Intelligent construction whole-process collaborative management system and method based on BIM (Building Information Modeling)

Abstract

The invention discloses an intelligent building whole-process collaborative management system and method based on BIM, and relates to the field of building construction management, and the method comprises the steps: collecting the behavior data of project participants, constructing a man-machine cognitive behavior model, and obtaining a task execution track; according to a task node, a progress plan and a resource allocation condition in the current building engineering BIM model, constructing a preliminary collaborative task graph, and obtaining a task collaborative path by utilizing a cognitive inference engine; and based on the task cooperation path, obtaining a component state, an execution track and environment disturbance information, forming a digital twinborn dynamic model, and obtaining construction data. According to the method, the man-machine cognitive behavior model is constructed, the task execution trajectory is obtained, modeling and task activity clustering of the behavior data of the constructors are achieved, the cognitive intention and the task response process of each participant can be clearly described in the multi-role collaborative construction process, and the understanding of actual construction behaviors is enhanced.

Description

Technical Field

[0001] The present invention relates to the field of building construction management, and in particular to a BIM-based intelligent construction full-process collaborative management system and method. Background Art

[0002] In the field of construction management, building information modeling technology has been widely used in various task management throughout the construction life cycle due to its advantages in visualization, information integration and multi-disciplinary collaboration. Existing methods usually preset schedules, component processes and resource arrangements in the BIM model, and combine them with rule-based or task node-driven process engines to achieve the scheduling of construction tasks, resource allocation and integrated update of on-site feedback information. It has significant advantages in structured information management and construction logic expression, and also provides a basic framework for the automatic dispatching and status perception of construction tasks. In order to improve the application depth of BIM models, some methods introduce rule engines based on construction logs, sensor information or task annotations for task adjustment and construction feedback processing, so that the feedback loop of BIM at the construction site gradually has closed-loop characteristics.

[0003] However, existing methods still have two limitations in actual complex construction environments. When it comes to multi-role and multi-task collaborative scheduling, they often lack the ability to deeply model the behavioral patterns of construction personnel, making it difficult to characterize the behavioral cognitive laws of people in the process of task selection and path deviation. The dynamic disturbance response mechanism in the construction process relies on rule reconstruction or manual intervention, and lacks the ability to continuously evolve based on construction behavior deviations, resulting in the scheduling adjustment process not being adaptive. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a BIM-based intelligent construction full-process collaborative management method to solve the problem of lack of behavioral cognitive modeling and construction disturbance adaptive scheduling.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a BIM-based intelligent construction full-process collaborative management method, which includes collecting behavioral data of project participants, building a human-computer cognitive behavior model, and obtaining task execution trajectories;

[0008] Based on the task nodes, schedule and resource allocation in the current construction project BIM model, a preliminary collaborative task map is constructed, and the task collaborative path is obtained using the cognitive reasoning engine;

[0009] Based on the task collaborative path, the component status, execution trajectory and environmental disturbance information are obtained to form a digital twin dynamic model and obtain construction data;

[0010] Comparing construction data with task execution trajectories, we can obtain behavioral deviations during the construction process. Based on cognitive deviations from rule-learning fusion, we can obtain deviations from the task path.

[0011] Based on the deviation from the task path, construction tasks are reallocated through rolling optimization.

[0012] As a preferred solution of the BIM-based intelligent construction full-process collaborative management method of the present invention, wherein: collecting the behavioral data of project participants, building a human-computer cognitive behavior model, and obtaining the task execution trajectory, the following steps are included:

[0013] By collecting behavioral data of project participants through collaborative software platforms, mobile terminals and operation logs during the construction process;

[0014] The behavioral data is semantically annotated and features extracted, and a cognitive model based on a hierarchical Bayesian network is used to construct a human-computer cognitive behavior model.

[0015] The behavioral data is input into the human-computer cognitive behavior model for cluster analysis to obtain the task execution trajectory.

