A construction simulation configuration document generation method and device
By performing structured parsing and event sequence processing on the target text of construction simulation, a construction simulation configuration document is generated, which solves the problem of opaque construction simulation modeling logic and improves the credibility and efficiency of simulation calculation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA THREE GORGES CORPORATION
- Filing Date
- 2026-05-18
- Publication Date
- 2026-07-24
AI Technical Summary
The logic of construction simulation modeling is not directly displayed, which reduces the credibility of simulation modeling calculations.
By performing structured semantic parsing on the simulation target text, a set of simulation target triples is generated, a construction event sequence template is constructed, construction events are extracted and instantiated, and finally converted into a construction simulation configuration document to display the simulation inference logic and parameters.
It enhances the credibility and interpretability of construction simulation modeling, ensures the transparency of modeling logic, and improves the efficiency and accuracy of simulation calculations.
Smart Images
Figure CN122452533A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of construction simulation technology, specifically to a method and apparatus for generating construction simulation configuration documents. Background Technology
[0002] The value of construction simulation lies in predicting potential problems and risks during construction through virtual simulations of the construction process. Currently, simulation modeling mainly relies on engineers to create models based on engineering data and their experience. However, the modeling logic is not directly displayed, which reduces the reliability of the simulation calculations. Summary of the Invention
[0003] This invention provides a method and apparatus for generating construction simulation configuration documents to solve the problem that the logic of construction simulation modeling is not directly displayed, which reduces the credibility of simulation modeling calculations.
[0004] In a first aspect, the present invention provides a method for generating construction simulation configuration documents, the method comprising: Obtain the simulation target text under the target construction simulation scenario, perform structured semantic parsing on the simulation target text, and obtain the simulation target triple set; Construct a construction event sequence template; Construction events are extracted based on the simulation target triplet set and the construction event sequence template to obtain the event sequence set; The event sequence set is instantiated using construction event sequence parameters to obtain construction event sequence instances; Convert construction event sequence instances into construction simulation configuration documents.
[0005] This invention provides a method for generating construction simulation configuration documents. By performing structured semantic parsing on the simulation target text, a set of simulation target triples is obtained. Based on the set of simulation target triples and a construction event sequence template, construction events are extracted. The extracted event sequence set is then instantiated with construction event sequence parameters, and the construction event sequence instances are converted into construction simulation configuration documents. The construction simulation configuration documents can intuitively display the calculation logic, simulation parameters, event triggering rules, and decision options to be evaluated in the simulation, avoiding black-box settings and improving the credibility of construction simulation modeling and calculation.
[0006] In one alternative implementation, a construction event sequence template is constructed, including: Define construction event types; The construction event types are used as nodes, and the event triggering relationships are used as directed edges. A causal relationship graph is constructed based on the nodes and directed edges. A constrained depth-first search is performed on the causal relationship graph to obtain the causal path; Convert the causal path into a construction event sequence template.
[0007] This invention provides a method for generating construction simulation configuration documents. By defining construction event types and constructing a causal relationship graph, the triggering logic and sequential constraints between construction procedures are transformed into a traceable structured model. This significantly improves the interpretability of the modeling process, solves the problems of opaque and difficult-to-verify modeling logic, and provides an interpretable logical foundation for the subsequent generation of construction simulation configuration documents. Furthermore, by performing a constrained depth-first search on the causal relationship graph, the compliance and rationality of the construction process are ensured, and the causal path is transformed into a construction event sequence template, thereby improving the efficiency and scalability of construction simulation modeling.
[0008] In one alternative implementation, before performing a constrained depth-first search on the causal graph to obtain the causal path, the method further includes: Perform global connectivity detection on the causal relationship graph and optimize the causal relationship graph based on the global connectivity detection results.
[0009] This invention provides a method for generating construction simulation configuration documents. By performing global connectivity detection and optimization on the causal relationship graph, defects can be identified in advance, ensuring the complete connectivity of the construction process chain. At the same time, the graph structure of the causal relationship graph is simplified, improving the efficiency of subsequent path search, avoiding invalid simulation modeling and event sequence template failure, and significantly improving the reliability, versatility and generation efficiency of construction event sequence templates.
[0010] In one optional implementation, construction events are extracted based on the simulation target triplet set and the construction event sequence template to obtain an event sequence set, including: Map the analysis type field in the simulation target triplet set to engineering indicator keywords; The impact state variables of each event in the construction event sequence template are compared one by one with the keywords of the engineering indicators. Based on the comparison results, the construction event sequence template is removed to obtain the first event set. Based on the engineering semantic features corresponding to the first event set and the construction semantic features corresponding to the target object fields of the simulation target triplet set, the semantic coverage is calculated. The first event set is semantically filtered based on semantic coverage to obtain the second event set; Events are extracted from the causal path to obtain a subset of causal paths; the initial triggering events in the subset of causal paths are events from the second event set. The causal paths in the subset of causal paths are sorted, and the set of event sequences is determined based on the sorting results.
[0011] This invention provides a method for generating construction simulation configuration documents. It maps the analysis type of the simulation target triplet to engineering indicator keywords, then eliminates irrelevant events by comparing them with template-influenced state variables, ensuring that the selected event set directly serves the analysis needs of the simulation target and avoiding interference from invalid events. By calculating semantic coverage, a second semantic filter is applied to the events, ensuring that the selected events are semantically perfectly aligned with the construction target, avoiding deviations where procedures match but semantics do not. The second set of semantically filtered events is then used as the initial trigger events to extract causal paths, ensuring that the generated causal paths start entirely from the simulation target, avoiding the generation of invalid paths that deviate from the requirements, while preserving the complete construction logic chain. The causal paths are sorted, and the event sequence set is determined based on the sorting results, reducing subsequent manual screening costs. Through a multi-round screening mechanism, the method accurately matches the construction simulation target requirements, significantly improving the matching degree between event sequences and simulation targets, as well as modeling efficiency and result reliability.
