Construction project collaborative supervision method and system

Abstract

The invention relates to the technical field of project collaborative supervision, in particular to a construction project collaborative supervision method and system, and the method comprises the steps: constructing a construction period objective function based on the resource configuration data of a target construction project, constructing an overall constraint condition based on the resource configuration data of the target construction project, constructing a construction period optimization model of the target construction project based on the construction period target function and the overall constraint condition; and performing construction period optimization on the construction period optimization model of the target construction project based on an optimization algorithm to obtain an optimal construction progress sequence. The construction period objective function and the constraint condition are constructed based on the resource configuration data and the optimization algorithm, the scientific construction period optimization model is established, the construction progress is more reasonable and controllable, the construction period optimization model can provide an accurate construction progress plan for a project by calculating the optimal construction progress sequence, and the construction progress optimization efficiency is improved. Therefore, engineering delay is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering collaborative supervision, and particularly relates to a construction project collaborative supervision method and system. Background Art

[0002] A construction project refers to various construction activities such as buildings, facilities, and equipment carried out in accordance with certain technical standards, economic requirements, and management specifications to achieve specific goals.

[0003] Traditional methods often rely on manual formulation and adjustment of construction progress plans. The progress control is usually relatively rough and it is difficult to achieve precise optimization and adjustment. Due to the lack of advanced optimization algorithms and data-driven decision support, the progress arrangement is easily affected by human factors, resulting in project delays or resource waste. And traditional methods usually rely on on-site supervisors to manually check and record the construction progress, and it is impossible to achieve real-time and comprehensive progress monitoring. The progress update at the construction site is often not timely, and it is impossible to track the difference between the construction progress and the plan in real time, easily missing the best opportunity to discover problems. Moreover, it is very difficult to detect progress anomalies or deviations in real time during the construction process. Supervisors usually discover problems afterwards, resulting in project delays or the need for additional resources to make up for the gap. Since the progress anomalies are not identified in time, subsequent adjustments often require more time and cost. And traditional supervision methods rely more on experience and subjective judgment, lacking objective data-based support in the decision-making process. The progress control is usually based on data obtained from manual observation and manual recording, and it is difficult to analyze potential problems in the construction or detect small fluctuations in the progress, resulting in poor decision-making effects. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the above-mentioned disadvantages of the prior art and provide a construction project collaborative supervision method and system.

[0005] The technical solution adopted to solve the above technical problem is: A construction project collaborative supervision method includes:

[0006] Construct a project duration objective function based on the resource allocation data of the target construction project, construct overall constraint conditions based on the resource allocation data of the target construction project, and construct a project duration optimization model for the target construction project based on the project duration objective function and the overall constraint conditions;

[0007] Optimize the project duration of the project duration optimization model of the target construction project based on an optimization algorithm to obtain an optimal construction progress sequence;

[0008] Obtain construction images of the target construction project uploaded at a preset sampling time, and preprocess the construction images to obtain standard construction images;

[0009] Performing progress detection on the standard construction image based on a pre-trained progress detection model to obtain the real-time construction progress corresponding to the standard construction image, and sorting the real-time construction progress according to a time series to obtain a real-time construction progress sequence;

[0010] Matching the real-time construction progress sequence with the optimal construction progress sequence to obtain the matching degree between the two. If the matching degree is lower than a preset matching degree threshold, construction progress anomaly information is generated.

[0011] Preferably, the resource allocation data includes the amount of human resources, the amount of material resources, and the amount of equipment resources.

[0012] Preferably, the expression of the construction period objective function is as follows:

[0013]

[0014] where POF represents the construction period objective function, represents the planned completion period of the i-th sub-construction project in the target construction project, represents the resource replenishment time required for the i-th sub-construction project in the target construction project lacking e resources, represents the start time point of the next sub-construction project, represents the current time point of the sub-construction project, represents the existing amount of equipment resources for the current sub-construction project, represents the equipment resource demand for the current sub-construction project, represents the surplus amount of human resources at the i-th sub-construction project in the target construction project, represents the existing number of people for the current sub-construction project, represents the required number of people for the current sub-construction project, represents the surplus amount of material resources at the i-th sub-construction project in the target construction project, represents the warning value of the equipment resource amount for the i-th sub-construction project, represents the warning value of the human resource amount for the i-th sub-construction project, represents the warning value of the material resource amount for the i-th sub-construction project, represents the existing amount of material resources, represents the material resource demand for the current sub-construction project.

