Intelligent construction integrated collaboration platform and method

Abstract

The invention relates to the technical field of intelligent construction, and discloses an intelligent construction integrated collaboration platform and method.The platform comprises a data preprocessing module, a feature extraction module, a data fusion module, a task analysis module, a scheduling optimization module and a task execution module, original data in a target building are collected and subjected to normalization processing, and the normalization processing result is obtained; standardized data are obtained; extracting multi-level features in the standardized data to construct a data feature set; performing multi-dimensional coupling on the static attribute features and the dynamic behavior features in the data feature set to obtain fusion data; performing joint analysis on a dependency relationship and a resource conflict in a collaborative task list deconstructed by the fused data to obtain a conflict-free task list; scheduling the target optimization data in the conflict-free task list to obtain an optimization scheduling plan; updating the collaborative task list, and applying the updated list to the target building; according to the invention, the efficiency of intelligent building integration can be improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent construction technology, and in particular to an integrated collaborative platform and method for intelligent construction. Background Technology

[0002] In existing intelligent construction collaborative management solutions, data from each stage is typically isolated, lacking a unified mechanism for fusion of multi-source heterogeneous data. Static attribute data and dynamic behavioral data collected from the building environment fail to achieve effective cross-dimensional coupling, resulting in insufficient data value mining and difficulty in supporting accurate collaborative decision-making. Traditional methods for analyzing task dependencies and resource conflicts often employ a serial processing mode, failing to establish real-time, dynamic collaborative relationships between task logic and resource constraints, leading to low task scheduling efficiency and insufficient conflict resolution capabilities.

[0003] Furthermore, existing technologies lack sufficient consideration for the synergy between time priorities and optimization objectives, resulting in a significant disconnect between resource allocation strategies and task execution requirements. This fragmented approach makes it difficult for collaborative platforms to generate globally optimal scheduling schemes, impacting not only the overall efficiency of the construction process but also increasing the risks of resource conflicts and project delays. Therefore, improving the efficiency of integrated intelligent construction has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides an integrated intelligent construction collaborative platform and method to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides an integrated intelligent construction collaborative platform, characterized in that the platform includes a data preprocessing module, a feature extraction module, a data fusion module, a task parsing module, a scheduling optimization module, and a task execution module, wherein: The data preprocessing module is used to collect raw data from the target building, normalize the raw data, and obtain standardized data of the target building. The feature extraction module is used to extract multi-level features from the standardized data to construct a data feature set of the standardized data. The data fusion module is used to couple the static attribute features and dynamic behavior features in the data feature set in multiple dimensions to obtain the fused data of the data feature set. The task parsing module is used to jointly parse the dependencies and resource conflicts in the collaborative task list deconstructed from the fused data to obtain a conflict-free task list for the target building. The scheduling optimization module is used to schedule the target optimization data in the conflict-free task list according to the time priority, so as to obtain the optimized scheduling plan of the conflict-free task list. The task execution module is used to update the collaborative task list according to the optimized scheduling plan and apply the updated list to the target building.

[0006] In a preferred embodiment, when the data preprocessing module collects raw data from the target building and performs normalization processing on the raw data to obtain standardized data of the target building, it specifically performs the following: Collect raw data from the target building; Within a sliding time window, the original data is denoised to obtain a clean dataset of the original data; Tensor reconstruction is performed on the cleaning dataset to obtain the standardized data vector of the target building; The standardized data vector is distributed and normalized to obtain the standardized data of the target building.

[0007] In a preferred embodiment, when the feature extraction module extracts multi-level features from the standardized data to construct the data feature set of the standardized data, it is specifically used for: Based on the spatial reference system in the standardized data, the association relationship mining is performed on the data in the standardized data to obtain the spatial distribution feature set of the standardized data. In the continuous time domain, the spatiotemporal correlation structure of the spatial distribution feature set is constructed based on the correlation characteristics of the spatial distribution feature set; Based on the spatiotemporal correlation structure, the evolution path of the spatial distribution feature set is extracted to obtain the temporal evolution feature set of the spatial distribution feature set; The spatial distribution feature set and the temporal evolution feature set are quantized to obtain the state feature vector of the standardized data. The spatial distribution feature set, the temporal evolution feature set, and the state feature vector are adaptively weighted and fused to obtain the data feature set of the standardized data.

[0008] In a preferred embodiment, when the data fusion module performs multi-dimensional coupling of static attribute features and dynamic behavior features in the data feature set to obtain fused data of the data feature set, it is specifically used for: The static feature set of the data feature set is obtained by performing topological structure analysis on the static attribute features of the data feature set. Temporal pattern extraction is performed on the dynamic behavior features of the data feature set to obtain a serialized dynamic feature stream of the data feature set; A cross-correlation analysis is performed on the static feature set and the serialized dynamic feature stream to obtain the correlation feature matrix of the data feature set; The core feature representation of the correlation feature matrix is ​​obtained by performing a nonlinear manifold projection on the correlation feature matrix. Cross-dimensional semantic condensation is performed on the core feature representation to obtain the fused data of the data feature set.

[0009] When the data fusion module performs cross-correlation analysis on the static feature set and the serialized dynamic feature stream to obtain the correlation feature matrix of the data feature set, it is specifically used for: The topological attributes of the static feature set are decomposed to obtain the basic feature components of the static feature set; The temporal stability of the serialized dynamic feature stream is evaluated to obtain the dynamic evolution index of the serialized dynamic feature stream; Based on the fundamental feature components and the dynamic evolution index, the correlation strength between the static feature set and the serialized dynamic feature stream is generated, wherein the formula for calculating the correlation strength is as follows: ; In the formula, For the first in the static feature set The static feature and the first static feature in the serialized dynamic feature stream The strength of the correlation between dynamic features For the preset topological feature mapping function, For the first The aforementioned static features For the preset dynamic feature encoding function, For the first The aforementioned dynamic features, This is the tensor product operator. The preset dynamic compensation coefficient, It is the L2 norm. For the preset time dimension gradient, To represent the dynamic features The temporal gradient, The predefined evaluation function for feature significance. The time-series gradient The maximum value, To perform a logarithmic transformation on the saliency of the aforementioned features; Assigning a topological structure to the association strength yields the association feature matrix of the data feature set.

