Intelligent scheduling method and system for construction site resources with multi-decision integration

Abstract

This application relates to a multi-decision fusion intelligent scheduling method and system for construction site resources, belonging to the field of resource scheduling technology. The method includes: acquiring historical construction characteristic parameters of the previous historical construction area and construction characteristic parameters of the current construction area to be scheduled; acquiring construction error parameters and construction tolerances of the target resource in the historical construction area; analyzing error adaptation parameters based on construction tolerances and construction error parameters, and analyzing characteristic adaptation parameters based on historical and current construction characteristic parameters; predicting error variation coefficients, compensating for error adaptation parameters, obtaining compensated error adaptation parameters, calculating scheduling adaptation parameters, and, when meeting scheduling requirements, selecting the optimal scheduling construction area for target resource scheduling. This invention solves the problem that traditional construction site resource scheduling relies solely on experience-based judgment, failing to combine construction characteristics and errors to dynamically adapt to different areas, leading to frequent equipment calibration to avoid errors during cross-regional resource scheduling, thus resulting in low scheduling efficiency.

Description

Technical Field

[0001] This application relates to the field of resource scheduling, and in particular to intelligent resource scheduling methods and systems for construction sites that integrate multiple decision-making processes. Background Technology

[0002] With the increasing demands for efficiency in resource utilization and precision in scheduling at construction sites in the construction engineering field, intelligent cross-regional equipment scheduling has become a key technological requirement to ensure efficient construction progress.

[0003] Currently, traditional construction site resource scheduling methods rely solely on experience-based judgments and fail to fully integrate construction characteristics and error data to dynamically adapt to different construction areas. This makes it impossible to address equipment error issues in cross-regional scheduling in a targeted manner. Not only does it easily lead to frequent equipment calibration after scheduling to avoid errors, but it also makes it difficult to form an efficient scheduling solution that adapts to multiple regions. Summary of the Invention

[0004] This application provides a multi-decision fusion intelligent scheduling method and system for construction site resources, which improves the traditional scheduling method that relies solely on experience judgment and does not combine construction characteristics and errors to dynamically adapt to different regions. This results in frequent equipment calibration to avoid errors and low scheduling efficiency in cross-regional scheduling, thus improving the adaptability and efficiency of construction site resource scheduling.

[0005] The embodiments of this application disclose the following technical solutions:

[0006] In a first aspect, embodiments of this application provide a method for intelligent scheduling of construction site resources based on multi-decision fusion, the method comprising:

[0007] Obtain the historical construction characteristic parameters of the previous historical construction area used for target resource scheduling, and obtain the construction characteristic parameters of multiple construction areas currently to be used for target resource scheduling;

[0008] Obtain construction error parameters for the target resource during construction within the historical construction area, and obtain multiple construction tolerances for multiple construction areas;

[0009] Based on multiple construction tolerances and construction error parameters, multiple error adaptation parameters are obtained through analysis. Based on historical construction characteristic parameters and multiple construction characteristic parameters, multiple characteristic adaptation parameters are obtained through analysis.

[0010] Based on multiple historical construction characteristic parameters and multiple construction characteristic parameters, construction error changes are predicted to obtain multiple error change coefficients. Multiple error adaptation parameters are compensated to obtain multiple compensated error adaptation parameters. Combined with multiple characteristic adaptation parameters, multiple scheduling adaptation parameters are calculated. When any scheduling adaptation parameter meets the scheduling requirements, the optimal scheduling construction area is selected and the target resource is scheduled.

[0011] Secondly, embodiments of this application provide a multi-decision fusion intelligent scheduling system for construction site resources, the system comprising:

[0012] The construction feature parameter acquisition module is used to acquire the historical construction feature parameters of the previous historical construction area used for target resource scheduling, and to acquire the construction feature parameters of multiple construction areas currently to be used for target resource scheduling.

[0013] The construction error tolerance acquisition module is used to acquire the construction error parameters of the target resource during construction in the historical construction area, and to acquire multiple construction tolerances for multiple construction areas;

[0014] The dual-adaptive parameter analysis module is used to analyze and obtain multiple error adaptation parameters based on multiple construction tolerance and construction error parameters, and to analyze and obtain multiple characteristic adaptation parameters based on historical construction characteristic parameters and multiple construction characteristic parameters.

[0015] The target resource scheduling decision module is used to predict the changes in construction errors based on multiple historical construction characteristic parameters and multiple construction characteristic parameters, obtain multiple error change coefficients, compensate multiple error adaptation parameters to obtain multiple compensated error adaptation parameters, and calculate multiple scheduling adaptation parameters by combining multiple characteristic adaptation parameters. When any scheduling adaptation parameter meets the scheduling requirements, the optimal scheduling construction area is selected and the target resource is scheduled.

[0016] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0017] This application proposes a multi-decision fusion intelligent scheduling method and system for construction site resources. By acquiring construction characteristic parameters and error tolerance data step by step, analyzing dual-adaptation parameters, predicting and compensating for changes in construction errors, calculating comprehensive scheduling adaptation parameters, and selecting the optimal scheduling construction area, it achieves accurate and efficient scheduling of target resources across multiple areas of the construction site. First, it acquires historical construction characteristic parameters of the previous historical construction area of ​​the target resource, as well as construction characteristic parameters of multiple current construction areas to be scheduled. Simultaneously, it collects the construction error parameters of the target resource in the historical construction areas and the construction tolerances of each construction area to be scheduled. Next, it calculates the ratio of construction tolerance to construction error parameters to obtain error adaptation parameters, and calculates the similarity between historical and current construction characteristic parameters to obtain feature adaptation parameters. Then, it constructs a construction error change prediction branch group to predict the error change coefficient of each area to compensate and reduce the error adaptation parameters, obtaining compensated error adaptation parameters. Finally, it combines the compensated error adaptation parameters and feature adaptation parameters to calculate scheduling adaptation parameters, compares them with preset thresholds to select the optimal scheduling area, and performs target resource scheduling.

[0018] The technical solution of this application solves the problems of relying solely on experience to judge adaptability in traditional construction site resource scheduling, ignoring error changes caused by regional characteristic differences, and the inability of single parameter evaluation to reflect the true adaptability level by integrating multi-dimensional parameters and dynamically correcting errors. It improves the scientificity, accuracy and efficiency of construction site resource scheduling, and provides reliable support for ensuring construction quality, reducing construction costs and promoting construction progress. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0020] Figure 1 A flowchart illustrating the intelligent scheduling method for construction site resources with multi-decision fusion provided in this application embodiment;

[0021] Figure 2 A schematic diagram of the structure of the intelligent scheduling system for construction site resources with multi-decision fusion provided in the embodiments of this application.

[0022] The components represented by each number in the attached diagram are explained below:

[0023] Construction characteristic parameter acquisition module 01, construction error tolerance acquisition module 02, dual-adaptive parameter analysis module 03, target resource scheduling decision module 04. Detailed Implementation

[0024] This application provides a multi-decision fusion intelligent scheduling method and system for construction site resources, which is used to solve the technical problems in the prior art where construction site resource scheduling relies solely on experience judgment and does not combine construction characteristics and errors to dynamically adapt to different construction areas, resulting in frequent equipment calibration to avoid errors and low scheduling efficiency when scheduling resources across regions.

[0025] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] In the description of this application, 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 indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0027] In the description of this application, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0028] Example 1, as shown in the appendix Figure 1 As shown, this application provides a multi-decision fusion intelligent scheduling method for construction site resources, the method comprising the following steps:

[0029] S110: Obtain the historical construction characteristic parameters of the previous historical construction area used for target resource scheduling, and obtain the construction characteristic parameters of multiple construction areas currently to be used for target resource scheduling;

[0030] In this embodiment of the application, in the scenario of cross-regional scheduling of construction site resources, in order to achieve accurate matching and scheduling of equipment resources and improve scheduling efficiency, it is necessary to first clarify the historical operation background of the target resources and the actual situation of the current construction area to be scheduled, so as to ensure that subsequent scheduling decisions can fully conform to the past operation patterns of equipment and the current construction needs of the area.