[0015] Preferably, overall constraint conditions are constructed based on the resource allocation data of the target construction project, including:

[0016] Calculating the human monitoring index of the amount of human resources, where the calculation formula of the human monitoring index is as follows:

[0017]

[0018] Among them, represents the human monitoring index, represents the excess amount of equipment resources at the i-th sub-construction project;

[0019] Calculate the material monitoring index of the equipment resource amount, where the calculation formula of the equipment monitoring index is as follows:

[0020]

[0021] Among them, represents the equipment monitoring index;

[0022] Calculate the equipment monitoring index of the material resource amount, where the calculation formula of the material monitoring index is as follows:

[0023]

[0024] Among them, represents the material monitoring index.

[0025] Preferably, based on the resource allocation data of the target construction project, overall constraint conditions are constructed, and it further includes:

[0026] Based on the human monitoring index, the material monitoring index, and the equipment monitoring index, overall constraint conditions are constructed, where the expression of the overall constraint conditions is as follows:

[0027]

[0028] Preferably, based on an optimization algorithm, the construction period optimization model of the target construction project is optimized for the construction period to obtain an optimal construction progress sequence, including:

[0029] Randomly generate a group of individuals, and the position of each individual represents a combination of decision variables of the construction period optimization model;

[0030] For the combination of decision variables of the objective function represented by each individual, calculate the fitness value, where the fitness value is the value of the construction period objective function;

[0031] Update the light intensity and attraction of the individual, and update the position of the individual based on the light intensity and attraction of the individual;

[0032] Judge whether the training error reaches the convergence value or whether the number of iterations reaches the maximum value. If the training error reaches the convergence value and the number of iterations reaches the maximum value, the iteration ends and the combination of decision variables of the construction period objective function is output, otherwise the number of iterations is incremented by 1.

[0033] Preferably, the update formula for the light intensity of the individual is as follows:

[0034]

[0035] Wherein, and represent the light intensity of the i-th individual at the t-th iteration and the (t - 1)-th iteration, ρ represents a preset proportion, τ represents a preset proportionality coefficient, X t represents the position of the individual at the t-th iteration, and f(X t ) represents the fitness value corresponding to the position of the individual at the t-th iteration;

[0036] The update formula for the attractiveness of the individual is as follows:

[0037]

[0038] Wherein, β(r) represents the attractiveness of the individual, β 0 represents the maximum attractiveness, r ij represents the distance between the i-th individual and the j-th individual, and r ij =‖X i -X j ‖, X i and X j represent the positions of the i-th individual and the j-th individual;

[0039] The update formula for the position of the individual is as follows:

[0040]

[0041] Wherein, and represent the positions of the i-th individual at the (t + 1)-th iteration and the t-th iteration, represents the position of the j-th individual at the t-th iteration, ε i represents the random factor of the i-th individual, and α represents the step size scaling factor.

[0042] Preferably, the target detection model extracts features of different scales of the standard construction image through 3 efficient convolutional modules, which are respectively represented as C 1 , C 2 and C 3 , and uses multi-scale feature fusion to perform target recognition on features of different scales. Among them, for the smallest-scale feature C 3 , first perform a feature transformation on the smallest-scale feature C 3 through a 1×1 convolutional operation, and then perform an upsampling operation to obtain a feature of the same size as C 2 , and then combine this feature with C 2are fused and input into an efficient convolution module to extract the fused features. Then, through an upsampling operation, the fused features are mapped to the same size as C 1 and concatenated with C at the channel level. Finally, an efficient convolution module is used to extract the final features, and these features are input into a classification module to obtain the real-time construction progress of the standard construction image. 1 Preferably, the efficient convolution module uses two different branches to process the input features. Among them, the first branch first extracts the inter-channel dependence features of the input through a 3×3 depthwise convolution kernel, and then extracts the spatial dependence features of the input through a 1×1 pointwise convolution operation. The second branch first extracts the spatial dependence features of the input through a 1×1 pointwise convolution operation, then uses a 3×3 depthwise convolution operation to extract the inter-channel dependence features of the input features, and then weights each channel through an attention module to extract the weighted features. Finally, a 1×1 pointwise convolution operation is used to extract the spatial dependence features of the weighted features. The features of the two branches are integrated through channel-level concatenation, and the features of the two branches are integrated through a 3×3 depthwise convolution operation and a 1×1 pointwise convolution operation.