[0010] In a preferred embodiment, when the task parsing module performs joint parsing of dependencies and resource conflicts in the collaborative task list deconstructed from the fused data to obtain a conflict-free task list for the target building, it is specifically used for: The fused data is deconstructed to obtain a list of collaborative tasks for the fused data, and the dependency logic of the collaborative tasks in the list of collaborative tasks is parsed to obtain the structured dependency relationship of the collaborative tasks. Based on the structured dependencies, a conflict analysis is performed on the resource allocation of the target building to obtain the conflict hotspot mapping of the collaborative task; Priority coordination is performed on the structured dependencies and the conflict hotspot mappings to obtain a coordination scheme for the collaborative tasks; The coordination scheme is analyzed for task compatibility to obtain a list of conflict-free tasks for the target building.

[0011] When the task parsing module prioritizes the structured dependencies and conflict hotspot mappings to obtain a preliminary coordination scheme for the collaborative tasks, it is specifically used for: Graph theory feature analysis is performed on the task nodes in the structured dependency relationship to obtain the criticality index of the task nodes; The intensity of the conflict hotspot mapping is quantitatively assessed to obtain the competition intensity coefficient of building resources in the target building. The formula for calculating the competition intensity coefficient is as follows: ; In the formula, For the first The competition intensity coefficient of the aforementioned building resources. For the first The priority weight of each task node. For the first The task node mentioned above is for the first The required density of the aforementioned building resources The preset time decay coefficient, The preset time sensitivity decay factor, For the preset first The emergency time window for each of the aforementioned task nodes. For the first The maximum demand benchmark for the aforementioned building resources. For the first The task node mentioned above, for any first... The demand density of the aforementioned building resources The preset pressure adjustment coefficient, For the first The supply and demand pressure gradient of the aforementioned building resources, For the first The benchmark for the maximum supply and demand pressure of the aforementioned building resources. For the first The scarcity index of the aforementioned building resources, This is a logarithmic transformation of the scarcity index.

[0012] The coordination priority of the collaborative task is obtained by weighting and fusing the criticality index of the task node with the competition intensity coefficient of the building resource. Based on the coordination priority, the coordination tasks are prioritized to obtain a preliminary coordination scheme for the coordination tasks.

[0013] In a preferred embodiment, when the scheduling optimization module executes the process of scheduling target optimization data in the conflict-free task list according to time priority to obtain an optimized scheduling plan for the conflict-free task list, it is specifically used for: Temporal dependency mining is performed on the list of conflict-free tasks to obtain the set of temporal constraint rules for the list of conflict-free tasks. Based on the time-series constraint rule set, a resource supply reliability analysis is performed on the building resources to obtain a preliminary resource allocation strategy for the building resources. A target trade-off analysis is performed on the conflict-free task list to obtain the target optimization requirements for the conflict-free task list. The preliminary resource allocation strategy and the target optimization requirements are coordinated and decided to obtain the optimized scheduling blueprint of the building resources. The optimized scheduling blueprint is instantiated with a scheduling strategy to obtain the optimized scheduling plan for the list of conflict-free tasks.

[0014] In a preferred embodiment, when the task execution module updates the collaborative task list according to the optimized scheduling plan and applies the updated list to the target building, it is specifically used for: Discretize the optimized scheduling plan to obtain the task instruction sequence for the target building; The task instruction sequence is configured with parameters to obtain the executable instruction set of the target building; Based on the executable instruction set, the collaborative task list is subjected to version iteration management to obtain the updated collaborative task list of the target building; The updated list of collaborative tasks is distributed to the target building execution terminal.

[0015] To address the above problems, the present invention also provides an integrated collaborative method for intelligent construction, the method comprising: S1. Collect raw data from the target building, and normalize the raw data to obtain standardized data of the target building; S2. Extract multi-level features from the standardized data to construct a data feature set of the standardized data; S3. Couple the static attribute features and dynamic behavior features in the data feature set in multiple dimensions to obtain the fused data of the data feature set; S4. Perform joint analysis on the dependencies and resource conflicts in the collaborative task list deconstructed from the fused data to obtain a conflict-free task list for the target building. S5. Based on the time priority, schedule the target optimization data in the conflict-free task list to obtain the optimized scheduling plan of the conflict-free task list. S6. Update the collaborative task list according to the optimized scheduling plan, and apply the updated list to the target building.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention significantly improves the consistency and integrity of construction data through a complete technical process involving data preprocessing, multi-level feature extraction, and multi-dimensional coupling. It employs a method combining spatial distribution feature extraction and temporal evolution feature analysis, coupled with a feature tensor fusion mechanism, to transform multi-source heterogeneous data into a data feature set with unified semantic representation. By introducing an association computation model of topological feature mapping and dynamic feature encoding, it achieves deep coupling between static attributes and dynamic behavioral features, enhancing the expressive power of data features and providing a reliable data foundation for intelligent decision-making in the construction process.

[0017] 2. This invention effectively improves the efficiency and accuracy of collaborative construction management by constructing a joint analysis mechanism for task dependencies and resource conflicts. A dynamic coordination function is established using a combination of graph theory feature analysis and resource competition intensity quantification to accurately assess task criticality and resource competition dynamics. Through the organic integration of temporal dependency mining and multi-objective collaborative decision-making, a complete closed loop from task analysis to scheduling and execution is formed, ensuring effective connection between resource allocation and task execution, and significantly improving the collaborative efficiency and resource utilization efficiency of the construction process. Attached Figure Description

[0018] Figure 1 This is a platform architecture diagram of an integrated intelligent construction collaborative platform provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating an embodiment of the intelligent construction integrated collaborative method provided by the present invention.

[0019] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments belong to some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “said” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0022] Depending on the context, the word "if" or "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0023] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0024] In practice, the server-side equipment deployed by the integrated intelligent construction collaboration platform may consist of one or more devices. This integrated intelligent construction collaboration platform can be implemented as: a business instance, a virtual machine, or hardware devices. For example, the integrated intelligent construction collaboration platform can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, the integrated intelligent construction collaboration platform can be understood as software deployed on a cloud node, used to provide the integrated intelligent construction collaboration platform to various user terminals. Alternatively, the integrated intelligent construction collaboration platform can also be implemented as a virtual machine deployed on one or more devices in a cloud node. This virtual machine contains application software for managing various user terminals. Alternatively, the integrated intelligent construction collaboration platform can also be implemented as a server composed of numerous identical or different types of hardware devices, with one or more hardware devices configured to provide the integrated intelligent construction collaboration platform to various user terminals.

[0025] In terms of implementation, the integrated intelligent construction collaboration platform and the user terminal are mutually adaptable. That is, if the integrated intelligent construction collaboration platform is implemented as an application installed on a cloud service platform, then the user terminal is implemented as a client that establishes a communication connection with the application; or if the integrated intelligent construction collaboration platform is implemented as a website, then the user terminal is implemented as a webpage; or if the integrated intelligent construction collaboration platform is implemented as a cloud service platform, then the user terminal is implemented as a mini-program in an instant messaging application.