[0016] As a preferred solution of the BIM-based intelligent construction full-process collaborative management method described in the present invention, a preliminary collaborative task map is constructed based on the task nodes, schedule plan and resource allocation in the current construction project BIM model, and a task collaborative path is obtained using a cognitive reasoning engine, including the following steps:

[0017] Analyze the current BIM model and extract the dependencies and timing requirements between task nodes;

[0018] Combine the dependencies between task nodes with timing requirements and construction resource allocation to obtain a preliminary collaborative task map;

[0019] Use the cognitive reasoning engine to simulate and deduce the preliminary collaborative task map to generate task collaborative paths

[0020] As a preferred solution of the BIM-based intelligent construction full-process collaborative management method described in the present invention, the following steps are included: based on the task collaborative path, component status, execution trajectory and environmental disturbance information are obtained to form a digital twin dynamic model and obtain construction data.

[0021] Obtain BIM component status information, task execution trajectory and environmental disturbance information through multi-source sensing terminals;

[0022] By summarizing BIM component status information, task execution trajectory and environmental disturbance information, a multi-source data package is obtained;

[0023] Acquire timing information from BIM component status information, fuse multi-source data packages with the acquired timing information, and construct a digital twin dynamic model;

[0024] The multi-source data packages are input into the digital twin dynamic model for updating to obtain construction data.

[0025] As a preferred solution of the BIM-based intelligent construction full-process collaborative management method of the present invention, the construction data is compared with the task execution trajectory to obtain the behavioral deviation in the construction process, including the following steps:

[0026] Map and compare the construction data with the task execution trajectory to obtain the task matching matrix;

[0027] Based on the task matching matrix, identify abnormal data segments that are inconsistent with the standard task trajectory in time and space;

[0028] Extract the deviation feature vector set from the abnormal data segment to obtain the cognitive deviation label;

[0029] Based on the cognitive bias labels, behavioral biases in the construction process are obtained.

[0030] As a preferred solution of the BIM-based intelligent construction full-process collaborative management method of the present invention, wherein: based on the cognitive bias of rule-learning fusion, the deviation task path is obtained, including the following steps:

[0031] Based on behavioral deviations, a deviant behavior sample set with three-dimensional characteristics of time, space and task logic is constructed;

[0032] Perform rule matching and labeling on the deviant behavior sample set, extract behavioral deviation features and generate cognitive bias probability scores;

[0033] Input the deviant behavior sample set into the rule engine to obtain the rule judgment result;

[0034] The cognitive bias probability score is integrated with the rule judgment results to filter out deviations from the task path.

[0035] As a preferred solution of the BIM-based intelligent construction full-process collaborative management method of the present invention, the following steps are included: based on the deviation of the task path, the construction tasks are reallocated by rolling optimization:

[0036] Compare the deviated task path with the original construction schedule to extract task rescheduling constraints;

[0037] The task rescheduling constraints are analyzed through rolling optimization, and the construction tasks are reallocated.

[0038] In a second aspect, the present invention provides a BIM-based intelligent construction full-process collaborative management system, including a task execution trajectory module that collects behavioral data of project participants, builds a human-computer cognitive behavior model, and obtains task execution trajectories;

[0039] The task collaboration path module builds a preliminary collaborative task map based on the task nodes, schedule plan, and resource allocation in the current construction project BIM model, and uses the cognitive reasoning engine to obtain the task collaboration path;

[0040] The construction data module obtains component status, execution trajectory, and environmental disturbance information based on the task collaboration path, forms a digital twin dynamic model, and obtains construction data;

[0041] The deviation task path module compares the construction data with the task execution trajectory to obtain the behavioral deviation in the construction process. Based on the cognitive deviation of rule-learning fusion, the deviation task path is obtained.

[0042] The construction task allocation module reallocates construction tasks through rolling optimization based on deviations from the task path.

[0043] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the BIM-based intelligent construction full-process collaborative management method as described in the first aspect of the present invention.

[0044] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the BIM-based intelligent construction full-process collaborative management method as described in the first aspect of the present invention.