[0043]

[0044] The technical solution adopted to solve the above technical problems is: a construction project collaborative supervision method, which is applicable to the described construction project collaborative supervision method, including:

[0045] A construction period optimization unit, which is used to construct a construction period objective function based on the resource allocation data of the target construction project, construct overall constraint conditions based on the resource allocation data of the target construction project, and construct a construction period optimization model of the target construction project based on the construction period objective function and the overall constraint conditions;

[0046] A model solving unit, which is used to optimize the construction period of the construction period optimization model of the target construction project based on an optimization algorithm to obtain an optimal construction progress sequence;

[0047] An image acquisition unit, which is used to acquire the construction images of the target construction project uploaded according to a preset sampling time, and preprocess the construction images to obtain standard construction images;

[0048] A progress detection unit, which is used to detect the progress of the standard construction image based on a pre-trained progress detection model to obtain the real-time construction progress corresponding to the standard construction image, and sort the real-time construction progress according to the time series to obtain a real-time construction progress sequence;

[0049] ​Anomaly supervision unit, which is used to match the real-time construction progress sequence with the optimal construction progress sequence to obtain the matching degree between the two. If the matching degree is lower than the preset matching degree threshold, construction progress anomaly information is generated.

[0050] The beneficial effects of the present invention are as follows: (1) By constructing a construction period objective function and constraint conditions based on resource allocation data and optimization algorithms, the present invention establishes a scientific construction period optimization model, making the construction progress more reasonable and controllable. The construction period optimization model can provide an accurate construction progress plan for the project by calculating the optimal construction progress sequence, thus avoiding project delays; (2) By acquiring and processing construction images, the progress detection model can detect the construction progress in real time. This method can clearly reflect the actual situation of the construction progress through time series sorting, track and judge the gap with the optimal progress sequence in real time, and help to discover problems in construction in a timely manner; (3) When the matching degree between the real-time construction progress and the optimal construction progress sequence is lower than the preset threshold, the system will automatically generate construction progress anomaly information, which can effectively warn of construction progress deviation from the plan, provide project managers with timely adjustment of construction strategies, avoid project delays or resource waste, and combine the resource allocation, progress optimization and real-time monitoring of the project. Through the collaborative work of construction images and the progress detection model, supervisors can comprehensively understand the project progress and resource usage, thus improving the management efficiency and quality of construction projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic flow chart of the steps of the overall method in an embodiment proposed by the present invention;

[0052] Figure 2 It is a schematic system architecture diagram of the overall system in an embodiment proposed by the present invention.

[0053] Reference numerals: 1, construction period optimization unit; 2, model solving unit; 3, image acquisition unit; 4, progress detection unit; 5, anomaly supervision unit. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] Embodiment 1, as Figure 1 shown, a collaborative supervision method for construction projects proposed by the present invention includes:

[0055] S1. Construct a construction period objective function based on the resource allocation data of the target construction project, construct overall constraint conditions based on the resource allocation data of the target construction project, and construct a construction period optimization model of the target construction project based on the construction period objective function and the overall constraint conditions;

[0056] S2. Optimize the construction period of the target construction project for the construction period optimization model based on the optimization algorithm to obtain the optimal construction progress sequence;

[0057] S3. Obtain the construction images of the target construction project uploaded according to the preset sampling time, and preprocess the construction images to obtain standard construction images;

[0058] S4. Detect the construction progress of the standard construction images based on the pre-trained progress detection model to obtain the real-time construction progress corresponding to the standard construction images, and sort the real-time construction progress according to the time series to obtain the real-time construction progress sequence;

[0059] S5. Match the real-time construction progress sequence with the optimal construction progress sequence to obtain the matching degree between the two. If the matching degree is lower than the preset matching degree threshold, construction progress abnormal information is generated.

