AI-based dynamic construction scheduling and construction period risk early warning system and method

Abstract

This invention discloses an AI-based dynamic construction scheduling and schedule risk early warning system and method, belonging to the field of building construction technology. It includes a data acquisition module for acquiring relevant data of the target building, including building data; the building data includes building structure, component information, and spatial relationships, with the building structure including the building frame; and a data processing module for scheduling the construction of the target building based on the relevant data, including scheduling based on the construction of the building frame. This invention improves construction efficiency, reduces delay risks, reduces material waste, and supports efficient construction of complex structures by enhancing the precision of construction scheduling, providing real-time schedule warnings, optimizing resource allocation, and digitizing management decisions. It offers an innovative solution for the intelligent construction industry.

Description

Technical Field

[0001] This invention relates to the field of building construction technology, and in particular to an AI-based dynamic construction scheduling and schedule risk early warning system and method. Background Technology

[0002] In traditional construction, construction scheduling usually relies on the experience of project managers to conduct static scheduling, which is difficult to cope with complex and ever-changing site conditions and resource constraints.

[0003] In this area of ​​research, application CN202511700882.7 provides an AI-based method and system for engineering progress tracking and early warning. This technical solution overcomes the information silo problem in multimodal data integration of traditional methods by constructing an engineering spatiotemporal knowledge graph, thereby improving the comprehensiveness of the perception of the construction site status. It also establishes an intelligent mechanism for deviation analysis and trend inference, and through multi-dimensional comprehensive evaluation of geometric shape, construction procedure topology, resource arrival sequence, and quality compliance attributes, it realizes the prediction of the evolution trend of the engineering status, thereby improving the scientific nature and execution efficiency of engineering progress management.

[0004] Another application, CN202511134933.4, provides an AI-based dynamic production scheduling management system. This solution includes a task compression coefficient generation module, a task priority re-mapping module, a resource conflict index extraction module, a path breakpoint identification module, and an alternative task sequence construction module. This solution quantifies the urgency of tasks by constructing a time buffer between the latest task start time and the expected execution time. It can dynamically identify critical tasks affecting delivery nodes, making task priorities less static. Combined with path structure dependencies, it filters potential breakpoints in the process flow, reducing the risk of plan failures caused by abnormal nodes.

[0005] However, the above-mentioned technical solutions mostly adopt single-parameter early warning control values, such as setting thresholds based solely on cumulative displacement or rate of change. This approach is prone to false alarms and missed alarms. It lacks detailed analysis of complex risks such as cross-operation conflicts and supply chain disruptions, resulting in weak analytical functions of the early warning system, which is difficult to meet the needs of modern construction for efficient and precise management. Summary of the Invention

[0006] In view of the problems existing in the field of existing building construction technology, the present invention is proposed.

[0007] Therefore, one of the objectives of this invention is to provide an AI-based dynamic construction scheduling and schedule risk early warning system and method, which improves construction efficiency, reduces delay risks, reduces material waste, and supports efficient construction of complex structures by making construction scheduling more precise, schedule early warnings more real-time, optimizing resource allocation, and data-driven management decisions. This provides an innovative solution for the intelligent construction industry.

[0008] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0009] On the one hand, this invention provides an AI-based dynamic construction scheduling and schedule risk early warning system, including:

[0010] The data acquisition module is used to acquire relevant data of the target building, including building data; the building data includes building structure, component information and spatial relationships, and the building structure includes the building frame.

[0011] The data processing module is used to schedule the construction of the target building based on the relevant data, including scheduling the construction based on the construction of the building frame; the data processing module includes a differentiation unit and a processing unit.

[0012] The differentiation unit is used to differentiate the building frame, including differentiating shear wall structure, core tube structure and irregular column frame structure according to structural form, and obtaining relevant information corresponding to the shear wall structure, core tube structure and irregular column frame structure. The relevant information includes the building height and the consumption of building materials corresponding to the building height.

[0013] The processing unit is used to perform relevant processing based on the relevant information. The relevant processing includes obtaining changes in the building height based on the consumption of building materials. The steps for obtaining the information are as follows:

[0014] The changes in building height are acquired in 20-minute intervals, and the correlation between the consumption of building materials and the building height is acquired in each acquisition interval.

[0015] Based on the aforementioned correlation, an evaluation cycle is defined as at least five consecutive acquisition periods. During the evaluation cycle, the height difference between the shear wall structure and the irregular column frame structure and the main observation object is acquired under the same building material consumption, with the core tube structure as the main observation object.