[0031] Specifically, the first step is to focus on the past scheduling trajectory of the target resource and determine the previous historical construction area where the operation was last completed. Based on the construction records of that area, historical construction characteristic parameters that reflect the core attributes of the area are extracted to provide historical reference for subsequent comparative analysis with the current area characteristics.

[0032] Furthermore, we need to identify all the construction areas that require target resource scheduling. For each construction area to be scheduled, we need to collect the corresponding construction characteristic parameters through on-site surveys and construction plan analysis. The collected parameter dimensions must be consistent with the historical construction characteristic parameters to ensure that the historical and current construction are comparable.

[0033] This step involves first identifying historical construction areas and extracting feature parameters to build a reference benchmark, and then simultaneously collecting feature parameters from multiple current construction areas to be scheduled to form a comparative dataset. This provides crucial data support for subsequent calculation of feature adaptation parameters and analysis of the equipment's adaptability potential in different current areas, and also lays the foundation for subsequent optimization of scheduling decisions by combining error parameters.

[0034] Step S110 in the method provided in this application embodiment includes:

[0035] Determine the previous historical construction area used for target resource scheduling, and obtain the historical construction characteristic parameters of the historical construction area, wherein the target resource is equipment resource;

[0036] Obtain multiple construction areas currently scheduled for target resource allocation, and collect multiple construction characteristic parameters for these construction areas.

[0037] In this embodiment of the application, in order to obtain construction feature data that has historical reference value and current adaptability, and to clarify the differences between the past operating environment of equipment resources and the current construction area to be scheduled, it is necessary to first obtain the previous historical construction area of ​​the equipment and extract feature parameters, and then simultaneously collect feature parameters of multiple current construction areas to be scheduled, so as to ensure that the adaptability potential of the equipment and different current areas can be accurately analyzed in the future.

[0038] Specifically, the first step is to determine the historical construction area of ​​the target resource (i.e., equipment resource) and obtain the historical construction characteristic parameters.

[0039] In determining the historical construction area, the area where the equipment last completed the operation should be used as the benchmark to avoid the reference value being reduced due to the excessive time span of historical data.

[0040] Meanwhile, the historical construction characteristic parameters obtained should cover core indicators directly related to equipment operation, such as the size and structural strength of the construction area. These parameters can clearly reflect the operational requirements of the historical construction area for the equipment, thus providing an accurate historical reference for comparing the current area characteristics and judging the equipment's suitability.

[0041] Furthermore, after identifying historical construction areas and obtaining their historical construction characteristic parameters, the characteristic parameters of multiple construction areas currently awaiting target resource scheduling are collected simultaneously.

[0042] During the data collection process, it is necessary to ensure that the feature parameters collected for each construction area to be scheduled are consistent with the historical construction feature parameters. For example, they should also include indicators such as size specifications and structural strength, so that historical and current data can be directly compared, and errors in equipment compatibility judgment caused by inconsistent parameter dimensions can be avoided.

[0043] At the same time, it is necessary to ensure the accuracy of the collected data through on-site surveys, analysis of construction plans, and verification of equipment operation requirements. For example, professional surveying tools should be used to measure the size of the construction area, and regional geological survey reports or construction design documents should be consulted to obtain the structural strength, so as to prevent data errors from affecting the accuracy of subsequent scheduling decisions.

[0044] Furthermore, the historical construction feature parameters are associated with the current construction feature parameters. For example, attribute labels such as "corresponding historical construction area - historical size specifications - historical result strength" are added to the feature parameters of each current construction area to be scheduled. This ensures that the corresponding historical construction feature parameters can be quickly indexed for comparison during subsequent calculation and analysis, thereby improving the efficiency of data retrieval and analysis.

[0045] At the same time, the completeness of the collected parameters needs to be verified. If the strength parameters of a certain construction area to be scheduled are found to be missing, the survey needs to be supplemented in time to avoid the inability of the area to participate in the subsequent adaptability analysis due to incomplete construction characteristic parameters, which would affect the comprehensiveness of the scheduling area selection.

[0046] For example, if the target resource is a concrete pouring equipment, and the previous historical construction area used for scheduling is the basement construction area of ​​a residential project, the obtained historical construction characteristic parameters include the following dimensions: working surface length 20m, width 15m, height 3m, and structural strength: foundation bearing capacity 250kPa.

[0047] In addition, the multiple construction areas where the equipment is to be scheduled include the garage area of ​​a commercial complex and the ground area of ​​a factory. The collected characteristic parameters of the garage area are 25m in length, 18m in width, 4m in height, and 300kPa in foundation bearing capacity. The characteristic parameters of the factory ground area are 18m in length, 12m in width, 2.5m in height, and 220kPa in foundation bearing capacity.

[0048] The parameter acquisition method described above ensures the consistency of historical and current construction characteristic parameters in terms of dimensions, which can be directly used to compare the adaptability of equipment in different regions. It also fully obtains the differences in the operational requirements of equipment in each region, laying a data foundation for subsequent calculation of characteristic adaptation parameters, optimization of scheduling decisions based on error data, and selection of the optimal scheduling region.

[0049] S120: Obtain the construction error parameters of the target resource during construction in the historical construction area, and obtain multiple construction tolerances for multiple construction areas;

[0050] In this embodiment of the application, in order to clarify the error level of the equipment in the past operation and to understand the acceptable range of error for the current construction area to be scheduled, it is necessary to extract the construction error parameters of the equipment from the historical construction data, and at the same time determine the maximum allowable error of each construction area to be scheduled, so as to ensure that the error adaptation parameters can be accurately calculated in the future, and provide a key basis for judging the compatibility between the equipment and the current area.

[0051] First, obtain the construction error parameters of the target resource in the historical construction area to clarify the error benchmark of the equipment's past operations, and provide a reference for subsequent analysis of the error compatibility between the equipment and the current construction area to be scheduled.

[0052] Specifically, relying on the complete construction data records of the current construction area to be scheduled, these records need to cover real-time operating data during equipment operation, detection data of construction results, etc., such as the pouring thickness deviation record when the equipment poured concrete in the historical construction area, and the measurement data of the offset of the rebar binding position, etc.

[0053] Furthermore, based on construction data records, through verification and comparison using professional measurement tools and extraction of construction result acceptance reports, the actual error values ​​generated by the equipment in historical operations are accurately measured to form construction error parameters. These construction error parameters directly reflect the error performance of the equipment in similar construction scenarios.

[0054] Furthermore, the construction tolerances of multiple currently scheduled construction areas are acquired simultaneously to determine the upper limit of the tolerance for construction errors in each area, providing a basis for judging whether the equipment errors meet the area requirements.

[0055] Construction tolerance refers to the maximum permissible error in construction within each area. It needs to be determined in conjunction with the construction specifications, design requirements, and engineering quality standards of each construction area to be scheduled. For example, if a construction area to be scheduled is a precision equipment installation area, the maximum permissible positional error of the equipment operation is ±2mm, and this value is the construction tolerance of that area.

[0056] During the acquisition process, it is necessary to check the construction design drawings and engineering quality acceptance specifications of each region, or communicate and confirm with the design unit and supervision unit to ensure that the construction tolerance data of each construction area to be scheduled is accurate. This is to avoid the subsequent error adaptation parameter calculation being inaccurate due to tolerance value deviation, which would affect the equipment compatibility judgment.