[0060] In the present invention, the resource allocation data refers to the allocation situation and demand of various resources (such as labor, materials, equipment, etc.) in the construction project. The resource allocation data is an important part of project management and is used to formulate the project plan and scheduling; the optimization algorithm is an algorithm used to find the optimal solution in the construction period optimization model. Common optimization algorithms include genetic algorithms, particle swarm optimization algorithms, simulated annealing algorithms, etc. The optimization algorithm finds the most suitable resource allocation and construction progress by continuously adjusting the plan; preprocessing refers to operations such as cleaning, denoising, and enhancement on the construction images before analyzing them to improve the image quality and facilitate subsequent progress detection and analysis; the construction progress abnormal information refers to when the matching degree between the real-time construction progress and the optimal construction progress sequence is lower than the preset threshold, construction progress abnormal information will be generated, indicating that there are deviations or problems in the construction process, and it may be necessary to adjust the resources or progress arrangement.

[0061] Embodiment 2. A construction project collaborative supervision method proposed by the present invention. Compared with Embodiment 1, this embodiment further includes: the resource allocation data includes the amount of human resources, the amount of material resources, and the amount of equipment resources.

[0062] In an optional embodiment, the expression of the construction period objective function is as follows:

[0063]

[0064] Wherein, POF represents the construction period objective function, represents the planned completion period of the i-th sub-construction project in the target construction project, represents the resource replenishment time required for the i-th sub-construction project in the target construction project lacking e resources, represents the start time point of the next sub-construction project, represents the current time point of the sub-construction project, Indicates the existing equipment resource quantity of the current sub-construction project, Indicates the equipment resource demand quantity of the current sub-construction project, Indicates the surplus quantity of human resources when it comes to the i-th sub-construction project in the target construction project, Indicates the existing number of human resources of the current sub-construction project, Indicates the required number of human resources for the current sub-construction project, Indicates the surplus quantity of material resources when it comes to the i-th sub-construction project in the target construction project, Indicates the warning value of the equipment resource quantity of the i-th sub-construction project, Indicates the warning value of the human resource quantity of the i-th sub-construction project, Indicates the warning value of the material resource quantity of the i-th sub-construction project, Indicates the existing material resource quantity, Indicates the material resource demand quantity of the current sub-construction project.

[0065] In an optional embodiment, overall constraint conditions are constructed based on the resource allocation data of the target construction project, including:

[0066] A1. Calculate the human monitoring index of the human resource quantity, where the calculation formula of the human monitoring index is as follows:

[0067]

[0068] Wherein, Indicates the human monitoring index, Indicates the surplus quantity of equipment resources when it comes to the i-th sub-construction project;

[0069] A2. Calculate the material monitoring index of the equipment resource quantity, where the calculation formula of the equipment monitoring index is as follows:

[0070]

[0071] Wherein, Indicates the equipment monitoring index;

[0072] A3. Calculate the equipment monitoring index of the material resource quantity, where the calculation formula of the material monitoring index is as follows:

[0073]

[0074] Wherein, Indicates the material monitoring index.

[0075] In an optional embodiment, overall constraint conditions constructed based on the resource allocation data of the target construction project further include:

[0076] A4. Construct an overall constraint condition based on the human monitoring index, material monitoring index, and equipment monitoring index. The expression of the overall constraint condition is as follows:

[0077]

[0078] In an optional embodiment, perform duration optimization on the duration optimization model of the target construction project based on an optimization algorithm to obtain an optimal construction schedule sequence, including:

[0079] B1. Randomly generate a group of individuals, where the position of each individual represents a combination of decision variables of the duration optimization model;

[0080] B2. For the combination of decision variables of the objective function represented by each individual, calculate the fitness value, where the fitness value is the value of the duration objective function;

[0081] B3. Update the light intensity and attractiveness of the individual, and update the position of the individual based on the light intensity and attractiveness of the individual;

[0082] B4. Determine whether the training error reaches the convergence value or the number of iterations reaches the maximum value. If the training error reaches the convergence value and the number of iterations reaches the maximum value, the iteration ends and the combination of decision variables of the duration objective function is output; otherwise, the number of iterations is incremented by 1.