[0045] The beneficial effects of the present invention are as follows: by constructing a human-machine cognitive behavior model, the task execution trajectory is obtained, the modeling of construction personnel behavior data and the clustering of task activities are realized, and the cognitive intentions and task response processes of each participant can be clearly portrayed in the multi-role collaborative construction process, thereby enhancing the understanding of actual construction behavior. Furthermore, through cognitive bias based on rule-learning fusion, the deviation from the task path is obtained, and the behavior deviation data is constructed as a multi-dimensional feature sample. The scoring mechanism of the rule judgment result and the learning model are integrated to effectively identify the task execution path that does not conform to the cognitive law, thereby triggering the intelligent adjustment mechanism, which not only improves the recognizability of construction behavior and the accuracy of management response, but also makes the construction task allocation have stronger adaptability and dynamic optimization capabilities, and ultimately achieves the intelligent management goal of multi-role, multi-path, and highly dynamic collaboration in the entire construction process. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0047] Figure 1 This is a flowchart of the full-process collaborative management method of BIM-based intelligent construction.

[0048] Figure 2 This is a schematic diagram of the BIM intelligent construction full-process collaborative management system.

[0049] Figure 3 Flowchart of the task execution trajectory.

[0050] Figure 4 A flowchart of task nodes and progress. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0054] Reference Figures 1 to 4 , is an embodiment of the present invention, which provides a BIM-based intelligent construction full-process collaborative management method, including the following steps:

[0055] S1. Collect behavioral data of project participants, build a human-computer cognitive behavior model, and obtain the task execution trajectory.

[0056] S1.1. Collect behavioral data of project participants through collaborative software platforms, mobile terminals, and operation logs during the construction process.

[0057] Furthermore, during the construction process, the behavioral data of project participants are continuously collected through the collaborative software platform deployed at the construction site and remote management platform, the mobile terminals used by construction personnel, and the operation record logs generated by the background system. The collaborative software platform can record personnel's task receipt, feedback, interaction and operation behaviors. The location information, operation trajectory and task response time collected by the mobile terminal reflect the on-site behavior status of the personnel, and the operation record log provides system-level behavioral data such as task operation sequence, timestamp, resource call, etc.

[0058] S1.2. Semantically annotate and extract features from behavioral data, and use a cognitive modeling method based on a hierarchical Bayesian network to construct a human-computer cognitive behavior model.

[0059] Furthermore, after obtaining multi-source behavioral data from project participants, the data is first semantically annotated, and the original behavioral information is structured according to the dimensions of task type, operation intention, and time node to ensure that it has recognizable semantic meaning; then key features are extracted, including operation frequency, behavior duration, task switching sequence, spatial movement trajectory, etc., to form a multi-dimensional behavioral feature vector; on this basis, a hierarchical Bayesian network is introduced as a modeling framework, and the perception, judgment, and decision-making cognitive state of personnel are used as latent variables, and the observed behavioral characteristics are used as visible variables. Through training, the conditional probability relationship between variables is established, and a human-computer cognitive behavior model that expresses cognitive hierarchy, reasoning path, and behavior driving mechanism is constructed.

[0060] S1.3. Input the behavioral data into the human-computer cognitive behavior model for cluster analysis to obtain the task execution trajectory.

[0061] Furthermore, the labeled and feature-extracted behavioral data is used as input, and cluster analysis is performed based on the cognitive state transition probability defined in the model to explore the pattern similarity and sequence correlation between behaviors. During the clustering process, the behavioral fragments are classified based on the time sequence and spatial location features, and related behavioral sequence clusters are identified. By sequentially reconstructing and semantically associating the behavioral clusters in the clustering results, the task execution trajectory reflecting the actual work process of the personnel is extracted.

[0062] S2. Based on the task nodes, schedule plan and resource allocation in the current construction project BIM model, a preliminary collaborative task map is constructed, and the task collaborative path is obtained using the cognitive reasoning engine.

[0063] S2.1. Analyze the current BIM model and extract the dependencies and timing requirements between task nodes.

