Improve modeling accuracy: The generated building model file is exactly matched with the simulation results, and the accuracy rate can reach 100%. (3) Enhance robustness: The system can handle interferences such as different intonations, spelling mistakes, omissions, and redundancies, and the generated model file can still meet the simulation requirements. 4) User-friendly: Through the natural language interaction interface, users do not need to have professional building science knowledge and simulation software operation skills to quickly generate a building energy consumption model.

[0078] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0079] Based on the same inventive concept, an embodiment of the present application also provides a large language model-based automated building energy consumption modeling system for implementing the above-mentioned large language model-based automated building energy consumption modeling method. The implementation solutions provided by this system to solve problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the large language model-based automated building energy consumption modeling system provided below can refer to the limitations on the large language model-based automated building energy consumption modeling method in the above text, and will not be repeated here.

[0080] In an exemplary embodiment, as Figure 3 shown, a large language model-based automated building energy consumption modeling system 20 is provided, including: A natural language processing module 21, configured to obtain a natural language requirement description input by a user terminal; perform domain semantic analysis on the requirement description based on a natural language model to extract modeling parameters; the requirement description includes building space attributes.

[0081] A large language model fine-tuning module 22, configured to input the modeling parameters into a building large language model to generate a standardized modeling instruction set that conforms to the syntax specification of a target building energy consumption simulation engine; wherein, the building large language model is obtained by fine-tuning a pre-trained large language model with building domain professional Q&A corpora.

[0082] A simulation engine interface module 23, configured to call the interface of the target building energy consumption simulation engine to generate simulation instructions, and the simulation instructions are used to instruct the target building energy consumption simulation engine to output simulation results based on the standardized modeling instruction set; the simulation results include a building model file and key indicators of the building model file.

[0083] In one of the embodiments, the training method of the large language model fine-tuned with building domain professional Q&A corpora in the large language model fine-tuning module 22 may include the following steps: S1: Obtain a fine-tuning data set, which includes natural language description statements and a standardized modeling instruction set.

[0084] S2: Map the byte pair encoding vectors of the fine-tuning data set into a matrix, perform matrix operations on the fine-tuning data set using the following formula, and obtain an attention feature matrix using the softmax function: ; where is the query matrix, is the key-value matrix, is the value matrix, is the dimension of the query matrix and the key-value matrix.

[0085] S3: Split the query matrix, key-value matrix, and value matrix along the feature dimension into multiple independent subspaces, perform multi-head attention parallel computing on the multiple independent subspaces to obtain a feature tensor including multi-dimensional building modeling features; concatenate the feature tensors output by each independent subspace and project to obtain a fused modeling feature representation of the attention layer; where each independent subspace is used to learn different modeling dimension features.

[0086] S4: Input the fused modeling feature representation into a feed-forward neural network, and obtain a non-linear transformation output through the fully connected layer and activation function of the feed-forward neural network; perform residual connection on the fused modeling feature representation and the non-linear transformation output to obtain a residual result; perform layer normalization on the residual result to obtain a normalized feature vector.

[0087] S5: Decode the normalized feature vector to obtain a generated instruction set, construct a loss function by comparing the syntactic tree structure difference between the generated instruction set and the standard instruction, and obtain a loss value to drive the backpropagation optimization of the model parameters.

[0088] S6: Repeat steps S2 to S5 until the loss value is less than a preset value to obtain a large language model for building fine-tuned with building domain professional Q&A corpus.

[0089] In one embodiment, the training method of the large language model for building fine-tuned with building domain professional Q&A corpus in the large language model fine-tuning module 22 may further include the following steps: S1.1: Sample combinations of different building parameters according to the Latin hypercube orthogonal sampling strategy to generate a parameter combination sample set in the building modeling multi-dimensional parameter space. The parameter combination sample set includes combinations of standardized modeling instruction sets and corresponding building parameters, which are used to indicate the corresponding building model descriptions for different parameter settings.

[0090] S1.2: Establish a connection between the standardized modeling instruction set and the natural language description based on the parameter combination sample set to obtain a fine-tuning data set.

[0091] Preferably, the system may further include a robustness enhancement module 24, and the robustness enhancement module 24 includes the following units: A hierarchical requirement acquisition unit, configured to acquire a set of modeling requirement parameters at different levels, where the levels are at least divided into two levels; among them, the set of modeling requirement parameters at the first level includes geometric shape parameters of a building base; the set of modeling requirement parameters at the second level includes attributes and detail parameters at the first level; the detail parameters include at least one of window position, internal load, enclosure structure, equipment system parameters, and dynamic control parameters.