[0012] In one optional implementation, the event sequence set is instantiated using construction event sequence parameters to obtain construction event sequence instances, including: Iterate through the construction events in the event sequence set and extract the placeholders for the parameters to be assigned. Obtain parameter configuration data, and assign values to multiple instance parameters based on the placeholders of the parameters to be assigned, thereby obtaining construction event sequence instances.
[0013] This invention provides a method for generating construction simulation configuration documents. By extracting placeholders for parameters to be assigned in the construction event sequence and assigning values to multiple instances of parameters based on parameter configuration data, the logical definition of construction events and engineering parameters are decoupled. This method quickly generates multiple construction event sequence instances, significantly improving the efficiency, consistency, and multi-scenario adaptability of construction simulation modeling, and reducing manual modeling errors and maintenance costs.
[0014] In one alternative implementation, the construction event sequence instances are converted into a construction simulation configuration document, including: Obtain basic information about the construction project, and generate global configuration data based on the simulation target triplet set and the basic information about the construction project. Initial state data is determined based on the set of triplets of the simulation target. Based on construction event sequence instances, determine event planning data and branch logic combination data respectively; The construction simulation configuration document is generated based on global configuration data, initial state data, event plan data, and branch logic combination data.
[0015] This invention provides a method for generating construction simulation configuration documents. By constructing global configuration data, initial state data, event plan data, and branch logic combination data in layers, it achieves structured organization of all elements of construction simulation and fusion of multi-source data. This results in a clear and logical construction simulation configuration document, solving the problems of missing elements, logical confusion, and poor platform adaptability in simulation modeling. It significantly improves the accuracy, executability, and versatility of construction simulation modeling.
[0016] Secondly, the present invention provides a construction simulation configuration document generation device, the device comprising: The structured semantic parsing module is used to obtain the simulation target text under the target construction simulation scenario, perform structured semantic parsing on the simulation target text, and obtain the simulation target triple set; The building module is used to construct construction event sequence templates; The extraction module is used to extract construction events based on the simulation target triplet set and the construction event sequence template to obtain an event sequence set. The instantiation processing module is used to instantiate the event sequence set with construction event sequence parameters to obtain construction event sequence instances. The conversion module is used to convert construction event sequence instances into construction simulation configuration documents.
[0017] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the construction simulation configuration document generation method of the first aspect or any corresponding embodiment described above.
[0018] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the construction simulation configuration document generation method of the first aspect or any corresponding embodiment described above.
[0019] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute the construction simulation configuration document generation method of the first aspect or any corresponding embodiment described above. Attached Figure Description
[0020] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0021] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first step of a construction simulation configuration document generation method according to an embodiment of the present invention. Figure 3 This is a schematic diagram of a second process for generating a construction simulation configuration document according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the third process of a construction simulation configuration document generation method according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the fourth process of a construction simulation configuration document generation method according to an embodiment of the present invention; Figure 6 This is a structural block diagram of a construction simulation configuration document generation device according to an embodiment of the present invention; Figure 7 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation
[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0023] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.
[0024] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.
[0025] As an optional application scenario of this invention, such as Figure 1 As shown, the construction simulation configuration document generation system may include at least one terminal device and at least one server. Figure 1The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.
[0026] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.
[0027] This invention provides a method for generating construction simulation configuration documents, which automatically generates construction simulation configuration documents based on the characteristics of the engineering project and the simulation objectives, covering the automated generation of elements such as simulation scene parameter configuration and construction event sequence arrangement.
[0028] According to an embodiment of the present invention, a method for generating construction simulation configuration documents is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0029] This embodiment provides a method for generating construction simulation configuration documents, which can be used in the aforementioned terminal devices. Figure 2 This is a flowchart of a construction simulation configuration document generation method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Obtain the simulation target text under the target construction simulation scenario, perform structured semantic parsing on the simulation target text, and obtain the simulation target triple set.
[0030] Specifically, for construction simulation scenarios, it receives simulation target statements from users in natural language, such as: analyzing the schedule risks of foundation pit construction during the rainy season, as well as the spatial conflict risks of tower crane group cross-operation, focusing on the impact of continuous rainfall on the earthwork excavation progress, requiring the schedule delay to not exceed 15 days and without serious collisions.
[0031] Furthermore, the large language model is invoked to perform target parsing, converting the free text into a structured set of simulation target triples, denoted as O={(analysis type, target object, quantization criterion)}. O can contain multiple simulation target triples, each containing analysis type, target object, and quantization criterion.
[0032] The analysis type is used to define the category of engineering problems that the simulation focuses on, such as schedule risk analysis, spatial conflict risk analysis, cost risk analysis, and resource bottleneck risk analysis. The target object is used to clarify the specific construction unit, stage, working condition, or work group to be analyzed, and adopts a composite representation of object / condition, such as foundation pit engineering / rainy season construction stage, earthwork excavation progress / continuous rainfall working condition, tower crane group / cross-operation area, etc. The quantitative criteria give the numerical threshold or constraint inequality for judging the risk, such as delay ≤15 days, serious collision = 0 times, cost overrun ≤5%, hoisting waiting time ≤2 hours / shift, etc.
[0033] For example, the simulation target triplet set is: (Schedule risk analysis, foundation pit project / rainy season construction stage, delay ≤ 15 days), or (Spatial conflict risk analysis, tower crane group / cross-operation area, number of serious collisions = 0).