[0064] Furthermore, by analyzing the component attributes, construction schedule and resource allocation information in the current construction project BIM model, the component units, operation procedures and their associated parameters corresponding to each construction task are identified, and on this basis, the sequence, parallel relationship and resource dependency relationship between tasks are extracted; combined with construction logic and node constraints, the topological structure and logical connection between task nodes are summarized, and then the dependency path between tasks and their corresponding timing requirements are clarified.

[0065] S2.2. Combine the dependencies between task nodes with the timing requirements and the construction resource allocation to obtain a preliminary collaborative task map.

[0066] Furthermore, on the basis of clarifying the dependencies and timing requirements between task nodes, the resource allocation situation of the construction site is further retrieved, including the availability, operation capacity and distribution status of manpower, equipment and materials; the execution requirements of the task are matched with the configuration capabilities of the resources, and resource conflicts, concurrent operation constraints and scheduling priorities are comprehensively considered. By constructing a mapping relationship between tasks and resources, a preliminary collaborative task map containing task execution logic, resource allocation information and time constraints is generated.

[0067] S2.3. Use the cognitive reasoning engine to simulate and deduce the preliminary collaborative task map to generate a task collaborative path.

[0068] Furthermore, based on the preliminary collaborative task map, the task execution process is simulated and deduced based on the cognitive reasoning engine, comprehensively considering the logical relationship between tasks, resource allocation and time constraints. By introducing cognitive rules and reasoning strategies, the task execution sequence and conflict resolution methods in various collaborative scenarios are simulated, and the task scheduling sequence and resource call strategy are dynamically adjusted to generate a task collaborative path that meets logical consistency and resource feasibility.

[0069] S3. Based on the task collaborative path, obtain the component status, execution trajectory and environmental disturbance information, form a digital twin dynamic model, and obtain construction data.

[0070] S3.1. Obtain BIM component status information, task execution trajectory, and environmental disturbance information through multi-source sensing terminals.

[0071] Furthermore, by deploying multi-source sensing terminals at the construction site, the status information of BIM components can be collected in real time, including the positioning, installation progress and deformation of the components. At the same time, wearable devices, positioning modules and on-site camera equipment can be combined to record the task execution trajectory of construction personnel. Environmental sensors can be further used to collect environmental disturbance factors such as noise, temperature and humidity, and light intensity, thereby constructing multi-dimensional perception data covering component status, personnel behavior and environmental impact.

[0072] S3.2. By summarizing BIM component status information, task execution trajectory and environmental disturbance information, a multi-source data package is obtained.

[0073] Furthermore, the collected BIM component status information, task execution trajectory and environmental disturbance information are organized in a unified data format, data from different sources are synchronously proofread and matched through timestamps, and data are grouped and classified according to task nodes or spatial areas to form a multi-source data package with temporal consistency and spatial correspondence.

[0074] S3.3. Obtain timing information from BIM component status information, fuse multi-source data packets with the acquired timing information, and construct a digital twin dynamic model.

[0075] Furthermore, the timestamps and lifecycle nodes of each component at different construction stages are extracted from the BIM component status information to form component-level timing information. This timing information is matched and fused with the previously constructed multi-source data package to ensure that each type of perception data is accurately aligned with the component activity in the time dimension. According to the three-dimensional structure of component-task-time, data binding, timing playback and status update are completed in sequence; finally, a dynamic mapping relationship is constructed based on the fused data drive to form a digital twin dynamic model that can evolve over time to reflect the component status, behavior trajectory and environmental impact.

[0076] S3.4. Input the multi-source data package into the digital twin dynamic model for updating to obtain construction data.

[0077] Furthermore, the fused multi-source data package is input into the digital twin dynamic model, and the continuous simulation of the construction site status is achieved by dynamically updating the component status, task trajectory, and environmental disturbance. The specific expression is:

[0078] Dt+1 =f(D t ,S t ,T t ,E t );

[0079] Among them, D t is the state of the digital twin model at time t, f is the state transfer function, S t is the component state at time t, T t is the task trajectory at time t.

[0080] S4. Compare the construction data with the task execution trajectory to obtain the behavioral deviation during the construction process.

[0081] S4.1. Map and compare the construction data with the task execution trajectory to obtain the task matching matrix.