[0092] An integrity check unit, configured to perform an integrity check based on the modeling requirement parameters and requirement descriptions corresponding to the levels. If the requirement descriptions cannot cover the modeling requirement parameters corresponding to the levels, a first prompt message is generated, and the first prompt message is used to prompt the user to input the missing modeling requirement parameters.

[0093] Further, the system may further include a robustness enhancement module 24, and the robustness enhancement module 24 includes the following units: A noise recognition unit, configured to perform a combined lexical and semantic analysis on the natural language description input by the user, identify the noise and classify the noise type; the noise type includes spelling mistakes, omissions, and redundancies.

[0094] A data correction unit, configured to perform differential noise processing according to the noise type to obtain corrected data.

[0095] A requirement description generation unit, configured to generate a requirement description based on the corrected data.

[0096] Further, the system may further include a robustness enhancement module 24, and the robustness enhancement module 24 includes the following units: An undefined format processing unit, configured to extract implicit building semantic elements from the requirement description with an undefined format input by the user terminal, and generate a structured set of semantic elements.

[0097] An error feedback unit, configured to generate a candidate modeling instruction set based on the set of semantic elements, and call the syntax verification interface of the simulation engine to detect the feedback signal of the instruction set; the feedback signal includes logical conflicts and format errors.

[0098] An adaptive adjustment unit, configured to dynamically adjust the weight parameters of the model decoder according to the feedback signal returned by the syntax verification interface to obtain a corrected instruction; store the corrected instruction and the corresponding prompt format features into a fine-tuning data set to form an extensible format-rule mapping relationship, and the format-rule mapping relationship is used to process the requirement description with an undefined format.

[0099] Further, the simulation engine interface module 23 may further include: A visualization unit for obtaining visualization requirements and obtaining visualization results based on a multimodal visualization mapping strategy, where the multimodal visualization mapping strategy includes at least one of temporal evolution, spatial distribution, and correlation analysis.

[0100] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of an automated building energy consumption modeling method based on a large language model as described above are implemented.

[0101] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0102] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can refer to the partial descriptions of the method embodiments. The device embodiments described above are only illustrative. The components described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present disclosure solution. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0103] The above embodiments only represent several implementation manners of the embodiments of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the embodiments of the application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the embodiments of the present application, several modifications and improvements can be made, and these all belong to the protection scope of the embodiments of the present application.

Claims

1. An automated building energy consumption modeling method based on a large language model, characterized in that: The method comprises: Obtaining a natural language demand description input by a user, and performing domain semantic analysis on the demand description based on a natural language model to extract modeling parameters; the demand description includes building space attributes; Input the modeling parameters into a building language model to generate a standardized modeling instruction set that meets the syntax specification of the target building energy consumption simulation engine; wherein the building language model is a pre-trained language model obtained by fine-tuning the professional question-and-answer corpus in the field of architecture; The interface of the target building energy consumption simulation engine is called to generate simulation instructions, wherein the simulation instructions are used to instruct the target building energy consumption simulation engine to output simulation results based on the standardized modeling instruction set; the simulation results include a building model file and key indicators of the building model file.

2. The method according to claim 1, characterized in that The pre-trained large language model is fine-tuned with professional question-answer corpus in the field of architecture, including the following steps: S1: Acquire a fine-tuning dataset, wherein the fine-tuning dataset includes the natural language description sentence and the standardized modeling instruction set; S2: Map the byte pair encoding vector of the fine-tuning dataset into a matrix, use the following formula to perform matrix operations on the fine-tuning dataset, and use the softmax function to obtain the attention feature matrix: ； in, is the query matrix, is the key-value matrix, is the value matrix, are the dimensions of the query matrix and the key-value matrix; S3: Split the query matrix, the key-value matrix and the value matrix into multiple independent subspaces along the feature dimension, perform multi-head attention parallel calculation on the multiple independent subspaces, and obtain a feature tensor including multi-dimensional building modeling features; concatenate the feature tensors output by each independent subspace, and project them to obtain a fusion modeling feature representation of the attention layer; wherein each independent subspace is used to learn different modeling dimension features; S4: inputting the fusion modeling feature representation into a feedforward neural network, obtaining a nonlinear transformation output through a fully connected layer and an activation function of the feedforward neural network; connecting the fusion modeling feature representation and the nonlinear transformation output residual to obtain a residual result; performing layer normalization on the residual result to obtain a normalized feature vector; S5: decoding the normalized feature vector to obtain a generated instruction set, constructing a loss function and obtaining a loss value by comparing the syntax tree structure difference between the generated instruction set and the standard instruction, and driving the back propagation optimization of the model parameters; S6: Repeat steps S2 to S5 until the loss value is less than a preset value, thereby obtaining the large architectural language model fine-tuned by professional question-and-answer corpus in the architectural field.