[0026] like Figure 1 The diagram shown is a platform architecture diagram of an integrated collaborative platform for intelligent construction provided in an embodiment of the present invention.

[0027] The intelligent construction integrated collaborative platform 100 described in this invention can be located on a cloud server. In terms of implementation, it can function as one or more service devices, or as an application installed on the cloud (e.g., a mobile service operator's server, server cluster, etc.), or it can be developed as a website. Depending on the functions implemented, the intelligent construction integrated collaborative platform 100 may include a data preprocessing module 101, a feature extraction module 102, a data fusion module 103, a task parsing module 104, a scheduling optimization module 105, and a task execution module 106. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, stored in the memory of the electronic device.

[0028] In this embodiment of the invention, each of the above-mentioned modules in the integrated intelligent construction collaborative platform can be implemented independently and can call other modules. Here, "calling" can be understood as a module connecting to multiple modules of another type and providing corresponding services to those connected modules. In the integrated intelligent construction collaborative platform provided by this embodiment of the invention, the applicable scope of the platform architecture can be adjusted by adding modules and directly calling them without modifying the program code, achieving cluster-based horizontal expansion to quickly and flexibly expand the integrated intelligent construction collaborative platform. In practical applications, the above-mentioned modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in a cloud server.

[0029] The following describes the various components and specific workflows of the integrated intelligent construction collaborative platform, using specific embodiments as examples: The data preprocessing module 101 is used to collect raw data from the target building, normalize the raw data, and obtain standardized data of the target building. In this embodiment of the invention, when the data preprocessing module performs normalization processing on the raw data collected from the target building to obtain standardized data of the target building, it is specifically used for: Collect raw data from the target building; Within a sliding time window, the original data is denoised to obtain a clean dataset of the original data; Tensor reconstruction is performed on the cleaning dataset to obtain the standardized data vector of the target building; The standardized data vector is distributed and normalized to obtain the standardized data of the target building.

[0030] When collecting raw data from the target building, data acquisition is achieved by constructing virtual data acquisition nodes. These nodes are deployed according to the predefined spatial coordinates and logical relationships in the building information, and continuously receive structured and unstructured data inputs from various data sources to form a raw data set containing time series markers. The data acquisition process uses timestamp synchronization technology to ensure that all data units have a unified time reference.

[0031] When denoising the original data in a sliding time window, a fixed-length time segment is used as the basic processing unit. In each window, a mean-value filtering method is applied to sort all data points in the window in ascending order of numerical value and take the value of the middle position as the output value. This sorting and replacement mechanism effectively eliminates abnormal fluctuations in the data. This operation is repeated until the entire data sequence is completely covered, and finally a smoothed clean dataset is generated. This method can effectively preserve the edge features of the data while removing impulse noise.

[0032] When performing tensor reconstruction on the cleaning dataset, the temporal data is reorganized according to the topological correlation of building elements. The multi-dimensional data collected at the same time are arranged and combined according to the spatial hierarchy to construct a three-dimensional data structure with time dimension, spatial dimension and feature dimension. The position of each data point is determined by its time coordinate, spatial coordinate and feature type, forming a standardized data vector that maintains the inherent correlation characteristics. This vector completely preserves the spatiotemporal characteristics of the original data.

[0033] When performing distribution normalization on standardized data vectors, the extreme value normalization method is used to identify the maximum and minimum values ​​of each dimension in the data vector. Through linear transformation, each data point is mapped to a closed interval between zero and one. The specific calculation process is to subtract the minimum value of the dimension from each data value and then divide by the range of that dimension to ensure that all feature dimensions have a uniform numerical dimension and distribution range, thereby generating standardized data that meets the specifications.

[0034] The beneficial effects are as follows: data is continuously received according to predefined spatial coordinates and logical relationships to form a raw data set with time series labels. Then, the median filtering method is used in a sliding time window to sort the data and take the median value to generate a clean dataset. Then, according to the topological correlation of building elements, the time series data is reorganized into a three-dimensional data structure with time dimension, spatial dimension and feature dimension to form a standardized data vector. Finally, the extreme value normalization method is used to linearly transform the data of each dimension to the zero-one interval to ensure the uniformity of dimensions and the standardization of distribution. Thus, the complete data preprocessing process from data acquisition to noise processing to structural reconstruction and standardization is completed, ensuring that the quality and specifications of building data meet the requirements of subsequent feature extraction.

[0035] The feature extraction module 102 is used to extract multi-level features from the standardized data to construct a data feature set of the standardized data. In this embodiment of the invention, when the feature extraction module performs the extraction of multi-level features from the standardized data to construct the data feature set of the standardized data, it is specifically used for: Based on the spatial reference system in the standardized data, the association relationship mining is performed on the data in the standardized data to obtain the spatial distribution feature set of the standardized data. In the continuous time domain, the spatiotemporal correlation structure of the spatial distribution feature set is constructed based on the correlation characteristics of the spatial distribution feature set; Based on the spatiotemporal correlation structure, the evolution path of the spatial distribution feature set is extracted to obtain the temporal evolution feature set of the spatial distribution feature set; The spatial distribution feature set and the temporal evolution feature set are quantized to obtain the state feature vector of the standardized data. The spatial distribution feature set, the temporal evolution feature set, and the state feature vector are adaptively weighted and fused to obtain the data feature set of the standardized data.

[0036] When mining data associations based on spatial reference frames in standardized data, spatial adjacency analysis is used. By calculating the co-occurrence frequency and relative position of data points in a preset spatial grid, a spatial dependency network between data is established. The similarity and difference of data distribution in different spatial regions are analyzed, feature combinations with stable spatial distribution patterns are identified, and a spatial distribution feature set of standardized data is formed.

[0037] When constructing a spatiotemporal correlation structure based on the correlation features of a spatial distribution feature set in the continuous time domain, a spatiotemporal dimension integration technique is adopted. Each feature node in the spatial distribution feature set is connected to the temporal dimension. By recording the continuous transfer trajectory of feature states on the time axis, the regularity of feature value changes with time is analyzed, and a spatiotemporal correlation structure that can simultaneously express spatial correlation and temporal evolution characteristics is constructed.

[0038] When extracting the evolution path of spatially distributed feature sets based on spatiotemporal correlation structures, temporal trajectory tracking technology is used to analyze the state change process of feature nodes in continuous time segments. By capturing the evolution direction and intensity change law of feature vectors, the development trend of features in the spatiotemporal dimension is identified, and the complete development path of features from the initial state to the final state is depicted, forming the temporal evolution feature set of spatially distributed feature sets.