[0034] Furthermore, to obtain reliable and parsable simulation target triples, a constrained generation and verification mechanism is adopted. The specific steps are as follows: Define the output structure specification of the simulation target triple set, describe a clear JSON format (JavaScript Object Notation, a data exchange pattern) template in natural language, requiring that the response content consists only of an array of triple objects, each object containing three required fields: Analysis type: string, corresponding to the analysis type mentioned above; Target object: string, corresponding to the target object mentioned above; Quantization criterion: string, corresponding to the quantization criterion mentioned above. The template also requires that all fields must not be empty, and that no additional fields or irrelevant text constraints are allowed. Representative examples are used to guide the model's calculation behavior. Construct prompt words, and concatenate the structure template and examples as part of the system instructions with the user's original statement and input them into the large language model, clearly instructing: only return JSON objects that conform to the above format, without any additional explanatory text; receive the text returned by the large language model, first perform JSON parsing on it; and then perform two layers of verification.
[0035] The two-layer validation includes: structural validation, which analyzes whether each array element fully contains all required fields and that all fields are of string type; and content validation, which analyzes whether field values have substantial validity, i.e., whether field values contain non-empty and non-placeholder characters, whether quantification criteria contain numerical values and units or explicit constraint words (such as "=0 times"), and whether there are logical conflicts between triples, such as contradictory threshold settings for the same object.
[0036] Furthermore, if any step in the above two-layer verification process fails, the error information is extracted, such as missing analysis type fields or no quantified values in the criteria; the verification error description is embedded in the correction feedback prompt, guiding the model to perform targeted repairs, regenerate, and undergo double verification again; all verified entries are extracted from the verified JSON to construct a simulation target triplet set O for subsequent simulation task configuration calls; for entries that still fail verification, they are included in the unparsed list with specific error reasons marked, and handed over for manual completion. On this basis, the triplet set is further manually reviewed, and after confirmation, it is included in the scope of simulation task configuration calls.
[0037] Step S202: Construct a construction event sequence template.
[0038] Step S203: Extract construction events based on the simulation target triplet set and the construction event sequence template to obtain the event sequence set.
[0039] Specifically, the goal of construction event extraction is to select a subset of events closely related to the current simulation target based on the parsed set of simulation target triples and the constructed construction event sequence template, for simulation calculation and execution.
[0040] Step S204: Instantiate the construction event sequence parameters of the event sequence set to obtain construction event sequence instances.
[0041] Specifically, the event sequence parameter instantiation process assigns a definite value or value range that conforms to the actual project to each parameter placeholder in the construction event extracted from the event, generating a set of simulation configuration instances that can be directly deduced. When simulating the same construction event sequence, the parameter value can fluctuate within the value range each time to reflect the randomness and dynamism of the actual construction process.
[0042] Step S205: Convert the construction event sequence instances into a construction simulation configuration document.
[0043] Specifically, the construction simulation configuration document generation process involves converting the instantiated event sequence into a standardized construction simulation configuration document that can be recognized and loaded by the construction simulation calculation model.
[0044] Furthermore, based on the construction simulation configuration document, multiple simulations and deductions can be performed on the overall construction layout, construction sequence, and division of flow sections to verify the feasibility of the construction organization design. The core indicators such as the construction period, resource input, and site conflicts of each scheme can be compared to provide support for scheme optimization. Alternatively, the construction progress and schedule can be controlled based on the construction simulation configuration document, such as the preparation of the overall construction schedule plan, the deduction of the critical path, the simulation of process overlap, intermittent waiting and special working conditions, the prediction of schedule bottlenecks and delay risks, and the support for schedule compression and node reverse scheduling optimization.
[0045] This embodiment provides a method for generating construction simulation configuration documents. By performing structured semantic parsing on the simulation target text, a set of simulation target triples is obtained. Based on the set of simulation target triples and the construction event sequence template, construction events are extracted. The extracted event sequence set is then instantiated with construction event sequence parameters. Finally, the construction event sequence instances are converted into construction simulation configuration documents. Through the construction simulation configuration documents, the calculation logic, simulation parameters, event triggering rules, and decision options to be evaluated in the simulation can be intuitively displayed, avoiding black-box settings and improving the credibility of construction simulation modeling and calculation.
[0046] This embodiment provides a method for generating construction simulation configuration documents, which can be used in the aforementioned terminal devices. Figure 3 This is a flowchart of a construction simulation configuration document generation method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: Step S301: Obtain the simulation target text under the target construction simulation scenario, perform structured semantic parsing on the simulation target text, and obtain the simulation target triplet set. For details, please refer to [link to details]. Figure 2 Step S201 of the illustrated embodiment will not be described again here.
[0047] Step S302: Construct a construction event sequence template.
[0048] In some optional implementations, step S302 above includes: Step S3021: Define the construction event type.
[0049] Specifically, the construction event type library is a structured collection of descriptions of various events that may occur during the construction process, with each event type defined by several standardized attribute fields.
[0050] The meanings and constraints of each attribute field in the construction event type include: Event Identifier: A globally unique code used for precise indexing and retrieval during simulation calculations; Event Category: Divided into three categories: planned events, random events, and response events. Planned events refer to events that have been pre-arranged in the construction organization design and whose occurrence time is determinable, such as the commencement of concrete pouring in a certain section. Random events refer to events that are governed by external or internal uncertainties and occur with a certain probability or condition, such as earthwork shutdown caused by heavy rain. Response events refer to events triggered by other events and used to describe handling or remedial actions, such as activating the emergency plan for foundation pit drainage; Event Description Text: A qualitative description of the event in natural language; Trigger Condition Expression: The event activation condition given in Boolean logic expression form, which can reference state variables and parameter thresholds during simulation runtime. For example, the trigger condition is: (daily rainfall ≥ 30...) mm) && (Current time is within the planned earthwork excavation period); Duration distribution model: Specifies the probability distribution of the duration of the event once it is triggered, including the distribution type and corresponding parameters (mean, standard deviation, shape parameters, etc.). Minimum and maximum duration constraints can also be specified. Distribution types include log-normal distribution, Weibull distribution, etc.; List of state variables affected by the event: Lists the state variables affected when the event occurs, and attaches an influence function expression to each variable. For example, for a rainstorm shutdown event, the influence could be {earthwork excavation progress = earthwork excavation progress × 0} or {excavation pit drainage load = excavation pit drainage load + 30 m³ / h}; List of triggerable subsequent event identifiers: Specifies which other events can be triggered during or at the end of the event's duration. For example, a foundation pit drainage equipment failure event can trigger an emergency drainage plan activation event.