[0016] A data fusion early warning module, comprising a statistical unit, an analysis unit, and an early warning unit;

[0017] The statistical unit is used to perform relevant statistics based on the height difference. The relevant statistics include the statistical analysis of the increase in the construction height of the shear wall structure and the irregular column frame structure in each acquisition period.

[0018] The analysis unit responds to the increment and is used to analyze the correlation between the increment of construction height and the consumption of building materials in each acquisition period, and regards the consumption of building materials corresponding to the increment of construction height in each acquisition period as the reference consumption.

[0019] The early warning unit is used to issue an early warning based on the association.

[0020] In a preferred embodiment of the present invention, the warning step in the warning unit includes:

[0021] Obtain the construction period for the target building and calculate the remaining duration of the construction period;

[0022] The remaining time limit is divided equally. In the first half of the equally divided time limit, the time length corresponding to this time limit is divided based on the evaluation period.

[0023] Within the segmented assessment period, if the consumption of building materials during the acquisition period included in a certain assessment period is lower than the reference consumption, the system will issue a warning that there is a risk of delay in the construction period; otherwise, no warning will be issued.

[0024] In a preferred embodiment of the present invention, the processing unit acquires the correlation between the consumption of building materials and the construction height during each acquisition time period, and calculates the correlation using the following formula:

[0025] ;

[0026] In the formula, Indicates the first The increment of the building height within a given time period;

[0027] This represents the material efficiency coefficient, which reflects the contribution of a unit amount of material to the height.

[0028] Indicates the first The total amount of building materials consumed within a specific acquisition period;

[0029] Indicates the first The cross-sectional area of ​​the construction during the acquisition period.

[0030] In a preferred embodiment of the present invention, the method further includes calculating the following formula:

[0031] ;

[0032] Discretized form (summing every 20 minutes):

[0033] ;

[0034] In the formula, Indicates time Total building height at the time;

[0035] Indicates time Material consumption rate at that time;

[0036] Indicates time The cross-sectional area during construction;

[0037] This indicates the time period number to be retrieved;

[0038] Indicates time Perform differentiation;

[0039] Represents an integer variable.

[0040] In a preferred embodiment of the present invention, the analysis unit analyzes the correlation between the increase in building height and the consumption of building materials during each acquisition period, and calculates the result according to the following formula:

[0041] ;

[0042] In the formula, Indicates the first The increment of the building height within a given time period;

[0043] Represents the intercept term;

[0044] Represents the regression coefficient;

[0045] This represents the random error term, used to reflect construction fluctuations or measurement errors.

[0046] In a preferred embodiment of the present invention, the dynamic construction scheduling based on the results of analysis and calculation includes the following steps:

[0047] A scheduling cycle is set, wherein the scheduling cycle consists of at least three consecutive acquisition periods;

[0048] Within the aforementioned scheduling period, the structure with the lowest incremental construction height among the shear wall structure, core tube structure, and irregular column frame structure is selected and regarded as the reference structure.

[0049] After the scheduling period ends, the structure corresponding to the reference structure will be regarded as the priority construction object for construction scheduling.

[0050] In a preferred embodiment of the present invention, strategy learning is performed based on the dynamic construction schedule. The strategy learning includes obtaining the structure whose increment is closest to the reference structure during the scheduling period, obtaining the consumption of building materials for this structure, taking the consumption of building materials as the control consumption, and prioritizing the construction of the reference structure based on this control consumption after the scheduling period ends.

[0051] In a preferred embodiment of the present invention, the strategy learning further includes issuing an early warning if the consumption of building materials for the reference structure is lower than the control consumption when construction is carried out on the reference structure in the future; otherwise, no early warning is issued.

[0052] On the other hand, the present invention provides a method for application to the AI-based dynamic construction scheduling and schedule risk early warning system described above, comprising the following steps:

[0053] Acquire relevant data about the target building, including building data; the building data includes building structure, component information, and spatial relationships, and the building structure includes the building frame.

[0054] The building frame is differentiated, including distinguishing shear wall structure, core tube structure and irregular column frame structure according to structural form, and obtaining relevant information corresponding to the shear wall structure, core tube structure and irregular column frame structure. The relevant information includes the building height and the consumption of building materials corresponding to the building height.