[0039] When quantifying the state features of spatial distribution feature sets and temporal evolution feature sets, dynamic feature evaluation technology is used to measure the variance of spatial distribution features in the time dimension and the fluctuation amplitude of temporal evolution features. By numerically representing the dynamic change degree and distribution concentration of features, the stability and change trend of feature states are analyzed, and a state feature vector of standardized data with clear numerical representation is generated.

[0040] When performing adaptive weighted fusion of spatial distribution feature sets, temporal evolution feature sets, and state feature vectors, a feature importance assessment technique is adopted. The fusion weight is calculated based on the quantitative index of each feature in the state feature vector. The three feature sets are integrated into a unified multidimensional data structure through weighted summation and dimension alignment operations. The complementarity and correlation between features are analyzed, and finally a complete data feature set of standardized data is generated.

[0041] The beneficial effects are as follows: after mining the correlations in standardized data through spatial adjacency analysis to form a spatial distribution feature set, a spatiotemporal correlation structure is constructed using spatiotemporal dimension integration technology. Then, the evolution path is extracted using time-series trajectory tracking technology to obtain a time-series evolution feature set. Next, state features are quantified using dynamic feature evaluation technology to generate state feature vectors. Finally, based on feature importance evaluation technology, the spatial distribution feature set, the time-series evolution feature set, and the state feature vectors are adaptively weighted and fused. The three types of feature sets are integrated into a unified multidimensional data structure, and the complementarity and correlation between features are analyzed. Finally, a complete data feature set of standardized data is generated, thereby realizing a complete feature extraction process from spatial feature mining to spatiotemporal feature fusion, ensuring the comprehensiveness and representativeness of the feature set.

[0042] The data fusion module 103 is used to couple the static attribute features and dynamic behavior features in the data feature set in multiple dimensions to obtain the fused data of the data feature set. In this embodiment of the invention, when the data fusion module performs multi-dimensional coupling of static attribute features and dynamic behavior features in the data feature set to obtain fused data of the data feature set, it is specifically used for: The static feature set of the data feature set is obtained by performing topological structure analysis on the static attribute features of the data feature set. Temporal pattern extraction is performed on the dynamic behavior features of the data feature set to obtain a serialized dynamic feature stream of the data feature set; A cross-correlation analysis is performed on the static feature set and the serialized dynamic feature stream to obtain the correlation feature matrix of the data feature set; The core feature representation of the correlation feature matrix is ​​obtained by performing a nonlinear manifold projection on the correlation feature matrix. Cross-dimensional semantic condensation is performed on the core feature representation to obtain the fused data of the data feature set.

[0043] When the data fusion module performs cross-correlation analysis on the static feature set and the serialized dynamic feature stream to obtain the correlation feature matrix of the data feature set, it is specifically used for: The topological attributes of the static feature set are decomposed to obtain the basic feature components of the static feature set; The temporal stability of the serialized dynamic feature stream is evaluated to obtain the dynamic evolution index of the serialized dynamic feature stream; Based on the fundamental feature components and the dynamic evolution index, the correlation strength between the static feature set and the serialized dynamic feature stream is generated, wherein the formula for calculating the correlation strength is as follows: ; In the formula, For the first in the static feature set The static feature and the first static feature in the serialized dynamic feature stream The strength of the correlation between dynamic features For the preset topological feature mapping function, For the first The aforementioned static features For the preset dynamic feature encoding function, For the first The aforementioned dynamic features, This is the tensor product operator. The preset dynamic compensation coefficient, It is the L2 norm. For the preset time dimension gradient, To represent the dynamic features The temporal gradient, The predefined evaluation function for feature significance. The time-series gradient The maximum value, To perform a logarithmic transformation on the saliency of the aforementioned features; Assigning a topological structure to the association strength yields the association feature matrix of the data feature set.

[0044] When performing topological structure analysis on the static attribute features of a data feature set, a feature association analysis method is used to identify the connection relationships and hierarchical structure between feature elements. By analyzing the dependency paths and combination patterns between features, discrete static attribute features are reorganized into a feature set with clear structural relationships, forming the static feature set of the data feature set.

[0045] When extracting time-series patterns from the dynamic behavioral features of the data feature set, a sliding window processing technique is used to extract dynamic feature segments in chronological order, analyze the changing trends and periodic patterns of feature values ​​within adjacent time segments, and transform the continuously changing dynamic behavioral features into a feature sequence with time-series labels, forming a serialized dynamic feature stream of the data feature set.

[0046] When performing cross-correlation analysis on static feature sets and serialized dynamic feature streams, a feature interaction strength calculation method is adopted. By calculating the interaction strength between static feature elements and dynamic feature sequences at each time point, a multi-dimensional correlation mapping between features is established. The potential relationship between features is quantified into correlation strength values ​​and arranged into a regular matrix form according to feature dimensions to form the correlation feature matrix of the data feature set.

[0047] When performing nonlinear manifold projection on the associated feature matrix, a data transformation method that preserves local structure is adopted to map the feature points in the high-dimensional matrix to a low-dimensional space. By preserving the relative distance and topological relationship between feature points, a low-dimensional representation that can represent the main feature structure of the original matrix is ​​extracted, forming the core feature representation of the associated feature matrix.

[0048] When performing cross-dimensional semantic condensation on core feature representations, a feature information extraction method is adopted. By eliminating redundant information and noise interference between feature dimensions, the expressive power of key feature dimensions is enhanced, and scattered feature information is integrated into compact and semantically rich feature representations, ultimately forming fused data of the data feature set. In the formula, static features originate from the static feature set formed after topological structure analysis of the static attribute features of the data feature set. Dynamic features originate from the serialized dynamic feature stream formed after temporal pattern extraction of the dynamic behavioral features of the data feature set. The topological feature mapping function, applied to the static features, generates vector representations in the topological space. The dynamic feature encoding function, applied to the dynamic features, generates temporal feature vectors. The tensor product operation calculates the outer product of these two vectors to obtain a higher-order tensor. The L2 norm is used to calculate the magnitudes of these two vectors for normalization. The temporal gradient is obtained by calculating the rate of change of the dynamic features over time. The feature significance evaluation function evaluates the importance of the static features to obtain a quantified value of feature significance. The dynamic compensation coefficient is obtained through training with historical data to adjust the weights of the temporal variation component. The maximization function selects the maximum value of the temporal gradient within a given time window for normalization. Logarithmic transformation numerically compresses feature significance to ensure computational stability.