[0051] Furthermore, the initial construction event type library is jointly compiled by construction safety management experts and construction organization designers, and is required to cover no less than 100 event types, including no less than 30 planned events, no less than 40 random events, and no less than 30 response events, to ensure the necessary characterization capability for common construction scenarios. The initial construction event type library focuses on general construction events that can be reused across projects, such as construction procedures, construction machinery failures, work stoppages due to weather, and failure to pass quality acceptance of key procedures.
[0052] Furthermore, the large language model is used to expand the event types in the initial construction event type library. The complete existing event type library and the feature description of the proposed construction simulation project are used as inputs to prompt the large language model to identify event types that are not yet covered in the existing event library but may have a significant impact on the project. For each suggested new event type, the model provides an initial expression of the event category, triggering conditions, and reasons for inclusion. The feature description of the construction simulation project includes project type, structural form, construction method, site conditions, climate characteristics, construction zones, and major schedule nodes.
[0053] Furthermore, all newly generated event types must be independently reviewed by at least two construction experts. The experts provide their review opinions from three dimensions: rationality, the ability to identify risks in the construction project, and redundancy with the existing event database. Only events approved by more than two-thirds of the experts can be officially added to the event type database and have their complete attribute fields supplemented.
[0054] In addition, when supplementing attribute fields, experts still need to review the list of triggerable subsequent event identifiers for each event to determine the rationality of each triggerable subsequent event. Unreasonable triggerable subsequent events are identified and removed from the list of triggerable subsequent event identifiers based on the following criteria: whether the timing is feasible, i.e., whether the triggering event will necessarily be later than the starting condition window of the target event in the time dimension; whether the engineering logic is contradictory, i.e., whether it contradicts the basic logic of engineering construction; whether the probability is lower than the analyzable threshold, i.e., the activation probability of the subsequent event is very low under normal construction conditions, and its consequences do not involve major safety or catastrophic losses, thus lacking analytical value; and whether the granularity of division is mismatched, i.e., there is a significant mismatch in the management granularity of the two events and a lack of necessary intermediate transitions.
[0055] Furthermore, the causal strength level of approved triggerable subsequent events can be marked. The causal strength level is divided into three levels: strong causality, weak causality, and conditional causality. The classification is based on the degree of certainty of the triggering relationship and the number of additional conditions required. Among them, strong causality means that after the triggering event occurs, under the mandatory constraints of construction logic or physical laws, the target event will almost inevitably occur, and there is no feasible alternative path to bypass the response. Weak causality means that the triggering event increases the probability of the target event occurring, but there is a significant possibility that it can be affected by management intervention or alternative solutions. Conditional causality means that in addition to the occurrence of the source event, the triggering of the target event must also meet one or more explicit additional conditions.
[0056] Step S3022: Using construction event types as nodes and event triggering relationships as directed edges, construct a causal relationship graph based on the nodes and directed edges.
[0057] Specifically, using all events in the construction event type library as nodes, a directed graph representing the causal relationships between events is constructed, namely a causal relationship graph, denoted as . , where the set of nodes For all event types, directed edges Indicates an event Possible events , i.e., event and events The triggering relationship.
[0058] Among them, directed edges The generation process is as follows: traverse each node marked as a random event or a planned event, and obtain a list of possible downstream events based on the attribute fields of the list of triggerable subsequent event identifiers; for each traversed event and each downstream event in the corresponding downstream event list, assume a causal relationship between them, and construct a directed edge. .
[0059] Furthermore, global connectivity detection is performed on the causal relationship graph, and the causal relationship graph is optimized based on the global connectivity detection results.
[0060] Furthermore, after expert review, the causal relationship diagram was... Perform a global connectivity check, which traverses every random event node in the graph and verifies whether there is at least one directed path that can reach a certain response event node within a given path length limit. Any random event that does not meet this condition is marked as an isolated risk node, prompting the addition of the corresponding response event type and connection path, and reconstructing the causal relationship graph until the connectivity of random events in the entire graph fully meets the standard.
[0061] Step S3023: Perform a constrained depth-first search on the causal relationship graph to obtain the causal path.
[0062] Specifically, in the causal relationship diagram The algorithm performs a constrained depth-first search to extract all causal paths that start from an initial triggering event and terminate at a terminal event that no longer leads to downstream edges. The initial triggering event is limited to random events or planned events directly related to external disturbances. The terminal event is a node that no longer has outgoing edges or is considered to have terminated after reaching a response event of interest to the user. An upper limit constraint on the path length is imposed during the search process. The purpose of this constraint is that excessively long causal chains tend to become extremely sparse in real construction due to multiple probability multiplications, and the indirect influence at the end of the chain is too weak to be of analytical value. The upper limit constraint is used to limit the length of the causal chain.
[0063] Step S3024: Convert the causal path into a construction event sequence template.
[0064] Specifically, for each causal path obtained from the search, it is saved as an event sequence template, which gives an ordered sequence of events from the triggering event to the terminating event.