[0057] This step, by obtaining the historical construction error parameters of the equipment and the construction tolerance of the current construction area to be scheduled, clarifies the error benchmark of the equipment itself and grasps the upper limit of the error tolerance of the current area. Together, they provide core data for subsequent calculation of error adaptation parameters, so as to ensure that the equipment scheduling decision is more in line with the actual construction needs.

[0058] Step S120 in the method provided in this application embodiment includes:

[0059] Based on the construction data records of the target resources carried out in the historical construction area, construction error parameters are measured and obtained;

[0060] Obtain the maximum permissible error for construction in multiple construction areas, and use it as multiple construction tolerances.

[0061] In this embodiment of the application, in order to clarify the error level of the target resource in the past operation and to know the upper limit of the tolerance of the construction error of the current construction area to be scheduled, it is necessary to accurately extract the equipment error parameters from the historical construction data and determine the construction tolerance in combination with the requirements of each construction area to be scheduled, so as to ensure the accuracy of subsequent error adaptation parameter calculation and improve the accuracy and efficiency of equipment scheduling.

[0062] First, construction error parameters are obtained based on the construction data records of the target resource within the historical construction area.

[0063] These construction data records must comprehensively cover the entire equipment operation process, including real-time parameter records during equipment operation and quality inspection records of construction results, to ensure that the data can fully reflect the actual error situation of the equipment in historical operations.

[0064] For example, if the target resource is a rebar cutter, the construction data records of its historical construction area must include information such as the length deviation measurement value after cutting different batches of rebar and the flatness test results of the cut surface. These data are the core basis for calculating the equipment error.

[0065] Furthermore, after obtaining complete construction data records, construction error parameters are measured and extracted using professional methods.

[0066] Specifically, the method of "data verification and comparison and acceptance report extraction" can be adopted: on the one hand, the work results left in the historical construction area are measured a second time using the same model of professional measuring tools as in the historical operation, and the error data is verified; on the other hand, the confirmed error values ​​are extracted from the quality acceptance reports and supervision inspection records of the historical construction, the two types of data are compared and calibrated, abnormal data are eliminated, and finally the construction error parameters that can truly reflect the normal operation level of the equipment are determined.

[0067] For example, for concrete pump trucks pouring concrete in historical construction areas, by reviewing the verticality deviation of the poured walls and combining it with the records in the acceptance report, the average verticality error is determined to be ±3mm after calibration. This value is the construction error parameter of the pump truck.

[0068] Furthermore, the construction tolerances of multiple construction areas to be scheduled are obtained simultaneously. Construction tolerance refers to the maximum permissible error for construction in each area, which must be determined strictly in conjunction with the construction specifications, engineering design requirements, and quality standards of each construction area to be scheduled.

[0069] For example, if the construction area to be scheduled is the cleanroom floor construction of an electronics factory, according to the "Cleanroom Design Code", the maximum allowable error for floor flatness is ±1mm, which is the construction tolerance of the construction area to be scheduled; if the construction area to be scheduled is the base construction of an ordinary municipal road, according to the "Urban Road Engineering Construction and Quality Acceptance Code", the maximum allowable error for base elevation is ±5cm, which is the construction tolerance of the construction area to be scheduled.

[0070] At the same time, the accuracy of the data needs to be verified through multiple channels when determining construction tolerances.

[0071] Specifically, firstly, the construction design drawings and technical specifications of each construction area to be scheduled are reviewed to extract the allowable error range marked in the drawings; secondly, the design and supervision units are communicated and confirmed to clarify the tolerance requirements for special construction links; finally, the obtained tolerance data is classified and organized to ensure that the tolerance parameters of each construction area to be scheduled correspond to clear construction links and quality standards, so as to avoid deviations in subsequent compatibility analysis due to ambiguity in the tolerance parameters.

[0072] For example, if the target resource is a tower crane and its historical construction area is a residential project construction site, by reviewing the construction data records (including the record of the deviation of the landing point of the hoisted object and the verticality test data of the tower body) and extracting the acceptance report, the construction error parameters are determined to be an average horizontal deviation of the landing point of the hoisted object of ±8cm and a verticality deviation of the tower body of ±0.3%.

[0073] Furthermore, the three construction areas currently awaiting scheduling are a commercial complex project (maximum permissible error for horizontal deviation of the load landing point ±10cm, tower verticality deviation ±0.4%), a hospital project (maximum permissible error for horizontal deviation of the load landing point ±6cm, tower verticality deviation ±0.2%), and a warehousing center project (maximum permissible error for horizontal deviation of the load landing point ±12cm, tower verticality deviation ±0.5%). Through reviewing the design drawings of each project and confirming with relevant parties, it was ultimately determined that the construction tolerances for these three areas are consistent with the aforementioned values.

[0074] Ultimately, the construction error parameters and construction tolerances obtained through the above steps not only clarify the error benchmark of the equipment itself, but also clarify the error tolerance boundary of each construction area to be scheduled. Together, they provide accurate data for subsequent calculation of error adaptation parameters.

[0075] S130: Based on multiple construction tolerances and construction error parameters, multiple error adaptation parameters are obtained through analysis. Based on historical construction characteristic parameters and multiple construction characteristic parameters, multiple characteristic adaptation parameters are obtained through analysis.

[0076] In this embodiment of the application, in order to quantify the compatibility between the equipment and each construction area to be scheduled from two dimensions of error tolerance and feature matching, and to avoid the one-sidedness of the compatibility analysis due to relying on only a single dimension, it is necessary to combine the obtained construction tolerance, construction error parameters and historical and current construction feature parameters to calculate the error adaptation parameters and feature adaptation parameters respectively, so as to form a multi-dimensional compatibility evaluation basis and provide data support for the subsequent selection of the optimal scheduling area.

[0077] Specifically, the analysis and calculation of multiple error adaptation parameters are carried out first. Among them, the error adaptation parameters are obtained by calculating the ratio of the construction tolerance of each construction area to be scheduled to the construction error parameters obtained in the early stage. This ratio directly reflects the tolerance of the construction area to be scheduled to the historical operation error of the equipment.

[0078] Furthermore, after completing the error adaptation parameter analysis, the analysis and calculation of multiple characteristic adaptation parameters are carried out simultaneously.

[0079] Among them, the characteristic adaptation parameters are obtained by analyzing the similarity between historical construction characteristic parameters and construction characteristic parameters of each construction area to be scheduled. The higher the similarity, the closer the core construction attributes of the construction area to be scheduled are to the historical construction areas that the equipment has adapted to in the past. When the equipment operates in this area, it can quickly adapt without adjusting too many operating parameters or performing complex preparations.

[0080] This step evaluates the compatibility between the equipment and the construction area to be scheduled from different dimensions by calculating the error adaptation parameter and the feature adaptation parameter respectively. Together, they provide a quantitative basis for subsequent optimization of the compatibility judgment by combining the error change coefficient and finally selecting the optimal scheduling area.

[0081] Step S130 in the method provided in this application embodiment includes:

[0082] Calculate the ratios of the multiple construction tolerances and construction error parameters respectively to obtain multiple error adaptation parameters;

[0083] Based on the historical construction characteristic parameters and multiple construction characteristic parameters, multiple characteristic adaptation parameters are obtained through analysis.

[0084] In this embodiment of the application, in order to quantify the adaptability level between the target resource and each construction area to be scheduled from two dimensions: error tolerance and feature matching degree, it is necessary to combine construction tolerance, construction error parameters and historical and current construction feature parameters to calculate error adaptation parameters and feature adaptation parameters respectively, so as to form a multi-dimensional adaptability evaluation basis, and provide data support for subsequent selection of the optimal scheduling area and improvement of resource scheduling efficiency.