[0083] It should be noted that in the optimization algorithm, an individual represents a possible solution. The "position" of each individual represents a combination of decision variables of the duration optimization model. An individual is a solution to the optimization problem and contains all the parameters in the model (such as resource allocation, task scheduling, etc.); concepts such as light intensity and attractiveness are usually used to simulate natural phenomena, especially in optimization algorithms. For example, light intensity can be used to represent the ability of an individual to attract other individuals during the optimization process, and attractiveness can reflect the interaction and influence between individuals. These concepts can help the algorithm find better solutions in the search space; during the optimization process, the training error refers to the difference between the current solution and the optimal solution. In the optimization problem of the objective function, the training error can represent the deviation between the duration of the current solution and the ideal duration.

[0084] In an optional embodiment, the update formula for the light intensity of an individual is as follows:

[0085]

[0086] Where and represent the light intensity of the i-th individual at the t-th iteration and the (t - 1)-th iteration respectively. ρ represents a preset proportion, τ represents a preset proportionality coefficient, X t represents the position of the individual at the t-th iteration, f(X t) represents the fitness value corresponding to the position of the individual at the t-th iteration;

[0087] The update formula for the attractiveness of the individual is as follows:

[0088]

[0089] where β(r) represents the attractiveness of the individual, and β 0 represents the maximum attractiveness, and r ij represents the distance between the i-th individual and the j-th individual, and r ij =‖X i -X j ‖, and X i and X j represent the positions of the i-th individual and the j-th individual;

[0090] The update formula for the position of the individual is as follows:

[0091]

[0092] where, and represent the positions of the i-th individual at the (t + 1)-th iteration and the t-th iteration, represents the position of the j-th individual at the t-th iteration, ε i represents the random factor of the i-th individual, and α represents the step size scaling factor.

[0093] In an alternative embodiment, the object detection model extracts features of different scales of the standard construction image through 3 efficient convolution modules, which are respectively denoted as C 1 , C 2 and C 3 . Multi-scale feature fusion is used to perform object recognition on features of different scales. Among them, for the smallest-scale feature C 3 , first, a 1×1 convolution operation is performed on the smallest-scale feature C 3 to perform feature transformation, and then an upsampling operation is performed to obtain a feature of the same size as C 2 . Then, this feature is fused with C 2 , and the fused feature is input into an efficient convolution module to extract the fused feature. Next, the fused feature is mapped to the same size as C 1 through an upsampling operation, and it is concatenated with C 1 at the channel level. Finally, an efficient convolution module is used to extract the final feature, and this feature is input into a classification module to obtain the real-time construction progress of the standard construction image.

[0094] It should be noted that the efficient convolution module refers to a specific convolution structure in a convolutional neural network (CNN) that is used to improve computational efficiency and enhance model performance; multi-scale feature fusion is a commonly used technique in object detection, aiming to extract information from feature maps of different scales and fuse this information to enhance the object recognition ability. In images of different scales, the sizes of target objects may vary. Therefore, through multi-scale fusion, the model's detection ability for objects of different sizes can be improved; upsampling refers to the operation of converting a low-resolution feature map into a higher-resolution one, usually achieved through interpolation (such as bilinear interpolation); channel-level concatenation refers to the splicing of multiple feature maps in the channel dimension of the feature map. In a convolutional neural network, feature maps can be concatenated to increase the number of channels, thereby fusing the information of multiple feature maps for subsequent feature extraction.

[0095] In an optional embodiment, the efficient convolution module uses two different branches to process the input features. Among them, the first branch first extracts the input channel-dependent features through a 3×3 depthwise convolution kernel, and then extracts the input spatial-dependent features through a 1×1 pointwise convolution operation. Among them, the second branch first extracts the input spatial-dependent features through a 1×1 pointwise convolution operation, then uses a 3×3 depth convolution operation to extract the channel-dependent features of the input features, and then weights each channel through an attention module to extract the weighted features. Finally, a 1×1 pointwise convolution operation is used to extract the spatial-dependent features of the weighted features. The features of the two branches are integrated through channel-level concatenation, and the features of the two branches are integrated through a 3×3 depth convolution operation and a 1×1 pointwise convolution operation.