[0049] The significance of this formula lies in achieving deep coupling between features by calculating the correlation strength between static and dynamic features. The first part of the formula captures the multi-dimensional interaction between static and dynamic features through tensor product operations and eliminates feature scale differences through normalization. The second part of the formula reflects the instantaneous change trend of dynamic features through temporal gradients and emphasizes the contribution of important static features through feature saliency. The weighted combination of the two parts considers both the semantic similarity between features and incorporates temporal dynamic characteristics to form a comprehensive assessment of correlation strength.

[0050] The formula shows that the association strength tends to increase when static and dynamic features have high similarity in the topological space. The association strength also increases when dynamic features change drastically over time. Furthermore, the association strength is further enhanced when static features have high significance. The dynamic compensation coefficient modulates the contribution of time-varying factors to the overall association strength. Normalization ensures that the association strength remains within a stable and comparable range, avoiding the influence of extreme values. Logarithmic transformation ensures that feature significance does not excessively dominate the calculation results, maintaining a balance among various factors.

[0051] The beneficial effects are as follows: After forming a static feature set by topological structure analysis of the static attribute features of the data feature set, a serialized dynamic feature stream is generated by temporal pattern extraction of dynamic behavioral features. This stream serves as the input source, and topological feature mapping and dynamic feature encoding are applied to generate vector representations. Tensor product operations are then used to capture multi-dimensional interaction relationships between features, and L2 norm is used for normalization. Simultaneously, cross-correlation analysis is performed on the static feature set and the serialized dynamic feature stream to obtain a correlation feature matrix. Subsequently, temporal gradients are used to reflect dynamic change trends and feature significance assessments to quantify importance. Dynamic compensation coefficients are combined to adjust weight allocation, leveraging the maximum... Value functions and logarithmic transformations ensure computational stability and balance. Then, nonlinear manifold projection is applied to the associated feature matrix to obtain the core feature representation. Finally, cross-dimensional semantic condensation is performed on the core feature representation to eliminate redundant information and strengthen key features. The scattered feature information is integrated into a compact and semantically rich feature representation, ultimately forming fused data of the data feature set. This achieves a complete processing flow from static feature parsing to dynamic feature extraction and then to multi-dimensional feature fusion, ensuring that feature information is fully mined and effectively integrated. Furthermore, it enhances the association strength value when feature similarity is high, dynamic changes are significant, or feature importance is prominent, maintaining the coordinated relationship between various factors.

[0052] The task parsing module 104 is used to jointly parse the dependencies and resource conflicts in the collaborative task list deconstructed from the fused data to obtain a conflict-free task list for the target building. In this embodiment of the invention, when the task parsing module performs joint parsing of dependencies and resource conflicts in the collaborative task list deconstructed from the fused data to obtain a conflict-free task list for the target building, it is specifically used for: The fused data is deconstructed to obtain a list of collaborative tasks for the fused data, and the dependency logic of the collaborative tasks in the list of collaborative tasks is parsed to obtain the structured dependency relationship of the collaborative tasks. Based on the structured dependencies, a conflict analysis is performed on the resource allocation of the target building to obtain the conflict hotspot mapping of the collaborative task; Priority coordination is performed on the structured dependencies and the conflict hotspot mappings to obtain a coordination scheme for the collaborative tasks; The coordination scheme is analyzed for task compatibility to obtain a list of conflict-free tasks for the target building.

[0053] When the task parsing module performs priority coordination on the structured dependencies and conflict hotspot mappings to obtain a preliminary coordination scheme for the collaborative tasks, it is specifically used for: Graph theory feature analysis is performed on the task nodes in the structured dependency relationship to obtain the criticality index of the task nodes; The intensity of the conflict hotspot mapping is quantitatively assessed to obtain the competition intensity coefficient of building resources in the target building. The formula for calculating the competition intensity coefficient is as follows: ; In the formula, For the first The competition intensity coefficient of the aforementioned building resources. For the first The priority weight of each task node. For the first The task node mentioned above is for the first The demand density of the aforementioned building resources The preset time decay coefficient, The preset time sensitivity decay factor, For the preset first The emergency time window for each of the aforementioned task nodes. For the first The maximum demand benchmark for the aforementioned building resources. For the first The task node mentioned above, for any first... The demand density of the aforementioned building resources The preset pressure adjustment coefficient, For the first The supply and demand pressure gradient of the aforementioned building resources, For the first The benchmark for the maximum supply and demand pressure of the aforementioned building resources. For the first The scarcity index of the aforementioned building resources, This is a logarithmic transformation of the scarcity index.

[0054] The coordination priority of the collaborative task is obtained by weighting and fusing the criticality index of the task node with the competition intensity coefficient of the building resource. Based on the coordination priority, the coordination tasks are prioritized to obtain a preliminary coordination scheme for the coordination tasks.

[0055] When deconstructing the fused data, a task element extraction approach is adopted. By identifying the task types and execution conditions contained in the data, the fused data is transformed into independent tasks. A logical arrangement of task sequences is established based on the input-output relationships between tasks, forming a collaborative task list with clearly defined task items and execution order. When parsing the dependency logic of the collaborative tasks in the collaborative task list, a dependency graph construction approach is used. This analyzes the preconditions and subsequent effects of each task, establishes directed connections between task nodes, and forms a structured dependency relationship that fully describes the task execution logic.

[0056] When performing conflict analysis on the resource allocation of the target building based on structured dependencies, a resource conflict detection method is adopted. This method iterates through the resource requirements of each task node and the matching status with the current resource pool, identifies task combinations with resource competition and their conflict severity, and generates a conflict hotspot map that marks the conflict location and intensity. When prioritizing the structured dependencies and conflict hotspot maps, a dynamic priority coordination method is used. This method comprehensively considers the importance of tasks in the dependency network and the severity of resource conflicts, generating a coordination scheme for the task execution sequence by balancing task urgency and resource availability.

[0057] When performing task compatibility analysis on the coordination scheme, a task compatibility verification method is adopted to check for resource usage conflicts and logical contradictions between adjacent tasks in the coordination scheme. For conflicting task pairs, the execution timing is adjusted or resources are reallocated. After multiple rounds of iterative optimization, all conflict points are eliminated, and finally a list of conflict-free tasks that can be executed smoothly is formed.