[0085] First, multiple error adaptation parameters are calculated to quantify the degree to which each scheduled construction area can accept historical operational errors of the target resources from the perspective of error tolerance.

[0086] Specifically, the formula for calculating the error adaptation parameter can be expressed as "error adaptation parameter = construction tolerance of a single construction area to be scheduled / construction error parameter". This ratio directly reflects the tolerance of the construction area to be scheduled for historical equipment operation errors.

[0087] The larger the error adaptation parameter, the more sufficient the maximum allowable construction error in the scheduled construction area is compared with the actual error margin generated by the equipment in the past. The lower the possibility that the equipment will need to stop operation for maintenance and calibration due to the error exceeding the allowable range when operating in the area, the stronger the adaptability.

[0088] For example, if the construction error parameter of the target resource in the historical construction area is ±4mm (i.e. the average actual error of the equipment in the past operation), and the construction tolerance of a certain construction area A to be scheduled is ±8mm, then the error adaptation parameter of this area is 8 / 4=2; the construction tolerance of another construction area B to be scheduled is ±6mm, and its error adaptation parameter is 6 / 4=1.5. Area A has a larger error adaptation parameter and a stronger tolerance for equipment errors.

[0089] During the calculation process, it is necessary to strictly ensure that the dimensions of the construction tolerance and construction error parameters of each construction area to be scheduled are consistent. For example, the dimensional deviation should be measured in "millimeters" and the pressure error should be measured in "kilopascals" to avoid errors in the ratio calculation due to inconsistent units, which would affect the accuracy of the error adaptation parameters.

[0090] Furthermore, after completing the calculation of error adaptation parameters, multiple feature adaptation parameters are analyzed and obtained to supplement the evaluation of the adaptability of target resources and each construction area to be scheduled from the perspective of construction feature matching.

[0091] The method provided in this application embodiment, "analyzing and obtaining multiple feature adaptation parameters based on the historical construction feature parameters and multiple construction feature parameters", includes:

[0092] The similarity between the historical construction feature parameters and multiple construction feature parameters is calculated and used as multiple feature adaptation parameters.

[0093] In this embodiment of the application, in order to quantify the degree of adaptation between the target resource and each construction area to be scheduled from the dimension of construction feature matching, it is necessary to determine the feature adaptation parameters by calculating the similarity between historical and current construction feature parameters, so as to form an objective and quantifiable feature adaptation basis.

[0094] Specifically, the first step is to clarify the range of historical construction feature parameters and current construction feature parameters that need to be included in the similarity calculation. These parameters need to be selected around the core dimensions of equipment operation adaptability, such as the working surface dimensions (length, width, height) and structural strength (foundation bearing capacity, working surface load limit), to ensure that the selected parameters can directly reflect the interaction requirements between the equipment and the regional environment during operation.

[0095] Furthermore, after determining the parameter range, the similarity is calculated using the "relative deviation weighting method" for all construction feature parameters to accurately quantify the degree of matching between historical and current construction features.

[0096] Specifically, firstly, the similarity contribution value of each construction feature parameter is calculated as "1 - |current construction feature parameter value - historical construction feature parameter value| / historical construction feature parameter value". Then, based on the influence weight of each construction feature parameter on equipment adaptation, the contribution values ​​of each construction feature parameter are weighted and summed to obtain the comprehensive similarity of the construction feature parameters, which serves as the feature adaptation parameter for the corresponding construction area to be scheduled.

[0097] For example, the working face length of a historical construction area is 20m and the foundation bearing capacity is 250kPa. The working face length of a certain construction area to be scheduled is 19m and the foundation bearing capacity is 245kPa. If the length weight is 0.3 and the strength weight is 0.7, the length similarity contribution value is 1-|19-20| / 20=0.95, the strength similarity contribution value is 1-|245-250| / 250=0.98, and the comprehensive similarity of construction feature parameters (i.e. feature adaptation parameters) is 0.95×0.3+0.98×0.7=0.971.

[0098] Among them, the larger the value of the feature adaptation parameter, the higher the matching degree of the construction characteristics between the construction area to be scheduled and the historical construction area. When the equipment is working in the construction area, it can quickly adapt without significantly adjusting the operating parameters or performing complex function debugging, so as to effectively reduce the preparation time and maintenance cost after scheduling.

[0099] Meanwhile, the validity of the parameter data needs to be verified during the calculation of feature adaptation parameters. If a core parameter of a construction area to be scheduled is missing or has an outlier, the data needs to be improved through supplementary surveys or confirmation with the design unit to avoid distortion of similarity calculation results due to data problems.

[0100] In addition, the rationality of the calculated feature adaptation parameters needs to be verified. If the feature adaptation parameters of a certain construction area to be scheduled are significantly lower than those of other areas, it is necessary to review whether the parameter selection is accurate and whether the weight setting is reasonable, so as to ensure that the feature adaptation parameters can truly reflect the feature matching level between the equipment and the area.

[0101] The similarity acquisition method based on weighted integration described above can objectively quantify the degree of matching between historical and current construction features, providing accurate feature dimension data for subsequent combination with error adaptation parameters to form a multi-dimensional scheduling adaptation evaluation basis.

[0102] S140: Based on multiple historical construction characteristic parameters and multiple construction characteristic parameters, predict the changes in construction errors to obtain multiple error change coefficients. Compensate multiple error adaptation parameters to obtain multiple compensated error adaptation parameters. Combine multiple characteristic adaptation parameters to calculate multiple scheduling adaptation parameters. When any scheduling adaptation parameter meets the scheduling requirements, select the optimal scheduling construction area and perform target resource scheduling.

[0103] In this embodiment of the application, in order to eliminate the interference of equipment error changes caused by the differences in construction characteristics of different construction areas to be scheduled on the adaptability judgment, it is necessary to first obtain the error change coefficient by predicting the construction error change to compensate for the error adaptation parameter, then combine the feature adaptation parameter to calculate the scheduling adaptation parameter, and finally select the optimal area based on the parameter threshold, so as to ensure that the scheduling decision not only conforms to the actual change law of equipment error, but also takes into account the feature matching level, thereby improving the scheduling accuracy and construction safety.

[0104] Specifically, a construction error change prediction branch group is first constructed to predict construction error changes, and then multiple error change coefficients are obtained to correct the equipment error offset problem caused by the difference in characteristics between the construction area to be scheduled and the historical construction area.

[0105] Among them, the construction error change prediction branch group is a cluster of machine learning models built based on historical construction data. By collecting past construction records from multiple construction areas, the change range of equipment error under different combinations of construction feature parameters is extracted to form a sample dataset. After multiple random divisions for training and testing, multiple construction error change prediction branches are constructed and verified, and finally integrated to form a branch group with error prediction capabilities.

[0106] Furthermore, for each construction area to be scheduled, the number of branches to be selected for that area is determined based on the ratio of its construction tolerance to the maximum construction tolerance among all construction areas to be scheduled, combined with the total number of construction error change prediction branches within the construction error change prediction branch group.

[0107] Furthermore, according to the determined number of branches, a corresponding number of prediction branches are randomly selected from the construction error change prediction branch group to form a construction error change prediction branch group specific to this region. Then, the combination of the construction characteristic parameters of this region and the historical construction characteristic parameters is input into the branch group. Each branch will output an error change coefficient. By averaging all the output coefficients, the final error change coefficient of this region can be obtained, so as to quantitatively reflect the trend of equipment error change caused by regional characteristic differences.

[0108] Furthermore, multiple error variation coefficients are used to compensate and reduce multiple error adaptation parameters in order to correct the problem of increased equipment error that may be caused by regional feature differences, so that the error adaptation parameters are more in line with the actual operation scenario.