[0096] Embodiment 3, as Figure 2 shown, a construction project collaborative supervision system proposed by the present invention, which is applicable to the described construction project collaborative supervision method, includes:

[0097] A construction period optimization unit 1, which is used to construct a construction period objective function based on the resource allocation data of the target construction project, construct overall constraint conditions based on the resource allocation data of the target construction project, and construct a construction period optimization model of the target construction project based on the construction period objective function and the overall constraint conditions;

[0098] A model solving unit 2, which is used to optimize the construction period of the construction period optimization model of the target construction project based on an optimization algorithm to obtain an optimal construction progress sequence;

[0099] An image acquisition unit 3, which is used to acquire the construction images of the target construction project uploaded according to the preset sampling time, and preprocess the construction images to obtain standard construction images;

[0100] The progress detection unit 4 is configured to perform progress detection on the standard construction image based on a pre-trained progress detection model to obtain the real-time construction progress corresponding to the standard construction image, and sort the real-time construction progress according to the time series to obtain a real-time construction progress sequence;

[0101] The abnormal supervision unit 5 is configured to match the real-time construction progress sequence with the optimal construction progress sequence to obtain the matching degree between the two. If the matching degree is lower than a preset matching degree threshold, construction progress abnormal information is generated.

[0102] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited thereto. Various changes can be made without departing from the spirit of the present invention within the scope of knowledge possessed by those skilled in the art to which the present invention pertains.

Claims

1. A construction project collaborative supervision method, characterized in that: include: Constructing a construction period objective function based on resource allocation data of the target construction project, constructing an overall constraint condition based on the resource allocation data of the target construction project, and constructing a construction period optimization model for the target construction project based on the construction period objective function and the overall constraint condition; Based on the optimization algorithm, the construction period optimization model of the target construction project is optimized to obtain the optimal construction progress sequence; Acquire a construction image of a target construction project uploaded at a preset sampling time, and preprocess the construction image to obtain a standard construction image; Performing progress detection on the standard construction image based on a pre-trained progress detection model to obtain the real-time construction progress corresponding to the standard construction image, and sorting the real-time construction progress according to a time series to obtain a real-time construction progress sequence; The real-time construction progress sequence is matched with the optimal construction progress sequence to obtain a matching degree between the two. If the matching degree is lower than a preset matching degree threshold, construction progress abnormality information is generated.

2. A construction project collaborative supervision method according to claim 1, characterized in that: The resource allocation data includes human resources, material resources and equipment resources.

3. A construction project collaborative supervision method according to claim 2, characterized in that: The expression of the construction period objective function is as follows: Among them, POF represents the construction period objective function, represents the planned completion date of the i-th sub-construction project in the target construction project, It represents the resource replenishment time required for the i-th sub-construction project in the target construction project that lacks e resources. Indicates the start time of the next sub-construction project. Indicates the current time point of the sub-construction project. Indicates the amount of equipment resources available in the current sub-construction project. Indicates the equipment resource demand of the current sub-construction project, represents the excess human resources in the i-th sub-construction project of the target construction project, Indicates the number of manpower available in the current sub-construction project. Indicates the number of manpower required for the current sub-construction project, represents the excess amount of material resources in the i-th sub-construction project of the target construction project, represents the warning value of the equipment resource quantity of the i-th sub-construction project, represents the warning value of the human resources of the ith sub-construction project, represents the warning value of the material resources of the i-th sub-construction project, Indicates the existing material resources. Indicates the material resource demand of the current sub-construction project.

4. A construction project collaborative supervision method according to claim 3, characterized in that: The overall constraint conditions are constructed based on the resource allocation data of the target construction project, including: Calculate the human resource monitoring index of the human resource quantity, wherein the calculation formula of the human resource monitoring index is as follows: in, Indicates human monitoring indicators, It represents the excess amount of equipment resources at the time of the i-th sub-construction project; Calculate the material monitoring index of the equipment resource quantity, wherein the calculation formula of the equipment monitoring index is as follows: in, Indicates equipment monitoring indicators; Calculate the equipment monitoring index of the material resource quantity, wherein the calculation formula of the material monitoring index is as follows: in, Indicates material monitoring indicators.