[0082] Furthermore, each state information in the construction data is mapped one by one to the corresponding node in the task execution trajectory, and matched and compared through multi-dimensional features such as timestamp, spatial position and task attributes to form a task matching matrix. The task matching matrix reflects the correspondence and matching degree between each construction task node and the actual construction data.

[0083] S4.2. Based on the task matching matrix, identify abnormal data segments that are inconsistent with the standard task trajectory in time and space.

[0084] Furthermore, based on the task matching matrix, the consistency of each task node in time, space and predetermined trajectory is gradually analyzed, and the matching degree is judged using the set threshold rules. Data segments that do not conform to the standard task trajectory in terms of timing deviation, position deviation or task execution sequence are automatically screened out, thereby clarifying possible abnormal behaviors or deviation areas in the construction process.

[0085] S4.3. Extract the deviation feature vector set from the abnormal data segment to obtain the cognitive deviation label.

[0086] Furthermore, within the identified abnormal data segments, multi-dimensional features including time deviation, spatial offset and task logic anomalies are extracted and quantitatively expressed in the form of feature vectors. Combined with the preset cognitive bias classification standards, the feature vectors are analyzed and labeled to generate cognitive bias labels that reflect the type and degree of cognitive bias of construction workers.

[0087] S4.4. Based on the cognitive bias labels, obtain the behavioral biases in the construction process.

[0088] Furthermore, based on cognitive bias labels, predefined behavioral bias mapping rules are used to convert label information into specific behavioral deviation types and ranges. By comprehensively analyzing the deviation characteristics represented by the labels, behavioral deviations such as time delays, spatial offsets, or task logic anomalies in the construction process are clarified, thereby providing targeted deviation identification results for construction management.

[0089] S5. Based on the cognitive bias of rule-learning fusion, we can get the deviation from the task path.

[0090] S5.1. Based on behavioral deviations, a deviation behavior sample set with three-dimensional characteristics of time, space, and task logic is constructed.

[0091] Furthermore, based on the identified behavioral deviations, the specific time point, spatial location and logical relationship of the related tasks are extracted, and a three-dimensional deviation feature vector containing the time dimension, spatial dimension and task logic dimension is constructed. The three-dimensional deviation feature vectors are aggregated to form a deviation behavior sample set, which is used to comprehensively describe the multidimensional characteristics of deviations in the construction process and provide basic data support for subsequent rule matching and deviation analysis.

[0092] S5.2. Perform rule matching and labeling on the deviant behavior sample set to extract behavioral deviation features and generate a cognitive bias probability score.

[0093] Furthermore, the system applies preset behavioral rules to each of the constructed deviant behavior sample sets, identifies samples that meet specific deviation types, and labels each sample with a corresponding cognitive bias label. Subsequently, the system combines the matching results with sample characteristics to calculate the probability score of the deviation occurring, forming a cognitive bias probability score that reflects the likelihood of behavioral abnormality.

[0094] Specifically, the expression is,

[0095]

[0096] Among them, P s is the probability score of cognitive bias of sample s, m is the total number of rules, w j is the weight of the jth behavioral rule, s i is the i-th deviant behavior sample, r j is the jth behavior rule, x is the feature vector index, w x is the x-th feature weight vector, and b is the bias term.

[0097] S5.3. Input the deviant behavior sample set into the rule engine to obtain the rule judgment result.

[0098] Furthermore, the constructed set of deviation behavior samples is input into the rule engine in sequence. Through rule matching and logical judgment, each sample is analyzed to see whether it meets the established rule conditions, and then the corresponding rule judgment results are generated. The rule judgment results reflect the degree of compliance of the samples in terms of time, space and task logic dimensions.

[0099] S5.4. Integrate the cognitive bias probability score with the rule judgment result to filter out deviations from the task path.

[0100] Furthermore, the cognitive bias probability score is weightedly fused with the rule judgment result. By setting a fusion threshold, the deviation degree of each deviant behavior sample is comprehensively evaluated, and samples exceeding the fusion threshold are screened out as abnormal points that deviate from the task path, thereby clarifying the task nodes and behaviors with significant deviations in the construction process.