[0109] Furthermore, by combining multiple feature adaptation parameters, a weighted summation method is used to obtain the scheduling adaptation parameters for each construction area to be scheduled, so as to comprehensively reflect the area's tolerance for equipment errors and feature matching level. The larger the value of the scheduling adaptation parameter, the stronger the area's adaptability.

[0110] Simultaneously, it is determined whether any scheduling adaptation parameter is greater than or equal to a preset scheduling adaptation parameter threshold (the threshold needs to be set in conjunction with construction quality requirements and equipment performance standards). If so, the area with the largest scheduling adaptation parameter is selected as the optimal scheduling construction area, and target resource scheduling is carried out directly.

[0111] Conversely, if the scheduling adaptation parameters of all regions are less than the preset scheduling adaptation parameter threshold, it indicates that the current equipment status is not well adapted to each region. The target resources need to be prepared first, and the scheduling should be re-evaluated after the equipment performance is optimized.

[0112] This step ensures the accuracy of error assessment by first predicting error changes and compensating for error adaptation parameters. Then, it calculates comprehensive scheduling indicators by combining characteristic adaptation parameters. Finally, it selects the optimal scheduling construction area based on the scheduling adaptation parameter threshold, providing a scientific basis for the efficient and accurate scheduling of target resources. This avoids misjudgment caused by ignoring regional characteristic differences or scheduling deviation caused by judging a single parameter.

[0113] Step S140 in the method provided in this application embodiment includes:

[0114] Obtain the predicted branch group of construction error changes;

[0115] Based on the ratio of each construction tolerance to the maximum construction tolerance, and combined with the total number of construction error change prediction branches within the construction error change prediction branch group, the number of multiple branches is determined.

[0116] Based on the number of branches, construction error change prediction branches are randomly selected to obtain multiple construction error change prediction branch groups. Each construction characteristic parameter and historical construction characteristic parameter combination are input separately, and the output is averaged to obtain multiple error change coefficients.

[0117] Multiple error variation coefficients are used to perform compensation and reduction calculations on multiple error adaptation parameters to obtain multiple compensation error adaptation parameters.

[0118] Multiple scheduling adaptation parameters are calculated based on multiple compensation error adaptation parameters and multiple feature adaptation parameters;

[0119] Determine whether any scheduling adaptation parameter is greater than or equal to the preset scheduling adaptation parameter threshold.

[0120] If so, the scheduling construction area corresponding to the largest scheduling adaptation parameter is selected as the optimal scheduling construction area for target resource scheduling.

[0121] If not, then prepare the target resources and then schedule them.

[0122] In this embodiment of the application, in order to avoid the scheduling decision deviating from the actual operation requirements due to the judgment based solely on the initial error adaptation parameters, it is necessary to first construct a construction error change prediction branch group to obtain the error change coefficient, then use the coefficient to compensate and correct the error adaptation parameters, and finally combine the feature adaptation parameters to calculate the scheduling adaptation parameters and select the optimal region, so as to ensure that the target resource scheduling not only conforms to the actual change law of equipment error, but also matches the regional construction characteristics.

[0123] Specifically, firstly, multiple construction error change prediction branches are constructed based on machine learning, and then integrated to obtain a construction error change prediction branch group, which provides a basis for accurately obtaining the error change coefficients of each construction area to be scheduled.

[0124] The method provided in this application embodiment, "obtaining the predicted branch group of construction error changes", includes:

[0125] Based on historical construction record data from multiple construction areas, a set of sample construction characteristic parameter combinations was collected, and the variation range of construction error parameters in two construction areas under different sample construction characteristic parameter combinations was collected. The sample error variation coefficient set was then labeled and obtained.

[0126] The sample construction feature parameter combination set and sample error change coefficient set are randomly divided multiple times to obtain multiple sets of construction error change prediction training data.

[0127] Based on machine learning, multiple branches for predicting construction error changes are constructed. These branches are then trained and tested using the multiple sets of training data for predicting construction error changes until training is complete, thus obtaining a group of branches for predicting construction error changes.

[0128] In this embodiment of the application, in order to quantify the changes in equipment error caused by the differences in characteristics of different construction areas to be scheduled, it is necessary to obtain the construction error change prediction branch group through the steps of historical construction data collection and labeling, sample division, model construction and training and testing, so as to provide a reliable prediction tool for subsequent calculation of error change coefficient and compensation and correction error adaptation parameters.

[0129] Specifically, the first step is to collect and label sample data. The core is to extract a set of sample construction feature parameters from complete historical construction records of multiple construction areas.

[0130] Among them, these sample construction feature parameter combinations need to cover the core dimensions of equipment operation adaptation and reflect the feature differences of different regions, such as "working surface length 18m + foundation bearing strength 220kPa", "working surface length 25m + foundation bearing strength 300kPa", "working surface length 20m + foundation bearing strength 250kPa", etc., to ensure that the combination set can cover common regional feature combination scenarios.

[0131] Meanwhile, for each set of sample construction feature parameters, the actual change range of construction error parameters is collected when the equipment switches between the corresponding two construction areas. For example, when the equipment switches from a historical construction area with "working surface length 20m + foundation bearing strength 250kPa" to a new area with "working surface length 18m + foundation bearing strength 220kPa", the pouring thickness error increases from ±3mm to ±3.5mm. The value corresponding to the change range is the error change coefficient corresponding to that sample combination. Based on this, all sample combinations are labeled to form a complete set of sample error change coefficients, providing accurate label data for subsequent model training.

[0132] Furthermore, after completing the sample data collection and labeling, the sample construction feature parameter combination set and sample error change coefficient set are randomly divided multiple times to obtain multiple sets of construction error change prediction training data.

[0133] The partitioning process must follow the principle of "uniform sample distribution" to ensure that each set of training data contains different types of construction feature parameter combinations and covers different ranges of error variation coefficients, so as to avoid model training biased towards a certain feature scenario due to sample distribution imbalance.

[0134] For example, the samples are divided into a training set, a validation set, and a test set in a 7:2:1 ratio. The training set is used for iterative updates of model parameters, the validation set is used to monitor model performance during training, and the test set is used to finally verify the model's prediction accuracy. Each division forms a complete set of training data for predicting changes in construction errors. This division is repeated 5-8 times to obtain multiple sets of training data. Subsequently, each set of data is used to train a prediction branch to improve the generalization ability of the branch cluster.

[0135] Furthermore, multiple branches for predicting construction error changes were constructed based on machine learning, and supervised training and testing were carried out using multiple sets of training data for predicting construction error changes.

[0136] Specifically, considering the need for error change prediction, Gradient Boosting Tree (XGBoost) was chosen as the basic model architecture. XGBoost effectively handles nonlinear relationships between features and adapts to the complex correlation between construction features and error changes.

[0137] When constructing each branch for predicting changes in construction errors, the model parameters should be set reasonably according to the scale and feature complexity of the corresponding training data: if the number of samples in the training data exceeds 10,000 and the feature dimension is more than 5, the number of decision trees in the gradient boosting tree can be set to 100-150 and the maximum tree depth to 8-10; if the number of samples is less than 5,000 and the feature dimension is less than 3, the number of decision trees can be reduced to 50-80 and the maximum tree depth can be set to 5-6 to avoid overfitting or underfitting of the model.

[0138] During training, the sample construction feature parameters of each training data set are input into the corresponding prediction branch. The model outputs the error variation coefficient of the prediction. The predicted value is then compared with the true value in the sample error variation coefficient set. The prediction deviation is quantified by calculating the mean square error (MSE). The model parameters are continuously adjusted based on the gradient descent algorithm in the existing technology to optimize the prediction accuracy.