[0065] Step S303: Extract construction events based on the simulation target triplet set and the construction event sequence template to obtain the event sequence set.
[0066] In some optional implementations, step S303 above includes: Step S3031: Map the analysis type field in the simulation target triplet set to engineering indicator keywords.
[0067] Specifically, the analysis type field in the simulation target triplet specifies the engineering problem dimension of this simulation, such as schedule analysis, spatial conflict analysis, or cost analysis; the list of state variables affecting each event in the event type library declares the names of various engineering indicators changed by the event, such as foundation pit schedule deviation, tower crane collision count, cumulative cost deviation, etc.
[0068] Step S3032: Compare the impact state variables of each event in the construction event sequence template with the engineering indicator keywords one by one, and remove events from the construction event sequence template based on the comparison results to obtain the first event set.
[0069] Specifically, a lookup table is constructed to map analysis types to engineering indicator keywords. For example, schedule analysis corresponds to all indicators containing schedule and progress, and spatial conflict analysis corresponds to indicators containing collision and space occupancy. The list of state variables affecting each event in the construction event type library is compared one by one with the mapped indicator keywords. Events with at least one indicator name falling within the keyword range are retained. Events completely unrelated to the simulation analysis dimension are eliminated by direct matching based on event attribute fields. The first event set is constructed based on the remaining events.
[0070] Step S3033: Calculate semantic coverage based on the engineering semantic features corresponding to the first event set and the construction semantic features corresponding to the target object fields of the simulation target triplet set.
[0071] Specifically, the target object field in the simulation target triplet provides a specific description of the construction location, construction stage, or working condition, such as foundation pit engineering / rainy season construction stage, or tower crane group / cross-operation area.
[0072] Furthermore, for each event retained in the first event set, the entity name, process name, spatial region identifier, and working condition qualifier in its event description text and trigger condition expression are extracted to form the event's engineering semantic features; at the same time, similar semantic features are extracted from the target object field, and the semantic coverage between the two is calculated.
[0073] Step S3034: Perform semantic filtering on the first event set based on semantic coverage to obtain the second event set.
[0074] Specifically, semantic coverage is used to measure the consistency between the event's occurrence scenario and the user's specified focus object. Only events with coverage higher than a set experience threshold are retained to form a second event set.
[0075] Step S3035: Extract events from the causal path to obtain a subset of causal paths; wherein the initial triggering events in the subset of causal paths are events in the second event set.
[0076] Specifically, the initial triggering events are extracted from the constructed causal path set and filtered by the above steps S3031-S3034 to obtain the causal path subset consisting of the event set.
[0077] Step S3036: Sort the causal paths in the causal path subset and determine the event sequence set based on the sorting results.
[0078] Specifically, the selection is further refined based on the degree of coverage and matching between the subset of causal paths and the content of interest to the user. If an event involved in a path can respond to multiple simulation target triples at the same time, its ranking weight is higher. The top N paths are selected as the event sequence set, which can be adjusted according to the set threshold.
[0079] In the ranking process, the causal strength level of the causal path can also be taken into account. A strong causal edge means that the transition will almost inevitably occur under normal construction conditions, and the loss of the overall credibility of the path is minimal. A weak causal edge means that the transition may be blocked by management intervention or alternative solutions, and the credibility of the path needs to be adjusted downward. A conditional causal edge requires that the additional conditions be met at the same time, and its credibility adjustment range is larger, and the probability of the additional conditions being met must be considered.
[0080] Different credibility benchmark weights are preset for the three strength levels. For example, strong causality is assigned a value close to the upper limit, weak causality is assigned a value in the middle, and conditional causality is assigned a value at the lower limit. When ranking paths, the weights corresponding to the strength levels of all causal edges on the path are multiplied together as a quantitative representation of the path's credibility. Paths marked as strong causality are ranked higher under the same conditions, while paths that heavily rely on weak causal or conditional causal connections are given lower priority.
[0081] Furthermore, the sorted and filtered event sequences are output in the form of a structured list. Each template contains an ordered sequence of event identifiers, and each item in the sequence strictly references the event identifiers in the event type library. For each sequence, the original association between the causal edge strength levels of the events and the list of subsequent event identifiers that can be triggered is preserved, but no specific parameter values are filled in. The thresholds, duration distribution parameters, and coefficients of the influence function in all triggering conditions are reserved as placeholders for instantiation and assignment in the subsequent simulation parameter space sampling stage. As a structured intermediate product that connects the preceding and following steps, the event sequence will be directly input into the parameter space sampling process to drive the automatic generation of diverse construction simulation configuration documents.
[0082] Step S304 involves instantiating the event sequence set using construction event sequence parameters to obtain construction event sequence instances. For details, please refer to [link to relevant documentation]. Figure 2 Step S204 of the illustrated embodiment will not be described again here.
[0083] Step S305: Convert the construction event sequence instances into a construction simulation configuration document. See details in [link to document]. Figure 2 Step S205 of the illustrated embodiment will not be described again here.
[0084] This embodiment provides a method for generating construction simulation configuration documents. By defining construction event types and constructing a causal relationship graph, the triggering logic and sequential constraints between construction procedures are transformed into a traceable structured model. This significantly improves the interpretability of the modeling process, solves the problems of opaque and difficult-to-verify modeling logic, and provides an interpretable logical foundation for the subsequent generation of construction simulation configuration documents. Furthermore, by performing a constrained depth-first search on the causal relationship graph, the compliance and rationality of the construction process are ensured, and the causal path is transformed into a construction event sequence template, thereby improving the efficiency and scalability of construction simulation modeling.