[0101] S6. Based on the deviation from the task path, the construction tasks are reallocated through rolling optimization.

[0102] S6.1. Compare the deviated task path with the original construction schedule and extract task rescheduling constraints.

[0103] Furthermore, the deviated task path is compared with the original construction schedule node by node, and the impact of the deviated part on subsequent tasks is analyzed. Combined with construction resources, time windows and dependencies, the constraints that need to be met for task rescheduling are extracted.

[0104] S6.2. Analyze task rescheduling constraints through rolling optimization and reallocate construction tasks.

[0105] Furthermore, based on the extracted task rescheduling constraints, a rolling optimization strategy is adopted to dynamically adjust the current construction tasks. Through phased planning and real-time feedback mechanism, the task allocation plan is gradually optimized to ensure rational resource utilization and progress coordination.

[0106] This embodiment also provides a BIM-based intelligent construction full-process collaborative management system, including:

[0107] The task execution trajectory module collects behavioral data of project participants, builds a human-computer cognitive behavior model, and obtains the task execution trajectory;

[0108] The task collaboration path module builds a preliminary collaborative task map based on the task nodes, schedule plan, and resource allocation in the current construction project BIM model, and uses the cognitive reasoning engine to obtain the task collaboration path;

[0109] The construction data module obtains component status, execution trajectory, and environmental disturbance information based on the task collaboration path, forms a digital twin dynamic model, and obtains construction data;

[0110] The deviation task path module compares the construction data with the task execution trajectory to obtain the behavioral deviation in the construction process. Based on the cognitive deviation of rule-learning fusion, the deviation task path is obtained.

[0111] The construction task allocation module reallocates construction tasks through rolling optimization based on deviations from the task path.

[0112] This embodiment also provides a computer device, which is suitable for the BIM-based intelligent construction full-process collaborative management method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the BIM-based intelligent construction full-process collaborative management method proposed in the above embodiment.

[0113] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0114] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the BIM-based intelligent construction full-process collaborative management method proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk.

[0115] In summary, the present invention obtains the task execution trajectory by constructing a human-computer cognitive behavior model, realizes the modeling of construction personnel behavior data and task activity clustering, can clearly portray the cognitive intentions and task response processes of each participant in the multi-role collaborative construction process, enhances the understanding of actual construction behavior, and then obtains the deviation from the task path through cognitive bias based on rule-learning fusion, realizes the construction of behavioral deviation data into multi-dimensional feature samples, and integrates the rule judgment results and the scoring mechanism of the learning model, effectively identifies the task execution path that does not conform to the cognitive law, and then triggers the intelligent adjustment mechanism, which not only improves the identifiability of construction behavior and the accuracy of management response, but also makes the construction task allocation have stronger adaptability and dynamic optimization capabilities, and finally realizes the intelligent management goal of multi-role, multi-path, and highly dynamic collaboration in the entire construction process.

[0116] 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 the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A BIM-based intelligent construction full-process collaborative management method, characterized by: include, Collect behavioral data of project participants, build a human-computer cognitive behavior model, and obtain task execution trajectories; Based on the task nodes, schedule and resource allocation in the current construction project BIM model, a preliminary collaborative task map is constructed, and the task collaborative path is obtained using the cognitive reasoning engine; Based on the task collaborative path, the component status, execution trajectory and environmental disturbance information are obtained to form a digital twin dynamic model and obtain construction data; Comparing construction data with task execution trajectories, we can obtain behavioral deviations during the construction process. Based on cognitive deviations from rule-learning fusion, we can obtain deviations from the task path. Based on the deviation from the task path, construction tasks are reallocated through rolling optimization.

2. The BIM-based intelligent construction full-process collaborative management method according to claim 1, characterized in that: Collecting the behavioral data of project participants, building a human-computer cognitive behavior model, and obtaining the task execution trajectory includes the following steps: By collecting behavioral data of project participants through collaborative software platforms, mobile terminals and operation logs during the construction process; The behavioral data is semantically annotated and features extracted, and a cognitive model based on a hierarchical Bayesian network is used to construct a human-computer cognitive behavior model. The behavioral data is input into the human-computer cognitive behavior model for cluster analysis to obtain the task execution trajectory.