5. A construction project collaborative supervision method according to claim 4, characterized in that: The overall constraint conditions are constructed based on the resource allocation data of the target construction project, and further include: An overall constraint condition is constructed based on the manpower monitoring index, the material monitoring index, and the equipment monitoring index, wherein the expression of the overall constraint condition is as follows:

6. A construction project collaborative supervision method according to claim 5, characterized in that: Based on the optimization algorithm, the construction period optimization model of the target construction project is optimized to obtain the optimal construction progress sequence, including: A group of individuals is randomly generated, and the position of each individual represents a combination of decision variables of the construction period optimization model; For each combination of decision variables of the objective function represented by each individual, a fitness value is calculated, wherein the fitness value is the value of the construction period objective function; updating the light intensity and attractiveness of the individual, and updating the position of the individual based on the light intensity and attractiveness of the individual; It is determined whether the training error reaches the convergence value or the number of iterations reaches the maximum value. If the training error reaches the convergence value and the number of iterations reaches the maximum value, the iteration ends and the combination of decision variables of the construction period objective function is output, otherwise the number of iterations is increased by 1.

7. A construction project collaborative supervision method according to claim 6, characterized in that: The update formula of the individual light intensity is as follows: in, and represents the light intensity of the i-th individual at the t-th iteration and the t-1-th iteration, ρ represents the preset weight, τ represents the preset proportional coefficient, X t represents the position of the individual at the tth iteration, f(X t ) represents the fitness value corresponding to the position of the individual at the tth iteration; The update formula of the individual's attractiveness is as follows: Among them, β(r) represents the individual's attractiveness, β0 represents the maximum attractiveness, r ij represents the distance between the i-th individual and the j-th individual, and r ij =‖X i -X j ‖,X i and X j represents the position of the i-th individual and the j-th individual; The update formula of the individual position is as follows: in, and represents the position of the i-th individual at the t+1th iteration and the tth iteration, represents the position of the jth individual at the tth iteration, ε i represents the random factor of the ith individual, and α represents the step size scaling factor.

8. A construction project collaborative supervision method according to claim 1, characterized in that: The target detection model uses three efficient convolution modules to extract features of different scales of the standard construction image, which are represented as C1, C2 and C3 respectively, and uses multi-scale feature fusion to identify targets for features of different scales. For the minimum scale feature C3, a 1×1 convolution operation is first used to transform the minimum scale feature C3, and then an upsampling operation is performed to obtain a feature of the same size as C2. The feature is then fused with C2 and input into an efficient convolution module to extract the fused feature. The fused feature is then mapped to the same size as C1 through an upsampling operation and is channel-level concatenated with C1. Finally, an efficient convolution module is used to extract the final feature, and the feature is input into a classification module to obtain the real-time construction progress of the standard construction image.

9. A construction project collaborative supervision method according to claim 8, characterized in that: The efficient convolution module uses two different branches to process input features, wherein the first branch first extracts the input channel dependency features through a 3×3 depth-level convolution kernel, and then extracts the input spatial dependency features through a 1×1 pixel-level convolution operation, wherein the second branch first extracts the input spatial dependency features through a 1×1 pixel-level convolution operation, and then uses a 3×3 depth-level convolution operation to extract the channel dependency features of the input features, and then uses an attention module to weight each channel to extract the weighted features, and finally uses a 1×1 pixel-level convolution operation to extract the spatial dependency features of the weighted features, and integrates the features of the two branches through channel-level cascade, and integrates the features of the two branches through a 3×3 depth-level convolution operation and a 1×1 pixel-level convolution operation.

10. A construction project collaborative supervision system, which is applicable to a construction project collaborative supervision method according to any one of claims 1 to 9, characterized in that: include: A construction period optimization unit (1), the construction period optimization unit (1) is used to construct a construction period objective function based on resource configuration data of a target construction project, to construct an overall constraint condition based on the resource configuration data of the target construction project, and to construct a construction period optimization model of the target construction project based on the construction period objective function and the overall constraint condition; A model solving unit (2), the model solving unit (2) is used to optimize the construction period of the target construction project based on an optimization algorithm to obtain an optimal construction progress sequence; An image acquisition unit (3), the image acquisition unit (3) being used to acquire a construction image of a target construction project uploaded at a preset sampling time, and to pre-process the construction image to obtain a standard construction image; A progress detection unit (4), the progress detection unit (4) is used to perform progress detection on the standard construction image based on a pre-trained progress detection model to obtain the real-time construction progress corresponding to the standard construction image, and to sort the real-time construction progress according to a time series to obtain a real-time construction progress sequence; The abnormality monitoring unit (5) is used to match the real-time construction progress sequence with the optimal construction progress sequence to obtain a matching degree between the two, and if the matching degree is lower than a preset matching degree threshold, generate construction progress abnormality information.

Images