[0058] The priority weight of task nodes is derived from the quantitative assessment of the importance of each task in the collaborative task list. The demand density of building resources for task nodes is derived by analyzing the type and quantity of resources required for each task execution. The time decay coefficient is a pre-set numerical parameter based on historical task execution data. The time sensitivity decay factor calculates the impact of the task's urgent time window on resource demand using an exponential function. The urgent time window is a timeliness indicator determined based on the difference between the task plan and the current time. The maximum demand benchmark is the highest value selected after comparing the weighted total demand of all building resources. The pressure adjustment coefficient is a pre-set adjustment parameter based on the system's operating status. The supply and demand pressure gradient of building resources is derived by calculating the difference between the current demand and supply of resources. The maximum supply and demand pressure benchmark is the highest value selected after comparing the supply and demand pressure of all building resources. The scarcity index of building resources is an assessment value derived by analyzing the ratio of resource inventory to demand. The logarithmic transformation uses the natural logarithm function to process the scarcity index to smooth its numerical fluctuations.

[0059] This formula quantifies the competitive intensity faced by building resources during task execution. The first part of the formula calculates the real-time demand pressure of resources at the current moment using a weighted summation method. The second part of the formula reflects the long-term tension of resources through supply and demand pressure and scarcity indicators. The combination of the two parts can comprehensively assess the competitive situation of resources in both short-term and long-term dimensions.

[0060] The competition intensity coefficient increases accordingly as the resource demand density of a task increases. The time sensitivity decay factor enhances competition intensity when the task's urgency window shortens. The competition intensity coefficient rises significantly when the resource supply and demand pressure gradient increases. The competition intensity coefficient gains additional growth when the resource scarcity index increases. Normalization of the maximum demand benchmark ensures the comparability of competition intensity among different resources. Normalization of the maximum supply and demand pressure benchmark maintains the stability of the system evaluation. Logarithmic transformation effectively mitigates the impact of extreme fluctuations in the scarcity index on the calculation results. The pressure adjustment coefficient controls the contribution ratio of supply and demand pressure to the overall competition intensity.

[0061] The beneficial effects are as follows: After extracting task elements from the fused data to form a collaborative task list with clear task items and execution order, dependency logic parsing is performed to establish a structured dependency relationship that fully describes the task execution logic. Based on this, considering factors such as task priority weights and resource demand density, and combining time sensitivity decay factors and emergency time window timeliness indicators, resource conflict detection is performed based on the structured dependency relationship to generate conflict hotspot mappings that mark conflict locations and intensities. Then, through dynamic priority coordination, a coordination scheme for the task execution sequence is generated by comprehensively considering task importance and the degree of resource conflict. Simultaneously, the maximum demand benchmark and supply and demand pressure are utilized. The force gradient is normalized, and a logarithmic transformation of the scarcity index is introduced to smooth the fluctuations. Finally, after task compatibility verification, the execution time of conflicting task pairs is adjusted or resources are reallocated. Through multiple rounds of iterative optimization, until all conflict points are eliminated, a list of conflict-free tasks that can be executed smoothly is formed. This achieves accurate quantification of the intensity of competition for building resources, comprehensively reflects the overall competitive situation of resources in terms of short-term demand pressure and long-term tension, ensures that the evaluation results are comparable and stable, and completes the entire process from task deconstruction to dependency analysis to conflict detection and conflict resolution, ensuring that the execution process of building tasks has complete logic and resource coordination.

[0062] The scheduling optimization module 105 is used to schedule the target optimization data in the conflict-free task list according to the time priority, so as to obtain the optimized scheduling plan of the conflict-free task list. In this embodiment of the invention, when the scheduling optimization module executes the step of scheduling the target optimization data in the conflict-free task list according to the time priority to obtain the optimized scheduling plan of the conflict-free task list, it is specifically used for: Temporal dependency mining is performed on the list of conflict-free tasks to obtain the set of temporal constraint rules for the list of conflict-free tasks. Based on the time-series constraint rule set, a resource supply reliability analysis is performed on the building resources to obtain a preliminary resource allocation strategy for the building resources. A target trade-off analysis is performed on the conflict-free task list to obtain the target optimization requirements for the conflict-free task list. The preliminary resource allocation strategy and the target optimization requirements are coordinated and decided to obtain the optimized scheduling blueprint of the building resources. The optimized scheduling blueprint is instantiated with a scheduling strategy to obtain the optimized scheduling plan for the list of conflict-free tasks.

[0063] When mining temporal dependencies in a conflict-free task list, a task sequence pattern recognition method is used to analyze the temporal order constraints between tasks, identify the order requirements and time intervals of task execution, and transform the temporal dependencies between tasks into explicit temporal constraint rules. By traversing the temporal relationships of all task nodes in the task list, a complete temporal constraint system is established, forming a set of temporal constraint rules for the conflict-free task list.

[0064] When performing resource supply reliability analysis on building resources based on time-constrained rule sets, a resource time availability assessment method is adopted to check the availability status of each resource during the task execution period, identify the degree of matching between resource supply and task time requirements, and find resource allocation nodes with time conflicts by analyzing the resource occupancy in the time dimension and the overlap of task time windows. The correspondence between resources and task time requirements is established, and a preliminary resource allocation strategy for building resources is formed.

[0065] When conducting target trade-off analysis on a conflict-free task list, a multi-objective optimization identification method is adopted. This method analyzes the interrelationship between schedule requirements, resource consumption indicators, and quality standards during task execution, determines the priority order and weight allocation of each optimization objective, and establishes a trade-off mechanism between objectives by evaluating the degree of mutual influence between different objectives, thereby forming the target optimization requirements for the conflict-free task list.

[0066] When making target coordination decisions on the initial resource allocation strategy and target optimization requirements, a resource-target collaborative optimization method is adopted. The resource allocation scheme is adjusted to meet the weight requirements of each optimization target. Under the premise of ensuring task timing constraints, the conflict between different targets is balanced. Through iterative optimization, the resource allocation scheme is gradually adjusted so that the resource allocation strategy and target optimization requirements reach the best matching state, forming an optimized scheduling blueprint for building resources.

[0067] When instantiating scheduling strategies for the optimized scheduling blueprint, a task-resource binding method is adopted to transform the abstract resource allocation in the blueprint into a specific task execution plan. The start time, end time and corresponding resource allocation details of each task are determined. By establishing the correspondence between the task schedule table and the resource allocation table, the optimized scheduling blueprint is transformed into an executable scheduling plan, forming an optimized scheduling plan with a conflict-free task list.

[0068] The beneficial effects are as follows: by mining the temporal dependency relationship of the conflict-free task list to form a temporal constraint rule set, a resource supply reliability analysis of building resources is performed based on the rule set to obtain a preliminary resource allocation strategy. At the same time, a target trade-off analysis is performed on the conflict-free task list to generate target optimization requirements. Then, through the resource target collaborative optimization method, the preliminary resource allocation strategy and target optimization requirements are coordinated and decided to obtain an optimized scheduling blueprint for building resources. Finally, the task resource binding method is used to transform the optimized scheduling blueprint into a specific task execution plan, determining the start time and end time of each task and the corresponding resource allocation details. By establishing the correspondence between the task time table and the resource allocation table, an optimized scheduling plan for the conflict-free task list is formed, thus realizing a complete process from task temporal analysis to resource coordination and allocation to scheduling plan generation, ensuring a high degree of coordination between task execution and resource supply.