[0085] Furthermore, the analysis type of the simulation target triplet is mapped to engineering indicator keywords. Irrelevant events are then eliminated by comparing them with template state variables, ensuring that the selected event set directly serves the analysis needs of the simulation target and avoiding interference from invalid events. By calculating semantic coverage, a second semantic filter is performed on the events to ensure that the selected events are semantically consistent with the construction target, avoiding deviations such as matching procedures but semantic inconsistencies. The second event set after semantic filtering is then used as the initial trigger event to extract causal paths, ensuring that the generated causal paths start entirely from the simulation target, avoiding the generation of invalid paths that deviate from the requirements, while preserving the complete construction logic chain. The causal paths are sorted, and the event sequence set is determined based on the sorting results, reducing the cost of subsequent manual screening. Through a multi-round screening mechanism, the requirements of the construction simulation target are accurately matched, significantly improving the matching degree between the extracted event sequences and the simulation target, as well as the modeling efficiency and the reliability of the results.
[0086] This embodiment provides a method for generating construction simulation configuration documents, which can be used in the aforementioned terminal devices. Figure 4 This is a flowchart of a construction simulation configuration document generation method according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps: Step S401: Obtain the simulation target text under the target construction simulation scenario, perform structured semantic parsing on the simulation target text, and obtain the simulation target triplet set. For details, please refer to... Figure 3 Step S301 of the illustrated embodiment will not be described again here.
[0087] Step S402: Construct a construction event sequence template. See details below. Figure 3 Step S302 of the illustrated embodiment will not be described again here.
[0088] Step S403: Based on the simulation target triplet set and the construction event sequence template, construction events are extracted to obtain an event sequence set. For details, please refer to [link to relevant documentation]. Figure 3 Step S303 of the illustrated embodiment will not be described again here.
[0089] Step S404: Instantiate the construction event sequence parameters of the event sequence set to obtain construction event sequence instances.
[0090] In some optional implementations, step S404 above includes: Step S4041: Traverse the construction events in the event sequence set and extract the placeholders for the parameters to be assigned.
[0091] Specifically, for each selected construction event, the complete attribute record in the event type library is retrieved for each event, and the following three types of parameter placeholders to be assigned values are extracted: Threshold parameters in the trigger condition expression: The event library attribute "trigger condition expression" contains Boolean logic expressions referencing external conditions, where numerical thresholds appear as placeholders, such as the specific millimeters of the daily rainfall threshold and the specific meters per second of the wind speed threshold; Distribution parameters of the duration distribution model: The event library attribute "duration distribution model" specifies the distribution type and its parameter placeholders, such as the mean and standard deviation of the normal distribution, and the shape and scale parameters of the Weibull distribution; Coefficients in the influence function expression: In the event library attribute "list of state variables of influence," each influence function expression contains coefficient placeholders, such as the decrease rate of progress advancement and the increment value of the number of collisions.
[0092] Furthermore, all placeholders for parameters to be assigned are integrated into a list of parameters to be assigned, and after deduplication, the parameter space dimension definition for this construction event sequence is formed.
[0093] Step S4042: Obtain parameter configuration data, assign values to multiple instance parameters based on the parameter configuration data and placeholders of the parameters to be assigned, and obtain construction event sequence instances.
[0094] Specifically, for each placeholder parameter to be assigned a value, its reasonable value range or prior distribution is determined based on the following three sources: Project characteristic data: including historical meteorological records of the project location, site layout data, construction quotas, and historical work efficiency statistics of the enterprise. For example, the daily rainfall threshold can be selected from the daily rainfall quantiles of the local rainy season, and the equipment failure rate can be extracted from the maintenance records of similar projects; Built-in guiding values in the event type library: the attributes of some events have preset reference value ranges or recommended distributions when entering the event library. For example, the duration distribution model may have marked the range of typical parameters; Construction domain knowledge rules: several constraint relationships between parameters are predefined by experts, such as the correlation constraint between concrete curing time and ambient temperature.
[0095] Furthermore, based on the scale of the analysis requirements, Latin hypercube sampling or stratified sampling methods are applied. According to the parameter value range and distribution set above, several sets of parameter assignment schemes are generated in the parameter space. Each set of assignment schemes covers all the placeholders of the parameters to be assigned. Each set of assignment schemes is a specific parameter configuration. It is filled into the placeholder position corresponding to the construction event sequence to obtain a construction event sequence instance with fully instantiated parameters.
[0096] Furthermore, all validated instantiated event sequences are output in list form. Each construction event sequence instance contains a complete event sequence populated with specific values. Each event record retains an event identifier, a numerically defined trigger condition expression, a parameterized duration distribution, a calibrated influence function expression, and specific values for the causal transition probability between events.
[0097] Step S405 converts the construction event sequence instances into a construction simulation configuration document. See details in [link to document]. Figure 3 Step S305 of the illustrated embodiment will not be described again here.
[0098] This embodiment provides a method for generating construction simulation configuration documents. By extracting placeholders for parameters to be assigned in the construction event sequence and assigning values to multiple instance parameters based on parameter configuration data, the method decouples the construction event logic from the engineering parameters, quickly generates multiple construction event sequence instances, significantly improves the efficiency, consistency, and multi-scenario adaptability of construction simulation modeling, and reduces manual modeling errors and maintenance costs.
[0099] This embodiment provides a method for generating construction simulation configuration documents, which can be used in the aforementioned terminal devices. Figure 5 This is a flowchart of a construction simulation configuration document generation method according to an embodiment of the present invention, such as... Figure 5 As shown, the process includes the following steps: Step S501: Obtain the simulation target text under the target construction simulation scenario, perform structured semantic parsing on the simulation target text, and obtain the simulation target triplet set. For details, please refer to... Figure 4 Step S401 of the illustrated embodiment will not be described again here.