3. The method according to claim 2, characterized in that The method further comprises the following steps: S1.1: Sampling different combinations of the building parameters according to a Latin hypercube orthogonal sampling strategy to generate a parameter combination sample set in a building modeling multidimensional parameter space, wherein the parameter combination sample set includes a combination of the standardized modeling instruction set and the corresponding building parameters, and is used to indicate corresponding building model descriptions of different parameter settings; S1.2: Establish a connection between the standardized modeling instruction set and the natural language description based on the parameter combination sample set to obtain the fine-tuning data set.

4. The method according to claim 1, characterized in that: Before performing domain semantic analysis on the requirement description based on the natural language model to extract modeling parameters, the method further includes: Acquire a hierarchical set of modeling requirement parameters, wherein the hierarchical set is divided into at least two levels; wherein the modeling requirement parameter set of the first level includes geometric parameters of the building base; the modeling requirement parameter set of the second level includes attributes and detail parameters of the first level; the detail parameters include at least one of window position, internal load, enclosure structure, equipment system parameters, and dynamic control parameters; An integrity check is performed based on the modeling requirement parameters corresponding to the level and the requirement description. If the requirement description cannot cover the modeling requirement parameters corresponding to the level, a first prompt message is generated, wherein the first prompt message is used to instruct the user to input the missing modeling requirement parameters.

5. The method according to claim 1, characterized in that Before performing domain semantic analysis on the requirement description based on the natural language model to extract modeling parameters, the method further includes: Performing a lexical-semantic joint analysis on the natural language description input by the user, identifying noise and classifying noise types; the noise types include spelling errors, omissions and redundancies; Performing differential noise processing according to the noise type to obtain corrected data; The requirement description is generated based on the correction data.

6. The method according to claim 2, characterized in that The architectural language model processes the undefined requirement description through an adaptive learning mechanism, including: Extracting implicit architectural semantic elements from the requirement description in an undefined format input by the user end, and generating a structured semantic element set; Generate a candidate modeling instruction set based on the semantic element set, and call the syntax verification interface of the simulation engine to detect the feedback signal of the instruction set; the feedback signal includes logic conflicts and format errors; According to the feedback signal returned by the syntax verification interface, the weight parameters of the model decoder are dynamically adjusted to obtain correction instructions; the correction instructions and the corresponding prompt format features are stored in the fine-tuning data set to form an extensible format-rule mapping relationship, and the format-rule mapping relationship is used to process the requirement description in the non-predefined format.

7. The method according to claim 1, characterized in that After the interface of the target building energy consumption simulation engine is called to generate the simulation instruction, the method further includes: Obtain visualization requirements and obtain visualization results based on a multimodal visualization mapping strategy; the multimodal visualization mapping strategy includes at least one of temporal evolution, spatial distribution and association analysis.

8. An automated building energy consumption modeling system based on a large language model, characterized in that: include: A natural language processing module is used to obtain the natural language requirement description input by the user; Performing domain semantic analysis on the requirement description based on a natural language model to extract modeling parameters; The requirement description includes building space attributes; A large language model fine-tuning module is used to input the modeling parameters into the building large language model to generate a standardized modeling instruction set that conforms to the grammatical specification of the target building energy consumption simulation engine; wherein the building large language model is obtained by fine-tuning the professional question-and-answer corpus in the field of architecture; The simulation engine interface module is used to call the interface of the target building energy consumption simulation engine and generate simulation instructions, wherein the simulation instructions are used to instruct the target building energy consumption simulation engine to output simulation results based on the standardized modeling instruction set; the simulation results include a building model file and key indicators of the building model file.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images