[0069] The task execution module 106 is used to update the collaborative task list according to the optimized scheduling plan and apply the updated list to the target building. In this embodiment of the invention, when the task execution module performs the step of updating the collaborative task list according to the optimized scheduling plan and applying the updated list to the target building, it is specifically used for: Discretize the optimized scheduling plan to obtain the task instruction sequence for the target building; The task instruction sequence is configured with parameters to obtain the executable instruction set of the target building; Based on the executable instruction set, the collaborative task list is subjected to version iteration management to obtain the updated collaborative task list of the target building; The updated list of collaborative tasks is distributed to the target building execution terminal.

[0070] When converting task instructions into optimized scheduling plans, a step-by-step decomposition method is adopted. Each task node in the plan is transformed into an independent operation unit with a clear execution order. A continuous flow of operation steps is formed according to the time progression. The accuracy of the execution order is ensured by establishing the connection relationship between steps. The order of steps is adjusted according to task characteristics and correlations, and finally, the task instruction sequence of the target building is generated.

[0071] When setting parameters for the task instruction sequence, an instruction element configuration method is adopted. Each operation instruction is matched with corresponding resource identification information, execution time range and quality standard requirements. The coordination between elements is verified to ensure that the instruction can be implemented. The adaptability of resource allocation and time arrangement is checked, the degree of conformity between quality requirements and implementation conditions is confirmed, and contradictory or unimplementable element combinations are eliminated to form an executable instruction set for the target building.

[0072] When updating the collaborative task list based on the executable instruction set, a task progress tracking method is adopted. The task status identifier is dynamically refreshed according to the progress of instruction implementation, completed tasks are removed and newly generated tasks are added to maintain the consistency between the task list and the current implementation status, record the task version change process, maintain the integrity of task association relationships, ensure that the task list always reflects the latest implementation status, and generate the updated collaborative task list of the target building.

[0073] When transmitting the updated collaborative task list to the target building execution terminal, a unified list version method is adopted. Data verification measures are used to ensure that the list version received by each terminal is completely consistent. A terminal implementation status feedback channel is established to monitor the list transmission progress, handle data deviations during transmission, confirm that all terminals have successfully received and verified the new version list, and complete the deployment and synchronization of the collaborative task list.

[0074] The beneficial effects are as follows: by transforming the task arrangement in the optimized scheduling plan into independent operation steps with a clear execution order to form a sequence of task instructions, and then configuring corresponding resource identification content, implementation time range and quality specification requirements for each operation instruction to generate an executable instruction set, the task status is dynamically updated according to the instruction execution progress and the task association logic is maintained to form an updated collaborative task list. Finally, by comparing data, it is ensured that the version of the list received by each terminal is completely consistent and an implementation status feedback channel is established to complete the deployment and synchronization of the collaborative task list. This realizes a complete execution process from plan conversion to instruction generation to task update to terminal coordination, ensuring the continuity and coordination of the construction task implementation process.

[0075] Reference Figure 2 The diagram shown is a flowchart illustrating an integrated intelligent construction collaboration method according to an embodiment of the present invention. In this embodiment, the integrated intelligent construction collaboration method includes: S1. Collect raw data from the target building, and normalize the raw data to obtain standardized data of the target building; S2. Extract multi-level features from the standardized data to construct a data feature set of the standardized data; S3. Couple the static attribute features and dynamic behavior features in the data feature set in multiple dimensions to obtain the fused data of the data feature set; S4. Perform joint analysis on the dependencies and resource conflicts in the collaborative task list deconstructed from the fused data to obtain a conflict-free task list for the target building. S5. Based on the time priority, schedule the target optimization data in the conflict-free task list to obtain the optimized scheduling plan of the conflict-free task list. S6. Update the collaborative task list according to the optimized scheduling plan, and apply the updated list to the target building.

[0076] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0077] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application platform that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An integrated intelligent construction collaborative platform, characterized in that, The platform includes a data preprocessing module, a feature extraction module, a data fusion module, a task parsing module, a scheduling optimization module, and a task execution module, wherein: The data preprocessing module is used to collect raw data from the target building, normalize the raw data, and obtain standardized data of the target building. The feature extraction module is used to extract multi-level features from the standardized data to construct a data feature set of the standardized data. The data fusion module is used to couple the static attribute features and dynamic behavior features in the data feature set in multiple dimensions to obtain the fused data of the data feature set. The task parsing module is used to jointly parse the dependencies and resource conflicts in the collaborative task list deconstructed from the fused data to obtain a conflict-free task list for the target building. The scheduling optimization module is used to schedule the target optimization data in the conflict-free task list according to the time priority, so as to obtain the optimized scheduling plan of the conflict-free task list. The task execution module is used to update the collaborative task list according to the optimized scheduling plan and apply the updated list to the target building.

2. The intelligent construction integrated collaborative platform as described in claim 1, characterized in that, When the data preprocessing module collects raw data from the target building and normalizes the raw data to obtain standardized data for the target building, it specifically performs the following: Collect raw data from the target building; Within a sliding time window, the original data is denoised to obtain a clean dataset of the original data; Tensor reconstruction is performed on the cleaning dataset to obtain the standardized data vector of the target building; The standardized data vector is distributed and normalized to obtain the standardized data of the target building.

3. The intelligent construction integrated collaborative platform as described in claim 1, characterized in that, When the feature extraction module extracts multi-level features from the standardized data to construct the data feature set of the standardized data, it is specifically used for: Based on the spatial reference system in the standardized data, the association relationship mining is performed on the data in the standardized data to obtain the spatial distribution feature set of the standardized data. In the continuous time domain, the spatiotemporal correlation structure of the spatial distribution feature set is constructed based on the correlation characteristics of the spatial distribution feature set; Based on the spatiotemporal correlation structure, the evolution path of the spatial distribution feature set is extracted to obtain the temporal evolution feature set of the spatial distribution feature set; The spatial distribution feature set and the temporal evolution feature set are quantized to obtain the state feature vector of the standardized data. The spatial distribution feature set, the temporal evolution feature set, and the state feature vector are adaptively weighted and fused to obtain the data feature set of the standardized data.