[0055] Based on the aforementioned relevant information, relevant processing is performed, including obtaining changes in construction height based on the consumption of building materials. The steps for obtaining this information are as follows:

[0056] The changes in building height are acquired in 20-minute intervals, and the correlation between the consumption of building materials and the building height is acquired in each acquisition interval.

[0057] Based on the aforementioned correlation, an evaluation cycle is defined as at least five consecutive acquisition periods. During the evaluation cycle, the height difference between the shear wall structure and the irregular column frame structure and the main observation object is acquired under the same building material consumption, with the core tube structure as the main observation object.

[0058] Based on the height difference, relevant statistics are performed, including the increase in the construction height of the shear wall structure and the irregular column frame structure during each acquisition period;

[0059] Based on the increment, the correlation between the increment of construction height and the consumption of building materials in each acquisition period is analyzed, and the consumption of building materials corresponding to the increment of construction height in each acquisition period is regarded as the reference consumption.

[0060] Warnings will be issued based on the aforementioned associations.

[0061] Beneficial effects:

[0062] 1. The system dynamically calculates the construction efficiency of each structure based on the correlation between the consumption of building materials and the building height, and prioritizes the construction of structures with lower efficiency to reduce idle resources and improve overall construction efficiency. For example, within the scheduling cycle, the system will identify the structure with the lowest building height increment and make it the priority construction target for the next cycle to ensure the compactness and efficiency of the construction process.

[0063] 2. The statistical and analytical units in the data fusion and early warning module calculate the reference consumption by statistically analyzing the correlation between the increase in construction height and material consumption in each acquisition period, thus providing data support for early warning. For example, the system will statistically analyze the increase in construction height of shear walls and irregular column frame structures in each 20-minute period and analyze its relationship with material consumption, thereby identifying potential construction efficiency problems.

[0064] 3. Furthermore, the early warning unit dynamically divides the assessment period based on the remaining construction period and material consumption. If the material consumption in a certain assessment period is lower than the reference consumption, an early warning of the risk of construction delay will be issued. For example, the system will divide the remaining construction period equally and monitor whether the material consumption meets the standard based on the assessment period (such as five consecutive 20-minute time intervals) in the first half of the period. If it does not meet the standard, an early warning will be triggered so that managers can take timely measures to avoid delays.

[0065] 4. The system helps construction teams optimize material ratios and construction techniques by calculating the contribution of material consumption to building height (e.g., material efficiency coefficient quantifies the actual impact of unit material usage on height). Furthermore, through a strategy learning mechanism, the system compares the material consumption of each structure during the scheduling cycle, identifies the optimal construction strategy, and promotes it in future construction. For example, if the material consumption of an irregular column frame structure is close to that of a reference structure (e.g., a core tube) during a certain period, the system will set its consumption as the control consumption and prioritize the use of similar techniques in subsequent construction, thereby reducing material waste. Attached Figure Description

[0066] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a schematic diagram of the modular structure of the AI-based dynamic construction scheduling and schedule risk early warning system according to an embodiment of the present invention. Figure 2 This is a schematic diagram of the method flow according to an embodiment of the present invention; The diagram is labeled as follows: 110 - Data acquisition module; 120 - Data processing module; 1201 - Differentiation unit; 1202 - Processing unit; 130 - Data fusion and early warning module; 1301 - Statistical unit; 1302 - Analysis unit; 1303 - Early warning unit. Detailed Implementation

[0067] 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, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention are within the scope of protection of the present invention.

[0068] Because existing technical solutions mostly use single-parameter early warning control values, the analysis function of the early warning system is weak, making it difficult to meet the needs of modern building construction for efficient and precise management.

[0069] Based on this, the present invention proposes an AI-based dynamic construction scheduling and schedule risk early warning system and method, which significantly improves construction efficiency by finely distinguishing building structures and dynamically adjusting the construction sequence; at the same time, it effectively reduces the probability of schedule delays through multi-dimensional data statistics and analysis and dynamic early warning mechanism; and by quantifying the correlation between material consumption and high growth and optimizing resource allocation, it reduces material waste, providing an efficient and reliable solution for the intelligentization of the construction industry.

[0070] The present solution will be further described in detail below through embodiments and in conjunction with the accompanying drawings.