[0100] Step S502: Construct a construction event sequence template. See details below. Figure 4 Step S402 of the illustrated embodiment will not be described again here.
[0101] Step S503: Based on the simulation target triplet set and the construction event sequence template, construction events are extracted to obtain an event sequence set. For details, please refer to [link to relevant documentation]. Figure 4 Step S403 of the illustrated embodiment will not be described again here.
[0102] Step S504 involves instantiating the event sequence set using construction event sequence parameters to obtain construction event sequence instances. For details, please refer to [link to relevant documentation]. Figure 4 Step S404 of the illustrated embodiment will not be described again here.
[0103] Step S505: Convert the construction event sequence instances into a construction simulation configuration document.
[0104] In some optional implementations, step S505 above includes: Step S5051: Obtain basic information about the construction project and generate global configuration data based on the simulation target triplet set and the basic information about the construction project.
[0105] Specifically, based on the target triple set and project basic information, a global configuration section of the construction simulation configuration document is generated. The global configuration data includes: the unique identifier and name of the construction simulation configuration, the index of the associated target triple set, the simulation start and end time, the time step, the meteorological calendar setting, and the list of monitoring indicators to be output. Among them, the list of monitoring indicators is determined according to the analysis type and quantitative criteria of the target triple, ensuring that relevant engineering indicators are recorded during the simulation operation.
[0106] Step S5052: Determine the initial state data based on the set of simulation target triples.
[0107] Specifically, based on the target object field in the simulation target triplet set, the corresponding engineering entities, spatial regions, and initial working conditions in the target simulation model are written into the construction simulation configuration document; for example, the foundation pit project / rainy season construction stage is mapped to the foundation pit partition identifier and the initial excavation surface elevation, and the tower crane group / cross-operation area is mapped to the tower crane number and its position coordinates participating in the simulation, so that the simulation model can initialize and define the correct engineering scenario when calculating.
[0108] Step S5053: Determine the event plan data and branch logic combination data based on the construction event sequence instances.
[0109] Specifically, each event in the instantiated event sequence is written into the event plan section of the construction simulation configuration file in chronological order. In the event plan data, the record content of each event strictly references the attribute structure of the event type library, including event identifier, event category, event description text, fixed trigger condition expression, fixed duration distribution model, fixed influence function expression, and a list of subsequent event identifiers that can be triggered.
[0110] Furthermore, for the causal transition relationship between adjacent events in the construction event sequence instance, based on the list of triggerable subsequent event identifiers in the event type library and the causal edge strength level, the possible branches after each event is completed are explicitly declared in the construction simulation configuration document; where, for deterministic triggering relationships, it directly points to the next event; for probabilistic triggering relationships, the specific value of the transition probability is noted; so that the simulation model can correctly execute random branches and Monte Carlo deductions during calculation.
[0111] Step S5054: Generate a construction simulation configuration document based on global configuration data, initial state data, event plan data, and branch logic combination data.
[0112] Specifically, global configuration data, initial state data, event plan data, and branch logic combination data are combined into a complete construction simulation configuration document, which is output in a structured format compatible with the construction simulation calculation model. The output format can adopt a standardized construction simulation configuration document exchange format or a file format proprietary to the simulation platform. The document retains the event type library reference relationship to support traceability and verification. After output, each construction simulation configuration document constitutes an independent engineering simulation scheme that can be loaded and run by the simulation engine and directly delivered to the simulation execution stage.
[0113] This embodiment provides a method for generating construction simulation configuration documents. By constructing global configuration data, initial state data, event plan data, and branch logic combination data in layers, it achieves structured organization of all elements of construction simulation and fusion of multi-source data. This results in a logically clear construction simulation configuration document, solving the problems of missing elements, logical confusion, and poor platform adaptability in construction simulation modeling. It significantly improves the accuracy, executability, and versatility of construction simulation modeling.
[0114] This embodiment also provides a construction simulation configuration document generation device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.
[0115] This embodiment provides a construction simulation configuration document generation device, such as... Figure 6 As shown, it includes: The structured semantic parsing module 601 is used to obtain the simulation target text under the target construction simulation scenario, perform structured semantic parsing on the simulation target text, and obtain the simulation target triple set; Module 602 is used to build construction event sequence templates; The extraction module 603 is used to extract construction events based on the simulation target triplet set and the construction event sequence template to obtain an event sequence set. The instantiation processing module 604 is used to instantiate the event sequence set with construction event sequence parameters to obtain construction event sequence instances. The conversion module 605 is used to convert construction event sequence instances into construction simulation configuration documents.
[0116] In some alternative implementations, the construction module 602 includes: Define a unit to define the type of construction event; The building unit is used to construct a causal relationship graph based on the nodes and the event triggering relationship as directed edges, using construction event types as nodes and event triggering relationships as directed edges. The search unit is used to perform a constrained depth-first search on the causal relationship graph to obtain the causal path; The transformation unit is used to convert causal paths into construction event sequence templates.
[0117] In some alternative implementations, the construction module 602 further includes: The global connectivity detection unit is used to perform global connectivity detection on the causal relationship graph and optimize the causal relationship graph based on the global connectivity detection results.
[0118] In some alternative implementations, the extraction module 603 includes: The mapping unit is used to map the analysis type field in the simulation target triplet set to engineering indicator keywords; The comparison unit is used to compare the impact state variables of each event in the construction event sequence template with the engineering indicator keywords one by one, and to remove events from the construction event sequence template based on the comparison results to obtain the first event set; The calculation unit is used to calculate semantic coverage based on the engineering semantic features corresponding to the first event set and the construction semantic features corresponding to the target object fields of the simulation target triplet set. A semantic filtering unit is used to perform semantic filtering on the first event set based on semantic coverage to obtain the second event set; The event extraction unit is used to extract events from the causal path to obtain a subset of causal paths; wherein the initial triggering events in the subset of causal paths are events from the second event set; The sorting unit is used to sort the causal paths in the subset of causal paths and determine the set of event sequences based on the sorting results.