[0139] Meanwhile, after every 10-15 rounds of training, the model performance is tested using the validation set data of the corresponding group. If the prediction error on the validation set no longer decreases or shows an upward trend for three consecutive rounds, it indicates that the model has converged, and training of that branch is stopped.

[0140] In addition, if it is found during training that the prediction error of the model for a certain type of feature combination is consistently high, then it is necessary to supplement the sample data of that type of feature combination and reintegrate it into the training set for training until the prediction error on the validation set stabilizes within a preset range, such as MSE being less than 0.001.

[0141] Furthermore, after all prediction branches have been trained, a final performance test is conducted using the test set data of the corresponding group. Only branches whose prediction error on the test set meets the requirements (i.e., MAE is less than 0.005) are retained, while those that do not meet the performance requirements are removed, in order to ensure that each branch has reliable error prediction capabilities.

[0142] Finally, all compliant branches are integrated to form a construction error change prediction branch group. Each branch in this construction error change prediction branch group can output a relatively accurate error change coefficient based on the input combination of construction feature parameters. Moreover, the multi-branch design can reduce the prediction bias of a single model through subsequent averaging processing, providing stable and accurate tool support for obtaining the error change coefficients of each construction area to be scheduled.

[0143] For example, if the collected sample construction feature parameter combination set contains 2000 combinations of three types of features: "work surface size-strength-process", and the sample error variation coefficient set covers the error variation range of 0.01-0.15, the sample is randomly divided into 8 sets of training data, and 8 gradient boosting tree prediction branches are constructed accordingly.

[0144] The first set of training data contained 1400 training samples, 400 validation samples, and 200 test samples. During training, the number of decision trees was set to 120, with a maximum tree depth of 8. After 25 rounds of training, the validation set MSE stabilized at 0.0008, and the test set MAE was 0.004, meeting the performance requirements. The remaining seven branches all met the standards after training and testing, and were ultimately integrated into an eight-branch group for construction error change prediction. This group can subsequently output reliable error change coefficient prediction results for different combinations of features of the construction areas to be scheduled.

[0145] Furthermore, after obtaining the predicted branch group of construction error changes, the number of branches needs to be determined based on the construction tolerance of the construction area to be scheduled and the characteristics of the branch group, so as to carry out targeted prediction of error change coefficients.

[0146] Specifically, firstly, the construction tolerances of all construction areas to be scheduled are counted, and the largest construction tolerance is selected. Then, for each construction area to be scheduled, the formula "(1 - construction tolerance of a single construction area / maximum construction tolerance) × total number of branches predicted by the construction error change within the branch group" is used to calculate and round the result to obtain the number of branches to be selected for each area.

[0147] For example, if the total number of branches for predicting construction error changes is 8, and the maximum construction tolerance in all construction areas to be scheduled is ±10mm, and the construction tolerance of a certain construction area A to be scheduled is ±5mm (the ratio of a single tolerance to the maximum tolerance is 0.5), then the number of branches in this area is (1-0.5)×8=4; the construction tolerance of another construction area B to be scheduled is ±8mm (the ratio is 0.8), then the number of branches is (1-0.8)×8=2. By allocating more branches to construction areas with smaller construction tolerances, the accuracy of the error change coefficient prediction can be improved.

[0148] Furthermore, for each construction area to be scheduled, a corresponding number of construction error change prediction branches are randomly selected from the construction error change prediction branch group to form a construction error change prediction branch group specific to that area.

[0149] Furthermore, the combination of construction feature parameters and historical construction feature parameters for each construction area to be scheduled is input into its corresponding construction error change prediction branch group. Each branch will output an error change coefficient for that area based on the input feature combination.

[0150] After all branches have finished outputting, the arithmetic mean of all error change coefficients within the same region's construction error change prediction branch group is taken to obtain the final error change coefficient for that region.

[0151] For example, if the construction error change prediction branch group of the construction area A to be scheduled contains 4 construction error change prediction branches, and the output error change coefficients are 0.04, 0.05, 0.04 and 0.05 respectively, the error change coefficient after mean value processing is 0.045 ((0.04+0.05+0.04+0.05)=0.045). This value can quantitatively reflect the proportion of equipment error increase caused by regional characteristic differences.

[0152] Furthermore, the formula “error adaptation parameter × (1 - error variation coefficient)” is used to compensate and reduce the multiple error adaptation parameters calculated in the previous stage, so as to obtain multiple compensated error adaptation parameters.

[0153] For example, if the initial error adaptation parameter of a certain construction area to be scheduled is 2.0 and the corresponding error variation coefficient is 0.045, then the compensation error adaptation parameter is 2.0×(1-0.045)=1.91. Through compensation reduction processing, the influence of the increase in equipment error due to regional feature differences on the adaptability judgment is corrected, making the error adaptation parameter more in line with the error tolerance capability under the actual operation scenario.

[0154] Furthermore, after completing the calculation of the compensation error adaptation parameters, the scheduling adaptation parameters for each construction area to be scheduled are obtained by weighted calculation, combining multiple characteristic adaptation parameters obtained in the early stage.

[0155] The weighting values ​​need to be set according to the importance of error and feature in the construction scenario. For example, in the scenario of precision equipment installation, the error compensation adaptation parameter has a greater impact on construction quality, so the weight is set to 0.6, and the feature adaptation parameter weight is set to 0.4. In the scenario of ordinary roadbed construction, the two have a relatively balanced impact on scheduling adaptability, so the weights can be set to 0.5:0.5.

[0156] For example, if the compensation error adaptation parameter of a certain construction area to be scheduled is 1.91 and the feature adaptation parameter is 0.94, the scheduling adaptation parameter is calculated with a weight of 0.6:0.4 as 1.91×0.6+0.94×0.4=1.522. This scheduling adaptation parameter comprehensively reflects the actual tolerance of the area to equipment errors and the feature matching level. The larger the value, the stronger the adaptability of the area.

[0157] Furthermore, after obtaining the scheduling adaptation parameters for all construction areas to be scheduled, they need to be compared with the preset scheduling adaptation parameter thresholds to determine whether any parameter is greater than or equal to the threshold.

[0158] The preset scheduling adaptation parameter threshold needs to be determined in conjunction with construction quality standards, equipment performance limits and project schedule requirements. For example, precision construction scenarios have higher requirements for adaptability, so the scheduling adaptation parameter threshold is set to 1.4; the scheduling adaptation parameter threshold for ordinary construction scenarios can be appropriately reduced to 1.2.

[0159] Specifically, if there are suitable scheduling adaptation parameters, the scheduling adaptation parameter with the largest value is selected from these parameters, and the corresponding construction area to be scheduled is the optimal scheduling construction area, and the target resource (equipment resource) scheduling is carried out directly.

[0160] Conversely, if the scheduling adaptation parameters of all construction areas to be scheduled are less than the preset scheduling adaptation parameter threshold, it indicates that the current equipment status is not well adapted to each area. The target resources need to be prepared first, such as adjusting the equipment operation accuracy, replacing worn core components, and recalibrating the equipment operating parameters. After the equipment performance is optimized, the scheduling adaptation parameters of each area are recalculated, and the scheduling process is then executed.

[0161] For example, if there are three construction areas to be scheduled, the compensation error adaptation parameter of area 1 is 1.91, the feature adaptation parameter is 0.94, and the scheduling adaptation parameter is 1.522; the compensation error adaptation parameter of area 2 is 1.72, the feature adaptation parameter is 0.90, and the scheduling adaptation parameter is 1.392; and the compensation error adaptation parameter of area 3 is 1.55, the feature adaptation parameter is 0.86, and the scheduling adaptation parameter is 1.254, and the preset scheduling adaptation parameter threshold is 1.2.