[0071] Reference Figures 1 to 2 As one embodiment of the present invention, this embodiment provides an AI-based dynamic construction scheduling and schedule risk early warning system, including:

[0072] The data acquisition module 110 is used to acquire relevant data of the target building, including building data; the building data includes building structure, component information and spatial relationship (this spatial relationship is the layout of the target building), and the building structure includes the building frame (the concrete frame of the target building).

[0073] In this embodiment, the system collects building data of the target building, including building structure (such as shear walls, core tube, and irregular column frame), component information, and spatial relationships. This data provides basic input for subsequent construction scheduling and risk warning.

[0074] This can cover all building element data, avoiding scheduling deviations caused by missing information;

[0075] Furthermore, by distinguishing different structural types (such as shear walls and irregular columns), a basis for differentiated construction strategies is provided, thereby improving the rationality of construction scheduling.

[0076] The data processing module 120 is used to schedule the construction of the target building based on relevant data, including scheduling the construction based on the construction of the building frame; the data processing module 120 includes a differentiation unit 1201 and a processing unit 1202.

[0077] The differentiation unit 1201 is used to differentiate the building frame, including differentiating shear wall structure, core tube structure and irregular column frame structure according to the structural form, and obtaining relevant information corresponding to shear wall structure, core tube structure and irregular column frame structure, including the building height and the consumption of building materials corresponding to the building height.

[0078] In one feasible implementation, this embodiment can formulate scheduling strategies for different structural characteristics to avoid resource waste or inefficiency caused by a "one-size-fits-all" approach.

[0079] It can also clarify the relationship between the consumption of various structural materials and the height, providing a quantitative basis for subsequent optimization.

[0080] Processing unit 1202 is used to perform relevant processing based on relevant information. The relevant processing includes obtaining changes in construction height based on the consumption of building materials. The steps for obtaining the information are as follows:

[0081] The changes in building height are captured in 20-minute intervals, and the correlation between the consumption of building materials and building height is captured in each interval.

[0082] Based on the correlation effect, an evaluation cycle is defined as at least 5 consecutive acquisition periods. During the evaluation cycle, the height difference between the shear wall structure and the irregular column frame structure and the main observation object is acquired under the same consumption of building materials, with the core tube structure as the main observation object.

[0083] Core tube structures, due to their high vertical load-bearing capacity and construction stability, typically bear the main vertical loads in high-rise buildings. Irregular column frame structures and shear wall structures, with their irregular cross-sections, present significant construction challenges (e.g., complex formwork reinforcement and difficulty in achieving proper concrete compaction). In contrast, core tube structures are usually regular rectangles, allowing for a high degree of standardization in construction processes. Using the core tube as a reference, the system can offset the impact of construction fluctuations in irregular columns on the overall progress.

[0084] Even if the irregular column is delayed due to weather or process issues, the stable progress of the core tube can provide a buffer for the overall project schedule.

[0085] Therefore, in a feasible implementation plan, it is of practical significance to focus on the core tube structure as the main object of observation.

[0086] Capturing the relationship between material consumption and construction progress helps avoid the shortcomings of static scheduling in adapting to changes on site and also helps identify inefficient construction processes.

[0087] The data fusion early warning module 130 includes a statistical unit 1301, an analysis unit 1302, and an early warning unit 1303.

[0088] The statistical unit 1301 is used to perform relevant statistics based on the height difference. The relevant statistics include the increase in the construction height of the shear wall structure and the irregular column frame structure in each acquisition period (how much the construction height has increased).

[0089] The statistical unit summarizes the height increments of shear walls and irregularly shaped column frame structures over different time periods and calculates the height difference between them and the core tube structure. For example, if the core tube height exceeds a threshold ahead of the shear wall height, it may indicate a delay in shear wall construction.

[0090] This method of quantifying construction deviations through height differences can intuitively reflect potential schedule risks;

[0091] Furthermore, by focusing on the core tube as the primary object of observation, a reference benchmark is established for the collaborative construction of multiple structures, thus avoiding the limitations of a single-structure perspective.

[0092] The analysis unit 1302 responds to the increment, which is used to analyze the relationship between the increment of construction height and the consumption of building materials in each acquisition period, and regards the consumption of building materials corresponding to the increment of construction height in each acquisition period as the reference consumption.

[0093] Reference consumption is set based on statistical units to avoid false alarms or omissions caused by subjective judgment.

[0094] The early warning unit 1303 is used to issue early warnings based on correlations. The early warning steps include:

[0095] Obtain the construction period for the target building and calculate the remaining construction period (the remaining period is calculated after the first assessment cycle ends).