[0119] In some alternative implementations, the instantiation processing module 604 includes: The traversal unit is used to traverse the construction event sequence template in the event sequence set and extract the placeholders for the parameters to be assigned. The assignment unit is used to obtain parameter configuration data, and based on the parameter configuration data, assign values to multiple instance parameters of the placeholder parameter to be assigned to obtain the construction event sequence instance.
[0120] In some alternative implementations, the conversion module 605 includes: The first generation unit is used to acquire basic information about the construction project and generate global configuration data based on the set of triplets of the simulation target and the basic information about the construction project. The first determining unit is used to determine the initial state data based on the set of triplets of the simulation target; The second determining unit is used to determine event plan data and branch logic combination data based on construction event sequence instances, respectively. The second generation unit is used to generate construction simulation configuration documents based on global configuration data, initial state data, event plan data, and branch logic combination data.
[0121] The construction simulation configuration document generation device provided in this embodiment of the invention can execute a construction simulation configuration document generation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.
[0122] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.
[0123] The following is a detailed reference. Figure 7This diagram illustrates a suitable structural schematic for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 701, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 702 or a program loaded from memory 708 into random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the electronic device. The processor 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.
[0124] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 708 including, for example, magnetic tapes, hard disks, etc.; and communication devices 709. Communication device 709 allows electronic devices to exchange data via wireless or wired communication with other devices. Although Figure 7 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.
[0125] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 709, or installed from a memory 708, or installed from a ROM 702. When the computer program is executed by the processor 701, it performs the functions defined in a construction simulation configuration document generation method according to embodiments of the present invention.
[0126] Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.
[0127] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium after being downloaded via a network. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, a construction simulation configuration document generation method shown in the above embodiments is implemented.
[0128] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.
[0129] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.
Claims
1. A method for generating construction simulation configuration documents, characterized in that, The method includes: Obtain the simulation target text under the target construction simulation scenario, perform structured semantic parsing on the simulation target text, and obtain the simulation target triple set; Construct a construction event sequence template; Based on the simulation target triplet set and the construction event sequence template, construction events are extracted to obtain an event sequence set; The event sequence set is instantiated using construction event sequence parameters to obtain construction event sequence instances; Convert the construction event sequence instances into a construction simulation configuration document.
2. The method according to claim 1, characterized in that, The construction event sequence template includes: Define construction event types; Using the construction event types as nodes and the event triggering relationships as directed edges, a causal relationship graph is constructed based on the nodes and the directed edges. A constrained depth-first search is performed on the causal relationship graph to obtain the causal path; The causal path is converted into the construction event sequence template.
3. The method according to claim 2, characterized in that, Before performing a constrained depth-first search on the causal graph to obtain the causal path, the method further includes: A global connectivity test is performed on the causal relationship graph, and the causal relationship graph is optimized based on the global connectivity test results.
4. The method according to claim 2, characterized in that, The construction event extraction based on the simulation target triplet set and the construction event sequence template yields an event sequence set, including: Map the analysis type field in the set of simulation target triples to engineering indicator keywords; The impact state variables of each event in the construction event sequence template are compared one by one with the engineering indicator keywords, and the events in the construction event sequence template are removed based on the comparison results to obtain the first event set; Based on the engineering semantic features corresponding to the first event set and the construction semantic features corresponding to the target object field of the simulation target triplet set, the semantic coverage is calculated. Based on the semantic coverage, the first event set is semantically filtered to obtain the second event set; Event extraction is performed on the causal path to obtain a subset of causal paths; wherein the initial triggering event in the subset of causal paths is an event from the second event set; The causal paths in the subset of causal paths are sorted, and the set of event sequences is determined based on the sorting results.
5. The method according to claim 1, characterized in that, The step of instantiating the event sequence set into construction event sequence instances by performing construction event sequence parameter instantiation processing includes: Traverse the construction events in the event sequence set and extract the placeholders for the parameters to be assigned. Obtain parameter configuration data, and assign multiple instance parameters to the placeholders of the parameters to be assigned based on the parameter configuration data to obtain the construction event sequence instance.
6. The method according to claim 1, characterized in that, The step of converting the construction event sequence instances into a construction simulation configuration document includes: Obtain basic information about the construction project, and generate global configuration data based on the set of triplets of the simulation target and the basic information about the construction project. Initial state data are determined based on the set of triplets representing the simulation target. Based on the construction event sequence instances, determine the event plan data and branch logic combination data respectively; The construction simulation configuration document is generated based on the global configuration data, the initial state data, the event plan data, and the branch logic combination data.
7. A construction simulation configuration document generation device, characterized in that, The device includes: The structured semantic parsing module is used to obtain the simulation target text under the target construction simulation scenario, and to perform structured semantic parsing on the simulation target text to obtain a set of simulation target triples; The building module is used to construct construction event sequence templates; The extraction module is used to extract construction events based on the simulation target triplet set and the construction event sequence template to obtain an event sequence set; The instantiation processing module is used to instantiate the event sequence set with construction event sequence parameters to obtain construction event sequence instances. The conversion module is used to convert the construction event sequence instances into a construction simulation configuration document.
8. An electronic device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the construction simulation configuration document generation method according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the construction simulation configuration document generation method according to any one of claims 1 to 6.
10. A computer program product, characterized in that, Includes computer instructions, which are used to cause a computer to execute the construction simulation configuration document generation method according to any one of claims 1 to 6.