4. The intelligent construction integrated collaborative platform as described in claim 1, characterized in that, When the data fusion module performs multi-dimensional coupling of static attribute features and dynamic behavior features in the data feature set to obtain fused data of the data feature set, it is specifically used for: The static feature set of the data feature set is obtained by performing topological structure analysis on the static attribute features of the data feature set. Temporal pattern extraction is performed on the dynamic behavior features of the data feature set to obtain a serialized dynamic feature stream of the data feature set; A cross-correlation analysis is performed on the static feature set and the serialized dynamic feature stream to obtain the correlation feature matrix of the data feature set; The core feature representation of the correlation feature matrix is ​​obtained by performing a nonlinear manifold projection on the correlation feature matrix. Cross-dimensional semantic condensation is performed on the core feature representation to obtain the fused data of the data feature set.

5. The intelligent construction integrated collaborative platform as described in claim 4, characterized in that, When the data fusion module performs cross-correlation analysis on the static feature set and the serialized dynamic feature stream to obtain the correlation feature matrix of the data feature set, it is specifically used for: The topological attributes of the static feature set are decomposed to obtain the basic feature components of the static feature set; The temporal stability of the serialized dynamic feature stream is evaluated to obtain the dynamic evolution index of the serialized dynamic feature stream; Based on the fundamental feature components and the dynamic evolution index, the correlation strength between the static feature set and the serialized dynamic feature stream is generated, wherein the formula for calculating the correlation strength is as follows: ； In the formula, For the first in the static feature set The static feature and the first static feature in the serialized dynamic feature stream The strength of the correlation between dynamic features For the preset topological feature mapping function, For the first The aforementioned static features For the preset dynamic feature encoding function, For the first The aforementioned dynamic features, This is the tensor product operator. The preset dynamic compensation coefficient, It is the L2 norm. For the preset time dimension gradient, To represent the dynamic features The temporal gradient, The predefined evaluation function for feature significance. The time-series gradient The maximum value, To perform a logarithmic transformation on the saliency of the aforementioned features; Assigning a topological structure to the association strength yields the association feature matrix of the data feature set.

6. The intelligent construction integrated collaborative platform as described in claim 1, characterized in that, When the task parsing module performs joint parsing of dependencies and resource conflicts in the collaborative task list deconstructed from the fused data to obtain a conflict-free task list for the target building, it is specifically used for: The fused data is deconstructed to obtain a list of collaborative tasks for the fused data, and the dependency logic of the collaborative tasks in the list of collaborative tasks is parsed to obtain the structured dependency relationship of the collaborative tasks. Based on the structured dependencies, a conflict analysis is performed on the resource allocation of the target building to obtain the conflict hotspot mapping of the collaborative task; Priority coordination is performed on the structured dependencies and the conflict hotspot mappings to obtain a coordination scheme for the collaborative tasks; The coordination scheme is analyzed for task compatibility to obtain a list of conflict-free tasks for the target building.

7. The intelligent construction integrated collaborative platform as described in claim 6, characterized in that, When the task parsing module prioritizes the structured dependencies and conflict hotspot mappings to obtain a preliminary coordination scheme for the collaborative tasks, it is specifically used for: Graph theory feature analysis is performed on the task nodes in the structured dependency relationship to obtain the criticality index of the task nodes; The intensity of the conflict hotspot mapping is quantitatively assessed to obtain the competition intensity coefficient of building resources in the target building. The formula for calculating the competition intensity coefficient is as follows: ； In the formula, For the first The competition intensity coefficient of the aforementioned building resources. For the first The priority weight of each task node. For the first The task node mentioned above is for the first The demand density of the aforementioned building resources The preset time decay coefficient, The preset time sensitivity decay factor, For the preset first The emergency time window for each of the aforementioned task nodes. For the first The maximum demand benchmark for the aforementioned building resources. For the first The task node mentioned above, for any first... The demand density of the aforementioned building resources The preset pressure adjustment coefficient, For the first The supply and demand pressure gradient of the aforementioned building resources, For the first The benchmark for the maximum supply and demand pressure of the aforementioned building resources. For the first The scarcity index of the aforementioned building resources, This is a logarithmic transformation of the scarcity index; The coordination priority of the collaborative task is obtained by weighting and fusing the criticality index of the task node with the competition intensity coefficient of the building resource. Based on the coordination priority, the coordination tasks are prioritized to obtain a preliminary coordination scheme for the coordination tasks.

8. The intelligent construction integrated collaborative platform as described in claim 1, characterized in that, When the scheduling optimization module executes the process of scheduling target optimization data in the conflict-free task list according to time priority to obtain an optimized scheduling plan for the conflict-free task list, it is specifically used for: Temporal dependency mining is performed on the list of conflict-free tasks to obtain the set of temporal constraint rules for the list of conflict-free tasks. Based on the time-series constraint rule set, a resource supply reliability analysis is performed on the building resources to obtain a preliminary resource allocation strategy for the building resources. A target trade-off analysis is performed on the conflict-free task list to obtain the target optimization requirements for the conflict-free task list. The preliminary resource allocation strategy and the target optimization requirements are coordinated and decided to obtain the optimized scheduling blueprint of the building resources. The optimized scheduling blueprint is instantiated with a scheduling strategy to obtain the optimized scheduling plan for the list of conflict-free tasks.

9. The intelligent construction integrated collaborative platform as described in claim 1, characterized in that, When the task execution module updates the collaborative task list according to the optimized scheduling plan and applies the updated list to the target building, it is specifically used for: Discretize the optimized scheduling plan to obtain the task instruction sequence for the target building; The task instruction sequence is configured with parameters to obtain the executable instruction set of the target building; Based on the executable instruction set, the collaborative task list is subjected to version iteration management to obtain the updated collaborative task list of the target building; The updated list of collaborative tasks is distributed to the target building execution terminal.

10. A smart construction integrated collaborative method, characterized in that, The method for using the intelligent construction integrated collaborative platform according to claim 1: S1. Collect raw data from the target building, and normalize the raw data to obtain standardized data of the target building; S2. Extract multi-level features from the standardized data to construct a data feature set of the standardized data; S3. Couple the static attribute features and dynamic behavior features in the data feature set in multiple dimensions to obtain the fused data of the data feature set; S4. Perform joint analysis on the dependencies and resource conflicts in the collaborative task list deconstructed from the fused data to obtain a conflict-free task list for the target building. S5. Based on the time priority, schedule the target optimization data in the conflict-free task list to obtain the optimized scheduling plan of the conflict-free task list. S6. Update the collaborative task list according to the optimized scheduling plan, and apply the updated list to the target building.

Images