[0162] Among them, the scheduling adaptation parameters of all three regions meet the requirements (i.e., all are greater than 1.2). Region 1 has the largest scheduling adaptation parameter and is determined as the optimal scheduling region. If the scheduling adaptation parameter of region 3 is 1.18 (less than the scheduling adaptation parameter threshold of 1.2), then only regions 1 and 2 meet the requirements, and region 1 is still selected for target resource scheduling.

[0163] Conversely, if the scheduling adaptation parameters for the three regions are 1.15, 1.12, and 1.08, respectively, all of which are less than the scheduling adaptation parameter threshold of 1.2, then the equipment needs to be prepared first. This may involve recalibrating the equipment's operating parameters, replacing worn key components, or carrying out routine maintenance. After the equipment performance is improved, the scheduling will be reassessed. If any region in the recalculated scheduling adaptation parameters reaches or exceeds the preset scheduling adaptation parameter threshold, then the optimal scheduling region with the largest scheduling adaptation parameter will be selected for resource scheduling.

[0164] If the standard is still not met, the preparation plan needs to be further optimized, such as upgrading the equipment control platform and replacing the sensors with higher precision ones, until the equipment can be adapted to at least one construction area to be scheduled, so as to ensure that the equipment can be put into operation directly after scheduling and improve construction efficiency.

[0165] This step involves constructing a construction error change prediction branch group to accurately predict the construction error changes in each construction area to be scheduled, thereby obtaining the error change coefficient. After using the coefficient to compensate and correct the error adaptation parameters, the scheduling adaptation parameters are calculated in combination with the characteristic adaptation parameters. Finally, the optimal scheduling area is selected by threshold judgment, realizing the transformation of target resource scheduling from experience-based judgment to quantitative decision-making, and providing scientific support for efficient and accurate scheduling of resources on the construction site.

[0166] The embodiments of this application, through the specific implementation methods described above, achieve the following technical effects:

[0167] This application proposes a multi-decision fusion-based intelligent scheduling method for construction site resources. First, it acquires historical construction characteristic parameters of the previous historical construction area for the target resource, as well as construction characteristic parameters of multiple construction areas currently awaiting scheduling, clarifying the core attribute differences between the equipment's past operating environment and the current construction area to be scheduled. Then, it simultaneously acquires construction error parameters of the target resource within the historical construction area, and construction tolerances of multiple construction areas to be scheduled, understanding the equipment's own error level and the upper limit of error tolerance for each area. Next, it calculates multiple error adaptation parameters based on the ratio of construction tolerance to construction error parameters, and calculates multiple feature adaptation parameters based on the similarity between historical and current construction characteristic parameters, quantifying the degree of adaptation from both error tolerance and feature matching dimensions. Then, it constructs a construction error change prediction branch group, determining the number of branches based on the characteristics of the construction tolerance and construction error change prediction branch group of the construction area to be scheduled, randomly selecting branches to form a construction error change prediction branch group, and averaging the input feature parameter combinations to obtain the error change coefficient. The error adaptation parameters are then compensated and reduced to obtain compensated error adaptation parameters. Finally, it combines the compensated error adaptation parameters and feature adaptation parameters to calculate scheduling adaptation parameters, compares them with preset scheduling adaptation parameter thresholds to select the optimal scheduling area, and then performs target resource scheduling.

[0168] The method provided in this application, through the technical solution of "feature and error data acquisition - dual adaptation parameter calculation - error change prediction and compensation - scheduling adaptation parameter calculation - optimal scheduling area selection", solves the problems of relying solely on experience judgment, ignoring error changes caused by regional construction characteristics differences, and the difficulty of reflecting the true adaptation level by single-dimensional evaluation in traditional construction site resource scheduling. It avoids frequent equipment preparation, construction rework, and resource waste caused by subjective scheduling decisions or error misjudgment, and improves the scientificity and accuracy of construction site resource scheduling.

[0169] Example 2, as shown in the appendix Figure 2 As shown, based on the inventive concept of the multi-decision fusion intelligent scheduling method for construction site resources provided in Embodiment 1, this application also provides a multi-decision fusion intelligent scheduling system for construction site resources, specifically including:

[0170] The construction feature parameter acquisition module 01 is used to acquire the historical construction feature parameters of the previous historical construction area used for target resource scheduling, and to acquire the construction feature parameters of multiple construction areas currently to be used for target resource scheduling.

[0171] Construction error tolerance acquisition module 02 is used to acquire construction error parameters of the target resource during construction in the historical construction area, and to acquire multiple construction tolerances for multiple construction areas;

[0172] The dual-adaptive parameter analysis module 03 is used to analyze and obtain multiple error adaptation parameters based on multiple construction tolerance and construction error parameters, and to analyze and obtain multiple feature adaptation parameters based on historical construction feature parameters and multiple construction feature parameters.

[0173] The target resource scheduling decision module 04 is used to predict the changes in construction error based on multiple historical construction characteristic parameters and multiple construction characteristic parameters, obtain multiple error change coefficients, compensate multiple error adaptation parameters to obtain multiple compensated error adaptation parameters, and calculate multiple scheduling adaptation parameters by combining multiple characteristic adaptation parameters. When any scheduling adaptation parameter meets the scheduling requirements, the optimal scheduling construction area is selected and the target resource is scheduled.

[0174] In one embodiment, the construction feature parameter acquisition module 01 is further configured to:

[0175] Determine the previous historical construction area used for target resource scheduling, and obtain the historical construction characteristic parameters of the historical construction area, wherein the target resource is equipment resource; obtain multiple construction areas currently to be used for target resource scheduling, and collect multiple construction characteristic parameters of the multiple construction areas.

[0176] In one embodiment, the construction error tolerance acquisition module 02 is further used for:

[0177] Based on the construction data records of the target resource in the historical construction area, construction error parameters are measured and obtained; the maximum permissible error of construction in multiple construction areas is obtained as multiple construction tolerances.

[0178] In one embodiment, the dual-adaptive parameter analysis module 03 is further used for:

[0179] Calculate the ratios of the multiple construction tolerances and construction error parameters to obtain multiple error adaptation parameters; analyze and obtain multiple characteristic adaptation parameters based on the historical construction characteristic parameters and multiple construction characteristic parameters.

[0180] Furthermore, the dual-adaptive parameter analysis module 03 also includes:

[0181] The similarity between the historical construction feature parameters and multiple construction feature parameters is calculated and used as multiple feature adaptation parameters.

[0182] In one embodiment, the target resource scheduling decision module 04 is further configured to:

[0183] Obtain a cluster of predicted construction error variations. Based on the ratio of each construction tolerance to the maximum construction tolerance, and considering the total number of predicted construction error variations branches within the cluster, determine the number of branches. Randomly select branches from each cluster to obtain multiple groups of predicted construction error variations. Input each construction characteristic parameter and historical construction characteristic parameter combination separately, output and average to obtain multiple error variation coefficients. Use these multiple error variation coefficients to compensate and reduce multiple error adaptation parameters, obtaining multiple compensated error adaptation parameters. Calculate multiple scheduling adaptation parameters based on these compensated error adaptation parameters and multiple characteristic adaptation parameters. Determine if any scheduling adaptation parameter is greater than or equal to a preset scheduling adaptation parameter threshold. If so, select the scheduling construction area corresponding to the largest scheduling adaptation parameter as the optimal scheduling construction area for target resource scheduling. If not, prepare the target resources and then schedule them.

[0184] Furthermore, the target resource scheduling decision module 04 also includes:

[0185] Based on historical construction records from multiple construction areas, a set of sample construction feature parameter combinations is collected. The variation amplitude of construction error parameters within two construction areas under different sample construction feature parameter combinations is also collected, and a set of sample error variation coefficients is obtained. The sample construction feature parameter combination set and the sample error variation coefficient set are randomly divided multiple times to obtain multiple sets of construction error variation prediction training data. Based on machine learning, multiple construction error variation prediction branches are constructed, and supervised training and testing are performed using the multiple sets of construction error variation prediction training data until training is complete, resulting in a cluster of construction error variation prediction branches.