[0096] The remaining timeframe is divided equally (into two identical timeframes). Within the first half of the equally divided timeframe, the corresponding time length is further divided based on the assessment period (i.e., the corresponding time length is divided into multiple assessment periods).

[0097] Within the segmented assessment period, if the consumption of building materials during the acquisition period included in a certain assessment period is lower than the reference consumption, the system will issue a warning that there is a risk of delay in the construction period; otherwise, no warning will be issued (no warning will be issued for the risk of delay in the construction period).

[0098] This approach focuses on key stages (such as the first half of the project), concentrates resources to intervene in high-risk aspects, and can dynamically update the remaining project duration based on actual progress, avoiding the problem that fixed thresholds cannot adapt to changes in progress.

[0099] Within the processing unit, the correlation between the consumption of building materials and the building height is obtained during each acquisition period, calculated using the following formula:

[0100] ;

[0101] In the formula, Indicates the first The increment of the building height within a given time period;

[0102] The material efficiency coefficient (dimensionless) reflects the contribution of a unit of material usage to the height (it needs to be calibrated using historical data).

[0103] Indicates the first The total amount of building materials consumed within a specific acquisition period;

[0104] Indicates the first The cross-sectional area (e.g., the cross-sectional area of ​​shear walls or core tubes) of the construction during the acquisition period.

[0105] Suitable for scenarios where material consumption and height increase linearly (such as concrete pouring), through real-time monitoring. and Dynamic calculation .

[0106] It also includes calculations based on the following formula:

[0107] ;

[0108] Discretized form (summing every 20 minutes):

[0109] ;

[0110] In the formula, Indicates time Total building height at the time;

[0111] Indicates time Material consumption rate at that time;

[0112] Indicates time The cross-sectional area during construction;

[0113] This indicates the time period number to be retrieved;

[0114] Indicates time Differentiate (representing an infinitely small time interval);

[0115] During the integration process, Total time Divided into countless tiny acquisition periods, each with an assumed material consumption rate. The cross-sectional area of ​​the construction is constant, thus accumulating the height increment over all minute time intervals through integration;

[0116] Represents an integer variable (used to iterate through all discrete acquisition time periods).

[0117] By accumulating material consumption data for each time period, the total height change can be calculated, which is suitable for long-term construction progress tracking.

[0118] Within the analysis unit, the correlation between the increase in building height and the consumption of building materials during each acquisition period is analyzed and calculated based on the following formula:

[0119] ;

[0120] In the formula, Indicates the first The increment of the building height within a given time period;

[0121] This represents the intercept term (dimensionless, used to reflect the fixed influence of other unmodeled factors on the building height);

[0122] Represents the regression coefficient (indicating the contribution of unit building material consumption to height growth);

[0123] This represents the random error term, used to reflect construction fluctuations or measurement errors.

[0124] In the analysis unit, the correlation between the increase in building height and the consumption of building materials is quantified through mathematical models in order to identify deviations in construction efficiency or potential risks.

[0125] Fitting by least squares method and The linear relationship between quantitative material consumption and rapid growth. If... Significant deviations from theoretical values ​​(such as the theoretical efficiency of concrete pouring) may indicate construction problems (such as insufficient vibration or material waste). How to fit the data using the least squares method is a key question. and This is obviously well known to those skilled in the art, and the applicant will not elaborate further here.

[0126] Dynamic construction scheduling is carried out based on the analysis and calculation results. The steps include:

[0127] Set a scheduling period, which consists of at least three consecutive acquisition periods.

[0128] Within the scheduling period, among shear wall structures, core tube structures, and irregular column frame structures, the structure with the lowest increment in construction height is selected and regarded as the reference structure.

[0129] After the scheduling period ends, the structure corresponding to the reference structure (one of the shear wall structure, core tube structure, and irregular column frame structure) will be regarded as the priority construction object for construction scheduling.

[0130] Strategy learning is based on dynamic construction scheduling. Strategy learning includes obtaining the structure that is closest to the reference structure in the incremental period during the scheduling period, obtaining the building material consumption of this structure, taking the building material consumption as the control consumption, and prioritizing the construction of the reference structure based on this control consumption after the scheduling period ends.

[0131] Building upon the above, the strategy learning further includes issuing an early warning if the consumption of building materials for the reference structure is lower than the control consumption when construction is carried out on the reference structure in the future; otherwise, no warning is issued.