3. The BIM-based intelligent construction full-process collaborative management method according to claim 2, characterized in that: According to the task nodes, schedule and resource allocation in the current construction project BIM model, a preliminary collaborative task map is constructed, and the task collaborative path is obtained using the cognitive reasoning engine. The following steps are included: Analyze the current BIM model and extract the dependencies and timing requirements between task nodes; Combine the dependencies between task nodes with timing requirements and construction resource allocation to obtain a preliminary collaborative task map; The preliminary collaborative task map is simulated and deduced through the cognitive reasoning engine to generate a task collaborative path.

4. The BIM-based intelligent construction full-process collaborative management method according to claim 3, characterized in that: Based on the task collaborative path, the component status, execution trajectory and environmental disturbance information are obtained to form a digital twin dynamic model and obtain construction data, including the following steps: Obtain BIM component status information, task execution trajectory and environmental disturbance information through multi-source sensing terminals; By summarizing BIM component status information, task execution trajectory and environmental disturbance information, a multi-source data package is obtained; Acquire timing information from BIM component status information, fuse multi-source data packages with the acquired timing information, and construct a digital twin dynamic model; The multi-source data packages are input into the digital twin dynamic model for updating to obtain construction data.

5. The BIM-based intelligent construction full-process collaborative management method according to claim 4, characterized in that: Comparing the construction data with the task execution trajectory to obtain the behavioral deviation during the construction process includes the following steps: Map and compare the construction data with the task execution trajectory to obtain the task matching matrix; Based on the task matching matrix, identify abnormal data segments that are inconsistent with the standard task trajectory in time and space; Extract the deviation feature vector set from the abnormal data segment to obtain the cognitive deviation label; Based on the cognitive bias labels, behavioral biases in the construction process are obtained.

6. The BIM-based intelligent construction full-process collaborative management method according to claim 5, characterized in that: Based on the cognitive bias of rule-learning fusion, the deviation task path is obtained, which includes the following steps: Based on behavioral deviations, a deviant behavior sample set with three-dimensional characteristics of time, space and task logic is constructed; Perform rule matching and labeling on the deviant behavior sample set, extract behavioral deviation features and generate cognitive bias probability scores; Input the deviant behavior sample set into the rule engine to obtain the rule judgment result; The cognitive bias probability score is integrated with the rule judgment results to filter out deviations from the task path.

7. The BIM-based intelligent construction full-process collaborative management method according to claim 6, characterized in that: Based on the deviation from the task path, the construction tasks are reallocated through rolling optimization. The following steps are included: Compare the deviated task path with the original construction schedule to extract task rescheduling constraints; The task rescheduling constraints are analyzed through rolling optimization, and the construction tasks are reallocated.

8. A BIM-based intelligent construction full-process collaborative management system, based on the BIM-based intelligent construction full-process collaborative management method according to any one of claims 1 to 7, characterized in that: include, The task execution trajectory module collects behavioral data of project participants, builds a human-computer cognitive behavior model, and obtains the task execution trajectory; The task collaboration path module builds a preliminary collaborative task map based on the task nodes, schedule plan, and resource allocation in the current construction project BIM model, and uses the cognitive reasoning engine to obtain the task collaboration path; The construction data module obtains component status, execution trajectory, and environmental disturbance information based on the task collaboration path, forms a digital twin dynamic model, and obtains construction data; The deviation task path module compares the construction data with the task execution trajectory to obtain the behavioral deviation in the construction process. Based on the cognitive deviation of rule-learning fusion, the deviation task path is obtained. The construction task allocation module reallocates construction tasks through rolling optimization based on deviations from the task path.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the BIM-based intelligent construction full-process collaborative management method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the BIM-based intelligent construction full-process collaborative management method according to any one of claims 1 to 7 are implemented.

Images