[0186] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0187] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0188] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A multi-decision fusion-based intelligent resource scheduling method for construction sites, characterized in that: The method includes: Obtain the historical construction characteristic parameters of the previous historical construction area used for target resource scheduling, and obtain the construction characteristic parameters of multiple construction areas currently to be used for target resource scheduling; Obtain construction error parameters for the target resource during construction within the historical construction area, and obtain multiple construction tolerances for multiple construction areas; Based on multiple construction tolerances and construction error parameters, multiple error adaptation parameters are obtained through analysis. Based on historical construction characteristic parameters and multiple construction characteristic parameters, multiple characteristic adaptation parameters are obtained through analysis. Based on multiple historical construction characteristic parameters and multiple construction characteristic parameters, construction error changes are predicted to obtain multiple error change coefficients. Multiple error adaptation parameters are compensated to obtain multiple compensated error adaptation parameters. Combined with multiple characteristic adaptation parameters, multiple scheduling adaptation parameters are calculated. When any scheduling adaptation parameter meets the scheduling requirements, the optimal scheduling construction area is selected and the target resource is scheduled. Specifically, based on multiple historical construction characteristic parameters and multiple construction characteristic parameters, construction error changes are predicted to obtain multiple error change coefficients. Compensation processing is then applied to multiple error adaptation parameters to obtain multiple compensated error adaptation parameters, including: Obtain the predicted branch group of construction error changes; Based on the ratio of each construction tolerance to the maximum construction tolerance, and combined with the total number of construction error change prediction branches within the construction error change prediction branch group, the number of multiple branches is determined. Based on the number of branches, construction error change prediction branches are randomly selected to obtain multiple construction error change prediction branch groups. Each construction characteristic parameter and historical construction characteristic parameter combination are input separately, and the output is averaged to obtain multiple error change coefficients. Multiple error variation coefficients are used to perform compensation and reduction calculations on multiple error adaptation parameters to obtain multiple compensation error adaptation parameters.

2. The intelligent scheduling method for construction site resources based on multi-decision fusion according to claim 1, characterized in that, Obtain the historical construction characteristic parameters of the previous historical construction area used for target resource scheduling, and obtain the construction characteristic parameters of multiple construction areas currently to be used for target resource scheduling, including: Determine the previous historical construction area used for target resource scheduling, and obtain the historical construction characteristic parameters of the historical construction area, wherein the target resource is equipment resource; Obtain multiple construction areas currently scheduled for target resource allocation, and collect multiple construction characteristic parameters for these construction areas.

3. The intelligent scheduling method for construction site resources based on multi-decision fusion according to claim 1, characterized in that, Obtain construction error parameters for the target resource during construction within the historical construction area, and obtain multiple construction tolerances for multiple construction areas, including: Based on the construction data records of the target resources carried out in the historical construction area, construction error parameters are measured and obtained; Obtain the maximum permissible error for construction in multiple construction areas, and use it as multiple construction tolerances.

4. The intelligent scheduling method for construction site resources based on multi-decision fusion according to claim 1, characterized in that, Based on multiple construction tolerances and construction error parameters, multiple error adaptation parameters are obtained through analysis. Based on historical construction characteristic parameters and multiple construction characteristic parameters, multiple characteristic adaptation parameters are obtained through analysis, including: Calculate the ratios of the multiple construction tolerances and construction error parameters respectively to obtain multiple error adaptation parameters; Based on the historical construction characteristic parameters and multiple construction characteristic parameters, multiple characteristic adaptation parameters are obtained through analysis.

5. The intelligent scheduling method for construction site resources based on multi-decision fusion according to claim 1, characterized in that, Based on the historical construction characteristic parameters and multiple construction characteristic parameters, several characteristic adaptation parameters are obtained through analysis, including: The similarity between the historical construction feature parameters and multiple construction feature parameters is calculated and used as multiple feature adaptation parameters.

6. The intelligent scheduling method for construction site resources based on multi-decision fusion according to claim 1, characterized in that, Obtain the construction error change prediction branch group, including: Based on historical construction record data from multiple construction areas, a set of sample construction characteristic parameter combinations was collected, and the variation range of construction error parameters in two construction areas under different sample construction characteristic parameter combinations was collected. The sample error variation coefficient set was then labeled and obtained. The sample construction feature parameter combination set and sample error change coefficient set are randomly divided multiple times to obtain multiple sets of construction error change prediction training data. Based on machine learning, multiple branches for predicting construction error changes are constructed. These branches are then trained and tested using the multiple sets of training data for predicting construction error changes until training is complete, thus obtaining a group of branches for predicting construction error changes.

7. The intelligent scheduling method for construction site resources based on multi-decision fusion according to claim 1, characterized in that, By combining multiple feature adaptation parameters, multiple scheduling adaptation parameters are calculated. When any one of the scheduling adaptation parameters meets the scheduling requirements, the optimal scheduling construction area is selected, and target resource scheduling is performed, including: Multiple scheduling adaptation parameters are calculated based on multiple compensation error adaptation parameters and multiple feature adaptation parameters; Determine whether any scheduling adaptation parameter is greater than or equal to the preset scheduling adaptation parameter threshold. If so, the scheduling construction area corresponding to the largest scheduling adaptation parameter is selected as the optimal scheduling construction area for target resource scheduling. If not, then prepare the target resources and then schedule them.

8. A multi-decision fusion intelligent scheduling system for construction site resources, characterized in that: The system is used to execute the intelligent scheduling method for construction site resources with multi-decision fusion as described in any one of claims 1-7, and the system includes: The construction feature parameter acquisition module is used to acquire the historical construction feature parameters of the previous historical construction area used for target resource scheduling, and to acquire the construction feature parameters of multiple construction areas currently to be used for target resource scheduling. The construction error tolerance acquisition module is used to acquire the construction error parameters of the target resource during construction in the historical construction area, and to acquire multiple construction tolerances for multiple construction areas; The dual-adaptive parameter analysis module is used to analyze and obtain multiple error adaptation parameters based on multiple construction tolerance and construction error parameters, and to analyze and obtain multiple characteristic adaptation parameters based on historical construction characteristic parameters and multiple construction characteristic parameters. The target resource scheduling decision module is used to predict the changes in construction error based on multiple historical construction characteristic parameters and multiple construction characteristic parameters, obtain multiple error change coefficients, compensate multiple error adaptation parameters to obtain multiple compensated error adaptation parameters, and calculate multiple scheduling adaptation parameters by combining multiple characteristic adaptation parameters. When any scheduling adaptation parameter meets the scheduling requirements, the optimal scheduling construction area is selected and the target resource is scheduled. Specifically, based on multiple historical construction characteristic parameters and multiple construction characteristic parameters, construction error changes are predicted to obtain multiple error change coefficients. Compensation processing is then applied to multiple error adaptation parameters to obtain multiple compensated error adaptation parameters, including: Obtain the predicted branch group of construction error changes; Based on the ratio of each construction tolerance to the maximum construction tolerance, and combined with the total number of construction error change prediction branches within the construction error change prediction branch group, the number of multiple branches is determined. Based on the number of branches, construction error change prediction branches are randomly selected to obtain multiple construction error change prediction branch groups. Each construction characteristic parameter and historical construction characteristic parameter combination are input separately, and the output is averaged to obtain multiple error change coefficients. Multiple error variation coefficients are used to perform compensation and reduction calculations on multiple error adaptation parameters to obtain multiple compensation error adaptation parameters.

Images