[0132] The system learns the optimal construction strategy (such as the shear wall material consumption being close to the ideal value within a certain period) to gradually improve overall efficiency, forming a closed loop of "monitoring-analysis-optimization-feedback" to adapt to changes in the construction environment (such as fluctuations in material quality).

[0133] As can be seen from the above, this application achieves precise construction scheduling, real-time risk warning, and optimal resource utilization through data-driven, dynamic scheduling, and closed-loop optimization.

[0134] This embodiment, in conjunction with the aforementioned AI-based dynamic construction scheduling and schedule risk early warning system, also proposes a working method for applying this system, as follows:

[0135] S10: Obtain relevant data for the target building, including building data; building data includes building structure, component information and spatial relationships, and building structure includes building frame.

[0136] S20: Differentiate building frames, including distinguishing shear wall structures, core tube structures and irregular column frame structures according to structural form, and obtain relevant information corresponding to shear wall structures, core tube structures and irregular column frame structures, including building height and the amount of building materials consumed corresponding to building height;

[0137] S30: Perform relevant processing based on the relevant information, including obtaining changes in construction height based on the consumption of building materials. The steps for obtaining this information are as follows:

[0138] The changes in building height are captured in 20-minute intervals, and the correlation between the consumption of building materials and building height is captured in each interval.

[0139] Based on the correlation effect, an evaluation cycle is defined as at least 5 consecutive acquisition periods. During the evaluation cycle, the height difference between the shear wall structure and the irregular column frame structure and the main observation object is acquired under the same consumption of building materials, with the core tube structure as the main observation object.

[0140] S40: Based on the height difference, relevant statistics are performed, including the increase in the construction height of shear wall structures and irregular column frame structures in each acquisition period;

[0141] S50: Based on the increment, analyze the relationship between the increment of construction height and the consumption of building materials in each acquisition period, and regard the consumption of building materials corresponding to the increment of construction height in each acquisition period as the reference consumption.

[0142] S60: Issue warnings based on associations.

[0143] In summary, this invention improves construction efficiency, reduces delay risks, and minimizes material waste by enabling precise construction scheduling, real-time project schedule warnings, optimized resource allocation, and data-driven management decisions. It also supports efficient construction of complex structures, providing an innovative solution for the intelligentization of the construction industry.

[0144] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An AI-based dynamic construction scheduling and schedule risk early warning system, characterized in that, include: The data acquisition module is used to acquire relevant data of the target building, including building data; The building data includes building structure, component information, and spatial relationships, and the building structure includes the building frame; The data processing module is used to schedule the construction of the target building based on the relevant data, including scheduling the construction based on the construction of the building frame; the data processing module includes a differentiation unit and a processing unit. The differentiation unit is used to differentiate the building frame, including differentiating shear wall structure, core tube structure and irregular column frame structure according to structural form, and obtaining relevant information corresponding to the shear wall structure, core tube structure and irregular column frame structure. The relevant information includes the building height and the consumption of building materials corresponding to the building height. The processing unit is used to perform relevant processing based on the relevant information. The relevant processing includes obtaining changes in the building height based on the consumption of building materials. The steps for obtaining the information are as follows: The changes in building height are acquired in 20-minute intervals, and the correlation between the consumption of building materials and the building height is acquired in each acquisition interval. Based on the aforementioned correlation, an evaluation cycle is defined as at least five consecutive acquisition periods. During the evaluation cycle, the height difference between the shear wall structure and the irregular column frame structure and the main observation object is acquired under the same building material consumption, with the core tube structure as the main observation object. A data fusion early warning module, comprising a statistical unit, an analysis unit, and an early warning unit; The statistical unit is used to perform relevant statistics based on the height difference. The relevant statistics include the statistical analysis of the increase in the construction height of the shear wall structure and the irregular column frame structure in each acquisition period. The analysis unit responds to the increment and is used to analyze the correlation between the increment of construction height and the consumption of building materials in each acquisition period, and regards the consumption of building materials corresponding to the increment of construction height in each acquisition period as the reference consumption. The early warning unit is used to issue an early warning based on the association.

2. The AI-based dynamic construction scheduling and schedule risk early warning system as described in claim 1, characterized in that, In the aforementioned early warning unit, the early warning steps include: Obtain the construction period for the target building and calculate the remaining duration of the construction period; The remaining time limit is divided equally. In the first half of the equally divided time limit, the time length corresponding to this time limit is divided based on the evaluation period. Within the segmented assessment period, if the consumption of building materials during the acquisition period included in a certain assessment period is lower than the reference consumption, the system will issue a warning that there is a risk of delay in the construction period; otherwise, no warning will be issued.

3. The AI-based dynamic construction scheduling and schedule risk early warning system as described in claim 1, characterized in that, In the processing unit, the correlation between the consumption of building materials and the construction height is obtained during each acquisition period, and calculated according to the following formula: ； In the formula, Indicates the first The increment of the building height within a given time period; This represents the material efficiency coefficient, which reflects the contribution of a unit amount of material to the height. Indicates the first The total amount of building materials consumed within a specific acquisition period; Indicates the first The cross-sectional area of ​​the construction during the acquisition period.

4. The AI-based dynamic construction scheduling and schedule risk early warning system as described in claim 3, characterized in that, It also includes calculations based on the following formula: ； Discretized form (summing every 20 minutes): ； In the formula, Indicates time Total building height at the time; Indicates time Material consumption rate at that time; Indicates time The cross-sectional area during construction; This indicates the time period number to be retrieved; Indicates time Perform differentiation; Represents an integer variable.

5. The AI-based dynamic construction scheduling and schedule risk early warning system as described in claim 1, characterized in that, In the analysis unit, the correlation between the increase in building height and the consumption of building materials during each acquisition period is analyzed and calculated according to the following formula: ； In the formula, Indicates the first The increment of the building height within a given time period; Represents the intercept term; Represents the regression coefficient; This represents the random error term, used to reflect construction fluctuations or measurement errors.

6. The AI-based dynamic construction scheduling and schedule risk early warning system as described in claim 5, characterized in that, Dynamic construction scheduling is carried out based on the analysis and calculation results. The steps include: A scheduling cycle is set, wherein the scheduling cycle consists of at least three consecutive acquisition periods; Within the aforementioned scheduling period, the structure with the lowest incremental construction height among the shear wall structure, core tube structure, and irregular column frame structure is selected and regarded as the reference structure. After the scheduling period ends, the structure corresponding to the reference structure will be regarded as the priority construction object for construction scheduling.

7. The AI-based dynamic construction scheduling and schedule risk early warning system as described in claim 6, characterized in that, Based on the dynamic construction schedule, strategy learning is performed. The strategy learning includes obtaining the structure whose increment is closest to the reference structure during the scheduling period, obtaining the building material consumption of this structure, taking the building material consumption as the control consumption, and prioritizing the construction of the reference structure based on this control consumption after the scheduling period ends.

8. The AI-based dynamic construction scheduling and schedule risk early warning system as described in claim 7, characterized in that, The strategy learning also includes issuing an early warning if the consumption of building materials for the reference structure is lower than the control consumption when construction is carried out on the reference structure in the future. Conversely, no warning will be issued.

9. A method applied to the AI-based dynamic construction scheduling and schedule risk early warning system as described in claim 1, characterized in that, Includes the following steps: Acquire relevant data about the target building, including building data; The building data includes building structure, component information, and spatial relationships, and the building structure includes the building frame; The building frame is differentiated, including distinguishing shear wall structure, core tube structure and irregular column frame structure according to structural form, and obtaining relevant information corresponding to the shear wall structure, core tube structure and irregular column frame structure. The relevant information includes the building height and the consumption of building materials corresponding to the building height. Based on the aforementioned relevant information, relevant processing is performed, including obtaining changes in construction height based on the consumption of building materials. The steps for obtaining this information are as follows: The changes in building height are acquired in 20-minute intervals, and the correlation between the consumption of building materials and the building height is acquired in each acquisition interval. Based on the aforementioned correlation, an evaluation cycle is defined as at least five consecutive acquisition periods. During the evaluation cycle, the height difference between the shear wall structure and the irregular column frame structure and the main observation object is acquired under the same building material consumption, with the core tube structure as the main observation object. Based on the height difference, relevant statistics are performed, including the increase in the construction height of the shear wall structure and the irregular column frame structure during each acquisition period; Based on the increment, the correlation between the increment of construction height and the consumption of building materials in each acquisition period is analyzed, and the consumption of building materials corresponding to the increment of construction height in each acquisition period is regarded as the reference consumption. Warnings will be issued based on the aforementioned associations.

Images